Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Brooklyn Nicholson
|
d049d88dd7 |
@@ -9,12 +9,6 @@ node_modules
|
||||
.venv
|
||||
**/.venv
|
||||
|
||||
# Built artifacts that are regenerated inside the image. Excluded so local
|
||||
# rebuilds on the developer's machine don't invalidate the npm-install layer
|
||||
# that now depends on the full ui-tui/packages/hermes-ink/ tree being present.
|
||||
ui-tui/dist/
|
||||
ui-tui/packages/hermes-ink/dist/
|
||||
|
||||
# CI/CD
|
||||
.github
|
||||
|
||||
|
||||
@@ -76,16 +76,6 @@ jobs:
|
||||
run: |
|
||||
mkdir -p _site/docs
|
||||
cp -r website/build/* _site/docs/
|
||||
# llms.txt / llms-full.txt are also published at the site root
|
||||
# (https://hermes-agent.nousresearch.com/llms.txt) because some
|
||||
# agents and IDE plugins probe the classic root-level path rather
|
||||
# than /docs/llms.txt. Same file, two URLs, one source of truth.
|
||||
if [ -f website/build/llms.txt ]; then
|
||||
cp website/build/llms.txt _site/llms.txt
|
||||
fi
|
||||
if [ -f website/build/llms-full.txt ]; then
|
||||
cp website/build/llms-full.txt _site/llms-full.txt
|
||||
fi
|
||||
|
||||
- name: Upload artifact
|
||||
uses: actions/upload-pages-artifact@56afc609e74202658d3ffba0e8f6dda462b719fa # v3
|
||||
|
||||
+9
-18
@@ -28,26 +28,10 @@ WORKDIR /opt/hermes
|
||||
# ---------- Layer-cached dependency install ----------
|
||||
# Copy only package manifests first so npm install + Playwright are cached
|
||||
# unless the lockfiles themselves change.
|
||||
#
|
||||
# ui-tui/packages/hermes-ink/ is copied IN FULL (not just its manifests)
|
||||
# because it is referenced as a `file:` workspace dependency from
|
||||
# ui-tui/package.json. Copying the tree up front lets npm resolve the
|
||||
# workspace to real content instead of stopping at a bare package.json.
|
||||
COPY package.json package-lock.json ./
|
||||
COPY web/package.json web/package-lock.json web/
|
||||
COPY ui-tui/package.json ui-tui/package-lock.json ui-tui/
|
||||
COPY ui-tui/packages/hermes-ink/ ui-tui/packages/hermes-ink/
|
||||
|
||||
# `npm_config_install_links=false` forces npm to install `file:` deps as
|
||||
# symlinks (the npm 10+ default) even on Debian's older bundled npm 9.x,
|
||||
# which defaults to `install-links=true` and installs file deps as *copies*.
|
||||
# The host-side package-lock.json is generated with a newer npm that uses
|
||||
# symlinks, so an install-as-copy produces a hidden node_modules/.package-lock.json
|
||||
# that permanently disagrees with the root lock on the @hermes/ink entry.
|
||||
# That disagreement trips the TUI launcher's `_tui_need_npm_install()`
|
||||
# check on every startup and triggers a runtime `npm install` that then
|
||||
# fails with EACCES (node_modules/ is root-owned from build time).
|
||||
ENV npm_config_install_links=false
|
||||
COPY ui-tui/packages/hermes-ink/package.json ui-tui/packages/hermes-ink/package-lock.json ui-tui/packages/hermes-ink/
|
||||
|
||||
RUN npm install --prefer-offline --no-audit && \
|
||||
npx playwright install --with-deps chromium --only-shell && \
|
||||
@@ -61,7 +45,14 @@ COPY --chown=hermes:hermes . .
|
||||
|
||||
# Build browser dashboard and terminal UI assets.
|
||||
RUN cd web && npm run build && \
|
||||
cd ../ui-tui && npm run build
|
||||
cd ../ui-tui && npm run build && \
|
||||
rm -rf node_modules/@hermes/ink && \
|
||||
rm -rf packages/hermes-ink/node_modules && \
|
||||
cp -R packages/hermes-ink node_modules/@hermes/ink && \
|
||||
npm install --omit=dev --prefer-offline --no-audit --prefix node_modules/@hermes/ink && \
|
||||
rm -rf node_modules/@hermes/ink/node_modules/react && \
|
||||
node --input-type=module -e "await import('@hermes/ink')" && \
|
||||
touch .hermes-prebuilt-tui
|
||||
|
||||
# ---------- Permissions ----------
|
||||
# Make install dir world-readable so any HERMES_UID can read it at runtime.
|
||||
|
||||
@@ -1,505 +0,0 @@
|
||||
# Hermes Agent v0.12.0 (v2026.4.30)
|
||||
|
||||
**Release Date:** April 30, 2026
|
||||
**Since v0.11.0:** 1,096 commits · 550 merged PRs · 1,270 files changed · 217,776 insertions · 213 community contributors (including co-authors)
|
||||
|
||||
> The Curator release — Hermes Agent now maintains itself. An autonomous background Curator grades, prunes, and consolidates your skill library on its own schedule. The self-improvement loop that reviews what to save got a substantial upgrade. Four new inference providers, a 18th messaging platform, a 19th via Teams plugin, native Spotify + Google Meet integrations, ComfyUI and TouchDesigner-MCP moved from optional to bundled-by-default, and a ~57% cut to visible TUI cold start.
|
||||
|
||||
---
|
||||
|
||||
## ✨ Highlights
|
||||
|
||||
- **Autonomous Curator** — `hermes curator` runs as a background agent on the gateway's cron ticker (7-day cycle default). It grades your skill library, consolidates related skills, prunes dead ones, and writes per-run reports to `logs/curator/run.json` + `REPORT.md`. Archived skills are classified consolidated-vs-pruned via model + heuristic. Defense-in-depth gates protect bundled/hub skills from mutation. Unified under `auxiliary.curator` — pick the curator's model in `hermes model`, manage it from the dashboard. `hermes curator status` ranks skills by usage (most-used / least-used). ([#17277](https://github.com/NousResearch/hermes-agent/pull/17277), [#17307](https://github.com/NousResearch/hermes-agent/pull/17307), [#17941](https://github.com/NousResearch/hermes-agent/pull/17941), [#17868](https://github.com/NousResearch/hermes-agent/pull/17868), [#18033](https://github.com/NousResearch/hermes-agent/pull/18033))
|
||||
|
||||
- **Self-improvement loop — substantially upgraded** — The background review fork (the core of Hermes' self-improvement: after each turn it decides what memories/skills to save or update) is now class-first (rubric-based rather than free-form), active-update biased (prefers the skill the agent just loaded), handles `references/`/`templates/` sub-files, and properly inherits the parent's live runtime (provider, model, credentials actually propagate). Restricted to memory + skills toolsets so it can't sprawl. Memory providers shut down cleanly. Prior-turn tool messages excluded from the summary so the fork sees a clean context. ([#16026](https://github.com/NousResearch/hermes-agent/pull/16026), [#17213](https://github.com/NousResearch/hermes-agent/pull/17213), [#16099](https://github.com/NousResearch/hermes-agent/pull/16099), [#16569](https://github.com/NousResearch/hermes-agent/pull/16569), [#16204](https://github.com/NousResearch/hermes-agent/pull/16204), [#15057](https://github.com/NousResearch/hermes-agent/pull/15057))
|
||||
|
||||
- **Skill integrations — major expansion** — **ComfyUI v5** with official CLI + REST + hardware-gated local install, moved from optional to **built-in by default** ([#17610](https://github.com/NousResearch/hermes-agent/pull/17610), [#17631](https://github.com/NousResearch/hermes-agent/pull/17631), [#17734](https://github.com/NousResearch/hermes-agent/pull/17734)). **TouchDesigner-MCP** bundled by default, expanded with GLSL, post-FX, audio, geometry, and 9 new reference docs ([#16753](https://github.com/NousResearch/hermes-agent/pull/16753), [#16624](https://github.com/NousResearch/hermes-agent/pull/16624), [#16768](https://github.com/NousResearch/hermes-agent/pull/16768) — @kshitijk4poor + @SHL0MS). **Humanizer** skill ports a text-cleaner that strips AI-isms ([#16787](https://github.com/NousResearch/hermes-agent/pull/16787)). **claude-design** HTML artifact skill + design-md (Google DESIGN.md spec) + airtable salvage + `skill_manage` edits in `external_dirs` + direct-URL skill install + `/reload-skills` slash command. ([#16358](https://github.com/NousResearch/hermes-agent/pull/16358), [#14876](https://github.com/NousResearch/hermes-agent/pull/14876), [#16291](https://github.com/NousResearch/hermes-agent/pull/16291), [#17512](https://github.com/NousResearch/hermes-agent/pull/17512), [#16323](https://github.com/NousResearch/hermes-agent/pull/16323), [#17744](https://github.com/NousResearch/hermes-agent/pull/17744))
|
||||
|
||||
- **LM Studio — first-class provider** — upgraded from a custom-endpoint alias to a full-blown native provider: dedicated auth, `hermes doctor` checks, reasoning transport, live `/models` listing. (Salvage of @kshitijk4poor's #17061.) ([#17102](https://github.com/NousResearch/hermes-agent/pull/17102))
|
||||
|
||||
- **Four more new inference providers** — **GMI Cloud** (first-class, salvage of #11955 — @isaachuangGMICLOUD), **Azure AI Foundry** with auto-detection, **MiniMax OAuth** with PKCE browser flow (salvage #15203), **Tencent Tokenhub** (salvage of #16860). ([#16663](https://github.com/NousResearch/hermes-agent/pull/16663), [#15845](https://github.com/NousResearch/hermes-agent/pull/15845), [#17524](https://github.com/NousResearch/hermes-agent/pull/17524), [#16960](https://github.com/NousResearch/hermes-agent/pull/16960))
|
||||
|
||||
- **Pluggable gateway platforms + Microsoft Teams** — the gateway is now a plugin host. Drop-in messaging adapters live outside the core, and Microsoft Teams is the first plugin-shipped platform. (Salvage of #17664.) ([#17751](https://github.com/NousResearch/hermes-agent/pull/17751), [#17828](https://github.com/NousResearch/hermes-agent/pull/17828))
|
||||
|
||||
- **Tencent 元宝 (Yuanbao) — 18th messaging platform** — native gateway adapter with text + media delivery. ([#16298](https://github.com/NousResearch/hermes-agent/pull/16298), [#17424](https://github.com/NousResearch/hermes-agent/pull/17424))
|
||||
|
||||
- **Spotify — native tools + bundled skill + wizard** — 7 tools (play, search, queue, playlists, devices) behind PKCE OAuth, interactive setup wizard, bundled skill, surfacing in `hermes tools`, cron usage documented. ([#15121](https://github.com/NousResearch/hermes-agent/pull/15121), [#15130](https://github.com/NousResearch/hermes-agent/pull/15130), [#15154](https://github.com/NousResearch/hermes-agent/pull/15154), [#15180](https://github.com/NousResearch/hermes-agent/pull/15180))
|
||||
|
||||
- **Google Meet plugin** — join calls, transcribe, speak, follow up. Realtime OpenAI transport + Node bot server, full pipeline bundled as a plugin. ([#16364](https://github.com/NousResearch/hermes-agent/pull/16364))
|
||||
|
||||
- **`hermes -z` one-shot mode + `hermes update --check`** — non-interactive `hermes -z <prompt>` with `--model`/`--provider`/`HERMES_INFERENCE_MODEL`. `hermes update --check` preflight. Opt-in pre-update HERMES_HOME backup. ([#15702](https://github.com/NousResearch/hermes-agent/pull/15702), [#15704](https://github.com/NousResearch/hermes-agent/pull/15704), [#15841](https://github.com/NousResearch/hermes-agent/pull/15841), [#16539](https://github.com/NousResearch/hermes-agent/pull/16539), [#16566](https://github.com/NousResearch/hermes-agent/pull/16566))
|
||||
|
||||
- **Models dashboard tab + in-browser model config** — rich per-model analytics, switch main + auxiliary models from the dashboard. ([#17745](https://github.com/NousResearch/hermes-agent/pull/17745), [#17802](https://github.com/NousResearch/hermes-agent/pull/17802))
|
||||
|
||||
- **Remote model catalog manifest** — OpenRouter + Nous Portal model catalogs are now pulled from a remote manifest so new models show up without a release. ([#16033](https://github.com/NousResearch/hermes-agent/pull/16033))
|
||||
|
||||
- **Native multimodal image routing** — images now route based on the model's actual vision capability rather than provider defaults. ([#16506](https://github.com/NousResearch/hermes-agent/pull/16506))
|
||||
|
||||
- **Gateway media parity** — native multi-image sending across Telegram, Discord, Slack, Mattermost, Email, and Signal; centralized audio routing with FLAC support + Telegram document fallback. ([#17909](https://github.com/NousResearch/hermes-agent/pull/17909), [#17833](https://github.com/NousResearch/hermes-agent/pull/17833))
|
||||
|
||||
- **TUI catches up to (and past) the classic CLI** — LaTeX rendering (@austinpickett), `/reload` .env hot-reload, pluggable busy-indicator styles (@OutThisLife, #13610), opt-in auto-resume of last session, expanded light-terminal auto-detection, session delete from `/resume` picker with `d`, modified mouse-wheel line scroll, and a `/mouse` toggle that kills ConPTY's phantom mouse injection (@kevin-ho). ([#17175](https://github.com/NousResearch/hermes-agent/pull/17175), [#17286](https://github.com/NousResearch/hermes-agent/pull/17286), [#17150](https://github.com/NousResearch/hermes-agent/pull/17150), [#17130](https://github.com/NousResearch/hermes-agent/pull/17130), [#17113](https://github.com/NousResearch/hermes-agent/pull/17113), [#17668](https://github.com/NousResearch/hermes-agent/pull/17668), [#17669](https://github.com/NousResearch/hermes-agent/pull/17669), [#15488](https://github.com/NousResearch/hermes-agent/pull/15488))
|
||||
|
||||
- **Observability + achievements plugins** — bundled Langfuse observability plugin (salvage #16845) + bundled hermes-achievements plugin that scans full session history. ([#16917](https://github.com/NousResearch/hermes-agent/pull/16917), [#17754](https://github.com/NousResearch/hermes-agent/pull/17754))
|
||||
|
||||
- **TTS provider registry + Piper local TTS** — pluggable `tts.providers.<name>` registry; Piper ships as a native local TTS provider. (Closes #8508.) ([#17843](https://github.com/NousResearch/hermes-agent/pull/17843), [#17885](https://github.com/NousResearch/hermes-agent/pull/17885))
|
||||
|
||||
- **Vercel Sandbox backend** — Vercel sandboxes as an execute_code/terminal backend (@kshitijk4poor). ([#17445](https://github.com/NousResearch/hermes-agent/pull/17445))
|
||||
|
||||
- **Secret redaction off by default** — default flipped to off. Prevents the long-standing patch-corruption incidents where fake secret-shaped substrings mangled tool outputs. Opt in via `redaction.enabled: true` when you need it. ([#16794](https://github.com/NousResearch/hermes-agent/pull/16794))
|
||||
|
||||
- **Cold-start performance** — visible TUI cold start cut **~57%** via lazy agent init (@OutThisLife), lazy imports of OpenAI / Anthropic / Firecrawl / account_usage, mtime-cached `load_config()`, memoized `get_tool_definitions()` with TTL-cached `check_fn` results, precompiled dangerous-command patterns. ([#17190](https://github.com/NousResearch/hermes-agent/pull/17190), [#17046](https://github.com/NousResearch/hermes-agent/pull/17046), [#17041](https://github.com/NousResearch/hermes-agent/pull/17041), [#17098](https://github.com/NousResearch/hermes-agent/pull/17098), [#17206](https://github.com/NousResearch/hermes-agent/pull/17206))
|
||||
|
||||
- **Configurable prompt cache TTL** — `prompt_caching.cache_ttl` (5m default, 1h opt-in — cost savings for bursty sessions that keep cache warm). Salvage of #12659. ([#15065](https://github.com/NousResearch/hermes-agent/pull/15065))
|
||||
|
||||
---
|
||||
|
||||
## 🧠 Autonomous Curator & Self-Improvement Loop
|
||||
|
||||
### Curator — autonomous skill maintenance
|
||||
- **`hermes curator` as a background agent** — runs on the gateway's cron ticker, 7-day cycle by default, umbrella-first prompt, inherits parent config, unbounded iterations ([#17277](https://github.com/NousResearch/hermes-agent/pull/17277) — issue #7816)
|
||||
- **Per-run reports** — `logs/curator/run.json` + `REPORT.md` per cycle ([#17307](https://github.com/NousResearch/hermes-agent/pull/17307))
|
||||
- **Consolidated vs pruned classification** — archived skills split with model + heuristic ([#17941](https://github.com/NousResearch/hermes-agent/pull/17941))
|
||||
- **`hermes curator status`** — ranks skills by usage, shows most-used and least-used ([#18033](https://github.com/NousResearch/hermes-agent/pull/18033))
|
||||
- **Unified under `auxiliary.curator`** — pick the model in `hermes model`, configure from the dashboard ([#17868](https://github.com/NousResearch/hermes-agent/pull/17868))
|
||||
- **Documentation** — dedicated curator feature page on the docs site ([#17563](https://github.com/NousResearch/hermes-agent/pull/17563))
|
||||
- Fix: seed defaults on update, create `logs/curator/` directory, defer fire import ([#17927](https://github.com/NousResearch/hermes-agent/pull/17927))
|
||||
- Fix: scan nested archive subdirs in `restore_skill` (@0xDevNinja) ([#17951](https://github.com/NousResearch/hermes-agent/pull/17951))
|
||||
- Fix: use actual skill activity in curator status (@y0shua1ee) ([#17953](https://github.com/NousResearch/hermes-agent/pull/17953))
|
||||
- Fix: `skill_manage` refuses writes on pinned skills; pinning now blocks curator writes ([#17562](https://github.com/NousResearch/hermes-agent/pull/17562), [#17578](https://github.com/NousResearch/hermes-agent/pull/17578))
|
||||
- Fix: `bump_use()` wired into skill invocation + preload + skill_view (salvage #17782) ([#17932](https://github.com/NousResearch/hermes-agent/pull/17932))
|
||||
|
||||
### Self-improvement loop (background review fork)
|
||||
- **Class-first skill-review prompt** — rubric-based grading rather than free-form "should this update" ([#16026](https://github.com/NousResearch/hermes-agent/pull/16026))
|
||||
- **Active-update bias** — prefers updating skills the agent just loaded, handles `references/` + `templates/` sub-files ([#17213](https://github.com/NousResearch/hermes-agent/pull/17213))
|
||||
- **Fork inherits parent's live runtime** — provider, model, credentials actually propagate now ([#16099](https://github.com/NousResearch/hermes-agent/pull/16099))
|
||||
- **Scoped toolsets** — review fork restricted to memory + skills (no shell, no web) ([#16569](https://github.com/NousResearch/hermes-agent/pull/16569))
|
||||
- **Clean shutdown** — background review memory providers exit properly (salvage #15289) ([#16204](https://github.com/NousResearch/hermes-agent/pull/16204))
|
||||
- **Clean context** — prior-history tool messages excluded from review summary (salvage #14967) ([#15057](https://github.com/NousResearch/hermes-agent/pull/15057))
|
||||
|
||||
---
|
||||
|
||||
## 🧩 Skills Ecosystem
|
||||
|
||||
### Skill integrations — newly bundled or promoted
|
||||
- **ComfyUI v5** — official CLI + REST + hardware-gated local install; **moved from optional to built-in** ([#17610](https://github.com/NousResearch/hermes-agent/pull/17610), [#17631](https://github.com/NousResearch/hermes-agent/pull/17631), [#17734](https://github.com/NousResearch/hermes-agent/pull/17734), [#17612](https://github.com/NousResearch/hermes-agent/pull/17612))
|
||||
- **TouchDesigner-MCP** — **bundled by default** ([#16753](https://github.com/NousResearch/hermes-agent/pull/16753) — @kshitijk4poor), expanded with GLSL, post-FX, audio, geometry references ([#16624](https://github.com/NousResearch/hermes-agent/pull/16624)), 9 new reference docs ([#16768](https://github.com/NousResearch/hermes-agent/pull/16768) — @SHL0MS)
|
||||
- **Humanizer** — strips AI-isms from text ([#16787](https://github.com/NousResearch/hermes-agent/pull/16787))
|
||||
- **claude-design** — HTML artifact skill with disambiguation from other design skills ([#16358](https://github.com/NousResearch/hermes-agent/pull/16358))
|
||||
- **design-md** — Google's DESIGN.md spec skill ([#14876](https://github.com/NousResearch/hermes-agent/pull/14876))
|
||||
- **airtable** — salvaged skill + skill API keys wired into `.env` (#15838) ([#16291](https://github.com/NousResearch/hermes-agent/pull/16291))
|
||||
- **pretext** — creative browser demos with @chenglou/pretext ([#17259](https://github.com/NousResearch/hermes-agent/pull/17259))
|
||||
- **spike** + **sketch** — throwaway experiments + HTML mockups, adapted from gsd-build ([#17421](https://github.com/NousResearch/hermes-agent/pull/17421))
|
||||
|
||||
### Skills UX
|
||||
- **Install skills from a direct HTTP(S) URL** — `hermes skills install <url>` ([#16323](https://github.com/NousResearch/hermes-agent/pull/16323))
|
||||
- **`/reload-skills`** slash command (salvage #17670) ([#17744](https://github.com/NousResearch/hermes-agent/pull/17744))
|
||||
- **`hermes skills list`** shows enabled/disabled status ([#16129](https://github.com/NousResearch/hermes-agent/pull/16129))
|
||||
- **`skill_manage` refuses writes on pinned skills** ([#17562](https://github.com/NousResearch/hermes-agent/pull/17562))
|
||||
- **`skill_manage` edits external_dirs skills in place** (salvage #9966) ([#17512](https://github.com/NousResearch/hermes-agent/pull/17512), [#17289](https://github.com/NousResearch/hermes-agent/pull/17289))
|
||||
- Fix: inline-shell rendering in `skill_view` ([#15376](https://github.com/NousResearch/hermes-agent/pull/15376))
|
||||
- Fix: exclude `.archive/` from skill index walk (salvage #17639) ([#17931](https://github.com/NousResearch/hermes-agent/pull/17931))
|
||||
- Fix: dedicated docs page per bundled + optional skill ([#14929](https://github.com/NousResearch/hermes-agent/pull/14929))
|
||||
- Fix: `google-workspace` shared HERMES_HOME helper + ship deps as optional extra ([#15405](https://github.com/NousResearch/hermes-agent/pull/15405))
|
||||
- Fix: auto-wrap ASCII-art code blocks in generated skill pages ([#16497](https://github.com/NousResearch/hermes-agent/pull/16497))
|
||||
- Point agent at `hermes-agent` skill + docs site for Hermes questions ([#16535](https://github.com/NousResearch/hermes-agent/pull/16535))
|
||||
|
||||
---
|
||||
|
||||
## 🏗️ Core Agent & Architecture
|
||||
|
||||
### Provider & Model Support
|
||||
|
||||
#### New providers
|
||||
- **GMI Cloud** — first-class API-key provider on par with Arcee/Kilocode/Xiaomi (salvage of #11955 — @isaachuangGMICLOUD) ([#16663](https://github.com/NousResearch/hermes-agent/pull/16663))
|
||||
- **Azure AI Foundry** — auto-detection, full wiring ([#15845](https://github.com/NousResearch/hermes-agent/pull/15845))
|
||||
- **LM Studio** — upgraded from custom-endpoint alias to first-class provider: dedicated auth, doctor checks, reasoning transport, live `/models` (salvage of #17061 — @kshitijk4poor) ([#17102](https://github.com/NousResearch/hermes-agent/pull/17102))
|
||||
- **MiniMax OAuth** — PKCE browser flow with full OAuth integration (salvage #15203) ([#17524](https://github.com/NousResearch/hermes-agent/pull/17524))
|
||||
- **Tencent Tokenhub** — new provider (salvage of #16860) ([#16960](https://github.com/NousResearch/hermes-agent/pull/16960))
|
||||
|
||||
#### Model catalog
|
||||
- **Remote model catalog manifest** — OpenRouter + Nous Portal catalogs pulled from remote manifest so new models show up without a release ([#16033](https://github.com/NousResearch/hermes-agent/pull/16033))
|
||||
- `openai/gpt-5.5` and `gpt-5.5-pro` added to OpenRouter + Nous Portal ([#15343](https://github.com/NousResearch/hermes-agent/pull/15343))
|
||||
- `deepseek-v4-pro` and `deepseek-v4-flash` added ([#14934](https://github.com/NousResearch/hermes-agent/pull/14934))
|
||||
- `qwen3.6-plus` added to Alibaba-supported models ([#16896](https://github.com/NousResearch/hermes-agent/pull/16896))
|
||||
- Gemini free-tier keys blocked at setup with 429 guidance surfacing ([#15100](https://github.com/NousResearch/hermes-agent/pull/15100))
|
||||
|
||||
#### Model configuration
|
||||
- **Configurable `prompt_caching.cache_ttl`** — 5m default, 1h opt-in (salvage #12659) ([#15065](https://github.com/NousResearch/hermes-agent/pull/15065))
|
||||
- `/fast` whitelist broadened to all OpenAI + Anthropic models ([#16883](https://github.com/NousResearch/hermes-agent/pull/16883))
|
||||
- `auxiliary.extra_body.reasoning` translates into Codex Responses API ([#17004](https://github.com/NousResearch/hermes-agent/pull/17004))
|
||||
- `hermes fallback` command for managing fallback providers ([#16052](https://github.com/NousResearch/hermes-agent/pull/16052))
|
||||
|
||||
### Agent Loop & Conversation
|
||||
- **Native multimodal image routing** — based on model vision capability, not provider defaults ([#16506](https://github.com/NousResearch/hermes-agent/pull/16506))
|
||||
- **Delegate `child_timeout_seconds` default bumped to 600s** ([#14809](https://github.com/NousResearch/hermes-agent/pull/14809))
|
||||
- **Diagnostic dump when subagent times out with 0 API calls** ([#15105](https://github.com/NousResearch/hermes-agent/pull/15105))
|
||||
- **Gateway busts cached agent on compression/context_length config edits** ([#17008](https://github.com/NousResearch/hermes-agent/pull/17008))
|
||||
- **Opt-in runtime-metadata footer on final replies** ([#17026](https://github.com/NousResearch/hermes-agent/pull/17026))
|
||||
- `/reload-mcp` awareness — rebuild cached agents + prompt-cache cost confirmation ([#17729](https://github.com/NousResearch/hermes-agent/pull/17729))
|
||||
- Fix: repair CamelCase + `_tool` suffix tool-call emissions ([#15124](https://github.com/NousResearch/hermes-agent/pull/15124))
|
||||
- Fix: retry on `json.JSONDecodeError` instead of treating as local validation error ([#15107](https://github.com/NousResearch/hermes-agent/pull/15107))
|
||||
- Fix: handle unescaped control chars in `tool_call.arguments` ([#15356](https://github.com/NousResearch/hermes-agent/pull/15356))
|
||||
- Fix: ordering fix in `_copy_reasoning_content_for_api` — cross-provider reasoning isolation (@Zjianru) ([#15749](https://github.com/NousResearch/hermes-agent/pull/15749))
|
||||
- Fix: inject empty `reasoning_content` for DeepSeek/Kimi `tool_calls` unconditionally (@Zjianru) ([#15762](https://github.com/NousResearch/hermes-agent/pull/15762))
|
||||
- Fix: persist streamed `reasoning_content` on assistant turns (#16844) ([#16892](https://github.com/NousResearch/hermes-agent/pull/16892))
|
||||
- Fix: cancel coroutine on timeout so worker thread exits; full traceback on tool failure ([#17428](https://github.com/NousResearch/hermes-agent/pull/17428))
|
||||
- Fix: isolate `get_tool_definitions` quiet_mode cache + dedup LCM injection (#17335) ([#17889](https://github.com/NousResearch/hermes-agent/pull/17889))
|
||||
- Fix: serialize concurrent `hermes_tools` RPC calls from `execute_code` (#17770) ([#17894](https://github.com/NousResearch/hermes-agent/pull/17894), [#17902](https://github.com/NousResearch/hermes-agent/pull/17902))
|
||||
- Fix: rename `[SYSTEM:` → `[IMPORTANT:` in all user-injected markers (dodges Azure content filter) ([#16114](https://github.com/NousResearch/hermes-agent/pull/16114))
|
||||
|
||||
### Compression
|
||||
- **Retry summary on main model for unknown errors before giving up** ([#16774](https://github.com/NousResearch/hermes-agent/pull/16774))
|
||||
- **Notify users when configured aux model fails even if main-model fallback recovers** ([#16775](https://github.com/NousResearch/hermes-agent/pull/16775))
|
||||
- `/compress` wrapped in `_busy_command` to block input during compression ([#15388](https://github.com/NousResearch/hermes-agent/pull/15388))
|
||||
- Fix: reserve system + tools headroom when aux binds threshold ([#15631](https://github.com/NousResearch/hermes-agent/pull/15631))
|
||||
- Fix: use text-char sum for multimodal token estimation in `_find_tail_cut_by_tokens` ([#16369](https://github.com/NousResearch/hermes-agent/pull/16369))
|
||||
|
||||
### Session, Memory & State
|
||||
- **Trigram FTS5 index for CJK search, replace LIKE fallback** (@alt-glitch) ([#16651](https://github.com/NousResearch/hermes-agent/pull/16651))
|
||||
- **Index `tool_name` + `tool_calls` in FTS5, with repair + migration** (salvages #16866) ([#16914](https://github.com/NousResearch/hermes-agent/pull/16914))
|
||||
- **Checkpoints: auto-prune orphan and stale shadow repos at startup** ([#16303](https://github.com/NousResearch/hermes-agent/pull/16303))
|
||||
- **Memory providers notified on mid-process session_id rotation** (#6672) ([#17409](https://github.com/NousResearch/hermes-agent/pull/17409))
|
||||
- Fix: quote underscored terms in FTS5 query sanitization ([#16915](https://github.com/NousResearch/hermes-agent/pull/16915))
|
||||
- Fix: resolve viking_read 500/412 on file URIs + pseudo-summary URIs (salvage #5886) ([#17869](https://github.com/NousResearch/hermes-agent/pull/17869))
|
||||
- Fix: skip external-provider sync on interrupted turns ([#15395](https://github.com/NousResearch/hermes-agent/pull/15395))
|
||||
- Fix: close embedded Hindsight async client cleanly (salvage #14605) ([#16209](https://github.com/NousResearch/hermes-agent/pull/16209))
|
||||
- Fix: pass session transcript to `shutdown_memory_provider` on gateway + CLI (#15165) ([#16571](https://github.com/NousResearch/hermes-agent/pull/16571))
|
||||
- Fix: write-origin metadata seam ([#15346](https://github.com/NousResearch/hermes-agent/pull/15346))
|
||||
- Fix: preserve symlinks during atomic file writes ([#16980](https://github.com/NousResearch/hermes-agent/pull/16980))
|
||||
- Refactor: remove `flush_memories` entirely ([#15696](https://github.com/NousResearch/hermes-agent/pull/15696))
|
||||
|
||||
### Auxiliary models
|
||||
- Fix: surface auxiliary failures in UI (previously silent) ([#15324](https://github.com/NousResearch/hermes-agent/pull/15324))
|
||||
- Fix: surface title-gen auxiliary failures instead of silently dropping ([#16371](https://github.com/NousResearch/hermes-agent/pull/16371))
|
||||
- Fix: generalize unsupported-parameter detector and harden `max_tokens` retry ([#15633](https://github.com/NousResearch/hermes-agent/pull/15633))
|
||||
|
||||
---
|
||||
|
||||
## 📱 Messaging Platforms (Gateway)
|
||||
|
||||
### New Platforms
|
||||
- **Microsoft Teams (19th platform)** — as a plugin, + xdist collision guard ([#17828](https://github.com/NousResearch/hermes-agent/pull/17828))
|
||||
- **Yuanbao (Tencent 元宝, 18th platform)** — native adapter with text + media delivery ([#16298](https://github.com/NousResearch/hermes-agent/pull/16298), [#17424](https://github.com/NousResearch/hermes-agent/pull/17424), [#16880](https://github.com/NousResearch/hermes-agent/pull/16880))
|
||||
|
||||
### Pluggable Gateway Platforms
|
||||
- **Drop-in messaging adapters** — the gateway is now a plugin host for platforms (salvage of #17664) ([#17751](https://github.com/NousResearch/hermes-agent/pull/17751))
|
||||
|
||||
### Telegram
|
||||
- **Chat allowlists for groups and forums** (@web3blind) ([#15027](https://github.com/NousResearch/hermes-agent/pull/15027))
|
||||
- **Send fresh finals for stale preview streams** (port openclaw#72038) ([#16261](https://github.com/NousResearch/hermes-agent/pull/16261))
|
||||
- **Render markdown tables as row-group bullets + prompt hint** ([#16997](https://github.com/NousResearch/hermes-agent/pull/16997))
|
||||
- Document fallback in centralized audio routing ([#17833](https://github.com/NousResearch/hermes-agent/pull/17833))
|
||||
- Native multi-image sending ([#17909](https://github.com/NousResearch/hermes-agent/pull/17909))
|
||||
|
||||
### Discord
|
||||
- **Opt-in toolsets + ID injection + tool split + Feishu wiring** (salvage #15457, #15458) ([#15610](https://github.com/NousResearch/hermes-agent/pull/15610), [#15613](https://github.com/NousResearch/hermes-agent/pull/15613))
|
||||
- Fix: coerce `limit` parameter to int before `min()` call ([#16319](https://github.com/NousResearch/hermes-agent/pull/16319))
|
||||
|
||||
### Slack
|
||||
- **Register every gateway command as a native slash (Discord/Telegram parity)** ([#16164](https://github.com/NousResearch/hermes-agent/pull/16164))
|
||||
- **`strict_mention` config** — prevents thread auto-engagement ([#16193](https://github.com/NousResearch/hermes-agent/pull/16193))
|
||||
- **`channel_skill_bindings`** — bind specific skills to specific Slack channels ([#16283](https://github.com/NousResearch/hermes-agent/pull/16283))
|
||||
|
||||
### Signal
|
||||
- **Native formatting** — markdown → bodyRanges, reply quotes, reactions ([#17417](https://github.com/NousResearch/hermes-agent/pull/17417))
|
||||
- Native multi-image sending ([#17909](https://github.com/NousResearch/hermes-agent/pull/17909))
|
||||
|
||||
### Feishu / Mattermost / Email / Signal
|
||||
- All participate in **native multi-image sending** ([#17909](https://github.com/NousResearch/hermes-agent/pull/17909))
|
||||
|
||||
### Gateway Core
|
||||
- **Centralized audio routing + FLAC support + Telegram doc fallback** ([#17833](https://github.com/NousResearch/hermes-agent/pull/17833))
|
||||
- **Native multi-image sending** across Telegram, Discord, Slack, Mattermost, Email, Signal ([#17909](https://github.com/NousResearch/hermes-agent/pull/17909))
|
||||
- **Make hygiene hard message limit configurable** ([#17000](https://github.com/NousResearch/hermes-agent/pull/17000))
|
||||
- **Opt-in runtime-metadata footer on final replies** ([#17026](https://github.com/NousResearch/hermes-agent/pull/17026))
|
||||
- **`pre_gateway_dispatch` hook** — plugins can intercept before dispatch ([#15050](https://github.com/NousResearch/hermes-agent/pull/15050))
|
||||
- **`pre_approval_request` / `post_approval_response` hooks** ([#16776](https://github.com/NousResearch/hermes-agent/pull/16776))
|
||||
- Fix: timeouts — guard `load_config()` call against runtime exceptions ([#16318](https://github.com/NousResearch/hermes-agent/pull/16318))
|
||||
- Fix: support passing handler tools via registry ([#15613](https://github.com/NousResearch/hermes-agent/pull/15613))
|
||||
|
||||
---
|
||||
|
||||
## 🔧 Tool System
|
||||
|
||||
### Plugin-first architecture
|
||||
- **Pluggable gateway platforms** — platforms can ship as plugins ([#17751](https://github.com/NousResearch/hermes-agent/pull/17751))
|
||||
- **Microsoft Teams as first plugin-shipped platform** ([#17828](https://github.com/NousResearch/hermes-agent/pull/17828))
|
||||
- **`pre_gateway_dispatch` hook** ([#15050](https://github.com/NousResearch/hermes-agent/pull/15050))
|
||||
- **`pre_approval_request` + `post_approval_response` hooks** ([#16776](https://github.com/NousResearch/hermes-agent/pull/16776))
|
||||
- **`duration_ms` on `post_tool_call`** (inspired by Claude Code 2.1.119) ([#15429](https://github.com/NousResearch/hermes-agent/pull/15429))
|
||||
- **Bundled plugins**: Spotify ([#15174](https://github.com/NousResearch/hermes-agent/pull/15174)), Google Meet ([#16364](https://github.com/NousResearch/hermes-agent/pull/16364)), Langfuse observability ([#16917](https://github.com/NousResearch/hermes-agent/pull/16917)), hermes-achievements ([#17754](https://github.com/NousResearch/hermes-agent/pull/17754))
|
||||
- **Page-scoped plugin slots for built-in dashboard pages** ([#15658](https://github.com/NousResearch/hermes-agent/pull/15658))
|
||||
- **Declarative plugin installation for NixOS module** (@alt-glitch) ([#15953](https://github.com/NousResearch/hermes-agent/pull/15953))
|
||||
|
||||
### Browser
|
||||
- **CDP supervisor** — dialog detection + response + cross-origin iframe eval ([#14540](https://github.com/NousResearch/hermes-agent/pull/14540))
|
||||
- **Auto-spawn local Chromium for LAN/localhost URLs** when cloud provider is configured ([#16136](https://github.com/NousResearch/hermes-agent/pull/16136))
|
||||
|
||||
### Execute code / Terminal
|
||||
- **Vercel Sandbox backend** for `execute_code` / terminal (@kshitijk4poor) ([#17445](https://github.com/NousResearch/hermes-agent/pull/17445))
|
||||
- **Collapse subagent `task_id`s to shared container** ([#16177](https://github.com/NousResearch/hermes-agent/pull/16177))
|
||||
- **Docker: run container as host user** to avoid root-owned bind mounts (@benbarclay) ([#17305](https://github.com/NousResearch/hermes-agent/pull/17305))
|
||||
- Fix: safely quote `~/` subpaths in wrapped `cd` commands ([#15394](https://github.com/NousResearch/hermes-agent/pull/15394))
|
||||
- Fix: close file descriptor in `LocalEnvironment._update_cwd` ([#17300](https://github.com/NousResearch/hermes-agent/pull/17300))
|
||||
- Fix: SSH — prevent tar from overwriting remote home dir permissions ([#17898](https://github.com/NousResearch/hermes-agent/pull/17898), [#17867](https://github.com/NousResearch/hermes-agent/pull/17867))
|
||||
|
||||
### Image generation
|
||||
- See Provider section for updates; no new image providers this window.
|
||||
|
||||
### TTS / Voice
|
||||
- **Pluggable TTS provider registry** under `tts.providers.<name>` ([#17843](https://github.com/NousResearch/hermes-agent/pull/17843))
|
||||
- **Piper** as native local TTS provider (closes #8508) ([#17885](https://github.com/NousResearch/hermes-agent/pull/17885))
|
||||
- **Voice mode CLI parity in the TUI** — VAD loop + TTS + crash forensics ([#14810](https://github.com/NousResearch/hermes-agent/pull/14810))
|
||||
- Fix: vision — use HERMES_HOME-based cache dir instead of cwd ([#17719](https://github.com/NousResearch/hermes-agent/pull/17719))
|
||||
|
||||
### Cron
|
||||
- **Honor `hermes tools` config for the cron platform** ([#14798](https://github.com/NousResearch/hermes-agent/pull/14798))
|
||||
- **Per-job `workdir`** — project-aware cron runs ([#15110](https://github.com/NousResearch/hermes-agent/pull/15110))
|
||||
- **`context_from` field** — chain cron job outputs ([#15606](https://github.com/NousResearch/hermes-agent/pull/15606))
|
||||
- Fix: promote `croniter` to a core dependency ([#17577](https://github.com/NousResearch/hermes-agent/pull/17577))
|
||||
|
||||
### Web search
|
||||
- **Expose `limit` for `web_search`** ([#16934](https://github.com/NousResearch/hermes-agent/pull/16934))
|
||||
|
||||
### Maps
|
||||
- Fix: include seconds in timezone UTC offset output ([#16300](https://github.com/NousResearch/hermes-agent/pull/16300))
|
||||
|
||||
### Approvals
|
||||
- **Hardline blocklist for unrecoverable commands** ([#15878](https://github.com/NousResearch/hermes-agent/pull/15878))
|
||||
- Perf: precompile DANGEROUS_PATTERNS and HARDLINE_PATTERNS ([#17206](https://github.com/NousResearch/hermes-agent/pull/17206))
|
||||
|
||||
### ACP
|
||||
- **Advertise and forward image prompts** ([#18030](https://github.com/NousResearch/hermes-agent/pull/18030))
|
||||
|
||||
### API Server
|
||||
- **POST `/v1/runs/{run_id}/stop`** (salvage of #15656) ([#15842](https://github.com/NousResearch/hermes-agent/pull/15842))
|
||||
- **Expose run status for external UIs** (#17085) ([#17458](https://github.com/NousResearch/hermes-agent/pull/17458))
|
||||
|
||||
### Nix
|
||||
- **Declarative plugin installation for NixOS module** (@alt-glitch) ([#15953](https://github.com/NousResearch/hermes-agent/pull/15953))
|
||||
- Fix: use `--rebuild` in fix-lockfiles to bypass cached FOD store paths ([#15444](https://github.com/NousResearch/hermes-agent/pull/15444))
|
||||
- Fix: `extraPackages` now actually works via per-user profile ([#17047](https://github.com/NousResearch/hermes-agent/pull/17047))
|
||||
- Fix: refresh web/ npm-deps hash to unblock main builds ([#17174](https://github.com/NousResearch/hermes-agent/pull/17174))
|
||||
- Fix: replace magic-nix-cache with Cachix ([#17928](https://github.com/NousResearch/hermes-agent/pull/17928))
|
||||
|
||||
---
|
||||
|
||||
## 🖥️ TUI
|
||||
|
||||
### New features
|
||||
- **LaTeX rendering** (@austinpickett) ([#17175](https://github.com/NousResearch/hermes-agent/pull/17175))
|
||||
- **`/reload` .env hot-reload** — ported from the classic CLI ([#17286](https://github.com/NousResearch/hermes-agent/pull/17286))
|
||||
- **Pluggable busy-indicator styles** (@OutThisLife, #13610) ([#17150](https://github.com/NousResearch/hermes-agent/pull/17150))
|
||||
- **Opt-in auto-resume of the most recent session** (@OutThisLife) ([#17130](https://github.com/NousResearch/hermes-agent/pull/17130))
|
||||
- **Expanded light-terminal auto-detection** — `HERMES_TUI_THEME` + background hex (@OutThisLife) ([#17113](https://github.com/NousResearch/hermes-agent/pull/17113))
|
||||
- **Delete sessions from `/resume` picker with `d`** (@OutThisLife) ([#17668](https://github.com/NousResearch/hermes-agent/pull/17668))
|
||||
- **Line-by-line scroll on modified mouse wheel** (@OutThisLife) ([#17669](https://github.com/NousResearch/hermes-agent/pull/17669))
|
||||
- **Delete queued message while editing with ctrl-x / cancel with esc** (@OutThisLife) ([#16707](https://github.com/NousResearch/hermes-agent/pull/16707))
|
||||
- **Per-section visibility for the details accordion** (@OutThisLife) ([#14968](https://github.com/NousResearch/hermes-agent/pull/14968))
|
||||
- **Voice mode CLI parity** — VAD loop + TTS + crash forensics ([#14810](https://github.com/NousResearch/hermes-agent/pull/14810))
|
||||
- **Contextual first-touch hints ported to TUI** — `/busy`, `/verbose` ([#16054](https://github.com/NousResearch/hermes-agent/pull/16054))
|
||||
- **Mini help menu on `?` in the input field** (@ethernet8023) ([#18043](https://github.com/NousResearch/hermes-agent/pull/18043))
|
||||
|
||||
### Fixes
|
||||
- Fix: proactive mouse disable on ConPTY + `/mouse` toggle command (@kevin-ho, WSL2 ghost-mouse fix) ([#15488](https://github.com/NousResearch/hermes-agent/pull/15488))
|
||||
- Fix: restore skills search RPC ([#15870](https://github.com/NousResearch/hermes-agent/pull/15870))
|
||||
- Perf: cache text measurements across yoga flex re-passes ([#14818](https://github.com/NousResearch/hermes-agent/pull/14818))
|
||||
- Perf: stabilize long-session scrolling ([#15926](https://github.com/NousResearch/hermes-agent/pull/15926))
|
||||
- Perf: lazily seed virtual history heights ([#16523](https://github.com/NousResearch/hermes-agent/pull/16523))
|
||||
- Perf: cut visible cold start ~57% with lazy agent init ([#17190](https://github.com/NousResearch/hermes-agent/pull/17190))
|
||||
|
||||
---
|
||||
|
||||
## 🖱️ CLI & User Experience
|
||||
|
||||
### New commands
|
||||
- **`hermes -z <prompt>`** — non-interactive one-shot mode ([#15702](https://github.com/NousResearch/hermes-agent/pull/15702))
|
||||
- **`hermes -z` with `--model` / `--provider` / `HERMES_INFERENCE_MODEL`** ([#15704](https://github.com/NousResearch/hermes-agent/pull/15704))
|
||||
- **`hermes update --check`** preflight flag ([#15841](https://github.com/NousResearch/hermes-agent/pull/15841))
|
||||
- **`hermes fallback`** command for managing fallback providers ([#16052](https://github.com/NousResearch/hermes-agent/pull/16052))
|
||||
- **`/busy`** slash command for busy input mode ([#15382](https://github.com/NousResearch/hermes-agent/pull/15382))
|
||||
- **`/busy` input mode 'steer'** as a third option ([#16279](https://github.com/NousResearch/hermes-agent/pull/16279))
|
||||
- **`/btw` as alias for `/background`** ([#16053](https://github.com/NousResearch/hermes-agent/pull/16053))
|
||||
- **`/reload-skills`** slash command (salvage #17670) ([#17744](https://github.com/NousResearch/hermes-agent/pull/17744))
|
||||
- **Surface `/queue`, `/bg`, `/steer` in agent-running placeholder** ([#16118](https://github.com/NousResearch/hermes-agent/pull/16118))
|
||||
|
||||
### Setup / onboarding
|
||||
- **Auto-reconfigure on existing installs** ([#15879](https://github.com/NousResearch/hermes-agent/pull/15879))
|
||||
- **Contextual first-touch hints for `/busy` and `/verbose`** ([#16046](https://github.com/NousResearch/hermes-agent/pull/16046))
|
||||
- **Cost-saving tips from the April 30 tip-of-the-day** ([#17841](https://github.com/NousResearch/hermes-agent/pull/17841))
|
||||
- **Hyperlink startup banner title to the latest GitHub Release** ([#14945](https://github.com/NousResearch/hermes-agent/pull/14945))
|
||||
|
||||
### Update / backup
|
||||
- **Snapshot pairing data before `git pull`** ([#16383](https://github.com/NousResearch/hermes-agent/pull/16383))
|
||||
- **Auto-backup HERMES_HOME before `hermes update`** (opt-in, off by default) ([#16539](https://github.com/NousResearch/hermes-agent/pull/16539), [#16566](https://github.com/NousResearch/hermes-agent/pull/16566))
|
||||
- **Exclude `checkpoints/` from backups** ([#16572](https://github.com/NousResearch/hermes-agent/pull/16572))
|
||||
- **Exclude SQLite WAL/SHM/journal sidecars from backups** ([#16576](https://github.com/NousResearch/hermes-agent/pull/16576))
|
||||
- **Installer FHS layout for root installs on Linux** ([#15608](https://github.com/NousResearch/hermes-agent/pull/15608))
|
||||
- Fix: kill stale dashboards instead of warning ([#17832](https://github.com/NousResearch/hermes-agent/pull/17832))
|
||||
- Fix: show correct update status on nix-built hermes ([#17550](https://github.com/NousResearch/hermes-agent/pull/17550))
|
||||
|
||||
### Slash-command housekeeping
|
||||
- Refactor: drop `/provider`, `/plan` handler, and clean up slash registry ([#15047](https://github.com/NousResearch/hermes-agent/pull/15047))
|
||||
- Refactor: drop `persist_session` plumbing + fix broken `/btw` mid-turn bypass ([#16075](https://github.com/NousResearch/hermes-agent/pull/16075))
|
||||
|
||||
### OpenClaw migration (for folks coming from OpenClaw)
|
||||
- **Hardened OpenClaw import** — plan-first apply, redaction, pre-migration backup ([#16911](https://github.com/NousResearch/hermes-agent/pull/16911))
|
||||
- Fix: case-preserving brand rewrite + one-time `~/.openclaw` residue banner ([#16327](https://github.com/NousResearch/hermes-agent/pull/16327))
|
||||
- Fix: resolve `openclaw` workspace files from `agents.defaults.workspace` ([#16879](https://github.com/NousResearch/hermes-agent/pull/16879))
|
||||
- Fix: resolve model aliases against real OpenClaw catalog schema (salvage #16778) ([#16977](https://github.com/NousResearch/hermes-agent/pull/16977))
|
||||
|
||||
---
|
||||
|
||||
## 📊 Web Dashboard
|
||||
|
||||
- **Models tab** — rich per-model analytics ([#17745](https://github.com/NousResearch/hermes-agent/pull/17745))
|
||||
- **Configure main + auxiliary models from the Models page** ([#17802](https://github.com/NousResearch/hermes-agent/pull/17802))
|
||||
- **Dashboard Chat tab — xterm.js + JSON-RPC sidecar** (supersedes #12710 + #13379, @OutThisLife) ([#14890](https://github.com/NousResearch/hermes-agent/pull/14890))
|
||||
- **Dashboard layout refresh** (@austinpickett) ([#14899](https://github.com/NousResearch/hermes-agent/pull/14899))
|
||||
- **`--stop` and `--status` flags** on the dashboard CLI ([#17840](https://github.com/NousResearch/hermes-agent/pull/17840))
|
||||
- **Page-scoped plugin slots for built-in pages** ([#15658](https://github.com/NousResearch/hermes-agent/pull/15658))
|
||||
- Fix: replace all buttons for design system buttons ([#17007](https://github.com/NousResearch/hermes-agent/pull/17007))
|
||||
|
||||
---
|
||||
|
||||
## ⚡ Performance
|
||||
|
||||
- **TUI visible cold start cut ~57%** via lazy agent init ([#17190](https://github.com/NousResearch/hermes-agent/pull/17190))
|
||||
- **Lazy-import OpenAI, Anthropic, Firecrawl, account_usage** ([#17046](https://github.com/NousResearch/hermes-agent/pull/17046))
|
||||
- **mtime-cache `load_config()` and `read_raw_config()`** ([#17041](https://github.com/NousResearch/hermes-agent/pull/17041))
|
||||
- **Memoize `get_tool_definitions()` + TTL-cache `check_fn` results** ([#17098](https://github.com/NousResearch/hermes-agent/pull/17098))
|
||||
- **Precompile DANGEROUS_PATTERNS and HARDLINE_PATTERNS** ([#17206](https://github.com/NousResearch/hermes-agent/pull/17206))
|
||||
- **Cache Ink text measurements across yoga flex re-passes** ([#14818](https://github.com/NousResearch/hermes-agent/pull/14818))
|
||||
- **Stabilize long-session scrolling** ([#15926](https://github.com/NousResearch/hermes-agent/pull/15926))
|
||||
- **Lazily seed virtual history heights** ([#16523](https://github.com/NousResearch/hermes-agent/pull/16523))
|
||||
|
||||
---
|
||||
|
||||
## 🔒 Security & Reliability
|
||||
|
||||
- **Secret redaction off by default** — stops corrupting patches / API payloads with fake-key substitutions. Opt in via `redaction.enabled: true` ([#16794](https://github.com/NousResearch/hermes-agent/pull/16794))
|
||||
- **`[SYSTEM:` → `[IMPORTANT:`** in all user-injected markers (Azure content filter dodge) ([#16114](https://github.com/NousResearch/hermes-agent/pull/16114))
|
||||
- **Hardline blocklist for unrecoverable commands** ([#15878](https://github.com/NousResearch/hermes-agent/pull/15878))
|
||||
- **Canonical `mask_secret` helper; fix status.py DIM drift** ([#17207](https://github.com/NousResearch/hermes-agent/pull/17207))
|
||||
- **Sweep expired paste.rs uploads on a real timer** ([#16431](https://github.com/NousResearch/hermes-agent/pull/16431))
|
||||
- **Preserve symlinks during atomic file writes** ([#16980](https://github.com/NousResearch/hermes-agent/pull/16980))
|
||||
- **Probe `/dev/tty` by opening it, not bare existence** ([#17024](https://github.com/NousResearch/hermes-agent/pull/17024))
|
||||
|
||||
---
|
||||
|
||||
## 🐛 Notable Bug Fixes
|
||||
|
||||
This window includes 360 `fix:` PRs. Selected highlights from across the stack:
|
||||
|
||||
- **Background review fork inherits parent's live runtime** — provider/model/creds now propagate correctly ([#16099](https://github.com/NousResearch/hermes-agent/pull/16099))
|
||||
- **Hindsight configurable `HINDSIGHT_TIMEOUT` env var** ([#15077](https://github.com/NousResearch/hermes-agent/pull/15077))
|
||||
- **Tools: normalize numeric entries + clear stale `no_mcp` in `_save_platform_tools`** ([#15607](https://github.com/NousResearch/hermes-agent/pull/15607))
|
||||
- **MCP: rewrite `definitions` refs to `$defs` in input schemas** — closes provider-side 400s
|
||||
- **Azure content filter compatibility** — renamed `[SYSTEM:` markers so Azure's content filter stops flagging them ([#16114](https://github.com/NousResearch/hermes-agent/pull/16114))
|
||||
- **Vision cache uses HERMES_HOME instead of cwd** ([#17719](https://github.com/NousResearch/hermes-agent/pull/17719))
|
||||
- **FTS5 search** — tool_name + tool_calls indexing with repair + migration ([#16914](https://github.com/NousResearch/hermes-agent/pull/16914))
|
||||
- **Streaming reasoning persists on assistant turns** ([#16892](https://github.com/NousResearch/hermes-agent/pull/16892))
|
||||
- **execute_code concurrent RPC serialization** (#17770) ([#17894](https://github.com/NousResearch/hermes-agent/pull/17894), [#17902](https://github.com/NousResearch/hermes-agent/pull/17902))
|
||||
- **Background reviewer scoped to memory + skills toolsets** — no more accidental web/shell escapes ([#16569](https://github.com/NousResearch/hermes-agent/pull/16569))
|
||||
- **Compression recovery** — retry on main before giving up; notify user when aux fails ([#16774](https://github.com/NousResearch/hermes-agent/pull/16774), [#16775](https://github.com/NousResearch/hermes-agent/pull/16775))
|
||||
- **`croniter` promoted to a core dependency** ([#17577](https://github.com/NousResearch/hermes-agent/pull/17577))
|
||||
- **Discord tool `limit` parameter coerced to int** before `min()` call ([#16319](https://github.com/NousResearch/hermes-agent/pull/16319))
|
||||
- **Yuanbao messaging platform entrance fix** ([#16880](https://github.com/NousResearch/hermes-agent/pull/16880))
|
||||
- **ACP advertise and forward image prompts** ([#18030](https://github.com/NousResearch/hermes-agent/pull/18030))
|
||||
- **DeepSeek / Kimi reasoning content isolation** across cross-provider histories (@Zjianru) ([#15749](https://github.com/NousResearch/hermes-agent/pull/15749), [#15762](https://github.com/NousResearch/hermes-agent/pull/15762))
|
||||
- **Preserve reasoning_content replay on DeepSeek v4 + Kimi/Moonshot thinking** ([#18045](https://github.com/NousResearch/hermes-agent/pull/18045))
|
||||
|
||||
The vast majority of the 360 fixes landed in the streaming/compression/tool-calling paths across all providers — DeepSeek, Kimi, Moonshot, GLM, Qwen, MiniMax, Gemini, Anthropic, OpenAI — alongside TUI polish (resize, scroll, sticky-prompt) and gateway platform-specific edge cases.
|
||||
|
||||
---
|
||||
|
||||
## 🧪 Testing & CI
|
||||
|
||||
- Hermetic test parity (`scripts/run_tests.sh`) held across this window
|
||||
- **Microsoft Teams xdist collision guard** — prevents worker collisions when Teams platform tests run in parallel ([#17828](https://github.com/NousResearch/hermes-agent/pull/17828))
|
||||
- Chore: remove unused imports and dead locals (ruff F401, F841) ([#17010](https://github.com/NousResearch/hermes-agent/pull/17010))
|
||||
|
||||
---
|
||||
|
||||
## 📚 Documentation
|
||||
|
||||
- **Curator feature page** added to docs site ([#17563](https://github.com/NousResearch/hermes-agent/pull/17563))
|
||||
- **Document pin also blocking `skill_manage` writes** ([#17578](https://github.com/NousResearch/hermes-agent/pull/17578))
|
||||
- **Direct-URL skill install documented** across features, reference, guide, and `hermes-agent` skill ([#16355](https://github.com/NousResearch/hermes-agent/pull/16355))
|
||||
- **Hooks tutorial — build a BOOT.md startup checklist** (replaces the removed built-in hook) ([#17202](https://github.com/NousResearch/hermes-agent/pull/17202))
|
||||
- **ComfyUI docs: ask local vs cloud FIRST before hardware check** ([#17612](https://github.com/NousResearch/hermes-agent/pull/17612))
|
||||
- **Obliteratus skill: link YouTube video guide in SKILL.md** ([#15808](https://github.com/NousResearch/hermes-agent/pull/15808))
|
||||
- Per-skill docs pages generated for bundled + optional skills; ASCII art code blocks auto-wrapped ([#14929](https://github.com/NousResearch/hermes-agent/pull/14929), [#16497](https://github.com/NousResearch/hermes-agent/pull/16497))
|
||||
|
||||
---
|
||||
|
||||
## ⚖️ Removed / Reverted
|
||||
|
||||
- **Kanban multi-profile collaboration board** — landed in #16081, reverted in ([#16098](https://github.com/NousResearch/hermes-agent/pull/16098)) while the design is reworked
|
||||
- **computer-use cua-driver** — 3 preparatory PRs landed then were reverted in ([#16927](https://github.com/NousResearch/hermes-agent/pull/16927))
|
||||
- **BOOT.md built-in hook** removed ([#17093](https://github.com/NousResearch/hermes-agent/pull/17093)); the hooks tutorial ([#17202](https://github.com/NousResearch/hermes-agent/pull/17202)) shows how to build the same workflow yourself with a shell hook
|
||||
- **`/provider` + `/plan` slash commands dropped** ([#15047](https://github.com/NousResearch/hermes-agent/pull/15047))
|
||||
- **`flush_memories` removed entirely** ([#15696](https://github.com/NousResearch/hermes-agent/pull/15696))
|
||||
|
||||
---
|
||||
|
||||
## 👥 Contributors
|
||||
|
||||
### Core
|
||||
- **@teknium1** (Teknium)
|
||||
|
||||
### Top Community Contributors (by merged PR count since v0.11.0)
|
||||
|
||||
- **@OutThisLife** (Brooklyn) — 52 PRs · TUI — light-terminal detection + pluggable busy styles + auto-resume + session-delete from /resume + mouse-wheel scrolling + xterm.js dashboard Chat tab + cold-start cut + accordion polish
|
||||
- **@kshitijk4poor** — 12 PRs · LM Studio first-class provider (salvage), Vercel Sandbox backend, GMI Cloud salvage, bundled-by-default touchdesigner-mcp, many tool-call / reasoning fixes
|
||||
- **@helix4u** — 10 PRs · MCP schema robustness, assorted stability fixes
|
||||
- **@alt-glitch** — 8 PRs · trigram FTS5 CJK search, declarative Nix plugin install, matrix/feishu hints and fixes
|
||||
- **@ethernet8023** — 4 PRs
|
||||
- **@austinpickett** — 4 PRs · LaTeX rendering in TUI, dashboard layout refresh
|
||||
- **@benbarclay** — 3 PRs · Docker run-as-host-user so bind mounts don't get root-owned
|
||||
- **@vominh1919** — 2 PRs
|
||||
- **@stephenschoettler** — 2 PRs
|
||||
- **@kevin-ho** — ConPTY mouse-injection fix (#15488)
|
||||
- **@Zjianru** — cross-provider reasoning_content isolation + DeepSeek/Kimi empty-reasoning injection (#15749, #15762)
|
||||
- **@web3blind** — Telegram chat allowlists for groups and forums (#15027)
|
||||
- **@SHL0MS** — 9 new TouchDesigner-MCP reference docs (#16768)
|
||||
- **@0xDevNinja** — curator `restore_skill` nested-archive fix (#17951)
|
||||
- **@y0shua1ee** — curator `use` activity fix (#17953)
|
||||
|
||||
### Also contributing
|
||||
Salvaged or co-authored work from **@isaachuangGMICLOUD** (GMI Cloud), earlier upstream PRs from the original author of each salvage chain, and a long tail of one-shot fixes, documentation nudges, and skill contributions from the community.
|
||||
|
||||
### All Contributors (alphabetical, excluding @teknium1)
|
||||
|
||||
@0xbyt4, @0xharryriddle, @0xDevNinja, @0z1-ghb, @5park1e, @A-FdL-Prog, @aj-nt, @akhater, @alblez, @alexg0bot,
|
||||
@alexzhu0, @AllardQuek, @alt-glitch, @amanning3390, @amanuel2, @AndreKurait, @andrewhosf, @Andy283, @andyylin,
|
||||
@angel12, @AntAISecurityLab, @ash, @austinpickett, @badgerbees, @BadTechBandit, @Bartok9, @beenherebefore,
|
||||
@beesrsj2500, @BeliefanX, @benbarclay, @benjaminsehl, @BlackishGreen33, @bloodcarter, @BlueBirdBack,
|
||||
@briandevans, @brooklynnicholson, @bsgdigital, @buray, @bwjoke, @camaragon, @cdanis, @cgarwood82,
|
||||
@charles-brooks, @chen1749144759, @chengoak, @ching-kaching, @Contentment003111, @crayfish-ai, @CruxExperts,
|
||||
@cyclingwithelephants, @dandaka, @danklynn, @ddupont808, @dhabibi, @difujia, @dimitrovi, @dlkakbs,
|
||||
@dontcallmejames, @EKKOLearnAI, @emozilla, @ericnicolaides, @Erosika, @ethernet8023, @exiao, @Feranmi10,
|
||||
@flobo3, @foxion37, @georgeglessner, @georgex8001, @ghostmfr, @H-Ali13381, @HangGlidersRule, @harryplusplus,
|
||||
@haru398801, @heathley, @hejuntt1014, @hekaru-agent, @helix4u, @Heltman, @HenkDz, @heyitsaamir, @hharry11,
|
||||
@hhhonzik, @hhuang91, @HiddenPuppy, @htsh, @iamagenius00, @in-liberty420, @innocarpe, @irispillars, @iRonin,
|
||||
@isaachuangGMICLOUD, @Ito-69, @j3ffffff, @jackjin1997, @jakubkrcmar, @Jason2031, @JayGwod, @jerome-benoit,
|
||||
@johnncenae, @Kailigithub, @keiravoss94, @kevin-ho, @knockyai, @konsisumer, @kshitijk4poor, @kunlabs, @l0hde,
|
||||
@Leihb, @leoneparise, @LeonSGP43, @liizfq, @liuhao1024, @loongzhao, @lsdsjy, @luyao618, @ma-pony, @Magaav,
|
||||
@MagicRay1217, @math0r-be, @MattMaximo, @maxims-oss, @MaxyMoos, @maymuneth, @mcndjxlefnd, @memosr,
|
||||
@MestreY0d4-Uninter, @mewwts, @Mirac1eSky, @MorAlekss, @mrhwick, @mrunmayee17, @mssteuer, @Nanako0129,
|
||||
@nazirulhafiy, @Nerijusas, @Nicecsh, @nicoloboschi, @nightq, @ningfangbin, @octo-patch, @Octopus,
|
||||
@OutThisLife, @Paperclip, @pein892, @perlowja, @prasadus92, @qike-ms, @qiyin-code, @Readon, @ReginaldasR,
|
||||
@revaraver, @rfilgueiras, @rmoen, @romanornr, @rugvedS07, @rylena, @samrusani, @Sanjays2402, @sasha-id,
|
||||
@Satoshi-agi, @scheidti, @scotttrinh, @season179, @SeeYangZhi, @sgaofen, @shamork, @shannonsands, @SHL0MS,
|
||||
@simbam99, @Societus, @socrates1024, @Sonoyunchu, @sprmn24, @stephenschoettler, @tangyuanjc, @TechPrototyper,
|
||||
@tekgnosis-net, @ThomassJonax, @tmimmanuel, @tochukwuada, @Tosko4, @Tranquil-Flow, @twozle, @txbxxx,
|
||||
@UgwujaGeorge, @Versun, @vlwkaos, @voidborne-d, @vominh1919, @Wang-tianhao, @Wangshengyang2004, @web3blind,
|
||||
@westers, @Wysie, @xandersbell, @xiahu88988, @XieNBi, @xinbenlv, @xnbi, @y0shua1ee, @yatesjalex, @yes999zc,
|
||||
@yeyitech, @Yoimex, @YueLich, @Yukipukii1, @zhiyanliu, @zicochaos, @Zjianru, @zkl2333, @zons-zhaozhy,
|
||||
@ztexydt-cqh.
|
||||
|
||||
Also: @Siddharth Balyan, @YuShu.
|
||||
|
||||
---
|
||||
|
||||
**Full Changelog**: [v2026.4.23...v2026.4.30](https://github.com/NousResearch/hermes-agent/compare/v2026.4.23...v2026.4.30)
|
||||
+30
-381
@@ -4,7 +4,6 @@ from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import contextvars
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
from collections import defaultdict, deque
|
||||
@@ -48,7 +47,6 @@ from acp.schema import (
|
||||
TextContentBlock,
|
||||
UnstructuredCommandInput,
|
||||
Usage,
|
||||
UsageUpdate,
|
||||
UserMessageChunk,
|
||||
)
|
||||
|
||||
@@ -67,7 +65,6 @@ from acp_adapter.events import (
|
||||
)
|
||||
from acp_adapter.permissions import make_approval_callback
|
||||
from acp_adapter.session import SessionManager, SessionState, _expand_acp_enabled_toolsets
|
||||
from acp_adapter.tools import build_tool_complete, build_tool_start
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -167,8 +164,6 @@ class HermesACPAgent(acp.Agent):
|
||||
"context": "Show conversation context info",
|
||||
"reset": "Clear conversation history",
|
||||
"compact": "Compress conversation context",
|
||||
"steer": "Inject guidance into the currently running agent turn",
|
||||
"queue": "Queue a prompt to run after the current turn finishes",
|
||||
"version": "Show Hermes version",
|
||||
}
|
||||
|
||||
@@ -198,16 +193,6 @@ class HermesACPAgent(acp.Agent):
|
||||
"name": "compact",
|
||||
"description": "Compress conversation context",
|
||||
},
|
||||
{
|
||||
"name": "steer",
|
||||
"description": "Inject guidance into the currently running agent turn",
|
||||
"input_hint": "guidance for the active turn",
|
||||
},
|
||||
{
|
||||
"name": "queue",
|
||||
"description": "Queue a prompt to run after the current turn finishes",
|
||||
"input_hint": "prompt to run next",
|
||||
},
|
||||
{
|
||||
"name": "version",
|
||||
"description": "Show Hermes version",
|
||||
@@ -318,66 +303,6 @@ class HermesACPAgent(acp.Agent):
|
||||
|
||||
return target_provider, new_model
|
||||
|
||||
@staticmethod
|
||||
def _build_usage_update(state: SessionState) -> UsageUpdate | None:
|
||||
"""Build ACP native context-usage data for clients like Zed.
|
||||
|
||||
Zed's circular context indicator is driven by ACP ``usage_update``
|
||||
session updates: ``size`` is the model context window and ``used`` is
|
||||
the current request pressure. Hermes estimates ``used`` from the same
|
||||
buckets it sends to providers: system prompt, conversation history, and
|
||||
tool schemas.
|
||||
"""
|
||||
agent = state.agent
|
||||
compressor = getattr(agent, "context_compressor", None)
|
||||
size = int(getattr(compressor, "context_length", 0) or 0)
|
||||
if size <= 0:
|
||||
return None
|
||||
|
||||
try:
|
||||
from agent.model_metadata import estimate_request_tokens_rough
|
||||
|
||||
used = estimate_request_tokens_rough(
|
||||
state.history,
|
||||
system_prompt=getattr(agent, "_cached_system_prompt", "") or "",
|
||||
tools=getattr(agent, "tools", None) or None,
|
||||
)
|
||||
except Exception:
|
||||
logger.debug("Could not estimate ACP native context usage", exc_info=True)
|
||||
used = int(getattr(compressor, "last_prompt_tokens", 0) or 0)
|
||||
|
||||
return UsageUpdate(
|
||||
session_update="usage_update",
|
||||
size=max(size, 0),
|
||||
used=max(used, 0),
|
||||
)
|
||||
|
||||
async def _send_usage_update(self, state: SessionState) -> None:
|
||||
"""Send ACP native context usage to the connected client."""
|
||||
if not self._conn:
|
||||
return
|
||||
update = self._build_usage_update(state)
|
||||
if update is None:
|
||||
return
|
||||
try:
|
||||
await self._conn.session_update(
|
||||
session_id=state.session_id,
|
||||
update=update,
|
||||
)
|
||||
except Exception:
|
||||
logger.warning(
|
||||
"Failed to send ACP usage update for session %s",
|
||||
state.session_id,
|
||||
exc_info=True,
|
||||
)
|
||||
|
||||
def _schedule_usage_update(self, state: SessionState) -> None:
|
||||
"""Schedule native context indicator refresh after ACP responses."""
|
||||
if not self._conn:
|
||||
return
|
||||
loop = asyncio.get_running_loop()
|
||||
loop.call_soon(asyncio.create_task, self._send_usage_update(state))
|
||||
|
||||
async def _register_session_mcp_servers(
|
||||
self,
|
||||
state: SessionState,
|
||||
@@ -548,99 +473,37 @@ class HermesACPAgent(acp.Agent):
|
||||
)
|
||||
return None
|
||||
|
||||
@staticmethod
|
||||
def _history_tool_call_name_args(tool_call: dict[str, Any]) -> tuple[str, dict[str, Any]]:
|
||||
"""Extract function name/arguments from an OpenAI-style tool_call."""
|
||||
function = tool_call.get("function") if isinstance(tool_call.get("function"), dict) else {}
|
||||
name = str(function.get("name") or tool_call.get("name") or "unknown_tool")
|
||||
raw_args = function.get("arguments") or tool_call.get("arguments") or tool_call.get("args") or {}
|
||||
if isinstance(raw_args, str):
|
||||
try:
|
||||
parsed = json.loads(raw_args)
|
||||
except Exception:
|
||||
parsed = {"raw": raw_args}
|
||||
raw_args = parsed
|
||||
if not isinstance(raw_args, dict):
|
||||
raw_args = {}
|
||||
return name, raw_args
|
||||
|
||||
@staticmethod
|
||||
def _history_tool_call_id(tool_call: dict[str, Any]) -> str:
|
||||
"""Return the stable provider tool call id for ACP history replay."""
|
||||
return str(
|
||||
tool_call.get("id")
|
||||
or tool_call.get("call_id")
|
||||
or tool_call.get("tool_call_id")
|
||||
or ""
|
||||
).strip()
|
||||
|
||||
async def _replay_session_history(self, state: SessionState) -> None:
|
||||
"""Send persisted user/assistant history to clients during session/load.
|
||||
|
||||
Zed's ACP history UI calls ``session/load`` after the user picks an item
|
||||
from the Agents sidebar. The agent must then replay the full conversation
|
||||
as user/assistant chunks plus reconstructed tool-call start/completion
|
||||
notifications; merely restoring server-side state makes Hermes remember
|
||||
context, but leaves the editor looking like a clean thread.
|
||||
as ``user_message_chunk`` / ``agent_message_chunk`` notifications; merely
|
||||
restoring server-side state makes Hermes remember context, but leaves the
|
||||
editor looking like a clean thread.
|
||||
"""
|
||||
if not self._conn or not state.history:
|
||||
return
|
||||
|
||||
active_tool_calls: dict[str, tuple[str, dict[str, Any]]] = {}
|
||||
|
||||
async def _send(update: Any) -> bool:
|
||||
for message in state.history:
|
||||
role = str(message.get("role") or "")
|
||||
if role not in {"user", "assistant"}:
|
||||
continue
|
||||
text = self._history_message_text(message)
|
||||
if not text:
|
||||
continue
|
||||
update = self._history_message_update(role=role, text=text)
|
||||
if update is None:
|
||||
continue
|
||||
try:
|
||||
await self._conn.session_update(session_id=state.session_id, update=update)
|
||||
return True
|
||||
except Exception:
|
||||
logger.warning(
|
||||
"Failed to replay ACP history for session %s",
|
||||
state.session_id,
|
||||
exc_info=True,
|
||||
)
|
||||
return False
|
||||
|
||||
for message in state.history:
|
||||
role = str(message.get("role") or "")
|
||||
|
||||
if role in {"user", "assistant"}:
|
||||
text = self._history_message_text(message)
|
||||
if text:
|
||||
update = self._history_message_update(role=role, text=text)
|
||||
if update is not None and not await _send(update):
|
||||
return
|
||||
|
||||
if role == "assistant" and isinstance(message.get("tool_calls"), list):
|
||||
for tool_call in message["tool_calls"]:
|
||||
if not isinstance(tool_call, dict):
|
||||
continue
|
||||
tool_call_id = self._history_tool_call_id(tool_call)
|
||||
if not tool_call_id:
|
||||
continue
|
||||
tool_name, args = self._history_tool_call_name_args(tool_call)
|
||||
active_tool_calls[tool_call_id] = (tool_name, args)
|
||||
if not await _send(build_tool_start(tool_call_id, tool_name, args)):
|
||||
return
|
||||
continue
|
||||
|
||||
if role == "tool":
|
||||
tool_call_id = str(message.get("tool_call_id") or "").strip()
|
||||
tool_name = str(message.get("tool_name") or "").strip()
|
||||
function_args: dict[str, Any] | None = None
|
||||
if tool_call_id in active_tool_calls:
|
||||
tool_name, function_args = active_tool_calls.pop(tool_call_id)
|
||||
if not tool_call_id or not tool_name:
|
||||
continue
|
||||
result = message.get("content")
|
||||
if not await _send(
|
||||
build_tool_complete(
|
||||
tool_call_id,
|
||||
tool_name,
|
||||
result=result if isinstance(result, str) else None,
|
||||
function_args=function_args,
|
||||
)
|
||||
):
|
||||
return
|
||||
return
|
||||
|
||||
async def new_session(
|
||||
self,
|
||||
@@ -652,24 +515,11 @@ class HermesACPAgent(acp.Agent):
|
||||
await self._register_session_mcp_servers(state, mcp_servers)
|
||||
logger.info("New session %s (cwd=%s)", state.session_id, cwd)
|
||||
self._schedule_available_commands_update(state.session_id)
|
||||
self._schedule_usage_update(state)
|
||||
return NewSessionResponse(
|
||||
session_id=state.session_id,
|
||||
models=self._build_model_state(state),
|
||||
)
|
||||
|
||||
def _schedule_history_replay(self, state: SessionState) -> None:
|
||||
"""Replay persisted history after session/load or session/resume returns.
|
||||
|
||||
Zed only attaches streamed transcript/tool updates once the load/resume
|
||||
response has completed. Sending replay notifications while the request is
|
||||
still in-flight can make the server look correct in logs while the editor
|
||||
drops or fails to attach the tool-call history.
|
||||
"""
|
||||
loop = asyncio.get_running_loop()
|
||||
replay_coro = self._replay_session_history(state)
|
||||
loop.call_soon(asyncio.create_task, replay_coro)
|
||||
|
||||
async def load_session(
|
||||
self,
|
||||
cwd: str,
|
||||
@@ -683,9 +533,8 @@ class HermesACPAgent(acp.Agent):
|
||||
return None
|
||||
await self._register_session_mcp_servers(state, mcp_servers)
|
||||
logger.info("Loaded session %s", session_id)
|
||||
self._schedule_history_replay(state)
|
||||
await self._replay_session_history(state)
|
||||
self._schedule_available_commands_update(session_id)
|
||||
self._schedule_usage_update(state)
|
||||
return LoadSessionResponse(models=self._build_model_state(state))
|
||||
|
||||
async def resume_session(
|
||||
@@ -701,17 +550,13 @@ class HermesACPAgent(acp.Agent):
|
||||
state = self.session_manager.create_session(cwd=cwd)
|
||||
await self._register_session_mcp_servers(state, mcp_servers)
|
||||
logger.info("Resumed session %s", state.session_id)
|
||||
self._schedule_history_replay(state)
|
||||
await self._replay_session_history(state)
|
||||
self._schedule_available_commands_update(state.session_id)
|
||||
self._schedule_usage_update(state)
|
||||
return ResumeSessionResponse(models=self._build_model_state(state))
|
||||
|
||||
async def cancel(self, session_id: str, **kwargs: Any) -> None:
|
||||
state = self.session_manager.get_session(session_id)
|
||||
if state and state.cancel_event:
|
||||
with state.runtime_lock:
|
||||
if state.is_running and state.current_prompt_text:
|
||||
state.interrupted_prompt_text = state.current_prompt_text
|
||||
state.cancel_event.set()
|
||||
try:
|
||||
if getattr(state, "agent", None) and hasattr(state.agent, "interrupt"):
|
||||
@@ -809,39 +654,6 @@ class HermesACPAgent(acp.Agent):
|
||||
if not has_content:
|
||||
return PromptResponse(stop_reason="end_turn")
|
||||
|
||||
# /steer on an idle session has no in-flight tool call to inject into.
|
||||
# Rewrite it so the payload runs as a normal user prompt, matching the
|
||||
# gateway's behavior (gateway/run.py ~L4898). Two sub-cases:
|
||||
# 1. Zed-interrupt salvage — a prior prompt was cancelled by the
|
||||
# client right before /steer arrived; replay it with the steer
|
||||
# text attached as explicit correction/guidance so the user's
|
||||
# in-flight work isn't lost.
|
||||
# 2. Plain idle — no prior work to salvage; just run the steer
|
||||
# payload as a regular prompt. Without this, _cmd_steer would
|
||||
# silently append to state.queued_prompts and respond with
|
||||
# "No active turn — queued for the next turn", which looks like
|
||||
# /queue even though the user never typed /queue.
|
||||
if isinstance(user_content, str) and user_text.startswith("/steer"):
|
||||
steer_text = user_text.split(maxsplit=1)[1].strip() if len(user_text.split(maxsplit=1)) > 1 else ""
|
||||
interrupted_prompt = ""
|
||||
rewrite_idle = False
|
||||
with state.runtime_lock:
|
||||
if not state.is_running and steer_text:
|
||||
if state.interrupted_prompt_text:
|
||||
interrupted_prompt = state.interrupted_prompt_text
|
||||
state.interrupted_prompt_text = ""
|
||||
else:
|
||||
rewrite_idle = True
|
||||
if interrupted_prompt:
|
||||
user_text = (
|
||||
f"{interrupted_prompt}\n\n"
|
||||
f"User correction/guidance after interrupt: {steer_text}"
|
||||
)
|
||||
user_content = user_text
|
||||
elif rewrite_idle:
|
||||
user_text = steer_text
|
||||
user_content = steer_text
|
||||
|
||||
# Intercept slash commands — handle locally without calling the LLM.
|
||||
# Slash commands are text-only; if the client included images/resources,
|
||||
# send the whole multimodal prompt to the agent instead of treating it as
|
||||
@@ -852,27 +664,8 @@ class HermesACPAgent(acp.Agent):
|
||||
if self._conn:
|
||||
update = acp.update_agent_message_text(response_text)
|
||||
await self._conn.session_update(session_id, update)
|
||||
await self._send_usage_update(state)
|
||||
return PromptResponse(stop_reason="end_turn")
|
||||
|
||||
# If Zed sends another regular prompt while the same ACP session is
|
||||
# still running, queue it instead of racing two AIAgent loops against
|
||||
# the same state.history. /steer and /queue are handled above and can
|
||||
# land immediately.
|
||||
with state.runtime_lock:
|
||||
if state.is_running:
|
||||
queued_text = user_text or "[Image attachment]"
|
||||
state.queued_prompts.append(queued_text)
|
||||
depth = len(state.queued_prompts)
|
||||
if self._conn:
|
||||
update = acp.update_agent_message_text(
|
||||
f"Queued for the next turn. ({depth} queued)"
|
||||
)
|
||||
await self._conn.session_update(session_id, update)
|
||||
return PromptResponse(stop_reason="end_turn")
|
||||
state.is_running = True
|
||||
state.current_prompt_text = user_text or "[Image attachment]"
|
||||
|
||||
logger.info("Prompt on session %s: %s", session_id, user_text[:100])
|
||||
|
||||
conn = self._conn
|
||||
@@ -885,37 +678,24 @@ class HermesACPAgent(acp.Agent):
|
||||
tool_call_meta: dict[str, dict[str, Any]] = {}
|
||||
previous_approval_cb = None
|
||||
|
||||
streamed_message = False
|
||||
|
||||
if conn:
|
||||
tool_progress_cb = make_tool_progress_cb(conn, session_id, loop, tool_call_ids, tool_call_meta)
|
||||
reasoning_cb = make_thinking_cb(conn, session_id, loop)
|
||||
thinking_cb = make_thinking_cb(conn, session_id, loop)
|
||||
step_cb = make_step_cb(conn, session_id, loop, tool_call_ids, tool_call_meta)
|
||||
message_cb = make_message_cb(conn, session_id, loop)
|
||||
|
||||
def stream_delta_cb(text: str) -> None:
|
||||
nonlocal streamed_message
|
||||
if text:
|
||||
streamed_message = True
|
||||
message_cb(text)
|
||||
|
||||
approval_cb = make_approval_callback(conn.request_permission, loop, session_id)
|
||||
else:
|
||||
tool_progress_cb = None
|
||||
reasoning_cb = None
|
||||
thinking_cb = None
|
||||
step_cb = None
|
||||
stream_delta_cb = None
|
||||
message_cb = None
|
||||
approval_cb = None
|
||||
|
||||
agent = state.agent
|
||||
agent.tool_progress_callback = tool_progress_cb
|
||||
# ACP thought panes should not receive Hermes' local kawaii waiting/status
|
||||
# updates. Route provider/model reasoning deltas instead; if the provider
|
||||
# emits no reasoning, Zed should not get a fake "thinking" accordion.
|
||||
agent.thinking_callback = None
|
||||
agent.reasoning_callback = reasoning_cb
|
||||
agent.thinking_callback = thinking_cb
|
||||
agent.step_callback = step_cb
|
||||
agent.stream_delta_callback = stream_delta_cb
|
||||
agent.message_callback = message_cb
|
||||
|
||||
# Approval callback is per-thread (thread-local, GHSA-qg5c-hvr5-hjgr).
|
||||
# Set it INSIDE _run_agent so the TLS write happens in the executor
|
||||
@@ -997,9 +777,6 @@ class HermesACPAgent(acp.Agent):
|
||||
result = await loop.run_in_executor(_executor, ctx.run, _run_agent)
|
||||
except Exception:
|
||||
logger.exception("Executor error for session %s", session_id)
|
||||
with state.runtime_lock:
|
||||
state.is_running = False
|
||||
state.current_prompt_text = ""
|
||||
return PromptResponse(stop_reason="end_turn")
|
||||
|
||||
if result.get("messages"):
|
||||
@@ -1021,32 +798,10 @@ class HermesACPAgent(acp.Agent):
|
||||
)
|
||||
except Exception:
|
||||
logger.debug("Failed to auto-title ACP session %s", session_id, exc_info=True)
|
||||
if final_response and conn and not streamed_message:
|
||||
if final_response and conn:
|
||||
update = acp.update_agent_message_text(final_response)
|
||||
await conn.session_update(session_id, update)
|
||||
|
||||
# Mark this turn idle before draining queued work so recursive prompt()
|
||||
# calls can acquire the session. Queued turns are intentionally run as
|
||||
# normal follow-up user prompts, preserving role alternation and history.
|
||||
with state.runtime_lock:
|
||||
state.is_running = False
|
||||
state.current_prompt_text = ""
|
||||
|
||||
while True:
|
||||
with state.runtime_lock:
|
||||
if not state.queued_prompts:
|
||||
break
|
||||
next_prompt = state.queued_prompts.pop(0)
|
||||
if conn:
|
||||
await conn.session_update(
|
||||
session_id,
|
||||
acp.update_user_message_text(next_prompt),
|
||||
)
|
||||
await self.prompt(
|
||||
prompt=[TextContentBlock(type="text", text=next_prompt)],
|
||||
session_id=session_id,
|
||||
)
|
||||
|
||||
usage = None
|
||||
if any(result.get(key) is not None for key in ("prompt_tokens", "completion_tokens", "total_tokens")):
|
||||
usage = Usage(
|
||||
@@ -1057,8 +812,6 @@ class HermesACPAgent(acp.Agent):
|
||||
cached_read_tokens=result.get("cache_read_tokens"),
|
||||
)
|
||||
|
||||
await self._send_usage_update(state)
|
||||
|
||||
stop_reason = "cancelled" if state.cancel_event and state.cancel_event.is_set() else "end_turn"
|
||||
return PromptResponse(stop_reason=stop_reason, usage=usage)
|
||||
|
||||
@@ -1126,8 +879,6 @@ class HermesACPAgent(acp.Agent):
|
||||
"context": self._cmd_context,
|
||||
"reset": self._cmd_reset,
|
||||
"compact": self._cmd_compact,
|
||||
"steer": self._cmd_steer,
|
||||
"queue": self._cmd_queue,
|
||||
"version": self._cmd_version,
|
||||
}.get(cmd)
|
||||
|
||||
@@ -1191,84 +942,22 @@ class HermesACPAgent(acp.Agent):
|
||||
return f"Could not list tools: {e}"
|
||||
|
||||
def _cmd_context(self, args: str, state: SessionState) -> str:
|
||||
"""Show ACP session context pressure and compression guidance."""
|
||||
n_messages = len(state.history)
|
||||
|
||||
# Count by role.
|
||||
if n_messages == 0:
|
||||
return "Conversation is empty (no messages yet)."
|
||||
# Count by role
|
||||
roles: dict[str, int] = {}
|
||||
for msg in state.history:
|
||||
role = msg.get("role", "unknown")
|
||||
roles[role] = roles.get(role, 0) + 1
|
||||
|
||||
agent = state.agent
|
||||
model = state.model or getattr(agent, "model", "")
|
||||
provider = getattr(agent, "provider", None) or "auto"
|
||||
compressor = getattr(agent, "context_compressor", None)
|
||||
context_length = int(getattr(compressor, "context_length", 0) or 0)
|
||||
threshold_tokens = int(getattr(compressor, "threshold_tokens", 0) or 0)
|
||||
|
||||
try:
|
||||
from agent.model_metadata import estimate_request_tokens_rough
|
||||
|
||||
system_prompt = getattr(agent, "_cached_system_prompt", "") or ""
|
||||
tools = getattr(agent, "tools", None) or None
|
||||
approx_tokens = estimate_request_tokens_rough(
|
||||
state.history,
|
||||
system_prompt=system_prompt,
|
||||
tools=tools,
|
||||
)
|
||||
except Exception:
|
||||
logger.debug("Could not estimate ACP context usage", exc_info=True)
|
||||
approx_tokens = 0
|
||||
|
||||
if threshold_tokens <= 0 and context_length > 0:
|
||||
threshold_tokens = int(context_length * 0.80)
|
||||
|
||||
lines = [
|
||||
f"Conversation: {n_messages} messages"
|
||||
if n_messages
|
||||
else "Conversation is empty (no messages yet).",
|
||||
f"Conversation: {n_messages} messages",
|
||||
f" user: {roles.get('user', 0)}, assistant: {roles.get('assistant', 0)}, "
|
||||
f"tool: {roles.get('tool', 0)}, system: {roles.get('system', 0)}",
|
||||
]
|
||||
model = state.model or getattr(state.agent, "model", "")
|
||||
if model:
|
||||
lines.append(f"Model: {model}")
|
||||
lines.append(f"Provider: {provider}")
|
||||
|
||||
if approx_tokens > 0:
|
||||
if context_length > 0:
|
||||
usage_pct = (approx_tokens / context_length) * 100
|
||||
lines.append(
|
||||
f"Context usage: ~{approx_tokens:,} / {context_length:,} tokens ({usage_pct:.1f}%)"
|
||||
)
|
||||
else:
|
||||
lines.append(f"Context usage: ~{approx_tokens:,} tokens")
|
||||
|
||||
if threshold_tokens > 0:
|
||||
if approx_tokens > 0:
|
||||
threshold_pct = (threshold_tokens / context_length) * 100 if context_length > 0 else 0
|
||||
remaining = max(threshold_tokens - approx_tokens, 0)
|
||||
if approx_tokens >= threshold_tokens:
|
||||
lines.append(
|
||||
f"Compression: due now (threshold ~{threshold_tokens:,}"
|
||||
+ (f", {threshold_pct:.0f}%" if threshold_pct else "")
|
||||
+ "). Run /compact."
|
||||
)
|
||||
else:
|
||||
lines.append(
|
||||
f"Compression: ~{remaining:,} tokens until threshold "
|
||||
f"(~{threshold_tokens:,}"
|
||||
+ (f", {threshold_pct:.0f}%" if threshold_pct else "")
|
||||
+ ")."
|
||||
)
|
||||
else:
|
||||
lines.append(f"Compression threshold: ~{threshold_tokens:,} tokens")
|
||||
|
||||
if getattr(agent, "compression_enabled", True) is False:
|
||||
lines.append("Compression is disabled for this agent.")
|
||||
else:
|
||||
lines.append("Tip: run /compact to compress manually before the threshold.")
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
def _cmd_reset(self, args: str, state: SessionState) -> str:
|
||||
@@ -1286,16 +975,10 @@ class HermesACPAgent(acp.Agent):
|
||||
if not hasattr(agent, "_compress_context"):
|
||||
return "Context compression not available for this agent."
|
||||
|
||||
from agent.model_metadata import estimate_request_tokens_rough
|
||||
from agent.model_metadata import estimate_messages_tokens_rough
|
||||
|
||||
original_count = len(state.history)
|
||||
# Include system prompt + tool schemas so the figure reflects real
|
||||
# request pressure, not a transcript-only underestimate (#6217).
|
||||
_sys_prompt = getattr(agent, "_cached_system_prompt", "") or ""
|
||||
_tools = getattr(agent, "tools", None) or None
|
||||
approx_tokens = estimate_request_tokens_rough(
|
||||
state.history, system_prompt=_sys_prompt, tools=_tools
|
||||
)
|
||||
approx_tokens = estimate_messages_tokens_rough(state.history)
|
||||
original_session_db = getattr(agent, "_session_db", None)
|
||||
|
||||
try:
|
||||
@@ -1315,13 +998,7 @@ class HermesACPAgent(acp.Agent):
|
||||
self.session_manager.save_session(state.session_id)
|
||||
|
||||
new_count = len(state.history)
|
||||
_sys_prompt_after = getattr(agent, "_cached_system_prompt", "") or _sys_prompt
|
||||
_tools_after = getattr(agent, "tools", None) or _tools
|
||||
new_tokens = estimate_request_tokens_rough(
|
||||
state.history,
|
||||
system_prompt=_sys_prompt_after,
|
||||
tools=_tools_after,
|
||||
)
|
||||
new_tokens = estimate_messages_tokens_rough(state.history)
|
||||
return (
|
||||
f"Context compressed: {original_count} -> {new_count} messages\n"
|
||||
f"~{approx_tokens:,} -> ~{new_tokens:,} tokens"
|
||||
@@ -1329,34 +1006,6 @@ class HermesACPAgent(acp.Agent):
|
||||
except Exception as e:
|
||||
return f"Compression failed: {e}"
|
||||
|
||||
def _cmd_steer(self, args: str, state: SessionState) -> str:
|
||||
steer_text = args.strip()
|
||||
if not steer_text:
|
||||
return "Usage: /steer <guidance>"
|
||||
|
||||
if state.is_running and hasattr(state.agent, "steer"):
|
||||
try:
|
||||
if state.agent.steer(steer_text):
|
||||
preview = steer_text[:80] + ("..." if len(steer_text) > 80 else "")
|
||||
return f"⏩ Steer queued for the active turn: {preview}"
|
||||
except Exception as exc:
|
||||
logger.warning("ACP steer failed for session %s: %s", state.session_id, exc)
|
||||
return f"⚠️ Steer failed: {exc}"
|
||||
|
||||
with state.runtime_lock:
|
||||
state.queued_prompts.append(steer_text)
|
||||
depth = len(state.queued_prompts)
|
||||
return f"No active turn — queued for the next turn. ({depth} queued)"
|
||||
|
||||
def _cmd_queue(self, args: str, state: SessionState) -> str:
|
||||
queued_text = args.strip()
|
||||
if not queued_text:
|
||||
return "Usage: /queue <prompt>"
|
||||
with state.runtime_lock:
|
||||
state.queued_prompts.append(queued_text)
|
||||
depth = len(state.queued_prompts)
|
||||
return f"Queued for the next turn. ({depth} queued)"
|
||||
|
||||
def _cmd_version(self, args: str, state: SessionState) -> str:
|
||||
return f"Hermes Agent v{HERMES_VERSION}"
|
||||
|
||||
|
||||
+7
-46
@@ -26,33 +26,6 @@ from typing import Any, Dict, List, Optional
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _win_path_to_wsl(path: str) -> str | None:
|
||||
"""Convert a Windows drive path to its WSL /mnt/<drive>/... equivalent."""
|
||||
match = re.match(r"^([A-Za-z]):[\\/](.*)$", path)
|
||||
if not match:
|
||||
return None
|
||||
drive = match.group(1).lower()
|
||||
tail = match.group(2).replace("\\", "/")
|
||||
return f"/mnt/{drive}/{tail}"
|
||||
|
||||
|
||||
def _translate_acp_cwd(cwd: str) -> str:
|
||||
"""Translate Windows ACP cwd values when Hermes itself is running in WSL.
|
||||
|
||||
Windows ACP clients can launch ``hermes acp`` inside WSL while still sending
|
||||
editor workspaces as Windows drive paths such as ``E:\\Projects``. Store
|
||||
and execute against the WSL mount path so agents, tools, and persisted ACP
|
||||
sessions all agree on the usable workspace. Native Linux/macOS keeps the
|
||||
original cwd unchanged.
|
||||
"""
|
||||
from hermes_constants import is_wsl
|
||||
|
||||
if not is_wsl():
|
||||
return cwd
|
||||
translated = _win_path_to_wsl(str(cwd))
|
||||
return translated if translated is not None else cwd
|
||||
|
||||
|
||||
def _normalize_cwd_for_compare(cwd: str | None) -> str:
|
||||
raw = str(cwd or ".").strip()
|
||||
if not raw:
|
||||
@@ -61,9 +34,11 @@ def _normalize_cwd_for_compare(cwd: str | None) -> str:
|
||||
|
||||
# Normalize Windows drive paths into the equivalent WSL mount form so
|
||||
# ACP history filters match the same workspace across Windows and WSL.
|
||||
translated = _win_path_to_wsl(expanded)
|
||||
if translated is not None:
|
||||
expanded = translated
|
||||
match = re.match(r"^([A-Za-z]):[\\/](.*)$", expanded)
|
||||
if match:
|
||||
drive = match.group(1).lower()
|
||||
tail = match.group(2).replace("\\", "/")
|
||||
expanded = f"/mnt/{drive}/{tail}"
|
||||
elif re.match(r"^/mnt/[A-Za-z]/", expanded):
|
||||
expanded = f"/mnt/{expanded[5].lower()}/{expanded[7:]}"
|
||||
|
||||
@@ -121,18 +96,12 @@ def _acp_stderr_print(*args, **kwargs) -> None:
|
||||
|
||||
|
||||
def _register_task_cwd(task_id: str, cwd: str) -> None:
|
||||
"""Bind a task/session id to the editor's working directory for tools.
|
||||
|
||||
Zed can launch Hermes from a Windows workspace while the ACP process runs
|
||||
inside WSL. In that case ACP sends cwd as e.g. ``E:\\Projects\\POTI``;
|
||||
local tools need the WSL mount equivalent or subprocess creation fails
|
||||
before the command can run.
|
||||
"""
|
||||
"""Bind a task/session id to the editor's working directory for tools."""
|
||||
if not task_id:
|
||||
return
|
||||
try:
|
||||
from tools.terminal_tool import register_task_env_overrides
|
||||
register_task_env_overrides(task_id, {"cwd": _translate_acp_cwd(cwd)})
|
||||
register_task_env_overrides(task_id, {"cwd": cwd})
|
||||
except Exception:
|
||||
logger.debug("Failed to register ACP task cwd override", exc_info=True)
|
||||
|
||||
@@ -176,11 +145,6 @@ class SessionState:
|
||||
model: str = ""
|
||||
history: List[Dict[str, Any]] = field(default_factory=list)
|
||||
cancel_event: Any = None # threading.Event
|
||||
is_running: bool = False
|
||||
queued_prompts: List[str] = field(default_factory=list)
|
||||
runtime_lock: Any = field(default_factory=Lock)
|
||||
current_prompt_text: str = ""
|
||||
interrupted_prompt_text: str = ""
|
||||
|
||||
|
||||
class SessionManager:
|
||||
@@ -211,7 +175,6 @@ class SessionManager:
|
||||
"""Create a new session with a unique ID and a fresh AIAgent."""
|
||||
import threading
|
||||
|
||||
cwd = _translate_acp_cwd(cwd)
|
||||
session_id = str(uuid.uuid4())
|
||||
agent = self._make_agent(session_id=session_id, cwd=cwd)
|
||||
state = SessionState(
|
||||
@@ -254,7 +217,6 @@ class SessionManager:
|
||||
"""Deep-copy a session's history into a new session."""
|
||||
import threading
|
||||
|
||||
cwd = _translate_acp_cwd(cwd)
|
||||
original = self.get_session(session_id) # checks DB too
|
||||
if original is None:
|
||||
return None
|
||||
@@ -356,7 +318,6 @@ class SessionManager:
|
||||
|
||||
def update_cwd(self, session_id: str, cwd: str) -> Optional[SessionState]:
|
||||
"""Update the working directory for a session and its tool overrides."""
|
||||
cwd = _translate_acp_cwd(cwd)
|
||||
state = self.get_session(session_id) # checks DB too
|
||||
if state is None:
|
||||
return None
|
||||
|
||||
+21
-822
@@ -28,11 +28,6 @@ TOOL_KIND_MAP: Dict[str, ToolKind] = {
|
||||
"terminal": "execute",
|
||||
"process": "execute",
|
||||
"execute_code": "execute",
|
||||
# Session/meta tools
|
||||
"todo": "other",
|
||||
"skill_view": "read",
|
||||
"skills_list": "read",
|
||||
"skill_manage": "edit",
|
||||
# Web / fetch
|
||||
"web_search": "fetch",
|
||||
"web_extract": "fetch",
|
||||
@@ -56,28 +51,6 @@ TOOL_KIND_MAP: Dict[str, ToolKind] = {
|
||||
}
|
||||
|
||||
|
||||
_POLISHED_TOOLS = {
|
||||
# Core operator loop
|
||||
"todo", "memory", "session_search", "delegate_task",
|
||||
# Files / execution
|
||||
"read_file", "write_file", "patch", "search_files", "terminal", "process", "execute_code",
|
||||
# Skills / web / browser / media
|
||||
"skill_view", "skills_list", "skill_manage", "web_search", "web_extract",
|
||||
"browser_navigate", "browser_click", "browser_type", "browser_press", "browser_scroll",
|
||||
"browser_back", "browser_snapshot", "browser_console", "browser_get_images", "browser_vision",
|
||||
"vision_analyze", "image_generate", "text_to_speech",
|
||||
# Schedulers / platform integrations
|
||||
"cronjob", "send_message", "clarify", "discord", "discord_admin",
|
||||
"ha_list_entities", "ha_get_state", "ha_list_services", "ha_call_service",
|
||||
"feishu_doc_read", "feishu_drive_list_comments", "feishu_drive_list_comment_replies",
|
||||
"feishu_drive_reply_comment", "feishu_drive_add_comment",
|
||||
"kanban_create", "kanban_show", "kanban_comment", "kanban_complete",
|
||||
"kanban_block", "kanban_link", "kanban_heartbeat",
|
||||
"yb_query_group_info", "yb_query_group_members", "yb_search_sticker",
|
||||
"yb_send_dm", "yb_send_sticker", "mixture_of_agents",
|
||||
}
|
||||
|
||||
|
||||
def get_tool_kind(tool_name: str) -> ToolKind:
|
||||
"""Return the ACP ToolKind for a hermes tool, defaulting to 'other'."""
|
||||
return TOOL_KIND_MAP.get(tool_name, "other")
|
||||
@@ -112,645 +85,18 @@ def build_tool_title(tool_name: str, args: Dict[str, Any]) -> str:
|
||||
if urls:
|
||||
return f"extract: {urls[0]}" + (f" (+{len(urls)-1})" if len(urls) > 1 else "")
|
||||
return "web extract"
|
||||
if tool_name == "process":
|
||||
action = str(args.get("action") or "").strip() or "manage"
|
||||
sid = str(args.get("session_id") or "").strip()
|
||||
return f"process {action}: {sid}" if sid else f"process {action}"
|
||||
if tool_name == "delegate_task":
|
||||
tasks = args.get("tasks")
|
||||
if isinstance(tasks, list) and tasks:
|
||||
return f"delegate batch ({len(tasks)} tasks)"
|
||||
goal = args.get("goal", "")
|
||||
if goal and len(goal) > 60:
|
||||
goal = goal[:57] + "..."
|
||||
return f"delegate: {goal}" if goal else "delegate task"
|
||||
if tool_name == "session_search":
|
||||
query = str(args.get("query") or "").strip()
|
||||
return f"session search: {query}" if query else "recent sessions"
|
||||
if tool_name == "memory":
|
||||
action = str(args.get("action") or "manage").strip() or "manage"
|
||||
target = str(args.get("target") or "memory").strip() or "memory"
|
||||
return f"memory {action}: {target}"
|
||||
if tool_name == "execute_code":
|
||||
code = str(args.get("code") or "").strip()
|
||||
first_line = next((line.strip() for line in code.splitlines() if line.strip()), "")
|
||||
if first_line:
|
||||
if len(first_line) > 70:
|
||||
first_line = first_line[:67] + "..."
|
||||
return f"python: {first_line}"
|
||||
return "python code"
|
||||
if tool_name == "todo":
|
||||
items = args.get("todos")
|
||||
if isinstance(items, list):
|
||||
return f"todo ({len(items)} item{'s' if len(items) != 1 else ''})"
|
||||
return "todo"
|
||||
if tool_name == "skill_view":
|
||||
name = str(args.get("name") or "?").strip() or "?"
|
||||
file_path = str(args.get("file_path") or "").strip()
|
||||
suffix = f"/{file_path}" if file_path else ""
|
||||
return f"skill view ({name}{suffix})"
|
||||
if tool_name == "skills_list":
|
||||
category = str(args.get("category") or "").strip()
|
||||
return f"skills list ({category})" if category else "skills list"
|
||||
if tool_name == "skill_manage":
|
||||
action = str(args.get("action") or "manage").strip() or "manage"
|
||||
name = str(args.get("name") or "?").strip() or "?"
|
||||
file_path = str(args.get("file_path") or "").strip()
|
||||
target = f"{name}/{file_path}" if file_path else name
|
||||
if len(target) > 64:
|
||||
target = target[:61] + "..."
|
||||
return f"skill {action}: {target}"
|
||||
if tool_name == "browser_navigate":
|
||||
return f"navigate: {args.get('url', '?')}"
|
||||
if tool_name == "browser_snapshot":
|
||||
return "browser snapshot"
|
||||
if tool_name == "browser_vision":
|
||||
return f"browser vision: {str(args.get('question', '?'))[:50]}"
|
||||
if tool_name == "browser_get_images":
|
||||
return "browser images"
|
||||
return "execute code"
|
||||
if tool_name == "vision_analyze":
|
||||
return f"analyze image: {str(args.get('question', '?'))[:50]}"
|
||||
if tool_name == "image_generate":
|
||||
prompt = str(args.get("prompt") or args.get("description") or "").strip()
|
||||
return f"generate image: {prompt[:50]}" if prompt else "generate image"
|
||||
if tool_name == "cronjob":
|
||||
action = str(args.get("action") or "manage").strip() or "manage"
|
||||
job_id = str(args.get("job_id") or args.get("id") or "").strip()
|
||||
return f"cron {action}: {job_id}" if job_id else f"cron {action}"
|
||||
return f"analyze image: {args.get('question', '?')[:50]}"
|
||||
return tool_name
|
||||
|
||||
|
||||
def _text(content: str) -> Any:
|
||||
return acp.tool_content(acp.text_block(content))
|
||||
|
||||
|
||||
def _json_loads_maybe(value: Optional[str]) -> Any:
|
||||
if not isinstance(value, str):
|
||||
return value
|
||||
try:
|
||||
return json.loads(value)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Some Hermes tools append a human hint after a JSON payload, e.g.
|
||||
# ``{...}\n\n[Hint: Results truncated...]``. Keep the structured rendering path
|
||||
# by decoding the first JSON value instead of falling back to raw text.
|
||||
try:
|
||||
decoded, _ = json.JSONDecoder().raw_decode(value.lstrip())
|
||||
return decoded
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
def _truncate_text(text: str, limit: int = 5000) -> str:
|
||||
if len(text) <= limit:
|
||||
return text
|
||||
return text[: max(0, limit - 100)] + f"\n... ({len(text)} chars total, truncated)"
|
||||
|
||||
|
||||
def _fenced_text(text: str, language: str = "") -> str:
|
||||
"""Return a Markdown fence that cannot be broken by backticks in text."""
|
||||
longest = max((len(run) for run in text.split("`")[1::2]), default=0)
|
||||
fence = "`" * max(3, longest + 1)
|
||||
return f"{fence}{language}\n{text}\n{fence}"
|
||||
|
||||
|
||||
def _format_todo_result(result: Optional[str]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict) or not isinstance(data.get("todos"), list):
|
||||
return None
|
||||
summary = data.get("summary") if isinstance(data.get("summary"), dict) else {}
|
||||
icon = {
|
||||
"completed": "✅",
|
||||
"in_progress": "🔄",
|
||||
"pending": "⏳",
|
||||
"cancelled": "✗",
|
||||
}
|
||||
lines = ["**Todo list**", ""]
|
||||
for item in data["todos"]:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
status = str(item.get("status") or "pending")
|
||||
content = str(item.get("content") or item.get("id") or "").strip()
|
||||
if content:
|
||||
lines.append(f"- {icon.get(status, '•')} {content}")
|
||||
if summary:
|
||||
cancelled = summary.get("cancelled", 0)
|
||||
lines.extend([
|
||||
"",
|
||||
"**Progress:** "
|
||||
f"{summary.get('completed', 0)} completed, "
|
||||
f"{summary.get('in_progress', 0)} in progress, "
|
||||
f"{summary.get('pending', 0)} pending"
|
||||
+ (f", {cancelled} cancelled" if cancelled else ""),
|
||||
])
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def _format_read_file_result(result: Optional[str], args: Optional[Dict[str, Any]]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return None
|
||||
if data.get("error") and not data.get("content"):
|
||||
return f"Read failed: {data.get('error')}"
|
||||
content = data.get("content")
|
||||
if not isinstance(content, str):
|
||||
return None
|
||||
path = str((args or {}).get("path") or data.get("path") or "file").strip()
|
||||
offset = (args or {}).get("offset")
|
||||
limit = (args or {}).get("limit")
|
||||
range_bits = []
|
||||
if offset:
|
||||
range_bits.append(f"from line {offset}")
|
||||
if limit:
|
||||
range_bits.append(f"limit {limit}")
|
||||
suffix = f" ({', '.join(range_bits)})" if range_bits else ""
|
||||
header = f"Read {path}{suffix}"
|
||||
if data.get("total_lines") is not None:
|
||||
header += f" — {data.get('total_lines')} total lines"
|
||||
# Hermes read_file output is line-numbered with `|`. If we send it as raw
|
||||
# Markdown, Zed can interpret pipes as tables and collapse the layout.
|
||||
# Fence the payload so file lines stay readable and literal.
|
||||
return _truncate_text(f"{header}\n\n{_fenced_text(content)}")
|
||||
|
||||
|
||||
def _format_search_files_result(result: Optional[str]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return None
|
||||
matches = data.get("matches")
|
||||
if not isinstance(matches, list):
|
||||
return None
|
||||
|
||||
total = data.get("total_count", len(matches))
|
||||
shown = min(len(matches), 12)
|
||||
truncated = bool(data.get("truncated")) or len(matches) > shown
|
||||
lines = [
|
||||
"Search results",
|
||||
f"Found {total} match{'es' if total != 1 else ''}; showing {shown}.",
|
||||
"",
|
||||
]
|
||||
|
||||
for match in matches[:shown]:
|
||||
if not isinstance(match, dict):
|
||||
lines.append(f"- {match}")
|
||||
continue
|
||||
|
||||
path = str(match.get("path") or match.get("file") or match.get("filename") or "?")
|
||||
line = match.get("line") or match.get("line_number")
|
||||
content = str(match.get("content") or match.get("text") or "").strip()
|
||||
loc = f"{path}:{line}" if line else path
|
||||
lines.append(f"- {loc}")
|
||||
if content:
|
||||
snippet = _truncate_text(" ".join(content.split()), 300)
|
||||
lines.append(f" {snippet}")
|
||||
|
||||
if truncated:
|
||||
lines.extend([
|
||||
"",
|
||||
"Results truncated. Narrow the search, add file_glob, or use offset to page.",
|
||||
])
|
||||
return _truncate_text("\n".join(lines), limit=7000)
|
||||
|
||||
|
||||
def _format_execute_code_result(result: Optional[str]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return result if isinstance(result, str) and result.strip() else None
|
||||
output = str(data.get("output") or "")
|
||||
error = str(data.get("error") or "")
|
||||
exit_code = data.get("exit_code")
|
||||
parts = [f"Exit code: {exit_code}" if exit_code is not None else "Execution complete"]
|
||||
if output:
|
||||
parts.extend(["", "Output:", output])
|
||||
if error:
|
||||
parts.extend(["", "Error:", error])
|
||||
return _truncate_text("\n".join(parts))
|
||||
|
||||
|
||||
def _extract_markdown_headings(content: str, limit: int = 8) -> list[str]:
|
||||
headings: list[str] = []
|
||||
for line in content.splitlines():
|
||||
stripped = line.strip()
|
||||
if stripped.startswith("#"):
|
||||
heading = stripped.lstrip("#").strip()
|
||||
if heading:
|
||||
headings.append(heading)
|
||||
if len(headings) >= limit:
|
||||
break
|
||||
return headings
|
||||
|
||||
|
||||
def _format_skill_view_result(result: Optional[str]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return None
|
||||
if data.get("success") is False:
|
||||
return f"Skill view failed: {data.get('error', 'unknown error')}"
|
||||
name = str(data.get("name") or "skill")
|
||||
file_path = str(data.get("file") or data.get("path") or "SKILL.md")
|
||||
description = str(data.get("description") or "").strip()
|
||||
content = str(data.get("content") or "")
|
||||
linked = data.get("linked_files") if isinstance(data.get("linked_files"), dict) else None
|
||||
|
||||
lines = ["**Skill loaded**", "", f"- **Name:** `{name}`", f"- **File:** `{file_path}`"]
|
||||
if description:
|
||||
lines.append(f"- **Description:** {description}")
|
||||
if content:
|
||||
lines.append(f"- **Content:** {len(content):,} chars loaded into agent context")
|
||||
if linked:
|
||||
linked_count = sum(len(v) for v in linked.values() if isinstance(v, list))
|
||||
lines.append(f"- **Linked files:** {linked_count}")
|
||||
|
||||
headings = _extract_markdown_headings(content)
|
||||
if headings:
|
||||
lines.extend(["", "**Sections**"])
|
||||
lines.extend(f"- {heading}" for heading in headings)
|
||||
|
||||
lines.extend([
|
||||
"",
|
||||
"_Full skill content is available to the agent but hidden here to keep ACP readable._",
|
||||
])
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def _format_skill_manage_result(result: Optional[str], args: Optional[Dict[str, Any]]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return None
|
||||
|
||||
action = str((args or {}).get("action") or "manage").strip() or "manage"
|
||||
name = str((args or {}).get("name") or data.get("name") or "skill").strip() or "skill"
|
||||
file_path = str((args or {}).get("file_path") or data.get("file_path") or "SKILL.md").strip() or "SKILL.md"
|
||||
success = data.get("success")
|
||||
status = "✅ Skill updated" if success is not False else "✗ Skill update failed"
|
||||
|
||||
lines = [f"**{status}**", "", f"- **Action:** `{action}`", f"- **Skill:** `{name}`"]
|
||||
if action not in {"delete"}:
|
||||
lines.append(f"- **File:** `{file_path}`")
|
||||
|
||||
message = str(data.get("message") or data.get("error") or "").strip()
|
||||
if message:
|
||||
lines.append(f"- **Result:** {message}")
|
||||
|
||||
replacements = data.get("replacements") or data.get("replacement_count")
|
||||
if replacements is not None:
|
||||
lines.append(f"- **Replacements:** {replacements}")
|
||||
|
||||
path = str(data.get("path") or "").strip()
|
||||
if path:
|
||||
lines.append(f"- **Path:** `{path}`")
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def _format_web_search_result(result: Optional[str]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return None
|
||||
web = data.get("data", {}).get("web") if isinstance(data.get("data"), dict) else data.get("web")
|
||||
if not isinstance(web, list):
|
||||
return None
|
||||
lines = [f"Web results: {len(web)}"]
|
||||
for item in web[:10]:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
title = str(item.get("title") or item.get("url") or "result").strip()
|
||||
url = str(item.get("url") or "").strip()
|
||||
desc = str(item.get("description") or "").strip()
|
||||
lines.append(f"• {title}" + (f" — {url}" if url else ""))
|
||||
if desc:
|
||||
lines.append(f" {desc}")
|
||||
return _truncate_text("\n".join(lines))
|
||||
|
||||
|
||||
def _format_web_extract_result(result: Optional[str]) -> Optional[str]:
|
||||
"""Return only web_extract errors for ACP; success stays compact via title."""
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return None
|
||||
if data.get("success") is False and data.get("error"):
|
||||
return f"Web extract failed: {data.get('error')}"
|
||||
results = data.get("results")
|
||||
if not isinstance(results, list):
|
||||
return None
|
||||
|
||||
failures: list[str] = []
|
||||
for item in results[:10]:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
error = str(item.get("error") or "").strip()
|
||||
if not error or error in {"None", "null"}:
|
||||
continue
|
||||
url = str(item.get("url") or "").strip()
|
||||
title = str(item.get("title") or url or "Untitled").strip()
|
||||
failures.append(
|
||||
f"- {title}" + (f" — {url}" if url and url != title else "") + f"\n Error: {_truncate_text(error, limit=500)}"
|
||||
)
|
||||
|
||||
if not failures:
|
||||
return None
|
||||
lines = [f"Web extract failed for {len(failures)} URL{'s' if len(failures) != 1 else ''}"]
|
||||
lines.extend(failures)
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def _format_process_result(result: Optional[str], args: Optional[Dict[str, Any]]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return result if isinstance(result, str) and result.strip() else None
|
||||
if data.get("success") is False and data.get("error"):
|
||||
return f"Process error: {data.get('error')}"
|
||||
action = str((args or {}).get("action") or "process").strip() or "process"
|
||||
if isinstance(data.get("processes"), list):
|
||||
processes = data["processes"]
|
||||
lines = [f"Processes: {len(processes)}"]
|
||||
for proc in processes[:20]:
|
||||
if not isinstance(proc, dict):
|
||||
lines.append(f"- {proc}")
|
||||
continue
|
||||
sid = str(proc.get("session_id") or proc.get("id") or "?")
|
||||
status = str(proc.get("status") or ("exited" if proc.get("exited") else "running"))
|
||||
cmd = str(proc.get("command") or "").strip()
|
||||
pid = proc.get("pid")
|
||||
code = proc.get("exit_code")
|
||||
bits = [status]
|
||||
if pid is not None:
|
||||
bits.append(f"pid {pid}")
|
||||
if code is not None:
|
||||
bits.append(f"exit {code}")
|
||||
lines.append(f"- `{sid}` — {', '.join(bits)}" + (f" — {cmd[:120]}" if cmd else ""))
|
||||
if len(processes) > 20:
|
||||
lines.append(f"... {len(processes) - 20} more process(es)")
|
||||
return "\n".join(lines)
|
||||
|
||||
status = str(data.get("status") or data.get("state") or action).strip()
|
||||
sid = str(data.get("session_id") or (args or {}).get("session_id") or "").strip()
|
||||
lines = [f"Process {action}: {status}" + (f" (`{sid}`)" if sid else "")]
|
||||
for key, label in (("command", "Command"), ("pid", "PID"), ("exit_code", "Exit code"), ("returncode", "Exit code"), ("lines", "Lines")):
|
||||
if data.get(key) is not None:
|
||||
lines.append(f"- **{label}:** {data.get(key)}")
|
||||
output = data.get("output") or data.get("new_output") or data.get("log") or data.get("stdout")
|
||||
error = data.get("error") or data.get("stderr")
|
||||
if output:
|
||||
lines.extend(["", "Output:", _truncate_text(str(output), limit=5000)])
|
||||
if error:
|
||||
lines.extend(["", "Error:", _truncate_text(str(error), limit=2000)])
|
||||
msg = data.get("message")
|
||||
if msg and not output and not error:
|
||||
lines.append(str(msg))
|
||||
return _truncate_text("\n".join(lines), limit=7000)
|
||||
|
||||
|
||||
def _format_delegate_result(result: Optional[str]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return None
|
||||
if data.get("error") and not isinstance(data.get("results"), list):
|
||||
return f"Delegation failed: {data.get('error')}"
|
||||
results = data.get("results")
|
||||
if not isinstance(results, list):
|
||||
return None
|
||||
total = data.get("total_duration_seconds")
|
||||
lines = [f"Delegation results: {len(results)} task{'s' if len(results) != 1 else ''}" + (f" in {total}s" if total is not None else "")]
|
||||
icon = {"completed": "✅", "failed": "✗", "error": "✗", "timeout": "⏱", "interrupted": "⚠"}
|
||||
for item in results:
|
||||
if not isinstance(item, dict):
|
||||
lines.append(f"- {item}")
|
||||
continue
|
||||
idx = item.get("task_index")
|
||||
status = str(item.get("status") or "unknown")
|
||||
model = item.get("model")
|
||||
dur = item.get("duration_seconds")
|
||||
role = item.get("_child_role")
|
||||
header = f"{icon.get(status, '•')} Task {idx + 1 if isinstance(idx, int) else '?'}: {status}"
|
||||
bits = []
|
||||
if model:
|
||||
bits.append(str(model))
|
||||
if role:
|
||||
bits.append(f"role={role}")
|
||||
if dur is not None:
|
||||
bits.append(f"{dur}s")
|
||||
if bits:
|
||||
header += " (" + ", ".join(bits) + ")"
|
||||
lines.extend(["", header])
|
||||
summary = str(item.get("summary") or "").strip()
|
||||
error = str(item.get("error") or "").strip()
|
||||
if summary:
|
||||
lines.append(_truncate_text(summary, limit=1200))
|
||||
if error:
|
||||
lines.append("Error: " + _truncate_text(error, limit=800))
|
||||
trace = item.get("tool_trace")
|
||||
if isinstance(trace, list) and trace:
|
||||
names = [str(t.get("tool") or "?") for t in trace if isinstance(t, dict)]
|
||||
if names:
|
||||
lines.append("Tools: " + ", ".join(names[:12]) + (f" (+{len(names)-12})" if len(names) > 12 else ""))
|
||||
return _truncate_text("\n".join(lines), limit=8000)
|
||||
|
||||
|
||||
def _format_session_search_result(result: Optional[str]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return None
|
||||
if data.get("success") is False:
|
||||
return f"Session search failed: {data.get('error', 'unknown error')}"
|
||||
results = data.get("results")
|
||||
if not isinstance(results, list):
|
||||
return None
|
||||
mode = data.get("mode") or "search"
|
||||
query = data.get("query")
|
||||
lines = ["Recent sessions" if mode == "recent" else f"Session search results" + (f" for `{query}`" if query else "")]
|
||||
if not results:
|
||||
lines.append(str(data.get("message") or "No matching sessions found."))
|
||||
return "\n".join(lines)
|
||||
for item in results:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
sid = str(item.get("session_id") or "?")
|
||||
title = str(item.get("title") or item.get("when") or "Untitled session").strip()
|
||||
when = str(item.get("last_active") or item.get("started_at") or item.get("when") or "").strip()
|
||||
count = item.get("message_count")
|
||||
source = str(item.get("source") or "").strip()
|
||||
meta = ", ".join(str(x) for x in [when, source, f"{count} msgs" if count is not None else ""] if x)
|
||||
lines.append(f"- **{title}** (`{sid}`)" + (f" — {meta}" if meta else ""))
|
||||
summary = str(item.get("summary") or item.get("preview") or "").strip()
|
||||
if summary:
|
||||
lines.append(" " + _truncate_text(" ".join(summary.split()), limit=500))
|
||||
return _truncate_text("\n".join(lines), limit=7000)
|
||||
|
||||
|
||||
def _format_memory_result(result: Optional[str], args: Optional[Dict[str, Any]]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return None
|
||||
action = str((args or {}).get("action") or "memory").strip() or "memory"
|
||||
target = str(data.get("target") or (args or {}).get("target") or "memory")
|
||||
if data.get("success") is False:
|
||||
lines = [f"✗ Memory {action} failed ({target})", str(data.get("error") or "unknown error")]
|
||||
matches = data.get("matches")
|
||||
if isinstance(matches, list) and matches:
|
||||
lines.append("Matches:")
|
||||
lines.extend(f"- {_truncate_text(str(m), 160)}" for m in matches[:5])
|
||||
return "\n".join(lines)
|
||||
lines = [f"✅ Memory {action} saved ({target})"]
|
||||
if data.get("message"):
|
||||
lines.append(str(data.get("message")))
|
||||
if data.get("entry_count") is not None:
|
||||
lines.append(f"Entries: {data.get('entry_count')}")
|
||||
if data.get("usage"):
|
||||
lines.append(f"Usage: {data.get('usage')}")
|
||||
# Avoid dumping all memory entries into ACP UI; show only the explicit new value preview.
|
||||
preview = str((args or {}).get("content") or (args or {}).get("old_text") or "").strip()
|
||||
if preview:
|
||||
lines.append("Preview: " + _truncate_text(preview, limit=300))
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def _format_edit_result(tool_name: str, result: Optional[str], args: Optional[Dict[str, Any]]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
path = str((args or {}).get("path") or "file").strip()
|
||||
if isinstance(data, dict):
|
||||
if data.get("success") is False or data.get("error"):
|
||||
return f"{tool_name} failed for {path}: {data.get('error', 'unknown error')}"
|
||||
message = str(data.get("message") or "").strip()
|
||||
replacements = data.get("replacements") or data.get("replacement_count")
|
||||
lines = [f"✅ {tool_name} completed" + (f" for `{path}`" if path else "")]
|
||||
if message:
|
||||
lines.append(message)
|
||||
if replacements is not None:
|
||||
lines.append(f"Replacements: {replacements}")
|
||||
if data.get("files_modified"):
|
||||
files = data.get("files_modified")
|
||||
if isinstance(files, list):
|
||||
lines.append("Files: " + ", ".join(f"`{f}`" for f in files[:8]))
|
||||
return "\n".join(lines)
|
||||
if isinstance(result, str) and result.strip():
|
||||
return _truncate_text(result, limit=3000)
|
||||
return f"✅ {tool_name} completed" + (f" for `{path}`" if path else "")
|
||||
|
||||
|
||||
def _format_browser_result(tool_name: str, result: Optional[str], args: Optional[Dict[str, Any]]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return result if isinstance(result, str) and result.strip() else None
|
||||
if data.get("success") is False or data.get("error"):
|
||||
return f"{tool_name} failed: {data.get('error', 'unknown error')}"
|
||||
if tool_name == "browser_get_images":
|
||||
images = data.get("images") or data.get("data")
|
||||
if isinstance(images, list):
|
||||
lines = [f"Images found: {len(images)}"]
|
||||
for img in images[:12]:
|
||||
if isinstance(img, dict):
|
||||
alt = str(img.get("alt") or "").strip()
|
||||
url = str(img.get("url") or img.get("src") or "").strip()
|
||||
lines.append(f"- {alt or 'image'}" + (f" — {url}" if url else ""))
|
||||
return _truncate_text("\n".join(lines), limit=5000)
|
||||
title = str(data.get("title") or data.get("url") or data.get("status") or tool_name)
|
||||
text = str(data.get("text") or data.get("content") or data.get("snapshot") or data.get("analysis") or data.get("message") or "").strip()
|
||||
lines = [title]
|
||||
if data.get("url") and data.get("url") != title:
|
||||
lines.append(str(data.get("url")))
|
||||
if text:
|
||||
lines.extend(["", _truncate_text(text, limit=5000)])
|
||||
return _truncate_text("\n".join(lines), limit=7000)
|
||||
|
||||
|
||||
def _format_media_or_cron_result(tool_name: str, result: Optional[str]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return result if isinstance(result, str) and result.strip() else None
|
||||
if data.get("success") is False or data.get("error"):
|
||||
return f"{tool_name} failed: {data.get('error', 'unknown error')}"
|
||||
lines = [f"✅ {tool_name} completed"]
|
||||
for key in ("file_path", "path", "url", "image_url", "job_id", "id", "status", "message", "next_run"):
|
||||
if data.get(key):
|
||||
lines.append(f"- **{key}:** {data.get(key)}")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def _format_generic_structured_result(tool_name: str, result: Optional[str]) -> Optional[str]:
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, (dict, list)):
|
||||
return result if isinstance(result, str) and result.strip() else None
|
||||
if isinstance(data, list):
|
||||
lines = [f"{tool_name}: {len(data)} item{'s' if len(data) != 1 else ''}"]
|
||||
for item in data[:12]:
|
||||
lines.append(f"- {_truncate_text(str(item), limit=240)}")
|
||||
return _truncate_text("\n".join(lines), limit=5000)
|
||||
|
||||
if data.get("success") is False or data.get("error"):
|
||||
return f"{tool_name} failed: {data.get('error', 'unknown error')}"
|
||||
|
||||
lines = [f"✅ {tool_name} completed" if data.get("success") is True else f"{tool_name} result"]
|
||||
priority_keys = (
|
||||
"message", "status", "id", "task_id", "issue_id", "title", "name", "entity_id",
|
||||
"state", "service", "url", "path", "file_path", "count", "total", "next_run",
|
||||
)
|
||||
seen = set()
|
||||
for key in priority_keys:
|
||||
value = data.get(key)
|
||||
if value in (None, "", [], {}):
|
||||
continue
|
||||
seen.add(key)
|
||||
lines.append(f"- **{key}:** {_truncate_text(str(value), limit=500)}")
|
||||
|
||||
for key, value in data.items():
|
||||
if key in seen or key in {"success", "raw", "content", "entries"}:
|
||||
continue
|
||||
if value in (None, "", [], {}):
|
||||
continue
|
||||
if isinstance(value, (dict, list)):
|
||||
preview = json.dumps(value, ensure_ascii=False, default=str)
|
||||
else:
|
||||
preview = str(value)
|
||||
lines.append(f"- **{key}:** {_truncate_text(preview, limit=500)}")
|
||||
if len(lines) >= 14:
|
||||
break
|
||||
|
||||
content = data.get("content")
|
||||
if isinstance(content, str) and content.strip():
|
||||
lines.extend(["", _truncate_text(content.strip(), limit=1500)])
|
||||
return _truncate_text("\n".join(lines), limit=7000)
|
||||
|
||||
|
||||
def _build_polished_completion_content(
|
||||
tool_name: str,
|
||||
result: Optional[str],
|
||||
function_args: Optional[Dict[str, Any]],
|
||||
) -> Optional[List[Any]]:
|
||||
formatter = {
|
||||
"todo": lambda: _format_todo_result(result),
|
||||
"read_file": lambda: _format_read_file_result(result, function_args),
|
||||
"write_file": lambda: _format_edit_result(tool_name, result, function_args),
|
||||
"patch": lambda: _format_edit_result(tool_name, result, function_args),
|
||||
"search_files": lambda: _format_search_files_result(result),
|
||||
"execute_code": lambda: _format_execute_code_result(result),
|
||||
"process": lambda: _format_process_result(result, function_args),
|
||||
"delegate_task": lambda: _format_delegate_result(result),
|
||||
"session_search": lambda: _format_session_search_result(result),
|
||||
"memory": lambda: _format_memory_result(result, function_args),
|
||||
"skill_view": lambda: _format_skill_view_result(result),
|
||||
"skill_manage": lambda: _format_skill_manage_result(result, function_args),
|
||||
"web_search": lambda: _format_web_search_result(result),
|
||||
"web_extract": lambda: _format_web_extract_result(result),
|
||||
"browser_navigate": lambda: _format_browser_result(tool_name, result, function_args),
|
||||
"browser_snapshot": lambda: _format_browser_result(tool_name, result, function_args),
|
||||
"browser_vision": lambda: _format_browser_result(tool_name, result, function_args),
|
||||
"browser_get_images": lambda: _format_browser_result(tool_name, result, function_args),
|
||||
"vision_analyze": lambda: _format_media_or_cron_result(tool_name, result),
|
||||
"image_generate": lambda: _format_media_or_cron_result(tool_name, result),
|
||||
"cronjob": lambda: _format_media_or_cron_result(tool_name, result),
|
||||
}.get(tool_name)
|
||||
if formatter is None and tool_name in _POLISHED_TOOLS:
|
||||
formatter = lambda: _format_generic_structured_result(tool_name, result)
|
||||
if formatter is None:
|
||||
return None
|
||||
text = formatter()
|
||||
if not text:
|
||||
return None
|
||||
return [_text(text)]
|
||||
|
||||
|
||||
def _build_patch_mode_content(patch_text: str) -> List[Any]:
|
||||
"""Parse V4A patch mode input into ACP diff blocks when possible."""
|
||||
if not patch_text:
|
||||
@@ -912,11 +258,7 @@ def _build_tool_complete_content(
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
polished_content = _build_polished_completion_content(tool_name, result, function_args)
|
||||
if polished_content:
|
||||
return polished_content
|
||||
|
||||
return [_text(display_result)]
|
||||
return [acp.tool_content(acp.text_block(display_result))]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -946,6 +288,7 @@ def build_tool_start(
|
||||
content = _build_patch_mode_content(patch_text)
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
raw_input=arguments,
|
||||
)
|
||||
|
||||
if tool_name == "write_file":
|
||||
@@ -954,172 +297,32 @@ def build_tool_start(
|
||||
content = [acp.tool_diff_content(path=path, new_text=file_content)]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
raw_input=arguments,
|
||||
)
|
||||
|
||||
if tool_name == "terminal":
|
||||
command = arguments.get("command", "")
|
||||
content = [_text(f"$ {command}")]
|
||||
content = [acp.tool_content(acp.text_block(f"$ {command}"))]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
raw_input=arguments,
|
||||
)
|
||||
|
||||
if tool_name == "read_file":
|
||||
# The title and location already identify the file. Sending a synthetic
|
||||
# "Reading ..." content block makes Zed render an unhelpful Output
|
||||
# section before the real file contents arrive on completion.
|
||||
path = arguments.get("path", "")
|
||||
content = [acp.tool_content(acp.text_block(f"Reading {path}"))]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=None, locations=locations,
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
raw_input=arguments,
|
||||
)
|
||||
|
||||
if tool_name == "search_files":
|
||||
pattern = arguments.get("pattern", "")
|
||||
target = arguments.get("target", "content")
|
||||
search_path = arguments.get("path")
|
||||
where = f" in {search_path}" if search_path else ""
|
||||
content = [_text(f"Searching for '{pattern}' ({target}){where}")]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
)
|
||||
|
||||
if tool_name == "todo":
|
||||
items = arguments.get("todos")
|
||||
if isinstance(items, list):
|
||||
preview_lines = ["Updating todo list", ""]
|
||||
for item in items[:8]:
|
||||
if isinstance(item, dict):
|
||||
preview_lines.append(f"- {item.get('status', 'pending')}: {item.get('content', item.get('id', ''))}")
|
||||
if len(items) > 8:
|
||||
preview_lines.append(f"... {len(items) - 8} more")
|
||||
content = [_text("\n".join(preview_lines))]
|
||||
else:
|
||||
content = [_text("Reading todo list")]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
)
|
||||
|
||||
if tool_name == "skill_view":
|
||||
name = str(arguments.get("name") or "?").strip() or "?"
|
||||
file_path = str(arguments.get("file_path") or "SKILL.md").strip() or "SKILL.md"
|
||||
content = [_text(f"Loading skill '{name}' ({file_path})")]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
)
|
||||
|
||||
if tool_name == "skill_manage":
|
||||
action = str(arguments.get("action") or "manage").strip() or "manage"
|
||||
name = str(arguments.get("name") or "?").strip() or "?"
|
||||
file_path = str(arguments.get("file_path") or "SKILL.md").strip() or "SKILL.md"
|
||||
path = f"skills/{name}/{file_path}" if file_path else f"skills/{name}"
|
||||
|
||||
if action == "patch":
|
||||
old = str(arguments.get("old_string") or "")
|
||||
new = str(arguments.get("new_string") or "")
|
||||
content = [acp.tool_diff_content(path=path, old_text=old or None, new_text=new)]
|
||||
elif action in {"edit", "create"}:
|
||||
content = [
|
||||
acp.tool_diff_content(
|
||||
path=path,
|
||||
new_text=str(arguments.get("content") or ""),
|
||||
)
|
||||
]
|
||||
elif action == "write_file":
|
||||
target = str(arguments.get("file_path") or "file")
|
||||
content = [
|
||||
acp.tool_diff_content(
|
||||
path=f"skills/{name}/{target}",
|
||||
new_text=str(arguments.get("file_content") or ""),
|
||||
)
|
||||
]
|
||||
elif action in {"delete", "remove_file"}:
|
||||
target = str(arguments.get("file_path") or file_path or name)
|
||||
content = [_text(f"Removing {target} from skill '{name}'")]
|
||||
else:
|
||||
content = [_text(f"Running skill_manage action '{action}' on skill '{name}' ({file_path})")]
|
||||
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
)
|
||||
|
||||
if tool_name == "execute_code":
|
||||
code = str(arguments.get("code") or "").strip()
|
||||
preview = code[:1200] + (f"\n... ({len(code)} chars total, truncated)" if len(code) > 1200 else "")
|
||||
content = [_text(f"Running Python helper script:\n\n```python\n{preview}\n```" if preview else "Running Python helper script")]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
)
|
||||
|
||||
if tool_name == "web_search":
|
||||
query = str(arguments.get("query") or "").strip()
|
||||
content = [_text(f"Searching the web for: {query}" if query else "Searching the web")]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
)
|
||||
|
||||
if tool_name == "web_extract":
|
||||
# The title identifies the URL(s). Avoid a duplicate content block so
|
||||
# Zed renders this like read_file: compact start, concise completion.
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=None, locations=locations,
|
||||
)
|
||||
|
||||
if tool_name == "process":
|
||||
action = str(arguments.get("action") or "").strip() or "manage"
|
||||
sid = str(arguments.get("session_id") or "").strip()
|
||||
data_preview = str(arguments.get("data") or "").strip()
|
||||
text = f"Process action: {action}" + (f"\nSession: {sid}" if sid else "")
|
||||
if data_preview:
|
||||
text += "\nInput: " + _truncate_text(data_preview, limit=500)
|
||||
content = [_text(text)]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
)
|
||||
|
||||
if tool_name == "delegate_task":
|
||||
tasks = arguments.get("tasks")
|
||||
if isinstance(tasks, list) and tasks:
|
||||
lines = [f"Delegating {len(tasks)} tasks", ""]
|
||||
for i, task in enumerate(tasks[:8], 1):
|
||||
if isinstance(task, dict):
|
||||
goal = str(task.get("goal") or "").strip()
|
||||
role = str(task.get("role") or "").strip()
|
||||
lines.append(f"{i}. " + _truncate_text(goal, limit=160) + (f" ({role})" if role else ""))
|
||||
if len(tasks) > 8:
|
||||
lines.append(f"... {len(tasks) - 8} more")
|
||||
content = [_text("\n".join(lines))]
|
||||
else:
|
||||
goal = str(arguments.get("goal") or "").strip()
|
||||
content = [_text("Delegating task" + (f":\n{_truncate_text(goal, limit=800)}" if goal else ""))]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
)
|
||||
|
||||
if tool_name == "session_search":
|
||||
query = str(arguments.get("query") or "").strip()
|
||||
content = [_text(f"Searching past sessions for: {query}" if query else "Loading recent sessions")]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
)
|
||||
|
||||
if tool_name == "memory":
|
||||
action = str(arguments.get("action") or "manage").strip() or "manage"
|
||||
target = str(arguments.get("target") or "memory").strip() or "memory"
|
||||
preview = str(arguments.get("content") or arguments.get("old_text") or "").strip()
|
||||
text = f"Memory {action} ({target})"
|
||||
if preview:
|
||||
text += "\nPreview: " + _truncate_text(preview, limit=500)
|
||||
content = [_text(text)]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
)
|
||||
|
||||
if tool_name in _POLISHED_TOOLS:
|
||||
try:
|
||||
args_text = json.dumps(arguments, indent=2, default=str)
|
||||
except (TypeError, ValueError):
|
||||
args_text = str(arguments)
|
||||
content = [_text(_truncate_text(args_text, limit=1200))]
|
||||
content = [acp.tool_content(acp.text_block(f"Searching for '{pattern}' ({target})"))]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
raw_input=arguments,
|
||||
)
|
||||
|
||||
# Generic fallback
|
||||
@@ -1131,7 +334,7 @@ def build_tool_start(
|
||||
content = [acp.tool_content(acp.text_block(args_text))]
|
||||
return acp.start_tool_call(
|
||||
tool_call_id, title, kind=kind, content=content, locations=locations,
|
||||
raw_input=None if tool_name in _POLISHED_TOOLS else arguments,
|
||||
raw_input=arguments,
|
||||
)
|
||||
|
||||
|
||||
@@ -1144,22 +347,18 @@ def build_tool_complete(
|
||||
) -> ToolCallProgress:
|
||||
"""Create a ToolCallUpdate (progress) event for a completed tool call."""
|
||||
kind = get_tool_kind(tool_name)
|
||||
if tool_name == "web_extract":
|
||||
error_text = _format_web_extract_result(result)
|
||||
content = [_text(error_text)] if error_text else None
|
||||
else:
|
||||
content = _build_tool_complete_content(
|
||||
tool_name,
|
||||
result,
|
||||
function_args=function_args,
|
||||
snapshot=snapshot,
|
||||
)
|
||||
content = _build_tool_complete_content(
|
||||
tool_name,
|
||||
result,
|
||||
function_args=function_args,
|
||||
snapshot=snapshot,
|
||||
)
|
||||
return acp.update_tool_call(
|
||||
tool_call_id,
|
||||
kind=kind,
|
||||
status="completed",
|
||||
content=content,
|
||||
raw_output=None if tool_name in _POLISHED_TOOLS else result,
|
||||
raw_output=result,
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -1241,24 +1241,10 @@ def convert_tools_to_anthropic(tools: List[Dict]) -> List[Dict]:
|
||||
if not tools:
|
||||
return []
|
||||
result = []
|
||||
seen_names: set = set()
|
||||
for t in tools:
|
||||
fn = t.get("function", {})
|
||||
name = fn.get("name", "")
|
||||
# Defensive dedup: Anthropic rejects requests with duplicate tool
|
||||
# names. Upstream injection paths already dedup, but this guard
|
||||
# converts a hard API failure into a warning. See: #18478
|
||||
if name and name in seen_names:
|
||||
logger.warning(
|
||||
"convert_tools_to_anthropic: duplicate tool name '%s' "
|
||||
"— dropping second occurrence",
|
||||
name,
|
||||
)
|
||||
continue
|
||||
if name:
|
||||
seen_names.add(name)
|
||||
result.append({
|
||||
"name": name,
|
||||
"name": fn.get("name", ""),
|
||||
"description": fn.get("description", ""),
|
||||
"input_schema": _normalize_tool_input_schema(
|
||||
fn.get("parameters", {"type": "object", "properties": {}})
|
||||
|
||||
+16
-118
@@ -259,68 +259,13 @@ _PROVIDERS_WITHOUT_VISION: frozenset = frozenset({
|
||||
"kimi-coding-cn",
|
||||
})
|
||||
|
||||
# OpenRouter app attribution headers (base — always sent)
|
||||
_OR_HEADERS_BASE = {
|
||||
# OpenRouter app attribution headers
|
||||
_OR_HEADERS = {
|
||||
"HTTP-Referer": "https://hermes-agent.nousresearch.com",
|
||||
"X-OpenRouter-Title": "Hermes Agent",
|
||||
"X-OpenRouter-Categories": "productivity,cli-agent",
|
||||
}
|
||||
|
||||
# Truthy values for boolean env-var parsing.
|
||||
_TRUTHY_ENV_VALUES = frozenset({"1", "true", "yes", "on"})
|
||||
|
||||
|
||||
def build_or_headers(or_config: dict | None = None) -> dict:
|
||||
"""Build OpenRouter headers, optionally including response-cache headers.
|
||||
|
||||
Precedence for response cache: env var > config.yaml > default (enabled).
|
||||
|
||||
Environment variables:
|
||||
``HERMES_OPENROUTER_CACHE`` — truthy (``1``/``true``/``yes``/``on``)
|
||||
enables caching; ``0``/``false``/``no``/``off`` disables.
|
||||
Overrides ``openrouter.response_cache`` in config.yaml.
|
||||
``HERMES_OPENROUTER_CACHE_TTL`` — integer seconds (1-86400).
|
||||
Overrides ``openrouter.response_cache_ttl`` in config.yaml.
|
||||
|
||||
*or_config* is the ``openrouter`` section from config.yaml. When *None*,
|
||||
falls back to reading config from disk via ``load_config()``.
|
||||
"""
|
||||
headers = dict(_OR_HEADERS_BASE)
|
||||
|
||||
# Resolve config from disk if not provided.
|
||||
if or_config is None:
|
||||
try:
|
||||
from hermes_cli.config import load_config
|
||||
or_config = load_config().get("openrouter", {})
|
||||
except Exception:
|
||||
or_config = {}
|
||||
|
||||
# Determine cache enabled: env var overrides config.
|
||||
env_cache = os.environ.get("HERMES_OPENROUTER_CACHE", "").strip().lower()
|
||||
if env_cache:
|
||||
cache_enabled = env_cache in _TRUTHY_ENV_VALUES
|
||||
else:
|
||||
cache_enabled = or_config.get("response_cache", False)
|
||||
|
||||
if not cache_enabled:
|
||||
return headers
|
||||
|
||||
headers["X-OpenRouter-Cache"] = "true"
|
||||
|
||||
# Determine TTL: env var overrides config.
|
||||
env_ttl = os.environ.get("HERMES_OPENROUTER_CACHE_TTL", "").strip()
|
||||
if env_ttl:
|
||||
if env_ttl.isdigit():
|
||||
ttl = int(env_ttl)
|
||||
if 1 <= ttl <= 86400:
|
||||
headers["X-OpenRouter-Cache-TTL"] = str(ttl)
|
||||
else:
|
||||
ttl = or_config.get("response_cache_ttl", 300)
|
||||
if isinstance(ttl, (int, float)) and 1 <= ttl <= 86400:
|
||||
headers["X-OpenRouter-Cache-TTL"] = str(int(ttl))
|
||||
|
||||
return headers
|
||||
|
||||
# Vercel AI Gateway app attribution headers. HTTP-Referer maps to
|
||||
# referrerUrl and X-Title maps to appName in the gateway's analytics.
|
||||
from hermes_cli import __version__ as _HERMES_VERSION
|
||||
@@ -1204,23 +1149,23 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
|
||||
|
||||
|
||||
|
||||
def _try_openrouter(explicit_api_key: str = None) -> Tuple[Optional[OpenAI], Optional[str]]:
|
||||
def _try_openrouter() -> Tuple[Optional[OpenAI], Optional[str]]:
|
||||
pool_present, entry = _select_pool_entry("openrouter")
|
||||
if pool_present:
|
||||
or_key = explicit_api_key or _pool_runtime_api_key(entry)
|
||||
or_key = _pool_runtime_api_key(entry)
|
||||
if not or_key:
|
||||
return None, None
|
||||
base_url = _pool_runtime_base_url(entry, OPENROUTER_BASE_URL) or OPENROUTER_BASE_URL
|
||||
logger.debug("Auxiliary client: OpenRouter via pool")
|
||||
return OpenAI(api_key=or_key, base_url=base_url,
|
||||
default_headers=build_or_headers()), _OPENROUTER_MODEL
|
||||
default_headers=_OR_HEADERS), _OPENROUTER_MODEL
|
||||
|
||||
or_key = explicit_api_key or os.getenv("OPENROUTER_API_KEY")
|
||||
or_key = os.getenv("OPENROUTER_API_KEY")
|
||||
if not or_key:
|
||||
return None, None
|
||||
logger.debug("Auxiliary client: OpenRouter")
|
||||
return OpenAI(api_key=or_key, base_url=OPENROUTER_BASE_URL,
|
||||
default_headers=build_or_headers()), _OPENROUTER_MODEL
|
||||
default_headers=_OR_HEADERS), _OPENROUTER_MODEL
|
||||
|
||||
|
||||
def _describe_openrouter_unavailable() -> str:
|
||||
@@ -1529,7 +1474,7 @@ def _build_codex_client(model: str) -> Tuple[Optional[Any], Optional[str]]:
|
||||
return CodexAuxiliaryClient(real_client, model), model
|
||||
|
||||
|
||||
def _try_anthropic(explicit_api_key: str = None) -> Tuple[Optional[Any], Optional[str]]:
|
||||
def _try_anthropic() -> Tuple[Optional[Any], Optional[str]]:
|
||||
try:
|
||||
from agent.anthropic_adapter import build_anthropic_client, resolve_anthropic_token
|
||||
except ImportError:
|
||||
@@ -1539,10 +1484,10 @@ def _try_anthropic(explicit_api_key: str = None) -> Tuple[Optional[Any], Optiona
|
||||
if pool_present:
|
||||
if entry is None:
|
||||
return None, None
|
||||
token = explicit_api_key or _pool_runtime_api_key(entry)
|
||||
token = _pool_runtime_api_key(entry)
|
||||
else:
|
||||
entry = None
|
||||
token = explicit_api_key or resolve_anthropic_token()
|
||||
token = resolve_anthropic_token()
|
||||
if not token:
|
||||
return None, None
|
||||
|
||||
@@ -1966,7 +1911,7 @@ def _to_async_client(sync_client, model: str, is_vision: bool = False):
|
||||
}
|
||||
sync_base_url = str(sync_client.base_url)
|
||||
if base_url_host_matches(sync_base_url, "openrouter.ai"):
|
||||
async_kwargs["default_headers"] = build_or_headers()
|
||||
async_kwargs["default_headers"] = dict(_OR_HEADERS)
|
||||
elif base_url_host_matches(sync_base_url, "api.githubcopilot.com"):
|
||||
from hermes_cli.copilot_auth import copilot_request_headers
|
||||
|
||||
@@ -2032,12 +1977,6 @@ def resolve_provider_client(
|
||||
(client, resolved_model) or (None, None) if auth is unavailable.
|
||||
"""
|
||||
_validate_proxy_env_urls()
|
||||
# Preserve the original provider name before alias normalization so a
|
||||
# user-declared ``custom_providers`` entry whose name coincidentally
|
||||
# matches a built-in alias (e.g. user names their custom provider "kimi"
|
||||
# which aliases to "kimi-coding") is still reachable via the named-custom
|
||||
# branch below.
|
||||
original_provider = (provider or "").strip().lower()
|
||||
# Normalise aliases
|
||||
provider = _normalize_aux_provider(provider)
|
||||
|
||||
@@ -2108,9 +2047,9 @@ def resolve_provider_client(
|
||||
return (_to_async_client(client, final_model, is_vision=is_vision) if async_mode
|
||||
else (client, final_model))
|
||||
|
||||
# ── OpenRouter ───────────────────────────────────────────
|
||||
# ── OpenRouter ───────────────────────────────────────────────────
|
||||
if provider == "openrouter":
|
||||
client, default = _try_openrouter(explicit_api_key=explicit_api_key)
|
||||
client, default = _try_openrouter()
|
||||
if client is None:
|
||||
logger.warning(
|
||||
"resolve_provider_client: openrouter requested but %s",
|
||||
@@ -2224,18 +2163,7 @@ def resolve_provider_client(
|
||||
# ── Named custom providers (config.yaml providers dict / custom_providers list) ───
|
||||
try:
|
||||
from hermes_cli.runtime_provider import _get_named_custom_provider
|
||||
# When the raw requested name is an alias (``kimi`` → ``kimi-coding``)
|
||||
# and the user defined a ``custom_providers`` entry under that alias
|
||||
# name, the custom entry is the intended target — the built-in alias
|
||||
# rewriting would otherwise hijack the request. Only preferred when
|
||||
# the raw name is an alias (not a canonical provider name) so custom
|
||||
# entries that coincidentally match a canonical provider (e.g. ``nous``)
|
||||
# still defer to the built-in per `_get_named_custom_provider`'s guard.
|
||||
custom_entry = None
|
||||
if original_provider and original_provider != provider:
|
||||
custom_entry = _get_named_custom_provider(original_provider)
|
||||
if custom_entry is None:
|
||||
custom_entry = _get_named_custom_provider(provider)
|
||||
custom_entry = _get_named_custom_provider(provider)
|
||||
if custom_entry:
|
||||
custom_base = custom_entry.get("base_url", "").strip()
|
||||
custom_key = custom_entry.get("api_key", "").strip()
|
||||
@@ -2336,7 +2264,7 @@ def resolve_provider_client(
|
||||
|
||||
if pconfig.auth_type == "api_key":
|
||||
if provider == "anthropic":
|
||||
client, default_model = _try_anthropic(explicit_api_key=explicit_api_key)
|
||||
client, default_model = _try_anthropic()
|
||||
if client is None:
|
||||
logger.warning("resolve_provider_client: anthropic requested but no Anthropic credentials found")
|
||||
return None, None
|
||||
@@ -2345,12 +2273,6 @@ def resolve_provider_client(
|
||||
|
||||
creds = resolve_api_key_provider_credentials(provider)
|
||||
api_key = str(creds.get("api_key", "")).strip()
|
||||
# Honour an explicit api_key override (e.g. from a fallback_model entry
|
||||
# or a custom_providers entry) so callers that pass an explicit
|
||||
# credential can authenticate against endpoints where no built-in
|
||||
# credential is registered for this provider alias.
|
||||
if explicit_api_key:
|
||||
api_key = explicit_api_key.strip() or api_key
|
||||
if not api_key:
|
||||
tried_sources = list(pconfig.api_key_env_vars)
|
||||
if provider == "copilot":
|
||||
@@ -2362,11 +2284,6 @@ def resolve_provider_client(
|
||||
|
||||
raw_base_url = str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
|
||||
base_url = _to_openai_base_url(raw_base_url)
|
||||
# Honour an explicit base_url override from the caller — used when a
|
||||
# fallback_model entry (or custom_providers lookup) routes through a
|
||||
# built-in provider name but targets a user-specified endpoint.
|
||||
if explicit_base_url:
|
||||
base_url = _to_openai_base_url(explicit_base_url.strip().rstrip("/"))
|
||||
|
||||
default_model = _API_KEY_PROVIDER_AUX_MODELS.get(provider, "")
|
||||
final_model = _normalize_resolved_model(model or default_model, provider)
|
||||
@@ -3292,26 +3209,7 @@ def _build_call_kwargs(
|
||||
kwargs["max_tokens"] = max_tokens
|
||||
|
||||
if tools:
|
||||
# Defensive dedup: providers like Google Vertex, Azure, and Bedrock
|
||||
# reject requests with duplicate tool names (HTTP 400). The upstream
|
||||
# injection paths (run_agent.py) already dedup, but this guard
|
||||
# converts a hard API failure into a warning if an upstream regression
|
||||
# reintroduces duplicates. See: #18478
|
||||
_seen: set = set()
|
||||
_deduped: list = []
|
||||
for _t in tools:
|
||||
_tname = (_t.get("function") or {}).get("name", "")
|
||||
if _tname and _tname in _seen:
|
||||
logger.warning(
|
||||
"_build_call_kwargs: duplicate tool name '%s' removed "
|
||||
"(provider=%s model=%s)",
|
||||
_tname, provider, model,
|
||||
)
|
||||
continue
|
||||
if _tname:
|
||||
_seen.add(_tname)
|
||||
_deduped.append(_t)
|
||||
kwargs["tools"] = _deduped
|
||||
kwargs["tools"] = tools
|
||||
|
||||
# Provider-specific extra_body
|
||||
merged_extra = dict(extra_body or {})
|
||||
|
||||
@@ -538,7 +538,7 @@ class ContextCompressor(ContextEngine):
|
||||
# Token-budget approach: walk backward accumulating tokens
|
||||
accumulated = 0
|
||||
boundary = len(result)
|
||||
min_protect = min(protect_tail_count, len(result))
|
||||
min_protect = min(protect_tail_count, len(result) - 1)
|
||||
for i in range(len(result) - 1, -1, -1):
|
||||
msg = result[i]
|
||||
raw_content = msg.get("content") or ""
|
||||
@@ -569,8 +569,6 @@ class ContextCompressor(ContextEngine):
|
||||
# Skip multimodal content (list of content blocks)
|
||||
if isinstance(content, list):
|
||||
continue
|
||||
if not isinstance(content, str):
|
||||
continue
|
||||
if len(content) < 200:
|
||||
continue
|
||||
h = hashlib.md5(content.encode("utf-8", errors="replace")).hexdigest()[:12]
|
||||
@@ -994,8 +992,8 @@ The user has requested that this compaction PRIORITISE preserving all informatio
|
||||
def _get_tool_call_id(tc) -> str:
|
||||
"""Extract the call ID from a tool_call entry (dict or SimpleNamespace)."""
|
||||
if isinstance(tc, dict):
|
||||
return tc.get("call_id", "") or tc.get("id", "") or ""
|
||||
return getattr(tc, "call_id", "") or getattr(tc, "id", "") or ""
|
||||
return tc.get("id", "")
|
||||
return getattr(tc, "id", "") or ""
|
||||
|
||||
def _sanitize_tool_pairs(self, messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
|
||||
"""Fix orphaned tool_call / tool_result pairs after compression.
|
||||
|
||||
@@ -3,7 +3,6 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
import random
|
||||
import threading
|
||||
import time
|
||||
@@ -14,7 +13,7 @@ from datetime import datetime
|
||||
from typing import Any, Dict, List, Optional, Set, Tuple
|
||||
|
||||
from hermes_constants import OPENROUTER_BASE_URL
|
||||
from hermes_cli.config import get_env_value, load_env
|
||||
from hermes_cli.config import get_env_value
|
||||
import hermes_cli.auth as auth_mod
|
||||
from hermes_cli.auth import (
|
||||
CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
|
||||
@@ -1381,16 +1380,6 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
|
||||
def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool, Set[str]]:
|
||||
changed = False
|
||||
active_sources: Set[str] = set()
|
||||
|
||||
# Prefer ~/.hermes/.env over os.environ — the user's config file is the
|
||||
# authoritative source for Hermes credentials. Stale env vars from parent
|
||||
# processes (Codex CLI, test scripts, etc.) should not override deliberate
|
||||
# changes to the .env file.
|
||||
def _get_env_prefer_dotenv(key: str) -> str:
|
||||
env_file = load_env()
|
||||
val = env_file.get(key) or os.environ.get(key) or ""
|
||||
return val.strip()
|
||||
|
||||
# Honour user suppression — `hermes auth remove <provider> <N>` for an
|
||||
# env-seeded credential marks the env:<VAR> source as suppressed so it
|
||||
# won't be re-seeded from the user's shell environment or ~/.hermes/.env.
|
||||
@@ -1402,8 +1391,8 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
|
||||
def _is_source_suppressed(_p, _s): # type: ignore[misc]
|
||||
return False
|
||||
if provider == "openrouter":
|
||||
# Prefer ~/.hermes/.env over os.environ
|
||||
token = _get_env_prefer_dotenv("OPENROUTER_API_KEY")
|
||||
# Check both os.environ and ~/.hermes/.env file
|
||||
token = (get_env_value("OPENROUTER_API_KEY") or "").strip()
|
||||
if token:
|
||||
source = "env:OPENROUTER_API_KEY"
|
||||
if _is_source_suppressed(provider, source):
|
||||
@@ -1429,7 +1418,7 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
|
||||
|
||||
env_url = ""
|
||||
if pconfig.base_url_env_var:
|
||||
env_url = _get_env_prefer_dotenv(pconfig.base_url_env_var).rstrip("/")
|
||||
env_url = (get_env_value(pconfig.base_url_env_var) or "").strip().rstrip("/")
|
||||
|
||||
env_vars = list(pconfig.api_key_env_vars)
|
||||
if provider == "anthropic":
|
||||
@@ -1440,8 +1429,8 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
|
||||
]
|
||||
|
||||
for env_var in env_vars:
|
||||
# Prefer ~/.hermes/.env over os.environ
|
||||
token = _get_env_prefer_dotenv(env_var)
|
||||
# Check both os.environ and ~/.hermes/.env file
|
||||
token = (get_env_value(env_var) or "").strip()
|
||||
if not token:
|
||||
continue
|
||||
source = f"env:{env_var}"
|
||||
|
||||
+47
-406
@@ -24,12 +24,11 @@ from __future__ import annotations
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import tempfile
|
||||
import threading
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any, Callable, Dict, List, NamedTuple, Optional, Set
|
||||
from typing import Any, Callable, Dict, List, Optional, Set
|
||||
|
||||
from hermes_constants import get_hermes_home
|
||||
from tools import skill_usage
|
||||
@@ -37,22 +36,6 @@ from tools import skill_usage
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _strip_aux_credential(value: Any) -> Optional[str]:
|
||||
if value is None:
|
||||
return None
|
||||
text = str(value).strip()
|
||||
return text or None
|
||||
|
||||
|
||||
class _ReviewRuntimeBinding(NamedTuple):
|
||||
"""Provider/model for the curator review fork plus optional per-slot overrides."""
|
||||
|
||||
provider: str
|
||||
model: str
|
||||
explicit_api_key: Optional[str]
|
||||
explicit_base_url: Optional[str]
|
||||
|
||||
|
||||
DEFAULT_INTERVAL_HOURS = 24 * 7 # 7 days
|
||||
DEFAULT_MIN_IDLE_HOURS = 2
|
||||
DEFAULT_STALE_AFTER_DAYS = 30
|
||||
@@ -72,7 +55,6 @@ def _default_state() -> Dict[str, Any]:
|
||||
"last_run_at": None,
|
||||
"last_run_duration_seconds": None,
|
||||
"last_run_summary": None,
|
||||
"last_report_path": None,
|
||||
"paused": False,
|
||||
"run_count": 0,
|
||||
}
|
||||
@@ -201,16 +183,7 @@ def should_run_now(now: Optional[datetime] = None) -> bool:
|
||||
Gates:
|
||||
- curator.enabled == True
|
||||
- not paused
|
||||
- last_run_at present AND older than interval_hours
|
||||
|
||||
First-run behavior: when there is no ``last_run_at`` (fresh install, or
|
||||
install that predates the curator), we DO NOT run immediately. The
|
||||
curator is designed to run after at least ``interval_hours`` (7 days by
|
||||
default) of skill activity, not on the first background tick after
|
||||
``hermes update``. On first observation we seed ``last_run_at`` to "now"
|
||||
and defer the first real pass by one full interval. Users who want to
|
||||
run it sooner can always invoke ``hermes curator run`` (with or without
|
||||
``--dry-run``) explicitly — that path bypasses this gate.
|
||||
- last_run_at missing, OR older than interval_hours
|
||||
|
||||
The idle check (min_idle_hours) is applied at the call site where we know
|
||||
whether an agent is actively running — here we only enforce the static
|
||||
@@ -224,21 +197,7 @@ def should_run_now(now: Optional[datetime] = None) -> bool:
|
||||
state = load_state()
|
||||
last = _parse_iso(state.get("last_run_at"))
|
||||
if last is None:
|
||||
# Never run before. Seed state so we wait a full interval before the
|
||||
# first real pass. Report-only; do not auto-mutate the library the
|
||||
# very first time a gateway ticks after an update.
|
||||
if now is None:
|
||||
now = datetime.now(timezone.utc)
|
||||
try:
|
||||
state["last_run_at"] = now.isoformat()
|
||||
state["last_run_summary"] = (
|
||||
"deferred first run — curator seeded, will run after one "
|
||||
"interval; use `hermes curator run --dry-run` to preview now"
|
||||
)
|
||||
save_state(state)
|
||||
except Exception as e: # pragma: no cover — best-effort persistence
|
||||
logger.debug("Failed to seed curator last_run_at: %s", e)
|
||||
return False
|
||||
return True
|
||||
|
||||
if now is None:
|
||||
now = datetime.now(timezone.utc)
|
||||
@@ -299,33 +258,6 @@ def apply_automatic_transitions(now: Optional[datetime] = None) -> Dict[str, int
|
||||
# Review prompt for the forked agent
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
CURATOR_DRY_RUN_BANNER = (
|
||||
"═══════════════════════════════════════════════════════════════\n"
|
||||
"DRY-RUN — REPORT ONLY. DO NOT MUTATE THE SKILL LIBRARY.\n"
|
||||
"═══════════════════════════════════════════════════════════════\n"
|
||||
"\n"
|
||||
"This is a PREVIEW pass. Follow every instruction below EXCEPT:\n"
|
||||
"\n"
|
||||
" • DO NOT call skill_manage with action=patch, create, delete, "
|
||||
"write_file, or remove_file.\n"
|
||||
" • DO NOT call terminal to mv skill directories into .archive/.\n"
|
||||
" • DO NOT call terminal to mv, cp, rm, or rewrite any file under "
|
||||
"~/.hermes/skills/.\n"
|
||||
" • skills_list and skill_view are FINE — read as much as you need.\n"
|
||||
"\n"
|
||||
"Your output IS the deliverable. Produce the exact same "
|
||||
"human-readable summary and structured YAML block you would "
|
||||
"produce on a live run — but describe the actions you WOULD take, "
|
||||
"not actions you took. A downstream reviewer will read the report "
|
||||
"and decide whether to approve a live run with "
|
||||
"`hermes curator run` (no flag).\n"
|
||||
"\n"
|
||||
"If you accidentally take a mutating action, say so explicitly in "
|
||||
"the summary so the reviewer can revert it.\n"
|
||||
"═══════════════════════════════════════════════════════════════"
|
||||
)
|
||||
|
||||
|
||||
CURATOR_REVIEW_PROMPT = (
|
||||
"You are running as Hermes' background skill CURATOR. This is an "
|
||||
"UMBRELLA-BUILDING consolidation pass, not a passive audit and not a "
|
||||
@@ -404,11 +336,6 @@ CURATOR_REVIEW_PROMPT = (
|
||||
" - skill_manage action=write_file — add a references/, templates/, "
|
||||
"or scripts/ file under an existing skill (the skill must already "
|
||||
"exist)\n"
|
||||
" - skill_manage action=delete — archive a skill. MUST pass "
|
||||
"`absorbed_into=<umbrella>` when you've merged its content into another "
|
||||
"skill, or `absorbed_into=\"\"` when you're truly pruning with no "
|
||||
"forwarding target. This drives cron-job skill-reference migration — "
|
||||
"guessing from your YAML summary after the fact is fragile.\n"
|
||||
" - terminal — mv a sibling into the archive "
|
||||
"OR move its content into a support subfile\n\n"
|
||||
"'keep' is a legitimate decision ONLY when the skill is already a "
|
||||
@@ -470,24 +397,6 @@ def _reports_root() -> Path:
|
||||
return root
|
||||
|
||||
|
||||
def _needle_in_path_component(needle: str, path: str) -> bool:
|
||||
"""Check if *needle* is a complete filename stem or directory name in *path*.
|
||||
|
||||
Unlike simple substring matching, this avoids false positives where short
|
||||
skill names are embedded in longer filenames (e.g. "api" matching
|
||||
"references/api-design.md"). Hyphens and underscores are normalised so
|
||||
"open-webui-setup" matches "open_webui_setup.md".
|
||||
"""
|
||||
norm_needle = needle.replace("-", "_")
|
||||
for part in path.replace("\\", "/").split("/"):
|
||||
if not part:
|
||||
continue
|
||||
stem = part.rsplit(".", 1)[0] if "." in part else part
|
||||
if stem.replace("-", "_") == norm_needle:
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def _classify_removed_skills(
|
||||
removed: List[str],
|
||||
added: List[str],
|
||||
@@ -566,29 +475,15 @@ def _classify_removed_skills(
|
||||
continue
|
||||
|
||||
# Look for the removed skill's name in file_path / content / raw.
|
||||
# Matching strategy differs by field type:
|
||||
# file_path — needle must be a complete path component
|
||||
# (filename stem or directory name), so "api" does NOT
|
||||
# falsely match "references/api-design.md".
|
||||
# content fields — word-boundary regex so "test" does NOT
|
||||
# falsely match "latest" or "testing".
|
||||
haystacks: List[tuple[str, str]] = []
|
||||
haystacks: List[str] = []
|
||||
for key in ("file_path", "file_content", "content", "new_string", "_raw"):
|
||||
v = args.get(key)
|
||||
if isinstance(v, str):
|
||||
haystacks.append((key, v))
|
||||
haystacks.append(v)
|
||||
hit = False
|
||||
for key, hay in haystacks:
|
||||
for hay in haystacks:
|
||||
for needle in needles:
|
||||
if not needle:
|
||||
continue
|
||||
if key == "file_path":
|
||||
matched = _needle_in_path_component(needle, hay)
|
||||
else:
|
||||
matched = bool(
|
||||
re.search(rf'\b{re.escape(needle)}\b', hay)
|
||||
)
|
||||
if matched:
|
||||
if needle and needle in hay:
|
||||
hit = True
|
||||
evidence = (
|
||||
f"skill_manage action={args.get('action', '?')} "
|
||||
@@ -691,76 +586,15 @@ def _parse_structured_summary(
|
||||
return out
|
||||
|
||||
|
||||
def _extract_absorbed_into_declarations(
|
||||
tool_calls: List[Dict[str, Any]],
|
||||
) -> Dict[str, Dict[str, Any]]:
|
||||
"""Walk this run's tool calls and extract model-declared absorption targets.
|
||||
|
||||
The curator prompt requires every ``skill_manage(action='delete')`` call
|
||||
to pass ``absorbed_into=<umbrella>`` when consolidating, or
|
||||
``absorbed_into=""`` when truly pruning. This is the single authoritative
|
||||
signal for classification — the model's own declaration at the moment of
|
||||
deletion, which beats both post-hoc YAML summary parsing and substring
|
||||
heuristics on other tool calls.
|
||||
|
||||
Returns ``{skill_name: {"into": "<umbrella>" | "", "declared": True}}``.
|
||||
Entries with ``into == ""`` are explicit prunings.
|
||||
Skills without a ``skill_manage(delete)`` call, or with one that omitted
|
||||
``absorbed_into``, are not in the returned dict — caller falls back to
|
||||
the existing heuristic/YAML logic for those (backward compat with older
|
||||
curator runs and any callers that don't populate the arg).
|
||||
"""
|
||||
out: Dict[str, Dict[str, Any]] = {}
|
||||
for tc in tool_calls or []:
|
||||
if not isinstance(tc, dict):
|
||||
continue
|
||||
if tc.get("name") != "skill_manage":
|
||||
continue
|
||||
raw = tc.get("arguments") or ""
|
||||
args: Dict[str, Any] = {}
|
||||
if isinstance(raw, dict):
|
||||
args = raw
|
||||
elif isinstance(raw, str):
|
||||
try:
|
||||
args = json.loads(raw)
|
||||
except Exception:
|
||||
continue
|
||||
if not isinstance(args, dict):
|
||||
continue
|
||||
if args.get("action") != "delete":
|
||||
continue
|
||||
name = args.get("name")
|
||||
if not isinstance(name, str) or not name.strip():
|
||||
continue
|
||||
# absorbed_into must be present (even empty string is meaningful);
|
||||
# missing key means the model didn't declare intent.
|
||||
if "absorbed_into" not in args:
|
||||
continue
|
||||
target = args.get("absorbed_into")
|
||||
if target is None:
|
||||
continue
|
||||
if not isinstance(target, str):
|
||||
continue
|
||||
out[name.strip()] = {"into": target.strip(), "declared": True}
|
||||
return out
|
||||
|
||||
|
||||
def _reconcile_classification(
|
||||
removed: List[str],
|
||||
heuristic: Dict[str, List[Dict[str, Any]]],
|
||||
model_block: Dict[str, List[Dict[str, str]]],
|
||||
destinations: Set[str],
|
||||
absorbed_declarations: Optional[Dict[str, Dict[str, Any]]] = None,
|
||||
) -> Dict[str, List[Dict[str, Any]]]:
|
||||
"""Merge heuristic (tool-call evidence) with the model's structured block.
|
||||
|
||||
Rules (evaluated in order; first match wins):
|
||||
- **Model-declared `absorbed_into` at delete time is authoritative.** Any
|
||||
entry in ``absorbed_declarations`` beats every other signal. This is
|
||||
the model telling us directly, at the moment of deletion, what it did.
|
||||
``into != ""`` and target exists → consolidated. ``into == ""`` →
|
||||
pruned. ``into != ""`` but target doesn't exist → hallucination; fall
|
||||
through to the usual signals.
|
||||
Rules:
|
||||
- Model-declared consolidation wins when its ``into`` target exists
|
||||
in ``destinations`` (survived or newly-created). This gives the
|
||||
model authority over intent + rationale.
|
||||
@@ -781,8 +615,6 @@ def _reconcile_classification(
|
||||
model_cons = {e["from"]: e for e in model_block.get("consolidations", [])}
|
||||
model_pruned = {e["name"]: e for e in model_block.get("prunings", [])}
|
||||
|
||||
declared = absorbed_declarations or {}
|
||||
|
||||
consolidated: List[Dict[str, Any]] = []
|
||||
pruned: List[Dict[str, Any]] = []
|
||||
|
||||
@@ -790,36 +622,6 @@ def _reconcile_classification(
|
||||
mc = model_cons.get(name)
|
||||
mp = model_pruned.get(name)
|
||||
hc = heur_cons.get(name)
|
||||
dec = declared.get(name)
|
||||
|
||||
# Authoritative: model declared `absorbed_into` at the delete call.
|
||||
if dec is not None:
|
||||
into_claim = dec.get("into", "")
|
||||
if into_claim and into_claim in destinations:
|
||||
entry: Dict[str, Any] = {
|
||||
"name": name,
|
||||
"into": into_claim,
|
||||
"source": "absorbed_into (model-declared at delete)",
|
||||
"reason": (mc.get("reason") or "") if mc else "",
|
||||
}
|
||||
if hc and hc.get("evidence"):
|
||||
entry["evidence"] = hc["evidence"]
|
||||
consolidated.append(entry)
|
||||
continue
|
||||
if into_claim == "":
|
||||
# Explicit prune declaration
|
||||
pruned.append({
|
||||
"name": name,
|
||||
"source": "absorbed_into=\"\" (model-declared prune)",
|
||||
"reason": (mp.get("reason") or "") if mp else "",
|
||||
})
|
||||
continue
|
||||
# into_claim is non-empty but target doesn't exist: the model
|
||||
# named a nonexistent umbrella at delete time. The tool already
|
||||
# rejects this at the skill_manage layer, so we shouldn't see it
|
||||
# in practice — but if it slips through (e.g. the umbrella was
|
||||
# deleted LATER in the same run), fall through to the usual
|
||||
# signals rather than trusting a broken reference.
|
||||
|
||||
# Model says consolidated — trust it if the destination is real.
|
||||
if mc and mc.get("into") in destinations:
|
||||
@@ -955,57 +757,15 @@ def _write_run_report(
|
||||
)
|
||||
model_block = _parse_structured_summary(llm_meta.get("final", "") or "")
|
||||
destinations = set(after_names) | set(added or [])
|
||||
# Authoritative signal: extract per-delete `absorbed_into` declarations
|
||||
# from this run's tool calls. These beat both the YAML summary block and
|
||||
# the substring heuristic — the model is telling us directly, at the
|
||||
# moment of deletion, whether each archived skill was consolidated
|
||||
# (into=<umbrella>) or pruned (into="").
|
||||
absorbed_declarations = _extract_absorbed_into_declarations(
|
||||
llm_meta.get("tool_calls", []) or []
|
||||
)
|
||||
classification = _reconcile_classification(
|
||||
removed=removed,
|
||||
heuristic=heuristic,
|
||||
model_block=model_block,
|
||||
destinations=destinations,
|
||||
absorbed_declarations=absorbed_declarations,
|
||||
)
|
||||
consolidated = classification["consolidated"]
|
||||
pruned = classification["pruned"]
|
||||
|
||||
# Rewrite cron job skill references. When the curator consolidates
|
||||
# skill X into umbrella Y, any cron job that lists X fails to load
|
||||
# it at run time — the scheduler skips it and the job runs without
|
||||
# the instructions it was scheduled to follow. Rewriting the
|
||||
# references in-place keeps scheduled jobs working across
|
||||
# consolidation passes. Best-effort: never let a cron-module issue
|
||||
# break the curator.
|
||||
cron_rewrites: Dict[str, Any] = {"rewrites": [], "jobs_updated": 0, "jobs_scanned": 0}
|
||||
try:
|
||||
consolidated_map = {
|
||||
e["name"]: e["into"]
|
||||
for e in consolidated
|
||||
if isinstance(e, dict) and e.get("name") and e.get("into")
|
||||
}
|
||||
pruned_names = [
|
||||
e["name"] for e in pruned
|
||||
if isinstance(e, dict) and e.get("name")
|
||||
]
|
||||
if consolidated_map or pruned_names:
|
||||
from cron.jobs import rewrite_skill_refs as _rewrite_cron_refs
|
||||
cron_rewrites = _rewrite_cron_refs(
|
||||
consolidated=consolidated_map,
|
||||
pruned=pruned_names,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.debug("Curator cron skill rewrite failed: %s", e, exc_info=True)
|
||||
cron_rewrites = {
|
||||
"rewrites": [],
|
||||
"jobs_updated": 0,
|
||||
"jobs_scanned": 0,
|
||||
"error": str(e),
|
||||
}
|
||||
|
||||
payload = {
|
||||
"started_at": started_at.isoformat(),
|
||||
"duration_seconds": round(elapsed_seconds, 2),
|
||||
@@ -1021,7 +781,6 @@ def _write_run_report(
|
||||
"consolidated_this_run": len(consolidated),
|
||||
"pruned_this_run": len(pruned),
|
||||
"state_transitions": len(transitions),
|
||||
"cron_jobs_rewritten": int(cron_rewrites.get("jobs_updated", 0)),
|
||||
"tool_calls_total": sum(tc_counts.values()),
|
||||
},
|
||||
"tool_call_counts": tc_counts,
|
||||
@@ -1031,7 +790,6 @@ def _write_run_report(
|
||||
"pruned_names": [p["name"] for p in pruned],
|
||||
"added": added,
|
||||
"state_transitions": transitions,
|
||||
"cron_rewrites": cron_rewrites,
|
||||
"llm_final": llm_meta.get("final", ""),
|
||||
"llm_summary": llm_meta.get("summary", ""),
|
||||
"llm_error": llm_meta.get("error"),
|
||||
@@ -1054,17 +812,6 @@ def _write_run_report(
|
||||
except Exception as e:
|
||||
logger.debug("Curator REPORT.md write failed: %s", e)
|
||||
|
||||
# cron_rewrites.json — only when at least one job was touched, to
|
||||
# keep run dirs uncluttered for the common no-op case.
|
||||
try:
|
||||
if int(cron_rewrites.get("jobs_updated", 0)) > 0:
|
||||
(run_dir / "cron_rewrites.json").write_text(
|
||||
json.dumps(cron_rewrites, indent=2, ensure_ascii=False) + "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
except Exception as e:
|
||||
logger.debug("Curator cron_rewrites.json write failed: %s", e)
|
||||
|
||||
return run_dir
|
||||
|
||||
|
||||
@@ -1195,39 +942,6 @@ def _render_report_markdown(p: Dict[str, Any]) -> str:
|
||||
lines.append(f"- `{t.get('name')}`: {t.get('from')} → {t.get('to')}")
|
||||
lines.append("")
|
||||
|
||||
# Cron job rewrites — show which scheduled jobs had their skill
|
||||
# references updated so users can audit that the auto-rewrite did
|
||||
# the right thing. Only present when at least one job changed.
|
||||
cron_rw = p.get("cron_rewrites") or {}
|
||||
cron_rewrites_list = cron_rw.get("rewrites") or []
|
||||
if cron_rewrites_list:
|
||||
lines.append(f"### Cron job skill references rewritten ({len(cron_rewrites_list)})\n")
|
||||
lines.append(
|
||||
"_Cron jobs that referenced a consolidated or pruned skill were "
|
||||
"updated in-place so they keep loading the right instructions "
|
||||
"on their next run. See `cron_rewrites.json` for the full record._\n"
|
||||
)
|
||||
SHOW = 25
|
||||
for entry in cron_rewrites_list[:SHOW]:
|
||||
job_name = entry.get("job_name") or entry.get("job_id") or "?"
|
||||
before = entry.get("before") or []
|
||||
after = entry.get("after") or []
|
||||
mapped = entry.get("mapped") or {}
|
||||
dropped = entry.get("dropped") or []
|
||||
lines.append(
|
||||
f"- `{job_name}`: `{', '.join(before)}` → `{', '.join(after) or '(none)'}`"
|
||||
)
|
||||
for old, new in mapped.items():
|
||||
lines.append(f" - `{old}` → `{new}` (consolidated)")
|
||||
for name in dropped:
|
||||
lines.append(f" - `{name}` dropped (pruned)")
|
||||
if len(cron_rewrites_list) > SHOW:
|
||||
lines.append(
|
||||
f"- … and {len(cron_rewrites_list) - SHOW} more "
|
||||
"(see `cron_rewrites.json`)"
|
||||
)
|
||||
lines.append("")
|
||||
|
||||
# Full LLM final response
|
||||
final = (p.get("llm_final") or "").strip()
|
||||
if final:
|
||||
@@ -1278,7 +992,6 @@ def _render_candidate_list() -> str:
|
||||
def run_curator_review(
|
||||
on_summary: Optional[Callable[[str], None]] = None,
|
||||
synchronous: bool = False,
|
||||
dry_run: bool = False,
|
||||
) -> Dict[str, Any]:
|
||||
"""Execute a single curator review pass.
|
||||
|
||||
@@ -1291,43 +1004,9 @@ def run_curator_review(
|
||||
|
||||
If *synchronous* is True, the LLM review runs in the calling thread; the
|
||||
default is to spawn a daemon thread so the caller returns immediately.
|
||||
|
||||
If *dry_run* is True, the automatic stale/archive transitions are SKIPPED
|
||||
and the LLM review pass is instructed to produce a report only — no
|
||||
skill_manage mutations, no terminal archive moves. The REPORT.md still
|
||||
gets written and ``state.last_report_path`` still records it so users
|
||||
can read what the curator WOULD have done.
|
||||
"""
|
||||
start = datetime.now(timezone.utc)
|
||||
if dry_run:
|
||||
# Count candidates without mutating state.
|
||||
try:
|
||||
report = skill_usage.agent_created_report()
|
||||
counts = {
|
||||
"checked": len(report),
|
||||
"marked_stale": 0,
|
||||
"archived": 0,
|
||||
"reactivated": 0,
|
||||
}
|
||||
except Exception:
|
||||
counts = {"checked": 0, "marked_stale": 0, "archived": 0, "reactivated": 0}
|
||||
else:
|
||||
# Pre-mutation snapshot — best-effort, never blocks the run. A
|
||||
# failed snapshot logs at debug and continues (the alternative is
|
||||
# that a transient disk issue silently disables curator forever,
|
||||
# which is worse). Users who want to require snapshots can disable
|
||||
# curator entirely until they can fix disk space.
|
||||
try:
|
||||
from agent import curator_backup
|
||||
snap = curator_backup.snapshot_skills(reason="pre-curator-run")
|
||||
if snap is not None and on_summary:
|
||||
try:
|
||||
on_summary(f"curator: snapshot created ({snap.name})")
|
||||
except Exception:
|
||||
pass
|
||||
except Exception as e:
|
||||
logger.debug("Curator pre-run snapshot failed: %s", e, exc_info=True)
|
||||
counts = apply_automatic_transitions(now=start)
|
||||
counts = apply_automatic_transitions(now=start)
|
||||
|
||||
auto_summary_parts = []
|
||||
if counts["marked_stale"]:
|
||||
@@ -1339,16 +1018,11 @@ def run_curator_review(
|
||||
auto_summary = ", ".join(auto_summary_parts) if auto_summary_parts else "no changes"
|
||||
|
||||
# Persist state before the LLM pass so a crash mid-review still records
|
||||
# the run and doesn't immediately re-trigger. In dry-run we do NOT bump
|
||||
# last_run_at or run_count — a preview shouldn't push the next scheduled
|
||||
# real pass out. We still record a summary so `hermes curator status`
|
||||
# shows that a preview ran.
|
||||
# the run and doesn't immediately re-trigger.
|
||||
state = load_state()
|
||||
if not dry_run:
|
||||
state["last_run_at"] = start.isoformat()
|
||||
state["run_count"] = int(state.get("run_count", 0)) + 1
|
||||
prefix = "dry-run auto: " if dry_run else "auto: "
|
||||
state["last_run_summary"] = f"{prefix}{auto_summary}"
|
||||
state["last_run_at"] = start.isoformat()
|
||||
state["run_count"] = int(state.get("run_count", 0)) + 1
|
||||
state["last_run_summary"] = f"auto: {auto_summary}"
|
||||
save_state(state)
|
||||
|
||||
def _llm_pass():
|
||||
@@ -1364,7 +1038,7 @@ def run_curator_review(
|
||||
try:
|
||||
candidate_list = _render_candidate_list()
|
||||
if "No agent-created skills" in candidate_list:
|
||||
final_summary = f"{prefix}{auto_summary}; llm: skipped (no candidates)"
|
||||
final_summary = f"auto: {auto_summary}; llm: skipped (no candidates)"
|
||||
llm_meta = {
|
||||
"final": "",
|
||||
"summary": "skipped (no candidates)",
|
||||
@@ -1374,21 +1048,14 @@ def run_curator_review(
|
||||
"error": None,
|
||||
}
|
||||
else:
|
||||
if dry_run:
|
||||
prompt = (
|
||||
f"{CURATOR_DRY_RUN_BANNER}\n\n"
|
||||
f"{CURATOR_REVIEW_PROMPT}\n\n"
|
||||
f"{candidate_list}"
|
||||
)
|
||||
else:
|
||||
prompt = f"{CURATOR_REVIEW_PROMPT}\n\n{candidate_list}"
|
||||
prompt = f"{CURATOR_REVIEW_PROMPT}\n\n{candidate_list}"
|
||||
llm_meta = _run_llm_review(prompt)
|
||||
final_summary = (
|
||||
f"{prefix}{auto_summary}; llm: {llm_meta.get('summary', 'no change')}"
|
||||
f"auto: {auto_summary}; llm: {llm_meta.get('summary', 'no change')}"
|
||||
)
|
||||
except Exception as e:
|
||||
logger.debug("Curator LLM pass failed: %s", e, exc_info=True)
|
||||
final_summary = f"{prefix}{auto_summary}; llm: error ({e})"
|
||||
final_summary = f"auto: {auto_summary}; llm: error ({e})"
|
||||
llm_meta = {
|
||||
"final": "",
|
||||
"summary": f"error ({e})",
|
||||
@@ -1447,52 +1114,6 @@ def run_curator_review(
|
||||
}
|
||||
|
||||
|
||||
def _resolve_review_runtime(cfg: Dict[str, Any]) -> _ReviewRuntimeBinding:
|
||||
"""Resolve provider/model and per-slot credentials for the curator review fork.
|
||||
|
||||
Same precedence as `_resolve_review_model()`. Non-empty ``api_key`` /
|
||||
``base_url`` from the active slot are returned as explicit overrides so
|
||||
``resolve_runtime_provider`` does not silently reuse the main chat
|
||||
credential chain for a routed auxiliary model.
|
||||
"""
|
||||
_main = cfg.get("model", {}) if isinstance(cfg.get("model"), dict) else {}
|
||||
_main_provider = _main.get("provider") or "auto"
|
||||
_main_model = _main.get("default") or _main.get("model") or ""
|
||||
|
||||
# 1. Canonical aux task slot
|
||||
_aux = cfg.get("auxiliary", {}) if isinstance(cfg.get("auxiliary"), dict) else {}
|
||||
_cur_task = _aux.get("curator", {}) if isinstance(_aux.get("curator"), dict) else {}
|
||||
_task_provider = (_cur_task.get("provider") or "").strip() or None
|
||||
_task_model = (_cur_task.get("model") or "").strip() or None
|
||||
if _task_provider and _task_provider != "auto" and _task_model:
|
||||
return _ReviewRuntimeBinding(
|
||||
_task_provider,
|
||||
_task_model,
|
||||
_strip_aux_credential(_cur_task.get("api_key")),
|
||||
_strip_aux_credential(_cur_task.get("base_url")),
|
||||
)
|
||||
|
||||
# 2. Legacy curator.auxiliary.{provider,model} (deprecated, pre-unification)
|
||||
_cur = cfg.get("curator", {}) if isinstance(cfg.get("curator"), dict) else {}
|
||||
_legacy = _cur.get("auxiliary", {}) if isinstance(_cur.get("auxiliary"), dict) else {}
|
||||
_legacy_provider = _legacy.get("provider") or None
|
||||
_legacy_model = _legacy.get("model") or None
|
||||
if _legacy_provider and _legacy_model:
|
||||
logger.info(
|
||||
"curator: using deprecated curator.auxiliary.{provider,model} "
|
||||
"config — please migrate to auxiliary.curator.{provider,model}"
|
||||
)
|
||||
return _ReviewRuntimeBinding(
|
||||
str(_legacy_provider),
|
||||
str(_legacy_model),
|
||||
_strip_aux_credential(_legacy.get("api_key")),
|
||||
_strip_aux_credential(_legacy.get("base_url")),
|
||||
)
|
||||
|
||||
# 3. Fall through to the main chat model
|
||||
return _ReviewRuntimeBinding(_main_provider, _main_model, None, None)
|
||||
|
||||
|
||||
def _resolve_review_model(cfg: Dict[str, Any]) -> tuple[str, str]:
|
||||
"""Pick (provider, model) for the curator review fork.
|
||||
|
||||
@@ -1508,8 +1129,32 @@ def _resolve_review_model(cfg: Dict[str, Any]) -> tuple[str, str]:
|
||||
2. Legacy ``curator.auxiliary.{provider,model}`` when both are set
|
||||
3. Main ``model.{provider,default/model}`` pair
|
||||
"""
|
||||
b = _resolve_review_runtime(cfg)
|
||||
return b.provider, b.model
|
||||
_main = cfg.get("model", {}) if isinstance(cfg.get("model"), dict) else {}
|
||||
_main_provider = _main.get("provider") or "auto"
|
||||
_main_model = _main.get("default") or _main.get("model") or ""
|
||||
|
||||
# 1. Canonical aux task slot
|
||||
_aux = cfg.get("auxiliary", {}) if isinstance(cfg.get("auxiliary"), dict) else {}
|
||||
_cur_task = _aux.get("curator", {}) if isinstance(_aux.get("curator"), dict) else {}
|
||||
_task_provider = (_cur_task.get("provider") or "").strip() or None
|
||||
_task_model = (_cur_task.get("model") or "").strip() or None
|
||||
if _task_provider and _task_provider != "auto" and _task_model:
|
||||
return _task_provider, _task_model
|
||||
|
||||
# 2. Legacy curator.auxiliary.{provider,model} (deprecated, pre-unification)
|
||||
_cur = cfg.get("curator", {}) if isinstance(cfg.get("curator"), dict) else {}
|
||||
_legacy = _cur.get("auxiliary", {}) if isinstance(_cur.get("auxiliary"), dict) else {}
|
||||
_legacy_provider = _legacy.get("provider") or None
|
||||
_legacy_model = _legacy.get("model") or None
|
||||
if _legacy_provider and _legacy_model:
|
||||
logger.info(
|
||||
"curator: using deprecated curator.auxiliary.{provider,model} "
|
||||
"config — please migrate to auxiliary.curator.{provider,model}"
|
||||
)
|
||||
return _legacy_provider, _legacy_model
|
||||
|
||||
# 3. Fall through to the main chat model
|
||||
return _main_provider, _main_model
|
||||
|
||||
|
||||
def _run_llm_review(prompt: str) -> Dict[str, Any]:
|
||||
@@ -1548,10 +1193,10 @@ def _run_llm_review(prompt: str) -> Dict[str, Any]:
|
||||
# arguments hits an auto-resolution path that fails for OAuth-only
|
||||
# providers and for pool-backed credentials.
|
||||
#
|
||||
# `_resolve_review_runtime()` honors `auxiliary.curator.{provider,model,...}`
|
||||
# `_resolve_review_model()` honors `auxiliary.curator.{provider,model}`
|
||||
# (canonical aux-task slot, wired through `hermes model` → auxiliary
|
||||
# picker and the dashboard Models tab), with a legacy fallback to
|
||||
# `curator.auxiliary.{provider,model,...}`. See docs/user-guide/features/curator.md.
|
||||
# `curator.auxiliary.{provider,model}`. See docs/user-guide/features/curator.md.
|
||||
_api_key = None
|
||||
_base_url = None
|
||||
_api_mode = None
|
||||
@@ -1561,13 +1206,9 @@ def _run_llm_review(prompt: str) -> Dict[str, Any]:
|
||||
from hermes_cli.config import load_config
|
||||
from hermes_cli.runtime_provider import resolve_runtime_provider
|
||||
_cfg = load_config()
|
||||
_binding = _resolve_review_runtime(_cfg)
|
||||
_provider, _model_name = _binding.provider, _binding.model
|
||||
_provider, _model_name = _resolve_review_model(_cfg)
|
||||
_rp = resolve_runtime_provider(
|
||||
requested=_provider,
|
||||
target_model=_model_name,
|
||||
explicit_api_key=_binding.explicit_api_key,
|
||||
explicit_base_url=_binding.explicit_base_url,
|
||||
requested=_provider, target_model=_model_name
|
||||
)
|
||||
_api_key = _rp.get("api_key")
|
||||
_base_url = _rp.get("base_url")
|
||||
|
||||
@@ -1,693 +0,0 @@
|
||||
"""Curator snapshot + rollback.
|
||||
|
||||
A pre-run snapshot of ``~/.hermes/skills/`` (excluding ``.curator_backups/``
|
||||
itself) is taken before any mutating curator pass. Snapshots are tar.gz
|
||||
files under ``~/.hermes/skills/.curator_backups/<utc-iso>/`` with a
|
||||
companion ``manifest.json`` describing the snapshot (reason, time, size,
|
||||
counted skill files). Rollback picks a snapshot, moves the current
|
||||
``skills/`` tree aside into another snapshot so even the rollback itself
|
||||
is undoable, then extracts the chosen snapshot into place.
|
||||
|
||||
The snapshot does NOT include:
|
||||
- ``.curator_backups/`` (would recurse)
|
||||
- ``.hub/`` (hub-installed skills — managed by the hub, not us)
|
||||
|
||||
It DOES include:
|
||||
- all SKILL.md files + their directories (``scripts/``, ``references/``,
|
||||
``templates/``, ``assets/``)
|
||||
- ``.usage.json`` (usage telemetry — needed to rehydrate state cleanly)
|
||||
- ``.archive/`` (so rollback restores previously-archived skills too)
|
||||
- ``.curator_state`` (so rolling back also restores the last-run-at
|
||||
pointer — otherwise the curator would immediately re-fire on the next
|
||||
tick)
|
||||
- ``.bundled_manifest`` (so protection markers stay consistent)
|
||||
|
||||
Alongside the skills tarball, each snapshot also captures a copy of
|
||||
``~/.hermes/cron/jobs.json`` as ``cron-jobs.json`` when it exists. Cron
|
||||
jobs reference skills by name in their ``skills``/``skill`` fields; the
|
||||
curator's consolidation pass rewrites those in place via
|
||||
``cron.jobs.rewrite_skill_refs()``. Without capturing the pre-run state,
|
||||
rolling back the skills tree would leave cron jobs pointing at the
|
||||
umbrella skills even though the narrow skills they were originally
|
||||
configured with have been restored. We store the whole jobs.json for
|
||||
fidelity but rollback only touches the ``skills``/``skill`` fields — the
|
||||
rest (schedule, next_run_at, enabled, prompt, etc.) is live state and
|
||||
we leave it alone.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
import tarfile
|
||||
import tempfile
|
||||
import time
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
from hermes_constants import get_hermes_home
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
DEFAULT_KEEP = 5
|
||||
|
||||
# Entries under skills/ that should NEVER be rolled up into a snapshot.
|
||||
# .hub/ is managed by the skills hub; rolling it back would break lockfile
|
||||
# invariants. .curator_backups is the backup dir itself — recursion bomb.
|
||||
_EXCLUDE_TOP_LEVEL = {".curator_backups", ".hub"}
|
||||
|
||||
# Snapshot id regex: UTC ISO with colons replaced by dashes so the filename
|
||||
# is portable (Windows-safe). An optional ``-NN`` suffix handles two
|
||||
# snapshots landing in the same wallclock second.
|
||||
_ID_RE = re.compile(r"^\d{4}-\d{2}-\d{2}T\d{2}-\d{2}-\d{2}Z(-\d{2})?$")
|
||||
|
||||
|
||||
def _backups_dir() -> Path:
|
||||
return get_hermes_home() / "skills" / ".curator_backups"
|
||||
|
||||
|
||||
def _skills_dir() -> Path:
|
||||
return get_hermes_home() / "skills"
|
||||
|
||||
|
||||
def _cron_jobs_file() -> Path:
|
||||
"""Source path for the live cron jobs store (``~/.hermes/cron/jobs.json``)."""
|
||||
return get_hermes_home() / "cron" / "jobs.json"
|
||||
|
||||
|
||||
CRON_JOBS_FILENAME = "cron-jobs.json"
|
||||
|
||||
|
||||
def _backup_cron_jobs_into(dest: Path) -> Dict[str, Any]:
|
||||
"""Copy the live cron jobs.json into ``dest`` as ``cron-jobs.json``.
|
||||
|
||||
Returns a small dict describing what was captured so the caller can
|
||||
fold it into the manifest. Never raises — if the cron file is missing
|
||||
or unreadable, the return dict has ``backed_up=False`` and the reason,
|
||||
and the snapshot proceeds without cron data (the snapshot is still
|
||||
useful for rolling back skills).
|
||||
"""
|
||||
src = _cron_jobs_file()
|
||||
info: Dict[str, Any] = {"backed_up": False, "jobs_count": 0}
|
||||
if not src.exists():
|
||||
info["reason"] = "no cron/jobs.json present"
|
||||
return info
|
||||
try:
|
||||
raw = src.read_text(encoding="utf-8")
|
||||
except OSError as e:
|
||||
logger.debug("Failed to read cron/jobs.json for backup: %s", e)
|
||||
info["reason"] = f"read error: {e}"
|
||||
return info
|
||||
# Count jobs as a nice diagnostic — but don't fail the snapshot if the
|
||||
# file is unparseable; just store the raw text and let rollback deal
|
||||
# with it (or not, if it's corrupted). jobs.json wraps the list as
|
||||
# `{"jobs": [...], "updated_at": ...}` — we count via that shape, and
|
||||
# fall back to bare-list shape just in case the format ever changes.
|
||||
try:
|
||||
parsed = json.loads(raw)
|
||||
if isinstance(parsed, dict):
|
||||
inner = parsed.get("jobs")
|
||||
if isinstance(inner, list):
|
||||
info["jobs_count"] = len(inner)
|
||||
elif isinstance(parsed, list):
|
||||
info["jobs_count"] = len(parsed)
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
info["jobs_count"] = 0
|
||||
info["parse_warning"] = "jobs.json was not valid JSON at snapshot time"
|
||||
try:
|
||||
(dest / CRON_JOBS_FILENAME).write_text(raw, encoding="utf-8")
|
||||
except OSError as e:
|
||||
logger.debug("Failed to write cron backup file: %s", e)
|
||||
info["reason"] = f"write error: {e}"
|
||||
return info
|
||||
info["backed_up"] = True
|
||||
return info
|
||||
|
||||
|
||||
def _utc_id(now: Optional[datetime] = None) -> str:
|
||||
"""UTC ISO-ish filesystem-safe timestamp: ``2026-05-01T13-05-42Z``."""
|
||||
if now is None:
|
||||
now = datetime.now(timezone.utc)
|
||||
# isoformat → "2026-05-01T13:05:42.123456+00:00"; strip subseconds and tz.
|
||||
s = now.replace(microsecond=0).isoformat()
|
||||
if s.endswith("+00:00"):
|
||||
s = s[:-6]
|
||||
return s.replace(":", "-") + "Z"
|
||||
|
||||
|
||||
def _load_config() -> Dict[str, Any]:
|
||||
try:
|
||||
from hermes_cli.config import load_config
|
||||
cfg = load_config()
|
||||
except Exception as e:
|
||||
logger.debug("Failed to load config for curator backup: %s", e)
|
||||
return {}
|
||||
if not isinstance(cfg, dict):
|
||||
return {}
|
||||
cur = cfg.get("curator") or {}
|
||||
if not isinstance(cur, dict):
|
||||
return {}
|
||||
bk = cur.get("backup") or {}
|
||||
return bk if isinstance(bk, dict) else {}
|
||||
|
||||
|
||||
def is_enabled() -> bool:
|
||||
"""Default ON — the whole point of the backup is safety by default."""
|
||||
return bool(_load_config().get("enabled", True))
|
||||
|
||||
|
||||
def get_keep() -> int:
|
||||
cfg = _load_config()
|
||||
try:
|
||||
n = int(cfg.get("keep", DEFAULT_KEEP))
|
||||
except (TypeError, ValueError):
|
||||
n = DEFAULT_KEEP
|
||||
return max(1, n)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Snapshot
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def _count_skill_files(base: Path) -> int:
|
||||
try:
|
||||
return sum(1 for _ in base.rglob("SKILL.md"))
|
||||
except OSError:
|
||||
return 0
|
||||
|
||||
|
||||
def _write_manifest(dest: Path, reason: str, archive_path: Path,
|
||||
skills_counted: int,
|
||||
cron_info: Optional[Dict[str, Any]] = None) -> None:
|
||||
manifest = {
|
||||
"id": dest.name,
|
||||
"reason": reason,
|
||||
"created_at": datetime.now(timezone.utc).isoformat(),
|
||||
"archive": archive_path.name,
|
||||
"archive_bytes": archive_path.stat().st_size,
|
||||
"skill_files": skills_counted,
|
||||
}
|
||||
if cron_info is not None:
|
||||
manifest["cron_jobs"] = {
|
||||
"backed_up": bool(cron_info.get("backed_up", False)),
|
||||
"jobs_count": int(cron_info.get("jobs_count", 0)),
|
||||
}
|
||||
if not cron_info.get("backed_up"):
|
||||
manifest["cron_jobs"]["reason"] = cron_info.get("reason", "not captured")
|
||||
if cron_info.get("parse_warning"):
|
||||
manifest["cron_jobs"]["parse_warning"] = cron_info["parse_warning"]
|
||||
(dest / "manifest.json").write_text(
|
||||
json.dumps(manifest, indent=2, sort_keys=True), encoding="utf-8"
|
||||
)
|
||||
|
||||
|
||||
def snapshot_skills(reason: str = "manual") -> Optional[Path]:
|
||||
"""Create a tar.gz snapshot of ``~/.hermes/skills/`` and prune old ones.
|
||||
|
||||
Returns the snapshot directory path, or ``None`` if the snapshot was
|
||||
skipped (backup disabled, skills dir missing, or an IO error occurred —
|
||||
in which case we log at debug and return None so the curator never
|
||||
aborts a pass because of a backup failure).
|
||||
"""
|
||||
if not is_enabled():
|
||||
logger.debug("Curator backup disabled by config; skipping snapshot")
|
||||
return None
|
||||
|
||||
skills = _skills_dir()
|
||||
if not skills.exists():
|
||||
logger.debug("No ~/.hermes/skills/ directory — nothing to back up")
|
||||
return None
|
||||
|
||||
backups = _backups_dir()
|
||||
try:
|
||||
backups.mkdir(parents=True, exist_ok=True)
|
||||
except OSError as e:
|
||||
logger.debug("Failed to create backups dir %s: %s", backups, e)
|
||||
return None
|
||||
|
||||
# Uniquify: if a snapshot with the same second already exists (can
|
||||
# happen if two curator runs fire in the same second), append a short
|
||||
# counter. Avoids clobbering and avoids timestamp collisions.
|
||||
base_id = _utc_id()
|
||||
snap_id = base_id
|
||||
counter = 1
|
||||
while (backups / snap_id).exists():
|
||||
snap_id = f"{base_id}-{counter:02d}"
|
||||
counter += 1
|
||||
|
||||
dest = backups / snap_id
|
||||
try:
|
||||
dest.mkdir(parents=True, exist_ok=False)
|
||||
except OSError as e:
|
||||
logger.debug("Failed to create snapshot dir %s: %s", dest, e)
|
||||
return None
|
||||
|
||||
archive = dest / "skills.tar.gz"
|
||||
try:
|
||||
# Stream into the tarball — no tempdir copy needed.
|
||||
with tarfile.open(archive, "w:gz", compresslevel=6) as tf:
|
||||
for entry in sorted(skills.iterdir()):
|
||||
if entry.name in _EXCLUDE_TOP_LEVEL:
|
||||
continue
|
||||
# arcname: store paths relative to skills/ so extraction
|
||||
# drops cleanly back into the skills dir.
|
||||
tf.add(str(entry), arcname=entry.name, recursive=True)
|
||||
# Capture cron/jobs.json alongside the tarball. Never fails the
|
||||
# snapshot — the skills side is the core guarantee; cron is
|
||||
# additive. We still record in the manifest whether it was
|
||||
# captured so rollback can surface "no cron data in this snapshot".
|
||||
cron_info = _backup_cron_jobs_into(dest)
|
||||
_write_manifest(dest, reason, archive,
|
||||
_count_skill_files(skills),
|
||||
cron_info=cron_info)
|
||||
except (OSError, tarfile.TarError) as e:
|
||||
logger.debug("Curator snapshot failed: %s", e, exc_info=True)
|
||||
# Clean up partial snapshot
|
||||
try:
|
||||
shutil.rmtree(dest, ignore_errors=True)
|
||||
except OSError:
|
||||
pass
|
||||
return None
|
||||
|
||||
_prune_old(keep=get_keep())
|
||||
logger.info("Curator snapshot created: %s (%s)", snap_id, reason)
|
||||
return dest
|
||||
|
||||
|
||||
def _prune_old(keep: int) -> List[str]:
|
||||
"""Delete regular snapshots beyond the newest *keep*. Returns deleted
|
||||
ids. Staging dirs (``.rollback-staging-*``) are implementation detail
|
||||
and pruned independently on every call."""
|
||||
backups = _backups_dir()
|
||||
if not backups.exists():
|
||||
return []
|
||||
entries: List[Tuple[str, Path]] = []
|
||||
stale_staging: List[Path] = []
|
||||
for child in backups.iterdir():
|
||||
if not child.is_dir():
|
||||
continue
|
||||
if child.name.startswith(".rollback-staging-"):
|
||||
# Staging dirs are only supposed to exist briefly during a
|
||||
# rollback. If we find one here (e.g. from a crashed rollback),
|
||||
# clean it up opportunistically.
|
||||
stale_staging.append(child)
|
||||
continue
|
||||
if _ID_RE.match(child.name):
|
||||
entries.append((child.name, child))
|
||||
# Newest first (lexicographic works because the id is UTC ISO).
|
||||
entries.sort(key=lambda t: t[0], reverse=True)
|
||||
deleted: List[str] = []
|
||||
for _, path in entries[keep:]:
|
||||
try:
|
||||
shutil.rmtree(path)
|
||||
deleted.append(path.name)
|
||||
except OSError as e:
|
||||
logger.debug("Failed to prune %s: %s", path, e)
|
||||
for path in stale_staging:
|
||||
try:
|
||||
shutil.rmtree(path)
|
||||
except OSError as e:
|
||||
logger.debug("Failed to clean stale staging dir %s: %s", path, e)
|
||||
return deleted
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# List + rollback
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def _read_manifest(snap_dir: Path) -> Dict[str, Any]:
|
||||
mf = snap_dir / "manifest.json"
|
||||
if not mf.exists():
|
||||
return {}
|
||||
try:
|
||||
return json.loads(mf.read_text(encoding="utf-8"))
|
||||
except (OSError, json.JSONDecodeError):
|
||||
return {}
|
||||
|
||||
|
||||
def list_backups() -> List[Dict[str, Any]]:
|
||||
"""Return all restorable snapshots, newest first. Only entries with a
|
||||
real ``skills.tar.gz`` tarball are listed — transient
|
||||
``.rollback-staging-*`` directories created mid-rollback are
|
||||
implementation detail and not shown."""
|
||||
backups = _backups_dir()
|
||||
if not backups.exists():
|
||||
return []
|
||||
out: List[Dict[str, Any]] = []
|
||||
for child in sorted(backups.iterdir(), reverse=True):
|
||||
if not child.is_dir():
|
||||
continue
|
||||
if not _ID_RE.match(child.name):
|
||||
continue
|
||||
if not (child / "skills.tar.gz").exists():
|
||||
continue
|
||||
mf = _read_manifest(child)
|
||||
mf.setdefault("id", child.name)
|
||||
mf.setdefault("path", str(child))
|
||||
if "archive_bytes" not in mf:
|
||||
arc = child / "skills.tar.gz"
|
||||
try:
|
||||
mf["archive_bytes"] = arc.stat().st_size
|
||||
except OSError:
|
||||
mf["archive_bytes"] = 0
|
||||
out.append(mf)
|
||||
return out
|
||||
|
||||
|
||||
def _resolve_backup(backup_id: Optional[str]) -> Optional[Path]:
|
||||
"""Return the path of the requested backup, or the newest one if
|
||||
*backup_id* is None. Returns None if no match."""
|
||||
backups = _backups_dir()
|
||||
if not backups.exists():
|
||||
return None
|
||||
if backup_id:
|
||||
target = backups / backup_id
|
||||
if (
|
||||
target.is_dir()
|
||||
and _ID_RE.match(backup_id)
|
||||
and (target / "skills.tar.gz").exists()
|
||||
):
|
||||
return target
|
||||
return None
|
||||
candidates = [
|
||||
c for c in sorted(backups.iterdir(), reverse=True)
|
||||
if c.is_dir() and _ID_RE.match(c.name) and (c / "skills.tar.gz").exists()
|
||||
]
|
||||
return candidates[0] if candidates else None
|
||||
|
||||
|
||||
def _restore_cron_skill_links(snapshot_dir: Path) -> Dict[str, Any]:
|
||||
"""Reconcile backed-up cron skill links into the live ``cron/jobs.json``.
|
||||
|
||||
We do NOT overwrite the whole cron file. Only the ``skills`` and
|
||||
``skill`` fields are restored, and only on jobs that still exist in the
|
||||
current file (matched by ``id``). Everything else about the job —
|
||||
schedule, next_run_at, last_run_at, enabled, prompt, workdir, hooks —
|
||||
is live state that the user/scheduler has modified since the snapshot;
|
||||
overwriting it would regress unrelated cron activity.
|
||||
|
||||
Rules:
|
||||
- Jobs present in backup AND live, with differing skills → skills restored.
|
||||
- Jobs present in backup AND live, with matching skills → no-op.
|
||||
- Jobs present in backup but gone from live (user deleted the job
|
||||
after the snapshot) → skipped, noted in the return report.
|
||||
- Jobs present in live but not in backup (user created a new cron
|
||||
job after the snapshot) → left untouched.
|
||||
|
||||
Never raises; failures are captured in the return dict. Writes through
|
||||
``cron.jobs`` to pick up the same lock + atomic-write path that tick()
|
||||
uses, so we don't race the scheduler.
|
||||
"""
|
||||
report: Dict[str, Any] = {
|
||||
"attempted": False,
|
||||
"restored": [],
|
||||
"skipped_missing": [],
|
||||
"unchanged": 0,
|
||||
"error": None,
|
||||
}
|
||||
backup_file = snapshot_dir / CRON_JOBS_FILENAME
|
||||
if not backup_file.exists():
|
||||
report["error"] = f"snapshot has no {CRON_JOBS_FILENAME}"
|
||||
return report
|
||||
|
||||
try:
|
||||
backup_text = backup_file.read_text(encoding="utf-8")
|
||||
backup_parsed = json.loads(backup_text)
|
||||
except (OSError, json.JSONDecodeError) as e:
|
||||
report["error"] = f"failed to load backed-up jobs: {e}"
|
||||
return report
|
||||
# jobs.json on disk is `{"jobs": [...], "updated_at": ...}`; accept both
|
||||
# that shape and a bare list for forward compat.
|
||||
if isinstance(backup_parsed, dict):
|
||||
backup_jobs = backup_parsed.get("jobs")
|
||||
elif isinstance(backup_parsed, list):
|
||||
backup_jobs = backup_parsed
|
||||
else:
|
||||
backup_jobs = None
|
||||
if not isinstance(backup_jobs, list):
|
||||
report["error"] = "backed-up cron-jobs.json has no jobs list"
|
||||
return report
|
||||
|
||||
# Build a lookup of the backed-up skill state keyed by job id.
|
||||
# We only need the two skill-ish fields (legacy single and modern list).
|
||||
backup_by_id: Dict[str, Dict[str, Any]] = {}
|
||||
for job in backup_jobs:
|
||||
if not isinstance(job, dict):
|
||||
continue
|
||||
jid = job.get("id")
|
||||
if not isinstance(jid, str) or not jid:
|
||||
continue
|
||||
backup_by_id[jid] = {
|
||||
"skills": job.get("skills"),
|
||||
"skill": job.get("skill"),
|
||||
"name": job.get("name") or jid,
|
||||
}
|
||||
|
||||
if not backup_by_id:
|
||||
report["attempted"] = True # we tried but there was nothing to do
|
||||
return report
|
||||
|
||||
# Load and rewrite the live jobs under the scheduler's lock.
|
||||
try:
|
||||
from cron.jobs import load_jobs, save_jobs, _jobs_file_lock
|
||||
except ImportError as e:
|
||||
report["error"] = f"cron module unavailable: {e}"
|
||||
return report
|
||||
|
||||
report["attempted"] = True
|
||||
try:
|
||||
with _jobs_file_lock:
|
||||
live_jobs = load_jobs()
|
||||
changed = False
|
||||
|
||||
live_ids = set()
|
||||
for live in live_jobs:
|
||||
if not isinstance(live, dict):
|
||||
continue
|
||||
jid = live.get("id")
|
||||
if not isinstance(jid, str) or not jid:
|
||||
continue
|
||||
live_ids.add(jid)
|
||||
|
||||
backup = backup_by_id.get(jid)
|
||||
if backup is None:
|
||||
continue # live job didn't exist at snapshot time
|
||||
|
||||
cur_skills = live.get("skills")
|
||||
cur_skill = live.get("skill")
|
||||
bkp_skills = backup.get("skills")
|
||||
bkp_skill = backup.get("skill")
|
||||
|
||||
if cur_skills == bkp_skills and cur_skill == bkp_skill:
|
||||
report["unchanged"] += 1
|
||||
continue
|
||||
|
||||
# Restore. Preserve absence (don't force the key to appear
|
||||
# if the backup didn't have it either).
|
||||
if bkp_skills is None:
|
||||
live.pop("skills", None)
|
||||
else:
|
||||
live["skills"] = bkp_skills
|
||||
if bkp_skill is None:
|
||||
live.pop("skill", None)
|
||||
else:
|
||||
live["skill"] = bkp_skill
|
||||
|
||||
report["restored"].append({
|
||||
"job_id": jid,
|
||||
"job_name": backup.get("name") or jid,
|
||||
"from": {"skills": cur_skills, "skill": cur_skill},
|
||||
"to": {"skills": bkp_skills, "skill": bkp_skill},
|
||||
})
|
||||
changed = True
|
||||
|
||||
# Jobs in backup but not in live = user deleted them after snapshot
|
||||
for jid, backup in backup_by_id.items():
|
||||
if jid not in live_ids:
|
||||
report["skipped_missing"].append({
|
||||
"job_id": jid,
|
||||
"job_name": backup.get("name") or jid,
|
||||
})
|
||||
|
||||
if changed:
|
||||
save_jobs(live_jobs)
|
||||
except Exception as e: # noqa: BLE001 — rollback must not die mid-restore
|
||||
logger.debug("Cron skill-link restore failed: %s", e, exc_info=True)
|
||||
report["error"] = f"restore failed mid-flight: {e}"
|
||||
|
||||
return report
|
||||
|
||||
|
||||
|
||||
def rollback(backup_id: Optional[str] = None) -> Tuple[bool, str, Optional[Path]]:
|
||||
"""Restore ``~/.hermes/skills/`` from a snapshot.
|
||||
|
||||
Strategy:
|
||||
1. Resolve the target snapshot (explicit id or newest regular).
|
||||
2. Take a safety snapshot of the CURRENT skills tree under
|
||||
``.curator_backups/pre-rollback-<ts>/`` so the rollback itself is
|
||||
undoable.
|
||||
3. Move all current top-level entries (except ``.curator_backups``
|
||||
and ``.hub``) into a tempdir.
|
||||
4. Extract the chosen snapshot into ``~/.hermes/skills/``.
|
||||
5. On failure during 4, move the tempdir contents back (best-effort)
|
||||
and return failure.
|
||||
|
||||
Returns ``(ok, message, snapshot_path)``.
|
||||
"""
|
||||
target = _resolve_backup(backup_id)
|
||||
if target is None:
|
||||
return (
|
||||
False,
|
||||
f"no matching backup found"
|
||||
+ (f" for id '{backup_id}'" if backup_id else "")
|
||||
+ " (use `hermes curator rollback --list` to see available snapshots)",
|
||||
None,
|
||||
)
|
||||
archive = target / "skills.tar.gz"
|
||||
if not archive.exists():
|
||||
return (False, f"snapshot {target.name} has no skills.tar.gz — corrupted?", None)
|
||||
|
||||
skills = _skills_dir()
|
||||
skills.mkdir(parents=True, exist_ok=True)
|
||||
backups = _backups_dir()
|
||||
backups.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Step 2: safety snapshot of current state FIRST. If this fails we bail
|
||||
# out before touching anything — otherwise a failed extract could leave
|
||||
# the user with no skills.
|
||||
try:
|
||||
snapshot_skills(reason=f"pre-rollback to {target.name}")
|
||||
except Exception as e:
|
||||
return (False, f"pre-rollback safety snapshot failed: {e}", None)
|
||||
|
||||
# Additionally move current entries into an internal staging dir so
|
||||
# the extract happens into an empty skills tree (predictable result).
|
||||
# This dir is implementation detail — not listed as a restorable
|
||||
# backup. The safety snapshot above is the user-facing undo handle.
|
||||
staged = backups / f".rollback-staging-{_utc_id()}"
|
||||
try:
|
||||
staged.mkdir(parents=True, exist_ok=False)
|
||||
except OSError as e:
|
||||
return (False, f"failed to create staging dir: {e}", None)
|
||||
|
||||
moved: List[Tuple[Path, Path]] = []
|
||||
try:
|
||||
for entry in list(skills.iterdir()):
|
||||
if entry.name in _EXCLUDE_TOP_LEVEL:
|
||||
continue
|
||||
dest = staged / entry.name
|
||||
shutil.move(str(entry), str(dest))
|
||||
moved.append((entry, dest))
|
||||
except OSError as e:
|
||||
# Best-effort rollback of the move
|
||||
for orig, dest in moved:
|
||||
try:
|
||||
shutil.move(str(dest), str(orig))
|
||||
except OSError:
|
||||
pass
|
||||
try:
|
||||
shutil.rmtree(staged, ignore_errors=True)
|
||||
except OSError:
|
||||
pass
|
||||
return (False, f"failed to stage current skills: {e}", None)
|
||||
|
||||
# Step 4: extract the snapshot into skills/
|
||||
try:
|
||||
with tarfile.open(archive, "r:gz") as tf:
|
||||
# Python 3.12+ supports filter='data' for safer extraction.
|
||||
# Fall back to the unfiltered call for older interpreters but
|
||||
# still reject absolute paths and .. components defensively.
|
||||
for member in tf.getmembers():
|
||||
name = member.name
|
||||
if name.startswith("/") or ".." in Path(name).parts:
|
||||
raise tarfile.TarError(
|
||||
f"refusing to extract unsafe path: {name!r}"
|
||||
)
|
||||
try:
|
||||
tf.extractall(str(skills), filter="data") # type: ignore[call-arg]
|
||||
except TypeError:
|
||||
# Python < 3.12 — no filter kwarg
|
||||
tf.extractall(str(skills))
|
||||
except (OSError, tarfile.TarError) as e:
|
||||
# Best-effort recover: move staged contents back
|
||||
for orig, dest in moved:
|
||||
try:
|
||||
shutil.move(str(dest), str(orig))
|
||||
except OSError:
|
||||
pass
|
||||
try:
|
||||
shutil.rmtree(staged, ignore_errors=True)
|
||||
except OSError:
|
||||
pass
|
||||
return (False, f"snapshot extract failed (state restored): {e}", None)
|
||||
|
||||
# Extract succeeded — the staging dir has served its purpose. The
|
||||
# user's undo handle is the safety snapshot tarball we took earlier.
|
||||
try:
|
||||
shutil.rmtree(staged, ignore_errors=True)
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
# Reconcile cron skill-links. Surgical: only the skills/skill fields
|
||||
# on jobs matched by id. Everything else in jobs.json is live state
|
||||
# (schedule, next_run_at, enabled, prompt, etc.) and we leave it
|
||||
# alone. Failures here don't fail the overall rollback — the skills
|
||||
# tree is already restored, which is the main guarantee.
|
||||
cron_report = _restore_cron_skill_links(target)
|
||||
|
||||
summary_bits = [f"restored from snapshot {target.name}"]
|
||||
if cron_report.get("attempted"):
|
||||
restored_n = len(cron_report.get("restored") or [])
|
||||
skipped_n = len(cron_report.get("skipped_missing") or [])
|
||||
if cron_report.get("error"):
|
||||
summary_bits.append(f"cron links: error — {cron_report['error']}")
|
||||
elif restored_n == 0 and skipped_n == 0 and cron_report.get("unchanged", 0) == 0:
|
||||
# Attempted but nothing matched — empty snapshot or no overlapping ids.
|
||||
pass
|
||||
else:
|
||||
parts = []
|
||||
if restored_n:
|
||||
parts.append(f"{restored_n} job(s) had skill links restored")
|
||||
if skipped_n:
|
||||
parts.append(f"{skipped_n} backed-up job(s) no longer exist (skipped)")
|
||||
if cron_report.get("unchanged"):
|
||||
parts.append(f"{cron_report['unchanged']} already matched")
|
||||
summary_bits.append("cron links: " + ", ".join(parts))
|
||||
|
||||
logger.info("Curator rollback: restored from %s (cron_report=%s)",
|
||||
target.name, cron_report)
|
||||
return (True, "; ".join(summary_bits), target)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Human-readable summary for CLI
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def format_size(n: int) -> str:
|
||||
for unit in ("B", "KB", "MB", "GB"):
|
||||
if n < 1024 or unit == "GB":
|
||||
return f"{n:.1f} {unit}" if unit != "B" else f"{n} B"
|
||||
n /= 1024
|
||||
return f"{n:.1f} GB"
|
||||
|
||||
|
||||
def summarize_backups() -> str:
|
||||
rows = list_backups()
|
||||
if not rows:
|
||||
return "No curator snapshots yet."
|
||||
lines = [f"{'id':<24} {'reason':<40} {'skills':>6} {'size':>8}"]
|
||||
lines.append("─" * len(lines[0]))
|
||||
for r in rows:
|
||||
lines.append(
|
||||
f"{r.get('id','?'):<24} "
|
||||
f"{(r.get('reason','?') or '?')[:40]:<40} "
|
||||
f"{r.get('skill_files', 0):>6} "
|
||||
f"{format_size(int(r.get('archive_bytes', 0))):>8}"
|
||||
)
|
||||
return "\n".join(lines)
|
||||
@@ -20,25 +20,25 @@ def summarize_manual_compression(
|
||||
headline = f"No changes from compression: {before_count} messages"
|
||||
if after_tokens == before_tokens:
|
||||
token_line = (
|
||||
f"Approx request size: ~{before_tokens:,} tokens (unchanged)"
|
||||
f"Rough transcript estimate: ~{before_tokens:,} tokens (unchanged)"
|
||||
)
|
||||
else:
|
||||
token_line = (
|
||||
f"Approx request size: ~{before_tokens:,} → "
|
||||
f"Rough transcript estimate: ~{before_tokens:,} → "
|
||||
f"~{after_tokens:,} tokens"
|
||||
)
|
||||
else:
|
||||
headline = f"Compressed: {before_count} → {after_count} messages"
|
||||
token_line = (
|
||||
f"Approx request size: ~{before_tokens:,} → "
|
||||
f"Rough transcript estimate: ~{before_tokens:,} → "
|
||||
f"~{after_tokens:,} tokens"
|
||||
)
|
||||
|
||||
note = None
|
||||
if not noop and after_count < before_count and after_tokens > before_tokens:
|
||||
note = (
|
||||
"Note: fewer messages can still raise this estimate when "
|
||||
"compression rewrites the transcript into denser summaries."
|
||||
"Note: fewer messages can still raise this rough transcript estimate "
|
||||
"when compression rewrites the transcript into denser summaries."
|
||||
)
|
||||
|
||||
return {
|
||||
|
||||
@@ -81,56 +81,15 @@ def _repair_schema(node: Any, is_schema: bool = True) -> Any:
|
||||
return repaired
|
||||
|
||||
# Rule 2: when anyOf is present, type belongs only on the children.
|
||||
# Additionally, Moonshot rejects null-type branches inside anyOf
|
||||
# (enum value (<nil>) does not match any type in [string]).
|
||||
# Collapse the anyOf to the first non-null branch and infer its type.
|
||||
if "anyOf" in repaired and isinstance(repaired["anyOf"], list):
|
||||
repaired.pop("type", None)
|
||||
non_null = [b for b in repaired["anyOf"]
|
||||
if isinstance(b, dict) and b.get("type") != "null"]
|
||||
if non_null and len(non_null) < len(repaired["anyOf"]):
|
||||
# Drop the anyOf wrapper — keep only the non-null branch.
|
||||
# If there's a single non-null branch, promote it and fall
|
||||
# through to Rules 1/3 so nullable/enum cleanup still applies
|
||||
# to the merged node.
|
||||
if len(non_null) == 1:
|
||||
merge = {k: v for k, v in repaired.items() if k != "anyOf"}
|
||||
merge.update(non_null[0])
|
||||
repaired = merge
|
||||
else:
|
||||
repaired["anyOf"] = non_null
|
||||
return repaired
|
||||
else:
|
||||
# Nothing to collapse — parent type stripped, children already
|
||||
# repaired by the recursive walk above.
|
||||
return repaired
|
||||
|
||||
# Moonshot also rejects non-standard keywords like ``nullable`` on
|
||||
# parameter schemas — strip it.
|
||||
repaired.pop("nullable", None)
|
||||
return repaired
|
||||
|
||||
# Rule 1: property schemas without type need one. $ref nodes are exempt
|
||||
# — their type comes from the referenced definition.
|
||||
# Fill missing type BEFORE Rule 3 so enum cleanup can check the type.
|
||||
if "$ref" not in repaired:
|
||||
repaired = _fill_missing_type(repaired)
|
||||
|
||||
# Rule 3: Moonshot rejects null/empty-string values inside enum arrays
|
||||
# when the parent type is a scalar (string, integer, etc.). The error:
|
||||
# "enum value (<nil>) does not match any type in [string]"
|
||||
# Strip null and empty-string from enum values, and if the enum becomes
|
||||
# empty, drop it entirely.
|
||||
if "enum" in repaired and isinstance(repaired["enum"], list):
|
||||
node_type = repaired.get("type")
|
||||
if node_type in ("string", "integer", "number", "boolean"):
|
||||
cleaned = [v for v in repaired["enum"]
|
||||
if v is not None and v != ""]
|
||||
if cleaned:
|
||||
repaired["enum"] = cleaned
|
||||
else:
|
||||
repaired.pop("enum")
|
||||
|
||||
return repaired
|
||||
if "$ref" in repaired:
|
||||
return repaired
|
||||
return _fill_missing_type(repaired)
|
||||
|
||||
|
||||
def _fill_missing_type(node: Dict[str, Any]) -> Dict[str, Any]:
|
||||
|
||||
@@ -182,64 +182,6 @@ SKILLS_GUIDANCE = (
|
||||
"Skills that aren't maintained become liabilities."
|
||||
)
|
||||
|
||||
KANBAN_GUIDANCE = (
|
||||
"# Kanban task execution protocol\n"
|
||||
"You have been assigned ONE task from "
|
||||
"the shared board at `~/.hermes/kanban.db`. Your task id is in "
|
||||
"`$HERMES_KANBAN_TASK`; your workspace is `$HERMES_KANBAN_WORKSPACE`. "
|
||||
"The `kanban_*` tools in your schema are your primary coordination surface — "
|
||||
"they write directly to the shared SQLite DB and work regardless of terminal "
|
||||
"backend (local/docker/modal/ssh).\n"
|
||||
"\n"
|
||||
"## Lifecycle\n"
|
||||
"\n"
|
||||
"1. **Orient.** Call `kanban_show()` first (no args — it defaults to your "
|
||||
"task). The response includes title, body, parent-task handoffs (summary + "
|
||||
"metadata), any prior attempts on this task if you're a retry, the full "
|
||||
"comment thread, and a pre-formatted `worker_context` you can treat as "
|
||||
"ground truth.\n"
|
||||
"2. **Work inside the workspace.** `cd $HERMES_KANBAN_WORKSPACE` before "
|
||||
"any file operations. The workspace is yours for this run. Don't modify "
|
||||
"files outside it unless the task explicitly asks.\n"
|
||||
"3. **Heartbeat on long operations.** Call `kanban_heartbeat(note=...)` "
|
||||
"every few minutes during long subprocesses (training, encoding, crawling). "
|
||||
"Skip heartbeats for short tasks.\n"
|
||||
"4. **Block on genuine ambiguity.** If you need a human decision you cannot "
|
||||
"infer (missing credentials, UX choice, paywalled source, peer output you "
|
||||
"need first), call `kanban_block(reason=\"...\")` and stop. Don't guess. "
|
||||
"The user will unblock with context and the dispatcher will respawn you.\n"
|
||||
"5. **Complete with structured handoff.** Call `kanban_complete(summary=..., "
|
||||
"metadata=...)`. `summary` is 1–3 human-readable sentences naming concrete "
|
||||
"artifacts. `metadata` is machine-readable facts "
|
||||
"(`{changed_files: [...], tests_run: N, decisions: [...]}`). Downstream "
|
||||
"workers read both via their own `kanban_show`. Never put secrets / "
|
||||
"tokens / raw PII in either field — run rows are durable forever.\n"
|
||||
"6. **If follow-up work appears, create it; don't do it.** Use "
|
||||
"`kanban_create(title=..., assignee=<right-profile>, parents=[your-task-id])` "
|
||||
"to spawn a child task for the appropriate specialist profile instead of "
|
||||
"scope-creeping into the next thing.\n"
|
||||
"\n"
|
||||
"## Orchestrator mode\n"
|
||||
"\n"
|
||||
"If your task is itself a decomposition task (e.g. a planner profile given "
|
||||
"a high-level goal), use `kanban_create` to fan out into child tasks — one "
|
||||
"per specialist, each with an explicit `assignee` and `parents=[...]` to "
|
||||
"express dependencies. Then `kanban_complete` your own task with a summary "
|
||||
"of the decomposition. Do NOT execute the work yourself; your job is "
|
||||
"routing, not implementation.\n"
|
||||
"\n"
|
||||
"## Do NOT\n"
|
||||
"\n"
|
||||
"- Do not shell out to `hermes kanban <verb>` for board operations. Use "
|
||||
"the `kanban_*` tools — they work across all terminal backends.\n"
|
||||
"- Do not complete a task you didn't actually finish. Block it.\n"
|
||||
"- Do not assign follow-up work to yourself. Assign it to the right "
|
||||
"specialist profile.\n"
|
||||
"- Do not call `delegate_task` as a board substitute. `delegate_task` is "
|
||||
"for short reasoning subtasks inside your own run; board tasks are for "
|
||||
"cross-agent handoffs that outlive one API loop."
|
||||
)
|
||||
|
||||
TOOL_USE_ENFORCEMENT_GUIDANCE = (
|
||||
"# Tool-use enforcement\n"
|
||||
"You MUST use your tools to take action — do not describe what you would do "
|
||||
|
||||
+3
-38
@@ -6,7 +6,6 @@ can invoke skills via /skill-name commands.
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, Optional
|
||||
@@ -21,35 +20,10 @@ from agent.skill_preprocessing import (
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_skill_commands: Dict[str, Dict[str, Any]] = {}
|
||||
_skill_commands_platform: Optional[str] = None
|
||||
# Patterns for sanitizing skill names into clean hyphen-separated slugs.
|
||||
_SKILL_INVALID_CHARS = re.compile(r"[^a-z0-9-]")
|
||||
_SKILL_MULTI_HYPHEN = re.compile(r"-{2,}")
|
||||
|
||||
|
||||
def _resolve_skill_commands_platform() -> Optional[str]:
|
||||
"""Return the current platform scope used for disabled-skill filtering.
|
||||
|
||||
Used to detect when the active platform has shifted so
|
||||
:func:`get_skill_commands` can drop a stale cache that was populated
|
||||
for a different platform's ``skills.platform_disabled`` view (#14536).
|
||||
|
||||
Resolves from (in order) ``HERMES_PLATFORM`` env var and
|
||||
``HERMES_SESSION_PLATFORM`` from the gateway session context. Returns
|
||||
``None`` when no platform scope is active (e.g. classic CLI, RL
|
||||
rollouts, standalone scripts).
|
||||
"""
|
||||
try:
|
||||
from gateway.session_context import get_session_env
|
||||
|
||||
resolved_platform = (
|
||||
os.getenv("HERMES_PLATFORM")
|
||||
or get_session_env("HERMES_SESSION_PLATFORM")
|
||||
)
|
||||
except Exception:
|
||||
resolved_platform = os.getenv("HERMES_PLATFORM")
|
||||
return resolved_platform or None
|
||||
|
||||
def _load_skill_payload(skill_identifier: str, task_id: str | None = None) -> tuple[dict[str, Any], Path | None, str] | None:
|
||||
"""Load a skill by name/path and return (loaded_payload, skill_dir, display_name)."""
|
||||
raw_identifier = (skill_identifier or "").strip()
|
||||
@@ -244,8 +218,7 @@ def scan_skill_commands() -> Dict[str, Dict[str, Any]]:
|
||||
Returns:
|
||||
Dict mapping "/skill-name" to {name, description, skill_md_path, skill_dir}.
|
||||
"""
|
||||
global _skill_commands, _skill_commands_platform
|
||||
_skill_commands_platform = _resolve_skill_commands_platform()
|
||||
global _skill_commands
|
||||
_skill_commands = {}
|
||||
try:
|
||||
from tools.skills_tool import SKILLS_DIR, _parse_frontmatter, skill_matches_platform, _get_disabled_skill_names
|
||||
@@ -305,16 +278,8 @@ def scan_skill_commands() -> Dict[str, Dict[str, Any]]:
|
||||
|
||||
|
||||
def get_skill_commands() -> Dict[str, Dict[str, Any]]:
|
||||
"""Return the current skill commands mapping (scan first if empty).
|
||||
|
||||
Rescans when the active platform scope changes (e.g. a gateway
|
||||
process serving Telegram and Discord concurrently) so each platform
|
||||
sees its own ``skills.platform_disabled`` view (#14536).
|
||||
"""
|
||||
if (
|
||||
not _skill_commands
|
||||
or _skill_commands_platform != _resolve_skill_commands_platform()
|
||||
):
|
||||
"""Return the current skill commands mapping (scan first if empty)."""
|
||||
if not _skill_commands:
|
||||
scan_skill_commands()
|
||||
return _skill_commands
|
||||
|
||||
|
||||
@@ -1,455 +0,0 @@
|
||||
"""Pure tool-call loop guardrail primitives.
|
||||
|
||||
The controller in this module is intentionally side-effect free: it tracks
|
||||
per-turn tool-call observations and returns decisions. Runtime code owns whether
|
||||
those decisions become warning guidance, synthetic tool results, or controlled
|
||||
turn halts.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any, Mapping
|
||||
|
||||
from utils import safe_json_loads
|
||||
|
||||
|
||||
IDEMPOTENT_TOOL_NAMES = frozenset(
|
||||
{
|
||||
"read_file",
|
||||
"search_files",
|
||||
"web_search",
|
||||
"web_extract",
|
||||
"session_search",
|
||||
"browser_snapshot",
|
||||
"browser_console",
|
||||
"browser_get_images",
|
||||
"mcp_filesystem_read_file",
|
||||
"mcp_filesystem_read_text_file",
|
||||
"mcp_filesystem_read_multiple_files",
|
||||
"mcp_filesystem_list_directory",
|
||||
"mcp_filesystem_list_directory_with_sizes",
|
||||
"mcp_filesystem_directory_tree",
|
||||
"mcp_filesystem_get_file_info",
|
||||
"mcp_filesystem_search_files",
|
||||
}
|
||||
)
|
||||
|
||||
MUTATING_TOOL_NAMES = frozenset(
|
||||
{
|
||||
"terminal",
|
||||
"execute_code",
|
||||
"write_file",
|
||||
"patch",
|
||||
"todo",
|
||||
"memory",
|
||||
"skill_manage",
|
||||
"browser_click",
|
||||
"browser_type",
|
||||
"browser_press",
|
||||
"browser_scroll",
|
||||
"browser_navigate",
|
||||
"send_message",
|
||||
"cronjob",
|
||||
"delegate_task",
|
||||
"process",
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ToolCallGuardrailConfig:
|
||||
"""Thresholds for per-turn tool-call loop detection.
|
||||
|
||||
Warnings are enabled by default and never prevent tool execution. Hard stops
|
||||
are explicit opt-in so interactive CLI/TUI sessions get a gentle nudge unless
|
||||
the user enables circuit-breaker behavior in config.yaml.
|
||||
"""
|
||||
|
||||
warnings_enabled: bool = True
|
||||
hard_stop_enabled: bool = False
|
||||
exact_failure_warn_after: int = 2
|
||||
exact_failure_block_after: int = 5
|
||||
same_tool_failure_warn_after: int = 3
|
||||
same_tool_failure_halt_after: int = 8
|
||||
no_progress_warn_after: int = 2
|
||||
no_progress_block_after: int = 5
|
||||
idempotent_tools: frozenset[str] = field(default_factory=lambda: IDEMPOTENT_TOOL_NAMES)
|
||||
mutating_tools: frozenset[str] = field(default_factory=lambda: MUTATING_TOOL_NAMES)
|
||||
|
||||
@classmethod
|
||||
def from_mapping(cls, data: Mapping[str, Any] | None) -> "ToolCallGuardrailConfig":
|
||||
"""Build config from the `tool_loop_guardrails` config.yaml section."""
|
||||
if not isinstance(data, Mapping):
|
||||
return cls()
|
||||
|
||||
warn_after = data.get("warn_after")
|
||||
if not isinstance(warn_after, Mapping):
|
||||
warn_after = {}
|
||||
hard_stop_after = data.get("hard_stop_after")
|
||||
if not isinstance(hard_stop_after, Mapping):
|
||||
hard_stop_after = {}
|
||||
|
||||
defaults = cls()
|
||||
return cls(
|
||||
warnings_enabled=_as_bool(data.get("warnings_enabled"), defaults.warnings_enabled),
|
||||
hard_stop_enabled=_as_bool(data.get("hard_stop_enabled"), defaults.hard_stop_enabled),
|
||||
exact_failure_warn_after=_positive_int(
|
||||
warn_after.get("exact_failure", data.get("exact_failure_warn_after")),
|
||||
defaults.exact_failure_warn_after,
|
||||
),
|
||||
same_tool_failure_warn_after=_positive_int(
|
||||
warn_after.get("same_tool_failure", data.get("same_tool_failure_warn_after")),
|
||||
defaults.same_tool_failure_warn_after,
|
||||
),
|
||||
no_progress_warn_after=_positive_int(
|
||||
warn_after.get("idempotent_no_progress", data.get("no_progress_warn_after")),
|
||||
defaults.no_progress_warn_after,
|
||||
),
|
||||
exact_failure_block_after=_positive_int(
|
||||
hard_stop_after.get("exact_failure", data.get("exact_failure_block_after")),
|
||||
defaults.exact_failure_block_after,
|
||||
),
|
||||
same_tool_failure_halt_after=_positive_int(
|
||||
hard_stop_after.get("same_tool_failure", data.get("same_tool_failure_halt_after")),
|
||||
defaults.same_tool_failure_halt_after,
|
||||
),
|
||||
no_progress_block_after=_positive_int(
|
||||
hard_stop_after.get("idempotent_no_progress", data.get("no_progress_block_after")),
|
||||
defaults.no_progress_block_after,
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ToolCallSignature:
|
||||
"""Stable, non-reversible identity for a tool name plus canonical args."""
|
||||
|
||||
tool_name: str
|
||||
args_hash: str
|
||||
|
||||
@classmethod
|
||||
def from_call(cls, tool_name: str, args: Mapping[str, Any] | None) -> "ToolCallSignature":
|
||||
canonical = canonical_tool_args(args or {})
|
||||
return cls(tool_name=tool_name, args_hash=_sha256(canonical))
|
||||
|
||||
def to_metadata(self) -> dict[str, str]:
|
||||
"""Return public metadata without raw argument values."""
|
||||
return {"tool_name": self.tool_name, "args_hash": self.args_hash}
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ToolGuardrailDecision:
|
||||
"""Decision returned by the tool-call guardrail controller."""
|
||||
|
||||
action: str = "allow" # allow | warn | block | halt
|
||||
code: str = "allow"
|
||||
message: str = ""
|
||||
tool_name: str = ""
|
||||
count: int = 0
|
||||
signature: ToolCallSignature | None = None
|
||||
|
||||
@property
|
||||
def allows_execution(self) -> bool:
|
||||
return self.action in {"allow", "warn"}
|
||||
|
||||
@property
|
||||
def should_halt(self) -> bool:
|
||||
return self.action in {"block", "halt"}
|
||||
|
||||
def to_metadata(self) -> dict[str, Any]:
|
||||
data: dict[str, Any] = {
|
||||
"action": self.action,
|
||||
"code": self.code,
|
||||
"message": self.message,
|
||||
"tool_name": self.tool_name,
|
||||
"count": self.count,
|
||||
}
|
||||
if self.signature is not None:
|
||||
data["signature"] = self.signature.to_metadata()
|
||||
return data
|
||||
|
||||
|
||||
def canonical_tool_args(args: Mapping[str, Any]) -> str:
|
||||
"""Return sorted compact JSON for parsed tool arguments."""
|
||||
if not isinstance(args, Mapping):
|
||||
raise TypeError(f"tool args must be a mapping, got {type(args).__name__}")
|
||||
return json.dumps(
|
||||
args,
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
default=str,
|
||||
)
|
||||
|
||||
|
||||
def classify_tool_failure(tool_name: str, result: str | None) -> tuple[bool, str]:
|
||||
"""Safety-fallback classifier used only when callers don't pass ``failed``.
|
||||
|
||||
Mirrors ``agent.display._detect_tool_failure`` exactly so the guardrail
|
||||
never disagrees with the CLI's user-visible ``[error]`` tag. Production
|
||||
callers in ``run_agent.py`` always pass an explicit ``failed=`` derived
|
||||
from ``_detect_tool_failure``; this function exists so standalone callers
|
||||
(tests, tooling) still get consistent behavior.
|
||||
"""
|
||||
if result is None:
|
||||
return False, ""
|
||||
|
||||
if tool_name == "terminal":
|
||||
data = safe_json_loads(result)
|
||||
if isinstance(data, dict):
|
||||
exit_code = data.get("exit_code")
|
||||
if exit_code is not None and exit_code != 0:
|
||||
return True, f" [exit {exit_code}]"
|
||||
return False, ""
|
||||
|
||||
if tool_name == "memory":
|
||||
data = safe_json_loads(result)
|
||||
if isinstance(data, dict):
|
||||
if data.get("success") is False and "exceed the limit" in data.get("error", ""):
|
||||
return True, " [full]"
|
||||
|
||||
lower = result[:500].lower()
|
||||
if '"error"' in lower or '"failed"' in lower or result.startswith("Error"):
|
||||
return True, " [error]"
|
||||
|
||||
return False, ""
|
||||
|
||||
|
||||
class ToolCallGuardrailController:
|
||||
"""Per-turn controller for repeated failed/non-progressing tool calls."""
|
||||
|
||||
def __init__(self, config: ToolCallGuardrailConfig | None = None):
|
||||
self.config = config or ToolCallGuardrailConfig()
|
||||
self.reset_for_turn()
|
||||
|
||||
def reset_for_turn(self) -> None:
|
||||
self._exact_failure_counts: dict[ToolCallSignature, int] = {}
|
||||
self._same_tool_failure_counts: dict[str, int] = {}
|
||||
self._no_progress: dict[ToolCallSignature, tuple[str, int]] = {}
|
||||
self._halt_decision: ToolGuardrailDecision | None = None
|
||||
|
||||
@property
|
||||
def halt_decision(self) -> ToolGuardrailDecision | None:
|
||||
return self._halt_decision
|
||||
|
||||
def before_call(self, tool_name: str, args: Mapping[str, Any] | None) -> ToolGuardrailDecision:
|
||||
signature = ToolCallSignature.from_call(tool_name, _coerce_args(args))
|
||||
if not self.config.hard_stop_enabled:
|
||||
return ToolGuardrailDecision(tool_name=tool_name, signature=signature)
|
||||
|
||||
exact_count = self._exact_failure_counts.get(signature, 0)
|
||||
if exact_count >= self.config.exact_failure_block_after:
|
||||
decision = ToolGuardrailDecision(
|
||||
action="block",
|
||||
code="repeated_exact_failure_block",
|
||||
message=(
|
||||
f"Blocked {tool_name}: the same tool call failed {exact_count} "
|
||||
"times with identical arguments. Stop retrying it unchanged; "
|
||||
"change strategy or explain the blocker."
|
||||
),
|
||||
tool_name=tool_name,
|
||||
count=exact_count,
|
||||
signature=signature,
|
||||
)
|
||||
self._halt_decision = decision
|
||||
return decision
|
||||
|
||||
if self._is_idempotent(tool_name):
|
||||
record = self._no_progress.get(signature)
|
||||
if record is not None:
|
||||
_result_hash, repeat_count = record
|
||||
if repeat_count >= self.config.no_progress_block_after:
|
||||
decision = ToolGuardrailDecision(
|
||||
action="block",
|
||||
code="idempotent_no_progress_block",
|
||||
message=(
|
||||
f"Blocked {tool_name}: this read-only call returned the same "
|
||||
f"result {repeat_count} times. Stop repeating it unchanged; "
|
||||
"use the result already provided or try a different query."
|
||||
),
|
||||
tool_name=tool_name,
|
||||
count=repeat_count,
|
||||
signature=signature,
|
||||
)
|
||||
self._halt_decision = decision
|
||||
return decision
|
||||
|
||||
return ToolGuardrailDecision(tool_name=tool_name, signature=signature)
|
||||
|
||||
def after_call(
|
||||
self,
|
||||
tool_name: str,
|
||||
args: Mapping[str, Any] | None,
|
||||
result: str | None,
|
||||
*,
|
||||
failed: bool | None = None,
|
||||
) -> ToolGuardrailDecision:
|
||||
args = _coerce_args(args)
|
||||
signature = ToolCallSignature.from_call(tool_name, args)
|
||||
if failed is None:
|
||||
failed, _ = classify_tool_failure(tool_name, result)
|
||||
|
||||
if failed:
|
||||
exact_count = self._exact_failure_counts.get(signature, 0) + 1
|
||||
self._exact_failure_counts[signature] = exact_count
|
||||
self._no_progress.pop(signature, None)
|
||||
|
||||
same_count = self._same_tool_failure_counts.get(tool_name, 0) + 1
|
||||
self._same_tool_failure_counts[tool_name] = same_count
|
||||
|
||||
if self.config.hard_stop_enabled and same_count >= self.config.same_tool_failure_halt_after:
|
||||
decision = ToolGuardrailDecision(
|
||||
action="halt",
|
||||
code="same_tool_failure_halt",
|
||||
message=(
|
||||
f"Stopped {tool_name}: it failed {same_count} times this turn. "
|
||||
"Stop retrying the same failing tool path and choose a different approach."
|
||||
),
|
||||
tool_name=tool_name,
|
||||
count=same_count,
|
||||
signature=signature,
|
||||
)
|
||||
self._halt_decision = decision
|
||||
return decision
|
||||
|
||||
if self.config.warnings_enabled and exact_count >= self.config.exact_failure_warn_after:
|
||||
return ToolGuardrailDecision(
|
||||
action="warn",
|
||||
code="repeated_exact_failure_warning",
|
||||
message=(
|
||||
f"{tool_name} has failed {exact_count} times with identical arguments. "
|
||||
"This looks like a loop; inspect the error and change strategy "
|
||||
"instead of retrying it unchanged."
|
||||
),
|
||||
tool_name=tool_name,
|
||||
count=exact_count,
|
||||
signature=signature,
|
||||
)
|
||||
|
||||
if self.config.warnings_enabled and same_count >= self.config.same_tool_failure_warn_after:
|
||||
return ToolGuardrailDecision(
|
||||
action="warn",
|
||||
code="same_tool_failure_warning",
|
||||
message=(
|
||||
f"{tool_name} has failed {same_count} times this turn. "
|
||||
"This looks like a loop; change approach before retrying."
|
||||
),
|
||||
tool_name=tool_name,
|
||||
count=same_count,
|
||||
signature=signature,
|
||||
)
|
||||
|
||||
return ToolGuardrailDecision(tool_name=tool_name, count=exact_count, signature=signature)
|
||||
|
||||
self._exact_failure_counts.pop(signature, None)
|
||||
self._same_tool_failure_counts.pop(tool_name, None)
|
||||
|
||||
if not self._is_idempotent(tool_name):
|
||||
self._no_progress.pop(signature, None)
|
||||
return ToolGuardrailDecision(tool_name=tool_name, signature=signature)
|
||||
|
||||
result_hash = _result_hash(result)
|
||||
previous = self._no_progress.get(signature)
|
||||
repeat_count = 1
|
||||
if previous is not None and previous[0] == result_hash:
|
||||
repeat_count = previous[1] + 1
|
||||
self._no_progress[signature] = (result_hash, repeat_count)
|
||||
|
||||
if self.config.warnings_enabled and repeat_count >= self.config.no_progress_warn_after:
|
||||
return ToolGuardrailDecision(
|
||||
action="warn",
|
||||
code="idempotent_no_progress_warning",
|
||||
message=(
|
||||
f"{tool_name} returned the same result {repeat_count} times. "
|
||||
"Use the result already provided or change the query instead of "
|
||||
"repeating it unchanged."
|
||||
),
|
||||
tool_name=tool_name,
|
||||
count=repeat_count,
|
||||
signature=signature,
|
||||
)
|
||||
|
||||
return ToolGuardrailDecision(tool_name=tool_name, count=repeat_count, signature=signature)
|
||||
|
||||
def _is_idempotent(self, tool_name: str) -> bool:
|
||||
if tool_name in self.config.mutating_tools:
|
||||
return False
|
||||
return tool_name in self.config.idempotent_tools
|
||||
|
||||
|
||||
def toolguard_synthetic_result(decision: ToolGuardrailDecision) -> str:
|
||||
"""Build a synthetic role=tool content string for a blocked tool call."""
|
||||
return json.dumps(
|
||||
{
|
||||
"error": decision.message,
|
||||
"guardrail": decision.to_metadata(),
|
||||
},
|
||||
ensure_ascii=False,
|
||||
)
|
||||
|
||||
|
||||
def append_toolguard_guidance(result: str, decision: ToolGuardrailDecision) -> str:
|
||||
"""Append runtime guidance to the current tool result content."""
|
||||
if decision.action not in {"warn", "halt"} or not decision.message:
|
||||
return result
|
||||
label = "Tool loop hard stop" if decision.action == "halt" else "Tool loop warning"
|
||||
suffix = (
|
||||
f"\n\n[{label}: "
|
||||
f"{decision.code}; count={decision.count}; {decision.message}]"
|
||||
)
|
||||
return (result or "") + suffix
|
||||
|
||||
|
||||
def _coerce_args(args: Mapping[str, Any] | None) -> Mapping[str, Any]:
|
||||
return args if isinstance(args, Mapping) else {}
|
||||
|
||||
|
||||
def _result_hash(result: str | None) -> str:
|
||||
parsed = safe_json_loads(result or "")
|
||||
if parsed is not None:
|
||||
try:
|
||||
canonical = json.dumps(
|
||||
parsed,
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
default=str,
|
||||
)
|
||||
except TypeError:
|
||||
canonical = str(parsed)
|
||||
else:
|
||||
canonical = result or ""
|
||||
return _sha256(canonical)
|
||||
|
||||
|
||||
def _as_bool(value: Any, default: bool) -> bool:
|
||||
if value is None:
|
||||
return default
|
||||
if isinstance(value, bool):
|
||||
return value
|
||||
if isinstance(value, (int, float)):
|
||||
return bool(value)
|
||||
if isinstance(value, str):
|
||||
lowered = value.strip().lower()
|
||||
if lowered in {"1", "true", "yes", "on", "enabled"}:
|
||||
return True
|
||||
if lowered in {"0", "false", "no", "off", "disabled"}:
|
||||
return False
|
||||
return default
|
||||
|
||||
|
||||
def _positive_int(value: Any, default: int) -> int:
|
||||
if value is None:
|
||||
return default
|
||||
try:
|
||||
parsed = int(value)
|
||||
except (TypeError, ValueError):
|
||||
return default
|
||||
return parsed if parsed >= 1 else default
|
||||
|
||||
|
||||
def _sha256(value: str) -> str:
|
||||
return hashlib.sha256(value.encode("utf-8")).hexdigest()
|
||||
@@ -477,13 +477,9 @@ class ChatCompletionsTransport(ProviderTransport):
|
||||
# so keep them apart in provider_data rather than merging.
|
||||
reasoning = getattr(msg, "reasoning", None)
|
||||
reasoning_content = getattr(msg, "reasoning_content", None)
|
||||
if reasoning_content is None and hasattr(msg, "model_extra"):
|
||||
model_extra = getattr(msg, "model_extra", None) or {}
|
||||
if isinstance(model_extra, dict) and "reasoning_content" in model_extra:
|
||||
reasoning_content = model_extra["reasoning_content"]
|
||||
|
||||
provider_data: Dict[str, Any] = {}
|
||||
if reasoning_content is not None:
|
||||
if reasoning_content:
|
||||
provider_data["reasoning_content"] = reasoning_content
|
||||
rd = getattr(msg, "reasoning_details", None)
|
||||
if rd:
|
||||
|
||||
@@ -143,18 +143,7 @@ class ResponsesApiTransport(ProviderTransport):
|
||||
kwargs["max_output_tokens"] = max_tokens
|
||||
|
||||
if is_xai_responses and session_id:
|
||||
existing_extra_headers = kwargs.get("extra_headers")
|
||||
merged_extra_headers: Dict[str, str] = {}
|
||||
if isinstance(existing_extra_headers, dict):
|
||||
merged_extra_headers.update(
|
||||
{
|
||||
str(key): str(value)
|
||||
for key, value in existing_extra_headers.items()
|
||||
if key and value is not None
|
||||
}
|
||||
)
|
||||
merged_extra_headers["x-grok-conv-id"] = session_id
|
||||
kwargs["extra_headers"] = merged_extra_headers
|
||||
kwargs["extra_headers"] = {"x-grok-conv-id": session_id}
|
||||
|
||||
return kwargs
|
||||
|
||||
|
||||
@@ -121,18 +121,6 @@ model:
|
||||
# # Data policy: "allow" (default) or "deny" to exclude providers that may store data
|
||||
# # data_collection: "deny"
|
||||
|
||||
# =============================================================================
|
||||
# OpenRouter Response Caching (only applies when using OpenRouter)
|
||||
# =============================================================================
|
||||
# Cache identical API responses at the OpenRouter edge for free instant replays.
|
||||
# When enabled, identical requests (same model, messages, parameters) return
|
||||
# cached responses with zero billing. Separate from Anthropic prompt caching.
|
||||
# See: https://openrouter.ai/docs/guides/features/response-caching
|
||||
#
|
||||
# openrouter:
|
||||
# response_cache: true # Enable response caching (default: true)
|
||||
# response_cache_ttl: 300 # Cache TTL in seconds, 1-86400 (default: 300)
|
||||
|
||||
# =============================================================================
|
||||
# Git Worktree Isolation
|
||||
# =============================================================================
|
||||
@@ -301,25 +289,6 @@ browser:
|
||||
# after this period of no activity between agent loops (default: 120 = 2 minutes)
|
||||
inactivity_timeout: 120
|
||||
|
||||
# =============================================================================
|
||||
# Tool Loop Guardrails
|
||||
# =============================================================================
|
||||
# Soft warnings are enabled by default. They append guidance to repeated failed
|
||||
# or non-progressing tool results but still let the tool execute. Hard stops are
|
||||
# opt-in circuit breakers for autonomous/cron sessions where stopping a loop is
|
||||
# preferable to spending the full iteration budget.
|
||||
tool_loop_guardrails:
|
||||
warnings_enabled: true
|
||||
hard_stop_enabled: false
|
||||
warn_after:
|
||||
exact_failure: 2
|
||||
same_tool_failure: 3
|
||||
idempotent_no_progress: 2
|
||||
hard_stop_after:
|
||||
exact_failure: 5
|
||||
same_tool_failure: 8
|
||||
idempotent_no_progress: 5
|
||||
|
||||
# =============================================================================
|
||||
# Context Compression (Auto-shrinks long conversations)
|
||||
# =============================================================================
|
||||
|
||||
@@ -15,6 +15,7 @@ Usage:
|
||||
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
import sys
|
||||
import json
|
||||
@@ -85,7 +86,7 @@ from hermes_cli.browser_connect import (
|
||||
try_launch_chrome_debug,
|
||||
)
|
||||
from hermes_cli.env_loader import load_hermes_dotenv
|
||||
from utils import base_url_host_matches, is_truthy_value
|
||||
from utils import base_url_host_matches
|
||||
|
||||
_hermes_home = get_hermes_home()
|
||||
_project_env = Path(__file__).parent / '.env'
|
||||
@@ -459,19 +460,32 @@ def load_cli_config() -> Dict[str, Any]:
|
||||
if "backend" in terminal_config:
|
||||
terminal_config["env_type"] = terminal_config["backend"]
|
||||
|
||||
# CWD resolution for CLI/TUI. The gateway has its own config bridge in
|
||||
# gateway/run.py but may lazily import cli.py (triggering this code).
|
||||
# Local backend: always os.getcwd(). Use `cd /dir && hermes` to control it.
|
||||
# Non-local with placeholder: pop so terminal_tool uses its per-backend default.
|
||||
# Non-local with explicit path: keep as-is.
|
||||
# Handle special cwd values: "." or "auto" means use current working directory.
|
||||
# Only resolve to the host's CWD for the local backend where the host
|
||||
# filesystem is directly accessible. For ALL remote/container backends
|
||||
# (ssh, docker, modal, singularity), the host path doesn't exist on the
|
||||
# target -- remove the key so terminal_tool.py uses its per-backend default.
|
||||
#
|
||||
# GUARD: If TERMINAL_CWD is already set to a real absolute path (by the
|
||||
# gateway's config bridge earlier in the process), don't clobber it.
|
||||
# This prevents a lazy import of cli.py during gateway runtime from
|
||||
# rewriting TERMINAL_CWD to the service's working directory.
|
||||
# See issue #10817.
|
||||
_CWD_PLACEHOLDERS = (".", "auto", "cwd")
|
||||
effective_backend = terminal_config.get("env_type", "local")
|
||||
|
||||
if effective_backend == "local":
|
||||
terminal_config["cwd"] = os.getcwd()
|
||||
defaults["terminal"]["cwd"] = terminal_config["cwd"]
|
||||
elif terminal_config.get("cwd") in _CWD_PLACEHOLDERS:
|
||||
terminal_config.pop("cwd", None)
|
||||
if terminal_config.get("cwd") in _CWD_PLACEHOLDERS:
|
||||
_existing_cwd = os.environ.get("TERMINAL_CWD", "")
|
||||
if _existing_cwd and _existing_cwd not in _CWD_PLACEHOLDERS and os.path.isabs(_existing_cwd):
|
||||
# Gateway (or earlier startup) already resolved a real path — keep it
|
||||
terminal_config["cwd"] = _existing_cwd
|
||||
defaults["terminal"]["cwd"] = _existing_cwd
|
||||
else:
|
||||
effective_backend = terminal_config.get("env_type", "local")
|
||||
if effective_backend == "local":
|
||||
terminal_config["cwd"] = os.getcwd()
|
||||
defaults["terminal"]["cwd"] = terminal_config["cwd"]
|
||||
else:
|
||||
# Remove so TERMINAL_CWD stays unset → tool picks backend default
|
||||
terminal_config.pop("cwd", None)
|
||||
|
||||
env_mappings = {
|
||||
"env_type": "TERMINAL_ENV",
|
||||
@@ -504,18 +518,13 @@ def load_cli_config() -> Dict[str, Any]:
|
||||
"sudo_password": "SUDO_PASSWORD",
|
||||
}
|
||||
|
||||
# Bridge config → env vars for terminal_tool. TERMINAL_CWD is force-exported
|
||||
# UNLESS we're inside a gateway process (detected by _HERMES_GATEWAY marker)
|
||||
# where it was already set correctly by gateway/run.py's config bridge.
|
||||
_is_gateway = os.environ.get("_HERMES_GATEWAY") == "1"
|
||||
# Apply config values to env vars so terminal_tool picks them up.
|
||||
# If the config file explicitly has a [terminal] section, those values are
|
||||
# authoritative and override any .env settings. When using defaults only
|
||||
# (no config file or no terminal section), don't overwrite env vars that
|
||||
# were already set by .env -- the user's .env is the fallback source.
|
||||
for config_key, env_var in env_mappings.items():
|
||||
if config_key in terminal_config:
|
||||
if env_var == "TERMINAL_CWD":
|
||||
if _is_gateway:
|
||||
continue
|
||||
# CLI: always export (overrides stale .env or inherited values)
|
||||
os.environ[env_var] = str(terminal_config[config_key])
|
||||
continue
|
||||
if _file_has_terminal_config or env_var not in os.environ:
|
||||
val = terminal_config[config_key]
|
||||
if isinstance(val, list):
|
||||
@@ -591,7 +600,6 @@ def load_cli_config() -> Dict[str, Any]:
|
||||
# Load configuration at module startup
|
||||
CLI_CONFIG = load_cli_config()
|
||||
|
||||
|
||||
# Initialize centralized logging early — agent.log + errors.log in ~/.hermes/logs/.
|
||||
# This ensures CLI sessions produce a log trail even before AIAgent is instantiated.
|
||||
try:
|
||||
@@ -926,20 +934,6 @@ def _run_state_db_auto_maintenance(session_db) -> None:
|
||||
try:
|
||||
from hermes_cli.config import load_config as _load_full_config
|
||||
from hermes_constants import get_hermes_home as _get_hermes_home
|
||||
_hermes_home_maint = _get_hermes_home()
|
||||
|
||||
# One-time prune of empty TUI ghost sessions.
|
||||
try:
|
||||
if not session_db.get_meta("ghost_session_prune_v1"):
|
||||
pruned = session_db.prune_empty_ghost_sessions(
|
||||
sessions_dir=_hermes_home_maint / "sessions"
|
||||
)
|
||||
session_db.set_meta("ghost_session_prune_v1", "1")
|
||||
if pruned:
|
||||
logger.info("Pruned %d empty TUI ghost sessions", pruned)
|
||||
except Exception as _prune_exc:
|
||||
logger.debug("Ghost session prune skipped: %s", _prune_exc)
|
||||
|
||||
cfg = (_load_full_config().get("sessions") or {})
|
||||
if not cfg.get("auto_prune", False):
|
||||
return
|
||||
@@ -947,7 +941,7 @@ def _run_state_db_auto_maintenance(session_db) -> None:
|
||||
retention_days=int(cfg.get("retention_days", 90)),
|
||||
min_interval_hours=int(cfg.get("min_interval_hours", 24)),
|
||||
vacuum=bool(cfg.get("vacuum_after_prune", True)),
|
||||
sessions_dir=_hermes_home_maint / "sessions",
|
||||
sessions_dir=_get_hermes_home() / "sessions",
|
||||
)
|
||||
except Exception as exc:
|
||||
logger.debug("state.db auto-maintenance skipped: %s", exc)
|
||||
@@ -1246,73 +1240,8 @@ def _cprint(text: str):
|
||||
Raw ANSI escapes written via print() are swallowed by patch_stdout's
|
||||
StdoutProxy. Routing through print_formatted_text(ANSI(...)) lets
|
||||
prompt_toolkit parse the escapes and render real colors.
|
||||
|
||||
When called from a background thread while a prompt_toolkit
|
||||
``Application`` is running (the common case for the self-improvement
|
||||
background review's ``💾 …`` summary, curator summaries, and other
|
||||
bg-thread emissions), a direct ``_pt_print`` races with the input
|
||||
area's redraw and the line can end up visually buried behind the
|
||||
prompt. Route those cases through ``run_in_terminal`` via
|
||||
``loop.call_soon_threadsafe``, which pauses the input area, prints
|
||||
the line above it, and redraws the prompt cleanly.
|
||||
"""
|
||||
try:
|
||||
from prompt_toolkit.application import get_app_or_none, run_in_terminal
|
||||
except Exception:
|
||||
_pt_print(_PT_ANSI(text))
|
||||
return
|
||||
|
||||
app = None
|
||||
try:
|
||||
app = get_app_or_none()
|
||||
except Exception:
|
||||
app = None
|
||||
|
||||
# No active app, or we're already on the app's main thread: the
|
||||
# direct prompt_toolkit print is safe and matches existing behavior
|
||||
# (spinner frames, streamed tokens, tool activity prefixes, …).
|
||||
if app is None or not getattr(app, "_is_running", False):
|
||||
_pt_print(_PT_ANSI(text))
|
||||
return
|
||||
|
||||
try:
|
||||
loop = app.loop # type: ignore[attr-defined]
|
||||
except Exception:
|
||||
loop = None
|
||||
if loop is None:
|
||||
_pt_print(_PT_ANSI(text))
|
||||
return
|
||||
|
||||
import asyncio as _asyncio
|
||||
try:
|
||||
current_loop = _asyncio.get_event_loop_policy().get_event_loop()
|
||||
except Exception:
|
||||
current_loop = None
|
||||
# Same thread as the app's loop → safe to print directly.
|
||||
if current_loop is loop and loop.is_running():
|
||||
_pt_print(_PT_ANSI(text))
|
||||
return
|
||||
|
||||
# Cross-thread emission: ask the app's event loop to schedule a
|
||||
# ``run_in_terminal`` that wraps ``_pt_print``. This hides the
|
||||
# prompt, prints, and redraws. Fire-and-forget — if scheduling
|
||||
# fails we fall back to a direct print so the line isn't lost.
|
||||
def _schedule():
|
||||
try:
|
||||
run_in_terminal(lambda: _pt_print(_PT_ANSI(text)))
|
||||
except Exception:
|
||||
try:
|
||||
_pt_print(_PT_ANSI(text))
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
try:
|
||||
loop.call_soon_threadsafe(_schedule)
|
||||
except Exception:
|
||||
try:
|
||||
_pt_print(_PT_ANSI(text))
|
||||
except Exception:
|
||||
pass
|
||||
_pt_print(_PT_ANSI(text))
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -2124,8 +2053,6 @@ class HermesCLI:
|
||||
|
||||
# Parse and validate toolsets
|
||||
self.enabled_toolsets = toolsets
|
||||
self.disabled_toolsets = CLI_CONFIG["agent"].get("disabled_toolsets") or []
|
||||
|
||||
if toolsets and "all" not in toolsets and "*" not in toolsets:
|
||||
# Validate each toolset — MCP server names are resolved via
|
||||
# live registry aliases (registered during discover_mcp_tools),
|
||||
@@ -2920,14 +2847,7 @@ class HermesCLI:
|
||||
|
||||
def _expand_ref(match):
|
||||
path = Path(match.group(1))
|
||||
# Use try/except instead of path.exists() to avoid TOCTOU race:
|
||||
# the paste file may be deleted between check and read, causing
|
||||
# the input to be silently dropped (#17666).
|
||||
try:
|
||||
return path.read_text(encoding="utf-8")
|
||||
except (OSError, IOError):
|
||||
logger.warning("Paste file gone or unreadable, returning placeholder: %s", path)
|
||||
return match.group(0)
|
||||
return path.read_text(encoding="utf-8") if path.exists() else match.group(0)
|
||||
|
||||
return paste_ref_re.sub(_expand_ref, text)
|
||||
|
||||
@@ -3583,7 +3503,6 @@ class HermesCLI:
|
||||
credential_pool=runtime.get("credential_pool"),
|
||||
max_iterations=self.max_turns,
|
||||
enabled_toolsets=self.enabled_toolsets,
|
||||
disabled_toolsets=self.disabled_toolsets,
|
||||
verbose_logging=self.verbose,
|
||||
quiet_mode=not self.verbose,
|
||||
ephemeral_system_prompt=self.system_prompt if self.system_prompt else None,
|
||||
@@ -3631,18 +3550,14 @@ class HermesCLI:
|
||||
tuple(runtime.get("args") or ()),
|
||||
)
|
||||
|
||||
# Force-create DB row on /title intent, then apply title.
|
||||
if self._pending_title and self._session_db and self.agent:
|
||||
if self._pending_title and self._session_db:
|
||||
try:
|
||||
self.agent._ensure_db_session()
|
||||
if self.agent._session_db_created:
|
||||
self._session_db.set_session_title(self.session_id, self._pending_title)
|
||||
_cprint(f" Session title applied: {self._pending_title}")
|
||||
self._pending_title = None
|
||||
# else: row creation failed transiently — keep _pending_title for retry
|
||||
self._session_db.set_session_title(self.session_id, self._pending_title)
|
||||
_cprint(f" Session title applied: {self._pending_title}")
|
||||
self._pending_title = None
|
||||
except (ValueError, Exception) as e:
|
||||
_cprint(f" Could not apply pending title: {e}")
|
||||
# Keep _pending_title so it can be retried after row creation succeeds
|
||||
self._pending_title = None
|
||||
return True
|
||||
except Exception as e:
|
||||
ChatConsole().print(f"[bold red]Failed to initialize agent: {e}[/]")
|
||||
@@ -4970,7 +4885,6 @@ class HermesCLI:
|
||||
|
||||
if self._session_db:
|
||||
try:
|
||||
self.agent._session_db_created = False
|
||||
self._session_db.create_session(
|
||||
session_id=self.session_id,
|
||||
source=os.environ.get("HERMES_SESSION_SOURCE", "cli"),
|
||||
@@ -4980,7 +4894,6 @@ class HermesCLI:
|
||||
"reasoning_config": self.reasoning_config,
|
||||
},
|
||||
)
|
||||
self.agent._session_db_created = True
|
||||
except Exception:
|
||||
pass
|
||||
# Notify memory providers that session_id rotated to a fresh
|
||||
@@ -6174,27 +6087,6 @@ class HermesCLI:
|
||||
except Exception as exc:
|
||||
print(f"(._.) curator: {exc}")
|
||||
|
||||
def _handle_kanban_command(self, cmd: str):
|
||||
"""Handle the /kanban command — delegate to the shared kanban CLI.
|
||||
|
||||
The string form passed here is the user's full ``/kanban ...``
|
||||
including the leading slash; we strip it and hand the remainder
|
||||
to ``kanban.run_slash`` which returns a single formatted string.
|
||||
"""
|
||||
from hermes_cli.kanban import run_slash
|
||||
|
||||
rest = cmd.strip()
|
||||
if rest.startswith("/"):
|
||||
rest = rest.lstrip("/")
|
||||
if rest.startswith("kanban"):
|
||||
rest = rest[len("kanban"):].lstrip()
|
||||
try:
|
||||
output = run_slash(rest)
|
||||
except Exception as exc: # pragma: no cover - defensive
|
||||
output = f"(._.) kanban error: {exc}"
|
||||
if output:
|
||||
print(output)
|
||||
|
||||
def _handle_skills_command(self, cmd: str):
|
||||
"""Handle /skills slash command — delegates to hermes_cli.skills_hub."""
|
||||
from hermes_cli.skills_hub import handle_skills_slash
|
||||
@@ -6440,8 +6332,6 @@ class HermesCLI:
|
||||
self._handle_cron_command(cmd_original)
|
||||
elif canonical == "curator":
|
||||
self._handle_curator_command(cmd_original)
|
||||
elif canonical == "kanban":
|
||||
self._handle_kanban_command(cmd_original)
|
||||
elif canonical == "skills":
|
||||
with self._busy_command(self._slow_command_status(cmd_original)):
|
||||
self._handle_skills_command(cmd_original)
|
||||
@@ -6559,8 +6449,6 @@ class HermesCLI:
|
||||
# No active run — treat as a normal next-turn message.
|
||||
self._pending_input.put(payload)
|
||||
_cprint(f" No agent running; queued as next turn: {payload[:80]}{'...' if len(payload) > 80 else ''}")
|
||||
elif canonical == "goal":
|
||||
self._handle_goal_command(cmd_original)
|
||||
elif canonical == "skin":
|
||||
self._handle_skin_command(cmd_original)
|
||||
elif canonical == "voice":
|
||||
@@ -6606,17 +6494,12 @@ class HermesCLI:
|
||||
self._console_print(f"[bold red]Quick command '{base_cmd}' has unsupported type (supported: 'exec', 'alias')[/]")
|
||||
# Check for plugin-registered slash commands
|
||||
elif base_cmd.lstrip("/") in _get_plugin_cmd_handler_names():
|
||||
from hermes_cli.plugins import (
|
||||
get_plugin_command_handler,
|
||||
resolve_plugin_command_result,
|
||||
)
|
||||
from hermes_cli.plugins import get_plugin_command_handler
|
||||
plugin_handler = get_plugin_command_handler(base_cmd.lstrip("/"))
|
||||
if plugin_handler:
|
||||
user_args = cmd_original[len(base_cmd):].strip()
|
||||
try:
|
||||
result = resolve_plugin_command_result(
|
||||
plugin_handler(user_args)
|
||||
)
|
||||
result = plugin_handler(user_args)
|
||||
if result:
|
||||
_cprint(str(result))
|
||||
except Exception as e:
|
||||
@@ -7041,166 +6924,6 @@ class HermesCLI:
|
||||
print(" status Show current browser mode")
|
||||
print()
|
||||
|
||||
# ────────────────────────────────────────────────────────────────
|
||||
# /goal — persistent cross-turn goals (Ralph-style loop)
|
||||
# ────────────────────────────────────────────────────────────────
|
||||
def _get_goal_manager(self):
|
||||
"""Return the GoalManager bound to the current session_id.
|
||||
|
||||
Cached on ``self._goal_manager`` and rebound lazily when
|
||||
``session_id`` changes (e.g. after /new or a compression-driven
|
||||
session split).
|
||||
"""
|
||||
try:
|
||||
from hermes_cli.goals import GoalManager
|
||||
from hermes_cli.config import load_config
|
||||
except Exception as exc:
|
||||
logging.debug("goal manager unavailable: %s", exc)
|
||||
return None
|
||||
|
||||
sid = getattr(self, "session_id", None) or ""
|
||||
if not sid:
|
||||
return None
|
||||
|
||||
existing = getattr(self, "_goal_manager", None)
|
||||
if existing is not None and getattr(existing, "session_id", None) == sid:
|
||||
return existing
|
||||
|
||||
try:
|
||||
cfg = load_config() or {}
|
||||
goals_cfg = cfg.get("goals") or {}
|
||||
max_turns = int(goals_cfg.get("max_turns", 20) or 20)
|
||||
except Exception:
|
||||
max_turns = 20
|
||||
|
||||
mgr = GoalManager(session_id=sid, default_max_turns=max_turns)
|
||||
self._goal_manager = mgr
|
||||
return mgr
|
||||
|
||||
def _handle_goal_command(self, cmd: str) -> None:
|
||||
"""Dispatch /goal subcommands: set / status / pause / resume / clear."""
|
||||
parts = (cmd or "").strip().split(None, 1)
|
||||
arg = parts[1].strip() if len(parts) > 1 else ""
|
||||
|
||||
mgr = self._get_goal_manager()
|
||||
if mgr is None:
|
||||
_cprint(f" {_DIM}Goals unavailable (no active session).{_RST}")
|
||||
return
|
||||
|
||||
lower = arg.lower()
|
||||
|
||||
# Bare /goal or /goal status → show current state
|
||||
if not arg or lower == "status":
|
||||
_cprint(f" {mgr.status_line()}")
|
||||
return
|
||||
|
||||
if lower == "pause":
|
||||
state = mgr.pause(reason="user-paused")
|
||||
if state is None:
|
||||
_cprint(f" {_DIM}No goal set.{_RST}")
|
||||
else:
|
||||
_cprint(f" ⏸ Goal paused: {state.goal}")
|
||||
return
|
||||
|
||||
if lower == "resume":
|
||||
state = mgr.resume()
|
||||
if state is None:
|
||||
_cprint(f" {_DIM}No goal to resume.{_RST}")
|
||||
else:
|
||||
_cprint(f" ▶ Goal resumed: {state.goal}")
|
||||
_cprint(
|
||||
f" {_DIM}Send any message (or press Enter on an empty prompt "
|
||||
f"is a no-op; type 'continue' to kick it off).{_RST}"
|
||||
)
|
||||
return
|
||||
|
||||
if lower in ("clear", "stop", "done"):
|
||||
had = mgr.has_goal()
|
||||
mgr.clear()
|
||||
if had:
|
||||
_cprint(" ✓ Goal cleared.")
|
||||
else:
|
||||
_cprint(f" {_DIM}No active goal.{_RST}")
|
||||
return
|
||||
|
||||
# Otherwise treat the arg as the goal text.
|
||||
try:
|
||||
state = mgr.set(arg)
|
||||
except ValueError as exc:
|
||||
_cprint(f" Invalid goal: {exc}")
|
||||
return
|
||||
|
||||
_cprint(f" ⊙ Goal set ({state.max_turns}-turn budget): {state.goal}")
|
||||
_cprint(
|
||||
f" {_DIM}After each turn, a judge model will check if the goal is done. "
|
||||
f"Hermes keeps working until it is, you pause/clear it, or the budget is "
|
||||
f"exhausted. Use /goal status, /goal pause, /goal resume, /goal clear.{_RST}"
|
||||
)
|
||||
# Kick the loop off immediately so the user doesn't have to send a
|
||||
# separate message after setting the goal.
|
||||
try:
|
||||
self._pending_input.put(state.goal)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _maybe_continue_goal_after_turn(self) -> None:
|
||||
"""Hook run after every CLI turn. Judges + maybe re-queues.
|
||||
|
||||
Safe to call when no goal is set — returns quickly.
|
||||
|
||||
Preemption is automatic: if a real user message is already in
|
||||
``_pending_input`` we skip judging (the user's new input takes
|
||||
priority and we'll re-judge after that turn). If judge says done,
|
||||
mark it done and tell the user. If judge says continue and we're
|
||||
under budget, push the continuation prompt onto the queue.
|
||||
"""
|
||||
mgr = self._get_goal_manager()
|
||||
if mgr is None or not mgr.is_active():
|
||||
return
|
||||
|
||||
# If a real user message is already queued, don't inject a
|
||||
# continuation prompt on top — let the user's turn go first.
|
||||
try:
|
||||
if getattr(self, "_pending_input", None) is not None \
|
||||
and not self._pending_input.empty():
|
||||
return
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Extract the agent's final response for this turn.
|
||||
last_response = ""
|
||||
try:
|
||||
hist = self.conversation_history or []
|
||||
for msg in reversed(hist):
|
||||
if msg.get("role") == "assistant":
|
||||
content = msg.get("content", "")
|
||||
if isinstance(content, list):
|
||||
# Multimodal content — flatten text parts.
|
||||
parts = [
|
||||
p.get("text", "")
|
||||
for p in content
|
||||
if isinstance(p, dict) and p.get("type") in ("text", "output_text")
|
||||
]
|
||||
last_response = "\n".join(t for t in parts if t)
|
||||
else:
|
||||
last_response = str(content or "")
|
||||
break
|
||||
except Exception:
|
||||
last_response = ""
|
||||
|
||||
decision = mgr.evaluate_after_turn(last_response, user_initiated=True)
|
||||
msg = decision.get("message") or ""
|
||||
if msg:
|
||||
_cprint(f" {msg}")
|
||||
|
||||
if decision.get("should_continue"):
|
||||
prompt = decision.get("continuation_prompt")
|
||||
if prompt:
|
||||
try:
|
||||
self._pending_input.put(prompt)
|
||||
except Exception as exc:
|
||||
logging.debug("goal continuation enqueue failed: %s", exc)
|
||||
|
||||
def _handle_skin_command(self, cmd: str):
|
||||
"""Handle /skin [name] — show or change the display skin."""
|
||||
try:
|
||||
@@ -7327,7 +7050,7 @@ class HermesCLI:
|
||||
import os
|
||||
from hermes_cli.colors import Colors as _Colors
|
||||
|
||||
current = is_truthy_value(os.environ.get("HERMES_YOLO_MODE"))
|
||||
current = bool(os.environ.get("HERMES_YOLO_MODE"))
|
||||
if current:
|
||||
os.environ.pop("HERMES_YOLO_MODE", None)
|
||||
_cprint(
|
||||
@@ -7524,20 +7247,10 @@ class HermesCLI:
|
||||
original_count = len(self.conversation_history)
|
||||
with self._busy_command("Compressing context..."):
|
||||
try:
|
||||
from agent.model_metadata import estimate_request_tokens_rough
|
||||
from agent.model_metadata import estimate_messages_tokens_rough
|
||||
from agent.manual_compression_feedback import summarize_manual_compression
|
||||
original_history = list(self.conversation_history)
|
||||
# Include system prompt + tool schemas in the estimate —
|
||||
# a transcript-only number understates real request pressure
|
||||
# and can even appear to grow after compression because a
|
||||
# dense handoff summary replaces many short turns (#6217).
|
||||
_sys_prompt = getattr(self.agent, "_cached_system_prompt", "") or ""
|
||||
_tools = getattr(self.agent, "tools", None) or None
|
||||
approx_tokens = estimate_request_tokens_rough(
|
||||
original_history,
|
||||
system_prompt=_sys_prompt,
|
||||
tools=_tools,
|
||||
)
|
||||
approx_tokens = estimate_messages_tokens_rough(original_history)
|
||||
if focus_topic:
|
||||
print(f"🗜️ Compressing {original_count} messages (~{approx_tokens:,} tokens), "
|
||||
f"focus: \"{focus_topic}\"...")
|
||||
@@ -7569,11 +7282,7 @@ class HermesCLI:
|
||||
):
|
||||
self.session_id = self.agent.session_id
|
||||
self._pending_title = None
|
||||
new_tokens = estimate_request_tokens_rough(
|
||||
self.conversation_history,
|
||||
system_prompt=_sys_prompt,
|
||||
tools=_tools,
|
||||
)
|
||||
new_tokens = estimate_messages_tokens_rough(self.conversation_history)
|
||||
summary = summarize_manual_compression(
|
||||
original_history,
|
||||
self.conversation_history,
|
||||
@@ -8375,17 +8084,6 @@ class HermesCLI:
|
||||
_cprint(f"{_DIM}Voice auto-restart failed: {e}{_RST}")
|
||||
threading.Thread(target=_restart_recording, daemon=True).start()
|
||||
|
||||
def _voice_speak_response_async(self, text: str) -> None:
|
||||
"""Schedule TTS and mark it pending before continuous recording can restart."""
|
||||
if not self._voice_tts or not text:
|
||||
return
|
||||
self._voice_tts_done.clear()
|
||||
threading.Thread(
|
||||
target=self._voice_speak_response,
|
||||
args=(text,),
|
||||
daemon=True,
|
||||
).start()
|
||||
|
||||
def _voice_speak_response(self, text: str):
|
||||
"""Speak the agent's response aloud using TTS (runs in background thread)."""
|
||||
if not self._voice_tts:
|
||||
@@ -9546,7 +9244,11 @@ class HermesCLI:
|
||||
# Speak response aloud if voice TTS is enabled
|
||||
# Skip batch TTS when streaming TTS already handled it
|
||||
if self._voice_tts and response and not use_streaming_tts:
|
||||
self._voice_speak_response_async(response)
|
||||
threading.Thread(
|
||||
target=self._voice_speak_response,
|
||||
args=(response,),
|
||||
daemon=True,
|
||||
).start()
|
||||
|
||||
|
||||
# Re-queue the interrupt message (and any that arrived while we were
|
||||
@@ -11546,17 +11248,6 @@ class HermesCLI:
|
||||
|
||||
app.invalidate() # Refresh status line
|
||||
|
||||
# Goal continuation: if a standing goal is active, ask
|
||||
# the judge whether the turn satisfied it. If not, and
|
||||
# there's no real user message already queued, push the
|
||||
# continuation prompt back into _pending_input so the
|
||||
# next loop iteration picks it up naturally (and any
|
||||
# user input that arrives in between still preempts).
|
||||
try:
|
||||
self._maybe_continue_goal_after_turn()
|
||||
except Exception as _goal_exc:
|
||||
logging.debug("goal continuation hook failed: %s", _goal_exc)
|
||||
|
||||
# Continuous voice: auto-restart recording after agent responds.
|
||||
# Dispatch to a daemon thread so play_beep (sd.wait) and
|
||||
# AudioRecorder.start (lock acquire) never block process_loop —
|
||||
@@ -11590,7 +11281,7 @@ class HermesCLI:
|
||||
pass # Non-fatal — don't break the main loop
|
||||
|
||||
except Exception as e:
|
||||
logger.warning("process_loop unhandled error (msg may be lost): %s", e)
|
||||
print(f"Error: {e}")
|
||||
|
||||
# Start processing thread
|
||||
process_thread = threading.Thread(target=process_loop, daemon=True)
|
||||
|
||||
+2
-137
@@ -797,36 +797,19 @@ def get_due_jobs() -> List[Dict[str, Any]]:
|
||||
|
||||
next_run = job.get("next_run_at")
|
||||
if not next_run:
|
||||
schedule = job.get("schedule", {})
|
||||
kind = schedule.get("kind")
|
||||
|
||||
# One-shot jobs use a small grace window via the dedicated helper.
|
||||
recovered_next = _recoverable_oneshot_run_at(
|
||||
schedule,
|
||||
job.get("schedule", {}),
|
||||
now,
|
||||
last_run_at=job.get("last_run_at"),
|
||||
)
|
||||
recovery_kind = "one-shot" if recovered_next else None
|
||||
|
||||
# Recurring jobs reach here only when something — typically a
|
||||
# direct jobs.json edit that bypassed add_job() — left
|
||||
# next_run_at unset. Without this branch, such jobs are
|
||||
# silently skipped forever; recompute next_run_at from the
|
||||
# schedule so they pick up at their next scheduled tick.
|
||||
if not recovered_next and kind in ("cron", "interval"):
|
||||
recovered_next = compute_next_run(schedule, now.isoformat())
|
||||
if recovered_next:
|
||||
recovery_kind = kind
|
||||
|
||||
if not recovered_next:
|
||||
continue
|
||||
|
||||
job["next_run_at"] = recovered_next
|
||||
next_run = recovered_next
|
||||
logger.info(
|
||||
"Job '%s' had no next_run_at; recovering %s run at %s",
|
||||
"Job '%s' had no next_run_at; recovering one-shot run at %s",
|
||||
job.get("name", job["id"]),
|
||||
recovery_kind,
|
||||
recovered_next,
|
||||
)
|
||||
for rj in raw_jobs:
|
||||
@@ -899,121 +882,3 @@ def save_job_output(job_id: str, output: str):
|
||||
raise
|
||||
|
||||
return output_file
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# Skill reference rewriting (curator integration)
|
||||
# =============================================================================
|
||||
|
||||
def rewrite_skill_refs(
|
||||
consolidated: Optional[Dict[str, str]] = None,
|
||||
pruned: Optional[List[str]] = None,
|
||||
) -> Dict[str, Any]:
|
||||
"""Rewrite cron job skill references after a curator consolidation pass.
|
||||
|
||||
When the curator consolidates a skill X into umbrella Y (or archives X
|
||||
as pruned), any cron job that lists ``X`` in its ``skills`` field will
|
||||
fail to load ``X`` at run time — the scheduler logs a warning and
|
||||
skips the skill, so the job runs without the instructions it was
|
||||
scheduled to follow. See cron/scheduler.py where ``skill_view`` is
|
||||
called per skill name.
|
||||
|
||||
This function repairs cron jobs in-place:
|
||||
|
||||
- A skill listed in ``consolidated`` is replaced with its umbrella
|
||||
target (the ``into`` value). If the umbrella is already in the
|
||||
job's skill list, the stale name is dropped without duplication.
|
||||
- A skill listed in ``pruned`` is dropped outright — there is no
|
||||
forwarding target.
|
||||
- Ordering and other skills in the list are preserved.
|
||||
- The legacy ``skill`` field is realigned via ``_apply_skill_fields``.
|
||||
|
||||
Args:
|
||||
consolidated: mapping of ``old_skill_name -> umbrella_skill_name``.
|
||||
pruned: list of skill names that were archived with no forwarding
|
||||
target.
|
||||
|
||||
Returns a report dict::
|
||||
|
||||
{
|
||||
"rewrites": [
|
||||
{
|
||||
"job_id": ...,
|
||||
"job_name": ...,
|
||||
"before": [...],
|
||||
"after": [...],
|
||||
"mapped": {"old": "new", ...},
|
||||
"dropped": ["old", ...],
|
||||
},
|
||||
...
|
||||
],
|
||||
"jobs_updated": N,
|
||||
"jobs_scanned": M,
|
||||
}
|
||||
|
||||
Best-effort: exceptions from loading/saving propagate to the caller so
|
||||
tests can assert behaviour; the curator invocation site wraps this
|
||||
call in a try/except so a failure here never breaks the curator.
|
||||
"""
|
||||
consolidated = dict(consolidated or {})
|
||||
pruned_set = set(pruned or [])
|
||||
# A skill listed in both wins as "consolidated" — it has a target,
|
||||
# which is the more useful of the two outcomes.
|
||||
pruned_set -= set(consolidated.keys())
|
||||
|
||||
if not consolidated and not pruned_set:
|
||||
return {"rewrites": [], "jobs_updated": 0, "jobs_scanned": 0}
|
||||
|
||||
with _jobs_file_lock:
|
||||
jobs = load_jobs()
|
||||
rewrites: List[Dict[str, Any]] = []
|
||||
changed = False
|
||||
|
||||
for job in jobs:
|
||||
skills_before = _normalize_skill_list(job.get("skill"), job.get("skills"))
|
||||
if not skills_before:
|
||||
continue
|
||||
|
||||
mapped: Dict[str, str] = {}
|
||||
dropped: List[str] = []
|
||||
new_skills: List[str] = []
|
||||
|
||||
for name in skills_before:
|
||||
if name in consolidated:
|
||||
target = consolidated[name]
|
||||
mapped[name] = target
|
||||
if target and target not in new_skills:
|
||||
new_skills.append(target)
|
||||
elif name in pruned_set:
|
||||
dropped.append(name)
|
||||
else:
|
||||
if name not in new_skills:
|
||||
new_skills.append(name)
|
||||
|
||||
if not mapped and not dropped:
|
||||
continue
|
||||
|
||||
job["skills"] = new_skills
|
||||
job["skill"] = new_skills[0] if new_skills else None
|
||||
changed = True
|
||||
|
||||
rewrites.append({
|
||||
"job_id": job.get("id"),
|
||||
"job_name": job.get("name") or job.get("id"),
|
||||
"before": list(skills_before),
|
||||
"after": list(new_skills),
|
||||
"mapped": mapped,
|
||||
"dropped": dropped,
|
||||
})
|
||||
|
||||
if changed:
|
||||
save_jobs(jobs)
|
||||
logger.info(
|
||||
"Curator rewrote skill references in %d cron job(s)", len(rewrites)
|
||||
)
|
||||
|
||||
return {
|
||||
"rewrites": rewrites,
|
||||
"jobs_updated": len(rewrites),
|
||||
"jobs_scanned": len(jobs),
|
||||
}
|
||||
|
||||
+5
-35
@@ -123,19 +123,9 @@ _LOCK_FILE = _LOCK_DIR / ".tick.lock"
|
||||
|
||||
|
||||
def _resolve_origin(job: dict) -> Optional[dict]:
|
||||
"""Extract origin info from a job, preserving any extra routing metadata.
|
||||
|
||||
Treats non-dict origins (free-form provenance strings, ints, lists from
|
||||
migration scripts or hand-edited jobs.json) as missing instead of
|
||||
crashing with ``AttributeError`` on ``origin.get(...)``. Without this
|
||||
guard, a job tagged with e.g. ``"combined-digest-replaces-x-and-y"``
|
||||
crashed every fire attempt with
|
||||
``'str' object has no attribute 'get'`` — ``mark_job_run`` recorded the
|
||||
failure, but the next tick re-loaded the same poisoned origin and
|
||||
crashed identically until the field was patched manually (#18722).
|
||||
"""
|
||||
"""Extract origin info from a job, preserving any extra routing metadata."""
|
||||
origin = job.get("origin")
|
||||
if not isinstance(origin, dict):
|
||||
if not origin:
|
||||
return None
|
||||
platform = origin.get("platform")
|
||||
chat_id = origin.get("chat_id")
|
||||
@@ -157,19 +147,6 @@ def _get_home_target_chat_id(platform_name: str) -> str:
|
||||
return value
|
||||
|
||||
|
||||
def _get_home_target_thread_id(platform_name: str) -> Optional[str]:
|
||||
"""Return the optional thread/topic ID for a platform home target."""
|
||||
env_var = _HOME_TARGET_ENV_VARS.get(platform_name.lower())
|
||||
if not env_var:
|
||||
return None
|
||||
value = os.getenv(f"{env_var}_THREAD_ID", "").strip()
|
||||
if not value:
|
||||
legacy = _LEGACY_HOME_TARGET_ENV_VARS.get(env_var)
|
||||
if legacy:
|
||||
value = os.getenv(f"{legacy}_THREAD_ID", "").strip()
|
||||
return value or None
|
||||
|
||||
|
||||
def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[dict]:
|
||||
"""Resolve one concrete auto-delivery target for a cron job."""
|
||||
|
||||
@@ -198,7 +175,7 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d
|
||||
return {
|
||||
"platform": platform_name,
|
||||
"chat_id": chat_id,
|
||||
"thread_id": _get_home_target_thread_id(platform_name),
|
||||
"thread_id": None,
|
||||
}
|
||||
return None
|
||||
|
||||
@@ -252,7 +229,7 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d
|
||||
return {
|
||||
"platform": platform_name,
|
||||
"chat_id": chat_id,
|
||||
"thread_id": _get_home_target_thread_id(platform_name),
|
||||
"thread_id": None,
|
||||
}
|
||||
|
||||
|
||||
@@ -417,7 +394,7 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
|
||||
thread_id = target.get("thread_id")
|
||||
|
||||
# Diagnostic: log thread_id for topic-aware delivery debugging
|
||||
origin = _resolve_origin(job) or {}
|
||||
origin = job.get("origin") or {}
|
||||
origin_thread = origin.get("thread_id")
|
||||
if origin_thread and not thread_id:
|
||||
logger.warning(
|
||||
@@ -782,7 +759,6 @@ def _build_job_prompt(job: dict, prerun_script: Optional[tuple] = None) -> str:
|
||||
return prompt
|
||||
|
||||
from tools.skills_tool import skill_view
|
||||
from tools.skill_usage import bump_use
|
||||
|
||||
parts = []
|
||||
skipped: list[str] = []
|
||||
@@ -794,12 +770,6 @@ def _build_job_prompt(job: dict, prerun_script: Optional[tuple] = None) -> str:
|
||||
skipped.append(skill_name)
|
||||
continue
|
||||
|
||||
# Bump usage so the curator sees this skill as actively used.
|
||||
try:
|
||||
bump_use(skill_name)
|
||||
except Exception:
|
||||
logger.debug("Cron job: failed to bump skill usage for '%s'", skill_name, exc_info=True)
|
||||
|
||||
content = str(loaded.get("content") or "").strip()
|
||||
if parts:
|
||||
parts.append("")
|
||||
|
||||
+1
-1
@@ -40,7 +40,7 @@ services:
|
||||
# - TEAMS_CLIENT_SECRET=${TEAMS_CLIENT_SECRET}
|
||||
# - TEAMS_TENANT_ID=${TEAMS_TENANT_ID}
|
||||
# - TEAMS_ALLOWED_USERS=${TEAMS_ALLOWED_USERS}
|
||||
# - TEAMS_PORT=${TEAMS_PORT:-3978}
|
||||
# - TEAMS_PORT=3978
|
||||
command: ["gateway", "run"]
|
||||
|
||||
dashboard:
|
||||
|
||||
@@ -86,41 +86,6 @@ if [ -d "$INSTALL_DIR/skills" ]; then
|
||||
python3 "$INSTALL_DIR/tools/skills_sync.py"
|
||||
fi
|
||||
|
||||
# Optionally start `hermes dashboard` as a side-process.
|
||||
#
|
||||
# Toggled by HERMES_DASHBOARD=1 (also accepts "true"/"yes", case-insensitive).
|
||||
# Host/port/TUI can be overridden via:
|
||||
# HERMES_DASHBOARD_HOST (default 0.0.0.0 — exposed outside the container)
|
||||
# HERMES_DASHBOARD_PORT (default 9119, matches `hermes dashboard` default)
|
||||
# HERMES_DASHBOARD_TUI (already honored by `hermes dashboard` itself)
|
||||
#
|
||||
# The dashboard is a long-lived server. We background it *before* the final
|
||||
# `exec hermes "$@"` so the user's chosen foreground command (chat, gateway,
|
||||
# sleep infinity, …) remains PID-of-interest for the container runtime. When
|
||||
# the container stops the whole process tree is torn down, so no explicit
|
||||
# cleanup is needed.
|
||||
case "${HERMES_DASHBOARD:-}" in
|
||||
1|true|TRUE|True|yes|YES|Yes)
|
||||
dash_host="${HERMES_DASHBOARD_HOST:-0.0.0.0}"
|
||||
dash_port="${HERMES_DASHBOARD_PORT:-9119}"
|
||||
dash_args=(--host "$dash_host" --port "$dash_port" --no-open)
|
||||
# Binding to anything other than localhost requires --insecure — the
|
||||
# dashboard refuses otherwise because it exposes API keys. Inside a
|
||||
# container this is the expected deployment (host reaches it via
|
||||
# published port), so opt in automatically.
|
||||
if [ "$dash_host" != "127.0.0.1" ] && [ "$dash_host" != "localhost" ]; then
|
||||
dash_args+=(--insecure)
|
||||
fi
|
||||
echo "Starting hermes dashboard on ${dash_host}:${dash_port} (background)"
|
||||
# Prefix dashboard output so it's distinguishable from the main
|
||||
# process in `docker logs`. stdbuf keeps the pipe line-buffered.
|
||||
(
|
||||
stdbuf -oL -eL hermes dashboard "${dash_args[@]}" 2>&1 \
|
||||
| sed -u 's/^/[dashboard] /'
|
||||
) &
|
||||
;;
|
||||
esac
|
||||
|
||||
# Final exec: two supported invocation patterns.
|
||||
#
|
||||
# docker run <image> -> exec `hermes` with no args (legacy default)
|
||||
|
||||
Binary file not shown.
+10
-109
@@ -36,26 +36,6 @@ def _coerce_bool(value: Any, default: bool = True) -> bool:
|
||||
return is_truthy_value(value, default=default)
|
||||
|
||||
|
||||
def _coerce_float(value: Any, default: float) -> float:
|
||||
"""Coerce numeric config values, falling back on malformed input."""
|
||||
if value is None:
|
||||
return default
|
||||
try:
|
||||
return float(value)
|
||||
except (TypeError, ValueError):
|
||||
return default
|
||||
|
||||
|
||||
def _coerce_int(value: Any, default: int) -> int:
|
||||
"""Coerce integer config values, falling back on malformed input."""
|
||||
if value is None:
|
||||
return default
|
||||
try:
|
||||
return int(value)
|
||||
except (TypeError, ValueError):
|
||||
return default
|
||||
|
||||
|
||||
def _normalize_unauthorized_dm_behavior(value: Any, default: str = "pair") -> str:
|
||||
"""Normalize unauthorized DM behavior to a supported value."""
|
||||
if isinstance(value, str):
|
||||
@@ -65,15 +45,6 @@ def _normalize_unauthorized_dm_behavior(value: Any, default: str = "pair") -> st
|
||||
return default
|
||||
|
||||
|
||||
def _normalize_notice_delivery(value: Any, default: str = "public") -> str:
|
||||
"""Normalize notice delivery mode to a supported value."""
|
||||
if isinstance(value, str):
|
||||
normalized = value.strip().lower()
|
||||
if normalized in {"public", "private"}:
|
||||
return normalized
|
||||
return default
|
||||
|
||||
|
||||
# Module-level cache for bundled platform plugin names (lives outside the
|
||||
# enum so it doesn't become an accidental enum member).
|
||||
_Platform__bundled_plugin_names: Optional[set] = None
|
||||
@@ -186,24 +157,18 @@ class HomeChannel:
|
||||
Default destination for a platform.
|
||||
|
||||
When a cron job specifies deliver="telegram" without a specific chat ID,
|
||||
messages are sent to this home channel. Thread-aware platforms may also
|
||||
store a thread/topic ID so the bare platform target routes to the exact
|
||||
conversation where /sethome was run.
|
||||
messages are sent to this home channel.
|
||||
"""
|
||||
platform: Platform
|
||||
chat_id: str
|
||||
name: str # Human-readable name for display
|
||||
thread_id: Optional[str] = None
|
||||
|
||||
def to_dict(self) -> Dict[str, Any]:
|
||||
result = {
|
||||
return {
|
||||
"platform": self.platform.value,
|
||||
"chat_id": self.chat_id,
|
||||
"name": self.name,
|
||||
}
|
||||
if self.thread_id:
|
||||
result["thread_id"] = self.thread_id
|
||||
return result
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: Dict[str, Any]) -> "HomeChannel":
|
||||
@@ -211,7 +176,6 @@ class HomeChannel:
|
||||
platform=Platform(data["platform"]),
|
||||
chat_id=str(data["chat_id"]),
|
||||
name=data.get("name", "Home"),
|
||||
thread_id=str(data["thread_id"]) if data.get("thread_id") else None,
|
||||
)
|
||||
|
||||
|
||||
@@ -337,13 +301,13 @@ class StreamingConfig:
|
||||
if not data:
|
||||
return cls()
|
||||
return cls(
|
||||
enabled=_coerce_bool(data.get("enabled"), False),
|
||||
enabled=data.get("enabled", False),
|
||||
transport=data.get("transport", "edit"),
|
||||
edit_interval=_coerce_float(data.get("edit_interval"), 1.0),
|
||||
buffer_threshold=_coerce_int(data.get("buffer_threshold"), 40),
|
||||
edit_interval=float(data.get("edit_interval", 1.0)),
|
||||
buffer_threshold=int(data.get("buffer_threshold", 40)),
|
||||
cursor=data.get("cursor", " ▉"),
|
||||
fresh_final_after_seconds=_coerce_float(
|
||||
data.get("fresh_final_after_seconds"), 60.0
|
||||
fresh_final_after_seconds=float(
|
||||
data.get("fresh_final_after_seconds", 60.0)
|
||||
),
|
||||
)
|
||||
|
||||
@@ -608,17 +572,6 @@ class GatewayConfig:
|
||||
)
|
||||
return self.unauthorized_dm_behavior
|
||||
|
||||
def get_notice_delivery(self, platform: Optional[Platform] = None) -> str:
|
||||
"""Return the effective notice-delivery mode for a platform."""
|
||||
if platform:
|
||||
platform_cfg = self.platforms.get(platform)
|
||||
if platform_cfg and "notice_delivery" in platform_cfg.extra:
|
||||
return _normalize_notice_delivery(
|
||||
platform_cfg.extra.get("notice_delivery"),
|
||||
"public",
|
||||
)
|
||||
return "public"
|
||||
|
||||
|
||||
def load_gateway_config() -> GatewayConfig:
|
||||
"""
|
||||
@@ -734,11 +687,6 @@ def load_gateway_config() -> GatewayConfig:
|
||||
platform_cfg.get("unauthorized_dm_behavior"),
|
||||
gw_data.get("unauthorized_dm_behavior", "pair"),
|
||||
)
|
||||
if "notice_delivery" in platform_cfg:
|
||||
bridged["notice_delivery"] = _normalize_notice_delivery(
|
||||
platform_cfg.get("notice_delivery"),
|
||||
"public",
|
||||
)
|
||||
if "reply_prefix" in platform_cfg:
|
||||
bridged["reply_prefix"] = platform_cfg["reply_prefix"]
|
||||
if "reply_in_thread" in platform_cfg:
|
||||
@@ -846,25 +794,11 @@ def load_gateway_config() -> GatewayConfig:
|
||||
if yaml_key in allow_mentions_cfg and not os.getenv(env_key):
|
||||
os.environ[env_key] = str(allow_mentions_cfg[yaml_key]).lower()
|
||||
|
||||
# Bridge top-level require_mention to Telegram when the telegram: section
|
||||
# does not already provide one. Users often write "require_mention: true"
|
||||
# at the top level alongside group_sessions_per_user, expecting it to work
|
||||
# the same way (#3979).
|
||||
_tl_require_mention = yaml_cfg.get("require_mention")
|
||||
if _tl_require_mention is not None:
|
||||
_tg_section = yaml_cfg.get("telegram") or {}
|
||||
if "require_mention" not in _tg_section:
|
||||
_tg_plat = platforms_data.setdefault(Platform.TELEGRAM.value, {})
|
||||
_tg_extra = _tg_plat.setdefault("extra", {})
|
||||
_tg_extra.setdefault("require_mention", _tl_require_mention)
|
||||
|
||||
# Telegram settings → env vars (env vars take precedence)
|
||||
telegram_cfg = yaml_cfg.get("telegram", {})
|
||||
if isinstance(telegram_cfg, dict):
|
||||
# Prefer telegram.require_mention; fall back to the top-level shorthand.
|
||||
_effective_rm = telegram_cfg.get("require_mention", yaml_cfg.get("require_mention"))
|
||||
if _effective_rm is not None and not os.getenv("TELEGRAM_REQUIRE_MENTION"):
|
||||
os.environ["TELEGRAM_REQUIRE_MENTION"] = str(_effective_rm).lower()
|
||||
if "require_mention" in telegram_cfg and not os.getenv("TELEGRAM_REQUIRE_MENTION"):
|
||||
os.environ["TELEGRAM_REQUIRE_MENTION"] = str(telegram_cfg["require_mention"]).lower()
|
||||
if "mention_patterns" in telegram_cfg and not os.getenv("TELEGRAM_MENTION_PATTERNS"):
|
||||
os.environ["TELEGRAM_MENTION_PATTERNS"] = json.dumps(telegram_cfg["mention_patterns"])
|
||||
frc = telegram_cfg.get("free_response_chats")
|
||||
@@ -966,12 +900,6 @@ def load_gateway_config() -> GatewayConfig:
|
||||
if "dm_mention_threads" in matrix_cfg and not os.getenv("MATRIX_DM_MENTION_THREADS"):
|
||||
os.environ["MATRIX_DM_MENTION_THREADS"] = str(matrix_cfg["dm_mention_threads"]).lower()
|
||||
|
||||
# Feishu settings → env vars (env vars take precedence)
|
||||
feishu_cfg = yaml_cfg.get("feishu", {})
|
||||
if isinstance(feishu_cfg, dict):
|
||||
if "allow_bots" in feishu_cfg and not os.getenv("FEISHU_ALLOW_BOTS"):
|
||||
os.environ["FEISHU_ALLOW_BOTS"] = str(feishu_cfg["allow_bots"]).lower()
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
"Failed to process config.yaml — falling back to .env / gateway.json values. "
|
||||
@@ -1092,7 +1020,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.TELEGRAM,
|
||||
chat_id=telegram_home,
|
||||
name=os.getenv("TELEGRAM_HOME_CHANNEL_NAME", "Home"),
|
||||
thread_id=os.getenv("TELEGRAM_HOME_CHANNEL_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
# Discord
|
||||
@@ -1109,7 +1036,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.DISCORD,
|
||||
chat_id=discord_home,
|
||||
name=os.getenv("DISCORD_HOME_CHANNEL_NAME", "Home"),
|
||||
thread_id=os.getenv("DISCORD_HOME_CHANNEL_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
# Reply threading mode for Discord (off/first/all)
|
||||
@@ -1125,15 +1051,7 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
if Platform.WHATSAPP not in config.platforms:
|
||||
config.platforms[Platform.WHATSAPP] = PlatformConfig()
|
||||
config.platforms[Platform.WHATSAPP].enabled = True
|
||||
whatsapp_home = os.getenv("WHATSAPP_HOME_CHANNEL")
|
||||
if whatsapp_home and Platform.WHATSAPP in config.platforms:
|
||||
config.platforms[Platform.WHATSAPP].home_channel = HomeChannel(
|
||||
platform=Platform.WHATSAPP,
|
||||
chat_id=whatsapp_home,
|
||||
name=os.getenv("WHATSAPP_HOME_CHANNEL_NAME", "Home"),
|
||||
thread_id=os.getenv("WHATSAPP_HOME_CHANNEL_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
|
||||
# Slack
|
||||
slack_token = os.getenv("SLACK_BOT_TOKEN")
|
||||
if slack_token:
|
||||
@@ -1159,7 +1077,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.SLACK,
|
||||
chat_id=slack_home,
|
||||
name=os.getenv("SLACK_HOME_CHANNEL_NAME", ""),
|
||||
thread_id=os.getenv("SLACK_HOME_CHANNEL_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
# Signal
|
||||
@@ -1180,7 +1097,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.SIGNAL,
|
||||
chat_id=signal_home,
|
||||
name=os.getenv("SIGNAL_HOME_CHANNEL_NAME", "Home"),
|
||||
thread_id=os.getenv("SIGNAL_HOME_CHANNEL_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
# Mattermost
|
||||
@@ -1200,7 +1116,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.MATTERMOST,
|
||||
chat_id=mattermost_home,
|
||||
name=os.getenv("MATTERMOST_HOME_CHANNEL_NAME", "Home"),
|
||||
thread_id=os.getenv("MATTERMOST_HOME_CHANNEL_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
# Matrix
|
||||
@@ -1232,7 +1147,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.MATRIX,
|
||||
chat_id=matrix_home,
|
||||
name=os.getenv("MATRIX_HOME_ROOM_NAME", "Home"),
|
||||
thread_id=os.getenv("MATRIX_HOME_ROOM_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
# Home Assistant
|
||||
@@ -1266,7 +1180,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.EMAIL,
|
||||
chat_id=email_home,
|
||||
name=os.getenv("EMAIL_HOME_ADDRESS_NAME", "Home"),
|
||||
thread_id=os.getenv("EMAIL_HOME_ADDRESS_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
# SMS (Twilio)
|
||||
@@ -1282,7 +1195,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.SMS,
|
||||
chat_id=sms_home,
|
||||
name=os.getenv("SMS_HOME_CHANNEL_NAME", "Home"),
|
||||
thread_id=os.getenv("SMS_HOME_CHANNEL_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
# API Server
|
||||
@@ -1345,7 +1257,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.DINGTALK,
|
||||
chat_id=dingtalk_home,
|
||||
name=os.getenv("DINGTALK_HOME_CHANNEL_NAME", "Home"),
|
||||
thread_id=os.getenv("DINGTALK_HOME_CHANNEL_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
# Feishu / Lark
|
||||
@@ -1373,7 +1284,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.FEISHU,
|
||||
chat_id=feishu_home,
|
||||
name=os.getenv("FEISHU_HOME_CHANNEL_NAME", "Home"),
|
||||
thread_id=os.getenv("FEISHU_HOME_CHANNEL_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
# WeCom (Enterprise WeChat)
|
||||
@@ -1396,7 +1306,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.WECOM,
|
||||
chat_id=wecom_home,
|
||||
name=os.getenv("WECOM_HOME_CHANNEL_NAME", "Home"),
|
||||
thread_id=os.getenv("WECOM_HOME_CHANNEL_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
# WeCom callback mode (self-built apps)
|
||||
@@ -1455,7 +1364,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.WEIXIN,
|
||||
chat_id=weixin_home,
|
||||
name=os.getenv("WEIXIN_HOME_CHANNEL_NAME", "Home"),
|
||||
thread_id=os.getenv("WEIXIN_HOME_CHANNEL_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
# BlueBubbles (iMessage)
|
||||
@@ -1479,7 +1387,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.BLUEBUBBLES,
|
||||
chat_id=bluebubbles_home,
|
||||
name=os.getenv("BLUEBUBBLES_HOME_CHANNEL_NAME", "Home"),
|
||||
thread_id=os.getenv("BLUEBUBBLES_HOME_CHANNEL_THREAD_ID") or None,
|
||||
)
|
||||
|
||||
# QQ (Official Bot API v2)
|
||||
@@ -1517,11 +1424,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.QQBOT,
|
||||
chat_id=qq_home,
|
||||
name=os.getenv("QQBOT_HOME_CHANNEL_NAME") or os.getenv(qq_home_name_env, "Home"),
|
||||
thread_id=(
|
||||
os.getenv("QQBOT_HOME_CHANNEL_THREAD_ID")
|
||||
or os.getenv("QQ_HOME_CHANNEL_THREAD_ID")
|
||||
or None
|
||||
),
|
||||
)
|
||||
|
||||
# Yuanbao — YUANBAO_APP_ID preferred
|
||||
@@ -1552,7 +1454,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
platform=Platform.YUANBAO,
|
||||
chat_id=yuanbao_home,
|
||||
name=os.getenv("YUANBAO_HOME_CHANNEL_NAME", "Home"),
|
||||
thread_id=os.getenv("YUANBAO_HOME_CHANNEL_THREAD_ID") or None,
|
||||
)
|
||||
yuanbao_dm_policy = os.getenv("YUANBAO_DM_POLICY")
|
||||
if yuanbao_dm_policy:
|
||||
|
||||
+7
-9
@@ -53,10 +53,9 @@ class DeliveryTarget:
|
||||
- "telegram" → Telegram home channel
|
||||
- "telegram:123456" → specific Telegram chat
|
||||
"""
|
||||
target_stripped = target.strip()
|
||||
target_lower = target_stripped.lower()
|
||||
target = target.strip().lower()
|
||||
|
||||
if target_lower == "origin":
|
||||
if target == "origin":
|
||||
if origin:
|
||||
return cls(
|
||||
platform=origin.platform,
|
||||
@@ -68,14 +67,13 @@ class DeliveryTarget:
|
||||
# Fallback to local if no origin
|
||||
return cls(platform=Platform.LOCAL, is_origin=True)
|
||||
|
||||
if target_lower == "local":
|
||||
if target == "local":
|
||||
return cls(platform=Platform.LOCAL)
|
||||
|
||||
# Check for platform:chat_id or platform:chat_id:thread_id format
|
||||
# Use the original case for chat_id/thread_id to preserve case-sensitive IDs
|
||||
if ":" in target_stripped:
|
||||
parts = target_stripped.split(":", 2)
|
||||
platform_str = parts[0].lower() # Platform names are case-insensitive
|
||||
if ":" in target:
|
||||
parts = target.split(":", 2)
|
||||
platform_str = parts[0]
|
||||
chat_id = parts[1] if len(parts) > 1 else None
|
||||
thread_id = parts[2] if len(parts) > 2 else None
|
||||
try:
|
||||
@@ -87,7 +85,7 @@ class DeliveryTarget:
|
||||
|
||||
# Just a platform name (use home channel)
|
||||
try:
|
||||
platform = Platform(target_lower)
|
||||
platform = Platform(target)
|
||||
return cls(platform=platform)
|
||||
except ValueError:
|
||||
# Unknown platform, treat as local
|
||||
|
||||
@@ -1,84 +0,0 @@
|
||||
"""Shared HTTP client factory for long-lived platform adapters.
|
||||
|
||||
Gateway messaging platforms (QQ Bot, Feishu, WeCom, DingTalk, Signal,
|
||||
BlueBubbles, WeCom-callback) keep a persistent ``httpx.AsyncClient``
|
||||
alive for the adapter's lifetime. That amortises TLS/connection setup
|
||||
across many API calls, but it also means the process's file-descriptor
|
||||
pressure is sensitive to how aggressively the pool recycles idle keep-
|
||||
alive connections.
|
||||
|
||||
httpx's default ``keepalive_expiry`` is 5 seconds. On macOS behind
|
||||
Cloudflare Warp (and other transparent proxies), peer-initiated FIN can
|
||||
sit in ``CLOSE_WAIT`` longer than that before the local socket actually
|
||||
drains — which, multiplied across 7 long-lived adapters plus the LLM
|
||||
client and MCP clients, walks straight into the default 256 fd limit.
|
||||
See #18451.
|
||||
|
||||
``platform_httpx_limits()`` returns a tighter ``httpx.Limits`` the
|
||||
adapter factories use instead of the httpx default. The values chosen:
|
||||
|
||||
* ``max_keepalive_connections=10`` — plenty for any single adapter;
|
||||
platform APIs rarely parallelise beyond this.
|
||||
* ``keepalive_expiry=2.0`` — close idle sockets aggressively so a
|
||||
proxy's lingering CLOSE_WAIT window can't starve the process.
|
||||
|
||||
Override via ``HERMES_GATEWAY_HTTPX_KEEPALIVE_EXPIRY`` /
|
||||
``HERMES_GATEWAY_HTTPX_MAX_KEEPALIVE`` env vars when tuning under load.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
|
||||
try:
|
||||
import httpx
|
||||
except ImportError: # pragma: no cover — optional dep
|
||||
httpx = None # type: ignore[assignment]
|
||||
|
||||
|
||||
_DEFAULT_KEEPALIVE_EXPIRY_S = 2.0
|
||||
_DEFAULT_MAX_KEEPALIVE = 10
|
||||
|
||||
|
||||
def platform_httpx_limits() -> "httpx.Limits | None":
|
||||
"""Return ``httpx.Limits`` tuned for persistent platform-adapter clients.
|
||||
|
||||
Returns ``None`` when httpx isn't importable, so callers can fall
|
||||
back to httpx's built-in default without a hard dependency on this
|
||||
helper being reachable.
|
||||
"""
|
||||
if httpx is None:
|
||||
return None
|
||||
|
||||
def _env_float(name: str, default: float) -> float:
|
||||
raw = os.environ.get(name, "").strip()
|
||||
if not raw:
|
||||
return default
|
||||
try:
|
||||
val = float(raw)
|
||||
except (TypeError, ValueError):
|
||||
return default
|
||||
return val if val > 0 else default
|
||||
|
||||
def _env_int(name: str, default: int) -> int:
|
||||
raw = os.environ.get(name, "").strip()
|
||||
if not raw:
|
||||
return default
|
||||
try:
|
||||
val = int(raw)
|
||||
except (TypeError, ValueError):
|
||||
return default
|
||||
return val if val > 0 else default
|
||||
|
||||
keepalive_expiry = _env_float(
|
||||
"HERMES_GATEWAY_HTTPX_KEEPALIVE_EXPIRY", _DEFAULT_KEEPALIVE_EXPIRY_S
|
||||
)
|
||||
max_keepalive = _env_int(
|
||||
"HERMES_GATEWAY_HTTPX_MAX_KEEPALIVE", _DEFAULT_MAX_KEEPALIVE
|
||||
)
|
||||
|
||||
return httpx.Limits(
|
||||
max_keepalive_connections=max_keepalive,
|
||||
# Leave max_connections at httpx default (100) — plenty of headroom.
|
||||
keepalive_expiry=keepalive_expiry,
|
||||
)
|
||||
@@ -62,14 +62,6 @@ MAX_NORMALIZED_TEXT_LENGTH = 65_536 # 64 KB cap for normalized content parts
|
||||
MAX_CONTENT_LIST_SIZE = 1_000 # Max items when content is an array
|
||||
|
||||
|
||||
def _coerce_port(value: Any, default: int = DEFAULT_PORT) -> int:
|
||||
"""Parse a listen port without letting malformed env/config values crash startup."""
|
||||
try:
|
||||
return int(value)
|
||||
except (TypeError, ValueError):
|
||||
return default
|
||||
|
||||
|
||||
def _normalize_chat_content(
|
||||
content: Any, *, _max_depth: int = 10, _depth: int = 0,
|
||||
) -> str:
|
||||
@@ -581,10 +573,7 @@ class APIServerAdapter(BasePlatformAdapter):
|
||||
super().__init__(config, Platform.API_SERVER)
|
||||
extra = config.extra or {}
|
||||
self._host: str = extra.get("host", os.getenv("API_SERVER_HOST", DEFAULT_HOST))
|
||||
raw_port = extra.get("port")
|
||||
if raw_port is None:
|
||||
raw_port = os.getenv("API_SERVER_PORT", str(DEFAULT_PORT))
|
||||
self._port: int = _coerce_port(raw_port, DEFAULT_PORT)
|
||||
self._port: int = int(extra.get("port", os.getenv("API_SERVER_PORT", str(DEFAULT_PORT))))
|
||||
self._api_key: str = extra.get("key", os.getenv("API_SERVER_KEY", ""))
|
||||
self._cors_origins: tuple[str, ...] = self._parse_cors_origins(
|
||||
extra.get("cors_origins", os.getenv("API_SERVER_CORS_ORIGINS", "")),
|
||||
@@ -738,11 +727,10 @@ class APIServerAdapter(BasePlatformAdapter):
|
||||
gateway platforms), falling back to the hermes-api-server default.
|
||||
"""
|
||||
from run_agent import AIAgent
|
||||
from gateway.run import _resolve_runtime_agent_kwargs, _resolve_gateway_model, _load_gateway_config, GatewayRunner
|
||||
from gateway.run import _resolve_runtime_agent_kwargs, _resolve_gateway_model, _load_gateway_config
|
||||
from hermes_cli.tools_config import _get_platform_tools
|
||||
|
||||
runtime_kwargs = _resolve_runtime_agent_kwargs()
|
||||
reasoning_config = GatewayRunner._load_reasoning_config()
|
||||
model = _resolve_gateway_model()
|
||||
|
||||
user_config = _load_gateway_config()
|
||||
@@ -752,6 +740,7 @@ class APIServerAdapter(BasePlatformAdapter):
|
||||
|
||||
# Load fallback provider chain so the API server platform has the
|
||||
# same fallback behaviour as Telegram/Discord/Slack (fixes #4954).
|
||||
from gateway.run import GatewayRunner
|
||||
fallback_model = GatewayRunner._load_fallback_model()
|
||||
|
||||
agent = AIAgent(
|
||||
@@ -770,7 +759,6 @@ class APIServerAdapter(BasePlatformAdapter):
|
||||
tool_complete_callback=tool_complete_callback,
|
||||
session_db=self._ensure_session_db(),
|
||||
fallback_model=fallback_model,
|
||||
reasoning_config=reasoning_config,
|
||||
)
|
||||
return agent
|
||||
|
||||
@@ -2363,11 +2351,10 @@ class APIServerAdapter(BasePlatformAdapter):
|
||||
)
|
||||
if agent_ref is not None:
|
||||
agent_ref[0] = agent
|
||||
effective_task_id = session_id or str(uuid.uuid4())
|
||||
result = agent.run_conversation(
|
||||
user_message=user_message,
|
||||
conversation_history=conversation_history,
|
||||
task_id=effective_task_id,
|
||||
task_id="default",
|
||||
)
|
||||
usage = {
|
||||
"input_tokens": getattr(agent, "session_prompt_tokens", 0) or 0,
|
||||
@@ -2564,11 +2551,10 @@ class APIServerAdapter(BasePlatformAdapter):
|
||||
)
|
||||
self._active_run_agents[run_id] = agent
|
||||
def _run_sync():
|
||||
effective_task_id = session_id or run_id
|
||||
r = agent.run_conversation(
|
||||
user_message=user_message,
|
||||
conversation_history=conversation_history,
|
||||
task_id=effective_task_id,
|
||||
task_id="default",
|
||||
)
|
||||
u = {
|
||||
"input_tokens": getattr(agent, "session_prompt_tokens", 0) or 0,
|
||||
|
||||
+19
-227
@@ -416,7 +416,7 @@ def is_host_excluded_by_no_proxy(hostname: str, no_proxy_value: str | None = Non
|
||||
from dataclasses import dataclass, field
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Optional, Any, Callable, Awaitable, Tuple, Union
|
||||
from typing import Dict, List, Optional, Any, Callable, Awaitable, Tuple
|
||||
from enum import Enum
|
||||
|
||||
from pathlib import Path as _Path
|
||||
@@ -981,7 +981,7 @@ def coerce_plaintext_gateway_command(event: "MessageEvent") -> None:
|
||||
return
|
||||
|
||||
|
||||
@dataclass
|
||||
@dataclass
|
||||
class SendResult:
|
||||
"""Result of sending a message."""
|
||||
success: bool
|
||||
@@ -991,45 +991,6 @@ class SendResult:
|
||||
retryable: bool = False # True for transient connection errors — base will retry automatically
|
||||
|
||||
|
||||
class EphemeralReply(str):
|
||||
"""System-notice reply that auto-deletes after a TTL.
|
||||
|
||||
Slash-command handlers in ``gateway/run.py`` can return this wrapper
|
||||
instead of a plain string to request that the reply message be deleted
|
||||
after ``ttl_seconds`` on platforms that support ``delete_message``.
|
||||
|
||||
Subclassing ``str`` keeps the wrapper transparent to anything that
|
||||
treats handler return values as text (existing tests use ``in`` /
|
||||
``startswith`` / equality; the ``_process_message_background`` pipeline
|
||||
extracts attachments from the string content). ``isinstance(r,
|
||||
EphemeralReply)`` still distinguishes ephemeral replies from plain
|
||||
strings so the send path can schedule deletion.
|
||||
|
||||
Platforms that don't override :meth:`BasePlatformAdapter.delete_message`
|
||||
silently ignore the TTL — the message is sent normally and left in
|
||||
place. When ``ttl_seconds`` is ``None``, the pipeline uses the
|
||||
configured ``display.ephemeral_system_ttl`` default. A default of ``0``
|
||||
disables auto-deletion globally, preserving prior behavior.
|
||||
"""
|
||||
|
||||
ttl_seconds: Optional[int]
|
||||
|
||||
def __new__(cls, text: str, ttl_seconds: Optional[int] = None):
|
||||
instance = super().__new__(cls, text)
|
||||
instance.ttl_seconds = ttl_seconds
|
||||
return instance
|
||||
|
||||
@property
|
||||
def text(self) -> str:
|
||||
"""Return the underlying text.
|
||||
|
||||
Provided for call sites that want an explicit string conversion,
|
||||
though ``str(reply)`` and using ``reply`` directly where a string
|
||||
is expected both work identically.
|
||||
"""
|
||||
return str.__str__(self)
|
||||
|
||||
|
||||
def merge_pending_message_event(
|
||||
pending_messages: Dict[str, MessageEvent],
|
||||
session_key: str,
|
||||
@@ -1073,11 +1034,6 @@ def merge_pending_message_event(
|
||||
existing.text = event.text
|
||||
if existing_is_photo or incoming_is_photo:
|
||||
existing.message_type = MessageType.PHOTO
|
||||
elif (
|
||||
getattr(existing, "message_type", None) == MessageType.TEXT
|
||||
and event.message_type != MessageType.TEXT
|
||||
):
|
||||
existing.message_type = event.message_type
|
||||
return
|
||||
|
||||
if (
|
||||
@@ -1112,10 +1068,8 @@ _RETRYABLE_ERROR_PATTERNS = (
|
||||
)
|
||||
|
||||
|
||||
# Type for message handlers. Handlers may return a plain string (normal
|
||||
# reply), an ``EphemeralReply`` to opt the reply into auto-deletion, or
|
||||
# ``None`` when the response was already delivered (e.g. via streaming).
|
||||
MessageHandler = Callable[[MessageEvent], Awaitable[Optional[Union[str, "EphemeralReply"]]]]
|
||||
# Type for message handlers
|
||||
MessageHandler = Callable[[MessageEvent], Awaitable[Optional[str]]]
|
||||
|
||||
|
||||
def resolve_channel_prompt(
|
||||
@@ -1500,64 +1454,6 @@ class BasePlatformAdapter(ABC):
|
||||
"""
|
||||
return False
|
||||
|
||||
def _get_ephemeral_system_ttl_default(self) -> int:
|
||||
"""Read ``display.ephemeral_system_ttl`` from config.
|
||||
|
||||
Returns the TTL in seconds to use when an :class:`EphemeralReply`
|
||||
does not specify one explicitly. ``0`` (the default) disables
|
||||
auto-deletion. Non-fatal if config is unreadable.
|
||||
"""
|
||||
try:
|
||||
from hermes_cli.config import load_config as _load_config
|
||||
except Exception:
|
||||
return 0
|
||||
try:
|
||||
cfg = _load_config()
|
||||
except Exception:
|
||||
return 0
|
||||
display = cfg.get("display", {}) if isinstance(cfg, dict) else {}
|
||||
if not isinstance(display, dict):
|
||||
return 0
|
||||
raw = display.get("ephemeral_system_ttl", 0)
|
||||
try:
|
||||
return int(raw)
|
||||
except (TypeError, ValueError):
|
||||
return 0
|
||||
|
||||
def _schedule_ephemeral_delete(
|
||||
self,
|
||||
chat_id: str,
|
||||
message_id: str,
|
||||
ttl_seconds: int,
|
||||
) -> None:
|
||||
"""Spawn a detached task that deletes ``message_id`` after ``ttl_seconds``.
|
||||
|
||||
Best-effort — failures (gateway restart, permission denied, message
|
||||
too old for Telegram's 48h window) are swallowed at debug level.
|
||||
Does not block the caller.
|
||||
"""
|
||||
|
||||
async def _run_delete() -> None:
|
||||
try:
|
||||
await asyncio.sleep(max(1, int(ttl_seconds)))
|
||||
await self.delete_message(chat_id=chat_id, message_id=message_id)
|
||||
except asyncio.CancelledError:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.debug(
|
||||
"[%s] Ephemeral delete failed for %s/%s: %s",
|
||||
self.name, chat_id, message_id, e,
|
||||
)
|
||||
|
||||
coro = _run_delete()
|
||||
try:
|
||||
asyncio.create_task(coro)
|
||||
except RuntimeError:
|
||||
# No running loop (e.g. unit tests that never reach the async
|
||||
# path). Close the coroutine cleanly so Python doesn't warn
|
||||
# about it never being awaited, then drop silently.
|
||||
coro.close()
|
||||
|
||||
async def send_slash_confirm(
|
||||
self,
|
||||
chat_id: str,
|
||||
@@ -1593,26 +1489,6 @@ class BasePlatformAdapter(ABC):
|
||||
"""
|
||||
return SendResult(success=False, error="Not supported")
|
||||
|
||||
async def send_private_notice(
|
||||
self,
|
||||
chat_id: str,
|
||||
user_id: Optional[str],
|
||||
content: str,
|
||||
reply_to: Optional[str] = None,
|
||||
metadata: Optional[Dict[str, Any]] = None,
|
||||
) -> SendResult:
|
||||
"""Send a notice privately when the platform supports it.
|
||||
|
||||
The default implementation falls back to a normal send so callers can
|
||||
use one code path across platforms.
|
||||
"""
|
||||
return await self.send(
|
||||
chat_id=chat_id,
|
||||
content=content,
|
||||
reply_to=reply_to,
|
||||
metadata=metadata,
|
||||
)
|
||||
|
||||
async def send_typing(self, chat_id: str, metadata=None) -> None:
|
||||
"""
|
||||
Send a typing indicator.
|
||||
@@ -2167,28 +2043,6 @@ class BasePlatformAdapter(ABC):
|
||||
lowered = error.lower()
|
||||
return "timed out" in lowered or "readtimeout" in lowered or "writetimeout" in lowered
|
||||
|
||||
def _unwrap_ephemeral(self, response: Any) -> Tuple[Optional[str], int]:
|
||||
"""Unwrap a handler response into (text, ttl_seconds).
|
||||
|
||||
Accepts a plain string, ``None``, or an :class:`EphemeralReply`.
|
||||
Returns ``(text, ttl)`` where ``ttl > 0`` means the caller should
|
||||
schedule a deletion via :meth:`_schedule_ephemeral_delete` after
|
||||
the send succeeds. ``ttl`` is forced to 0 when the adapter
|
||||
doesn't override :meth:`delete_message` so non-supporting
|
||||
platforms silently degrade to normal sends.
|
||||
"""
|
||||
if isinstance(response, EphemeralReply):
|
||||
ttl = response.ttl_seconds
|
||||
if ttl is None:
|
||||
try:
|
||||
ttl = int(self._get_ephemeral_system_ttl_default())
|
||||
except Exception:
|
||||
ttl = 0
|
||||
if ttl and ttl > 0 and type(self).delete_message is BasePlatformAdapter.delete_message:
|
||||
ttl = 0
|
||||
return response.text, int(ttl or 0)
|
||||
return response, 0
|
||||
|
||||
async def _send_with_retry(
|
||||
self,
|
||||
chat_id: str,
|
||||
@@ -2489,39 +2343,20 @@ class BasePlatformAdapter(ABC):
|
||||
|
||||
try:
|
||||
response = await self._message_handler(event)
|
||||
_text, _eph_ttl = self._unwrap_ephemeral(response)
|
||||
# Send the response BEFORE cancelling the old task so the send
|
||||
# cannot be affected by task-cancellation side effects (race
|
||||
# condition fix — issue #18912). Previously the send happened
|
||||
# after cancel_session_processing, which could silently drop the
|
||||
# "/new" confirmation when an agent was actively running.
|
||||
if _text:
|
||||
logger.info(
|
||||
"[%s] Sending command '/%s' response (%d chars) to %s",
|
||||
self.name,
|
||||
cmd,
|
||||
len(_text),
|
||||
event.source.chat_id,
|
||||
)
|
||||
_r = await self._send_with_retry(
|
||||
chat_id=event.source.chat_id,
|
||||
content=_text,
|
||||
reply_to=event.message_id,
|
||||
metadata=thread_meta,
|
||||
)
|
||||
if _eph_ttl > 0 and _r.success and _r.message_id:
|
||||
self._schedule_ephemeral_delete(
|
||||
chat_id=event.source.chat_id,
|
||||
message_id=_r.message_id,
|
||||
ttl_seconds=_eph_ttl,
|
||||
)
|
||||
# Old adapter task (if any) is cancelled AFTER the response has
|
||||
# been sent — keeps ordering deterministic and avoids the race.
|
||||
# Old adapter task (if any) is cancelled AFTER the runner has
|
||||
# fully handled the command — keeps ordering deterministic.
|
||||
await self.cancel_session_processing(
|
||||
session_key,
|
||||
release_guard=False,
|
||||
discard_pending=False,
|
||||
)
|
||||
if response:
|
||||
await self._send_with_retry(
|
||||
chat_id=event.source.chat_id,
|
||||
content=response,
|
||||
reply_to=event.message_id,
|
||||
metadata=thread_meta,
|
||||
)
|
||||
except Exception:
|
||||
# On failure, restore the original guard if one still exists so
|
||||
# we don't leave the session in a half-reset state.
|
||||
@@ -2601,20 +2436,13 @@ class BasePlatformAdapter(ABC):
|
||||
try:
|
||||
_thread_meta = {"thread_id": event.source.thread_id} if event.source.thread_id else None
|
||||
response = await self._message_handler(event)
|
||||
_text, _eph_ttl = self._unwrap_ephemeral(response)
|
||||
if _text:
|
||||
_r = await self._send_with_retry(
|
||||
if response:
|
||||
await self._send_with_retry(
|
||||
chat_id=event.source.chat_id,
|
||||
content=_text,
|
||||
content=response,
|
||||
reply_to=event.message_id,
|
||||
metadata=_thread_meta,
|
||||
)
|
||||
if _eph_ttl > 0 and _r.success and _r.message_id:
|
||||
self._schedule_ephemeral_delete(
|
||||
chat_id=event.source.chat_id,
|
||||
message_id=_r.message_id,
|
||||
ttl_seconds=_eph_ttl,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error("[%s] Command '/%s' dispatch failed: %s", self.name, cmd, e, exc_info=True)
|
||||
return
|
||||
@@ -2688,6 +2516,7 @@ class BasePlatformAdapter(ABC):
|
||||
# Fall back to a new Event only if the entry was removed externally.
|
||||
interrupt_event = self._active_sessions.get(session_key) or asyncio.Event()
|
||||
self._active_sessions[session_key] = interrupt_event
|
||||
callback_generation = getattr(interrupt_event, "_hermes_run_generation", None)
|
||||
|
||||
# Start continuous typing indicator (refreshes every 2 seconds)
|
||||
_thread_metadata = {"thread_id": event.source.thread_id} if event.source.thread_id else None
|
||||
@@ -2720,16 +2549,7 @@ class BasePlatformAdapter(ABC):
|
||||
|
||||
# Call the handler (this can take a while with tool calls)
|
||||
response = await self._message_handler(event)
|
||||
|
||||
# Slash-command handlers may return an EphemeralReply sentinel to
|
||||
# request that their reply message auto-delete after a TTL (used
|
||||
# for system notices like "✨ New session started!" that the user
|
||||
# doesn't need to keep in the thread). Unwrap here so all the
|
||||
# downstream extract_media / text-processing logic sees a plain
|
||||
# string, and remember the TTL + platform capability so the
|
||||
# post-send block can schedule the deletion.
|
||||
response, _ephemeral_ttl = self._unwrap_ephemeral(response)
|
||||
|
||||
|
||||
# Send response if any. A None/empty response is normal when
|
||||
# streaming already delivered the text (already_sent=True) or
|
||||
# when the message was queued behind an active agent. Log at
|
||||
@@ -2818,21 +2638,6 @@ class BasePlatformAdapter(ABC):
|
||||
)
|
||||
_record_delivery(result)
|
||||
|
||||
# Schedule auto-deletion of system-notice replies.
|
||||
# Detached so the handler returns immediately; errors
|
||||
# (permission denied, message too old) are swallowed.
|
||||
if (
|
||||
_ephemeral_ttl
|
||||
and _ephemeral_ttl > 0
|
||||
and result.success
|
||||
and result.message_id
|
||||
):
|
||||
self._schedule_ephemeral_delete(
|
||||
chat_id=event.source.chat_id,
|
||||
message_id=result.message_id,
|
||||
ttl_seconds=_ephemeral_ttl,
|
||||
)
|
||||
|
||||
# Human-like pacing delay between text and media
|
||||
human_delay = self._get_human_delay()
|
||||
|
||||
@@ -3010,20 +2815,7 @@ class BasePlatformAdapter(ABC):
|
||||
finally:
|
||||
# Fire any one-shot post-delivery callback registered for this
|
||||
# session (e.g. deferred background-review notifications).
|
||||
#
|
||||
# Snapshot the callback generation HERE (after the agent has run),
|
||||
# not at the top of this task. _hermes_run_generation is set on
|
||||
# the interrupt event by GatewayRunner._bind_adapter_run_generation
|
||||
# during _handle_message_with_agent — which happens DURING the
|
||||
# self._message_handler(event) await above. Snapshotting earlier
|
||||
# always captured None, which bypassed the generation-ownership
|
||||
# check in pop_post_delivery_callback and let stale runs fire a
|
||||
# fresher run's callbacks.
|
||||
_callback_generation = getattr(
|
||||
interrupt_event,
|
||||
"_hermes_run_generation",
|
||||
None,
|
||||
)
|
||||
_callback_generation = callback_generation
|
||||
if hasattr(self, "pop_post_delivery_callback"):
|
||||
_post_cb = self.pop_post_delivery_callback(
|
||||
session_key,
|
||||
|
||||
@@ -162,9 +162,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
|
||||
return False
|
||||
from aiohttp import web
|
||||
|
||||
# Tighter keepalive so idle CLOSE_WAIT drains promptly (#18451).
|
||||
from gateway.platforms._http_client_limits import platform_httpx_limits
|
||||
self.client = httpx.AsyncClient(timeout=30.0, limits=platform_httpx_limits())
|
||||
self.client = httpx.AsyncClient(timeout=30.0)
|
||||
try:
|
||||
await self._api_get("/api/v1/ping")
|
||||
info = await self._api_get("/api/v1/server/info")
|
||||
|
||||
@@ -228,11 +228,7 @@ class DingTalkAdapter(BasePlatformAdapter):
|
||||
return False
|
||||
|
||||
try:
|
||||
# Tighter keepalive so idle CLOSE_WAIT drains promptly (#18451).
|
||||
from gateway.platforms._http_client_limits import platform_httpx_limits
|
||||
self._http_client = httpx.AsyncClient(
|
||||
timeout=30.0, limits=platform_httpx_limits(),
|
||||
)
|
||||
self._http_client = httpx.AsyncClient(timeout=30.0)
|
||||
|
||||
credential = dingtalk_stream.Credential(
|
||||
self._client_id, self._client_secret
|
||||
|
||||
+48
-515
@@ -497,7 +497,6 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
self._ready_event = asyncio.Event()
|
||||
self._allowed_user_ids: set = set() # For button approval authorization
|
||||
self._allowed_role_ids: set = set() # For DISCORD_ALLOWED_ROLES filtering
|
||||
self.gateway_runner = None # Set by gateway/run.py for cross-platform delivery
|
||||
# Voice channel state (per-guild)
|
||||
self._voice_clients: Dict[int, Any] = {} # guild_id -> VoiceClient
|
||||
self._voice_locks: Dict[int, asyncio.Lock] = {} # guild_id -> serialize join/leave
|
||||
@@ -614,21 +613,6 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
# so LLM output or echoed user content can't ping the whole
|
||||
# server; override per DISCORD_ALLOW_MENTION_* env vars or the
|
||||
# discord.allow_mentions.* block in config.yaml.
|
||||
|
||||
# Close any existing client to prevent zombie websocket connections
|
||||
# on reconnect (see #18187). Without this, the old client remains
|
||||
# connected to Discord gateway and both fire on_message, causing
|
||||
# double responses.
|
||||
if self._client is not None:
|
||||
try:
|
||||
if not self._client.is_closed():
|
||||
await self._client.close()
|
||||
except Exception:
|
||||
logger.debug("[%s] Failed to close previous Discord client", self.name)
|
||||
finally:
|
||||
self._client = None
|
||||
self._ready_event.clear()
|
||||
|
||||
self._client = commands.Bot(
|
||||
command_prefix="!", # Not really used, we handle raw messages
|
||||
intents=intents,
|
||||
@@ -1930,225 +1914,6 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
return True
|
||||
return False
|
||||
|
||||
# ── Slash command authorization ─────────────────────────────────────
|
||||
# Slash commands (``_run_simple_slash`` and ``_handle_thread_create_slash``)
|
||||
# are a separate Discord interaction surface from regular messages and
|
||||
# historically ran with NO authorization check — bypassing every gate
|
||||
# ``on_message`` enforces (DISCORD_ALLOWED_USERS, DISCORD_ALLOWED_ROLES,
|
||||
# DISCORD_ALLOWED_CHANNELS, DISCORD_IGNORED_CHANNELS). Any guild member
|
||||
# could invoke ``/background``, ``/restart``, ``/sethome``, etc. as the
|
||||
# operator. ``_check_slash_authorization`` mirrors the on_message gates
|
||||
# one-for-one so the slash surface honors the same trust boundary.
|
||||
#
|
||||
# By design, this is a no-op for deployments with no allowlist env vars
|
||||
# set — ``_is_allowed_user`` returns True and the channel checks early-out
|
||||
# — preserving the existing "single-tenant, all guild members trusted"
|
||||
# default. Deployments that DO set any DISCORD_ALLOWED_* var get slash
|
||||
# parity with on_message.
|
||||
|
||||
def _evaluate_slash_authorization(
|
||||
self, interaction: "discord.Interaction",
|
||||
) -> Tuple[bool, Optional[str]]:
|
||||
"""Evaluate slash authorization without producing any response.
|
||||
|
||||
Returns ``(allowed, reason)``. ``reason`` is populated only when
|
||||
``allowed`` is False. This is the shared core used by both the
|
||||
responding wrapper (``_check_slash_authorization``) and side-effect-
|
||||
free callers like the ``/skill`` autocomplete callback, which must
|
||||
return an empty list for unauthorized users instead of leaking an
|
||||
ephemeral rejection per-keystroke.
|
||||
|
||||
Fail-closed semantics for malformed payloads: when an allowlist is
|
||||
configured but the interaction is missing the data needed to
|
||||
evaluate it (no channel id with channel policy active, no user
|
||||
with user/role policy active), the gate REJECTS rather than
|
||||
falling through. Without these guards a guild interaction that
|
||||
happens to deserialize without a channel id would silently bypass
|
||||
``DISCORD_ALLOWED_CHANNELS`` and a payload missing ``user`` would
|
||||
raise ``AttributeError`` in the user check below, surfacing as
|
||||
an opaque interaction failure rather than a clean rejection.
|
||||
"""
|
||||
chan_obj = getattr(interaction, "channel", None)
|
||||
in_dm = isinstance(chan_obj, discord.DMChannel) if chan_obj is not None else False
|
||||
|
||||
# ── Channel scope (mirrors on_message lines 3374-3388) ──
|
||||
# DMs aren't channel-gated — DMs follow on_message's DM lockdown
|
||||
# path which has its own user-allowlist enforcement.
|
||||
if not in_dm:
|
||||
chan_id_raw = getattr(interaction, "channel_id", None) or getattr(
|
||||
chan_obj, "id", None,
|
||||
)
|
||||
channel_ids: set = set()
|
||||
if chan_id_raw is not None:
|
||||
channel_ids.add(str(chan_id_raw))
|
||||
# Mirror on_message: also test the parent channel for threads
|
||||
# so per-channel allow/deny lists work consistently.
|
||||
if isinstance(chan_obj, discord.Thread):
|
||||
parent_id = self._get_parent_channel_id(chan_obj)
|
||||
if parent_id:
|
||||
channel_ids.add(str(parent_id))
|
||||
|
||||
allowed_raw = os.getenv("DISCORD_ALLOWED_CHANNELS", "")
|
||||
if allowed_raw:
|
||||
allowed = {c.strip() for c in allowed_raw.split(",") if c.strip()}
|
||||
if "*" not in allowed:
|
||||
if not channel_ids:
|
||||
# Channel policy is configured but the interaction
|
||||
# has no resolvable channel id. Fail closed.
|
||||
return (
|
||||
False,
|
||||
"channel id missing with DISCORD_ALLOWED_CHANNELS configured",
|
||||
)
|
||||
if not (channel_ids & allowed):
|
||||
return (False, "channel not in DISCORD_ALLOWED_CHANNELS")
|
||||
|
||||
# Ignored beats allowed: even when a thread's parent channel
|
||||
# is on the allowlist, an explicit DISCORD_IGNORED_CHANNELS
|
||||
# entry on the thread or its parent rejects the interaction.
|
||||
ignored_raw = os.getenv("DISCORD_IGNORED_CHANNELS", "")
|
||||
if ignored_raw and channel_ids:
|
||||
ignored = {c.strip() for c in ignored_raw.split(",") if c.strip()}
|
||||
if "*" in ignored or (channel_ids & ignored):
|
||||
return (False, "channel in DISCORD_IGNORED_CHANNELS")
|
||||
|
||||
# ── User / role allowlist (mirrors on_message line 681) ──
|
||||
user = getattr(interaction, "user", None)
|
||||
allowed_users = getattr(self, "_allowed_user_ids", set()) or set()
|
||||
allowed_roles = getattr(self, "_allowed_role_ids", set()) or set()
|
||||
if user is None or getattr(user, "id", None) is None:
|
||||
# No identifiable user. With any user/role allowlist
|
||||
# configured, fail closed rather than raise AttributeError
|
||||
# on ``interaction.user.id`` below. With no allowlist this
|
||||
# is the existing "no allowlist = everyone" backwards-compat.
|
||||
if allowed_users or allowed_roles:
|
||||
return (False, "missing interaction.user with allowlist configured")
|
||||
return (True, None)
|
||||
|
||||
user_id = str(user.id)
|
||||
if not self._is_allowed_user(user_id, author=user):
|
||||
return (
|
||||
False,
|
||||
"user not in DISCORD_ALLOWED_USERS / DISCORD_ALLOWED_ROLES",
|
||||
)
|
||||
|
||||
return (True, None)
|
||||
|
||||
async def _check_slash_authorization(
|
||||
self, interaction: "discord.Interaction", command_text: str,
|
||||
) -> bool:
|
||||
"""Mirror on_message's user/role/channel gates onto a slash invocation.
|
||||
|
||||
Returns True to proceed. Returns False *after* sending an ephemeral
|
||||
rejection, logging a warning, and scheduling a cross-platform admin
|
||||
alert — the caller must stop on False (the interaction has already
|
||||
been responded to).
|
||||
"""
|
||||
allowed, reason = self._evaluate_slash_authorization(interaction)
|
||||
if allowed:
|
||||
return True
|
||||
return await self._reject_slash(
|
||||
interaction, command_text, reason=reason or "unauthorized",
|
||||
)
|
||||
|
||||
async def _reject_slash(
|
||||
self, interaction: "discord.Interaction", command_text: str, *, reason: str,
|
||||
) -> bool:
|
||||
"""Send ephemeral reject + log warning + schedule admin alert. Returns False.
|
||||
|
||||
Tolerates a missing ``interaction.user`` -- the fail-closed branch
|
||||
in ``_evaluate_slash_authorization`` deliberately routes here for
|
||||
malformed payloads (no user) when an allowlist is configured, and
|
||||
``str(interaction.user.id)`` would raise AttributeError before the
|
||||
ephemeral rejection could be sent.
|
||||
"""
|
||||
user = getattr(interaction, "user", None)
|
||||
if user is not None:
|
||||
user_id = str(getattr(user, "id", "?"))
|
||||
user_name = getattr(user, "name", "?")
|
||||
else:
|
||||
user_id = "?"
|
||||
user_name = "?"
|
||||
chan_id = getattr(interaction, "channel_id", None) or getattr(
|
||||
getattr(interaction, "channel", None), "id", None,
|
||||
)
|
||||
guild_id = getattr(interaction, "guild_id", None)
|
||||
|
||||
logger.warning(
|
||||
"[Discord] Unauthorized slash attempt: user=%s id=%s channel=%s "
|
||||
"guild=%s cmd=%r reason=%r",
|
||||
user_name, user_id, chan_id, guild_id, command_text, reason,
|
||||
)
|
||||
|
||||
try:
|
||||
await interaction.response.send_message(
|
||||
"You're not authorized to use this command.",
|
||||
ephemeral=True,
|
||||
)
|
||||
except Exception as e:
|
||||
# Interaction may already be responded to (e.g. caller deferred
|
||||
# before the auth check, or Discord retried). Best-effort only.
|
||||
logger.debug("[Discord] Could not send unauthorized ephemeral: %s", e)
|
||||
|
||||
# Fire-and-forget: don't block the interaction handler on Telegram I/O.
|
||||
try:
|
||||
asyncio.create_task(self._notify_unauthorized_slash(
|
||||
user_name, user_id, chan_id, guild_id, command_text, reason,
|
||||
))
|
||||
except Exception as e:
|
||||
logger.debug("[Discord] Could not schedule admin notify task: %s", e)
|
||||
|
||||
return False
|
||||
|
||||
async def _notify_unauthorized_slash(
|
||||
self, user_name: str, user_id: str, chan_id, guild_id,
|
||||
command_text: str, reason: str,
|
||||
) -> None:
|
||||
"""Best-effort cross-platform alert to the gateway operator.
|
||||
|
||||
Tries TELEGRAM first (most operators set TELEGRAM_HOME_CHANNEL),
|
||||
then SLACK. Silently no-ops if no other platform is configured
|
||||
with a home channel.
|
||||
|
||||
A soft send failure -- adapter.send() returning a result with
|
||||
``success=False`` rather than raising -- continues the fallback
|
||||
chain. Treating a SendResult(success=False) as delivered would
|
||||
mean a Telegram outage that the adapter politely surfaces (e.g.
|
||||
rate-limit, auth failure) silently swallows the alert without
|
||||
attempting Slack. Hard exceptions still take the same path via
|
||||
the except branch below.
|
||||
"""
|
||||
runner = getattr(self, "gateway_runner", None)
|
||||
if not runner:
|
||||
return
|
||||
for target in (Platform.TELEGRAM, Platform.SLACK):
|
||||
try:
|
||||
adapter = runner.adapters.get(target)
|
||||
if not adapter:
|
||||
continue
|
||||
home = runner.config.get_home_channel(target)
|
||||
if not home or not getattr(home, "chat_id", None):
|
||||
continue
|
||||
msg = (
|
||||
"⚠️ Unauthorized Discord slash attempt\n"
|
||||
f"User: {user_name} ({user_id})\n"
|
||||
f"Channel: {chan_id} (guild {guild_id})\n"
|
||||
f"Command: {command_text}\n"
|
||||
f"Reason: {reason}"
|
||||
)
|
||||
result = await adapter.send(str(home.chat_id), msg)
|
||||
# Only return on confirmed delivery. SendResult(success=False)
|
||||
# -> continue to the next platform.
|
||||
if getattr(result, "success", None) is False:
|
||||
logger.debug(
|
||||
"[Discord] Admin notify via %s returned success=False"
|
||||
" (error=%r); falling through",
|
||||
target, getattr(result, "error", None),
|
||||
)
|
||||
continue
|
||||
return
|
||||
except Exception as e:
|
||||
logger.debug("[Discord] Admin notify via %s failed: %s", target, e)
|
||||
|
||||
async def send_image_file(
|
||||
self,
|
||||
chat_id: str,
|
||||
@@ -2536,11 +2301,6 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
except Exception:
|
||||
pass # logging must never block command dispatch
|
||||
|
||||
# Auth gate — must run before defer() so an ephemeral rejection can
|
||||
# be delivered on the still-unresponded interaction.
|
||||
if not await self._check_slash_authorization(interaction, command_text):
|
||||
return
|
||||
|
||||
await interaction.response.defer(ephemeral=True)
|
||||
event = self._build_slash_event(interaction, command_text)
|
||||
await self.handle_message(event)
|
||||
@@ -2685,8 +2445,7 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
message: str = "",
|
||||
auto_archive_duration: int = 1440,
|
||||
):
|
||||
# defer() is performed inside the handler *after* the auth gate
|
||||
# so a rejected invoker can receive an ephemeral rejection.
|
||||
await interaction.response.defer(ephemeral=True)
|
||||
await self._handle_thread_create_slash(interaction, name, message, auto_archive_duration)
|
||||
|
||||
@tree.command(name="queue", description="Queue a prompt for the next turn (doesn't interrupt)")
|
||||
@@ -2807,54 +2566,6 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
# supporting up to 25 categories × 25 skills = 625 skills.
|
||||
self._register_skill_group(tree)
|
||||
|
||||
# Optional defense-in-depth: hide every slash command from non-admin
|
||||
# guild members in Discord's slash picker. Server-side authorization
|
||||
# (``_check_slash_authorization``) is the actual gate; this is purely
|
||||
# UX so users don't see commands they can't invoke. Off by default
|
||||
# to preserve the slash UX for deployments that intentionally allow
|
||||
# everyone in the guild.
|
||||
if os.getenv("DISCORD_HIDE_SLASH_COMMANDS", "false").strip().lower() in (
|
||||
"true", "1", "yes", "on",
|
||||
):
|
||||
self._apply_owner_only_visibility(tree)
|
||||
|
||||
def _apply_owner_only_visibility(self, tree) -> None:
|
||||
"""Set default_member_permissions=0 on every registered slash command.
|
||||
|
||||
Discord interprets ``Permissions(0)`` as "requires no permissions",
|
||||
which paradoxically means the command is hidden from every guild
|
||||
member except those with the Administrator permission. Server admins
|
||||
can re-grant per user/role via Server Settings → Integrations →
|
||||
<bot> → Permissions.
|
||||
|
||||
Authoritative gate is ``_check_slash_authorization`` on every
|
||||
invocation, which catches stale clients, role grants made by
|
||||
mistake, and direct API calls bypassing Discord's UI hide.
|
||||
"""
|
||||
try:
|
||||
no_perms = discord.Permissions(0)
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
"[Discord] _apply_owner_only_visibility: cannot build Permissions(0): %s",
|
||||
e,
|
||||
)
|
||||
return
|
||||
applied = 0
|
||||
for cmd in tree.get_commands():
|
||||
try:
|
||||
cmd.default_permissions = no_perms
|
||||
applied += 1
|
||||
except Exception as e:
|
||||
logger.debug(
|
||||
"[Discord] Could not set default_permissions on %r: %s",
|
||||
getattr(cmd, "name", "?"), e,
|
||||
)
|
||||
logger.info(
|
||||
"[Discord] Hid %d slash command(s) from non-admin guild members "
|
||||
"(opt-in defense in depth via DISCORD_HIDE_SLASH_COMMANDS).",
|
||||
applied,
|
||||
)
|
||||
|
||||
def _register_skill_group(self, tree) -> None:
|
||||
"""Register a single ``/skill`` command with autocomplete on the name.
|
||||
|
||||
@@ -2873,32 +2584,40 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
hidden skills. The slash picker also becomes more discoverable —
|
||||
Discord live-filters by the user's typed prefix against both the
|
||||
skill name and its description.
|
||||
|
||||
The entries list and lookup dict are stored on ``self`` rather
|
||||
than captured in closure variables so :meth:`refresh_skill_group`
|
||||
can repopulate them when the user runs ``/reload-skills`` without
|
||||
needing to touch the Discord slash-command tree or trigger a
|
||||
``tree.sync()`` call.
|
||||
"""
|
||||
try:
|
||||
from hermes_cli.commands import discord_skill_commands_by_category
|
||||
|
||||
existing_names = set()
|
||||
try:
|
||||
existing_names = {cmd.name for cmd in tree.get_commands()}
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Populate the instance-level entries/lookup so the
|
||||
# autocomplete + handler callbacks below always read the
|
||||
# freshest state. refresh_skill_group() re-runs the same
|
||||
# collector and mutates these two attributes in place.
|
||||
self._skill_entries: list[tuple[str, str, str]] = []
|
||||
self._skill_lookup: dict[str, tuple[str, str]] = {}
|
||||
self._skill_group_reserved_names: set[str] = set(existing_names)
|
||||
self._refresh_skill_catalog_state()
|
||||
# Reuse the existing collector for consistent filtering
|
||||
# (per-platform disabled, hub-excluded, name clamping), then
|
||||
# flatten — the category grouping was only useful for the
|
||||
# nested layout.
|
||||
categories, uncategorized, hidden = discord_skill_commands_by_category(
|
||||
reserved_names=existing_names,
|
||||
)
|
||||
entries: list[tuple[str, str, str]] = list(uncategorized)
|
||||
for cat_skills in categories.values():
|
||||
entries.extend(cat_skills)
|
||||
|
||||
if not self._skill_entries:
|
||||
if not entries:
|
||||
return
|
||||
|
||||
# Stable alphabetical order so the autocomplete suggestion
|
||||
# list is predictable across restarts.
|
||||
entries.sort(key=lambda t: t[0])
|
||||
|
||||
# name -> (description, cmd_key) — used by both the autocomplete
|
||||
# callback and the handler for O(1) dispatch.
|
||||
skill_lookup: dict[str, tuple[str, str]] = {
|
||||
n: (d, k) for n, d, k in entries
|
||||
}
|
||||
|
||||
async def _autocomplete_name(
|
||||
interaction: "discord.Interaction", current: str,
|
||||
) -> list:
|
||||
@@ -2908,29 +2627,10 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
"/skill pdf" surfaces skills whose description mentions
|
||||
PDFs even if the name doesn't. Discord caps this list at
|
||||
25 entries per query.
|
||||
|
||||
Authorization: a quiet pre-check evaluates the slash
|
||||
allowlists and returns ``[]`` for unauthorized users so
|
||||
the installed skill catalog is not leaked to anyone who
|
||||
can see the command in the picker. Returning a generic
|
||||
empty list here is intentional — sending a per-keystroke
|
||||
ephemeral rejection would produce a barrage of error
|
||||
popups during typing.
|
||||
|
||||
Reads ``self._skill_entries`` so a ``/reload-skills`` run
|
||||
since process start shows up on the very next keystroke.
|
||||
"""
|
||||
try:
|
||||
allowed, _reason = self._evaluate_slash_authorization(interaction)
|
||||
except Exception:
|
||||
# Defensive: never raise from autocomplete. Fail
|
||||
# closed by returning an empty suggestion list.
|
||||
return []
|
||||
if not allowed:
|
||||
return []
|
||||
q = (current or "").strip().lower()
|
||||
choices: list = []
|
||||
for name, desc, _key in self._skill_entries:
|
||||
for name, desc, _key in entries:
|
||||
if not q or q in name.lower() or (desc and q in desc.lower()):
|
||||
if desc:
|
||||
label = f"{name} — {desc}"
|
||||
@@ -2954,13 +2654,7 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
async def _skill_handler(
|
||||
interaction: "discord.Interaction", name: str, args: str = "",
|
||||
):
|
||||
# Authorize BEFORE any skill lookup so that known and
|
||||
# unknown skill names produce identical rejections for
|
||||
# unauthorized users (no probing the installed catalog
|
||||
# via "Unknown skill: <name>" responses).
|
||||
if not await self._check_slash_authorization(interaction, "/skill"):
|
||||
return
|
||||
entry = self._skill_lookup.get(name)
|
||||
entry = skill_lookup.get(name)
|
||||
if not entry:
|
||||
await interaction.response.send_message(
|
||||
f"Unknown skill: `{name}`. Start typing for "
|
||||
@@ -2982,74 +2676,16 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
|
||||
logger.info(
|
||||
"[%s] Registered /skill command with %d skill(s) via autocomplete",
|
||||
self.name, len(self._skill_entries),
|
||||
self.name, len(entries),
|
||||
)
|
||||
if self._skill_group_hidden_count:
|
||||
if hidden:
|
||||
logger.info(
|
||||
"[%s] %d skill(s) filtered out of /skill (name clamp / reserved)",
|
||||
self.name, self._skill_group_hidden_count,
|
||||
self.name, hidden,
|
||||
)
|
||||
except Exception as exc:
|
||||
logger.warning("[%s] Failed to register /skill command: %s", self.name, exc)
|
||||
|
||||
def _refresh_skill_catalog_state(self) -> None:
|
||||
"""Re-scan disk for skills and repopulate ``self._skill_entries``.
|
||||
|
||||
Called once from :meth:`_register_skill_group` at startup and
|
||||
again from :meth:`refresh_skill_group` whenever the user runs
|
||||
``/reload-skills``. No Discord API calls are made — autocomplete
|
||||
and the handler both read from these instance attributes
|
||||
directly, so an in-place mutation is sufficient.
|
||||
"""
|
||||
from hermes_cli.commands import discord_skill_commands_by_category
|
||||
|
||||
reserved = getattr(self, "_skill_group_reserved_names", set())
|
||||
categories, uncategorized, hidden = discord_skill_commands_by_category(
|
||||
reserved_names=set(reserved),
|
||||
)
|
||||
entries: list[tuple[str, str, str]] = list(uncategorized)
|
||||
for cat_skills in categories.values():
|
||||
entries.extend(cat_skills)
|
||||
# Stable alphabetical order so the autocomplete suggestion
|
||||
# list is predictable across restarts.
|
||||
entries.sort(key=lambda t: t[0])
|
||||
|
||||
self._skill_entries = entries
|
||||
self._skill_lookup = {n: (d, k) for n, d, k in entries}
|
||||
self._skill_group_hidden_count = hidden
|
||||
|
||||
def refresh_skill_group(self) -> tuple[int, int]:
|
||||
"""Rescan skills and update the live ``/skill`` autocomplete state.
|
||||
|
||||
Invoked by :meth:`gateway.run.GatewayOrchestrator._handle_reload_skills_command`
|
||||
after :func:`agent.skill_commands.reload_skills` has refreshed
|
||||
the in-process skill-command registry. Without this call, the
|
||||
``/skill`` autocomplete dropdown keeps showing the list captured
|
||||
at process start — new skills stay invisible and deleted skills
|
||||
return an "Unknown skill" error when clicked.
|
||||
|
||||
Because autocomplete options are fetched dynamically by Discord,
|
||||
we only need to mutate the entries/lookup attributes read by the
|
||||
callbacks — no ``tree.sync()`` is required.
|
||||
|
||||
Returns ``(new_count, hidden_count)``.
|
||||
"""
|
||||
try:
|
||||
self._refresh_skill_catalog_state()
|
||||
except Exception as exc:
|
||||
logger.warning(
|
||||
"[%s] Failed to refresh /skill autocomplete after reload: %s",
|
||||
self.name, exc,
|
||||
)
|
||||
return (len(getattr(self, "_skill_entries", [])), 0)
|
||||
logger.info(
|
||||
"[%s] Refreshed /skill autocomplete: %d skill(s) available (%d filtered)",
|
||||
self.name,
|
||||
len(self._skill_entries),
|
||||
self._skill_group_hidden_count,
|
||||
)
|
||||
return (len(self._skill_entries), self._skill_group_hidden_count)
|
||||
|
||||
def _build_slash_event(self, interaction: discord.Interaction, text: str) -> MessageEvent:
|
||||
"""Build a MessageEvent from a Discord slash command interaction."""
|
||||
is_dm = isinstance(interaction.channel, discord.DMChannel)
|
||||
@@ -3107,9 +2743,6 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
auto_archive_duration: int = 1440,
|
||||
) -> None:
|
||||
"""Create a Discord thread from a slash command and start a session in it."""
|
||||
if not await self._check_slash_authorization(interaction, "/thread"):
|
||||
return
|
||||
await interaction.response.defer(ephemeral=True)
|
||||
result = await self._create_thread(
|
||||
interaction,
|
||||
name=name,
|
||||
@@ -3218,15 +2851,8 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
raw = os.getenv("DISCORD_FREE_RESPONSE_CHANNELS", "")
|
||||
if isinstance(raw, list):
|
||||
return {str(part).strip() for part in raw if str(part).strip()}
|
||||
# Coerce non-list scalars (str/int/float) to str before splitting.
|
||||
# YAML parses a bare numeric value such as
|
||||
# `free_response_channels: 1491973769726791812` as int, which was
|
||||
# previously falling through the isinstance(str) branch and silently
|
||||
# returning an empty set. str() here accepts whatever scalar the YAML
|
||||
# loader hands us without changing existing string/CSV semantics.
|
||||
s = str(raw).strip() if raw is not None else ""
|
||||
if s:
|
||||
return {part.strip() for part in s.split(",") if part.strip()}
|
||||
if isinstance(raw, str) and raw.strip():
|
||||
return {part.strip() for part in raw.split(",") if part.strip()}
|
||||
return set()
|
||||
|
||||
def _thread_parent_channel(self, channel: Any) -> Any:
|
||||
@@ -3404,7 +3030,6 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
view = ExecApprovalView(
|
||||
session_key=session_key,
|
||||
allowed_user_ids=self._allowed_user_ids,
|
||||
allowed_role_ids=self._allowed_role_ids,
|
||||
)
|
||||
|
||||
msg = await channel.send(embed=embed, view=view)
|
||||
@@ -3443,7 +3068,6 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
session_key=session_key,
|
||||
confirm_id=confirm_id,
|
||||
allowed_user_ids=self._allowed_user_ids,
|
||||
allowed_role_ids=self._allowed_role_ids,
|
||||
)
|
||||
|
||||
msg = await channel.send(embed=embed, view=view)
|
||||
@@ -3454,7 +3078,6 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
async def send_update_prompt(
|
||||
self, chat_id: str, prompt: str, default: str = "",
|
||||
session_key: str = "",
|
||||
metadata: Optional[Dict[str, Any]] = None,
|
||||
) -> SendResult:
|
||||
"""Send an interactive button-based update prompt (Yes / No).
|
||||
|
||||
@@ -3464,10 +3087,9 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
if not self._client or not DISCORD_AVAILABLE:
|
||||
return SendResult(success=False, error="Not connected")
|
||||
try:
|
||||
target_id = metadata.get("thread_id") if metadata and metadata.get("thread_id") else chat_id
|
||||
channel = self._client.get_channel(int(target_id))
|
||||
channel = self._client.get_channel(int(chat_id))
|
||||
if not channel:
|
||||
channel = await self._client.fetch_channel(int(target_id))
|
||||
channel = await self._client.fetch_channel(int(chat_id))
|
||||
|
||||
default_hint = f" (default: {default})" if default else ""
|
||||
embed = discord.Embed(
|
||||
@@ -3478,7 +3100,6 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
view = UpdatePromptView(
|
||||
session_key=session_key,
|
||||
allowed_user_ids=self._allowed_user_ids,
|
||||
allowed_role_ids=self._allowed_role_ids,
|
||||
)
|
||||
msg = await channel.send(embed=embed, view=view)
|
||||
return SendResult(success=True, message_id=str(msg.id))
|
||||
@@ -3536,7 +3157,6 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
session_key=session_key,
|
||||
on_model_selected=on_model_selected,
|
||||
allowed_user_ids=self._allowed_user_ids,
|
||||
allowed_role_ids=self._allowed_role_ids,
|
||||
)
|
||||
|
||||
msg = await channel.send(embed=embed, view=view)
|
||||
@@ -4092,72 +3712,6 @@ class DiscordAdapter(BasePlatformAdapter):
|
||||
# Discord UI Components (outside the adapter class)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def _component_check_auth(
|
||||
interaction,
|
||||
allowed_user_ids: Optional[set],
|
||||
allowed_role_ids: Optional[set],
|
||||
) -> bool:
|
||||
"""Shared user-or-role OR semantics for component view button clicks.
|
||||
|
||||
Mirrors ``DiscordAdapter._is_allowed_user`` / the slash and on_message
|
||||
gates so every Discord interaction surface honors the same trust
|
||||
boundary. Component views (ExecApprovalView, SlashConfirmView,
|
||||
UpdatePromptView, ModelPickerView) used to receive only
|
||||
``allowed_user_ids``: in role-only deployments
|
||||
(DISCORD_ALLOWED_ROLES set, DISCORD_ALLOWED_USERS empty) the user
|
||||
set was empty and the legacy "no allowlist = allow everyone" branch
|
||||
let any guild member click the buttons -- approving exec commands,
|
||||
cancelling slash confirmations, switching the model.
|
||||
|
||||
Behavior:
|
||||
|
||||
- both allowlists empty -> allow (preserves existing no-allowlist
|
||||
deployments, no regression)
|
||||
- user is in user allowlist -> allow
|
||||
- role allowlist set + user has a role in it -> allow
|
||||
- role allowlist set + interaction.user has no resolvable
|
||||
``roles`` attribute (e.g. DM context with a role policy active)
|
||||
-> reject (fail closed)
|
||||
- otherwise -> reject
|
||||
"""
|
||||
user_set = allowed_user_ids or set()
|
||||
role_set = allowed_role_ids or set()
|
||||
has_users = bool(user_set)
|
||||
has_roles = bool(role_set)
|
||||
if not has_users and not has_roles:
|
||||
return True
|
||||
|
||||
user = getattr(interaction, "user", None)
|
||||
if user is None:
|
||||
return False
|
||||
|
||||
if has_users:
|
||||
try:
|
||||
uid = str(user.id)
|
||||
except AttributeError:
|
||||
uid = ""
|
||||
if uid and uid in user_set:
|
||||
return True
|
||||
|
||||
if has_roles:
|
||||
roles_attr = getattr(user, "roles", None)
|
||||
if roles_attr is None:
|
||||
# Role policy is configured but the interaction doesn't
|
||||
# carry role data (DM-context Member, raw User payload).
|
||||
# Fail closed: a user without a resolvable role list cannot
|
||||
# satisfy a role allowlist.
|
||||
return False
|
||||
try:
|
||||
user_role_ids = {getattr(r, "id", None) for r in roles_attr}
|
||||
except TypeError:
|
||||
return False
|
||||
if user_role_ids & role_set:
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
|
||||
if DISCORD_AVAILABLE:
|
||||
|
||||
class ExecApprovalView(discord.ui.View):
|
||||
@@ -4170,23 +3724,17 @@ if DISCORD_AVAILABLE:
|
||||
Only users in the allowed list can click. Times out after 5 minutes.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
session_key: str,
|
||||
allowed_user_ids: set,
|
||||
allowed_role_ids: Optional[set] = None,
|
||||
):
|
||||
def __init__(self, session_key: str, allowed_user_ids: set):
|
||||
super().__init__(timeout=300) # 5-minute timeout
|
||||
self.session_key = session_key
|
||||
self.allowed_user_ids = allowed_user_ids
|
||||
self.allowed_role_ids = allowed_role_ids or set()
|
||||
self.resolved = False
|
||||
|
||||
def _check_auth(self, interaction: discord.Interaction) -> bool:
|
||||
"""Verify the user clicking is authorized."""
|
||||
return _component_check_auth(
|
||||
interaction, self.allowed_user_ids, self.allowed_role_ids,
|
||||
)
|
||||
if not self.allowed_user_ids:
|
||||
return True # No allowlist = anyone can approve
|
||||
return str(interaction.user.id) in self.allowed_user_ids
|
||||
|
||||
async def _resolve(
|
||||
self, interaction: discord.Interaction, choice: str,
|
||||
@@ -4278,24 +3826,17 @@ if DISCORD_AVAILABLE:
|
||||
5 minutes (matches the gateway primitive's timeout).
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
session_key: str,
|
||||
confirm_id: str,
|
||||
allowed_user_ids: set,
|
||||
allowed_role_ids: Optional[set] = None,
|
||||
):
|
||||
def __init__(self, session_key: str, confirm_id: str, allowed_user_ids: set):
|
||||
super().__init__(timeout=300)
|
||||
self.session_key = session_key
|
||||
self.confirm_id = confirm_id
|
||||
self.allowed_user_ids = allowed_user_ids
|
||||
self.allowed_role_ids = allowed_role_ids or set()
|
||||
self.resolved = False
|
||||
|
||||
def _check_auth(self, interaction: discord.Interaction) -> bool:
|
||||
return _component_check_auth(
|
||||
interaction, self.allowed_user_ids, self.allowed_role_ids,
|
||||
)
|
||||
if not self.allowed_user_ids:
|
||||
return True
|
||||
return str(interaction.user.id) in self.allowed_user_ids
|
||||
|
||||
async def _resolve(
|
||||
self, interaction: discord.Interaction, choice: str,
|
||||
@@ -4373,22 +3914,16 @@ if DISCORD_AVAILABLE:
|
||||
5-minute timeout on its side).
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
session_key: str,
|
||||
allowed_user_ids: set,
|
||||
allowed_role_ids: Optional[set] = None,
|
||||
):
|
||||
def __init__(self, session_key: str, allowed_user_ids: set):
|
||||
super().__init__(timeout=300)
|
||||
self.session_key = session_key
|
||||
self.allowed_user_ids = allowed_user_ids
|
||||
self.allowed_role_ids = allowed_role_ids or set()
|
||||
self.resolved = False
|
||||
|
||||
def _check_auth(self, interaction: discord.Interaction) -> bool:
|
||||
return _component_check_auth(
|
||||
interaction, self.allowed_user_ids, self.allowed_role_ids,
|
||||
)
|
||||
if not self.allowed_user_ids:
|
||||
return True
|
||||
return str(interaction.user.id) in self.allowed_user_ids
|
||||
|
||||
async def _respond(
|
||||
self, interaction: discord.Interaction, answer: str,
|
||||
@@ -4465,7 +4000,6 @@ if DISCORD_AVAILABLE:
|
||||
session_key: str,
|
||||
on_model_selected,
|
||||
allowed_user_ids: set,
|
||||
allowed_role_ids: Optional[set] = None,
|
||||
):
|
||||
super().__init__(timeout=120)
|
||||
self.providers = providers
|
||||
@@ -4474,16 +4008,15 @@ if DISCORD_AVAILABLE:
|
||||
self.session_key = session_key
|
||||
self.on_model_selected = on_model_selected
|
||||
self.allowed_user_ids = allowed_user_ids
|
||||
self.allowed_role_ids = allowed_role_ids or set()
|
||||
self.resolved = False
|
||||
self._selected_provider: str = ""
|
||||
|
||||
self._build_provider_select()
|
||||
|
||||
def _check_auth(self, interaction: discord.Interaction) -> bool:
|
||||
return _component_check_auth(
|
||||
interaction, self.allowed_user_ids, self.allowed_role_ids,
|
||||
)
|
||||
if not self.allowed_user_ids:
|
||||
return True
|
||||
return str(interaction.user.id) in self.allowed_user_ids
|
||||
|
||||
def _build_provider_select(self):
|
||||
"""Build the provider dropdown menu."""
|
||||
|
||||
+53
-214
@@ -64,7 +64,7 @@ from dataclasses import dataclass, field
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from types import SimpleNamespace
|
||||
from typing import Any, Dict, List, Literal, Optional, Sequence
|
||||
from typing import Any, Dict, List, Optional, Sequence
|
||||
from urllib.error import HTTPError, URLError
|
||||
from urllib.parse import urlencode
|
||||
from urllib.request import Request, urlopen
|
||||
@@ -141,7 +141,6 @@ from gateway.platforms.base import (
|
||||
)
|
||||
from gateway.status import acquire_scoped_lock, release_scoped_lock
|
||||
from hermes_constants import get_hermes_home
|
||||
from utils import atomic_json_write
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -388,8 +387,6 @@ class FeishuAdapterSettings:
|
||||
admins: frozenset[str] = frozenset()
|
||||
default_group_policy: str = ""
|
||||
group_rules: Dict[str, FeishuGroupRule] = field(default_factory=dict)
|
||||
allow_bots: str = "none" # "none" | "mentions" | "all"
|
||||
require_mention: bool = True
|
||||
|
||||
|
||||
@dataclass
|
||||
@@ -399,7 +396,6 @@ class FeishuGroupRule:
|
||||
policy: str # "open" | "allowlist" | "blacklist" | "admin_only" | "disabled"
|
||||
allowlist: set[str] = field(default_factory=set)
|
||||
blacklist: set[str] = field(default_factory=set)
|
||||
require_mention: Optional[bool] = None # None = inherit global
|
||||
|
||||
|
||||
@dataclass
|
||||
@@ -409,40 +405,6 @@ class FeishuBatchState:
|
||||
counts: Dict[str, int] = field(default_factory=dict)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Admission: policy types
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
RejectReason = Literal[
|
||||
"self_echo",
|
||||
"self_ids_unknown",
|
||||
"bots_disabled",
|
||||
"bot_not_mentioned",
|
||||
"group_policy_rejected",
|
||||
]
|
||||
|
||||
|
||||
def _is_bot_sender(sender: Any) -> bool:
|
||||
# receive_v1 docs say {user, bot}; accept "app" defensively.
|
||||
return getattr(sender, "sender_type", "") in ("bot", "app")
|
||||
|
||||
|
||||
def _sender_identity(sender: Any) -> frozenset:
|
||||
# Take any non-empty id variant — tenant sender_id_type decides which are populated.
|
||||
sid = getattr(sender, "sender_id", None)
|
||||
if sid is None:
|
||||
return frozenset()
|
||||
return frozenset(
|
||||
v for v in (
|
||||
getattr(sid, "open_id", None),
|
||||
getattr(sid, "user_id", None),
|
||||
getattr(sid, "union_id", None),
|
||||
)
|
||||
if v
|
||||
)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Markdown rendering helpers
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -1415,16 +1377,10 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
for chat_id, rule_cfg in raw_group_rules.items():
|
||||
if not isinstance(rule_cfg, dict):
|
||||
continue
|
||||
# Only override when the key is explicitly set — missing vs false
|
||||
# must not collapse.
|
||||
per_chat_require_mention: Optional[bool] = None
|
||||
if "require_mention" in rule_cfg:
|
||||
per_chat_require_mention = _to_boolean(rule_cfg.get("require_mention"))
|
||||
group_rules[str(chat_id)] = FeishuGroupRule(
|
||||
policy=str(rule_cfg.get("policy", "open")).strip().lower(),
|
||||
allowlist=set(str(u).strip() for u in rule_cfg.get("allowlist", []) if str(u).strip()),
|
||||
blacklist=set(str(u).strip() for u in rule_cfg.get("blacklist", []) if str(u).strip()),
|
||||
require_mention=per_chat_require_mention,
|
||||
)
|
||||
|
||||
# Bot-level admins
|
||||
@@ -1434,16 +1390,6 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
# Default group policy (for groups not in group_rules)
|
||||
default_group_policy = str(extra.get("default_group_policy", "")).strip().lower()
|
||||
|
||||
# Env-only so adapter and gateway auth bypass share one source; yaml
|
||||
# feishu.allow_bots is bridged to this env var at config load.
|
||||
allow_bots = os.getenv("FEISHU_ALLOW_BOTS", "none").strip().lower()
|
||||
if allow_bots not in ("none", "mentions", "all"):
|
||||
logger.warning(
|
||||
"[Feishu] Unknown allow_bots=%r, falling back to 'none'. Valid: none, mentions, all.",
|
||||
allow_bots,
|
||||
)
|
||||
allow_bots = "none"
|
||||
|
||||
return FeishuAdapterSettings(
|
||||
app_id=str(extra.get("app_id") or os.getenv("FEISHU_APP_ID", "")).strip(),
|
||||
app_secret=str(extra.get("app_secret") or os.getenv("FEISHU_APP_SECRET", "")).strip(),
|
||||
@@ -1500,10 +1446,6 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
admins=admins,
|
||||
default_group_policy=default_group_policy,
|
||||
group_rules=group_rules,
|
||||
allow_bots=allow_bots,
|
||||
require_mention=_to_boolean(
|
||||
extra.get("require_mention", os.getenv("FEISHU_REQUIRE_MENTION", "true"))
|
||||
),
|
||||
)
|
||||
|
||||
def _apply_settings(self, settings: FeishuAdapterSettings) -> None:
|
||||
@@ -1534,8 +1476,6 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
self._ws_reconnect_interval = settings.ws_reconnect_interval
|
||||
self._ws_ping_interval = settings.ws_ping_interval
|
||||
self._ws_ping_timeout = settings.ws_ping_timeout
|
||||
self._allow_bots = settings.allow_bots
|
||||
self._require_mention = settings.require_mention
|
||||
|
||||
def _build_event_handler(self) -> Any:
|
||||
if EventDispatcherHandler is None:
|
||||
@@ -2249,28 +2189,30 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
event = getattr(data, "event", None)
|
||||
message = getattr(event, "message", None)
|
||||
sender = getattr(event, "sender", None)
|
||||
if not message or not sender or not getattr(sender, "sender_id", None):
|
||||
logger.debug("[Feishu] Dropping malformed inbound event: missing message/sender")
|
||||
sender_id = getattr(sender, "sender_id", None)
|
||||
if not message or not sender_id:
|
||||
logger.debug("[Feishu] Dropping malformed inbound event: missing message or sender_id")
|
||||
return
|
||||
|
||||
message_id = getattr(message, "message_id", None)
|
||||
if not message_id or self._is_duplicate(message_id):
|
||||
logger.debug("[Feishu] Dropping duplicate/missing message_id: %s", message_id)
|
||||
return
|
||||
|
||||
reason = self._admit(sender, message)
|
||||
if reason is not None:
|
||||
logger.debug("[Feishu] dropping inbound event: %s", reason)
|
||||
if self._is_self_sent_bot_message(event):
|
||||
logger.debug("[Feishu] Dropping self-sent bot event: %s", message_id)
|
||||
return
|
||||
|
||||
chat_type = getattr(message, "chat_type", "p2p")
|
||||
chat_id = getattr(message, "chat_id", "") or ""
|
||||
if chat_type != "p2p" and not self._should_accept_group_message(message, sender_id, chat_id):
|
||||
logger.debug("[Feishu] Dropping group message that failed mention/policy gate: %s", message_id)
|
||||
return
|
||||
await self._process_inbound_message(
|
||||
data=data,
|
||||
message=message,
|
||||
sender_id=getattr(sender, "sender_id", None),
|
||||
sender_id=sender_id,
|
||||
chat_type=chat_type,
|
||||
message_id=message_id,
|
||||
is_bot=_is_bot_sender(sender),
|
||||
)
|
||||
|
||||
def _on_message_read_event(self, data: P2ImMessageMessageReadV1) -> None:
|
||||
@@ -2447,11 +2389,10 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
msg = items[0] if items else None
|
||||
if not msg:
|
||||
return
|
||||
# GET im/v1/messages returns sender.id=app_id for bot messages —
|
||||
# peer bots and us share sender_type="app" but differ on app_id.
|
||||
sender = getattr(msg, "sender", None)
|
||||
if str(getattr(sender, "id", "") or "") != self._app_id:
|
||||
return # only route reactions on this bot's own messages
|
||||
sender_type = str(getattr(sender, "sender_type", "") or "").lower()
|
||||
if sender_type != "app":
|
||||
return # only route reactions on our own bot messages
|
||||
chat_id = str(getattr(msg, "chat_id", "") or "")
|
||||
chat_type_raw = str(getattr(msg, "chat_type", "p2p") or "p2p")
|
||||
if not chat_id:
|
||||
@@ -2738,7 +2679,6 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
sender_id: Any,
|
||||
chat_type: str,
|
||||
message_id: str,
|
||||
is_bot: bool = False,
|
||||
) -> None:
|
||||
text, inbound_type, media_urls, media_types, mentions = await self._extract_message_content(message)
|
||||
|
||||
@@ -2764,27 +2704,19 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
)
|
||||
reply_to_text = await self._fetch_message_text(reply_to_message_id) if reply_to_message_id else None
|
||||
|
||||
sender_primary = (
|
||||
getattr(sender_id, "open_id", None)
|
||||
or getattr(sender_id, "user_id", None)
|
||||
or getattr(sender_id, "union_id", None)
|
||||
or "<unknown>"
|
||||
)
|
||||
logger.info(
|
||||
"[Feishu] Inbound %s message received: id=%s type=%s chat_id=%s sender=%s:%s text=%r media=%d",
|
||||
"[Feishu] Inbound %s message received: id=%s type=%s chat_id=%s text=%r media=%d",
|
||||
"dm" if chat_type == "p2p" else "group",
|
||||
message_id,
|
||||
inbound_type.value,
|
||||
getattr(message, "chat_id", "") or "",
|
||||
"bot" if is_bot else "user",
|
||||
sender_primary,
|
||||
text[:120],
|
||||
len(media_urls),
|
||||
)
|
||||
|
||||
chat_id = getattr(message, "chat_id", "") or ""
|
||||
chat_info = await self.get_chat_info(chat_id)
|
||||
sender_profile = await self._resolve_sender_profile(sender_id, is_bot=is_bot)
|
||||
sender_profile = await self._resolve_sender_profile(sender_id)
|
||||
source = self.build_source(
|
||||
chat_id=chat_id,
|
||||
chat_name=chat_info.get("name") or chat_id or "Feishu Chat",
|
||||
@@ -2793,7 +2725,6 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
user_name=sender_profile["user_name"],
|
||||
thread_id=getattr(message, "thread_id", None) or None,
|
||||
user_id_alt=sender_profile["user_id_alt"],
|
||||
is_bot=is_bot,
|
||||
)
|
||||
normalized = MessageEvent(
|
||||
text=text,
|
||||
@@ -2922,18 +2853,13 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
},
|
||||
)
|
||||
response.raise_for_status()
|
||||
# Snapshot Content-Type and body while the client context is
|
||||
# still active so pooled connections fully release on exit.
|
||||
# See #18451.
|
||||
content_type_hdr = str(response.headers.get("Content-Type", ""))
|
||||
body = response.content
|
||||
filename = self._derive_remote_filename(
|
||||
file_url,
|
||||
content_type=content_type_hdr,
|
||||
content_type=str(response.headers.get("Content-Type", "")),
|
||||
default_name=preferred_name,
|
||||
default_ext=default_ext,
|
||||
)
|
||||
cached_path = cache_document_from_bytes(body, filename)
|
||||
cached_path = cache_document_from_bytes(response.content, filename)
|
||||
return cached_path, filename
|
||||
|
||||
@staticmethod
|
||||
@@ -3521,12 +3447,7 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
return "dm"
|
||||
return "group"
|
||||
|
||||
async def _resolve_sender_profile(
|
||||
self,
|
||||
sender_id: Any,
|
||||
*,
|
||||
is_bot: bool = False,
|
||||
) -> Dict[str, Optional[str]]:
|
||||
async def _resolve_sender_profile(self, sender_id: Any) -> Dict[str, Optional[str]]:
|
||||
"""Map Feishu's three-tier user IDs onto Hermes' SessionSource fields.
|
||||
|
||||
Preference order for the primary ``user_id`` field:
|
||||
@@ -3543,11 +3464,7 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
union_id = getattr(sender_id, "union_id", None) or None
|
||||
# Prefer tenant-scoped user_id; fall back to app-scoped open_id.
|
||||
primary_id = user_id or open_id
|
||||
# bot/v3/bots/basic_batch only accepts open_id.
|
||||
name_lookup_id = open_id if is_bot else (primary_id or union_id)
|
||||
display_name = await self._resolve_sender_name_from_api(
|
||||
name_lookup_id, is_bot=is_bot,
|
||||
)
|
||||
display_name = await self._resolve_sender_name_from_api(primary_id or union_id)
|
||||
return {
|
||||
"user_id": primary_id,
|
||||
"user_name": display_name,
|
||||
@@ -3567,14 +3484,11 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
self._sender_name_cache.pop(sender_id, None)
|
||||
return None
|
||||
|
||||
async def _resolve_sender_name_from_api(
|
||||
self,
|
||||
sender_id: Optional[str],
|
||||
*,
|
||||
is_bot: bool = False,
|
||||
) -> Optional[str]:
|
||||
"""Bots divert to bot/basic_batch — contact API doesn't return bot names.
|
||||
Failures are silent so the pipeline never blocks on name resolution.
|
||||
async def _resolve_sender_name_from_api(self, sender_id: Optional[str]) -> Optional[str]:
|
||||
"""Fetch the sender's display name from the Feishu contact API with a 10-minute cache.
|
||||
|
||||
ID-type detection mirrors openclaw: ou_ → open_id, on_ → union_id, else user_id.
|
||||
Failures are silently suppressed; the message pipeline must not block on name resolution.
|
||||
"""
|
||||
if not sender_id or not self._client:
|
||||
return None
|
||||
@@ -3584,16 +3498,7 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
now = time.time()
|
||||
cached_name = self._get_cached_sender_name(trimmed)
|
||||
if cached_name is not None:
|
||||
return cached_name or None # "" cached means "known nameless"
|
||||
if is_bot:
|
||||
names = await self._fetch_bot_names([trimmed])
|
||||
if names is None:
|
||||
return None
|
||||
expire_at = now + _FEISHU_SENDER_NAME_TTL_SECONDS
|
||||
for oid, name in names.items():
|
||||
self._sender_name_cache[oid] = (name, expire_at)
|
||||
hit = self._sender_name_cache.get(trimmed)
|
||||
return (hit[0] or None) if hit else None
|
||||
return cached_name
|
||||
try:
|
||||
from lark_oapi.api.contact.v3 import GetUserRequest # lazy import
|
||||
if trimmed.startswith("ou_"):
|
||||
@@ -3622,35 +3527,6 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
logger.debug("[Feishu] Failed to resolve sender name for %s", sender_id, exc_info=True)
|
||||
return None
|
||||
|
||||
async def _fetch_bot_names(self, bot_ids: List[str]) -> Optional[Dict[str, str]]:
|
||||
if not self._client or not bot_ids:
|
||||
return None
|
||||
try:
|
||||
req = (
|
||||
BaseRequest.builder()
|
||||
.http_method(HttpMethod.GET)
|
||||
.uri("/open-apis/bot/v3/bots/basic_batch")
|
||||
.queries([("bot_ids", oid) for oid in bot_ids])
|
||||
.token_types({AccessTokenType.TENANT})
|
||||
.build()
|
||||
)
|
||||
resp = await asyncio.to_thread(self._client.request, req)
|
||||
content = getattr(getattr(resp, "raw", None), "content", None)
|
||||
if not content:
|
||||
return None
|
||||
payload = json.loads(content)
|
||||
if payload.get("code") != 0:
|
||||
return None
|
||||
bots = (payload.get("data") or {}).get("bots") or {}
|
||||
return {
|
||||
oid: str(info.get("name") or "").strip()
|
||||
for oid, info in bots.items()
|
||||
if oid
|
||||
}
|
||||
except Exception:
|
||||
logger.debug("[Feishu] Failed to fetch bot names for %s", bot_ids, exc_info=True)
|
||||
return None
|
||||
|
||||
async def _fetch_message_text(self, message_id: str) -> Optional[str]:
|
||||
if not self._client or not message_id:
|
||||
return None
|
||||
@@ -3714,60 +3590,10 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
logger.exception("[Feishu] Background inbound processing failed")
|
||||
|
||||
# =========================================================================
|
||||
# Inbound admission
|
||||
# Group policy and mention gating
|
||||
# =========================================================================
|
||||
|
||||
def _admit(self, sender: Any, message: Any) -> Optional[RejectReason]:
|
||||
sender_ids = _sender_identity(sender)
|
||||
self_ids = frozenset(v for v in (self._bot_open_id, self._bot_user_id) if v)
|
||||
is_bot = _is_bot_sender(sender)
|
||||
is_group = getattr(message, "chat_type", "p2p") != "p2p"
|
||||
chat_id = getattr(message, "chat_id", "") or ""
|
||||
require_mention = is_group and self._require_mention_for(chat_id)
|
||||
|
||||
# Defensive only — Feishu doesn't echo our outbound back as inbound,
|
||||
# and open_id is always populated on both sides.
|
||||
if self_ids and sender_ids & self_ids:
|
||||
return "self_echo"
|
||||
|
||||
if is_bot:
|
||||
mode = self._allow_bots
|
||||
if mode != "mentions" and mode != "all":
|
||||
return "bots_disabled"
|
||||
# Defensive: pre-hydration or malformed payloads.
|
||||
if not self_ids or not sender_ids:
|
||||
return "self_ids_unknown"
|
||||
# Step 4 covers mention enforcement for groups when require_mention
|
||||
# is on; check here only on paths step 4 won't reach.
|
||||
if mode == "mentions" and not require_mention and not self._mentions_self(message):
|
||||
return "bot_not_mentioned"
|
||||
|
||||
if not is_group:
|
||||
return None
|
||||
|
||||
if not self._allow_group_message(
|
||||
getattr(sender, "sender_id", None), chat_id, is_bot=is_bot,
|
||||
):
|
||||
return "group_policy_rejected"
|
||||
if require_mention and not self._mentions_self(message):
|
||||
return "group_policy_rejected"
|
||||
return None
|
||||
|
||||
def _require_mention_for(self, chat_id: str) -> bool:
|
||||
rule = self._group_rules.get(chat_id) if chat_id else None
|
||||
if rule and rule.require_mention is not None:
|
||||
return rule.require_mention
|
||||
return self._require_mention
|
||||
|
||||
# --- Group policy ---------------------------------------------------------
|
||||
|
||||
def _allow_group_message(
|
||||
self,
|
||||
sender_id: Any,
|
||||
chat_id: str = "",
|
||||
*,
|
||||
is_bot: bool = False,
|
||||
) -> bool:
|
||||
def _allow_group_message(self, sender_id: Any, chat_id: str = "") -> bool:
|
||||
"""Per-group policy gate for non-DM traffic."""
|
||||
sender_open_id = getattr(sender_id, "open_id", None)
|
||||
sender_user_id = getattr(sender_id, "user_id", None)
|
||||
@@ -3786,17 +3612,12 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
allowlist = self._allowed_group_users
|
||||
blacklist = set()
|
||||
|
||||
# Channel locks apply to everyone; allowlist/blacklist only gate humans
|
||||
# (bots were already cleared upstream by FEISHU_ALLOW_BOTS).
|
||||
if policy == "disabled":
|
||||
return False
|
||||
if policy == "open":
|
||||
return True
|
||||
if policy == "admin_only":
|
||||
return False
|
||||
if is_bot:
|
||||
return True
|
||||
|
||||
if policy == "allowlist":
|
||||
return bool(sender_ids and (sender_ids & allowlist))
|
||||
if policy == "blacklist":
|
||||
@@ -3804,16 +3625,17 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
|
||||
return bool(sender_ids and (sender_ids & self._allowed_group_users))
|
||||
|
||||
# --- Mention detection ----------------------------------------------------
|
||||
|
||||
def _mentions_self(self, message: Any) -> bool:
|
||||
# @_all is Feishu's @everyone placeholder.
|
||||
def _should_accept_group_message(self, message: Any, sender_id: Any, chat_id: str = "") -> bool:
|
||||
"""Require an explicit @mention before group messages enter the agent."""
|
||||
if not self._allow_group_message(sender_id, chat_id):
|
||||
return False
|
||||
# @_all is Feishu's @everyone placeholder — always route to the bot.
|
||||
raw_content = getattr(message, "content", "") or ""
|
||||
if "@_all" in raw_content:
|
||||
return True
|
||||
mentions = getattr(message, "mentions", None) or []
|
||||
if mentions and self._message_mentions_bot(mentions):
|
||||
return True
|
||||
if mentions:
|
||||
return self._message_mentions_bot(mentions)
|
||||
normalized = normalize_feishu_message(
|
||||
message_type=getattr(message, "message_type", "") or "",
|
||||
raw_content=raw_content,
|
||||
@@ -3822,6 +3644,23 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
)
|
||||
return self._post_mentions_bot(normalized.mentions)
|
||||
|
||||
def _is_self_sent_bot_message(self, event: Any) -> bool:
|
||||
"""Return True only for Feishu events emitted by this Hermes bot."""
|
||||
sender = getattr(event, "sender", None)
|
||||
sender_type = str(getattr(sender, "sender_type", "") or "").strip().lower()
|
||||
if sender_type not in {"bot", "app"}:
|
||||
return False
|
||||
|
||||
sender_id = getattr(sender, "sender_id", None)
|
||||
sender_open_id = str(getattr(sender_id, "open_id", "") or "").strip()
|
||||
sender_user_id = str(getattr(sender_id, "user_id", "") or "").strip()
|
||||
|
||||
if self._bot_open_id and sender_open_id == self._bot_open_id:
|
||||
return True
|
||||
if self._bot_user_id and sender_user_id == self._bot_user_id:
|
||||
return True
|
||||
return False
|
||||
|
||||
def _message_mentions_bot(self, mentions: List[Any]) -> bool:
|
||||
# IDs trump names: when both sides have open_id (or both user_id),
|
||||
# match requires equal IDs. Name fallback only when either side
|
||||
@@ -3965,7 +3804,7 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
recent = self._seen_message_order[-self._dedup_cache_size:]
|
||||
# Save as {msg_id: timestamp} so TTL filtering works across restarts.
|
||||
payload = {"message_ids": {k: self._seen_message_ids[k] for k in recent if k in self._seen_message_ids}}
|
||||
atomic_json_write(self._dedup_state_path, payload, indent=None)
|
||||
self._dedup_state_path.write_text(json.dumps(payload, ensure_ascii=False), encoding="utf-8")
|
||||
except OSError:
|
||||
logger.warning("[Feishu] Failed to persist dedup state to %s", self._dedup_state_path, exc_info=True)
|
||||
|
||||
|
||||
@@ -13,8 +13,6 @@ import time
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Dict
|
||||
|
||||
from utils import atomic_json_write
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from gateway.platforms.base import MessageEvent
|
||||
|
||||
@@ -239,11 +237,12 @@ class ThreadParticipationTracker:
|
||||
|
||||
def _save(self) -> None:
|
||||
path = self._state_path()
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
thread_list = list(self._threads)
|
||||
if len(thread_list) > self._max_tracked:
|
||||
thread_list = thread_list[-self._max_tracked:]
|
||||
self._threads = set(thread_list)
|
||||
atomic_json_write(path, thread_list, indent=None)
|
||||
path.write_text(json.dumps(thread_list), encoding="utf-8")
|
||||
|
||||
def mark(self, thread_id: str) -> None:
|
||||
"""Mark *thread_id* as participated and persist."""
|
||||
|
||||
@@ -139,7 +139,7 @@ class HomeAssistantAdapter(BasePlatformAdapter):
|
||||
|
||||
async def _ws_connect(self) -> bool:
|
||||
"""Establish WebSocket connection and authenticate."""
|
||||
ws_url = self._hass_url.replace("https://", "wss://").replace("http://", "ws://")
|
||||
ws_url = self._hass_url.replace("http://", "ws://").replace("https://", "wss://")
|
||||
ws_url = f"{ws_url}/api/websocket"
|
||||
|
||||
self._session = aiohttp.ClientSession(
|
||||
|
||||
@@ -243,14 +243,10 @@ class QQAdapter(BasePlatformAdapter):
|
||||
return False
|
||||
|
||||
try:
|
||||
# Tighter keepalive pool so idle CLOSE_WAIT sockets drain
|
||||
# faster behind proxies like Cloudflare Warp (#18451).
|
||||
from gateway.platforms._http_client_limits import platform_httpx_limits
|
||||
self._http_client = httpx.AsyncClient(
|
||||
timeout=30.0,
|
||||
follow_redirects=True,
|
||||
event_hooks={"response": [_ssrf_redirect_guard]},
|
||||
limits=platform_httpx_limits(),
|
||||
)
|
||||
|
||||
# 1. Get access token
|
||||
|
||||
@@ -192,15 +192,6 @@ class SignalAdapter(BasePlatformAdapter):
|
||||
group_allowed_str = os.getenv("SIGNAL_GROUP_ALLOWED_USERS", "")
|
||||
self.group_allow_from = set(_parse_comma_list(group_allowed_str))
|
||||
|
||||
# DM allowlist — mirrors SIGNAL_ALLOWED_USERS checked by run.py.
|
||||
# Stored here so the reaction hooks can skip unauthorized senders
|
||||
# (reactions fire before run.py's auth gate, so without this check
|
||||
# every inbound DM from any contact gets a 👀 reaction).
|
||||
# "*" means all users allowed (open mode); empty means no restriction
|
||||
# recorded at adapter level (run.py still enforces auth separately).
|
||||
dm_allowed_str = os.getenv("SIGNAL_ALLOWED_USERS", "*")
|
||||
self.dm_allow_from = set(_parse_comma_list(dm_allowed_str))
|
||||
|
||||
# HTTP client
|
||||
self.client: Optional[httpx.AsyncClient] = None
|
||||
|
||||
@@ -257,9 +248,7 @@ class SignalAdapter(BasePlatformAdapter):
|
||||
except Exception as e:
|
||||
logger.warning("Signal: Could not acquire phone lock (non-fatal): %s", e)
|
||||
|
||||
# Tighter keepalive so idle CLOSE_WAIT drains promptly (#18451).
|
||||
from gateway.platforms._http_client_limits import platform_httpx_limits
|
||||
self.client = httpx.AsyncClient(timeout=30.0, limits=platform_httpx_limits())
|
||||
self.client = httpx.AsyncClient(timeout=30.0)
|
||||
try:
|
||||
# Health check — verify signal-cli daemon is reachable
|
||||
try:
|
||||
@@ -545,18 +534,6 @@ class SignalAdapter(BasePlatformAdapter):
|
||||
except Exception:
|
||||
logger.exception("Signal: failed to fetch attachment %s", att_id)
|
||||
|
||||
# Skip envelopes with no meaningful content (no text, no attachments).
|
||||
# Catches profile key updates, empty messages, and other metadata-only
|
||||
# envelopes that still carry a dataMessage wrapper but have nothing
|
||||
# worth processing. See issue: signal-cli logs "Profile key update" +
|
||||
# Hermes receives msg='' triggering a full agent turn for nothing.
|
||||
if (not text or not text.strip()) and not media_urls:
|
||||
logger.debug(
|
||||
"Signal: skipping contentless envelope from %s (%d attachments)",
|
||||
redact_phone(sender), len(media_urls) if media_urls else 0,
|
||||
)
|
||||
return
|
||||
|
||||
# Build session source
|
||||
source = self.build_source(
|
||||
chat_id=chat_id,
|
||||
@@ -1439,28 +1416,8 @@ class SignalAdapter(BasePlatformAdapter):
|
||||
return None
|
||||
return (author, ts)
|
||||
|
||||
def _reactions_enabled(self, event: "MessageEvent" = None) -> bool:
|
||||
"""Check if message reactions are enabled for this event.
|
||||
|
||||
Two gates:
|
||||
1. SIGNAL_REACTIONS env var — set to false/0/no to disable globally.
|
||||
2. DM allowlist — if SIGNAL_ALLOWED_USERS is set, only react to
|
||||
messages from senders in that list. This prevents unauthorized
|
||||
contacts from seeing the 👀 reaction (which fires before run.py's
|
||||
auth gate and would otherwise reveal that a bot is listening).
|
||||
"""
|
||||
if os.getenv("SIGNAL_REACTIONS", "true").lower() in ("false", "0", "no"):
|
||||
return False
|
||||
if event is not None:
|
||||
sender = getattr(getattr(event, "source", None), "user_id", None)
|
||||
if sender and "*" not in self.dm_allow_from and sender not in self.dm_allow_from:
|
||||
return False
|
||||
return True
|
||||
|
||||
async def on_processing_start(self, event: MessageEvent) -> None:
|
||||
"""React with 👀 when processing begins."""
|
||||
if not self._reactions_enabled(event):
|
||||
return
|
||||
target = self._extract_reaction_target(event)
|
||||
if target:
|
||||
await self.send_reaction(event.source.chat_id, "👀", *target)
|
||||
@@ -1471,8 +1428,6 @@ class SignalAdapter(BasePlatformAdapter):
|
||||
On CANCELLED we leave the 👀 in place — no terminal outcome means
|
||||
the reaction should keep reflecting "in progress" (matches Telegram).
|
||||
"""
|
||||
if not self._reactions_enabled(event):
|
||||
return
|
||||
if outcome == ProcessingOutcome.CANCELLED:
|
||||
return
|
||||
target = self._extract_reaction_target(event)
|
||||
|
||||
+13
-236
@@ -9,7 +9,6 @@ Uses slack-bolt (Python) with Socket Mode for:
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import contextvars
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
@@ -22,7 +21,6 @@ try:
|
||||
from slack_bolt.async_app import AsyncApp
|
||||
from slack_bolt.adapter.socket_mode.async_handler import AsyncSocketModeHandler
|
||||
from slack_sdk.web.async_client import AsyncWebClient
|
||||
import aiohttp
|
||||
SLACK_AVAILABLE = True
|
||||
except ImportError:
|
||||
SLACK_AVAILABLE = False
|
||||
@@ -52,16 +50,6 @@ from gateway.platforms.base import (
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# ContextVar carrying the user_id of the slash-command invoker.
|
||||
# Set in _handle_slash_command, read in send() to match the correct
|
||||
# stashed response_url when multiple users issue commands on the same
|
||||
# channel concurrently. ContextVars propagate to child asyncio.Tasks
|
||||
# (Python 3.7+), so the value set in _handle_slash_command's task is
|
||||
# visible in _process_message_background's child task.
|
||||
_slash_user_id: contextvars.ContextVar[Optional[str]] = contextvars.ContextVar(
|
||||
"_slash_user_id", default=None,
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class _ThreadContextCache:
|
||||
@@ -322,11 +310,6 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
# Track active assistant thread status indicators so stop_typing can
|
||||
# clear them (chat_id → thread_ts).
|
||||
self._active_status_threads: Dict[str, str] = {}
|
||||
# Slash-command contexts: stash response_url + user_id so send()
|
||||
# can route the first reply ephemerally. Keyed by
|
||||
# (channel_id, user_id) to avoid cross-user collisions.
|
||||
# Each value: {"response_url": str, "ts": float}
|
||||
self._slash_command_contexts: Dict[Tuple[str, str], Dict[str, Any]] = {}
|
||||
|
||||
def _describe_slack_api_error(self, response: Any, *, file_obj: Optional[Dict[str, Any]] = None) -> Optional[str]:
|
||||
"""Convert Slack API auth/permission failures into actionable user-facing text."""
|
||||
@@ -385,103 +368,6 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
)
|
||||
return None
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Slash-command ephemeral helpers
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
_SLASH_CTX_TTL = 120.0 # seconds — response_url is valid for 30 min;
|
||||
# we use a much shorter TTL to avoid routing unrelated messages
|
||||
# as ephemeral if the command handler was slow or dropped.
|
||||
|
||||
def _pop_slash_context(
|
||||
self, chat_id: str,
|
||||
) -> Optional[Dict[str, Any]]:
|
||||
"""Return and remove the slash-command context for *chat_id*, if fresh.
|
||||
|
||||
Contexts older than ``_SLASH_CTX_TTL`` seconds are silently discarded.
|
||||
|
||||
Uses the ``_slash_user_id`` ContextVar (set in ``_handle_slash_command``)
|
||||
to match the exact ``(channel_id, user_id)`` key. This prevents a
|
||||
concurrent slash command from a different user on the same channel from
|
||||
stealing another user's ephemeral context. Falls back to a
|
||||
channel-only scan when the ContextVar is unset (e.g. send() called
|
||||
from a non-slash code path — should not match anything).
|
||||
"""
|
||||
now = time.monotonic()
|
||||
# Clean up stale entries on every lookup — dict is small.
|
||||
stale_keys = [
|
||||
k for k, v in self._slash_command_contexts.items()
|
||||
if now - v["ts"] > self._SLASH_CTX_TTL
|
||||
]
|
||||
for k in stale_keys:
|
||||
self._slash_command_contexts.pop(k, None)
|
||||
|
||||
# Precise match: (channel_id, user_id) from ContextVar.
|
||||
uid = _slash_user_id.get()
|
||||
if uid:
|
||||
return self._slash_command_contexts.pop((chat_id, uid), None)
|
||||
|
||||
# Fallback: channel-only scan (only reachable when ContextVar is
|
||||
# unset, i.e. send() called outside a slash-command async context).
|
||||
match_key = None
|
||||
for key in list(self._slash_command_contexts):
|
||||
if key[0] == chat_id:
|
||||
match_key = key
|
||||
break
|
||||
if match_key is None:
|
||||
return None
|
||||
return self._slash_command_contexts.pop(match_key)
|
||||
|
||||
async def _send_slash_ephemeral(
|
||||
self,
|
||||
ctx: Dict[str, Any],
|
||||
content: str,
|
||||
) -> "SendResult":
|
||||
"""Replace the initial ephemeral ack via ``response_url``.
|
||||
|
||||
Slack's ``response_url`` accepts a POST with ``replace_original``
|
||||
for up to 30 minutes after the slash command was invoked. This
|
||||
lets us swap the "Running /cmd…" placeholder with the real reply,
|
||||
and the message stays ephemeral ("Only visible to you").
|
||||
|
||||
Falls back to a simple ``True`` SendResult if the POST fails —
|
||||
the user already saw the initial ack, so a delivery failure here
|
||||
is non-critical.
|
||||
"""
|
||||
formatted = self.format_message(content)
|
||||
# Slack's response_url has the same ~40k char limit as chat_postMessage.
|
||||
# Truncate to MAX_MESSAGE_LENGTH and use only the first chunk — the
|
||||
# response_url replaces a single ephemeral ack, so multi-chunk isn't
|
||||
# possible. Long responses are rare for command replies.
|
||||
chunks = self.truncate_message(formatted, self.MAX_MESSAGE_LENGTH)
|
||||
text = chunks[0] if chunks else formatted
|
||||
payload = {
|
||||
"response_type": "ephemeral",
|
||||
"replace_original": True,
|
||||
"text": text,
|
||||
}
|
||||
try:
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.post(
|
||||
ctx["response_url"],
|
||||
json=payload,
|
||||
timeout=aiohttp.ClientTimeout(total=10),
|
||||
) as resp:
|
||||
if resp.status == 200:
|
||||
return SendResult(success=True, message_id=None)
|
||||
body = await resp.text()
|
||||
logger.warning(
|
||||
"[Slack] response_url POST returned %s: %s",
|
||||
resp.status,
|
||||
body[:200],
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
"[Slack] response_url POST failed: %s", e,
|
||||
)
|
||||
# Non-fatal — the user saw the initial ack already.
|
||||
return SendResult(success=True, message_id=None)
|
||||
|
||||
async def connect(self) -> bool:
|
||||
"""Connect to Slack via Socket Mode."""
|
||||
if not SLACK_AVAILABLE:
|
||||
@@ -528,21 +414,6 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
return False
|
||||
lock_acquired = True
|
||||
|
||||
# Close any previous handler before creating a new one so that
|
||||
# calling connect() a second time (e.g. during a gateway restart or
|
||||
# in-process reconnect attempt) does not leave a zombie Socket Mode
|
||||
# connection alive. Both the old and new connections would otherwise
|
||||
# receive every Slack event and dispatch it twice, producing double
|
||||
# responses — the same bug that affected DiscordAdapter (#18187).
|
||||
if self._handler is not None:
|
||||
try:
|
||||
await self._handler.close_async()
|
||||
except Exception:
|
||||
logger.debug("[%s] Failed to close previous Slack handler", self.name)
|
||||
finally:
|
||||
self._handler = None
|
||||
self._app = None
|
||||
|
||||
# First token is the primary — used for AsyncApp / Socket Mode
|
||||
primary_token = bot_tokens[0]
|
||||
self._app = AsyncApp(token=primary_token)
|
||||
@@ -575,16 +446,12 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
async def handle_message_event(event, say):
|
||||
await self._handle_slack_message(event)
|
||||
|
||||
# Handle app_mention explicitly. In some Slack app configurations,
|
||||
# channel mentions arrive only as app_mention events rather than the
|
||||
# generic message event. Forward them into the normal message
|
||||
# pipeline so @mentions reliably produce replies.
|
||||
# NOTE: when Slack fires BOTH message and app_mention for the same
|
||||
# @mention, they share the same event ts — the dedup in
|
||||
# _handle_slack_message (MessageDeduplicator) suppresses the second.
|
||||
# Acknowledge app_mention events to prevent Bolt 404 errors.
|
||||
# The "message" handler above already processes @mentions in
|
||||
# channels, so this is intentionally a no-op to avoid duplicates.
|
||||
@self._app.event("app_mention")
|
||||
async def handle_app_mention(event, say):
|
||||
await self._handle_slack_message(event)
|
||||
pass
|
||||
|
||||
# File lifecycle events can arrive around snippet uploads even when
|
||||
# the actual user message is what we care about. Ack them so Slack
|
||||
@@ -635,11 +502,7 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
|
||||
@self._app.command(_slash_pattern)
|
||||
async def handle_hermes_command(ack, command):
|
||||
slash = (command.get("command") or "").lstrip("/")
|
||||
await ack(
|
||||
response_type="ephemeral",
|
||||
text=f"Running `/{slash}`…",
|
||||
)
|
||||
await ack()
|
||||
await self._handle_slash_command(command)
|
||||
|
||||
# Register Block Kit action handlers for approval buttons
|
||||
@@ -711,17 +574,6 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
return SendResult(success=False, error="Not connected")
|
||||
|
||||
try:
|
||||
# Check for a pending slash-command context. When the user ran a
|
||||
# native slash command (e.g. /q, /stop, /model), the initial ack
|
||||
# already showed an ephemeral "Running /cmd…" message. If we have
|
||||
# a stashed response_url for this channel, replace that ack with
|
||||
# the actual command reply ephemerally instead of posting publicly.
|
||||
slash_ctx = self._pop_slash_context(chat_id)
|
||||
if slash_ctx:
|
||||
return await self._send_slash_ephemeral(
|
||||
slash_ctx, content,
|
||||
)
|
||||
|
||||
# Convert standard markdown → Slack mrkdwn
|
||||
formatted = self.format_message(content)
|
||||
|
||||
@@ -749,10 +601,6 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
|
||||
last_result = await self._get_client(chat_id).chat_postMessage(**kwargs)
|
||||
|
||||
# Clear Slack Assistant status as soon as the final message is posted.
|
||||
if thread_ts:
|
||||
await self.stop_typing(chat_id)
|
||||
|
||||
# Track the sent message ts so we can auto-respond to thread
|
||||
# replies without requiring @mention.
|
||||
sent_ts = last_result.get("ts") if last_result else None
|
||||
@@ -776,42 +624,6 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
logger.error("[Slack] Send error: %s", e, exc_info=True)
|
||||
return SendResult(success=False, error=str(e))
|
||||
|
||||
async def send_private_notice(
|
||||
self,
|
||||
chat_id: str,
|
||||
user_id: str,
|
||||
content: str,
|
||||
reply_to: Optional[str] = None,
|
||||
metadata: Optional[Dict[str, Any]] = None,
|
||||
) -> SendResult:
|
||||
"""Send a Slack ephemeral message visible only to one user."""
|
||||
if not self._app:
|
||||
return SendResult(success=False, error="Not connected")
|
||||
if not chat_id or not user_id:
|
||||
return SendResult(success=False, error="chat_id and user_id are required")
|
||||
|
||||
try:
|
||||
formatted = self.format_message(content)
|
||||
thread_ts = self._resolve_thread_ts(reply_to, metadata)
|
||||
kwargs = {
|
||||
"channel": chat_id,
|
||||
"user": user_id,
|
||||
"text": formatted,
|
||||
"mrkdwn": True,
|
||||
}
|
||||
if thread_ts:
|
||||
kwargs["thread_ts"] = thread_ts
|
||||
|
||||
result = await self._get_client(chat_id).chat_postEphemeral(**kwargs)
|
||||
return SendResult(
|
||||
success=True,
|
||||
message_id=result.get("message_ts") or result.get("ts"),
|
||||
raw_response=result,
|
||||
)
|
||||
except Exception as e: # pragma: no cover - defensive logging
|
||||
logger.error("[Slack] Ephemeral send error: %s", e, exc_info=True)
|
||||
return SendResult(success=False, error=str(e))
|
||||
|
||||
async def edit_message(
|
||||
self,
|
||||
chat_id: str,
|
||||
@@ -830,8 +642,6 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
ts=message_id,
|
||||
text=formatted,
|
||||
)
|
||||
if finalize:
|
||||
await self.stop_typing(chat_id)
|
||||
return SendResult(success=True, message_id=message_id)
|
||||
except Exception as e: # pragma: no cover - defensive logging
|
||||
logger.error(
|
||||
@@ -872,7 +682,7 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
# in an assistant-enabled context. Falls back to reactions.
|
||||
logger.debug("[Slack] assistant.threads.setStatus failed: %s", e)
|
||||
|
||||
async def stop_typing(self, chat_id: str, metadata=None) -> None:
|
||||
async def stop_typing(self, chat_id: str) -> None:
|
||||
"""Clear the assistant thread status indicator."""
|
||||
if not self._app:
|
||||
return
|
||||
@@ -1159,7 +969,7 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
return _ph(f'<{url}|{label}>')
|
||||
|
||||
text = re.sub(
|
||||
r'(?<!!)\[([^\]]+)\]\(([^()]*(?:\([^()]*\)[^()]*)*)\)',
|
||||
r'\[([^\]]+)\]\(([^()]*(?:\([^()]*\)[^()]*)*)\)',
|
||||
_convert_markdown_link,
|
||||
text,
|
||||
)
|
||||
@@ -1206,11 +1016,9 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
)
|
||||
|
||||
# 10) Convert italic: _text_ stays as _text_ (already Slack italic)
|
||||
# Single *text* → _text_ (Slack italic), but only when the
|
||||
# emphasized text touches non-whitespace on both sides so literal
|
||||
# delimiters like "a * b * c" are preserved.
|
||||
# Single *text* → _text_ (Slack italic)
|
||||
text = re.sub(
|
||||
r'(?<!\*)\*(\S(?:[^*\n]*?\S)?)\*(?!\*)',
|
||||
r'(?<!\*)\*([^*\n]+)\*(?!\*)',
|
||||
lambda m: _ph(f'_{m.group(1)}_'),
|
||||
text,
|
||||
)
|
||||
@@ -2716,14 +2524,9 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
# gateway command dispatcher by prepending the slash.
|
||||
text = f"/{slash_name} {text}".strip()
|
||||
|
||||
# Slack slash commands can originate from DMs or shared channels.
|
||||
# Preserve DM semantics only for DM channel IDs; shared channels must
|
||||
# keep group semantics so different users do not collide into one
|
||||
# session key.
|
||||
is_dm = str(channel_id).startswith("D")
|
||||
source = self.build_source(
|
||||
chat_id=channel_id,
|
||||
chat_type="dm" if is_dm else "group",
|
||||
chat_type="dm", # Slash commands are always in DM-like context
|
||||
user_id=user_id,
|
||||
)
|
||||
|
||||
@@ -2734,26 +2537,7 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
raw_message=command,
|
||||
)
|
||||
|
||||
# Stash the Slack response_url so the first reply for this
|
||||
# channel+user can be routed ephemerally (replaces the initial
|
||||
# "Running /cmd…" ack shown by handle_hermes_command).
|
||||
# Only stash for COMMAND events (text starts with "/") — free-form
|
||||
# questions via "/hermes <question>" must produce public replies so
|
||||
# the whole channel can see the agent's answer.
|
||||
response_url = command.get("response_url", "")
|
||||
if response_url and user_id and channel_id and text.startswith("/"):
|
||||
self._slash_command_contexts[(channel_id, user_id)] = {
|
||||
"response_url": response_url,
|
||||
"ts": time.monotonic(),
|
||||
}
|
||||
|
||||
# Set the ContextVar so send() can match the correct stashed
|
||||
# response_url even when multiple users slash concurrently.
|
||||
_slash_user_id_token = _slash_user_id.set(user_id or None)
|
||||
try:
|
||||
await self.handle_message(event)
|
||||
finally:
|
||||
_slash_user_id.reset(_slash_user_id_token)
|
||||
await self.handle_message(event)
|
||||
|
||||
def _has_active_session_for_thread(
|
||||
self,
|
||||
@@ -2914,13 +2698,6 @@ class SlackAdapter(BasePlatformAdapter):
|
||||
raw = os.getenv("SLACK_FREE_RESPONSE_CHANNELS", "")
|
||||
if isinstance(raw, list):
|
||||
return {str(part).strip() for part in raw if str(part).strip()}
|
||||
# Coerce non-list scalars (str/int/float) to str before splitting.
|
||||
# A bare numeric YAML value (`free_response_channels: 1234567890`) is
|
||||
# loaded as int and was previously falling through the isinstance(str)
|
||||
# branch to return an empty set. str() here accepts whatever scalar
|
||||
# the YAML loader hands us without changing existing string/CSV
|
||||
# semantics.
|
||||
s = str(raw).strip() if raw is not None else ""
|
||||
if s:
|
||||
return {part.strip() for part in s.split(",") if part.strip()}
|
||||
if isinstance(raw, str) and raw.strip():
|
||||
return {part.strip() for part in raw.split(",") if part.strip()}
|
||||
return set()
|
||||
|
||||
@@ -290,53 +290,14 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
# and any other slash-confirm prompts; see GatewayRunner._request_slash_confirm).
|
||||
self._slash_confirm_state: Dict[str, str] = {}
|
||||
|
||||
def _is_callback_user_authorized(
|
||||
self,
|
||||
user_id: str,
|
||||
*,
|
||||
chat_id: Optional[str] = None,
|
||||
chat_type: Optional[str] = None,
|
||||
thread_id: Optional[str] = None,
|
||||
user_name: Optional[str] = None,
|
||||
) -> bool:
|
||||
@staticmethod
|
||||
def _is_callback_user_authorized(user_id: str) -> bool:
|
||||
"""Return whether a Telegram inline-button caller may perform gated actions."""
|
||||
normalized_user_id = str(user_id or "").strip()
|
||||
if not normalized_user_id:
|
||||
return False
|
||||
|
||||
runner = getattr(getattr(self, "_message_handler", None), "__self__", None)
|
||||
auth_fn = getattr(runner, "_is_user_authorized", None)
|
||||
if callable(auth_fn):
|
||||
try:
|
||||
from gateway.session import SessionSource
|
||||
|
||||
normalized_chat_type = str(chat_type or "dm").strip().lower() or "dm"
|
||||
if normalized_chat_type == "private":
|
||||
normalized_chat_type = "dm"
|
||||
elif normalized_chat_type == "supergroup":
|
||||
normalized_chat_type = "forum" if thread_id is not None else "group"
|
||||
|
||||
source = SessionSource(
|
||||
platform=Platform.TELEGRAM,
|
||||
chat_id=str(chat_id or normalized_user_id),
|
||||
chat_type=normalized_chat_type,
|
||||
user_id=normalized_user_id,
|
||||
user_name=str(user_name).strip() if user_name else None,
|
||||
thread_id=str(thread_id) if thread_id is not None else None,
|
||||
)
|
||||
return bool(auth_fn(source))
|
||||
except Exception:
|
||||
logger.debug(
|
||||
"[Telegram] Falling back to env-only callback auth for user %s",
|
||||
normalized_user_id,
|
||||
exc_info=True,
|
||||
)
|
||||
|
||||
allowed_csv = os.getenv("TELEGRAM_ALLOWED_USERS", "").strip()
|
||||
if not allowed_csv:
|
||||
return True
|
||||
allowed_ids = {uid.strip() for uid in allowed_csv.split(",") if uid.strip()}
|
||||
return "*" in allowed_ids or normalized_user_id in allowed_ids
|
||||
return "*" in allowed_ids or user_id in allowed_ids
|
||||
|
||||
@classmethod
|
||||
def _metadata_thread_id(cls, metadata: Optional[Dict[str, Any]]) -> Optional[str]:
|
||||
@@ -512,17 +473,6 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
self.name, attempt,
|
||||
)
|
||||
self._polling_network_error_count = 0
|
||||
# start_polling() returning is necessary but not sufficient:
|
||||
# PTB's Updater can be left in a state where `running` is True
|
||||
# but the underlying long-poll task is wedged on a stale httpx
|
||||
# connection and never makes progress. No error_callback fires
|
||||
# in that state, so the reconnect ladder won't advance on its
|
||||
# own. Schedule a deferred probe to detect the wedge and
|
||||
# re-enter the ladder if needed.
|
||||
if not self.has_fatal_error:
|
||||
probe = asyncio.ensure_future(self._verify_polling_after_reconnect())
|
||||
self._background_tasks.add(probe)
|
||||
probe.add_done_callback(self._background_tasks.discard)
|
||||
except Exception as retry_err:
|
||||
logger.warning("[%s] Telegram polling reconnect failed: %s", self.name, retry_err)
|
||||
# start_polling failed — polling is dead and no further error
|
||||
@@ -534,50 +484,6 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
self._background_tasks.add(task)
|
||||
task.add_done_callback(self._background_tasks.discard)
|
||||
|
||||
async def _verify_polling_after_reconnect(self) -> None:
|
||||
"""Heartbeat probe scheduled after a successful reconnect.
|
||||
|
||||
PTB's Updater can survive a botched stop()+start_polling() cycle
|
||||
with `running=True` but a wedged consumer task. No error callback
|
||||
fires, so the reconnect ladder doesn't advance on its own. This
|
||||
probe detects the wedge by:
|
||||
|
||||
1. Sleeping HEARTBEAT_PROBE_DELAY so a healthy long-poll has time
|
||||
to complete at least one cycle.
|
||||
2. Verifying `Updater.running` is still True.
|
||||
3. Probing the bot endpoint with a tight asyncio timeout. A
|
||||
wedged httpx pool fails this probe; a healthy one returns
|
||||
well under the timeout.
|
||||
|
||||
On any failure, re-enter the reconnect ladder so the existing
|
||||
MAX_NETWORK_RETRIES path can ultimately escalate to fatal-error.
|
||||
"""
|
||||
HEARTBEAT_PROBE_DELAY = 60
|
||||
PROBE_TIMEOUT = 10
|
||||
|
||||
await asyncio.sleep(HEARTBEAT_PROBE_DELAY)
|
||||
|
||||
if self.has_fatal_error:
|
||||
return
|
||||
if not (self._app and self._app.updater and self._app.updater.running):
|
||||
logger.warning(
|
||||
"[%s] Updater not running %ds after reconnect — treating as wedged",
|
||||
self.name, HEARTBEAT_PROBE_DELAY,
|
||||
)
|
||||
await self._handle_polling_network_error(
|
||||
RuntimeError("Updater not running after reconnect heartbeat")
|
||||
)
|
||||
return
|
||||
|
||||
try:
|
||||
await asyncio.wait_for(self._app.bot.get_me(), PROBE_TIMEOUT)
|
||||
except Exception as probe_err:
|
||||
logger.warning(
|
||||
"[%s] Polling heartbeat probe failed %ds after reconnect: %s",
|
||||
self.name, HEARTBEAT_PROBE_DELAY, probe_err,
|
||||
)
|
||||
await self._handle_polling_network_error(probe_err)
|
||||
|
||||
async def _handle_polling_conflict(self, error: Exception) -> None:
|
||||
if self.has_fatal_error and self.fatal_error_code == "telegram_polling_conflict":
|
||||
return
|
||||
@@ -816,20 +722,6 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
# Persist thread_id to config so we don't recreate on next restart
|
||||
self._persist_dm_topic_thread_id(int(chat_id), topic_name, thread_id)
|
||||
|
||||
# Send a seed message so the topic is visible in Telegram's client.
|
||||
# Empty topics are hidden by the client UI until they contain a message.
|
||||
try:
|
||||
await self._bot.send_message(
|
||||
chat_id=int(chat_id),
|
||||
message_thread_id=thread_id,
|
||||
text=f"\U0001f4cc {topic_name}",
|
||||
)
|
||||
except Exception as seed_err:
|
||||
logger.debug(
|
||||
"[%s] Could not send seed message to topic '%s': %s",
|
||||
self.name, topic_name, seed_err,
|
||||
)
|
||||
|
||||
async def connect(self) -> bool:
|
||||
"""Connect to Telegram via polling or webhook.
|
||||
|
||||
@@ -1429,7 +1321,6 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
async def send_update_prompt(
|
||||
self, chat_id: str, prompt: str, default: str = "",
|
||||
session_key: str = "",
|
||||
metadata: Optional[Dict[str, Any]] = None,
|
||||
) -> SendResult:
|
||||
"""Send an inline-keyboard update prompt (Yes / No buttons).
|
||||
|
||||
@@ -1447,14 +1338,11 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
InlineKeyboardButton("✗ No", callback_data="update_prompt:n"),
|
||||
]
|
||||
])
|
||||
thread_id = self._metadata_thread_id(metadata)
|
||||
message_thread_id = self._message_thread_id_for_send(thread_id)
|
||||
msg = await self._bot.send_message(
|
||||
chat_id=int(chat_id),
|
||||
text=text,
|
||||
parse_mode=ParseMode.MARKDOWN,
|
||||
reply_markup=keyboard,
|
||||
message_thread_id=message_thread_id,
|
||||
**self._link_preview_kwargs(),
|
||||
)
|
||||
return SendResult(success=True, message_id=str(msg.message_id))
|
||||
@@ -1872,12 +1760,6 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
if not query or not query.data:
|
||||
return
|
||||
data = query.data
|
||||
query_message = getattr(query, "message", None)
|
||||
query_chat_id = getattr(query_message, "chat_id", None)
|
||||
query_chat = getattr(query_message, "chat", None)
|
||||
query_chat_type = getattr(query_chat, "type", None)
|
||||
query_thread_id = getattr(query_message, "message_thread_id", None)
|
||||
query_user_name = getattr(query.from_user, "first_name", None)
|
||||
|
||||
# --- Model picker callbacks ---
|
||||
if data.startswith(("mp:", "mm:", "mb", "mx", "mg:")):
|
||||
@@ -1899,13 +1781,7 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
|
||||
# Only authorized users may click approval buttons.
|
||||
caller_id = str(getattr(query.from_user, "id", ""))
|
||||
if not self._is_callback_user_authorized(
|
||||
caller_id,
|
||||
chat_id=query_chat_id,
|
||||
chat_type=str(query_chat_type) if query_chat_type is not None else None,
|
||||
thread_id=str(query_thread_id) if query_thread_id is not None else None,
|
||||
user_name=query_user_name,
|
||||
):
|
||||
if not self._is_callback_user_authorized(caller_id):
|
||||
await query.answer(text="⛔ You are not authorized to approve commands.")
|
||||
return
|
||||
|
||||
@@ -1955,14 +1831,8 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
choice = parts[1] # once, always, cancel
|
||||
confirm_id = parts[2]
|
||||
|
||||
caller_id = str(getattr(query.from_user, "id", ""))
|
||||
if not self._is_callback_user_authorized(
|
||||
caller_id,
|
||||
chat_id=query_chat_id,
|
||||
chat_type=str(query_chat_type) if query_chat_type is not None else None,
|
||||
thread_id=str(query_thread_id) if query_thread_id is not None else None,
|
||||
user_name=query_user_name,
|
||||
):
|
||||
caller_id = str(getattr(query.from_user, "id", ""))
|
||||
if not self._is_callback_user_authorized(caller_id):
|
||||
await query.answer(text="⛔ You are not authorized to answer this prompt.")
|
||||
return
|
||||
|
||||
@@ -2021,13 +1891,7 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
return
|
||||
answer = data.split(":", 1)[1] # "y" or "n"
|
||||
caller_id = str(getattr(query.from_user, "id", ""))
|
||||
if not self._is_callback_user_authorized(
|
||||
caller_id,
|
||||
chat_id=query_chat_id,
|
||||
chat_type=str(query_chat_type) if query_chat_type is not None else None,
|
||||
thread_id=str(query_thread_id) if query_thread_id is not None else None,
|
||||
user_name=query_user_name,
|
||||
):
|
||||
if not self._is_callback_user_authorized(caller_id):
|
||||
await query.answer(text="⛔ You are not authorized to answer update prompts.")
|
||||
return
|
||||
await query.answer(text=f"Sent '{answer}' to the update process.")
|
||||
|
||||
@@ -206,11 +206,7 @@ class WeComAdapter(BasePlatformAdapter):
|
||||
return False
|
||||
|
||||
try:
|
||||
# Tighter keepalive so idle CLOSE_WAIT drains promptly (#18451).
|
||||
from gateway.platforms._http_client_limits import platform_httpx_limits
|
||||
self._http_client = httpx.AsyncClient(
|
||||
timeout=30.0, follow_redirects=True, limits=platform_httpx_limits(),
|
||||
)
|
||||
self._http_client = httpx.AsyncClient(timeout=30.0, follow_redirects=True)
|
||||
await self._open_connection()
|
||||
self._mark_connected()
|
||||
self._listen_task = asyncio.create_task(self._listen_loop())
|
||||
|
||||
@@ -119,9 +119,7 @@ class WecomCallbackAdapter(BasePlatformAdapter):
|
||||
pass
|
||||
|
||||
try:
|
||||
# Tighter keepalive so idle CLOSE_WAIT drains promptly (#18451).
|
||||
from gateway.platforms._http_client_limits import platform_httpx_limits
|
||||
self._http_client = httpx.AsyncClient(timeout=20.0, limits=platform_httpx_limits())
|
||||
self._http_client = httpx.AsyncClient(timeout=20.0)
|
||||
self._app = web.Application()
|
||||
self._app.router.add_get("/health", self._handle_health)
|
||||
self._app.router.add_get(self._path, self._handle_verify)
|
||||
|
||||
@@ -2030,9 +2030,7 @@ async def send_weixin_direct(
|
||||
|
||||
live_adapter = _LIVE_ADAPTERS.get(resolved_token)
|
||||
send_session = getattr(live_adapter, '_send_session', None)
|
||||
if (live_adapter is not None and send_session is not None
|
||||
and not send_session.closed
|
||||
and send_session._loop is asyncio.get_running_loop()):
|
||||
if live_adapter is not None and send_session is not None and not send_session.closed:
|
||||
last_result: Optional[SendResult] = None
|
||||
cleaned = live_adapter.format_message(message)
|
||||
if cleaned:
|
||||
|
||||
@@ -185,13 +185,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
|
||||
self._bridge_log: Optional[Path] = None
|
||||
self._poll_task: Optional[asyncio.Task] = None
|
||||
self._http_session: Optional["aiohttp.ClientSession"] = None
|
||||
# Set to True by disconnect() before we SIGTERM our child bridge so
|
||||
# _check_managed_bridge_exit() can distinguish an intentional
|
||||
# shutdown-time exit (returncode -15 / -2 / 0) from a real crash.
|
||||
# Without this, every graceful gateway shutdown/restart would log
|
||||
# "Fatal whatsapp adapter error" plus dispatch a fatal-error
|
||||
# notification before the normal "✓ whatsapp disconnected" fires.
|
||||
self._shutting_down: bool = False
|
||||
|
||||
def _whatsapp_require_mention(self) -> bool:
|
||||
configured = self.config.extra.get("require_mention")
|
||||
@@ -562,21 +555,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
|
||||
if returncode is None:
|
||||
return None
|
||||
|
||||
# Planned shutdown: disconnect() sets _shutting_down before it sends
|
||||
# SIGTERM to the bridge, so a returncode of -15 (SIGTERM), -2 (SIGINT),
|
||||
# or 0 (clean exit) at that point is expected, not a crash. Treat it
|
||||
# as informational and skip the fatal-error path.
|
||||
# getattr-with-default keeps tests that construct the adapter via
|
||||
# ``WhatsAppAdapter.__new__`` (bypassing __init__) working without
|
||||
# every _make_adapter() helper having to seed the attribute.
|
||||
if getattr(self, "_shutting_down", False) and returncode in (0, -2, -15):
|
||||
logger.info(
|
||||
"[%s] Bridge exited during shutdown (code %d).",
|
||||
self.name,
|
||||
returncode,
|
||||
)
|
||||
return None
|
||||
|
||||
message = f"WhatsApp bridge process exited unexpectedly (code {returncode})."
|
||||
if not self.has_fatal_error:
|
||||
logger.error("[%s] %s", self.name, message)
|
||||
@@ -587,10 +565,6 @@ class WhatsAppAdapter(BasePlatformAdapter):
|
||||
|
||||
async def disconnect(self) -> None:
|
||||
"""Stop the WhatsApp bridge and clean up any orphaned processes."""
|
||||
# Flip the shutdown flag BEFORE signalling the child so the exit-check
|
||||
# path (which runs from other tasks like send() and the poll loop)
|
||||
# doesn't race us and report the intentional termination as fatal.
|
||||
self._shutting_down = True
|
||||
if self._bridge_process:
|
||||
try:
|
||||
try:
|
||||
@@ -902,15 +876,11 @@ class WhatsAppAdapter(BasePlatformAdapter):
|
||||
try:
|
||||
import aiohttp
|
||||
|
||||
# Must wrap in `async with` — a bare `await session.post(...)`
|
||||
# leaves the response object alive until GC, holding its TCP
|
||||
# socket in CLOSE_WAIT. See #18451.
|
||||
async with self._http_session.post(
|
||||
await self._http_session.post(
|
||||
f"http://127.0.0.1:{self._bridge_port}/typing",
|
||||
json={"chatId": chat_id},
|
||||
timeout=aiohttp.ClientTimeout(total=5)
|
||||
):
|
||||
pass
|
||||
)
|
||||
except Exception:
|
||||
pass # Ignore typing indicator failures
|
||||
|
||||
|
||||
@@ -1896,12 +1896,10 @@ class OwnerCommandMiddleware(InboundMiddleware):
|
||||
if cmd not in cls.ALLOWLIST:
|
||||
return None, None, False
|
||||
|
||||
# Sender identity check: bot owner <-> push.from_account == push.bot_owner_id.
|
||||
# The allowlisted commands (/approve, /deny, /stop, /reset, ...) are
|
||||
# privileged — leaking them to non-owners lets any group member approve
|
||||
# a dangerous tool call, kill the owner's task, or wipe session state.
|
||||
owner_id = str((push or {}).get("bot_owner_id") or "").strip()
|
||||
is_owner = bool(owner_id) and owner_id == from_account
|
||||
# Sender identity check: bot owner <-> push.from_account == push.bot_owner_id
|
||||
# owner_id = (push or {}).get("bot_owner_id") or ""
|
||||
# is_owner = bool(owner_id) and owner_id == from_account
|
||||
is_owner = True
|
||||
return cmd, cmd_line, is_owner
|
||||
|
||||
async def handle(self, ctx: InboundContext, next_fn) -> None:
|
||||
|
||||
+122
-1544
File diff suppressed because it is too large
Load Diff
+12
-29
@@ -458,15 +458,6 @@ class SessionEntry:
|
||||
was_auto_reset: bool = False
|
||||
auto_reset_reason: Optional[str] = None # "idle" or "daily"
|
||||
reset_had_activity: bool = False # whether the expired session had any messages
|
||||
|
||||
# Set by reset_session() when the user explicitly sends /new or /reset.
|
||||
# Consumed once by _handle_message_with_agent to trigger topic/channel
|
||||
# skill re-injection on the first message of the new session. We can't
|
||||
# reuse was_auto_reset for this because that flag fires the "session
|
||||
# expired due to inactivity" user-facing notice and a misleading
|
||||
# context-note prepend — both wrong for an explicit manual reset.
|
||||
# See issue #6508.
|
||||
is_fresh_reset: bool = False
|
||||
|
||||
# Set by the background expiry watcher after it finalizes an expired
|
||||
# session (invoking on_session_finalize hooks and evicting the cached
|
||||
@@ -517,7 +508,6 @@ class SessionEntry:
|
||||
if self.last_resume_marked_at
|
||||
else None
|
||||
),
|
||||
"is_fresh_reset": self.is_fresh_reset,
|
||||
}
|
||||
if self.origin:
|
||||
result["origin"] = self.origin.to_dict()
|
||||
@@ -566,7 +556,6 @@ class SessionEntry:
|
||||
resume_pending=data.get("resume_pending", False),
|
||||
resume_reason=data.get("resume_reason"),
|
||||
last_resume_marked_at=last_resume_marked_at,
|
||||
is_fresh_reset=data.get("is_fresh_reset", False),
|
||||
)
|
||||
|
||||
|
||||
@@ -1086,22 +1075,19 @@ class SessionStore:
|
||||
return len(removed_keys)
|
||||
|
||||
def suspend_recently_active(self, max_age_seconds: int = 120) -> int:
|
||||
"""Mark recently-active sessions as resumable after an unexpected exit.
|
||||
"""Mark recently-active sessions as suspended.
|
||||
|
||||
Called on gateway startup after a crash or fast restart to preserve
|
||||
in-flight sessions instead of destroying their conversation history
|
||||
(#7536). Only marks sessions updated within *max_age_seconds* to
|
||||
avoid touching long-idle sessions. Sets ``resume_pending=True`` so
|
||||
the next incoming message on the same session_key auto-resumes from
|
||||
the existing transcript.
|
||||
Called on gateway startup to prevent sessions that were likely
|
||||
in-flight when the gateway last exited from being blindly resumed
|
||||
(#7536). Only suspends sessions updated within *max_age_seconds*
|
||||
to avoid resetting long-idle sessions that are harmless to resume.
|
||||
Returns the number of sessions that were suspended.
|
||||
|
||||
Entries already flagged ``resume_pending=True`` are skipped. Entries
|
||||
explicitly ``suspended=True`` (from /stop or stuck-loop escalation)
|
||||
are also skipped. Terminal escalation for genuinely stuck sessions
|
||||
is still handled by the existing ``.restart_failure_counts`` counter
|
||||
(threshold 3), which runs after this method and sets ``suspended=True``.
|
||||
|
||||
Returns the number of sessions marked resumable.
|
||||
Entries flagged ``resume_pending=True`` are skipped — those were
|
||||
marked intentionally by the drain-timeout path as recoverable.
|
||||
Terminal escalation for genuinely stuck ``resume_pending`` sessions
|
||||
is handled by the existing ``.restart_failure_counts`` stuck-loop
|
||||
counter, which runs after this method on startup.
|
||||
"""
|
||||
from datetime import timedelta
|
||||
|
||||
@@ -1113,9 +1099,7 @@ class SessionStore:
|
||||
if entry.resume_pending:
|
||||
continue
|
||||
if not entry.suspended and entry.updated_at >= cutoff:
|
||||
entry.resume_pending = True
|
||||
entry.resume_reason = "restart_interrupted"
|
||||
entry.last_resume_marked_at = _now()
|
||||
entry.suspended = True
|
||||
count += 1
|
||||
if count:
|
||||
self._save()
|
||||
@@ -1148,7 +1132,6 @@ class SessionStore:
|
||||
display_name=old_entry.display_name,
|
||||
platform=old_entry.platform,
|
||||
chat_type=old_entry.chat_type,
|
||||
is_fresh_reset=True,
|
||||
)
|
||||
|
||||
self._entries[session_key] = new_entry
|
||||
|
||||
+4
-8
@@ -21,7 +21,6 @@ from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from hermes_constants import get_hermes_home
|
||||
from typing import Any, Optional
|
||||
from utils import atomic_json_write
|
||||
|
||||
if sys.platform == "win32":
|
||||
import msvcrt
|
||||
@@ -35,10 +34,6 @@ _IS_WINDOWS = sys.platform == "win32"
|
||||
_UNSET = object()
|
||||
_GATEWAY_LOCK_FILENAME = "gateway.lock"
|
||||
_gateway_lock_handle = None
|
||||
# Windows byte-range locks are mandatory for other readers. Lock a byte well
|
||||
# past the JSON payload so runtime status / PID readers can still read the file
|
||||
# while another process holds the mutual-exclusion lock.
|
||||
_WINDOWS_LOCK_OFFSET = 1024 * 1024
|
||||
|
||||
|
||||
def _get_pid_path() -> Path:
|
||||
@@ -210,7 +205,8 @@ def _read_json_file(path: Path) -> Optional[dict[str, Any]]:
|
||||
|
||||
|
||||
def _write_json_file(path: Path, payload: dict[str, Any]) -> None:
|
||||
atomic_json_write(path, payload, indent=None, separators=(",", ":"))
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
path.write_text(json.dumps(payload))
|
||||
|
||||
|
||||
def _read_pid_record(pid_path: Optional[Path] = None) -> Optional[dict]:
|
||||
@@ -290,7 +286,7 @@ def _try_acquire_file_lock(handle) -> bool:
|
||||
if handle.tell() == 0:
|
||||
handle.write("\n")
|
||||
handle.flush()
|
||||
handle.seek(_WINDOWS_LOCK_OFFSET)
|
||||
handle.seek(0)
|
||||
msvcrt.locking(handle.fileno(), msvcrt.LK_NBLCK, 1)
|
||||
else:
|
||||
fcntl.flock(handle.fileno(), fcntl.LOCK_EX | fcntl.LOCK_NB)
|
||||
@@ -302,7 +298,7 @@ def _try_acquire_file_lock(handle) -> bool:
|
||||
def _release_file_lock(handle) -> None:
|
||||
try:
|
||||
if _IS_WINDOWS:
|
||||
handle.seek(_WINDOWS_LOCK_OFFSET)
|
||||
handle.seek(0)
|
||||
msvcrt.locking(handle.fileno(), msvcrt.LK_UNLCK, 1)
|
||||
else:
|
||||
fcntl.flock(handle.fileno(), fcntl.LOCK_UN)
|
||||
|
||||
+3
-35
@@ -5,43 +5,11 @@ Provides subcommands for:
|
||||
- hermes chat - Interactive chat (same as ./hermes)
|
||||
- hermes gateway - Run gateway in foreground
|
||||
- hermes gateway start - Start gateway service
|
||||
- hermes gateway stop - Stop gateway service
|
||||
- hermes gateway stop - Stop gateway service
|
||||
- hermes setup - Interactive setup wizard
|
||||
- hermes status - Show status of all components
|
||||
- hermes cron - Manage cron jobs
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
__version__ = "0.12.0"
|
||||
__release_date__ = "2026.4.30"
|
||||
|
||||
|
||||
def _ensure_utf8():
|
||||
"""Force UTF-8 stdout/stderr on Windows to prevent UnicodeEncodeError.
|
||||
|
||||
Windows services and terminals default to cp1252, which cannot encode
|
||||
box-drawing characters used in CLI output. This causes unhandled
|
||||
UnicodeEncodeError crashes on gateway startup.
|
||||
"""
|
||||
if sys.platform != "win32":
|
||||
return
|
||||
os.environ.setdefault("PYTHONUTF8", "1")
|
||||
os.environ.setdefault("PYTHONIOENCODING", "utf-8")
|
||||
for stream_name in ("stdout", "stderr"):
|
||||
stream = getattr(sys, stream_name, None)
|
||||
if stream is None:
|
||||
continue
|
||||
try:
|
||||
if getattr(stream, "encoding", "").lower().replace("-", "") != "utf8":
|
||||
new_stream = open(
|
||||
stream.fileno(), "w", encoding="utf-8",
|
||||
buffering=1, closefd=False,
|
||||
)
|
||||
setattr(sys, stream_name, new_stream)
|
||||
except (AttributeError, OSError):
|
||||
pass
|
||||
|
||||
|
||||
_ensure_utf8()
|
||||
__version__ = "0.11.0"
|
||||
__release_date__ = "2026.4.23"
|
||||
|
||||
+7
-9
@@ -43,7 +43,7 @@ import yaml
|
||||
|
||||
from hermes_cli.config import get_hermes_home, get_config_path, read_raw_config
|
||||
from hermes_constants import OPENROUTER_BASE_URL
|
||||
from utils import atomic_replace, atomic_yaml_write, is_truthy_value
|
||||
from utils import atomic_replace
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -2480,8 +2480,8 @@ def _resolve_verify(
|
||||
tls_state = tls_state if isinstance(tls_state, dict) else {}
|
||||
|
||||
effective_insecure = (
|
||||
is_truthy_value(insecure, default=False) if insecure is not None
|
||||
else is_truthy_value(tls_state.get("insecure", False), default=False)
|
||||
bool(insecure) if insecure is not None
|
||||
else bool(tls_state.get("insecure", False))
|
||||
)
|
||||
effective_ca = (
|
||||
ca_bundle
|
||||
@@ -3653,7 +3653,7 @@ def _update_config_for_provider(
|
||||
|
||||
config["model"] = model_cfg
|
||||
|
||||
atomic_yaml_write(config_path, config, sort_keys=False)
|
||||
config_path.write_text(yaml.safe_dump(config, sort_keys=False))
|
||||
return config_path
|
||||
|
||||
|
||||
@@ -3712,7 +3712,7 @@ def _reset_config_provider() -> Path:
|
||||
model["provider"] = "auto"
|
||||
if "base_url" in model:
|
||||
model["base_url"] = OPENROUTER_BASE_URL
|
||||
atomic_yaml_write(config_path, config, sort_keys=False)
|
||||
config_path.write_text(yaml.safe_dump(config, sort_keys=False))
|
||||
return config_path
|
||||
|
||||
|
||||
@@ -4283,8 +4283,7 @@ def _minimax_oauth_login(
|
||||
print(f"Portal: {portal_base_url}")
|
||||
|
||||
with httpx.Client(timeout=httpx.Timeout(timeout_seconds),
|
||||
headers={"Accept": "application/json"},
|
||||
follow_redirects=True) as client:
|
||||
headers={"Accept": "application/json"}) as client:
|
||||
code_data = _minimax_request_user_code(
|
||||
client, portal_base_url=portal_base_url,
|
||||
client_id=pconfig.client_id,
|
||||
@@ -4361,8 +4360,7 @@ def _refresh_minimax_oauth_state(
|
||||
return state
|
||||
|
||||
portal_base_url = state["portal_base_url"]
|
||||
with httpx.Client(timeout=httpx.Timeout(timeout_seconds),
|
||||
follow_redirects=True) as client:
|
||||
with httpx.Client(timeout=httpx.Timeout(timeout_seconds)) as client:
|
||||
response = client.post(
|
||||
f"{portal_base_url}/oauth/token",
|
||||
data={
|
||||
|
||||
+60
-165
@@ -10,7 +10,6 @@ To add an alias: set ``aliases=("short",)`` on the existing ``CommandDef``.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
@@ -20,10 +19,6 @@ from collections.abc import Callable, Mapping
|
||||
from dataclasses import dataclass
|
||||
from typing import Any
|
||||
|
||||
from utils import is_truthy_value
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# prompt_toolkit is an optional CLI dependency — only needed for
|
||||
# SlashCommandCompleter and SlashCommandAutoSuggest. Gateway and test
|
||||
# environments that lack it must still be able to import this module
|
||||
@@ -98,8 +93,6 @@ COMMAND_REGISTRY: list[CommandDef] = [
|
||||
aliases=("q",), args_hint="<prompt>"),
|
||||
CommandDef("steer", "Inject a message after the next tool call without interrupting", "Session",
|
||||
args_hint="<prompt>"),
|
||||
CommandDef("goal", "Set a standing goal Hermes works on across turns until achieved", "Session",
|
||||
args_hint="[text | pause | resume | clear | status]"),
|
||||
CommandDef("status", "Show session info", "Session"),
|
||||
CommandDef("profile", "Show active profile name and home directory", "Info"),
|
||||
CommandDef("sethome", "Set this chat as the home channel", "Session",
|
||||
@@ -158,11 +151,6 @@ COMMAND_REGISTRY: list[CommandDef] = [
|
||||
CommandDef("curator", "Background skill maintenance (status, run, pin, archive)",
|
||||
"Tools & Skills", args_hint="[subcommand]",
|
||||
subcommands=("status", "run", "pause", "resume", "pin", "unpin", "restore")),
|
||||
CommandDef("kanban", "Multi-profile collaboration board (tasks, links, comments)",
|
||||
"Tools & Skills", args_hint="[subcommand]",
|
||||
subcommands=("list", "ls", "show", "create", "assign", "link", "unlink",
|
||||
"claim", "comment", "complete", "block", "unblock", "archive",
|
||||
"tail", "dispatch", "context", "init", "gc")),
|
||||
CommandDef("reload", "Reload .env variables into the running session", "Tools & Skills",
|
||||
cli_only=True),
|
||||
CommandDef("reload-mcp", "Reload MCP servers from config", "Tools & Skills",
|
||||
@@ -378,7 +366,7 @@ def _resolve_config_gates() -> set[str]:
|
||||
else:
|
||||
val = None
|
||||
break
|
||||
if is_truthy_value(val, default=False):
|
||||
if val:
|
||||
result.add(cmd.name)
|
||||
return result
|
||||
|
||||
@@ -399,11 +387,6 @@ def _is_gateway_available(cmd: CommandDef, config_overrides: set[str] | None = N
|
||||
return False
|
||||
|
||||
|
||||
def _requires_argument(args_hint: str) -> bool:
|
||||
"""Return True when selecting a command without text would be incomplete."""
|
||||
return args_hint.strip().startswith("<")
|
||||
|
||||
|
||||
def gateway_help_lines() -> list[str]:
|
||||
"""Generate gateway help text lines from the registry."""
|
||||
overrides = _resolve_config_gates()
|
||||
@@ -460,9 +443,7 @@ def telegram_bot_commands() -> list[tuple[str, str]]:
|
||||
|
||||
Telegram command names cannot contain hyphens, so they are replaced with
|
||||
underscores. Aliases are skipped -- Telegram shows one menu entry per
|
||||
canonical command. Commands that require arguments are skipped because
|
||||
selecting a Telegram BotCommand sends only ``/command`` and would execute
|
||||
an incomplete command.
|
||||
canonical command.
|
||||
|
||||
Plugin-registered slash commands are included so plugins get native
|
||||
autocomplete in Telegram without touching core code.
|
||||
@@ -472,14 +453,10 @@ def telegram_bot_commands() -> list[tuple[str, str]]:
|
||||
for cmd in COMMAND_REGISTRY:
|
||||
if not _is_gateway_available(cmd, overrides):
|
||||
continue
|
||||
if _requires_argument(cmd.args_hint):
|
||||
continue
|
||||
tg_name = _sanitize_telegram_name(cmd.name)
|
||||
if tg_name:
|
||||
result.append((tg_name, cmd.description))
|
||||
for name, description, args_hint in _iter_plugin_command_entries():
|
||||
if _requires_argument(args_hint):
|
||||
continue
|
||||
for name, description, _args_hint in _iter_plugin_command_entries():
|
||||
tg_name = _sanitize_telegram_name(name)
|
||||
if tg_name:
|
||||
result.append((tg_name, description))
|
||||
@@ -513,9 +490,9 @@ def _sanitize_telegram_name(raw: str) -> str:
|
||||
|
||||
|
||||
def _clamp_command_names(
|
||||
entries: list[tuple[str, ...]],
|
||||
entries: list[tuple[str, str]],
|
||||
reserved: set[str],
|
||||
) -> list[tuple[str, ...]]:
|
||||
) -> list[tuple[str, str]]:
|
||||
"""Enforce 32-char command name limit with collision avoidance.
|
||||
|
||||
Both Telegram and Discord cap slash command names at 32 characters.
|
||||
@@ -523,15 +500,10 @@ def _clamp_command_names(
|
||||
(against *reserved* names or earlier entries in the same batch), the name is
|
||||
shortened to 31 chars and a digit ``0``-``9`` is appended to differentiate.
|
||||
If all 10 digit slots are taken the entry is silently dropped.
|
||||
|
||||
Accepts tuples of any length >= 2. Extra elements beyond ``(name, desc)``
|
||||
(e.g. ``cmd_key``) are passed through unchanged, so callers can attach
|
||||
metadata that survives the rename.
|
||||
"""
|
||||
used: set[str] = set(reserved)
|
||||
result: list[tuple] = []
|
||||
for entry in entries:
|
||||
name, desc, *extra = entry
|
||||
result: list[tuple[str, str]] = []
|
||||
for name, desc in entries:
|
||||
if len(name) > _CMD_NAME_LIMIT:
|
||||
candidate = name[:_CMD_NAME_LIMIT]
|
||||
if candidate in used:
|
||||
@@ -547,7 +519,7 @@ def _clamp_command_names(
|
||||
if name in used:
|
||||
continue
|
||||
used.add(name)
|
||||
result.append((name, desc, *extra))
|
||||
result.append((name, desc))
|
||||
return result
|
||||
|
||||
|
||||
@@ -630,26 +602,13 @@ def _collect_gateway_skill_entries(
|
||||
try:
|
||||
from agent.skill_commands import get_skill_commands
|
||||
from tools.skills_tool import SKILLS_DIR
|
||||
from agent.skill_utils import get_external_skills_dirs
|
||||
_skills_dir = str(SKILLS_DIR.resolve())
|
||||
_hub_dir = str((SKILLS_DIR / ".hub").resolve()).rstrip("/") + "/"
|
||||
# Build set of allowed directory prefixes: local skills dir + any
|
||||
# user-configured ``skills.external_dirs``. Ensure each prefix ends
|
||||
# with ``/`` so ``/my-skills`` does not also match ``/my-skills-extra``.
|
||||
# Without this widening, external skills are visible in
|
||||
# ``hermes skills list`` and the agent's ``/skill-name`` dispatch but
|
||||
# silently excluded from gateway slash menus (#8110).
|
||||
_allowed_prefixes = [_skills_dir.rstrip("/") + "/"]
|
||||
_allowed_prefixes.extend(
|
||||
str(d).rstrip("/") + "/" for d in get_external_skills_dirs()
|
||||
)
|
||||
_hub_dir = str((SKILLS_DIR / ".hub").resolve())
|
||||
skill_cmds = get_skill_commands()
|
||||
for cmd_key in sorted(skill_cmds):
|
||||
info = skill_cmds[cmd_key]
|
||||
skill_path = info.get("skill_md_path", "")
|
||||
if not skill_path:
|
||||
continue
|
||||
if not any(skill_path.startswith(prefix) for prefix in _allowed_prefixes):
|
||||
if not skill_path.startswith(_skills_dir):
|
||||
continue
|
||||
if skill_path.startswith(_hub_dir):
|
||||
continue
|
||||
@@ -667,15 +626,17 @@ def _collect_gateway_skill_entries(
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Clamp names; cmd_key is passed through as extra payload so it survives
|
||||
# any clamp-induced renames.
|
||||
skill_triples = _clamp_command_names(skill_triples, reserved_names)
|
||||
# Clamp names; _clamp_command_names works on (name, desc) pairs so we
|
||||
# need to zip/unzip.
|
||||
skill_pairs = [(n, d) for n, d, _ in skill_triples]
|
||||
key_by_pair = {(n, d): k for n, d, k in skill_triples}
|
||||
skill_pairs = _clamp_command_names(skill_pairs, reserved_names)
|
||||
|
||||
# Skills fill remaining slots — only tier that gets trimmed
|
||||
remaining = max(0, max_slots - len(all_entries))
|
||||
hidden_count = max(0, len(skill_triples) - remaining)
|
||||
for n, d, k in skill_triples[:remaining]:
|
||||
all_entries.append((n, d, k))
|
||||
hidden_count = max(0, len(skill_pairs) - remaining)
|
||||
for n, d in skill_pairs[:remaining]:
|
||||
all_entries.append((n, d, key_by_pair.get((n, d), "")))
|
||||
|
||||
return all_entries[:max_slots], hidden_count
|
||||
|
||||
@@ -751,40 +712,24 @@ def discord_skill_commands(
|
||||
def discord_skill_commands_by_category(
|
||||
reserved_names: set[str],
|
||||
) -> tuple[dict[str, list[tuple[str, str, str]]], list[tuple[str, str, str]], int]:
|
||||
"""Return skill entries organized by category for Discord ``/skill`` autocomplete.
|
||||
"""Return skill entries organized by category for Discord ``/skill`` subcommand groups.
|
||||
|
||||
Skills whose directory is nested at least 2 levels under a scan root
|
||||
Skills whose directory is nested at least 2 levels under ``SKILLS_DIR``
|
||||
(e.g. ``creative/ascii-art/SKILL.md``) are grouped by their top-level
|
||||
category. Root-level skills (e.g. ``dogfood/SKILL.md``) are returned as
|
||||
*uncategorized*.
|
||||
*uncategorized* — the caller should register them as direct subcommands
|
||||
of the ``/skill`` group.
|
||||
|
||||
Scan roots include the local ``SKILLS_DIR`` **and** any configured
|
||||
``skills.external_dirs`` — matching the widened filter applied to the
|
||||
flat ``discord_skill_commands()`` collector in #18741. Without this
|
||||
parity, external-dir skills are visible via ``hermes skills list`` and
|
||||
the agent's ``/skill-name`` dispatch but silently absent from Discord's
|
||||
``/skill`` autocomplete.
|
||||
|
||||
Filtering mirrors :func:`discord_skill_commands`: hub skills excluded,
|
||||
per-platform disabled excluded, names clamped to 32 chars, descriptions
|
||||
clamped to 100 chars.
|
||||
|
||||
The legacy 25-group × 25-subcommand caps (from the old nested
|
||||
``/skill <cat> <name>`` layout) are **not** applied — the live caller
|
||||
(``_register_skill_group`` in ``gateway/platforms/discord.py``, refactored
|
||||
in PR #11580) flattens these results and feeds them into a single
|
||||
autocomplete callback, which scales to thousands of entries without any
|
||||
per-command payload concerns. ``hidden_count`` is retained in the return
|
||||
tuple for backward compatibility and still reports skills dropped for
|
||||
other reasons (32-char clamp collision vs a reserved name).
|
||||
The same filtering as :func:`discord_skill_commands` is applied: hub
|
||||
skills excluded, per-platform disabled excluded, names clamped.
|
||||
|
||||
Returns:
|
||||
``(categories, uncategorized, hidden_count)``
|
||||
|
||||
- *categories*: ``{category_name: [(name, description, cmd_key), ...]}``
|
||||
- *uncategorized*: ``[(name, description, cmd_key), ...]``
|
||||
- *hidden_count*: skills dropped due to name clamp collisions
|
||||
against already-registered command names.
|
||||
- *hidden_count*: skills dropped due to Discord group limits
|
||||
(25 subcommand groups, 25 subcommands per group)
|
||||
"""
|
||||
from pathlib import Path as _P
|
||||
|
||||
@@ -798,33 +743,14 @@ def discord_skill_commands_by_category(
|
||||
# Collect raw skill data --------------------------------------------------
|
||||
categories: dict[str, list[tuple[str, str, str]]] = {}
|
||||
uncategorized: list[tuple[str, str, str]] = []
|
||||
# Map clamped-32-char-name → what it came from, so we can emit an
|
||||
# actionable warning on collision. Reserved (gateway-builtin) command
|
||||
# names are marked with a sentinel so the warning distinguishes
|
||||
# "skill collided with a reserved command" from "two skills collided
|
||||
# on the 32-char clamp" — the latter is the rename-worthy case.
|
||||
_names_used: dict[str, str] = {n: "<reserved>" for n in reserved_names}
|
||||
_names_used: set[str] = set(reserved_names)
|
||||
hidden = 0
|
||||
|
||||
try:
|
||||
from agent.skill_commands import get_skill_commands
|
||||
from agent.skill_utils import get_external_skills_dirs
|
||||
from tools.skills_tool import SKILLS_DIR
|
||||
|
||||
_skills_dir = SKILLS_DIR.resolve()
|
||||
_hub_dir = (SKILLS_DIR / ".hub").resolve()
|
||||
# Build list of (resolved_root, is_local) tuples. Each external dir
|
||||
# becomes its own scan root for category derivation — a skill at
|
||||
# ``<external>/mlops/foo/SKILL.md`` is still categorized as "mlops".
|
||||
_scan_roots: list[_P] = [_skills_dir]
|
||||
try:
|
||||
for ext in get_external_skills_dirs():
|
||||
try:
|
||||
_scan_roots.append(_P(ext).resolve())
|
||||
except Exception:
|
||||
continue
|
||||
except Exception:
|
||||
pass
|
||||
skill_cmds = get_skill_commands()
|
||||
|
||||
for cmd_key in sorted(skill_cmds):
|
||||
@@ -833,21 +759,10 @@ def discord_skill_commands_by_category(
|
||||
if not skill_path:
|
||||
continue
|
||||
sp = _P(skill_path).resolve()
|
||||
# Hub skills are loaded via the skill hub, not surfaced as
|
||||
# slash commands.
|
||||
if str(sp).startswith(str(_hub_dir)):
|
||||
# Skip skills outside SKILLS_DIR or from the hub
|
||||
if not str(sp).startswith(str(_skills_dir)):
|
||||
continue
|
||||
# Accept skill if it lives under any scan root; record the
|
||||
# matching root so we can derive the category correctly.
|
||||
matched_root: _P | None = None
|
||||
for root in _scan_roots:
|
||||
try:
|
||||
sp.relative_to(root)
|
||||
except ValueError:
|
||||
continue
|
||||
matched_root = root
|
||||
break
|
||||
if matched_root is None:
|
||||
if str(sp).startswith(str(_hub_dir)):
|
||||
continue
|
||||
|
||||
skill_name = info.get("name", "")
|
||||
@@ -855,50 +770,22 @@ def discord_skill_commands_by_category(
|
||||
continue
|
||||
|
||||
raw_name = cmd_key.lstrip("/")
|
||||
# Clamp to 32 chars (Discord per-command name limit)
|
||||
# Clamp to 32 chars (Discord limit)
|
||||
discord_name = raw_name[:32]
|
||||
if discord_name in _names_used:
|
||||
# Two skills whose first 32 chars are identical. One wins
|
||||
# (the first one seen, which is alphabetical because the
|
||||
# caller iterates ``sorted(skill_cmds)``); the other is
|
||||
# dropped from Discord's /skill autocomplete.
|
||||
#
|
||||
# Silently counting this as ``hidden`` (the old behavior)
|
||||
# meant skill authors had no way to discover the drop —
|
||||
# their skill just didn't appear in the picker. Emit a
|
||||
# WARNING naming both sides so the author can rename the
|
||||
# losing skill's frontmatter name to something with a
|
||||
# distinct 32-char prefix.
|
||||
prior = _names_used[discord_name]
|
||||
if prior == "<reserved>":
|
||||
logger.warning(
|
||||
"Discord /skill: %r (from %r) collides on its 32-char "
|
||||
"clamp with a reserved gateway command name %r — the "
|
||||
"skill will not appear in the /skill autocomplete. "
|
||||
"Rename the skill's frontmatter ``name:`` to differ "
|
||||
"in its first 32 chars.",
|
||||
discord_name, cmd_key, discord_name,
|
||||
)
|
||||
else:
|
||||
logger.warning(
|
||||
"Discord /skill: %r and %r both clamp to %r on "
|
||||
"Discord's 32-char command-name limit — only %r "
|
||||
"will appear in the /skill autocomplete. Rename "
|
||||
"one skill's frontmatter ``name:`` to differ in "
|
||||
"its first 32 chars.",
|
||||
prior, cmd_key, discord_name, prior,
|
||||
)
|
||||
hidden += 1
|
||||
continue
|
||||
_names_used[discord_name] = cmd_key
|
||||
_names_used.add(discord_name)
|
||||
|
||||
desc = info.get("description", "")
|
||||
if len(desc) > 100:
|
||||
desc = desc[:97] + "..."
|
||||
|
||||
# Determine category from the relative path within the matched
|
||||
# scan root. e.g. creative/ascii-art/SKILL.md → ("creative", ...)
|
||||
rel = sp.parent.relative_to(matched_root)
|
||||
# Determine category from the relative path within SKILLS_DIR.
|
||||
# e.g. creative/ascii-art/SKILL.md → parts = ("creative", "ascii-art")
|
||||
try:
|
||||
rel = sp.parent.relative_to(_skills_dir)
|
||||
except ValueError:
|
||||
continue
|
||||
parts = rel.parts
|
||||
if len(parts) >= 2:
|
||||
cat = parts[0]
|
||||
@@ -908,7 +795,28 @@ def discord_skill_commands_by_category(
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return categories, uncategorized, hidden
|
||||
# Enforce Discord limits: 25 subcommand groups, 25 subcommands each ------
|
||||
_MAX_GROUPS = 25
|
||||
_MAX_PER_GROUP = 25
|
||||
|
||||
trimmed_categories: dict[str, list[tuple[str, str, str]]] = {}
|
||||
group_count = 0
|
||||
for cat in sorted(categories):
|
||||
if group_count >= _MAX_GROUPS:
|
||||
hidden += len(categories[cat])
|
||||
continue
|
||||
entries = categories[cat][:_MAX_PER_GROUP]
|
||||
hidden += max(0, len(categories[cat]) - _MAX_PER_GROUP)
|
||||
trimmed_categories[cat] = entries
|
||||
group_count += 1
|
||||
|
||||
# Uncategorized skills also count against the 25 top-level limit
|
||||
remaining_slots = _MAX_GROUPS - group_count
|
||||
if len(uncategorized) > remaining_slots:
|
||||
hidden += len(uncategorized) - remaining_slots
|
||||
uncategorized = uncategorized[:remaining_slots]
|
||||
|
||||
return trimmed_categories, uncategorized, hidden
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -921,13 +829,6 @@ def discord_skill_commands_by_category(
|
||||
_SLACK_MAX_SLASH_COMMANDS = 50
|
||||
_SLACK_NAME_LIMIT = 32
|
||||
_SLACK_INVALID_CHARS = re.compile(r"[^a-z0-9_\-]")
|
||||
_SLACK_RESERVED_COMMANDS = frozenset({
|
||||
# Built-in Slack slash commands that cannot be registered by apps.
|
||||
# https://slack.com/help/articles/201259356-Use-built-in-slash-commands
|
||||
"me", "status", "away", "dnd", "shrug", "remind", "msg", "feed",
|
||||
"who", "collapse", "expand", "leave", "join", "open", "search",
|
||||
"topic", "mute", "pro", "shortcuts",
|
||||
})
|
||||
|
||||
|
||||
def _sanitize_slack_name(raw: str) -> str:
|
||||
@@ -954,10 +855,6 @@ def slack_native_slashes() -> list[tuple[str, str, str]]:
|
||||
documented form (e.g. ``/background``, ``/bg``, and ``/btw`` all work).
|
||||
Plugin-registered slash commands are included too.
|
||||
|
||||
Commands whose sanitized name collides with a Slack built-in
|
||||
(e.g. ``/status``, ``/me``, ``/join``) are silently skipped. Users
|
||||
can still reach them via ``/hermes <command>``.
|
||||
|
||||
Results are clamped to Slack's 50-command limit with duplicate-name
|
||||
avoidance. ``/hermes`` is always reserved as the first entry so the
|
||||
legacy ``/hermes <subcommand>`` form keeps working for anything that
|
||||
@@ -975,8 +872,6 @@ def slack_native_slashes() -> list[tuple[str, str, str]]:
|
||||
slack_name = _sanitize_slack_name(name)
|
||||
if not slack_name or slack_name in seen:
|
||||
return
|
||||
if slack_name in _SLACK_RESERVED_COMMANDS:
|
||||
return
|
||||
if len(entries) >= _SLACK_MAX_SLASH_COMMANDS:
|
||||
return
|
||||
# Slack description cap is 2000 chars; keep it short.
|
||||
|
||||
+5
-103
@@ -400,12 +400,7 @@ DEFAULT_CONFIG = {
|
||||
# The gateway stops accepting new work, waits for running agents
|
||||
# to finish, then interrupts any remaining runs after the timeout.
|
||||
# 0 = no drain, interrupt immediately.
|
||||
#
|
||||
# 180s is calibrated for realistic in-flight agent turns: a typical
|
||||
# coding conversation mid-reasoning runs 60–150s per call, so a 60s
|
||||
# budget routinely interrupted legitimate work on /restart. Raise
|
||||
# further in config.yaml if you run very-long-reasoning models.
|
||||
"restart_drain_timeout": 180,
|
||||
"restart_drain_timeout": 60,
|
||||
# Max app-level retry attempts for API errors (connection drops,
|
||||
# provider timeouts, 5xx, etc.) before the agent surfaces the
|
||||
# failure. The OpenAI SDK already does its own low-level retries
|
||||
@@ -462,7 +457,6 @@ DEFAULT_CONFIG = {
|
||||
# remains available as a tool regardless of this setting — the routing
|
||||
# only controls how inbound user images are presented.
|
||||
"image_input_mode": "auto",
|
||||
"disabled_toolsets": [],
|
||||
},
|
||||
|
||||
"terminal": {
|
||||
@@ -612,24 +606,6 @@ DEFAULT_CONFIG = {
|
||||
"max_line_length": 2000,
|
||||
},
|
||||
|
||||
# Tool loop guardrails nudge models when they repeat failed or
|
||||
# non-progressing tool calls. Soft warnings are always-on by default;
|
||||
# hard stops are opt-in so interactive CLI/TUI sessions keep flowing.
|
||||
"tool_loop_guardrails": {
|
||||
"warnings_enabled": True,
|
||||
"hard_stop_enabled": False,
|
||||
"warn_after": {
|
||||
"exact_failure": 2,
|
||||
"same_tool_failure": 3,
|
||||
"idempotent_no_progress": 2,
|
||||
},
|
||||
"hard_stop_after": {
|
||||
"exact_failure": 5,
|
||||
"same_tool_failure": 8,
|
||||
"idempotent_no_progress": 5,
|
||||
},
|
||||
},
|
||||
|
||||
"compression": {
|
||||
"enabled": True,
|
||||
"threshold": 0.50, # compress when context usage exceeds this ratio
|
||||
@@ -644,18 +620,6 @@ DEFAULT_CONFIG = {
|
||||
"cache_ttl": "5m",
|
||||
},
|
||||
|
||||
# OpenRouter-specific settings.
|
||||
# response_cache: enable OpenRouter response caching (X-OpenRouter-Cache header).
|
||||
# When enabled, identical requests return cached responses for free (zero billing).
|
||||
# This is separate from Anthropic prompt caching and works alongside it.
|
||||
# See: https://openrouter.ai/docs/guides/features/response-caching
|
||||
# response_cache_ttl: how long cached responses remain valid, in seconds (1-86400).
|
||||
# Default 300 (5 minutes). Only used when response_cache is enabled.
|
||||
"openrouter": {
|
||||
"response_cache": True,
|
||||
"response_cache_ttl": 300,
|
||||
},
|
||||
|
||||
# AWS Bedrock provider configuration.
|
||||
# Only used when model.provider is "bedrock".
|
||||
"bedrock": {
|
||||
@@ -792,14 +756,6 @@ DEFAULT_CONFIG = {
|
||||
"tool_progress_command": False, # Enable /verbose command in messaging gateway
|
||||
"tool_progress_overrides": {}, # DEPRECATED — use display.platforms instead
|
||||
"tool_preview_length": 0, # Max chars for tool call previews (0 = no limit, show full paths/commands)
|
||||
# Auto-delete system-notice replies (e.g. "✨ New session started!",
|
||||
# "♻ Restarting gateway…", "⚡ Stopped…") after N seconds on platforms
|
||||
# that support message deletion (currently Telegram; other platforms
|
||||
# ignore and leave the message in place). Only affects slash-command
|
||||
# replies wrapped with gateway.platforms.base.EphemeralReply — agent
|
||||
# responses and content messages are never touched. Default 0
|
||||
# (disabled) preserves prior behavior.
|
||||
"ephemeral_system_ttl": 0,
|
||||
"platforms": {}, # Per-platform display overrides: {"telegram": {"tool_progress": "all"}, "slack": {"tool_progress": "off"}}
|
||||
# Gateway runtime-metadata footer appended to the FINAL message of a turn
|
||||
# (disabled by default to keep replies minimal). When enabled, renders
|
||||
@@ -842,7 +798,7 @@ DEFAULT_CONFIG = {
|
||||
# Voices: alloy, echo, fable, onyx, nova, shimmer
|
||||
},
|
||||
"xai": {
|
||||
"voice_id": "eve", # or custom voice ID — see https://docs.x.ai/developers/model-capabilities/audio/custom-voices
|
||||
"voice_id": "eve",
|
||||
"language": "en",
|
||||
"sample_rate": 24000,
|
||||
"bit_rate": 128000,
|
||||
@@ -969,23 +925,7 @@ DEFAULT_CONFIG = {
|
||||
# injected at the start of every API call for few-shot priming.
|
||||
# Never saved to sessions, logs, or trajectories.
|
||||
"prefill_messages_file": "",
|
||||
|
||||
# Goals — persistent cross-turn goals (Ralph-style loop).
|
||||
# After every turn, a lightweight judge call asks the auxiliary model
|
||||
# whether the active /goal is satisfied by the assistant's last
|
||||
# response. If not, Hermes feeds a continuation prompt back into the
|
||||
# same session and keeps working until the goal is done, the turn
|
||||
# budget is exhausted, or the user pauses/clears it. Judge failures
|
||||
# fail OPEN (continue) so a flaky judge never wedges progress — the
|
||||
# turn budget is the real backstop.
|
||||
"goals": {
|
||||
# Max continuation turns before Hermes auto-pauses the goal and
|
||||
# asks the user to /goal resume. Protects against judge false
|
||||
# negatives (goal actually done but judge says continue) and
|
||||
# unbounded model spend on fuzzy / unachievable goals.
|
||||
"max_turns": 20,
|
||||
},
|
||||
|
||||
|
||||
# Skills — external skill directories for sharing skills across tools/agents.
|
||||
# Each path is expanded (~, ${VAR}) and resolved. Read-only — skill creation
|
||||
# always goes to ~/.hermes/skills/.
|
||||
@@ -1039,14 +979,6 @@ DEFAULT_CONFIG = {
|
||||
# Archive a skill (move to skills/.archive/) after this many days
|
||||
# without use. Archived skills are recoverable — no auto-deletion.
|
||||
"archive_after_days": 90,
|
||||
# Pre-run backup: before every real curator pass (dry-run is
|
||||
# skipped), snapshot ~/.hermes/skills/ into
|
||||
# ~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz so the
|
||||
# user can roll back with `hermes curator rollback`.
|
||||
"backup": {
|
||||
"enabled": True,
|
||||
"keep": 5, # retain last N regular snapshots
|
||||
},
|
||||
},
|
||||
|
||||
# Honcho AI-native memory -- reads ~/.honcho/config.json as single source of truth.
|
||||
@@ -1172,24 +1104,6 @@ DEFAULT_CONFIG = {
|
||||
"max_parallel_jobs": None,
|
||||
},
|
||||
|
||||
# Kanban multi-agent coordination — controls the dispatcher loop that
|
||||
# spawns workers for ready tasks. The dispatcher ticks every N seconds
|
||||
# (default 60), reclaims stale claims, promotes dependency-satisfied
|
||||
# todos to ready, and fires `hermes -p <assignee> chat -q ...` for
|
||||
# each claimable ready task. One dispatcher per profile is sufficient;
|
||||
# running more than one on the same kanban.db will race for claims.
|
||||
"kanban": {
|
||||
# Run the dispatcher inside the gateway process. On by default —
|
||||
# the cost is ~300µs every `dispatch_interval_seconds` when idle,
|
||||
# and gateway is the supervisor users already have. Set to false
|
||||
# only if you run the dispatcher as a separate systemd unit or
|
||||
# don't want the gateway to spawn workers.
|
||||
"dispatch_in_gateway": True,
|
||||
# Seconds between dispatcher ticks (idle or not). Lower = snappier
|
||||
# pickup of newly-ready tasks; higher = less SQL pressure.
|
||||
"dispatch_interval_seconds": 60,
|
||||
},
|
||||
|
||||
# execute_code settings — controls the tool used for programmatic tool calls.
|
||||
"code_execution": {
|
||||
# Execution mode:
|
||||
@@ -2486,17 +2400,7 @@ def get_missing_skill_config_vars() -> List[Dict[str, Any]]:
|
||||
except Exception:
|
||||
return []
|
||||
|
||||
try:
|
||||
all_vars = discover_all_skill_config_vars()
|
||||
except Exception as e:
|
||||
# A malformed SKILL.md, unreadable external skill dir, or similar
|
||||
# should never break `hermes update`. Skill-config prompting is a
|
||||
# post-migration nicety, not a blocker.
|
||||
import logging
|
||||
logging.getLogger(__name__).debug(
|
||||
"discover_all_skill_config_vars failed: %s", e
|
||||
)
|
||||
return []
|
||||
all_vars = discover_all_skill_config_vars()
|
||||
if not all_vars:
|
||||
return []
|
||||
|
||||
@@ -4675,9 +4579,7 @@ def set_config_value(key: str, value: str):
|
||||
"terminal.vercel_runtime": "TERMINAL_VERCEL_RUNTIME",
|
||||
"terminal.docker_mount_cwd_to_workspace": "TERMINAL_DOCKER_MOUNT_CWD_TO_WORKSPACE",
|
||||
"terminal.docker_run_as_host_user": "TERMINAL_DOCKER_RUN_AS_HOST_USER",
|
||||
# terminal.cwd intentionally excluded — CLI resolves at runtime,
|
||||
# gateway bridges it in gateway/run.py. Persisting to .env causes
|
||||
# stale values to poison child processes.
|
||||
"terminal.cwd": "TERMINAL_CWD",
|
||||
"terminal.timeout": "TERMINAL_TIMEOUT",
|
||||
"terminal.sandbox_dir": "TERMINAL_SANDBOX_DIR",
|
||||
"terminal.persistent_shell": "TERMINAL_PERSISTENT_SHELL",
|
||||
|
||||
+7
-193
@@ -108,49 +108,6 @@ def _cmd_status(args) -> int:
|
||||
f"last_activity={last}"
|
||||
)
|
||||
|
||||
# Show top 5 most-active and least-active skills by activity_count
|
||||
# (use + view + patch). This is a different signal from
|
||||
# least-recently-active: activity_count reflects frequency,
|
||||
# last_activity_at reflects recency. A skill touched 30 times a year
|
||||
# ago is high-frequency but stale; a skill touched once yesterday is
|
||||
# recent but low-frequency. Both can matter.
|
||||
active_all = by_state.get("active", [])
|
||||
if active_all:
|
||||
most_active = sorted(
|
||||
active_all,
|
||||
key=lambda r: (r.get("activity_count") or 0, r.get("last_activity_at") or ""),
|
||||
reverse=True,
|
||||
)[:5]
|
||||
if most_active and (most_active[0].get("activity_count") or 0) > 0:
|
||||
print("\nmost active (top 5):")
|
||||
for r in most_active:
|
||||
last = _fmt_ts(r.get("last_activity_at"))
|
||||
print(
|
||||
f" {r['name']:40s} "
|
||||
f"activity={r.get('activity_count', 0):3d} "
|
||||
f"use={r.get('use_count', 0):3d} "
|
||||
f"view={r.get('view_count', 0):3d} "
|
||||
f"patches={r.get('patch_count', 0):3d} "
|
||||
f"last_activity={last}"
|
||||
)
|
||||
|
||||
least_active = sorted(
|
||||
active_all,
|
||||
key=lambda r: (r.get("activity_count") or 0, r.get("last_activity_at") or ""),
|
||||
)[:5]
|
||||
if least_active:
|
||||
print("\nleast active (top 5):")
|
||||
for r in least_active:
|
||||
last = _fmt_ts(r.get("last_activity_at"))
|
||||
print(
|
||||
f" {r['name']:40s} "
|
||||
f"activity={r.get('activity_count', 0):3d} "
|
||||
f"use={r.get('use_count', 0):3d} "
|
||||
f"view={r.get('view_count', 0):3d} "
|
||||
f"patches={r.get('patch_count', 0):3d} "
|
||||
f"last_activity={last}"
|
||||
)
|
||||
|
||||
return 0
|
||||
|
||||
|
||||
@@ -160,11 +117,7 @@ def _cmd_run(args) -> int:
|
||||
print("curator: disabled via config; enable with `curator.enabled: true`")
|
||||
return 1
|
||||
|
||||
dry = bool(getattr(args, "dry_run", False))
|
||||
if dry:
|
||||
print("curator: running DRY-RUN (report only, no mutations)...")
|
||||
else:
|
||||
print("curator: running review pass...")
|
||||
print("curator: running review pass...")
|
||||
|
||||
def _on_summary(msg: str) -> None:
|
||||
print(msg)
|
||||
@@ -172,29 +125,17 @@ def _cmd_run(args) -> int:
|
||||
result = curator.run_curator_review(
|
||||
on_summary=_on_summary,
|
||||
synchronous=bool(args.synchronous),
|
||||
dry_run=dry,
|
||||
)
|
||||
auto = result.get("auto_transitions", {})
|
||||
if auto:
|
||||
if dry:
|
||||
print(
|
||||
f"auto (preview): {auto.get('checked', 0)} candidate skill(s) "
|
||||
"— no transitions applied in dry-run"
|
||||
)
|
||||
else:
|
||||
print(
|
||||
f"auto: checked={auto.get('checked', 0)} "
|
||||
f"stale={auto.get('marked_stale', 0)} "
|
||||
f"archived={auto.get('archived', 0)} "
|
||||
f"reactivated={auto.get('reactivated', 0)}"
|
||||
)
|
||||
print(
|
||||
f"auto: checked={auto.get('checked', 0)} "
|
||||
f"stale={auto.get('marked_stale', 0)} "
|
||||
f"archived={auto.get('archived', 0)} "
|
||||
f"reactivated={auto.get('reactivated', 0)}"
|
||||
)
|
||||
if not args.synchronous:
|
||||
print("llm pass running in background — check `hermes curator status` later")
|
||||
if dry:
|
||||
print(
|
||||
"dry-run: no changes applied. When the report lands, read it with "
|
||||
"`hermes curator status` and run `hermes curator run` (no flag) to apply."
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
@@ -245,98 +186,6 @@ def _cmd_restore(args) -> int:
|
||||
return 0 if ok else 1
|
||||
|
||||
|
||||
def _cmd_backup(args) -> int:
|
||||
"""Take a manual snapshot of the skills tree. Same mechanism as the
|
||||
automatic pre-run snapshot, just user-initiated."""
|
||||
from agent import curator_backup
|
||||
if not curator_backup.is_enabled():
|
||||
print(
|
||||
"curator: backups are disabled via config "
|
||||
"(`curator.backup.enabled: false`); re-enable to snapshot"
|
||||
)
|
||||
return 1
|
||||
reason = getattr(args, "reason", None) or "manual"
|
||||
snap = curator_backup.snapshot_skills(reason=reason)
|
||||
if snap is None:
|
||||
print("curator: snapshot failed — check logs (backup disabled or IO error)")
|
||||
return 1
|
||||
print(f"curator: snapshot created at ~/.hermes/skills/.curator_backups/{snap.name}")
|
||||
return 0
|
||||
|
||||
|
||||
def _cmd_rollback(args) -> int:
|
||||
"""Restore the skills tree from a snapshot. Defaults to newest.
|
||||
|
||||
``--list`` prints available snapshots and exits. ``--id <stamp>`` picks
|
||||
a specific one. Without ``-y``, prompts for confirmation. A safety
|
||||
snapshot of the current tree is always taken first, so rollbacks are
|
||||
themselves undoable.
|
||||
"""
|
||||
from agent import curator_backup
|
||||
|
||||
if getattr(args, "list", False):
|
||||
print(curator_backup.summarize_backups())
|
||||
return 0
|
||||
|
||||
backup_id = getattr(args, "backup_id", None)
|
||||
target_path = curator_backup._resolve_backup(backup_id)
|
||||
if target_path is None:
|
||||
rows = curator_backup.list_backups()
|
||||
if not rows:
|
||||
print(
|
||||
"curator: no snapshots exist yet. Take one with "
|
||||
"`hermes curator backup` or wait for the next curator run."
|
||||
)
|
||||
else:
|
||||
print(
|
||||
f"curator: no snapshot matching "
|
||||
f"{'id ' + repr(backup_id) if backup_id else 'your query'}."
|
||||
)
|
||||
print("Available:")
|
||||
print(curator_backup.summarize_backups())
|
||||
return 1
|
||||
|
||||
manifest = curator_backup._read_manifest(target_path)
|
||||
print(f"Rollback target: {target_path.name}")
|
||||
if manifest:
|
||||
print(f" reason: {manifest.get('reason', '?')}")
|
||||
print(f" created_at: {manifest.get('created_at', '?')}")
|
||||
print(f" skill files: {manifest.get('skill_files', '?')}")
|
||||
cron = manifest.get("cron_jobs") or {}
|
||||
if isinstance(cron, dict):
|
||||
if cron.get("backed_up"):
|
||||
print(
|
||||
f" cron jobs: {cron.get('jobs_count', 0)} "
|
||||
f"(will be restored for skill-link fields only)"
|
||||
)
|
||||
else:
|
||||
reason = cron.get("reason", "not captured")
|
||||
print(f" cron jobs: not in snapshot ({reason})")
|
||||
print(
|
||||
"\nThis will replace the current ~/.hermes/skills/ tree (a safety "
|
||||
"snapshot of the current state is taken first so this is undoable). "
|
||||
"Cron jobs that still exist will have their skills/skill fields "
|
||||
"restored from the snapshot; all other cron fields are left alone."
|
||||
)
|
||||
|
||||
if not getattr(args, "yes", False):
|
||||
try:
|
||||
ans = input("Proceed? [y/N] ").strip().lower()
|
||||
except (EOFError, KeyboardInterrupt):
|
||||
print("\ncancelled")
|
||||
return 1
|
||||
if ans not in ("y", "yes"):
|
||||
print("cancelled")
|
||||
return 1
|
||||
|
||||
ok, msg, _ = curator_backup.rollback(backup_id=target_path.name)
|
||||
if ok:
|
||||
print(f"curator: {msg}")
|
||||
return 0
|
||||
print(f"curator: rollback failed — {msg}")
|
||||
return 1
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# argparse wiring (called from hermes_cli.main)
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -358,11 +207,6 @@ def register_cli(parent: argparse.ArgumentParser) -> None:
|
||||
"--sync", "--synchronous", dest="synchronous", action="store_true",
|
||||
help="Wait for the LLM review pass to finish (default: background thread)",
|
||||
)
|
||||
p_run.add_argument(
|
||||
"--dry-run", dest="dry_run", action="store_true",
|
||||
help="Report only — no state changes, no archives, no consolidation "
|
||||
"(use this to preview what curator would do)",
|
||||
)
|
||||
p_run.set_defaults(func=_cmd_run)
|
||||
|
||||
p_pause = subs.add_parser("pause", help="Pause the curator until resumed")
|
||||
@@ -383,36 +227,6 @@ def register_cli(parent: argparse.ArgumentParser) -> None:
|
||||
p_restore.add_argument("skill", help="Skill name")
|
||||
p_restore.set_defaults(func=_cmd_restore)
|
||||
|
||||
p_backup = subs.add_parser(
|
||||
"backup",
|
||||
help="Take a manual tar.gz snapshot of ~/.hermes/skills/ "
|
||||
"(curator also does this automatically before every real run)",
|
||||
)
|
||||
p_backup.add_argument(
|
||||
"--reason", default=None,
|
||||
help="Free-text label stored in manifest.json (default: 'manual')",
|
||||
)
|
||||
p_backup.set_defaults(func=_cmd_backup)
|
||||
|
||||
p_rollback = subs.add_parser(
|
||||
"rollback",
|
||||
help="Restore ~/.hermes/skills/ from a curator snapshot "
|
||||
"(defaults to the newest)",
|
||||
)
|
||||
p_rollback.add_argument(
|
||||
"--list", action="store_true",
|
||||
help="List available snapshots and exit without restoring",
|
||||
)
|
||||
p_rollback.add_argument(
|
||||
"--id", dest="backup_id", default=None,
|
||||
help="Snapshot id to restore (see `--list`); default: newest",
|
||||
)
|
||||
p_rollback.add_argument(
|
||||
"-y", "--yes", action="store_true",
|
||||
help="Skip confirmation prompt",
|
||||
)
|
||||
p_rollback.set_defaults(func=_cmd_rollback)
|
||||
|
||||
|
||||
def cli_main(argv=None) -> int:
|
||||
"""Standalone entry (also usable by hermes_cli.main fallthrough)."""
|
||||
|
||||
@@ -156,8 +156,6 @@ def curses_checklist(
|
||||
flush_stdin()
|
||||
return result_holder[0] if result_holder[0] is not None else cancel_returns
|
||||
|
||||
except KeyboardInterrupt:
|
||||
return cancel_returns
|
||||
except Exception:
|
||||
return _numbered_fallback(title, items, selected, cancel_returns, status_fn)
|
||||
|
||||
@@ -280,8 +278,6 @@ def curses_radiolist(
|
||||
flush_stdin()
|
||||
return result_holder[0] if result_holder[0] is not None else cancel_returns
|
||||
|
||||
except KeyboardInterrupt:
|
||||
return cancel_returns
|
||||
except Exception:
|
||||
return _radio_numbered_fallback(title, items, selected, cancel_returns)
|
||||
|
||||
@@ -405,8 +401,6 @@ def curses_single_select(
|
||||
return None
|
||||
return result_holder[0]
|
||||
|
||||
except KeyboardInterrupt:
|
||||
return None
|
||||
except Exception:
|
||||
all_items = list(items) + [cancel_label]
|
||||
cancel_idx = len(items)
|
||||
|
||||
+7
-82
@@ -1,19 +1,12 @@
|
||||
"""``hermes debug`` debug tools for Hermes Agent.
|
||||
"""``hermes debug`` — debug tools for Hermes Agent.
|
||||
|
||||
Currently supports:
|
||||
hermes debug share Upload debug report (system info + logs) to a
|
||||
paste service and print a shareable URL.
|
||||
By default, log content is run through
|
||||
``agent.redact.redact_sensitive_text`` with
|
||||
``force=True`` before upload so credentials in
|
||||
``~/.hermes/logs/*.log`` are not leaked into
|
||||
the public paste service. Pass ``--no-redact``
|
||||
to disable.
|
||||
"""
|
||||
|
||||
import io
|
||||
import json
|
||||
import logging
|
||||
import sys
|
||||
import time
|
||||
import urllib.error
|
||||
@@ -26,16 +19,6 @@ from typing import Optional
|
||||
from hermes_constants import get_hermes_home
|
||||
from utils import atomic_replace
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Banner prepended to upload-bound log content when redaction is enabled.
|
||||
# Visible in the public paste so reviewers know the content was sanitized.
|
||||
# Kept short; the trailing newline guarantees the banner sits on its own line.
|
||||
_REDACTION_BANNER = (
|
||||
"[hermes debug share: log content redacted at upload time. "
|
||||
"run with --no-redact to disable]\n"
|
||||
)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Paste services — try paste.rs first, dpaste.com as fallback.
|
||||
@@ -385,40 +368,17 @@ def _resolve_log_path(log_name: str) -> Optional[Path]:
|
||||
return None
|
||||
|
||||
|
||||
def _redact_log_text(text: str) -> str:
|
||||
"""Run ``redact_sensitive_text`` with ``force=True`` over upload-bound text.
|
||||
|
||||
Uses ``force=True`` so redaction fires regardless of the operator's
|
||||
``security.redact_secrets`` setting. The local on-disk log file is
|
||||
not modified; only the in-memory copy headed for the public paste
|
||||
service is sanitized. Returns the redacted text (or the original
|
||||
when empty / non-string).
|
||||
"""
|
||||
if not text:
|
||||
return text
|
||||
from agent.redact import redact_sensitive_text
|
||||
|
||||
return redact_sensitive_text(text, force=True)
|
||||
|
||||
|
||||
def _capture_log_snapshot(
|
||||
log_name: str,
|
||||
*,
|
||||
tail_lines: int,
|
||||
max_bytes: int = _MAX_LOG_BYTES,
|
||||
redact: bool = True,
|
||||
) -> LogSnapshot:
|
||||
"""Capture a log once and derive summary/full-log views from it.
|
||||
|
||||
The report tail and standalone log upload must come from the same file
|
||||
snapshot. Otherwise a rotation/truncate between reads can make the report
|
||||
look newer than the uploaded ``agent.log`` paste.
|
||||
|
||||
When ``redact`` is True (the default), both ``tail_text`` and
|
||||
``full_text`` are run through ``_redact_log_text`` so the snapshot
|
||||
returned is upload-safe. The on-disk log file is never modified.
|
||||
Pass ``redact=False`` to capture original log content (used by
|
||||
``hermes debug share --no-redact``).
|
||||
"""
|
||||
log_path = _resolve_log_path(log_name)
|
||||
if log_path is None:
|
||||
@@ -478,34 +438,18 @@ def _capture_log_snapshot(
|
||||
if truncated:
|
||||
full_text = f"[... truncated — showing last ~{max_bytes // 1024}KB ...]\n{full_text}"
|
||||
|
||||
if redact:
|
||||
tail_text = _redact_log_text(tail_text)
|
||||
full_text = _redact_log_text(full_text)
|
||||
|
||||
return LogSnapshot(path=log_path, tail_text=tail_text, full_text=full_text)
|
||||
except Exception as exc:
|
||||
return LogSnapshot(path=log_path, tail_text=f"(error reading: {exc})", full_text=None)
|
||||
|
||||
|
||||
def _capture_default_log_snapshots(
|
||||
log_lines: int, *, redact: bool = True
|
||||
) -> dict[str, LogSnapshot]:
|
||||
"""Capture all logs used by debug-share exactly once.
|
||||
|
||||
``redact`` is forwarded to each ``_capture_log_snapshot`` call so all
|
||||
captured logs share the same redaction policy for a given run.
|
||||
"""
|
||||
def _capture_default_log_snapshots(log_lines: int) -> dict[str, LogSnapshot]:
|
||||
"""Capture all logs used by debug-share exactly once."""
|
||||
errors_lines = min(log_lines, 100)
|
||||
return {
|
||||
"agent": _capture_log_snapshot(
|
||||
"agent", tail_lines=log_lines, redact=redact
|
||||
),
|
||||
"errors": _capture_log_snapshot(
|
||||
"errors", tail_lines=errors_lines, redact=redact
|
||||
),
|
||||
"gateway": _capture_log_snapshot(
|
||||
"gateway", tail_lines=errors_lines, redact=redact
|
||||
),
|
||||
"agent": _capture_log_snapshot("agent", tail_lines=log_lines),
|
||||
"errors": _capture_log_snapshot("errors", tail_lines=errors_lines),
|
||||
"gateway": _capture_log_snapshot("gateway", tail_lines=errors_lines),
|
||||
}
|
||||
|
||||
|
||||
@@ -588,7 +532,6 @@ def run_debug_share(args):
|
||||
log_lines = getattr(args, "lines", 200)
|
||||
expiry = getattr(args, "expire", 7)
|
||||
local_only = getattr(args, "local", False)
|
||||
redact = not getattr(args, "no_redact", False)
|
||||
|
||||
if not local_only:
|
||||
print(_PRIVACY_NOTICE)
|
||||
@@ -596,16 +539,8 @@ def run_debug_share(args):
|
||||
print("Collecting debug report...")
|
||||
|
||||
# Capture dump once — prepended to every paste for context.
|
||||
# The dump is already redacted at extract time via dump.py:_redact;
|
||||
# log_snapshots are redacted by _capture_default_log_snapshots when
|
||||
# redact=True so credentials never reach the public paste service.
|
||||
dump_text = _capture_dump()
|
||||
log_snapshots = _capture_default_log_snapshots(log_lines, redact=redact)
|
||||
|
||||
if redact:
|
||||
logger.info(
|
||||
"hermes debug share: applied force-mode redaction to log snapshots before upload"
|
||||
)
|
||||
log_snapshots = _capture_default_log_snapshots(log_lines)
|
||||
|
||||
report = collect_debug_report(
|
||||
log_lines=log_lines,
|
||||
@@ -621,15 +556,6 @@ def run_debug_share(args):
|
||||
if gateway_log:
|
||||
gateway_log = dump_text + "\n\n--- full gateway.log ---\n" + gateway_log
|
||||
|
||||
# Visible banner so reviewers reading the public paste know redaction
|
||||
# was applied at upload time. Banner is omitted under --no-redact.
|
||||
if redact:
|
||||
report = _REDACTION_BANNER + report
|
||||
if agent_log:
|
||||
agent_log = _REDACTION_BANNER + agent_log
|
||||
if gateway_log:
|
||||
gateway_log = _REDACTION_BANNER + gateway_log
|
||||
|
||||
if local_only:
|
||||
print(report)
|
||||
if agent_log:
|
||||
@@ -740,7 +666,6 @@ def run_debug(args):
|
||||
print(" --lines N Number of log lines to include (default: 200)")
|
||||
print(" --expire N Paste expiry in days (default: 7)")
|
||||
print(" --local Print report locally instead of uploading")
|
||||
print(" --no-redact Disable upload-time secret redaction (default: redact)")
|
||||
print()
|
||||
print("Options (delete):")
|
||||
print(" <url> ... One or more paste URLs to delete")
|
||||
|
||||
@@ -263,11 +263,8 @@ def run_doctor(args):
|
||||
if env_path.exists():
|
||||
check_ok(f"{_DHH}/.env file exists")
|
||||
|
||||
# Check for common issues. Pin encoding to UTF-8 because .env files are
|
||||
# written as UTF-8 everywhere in the codebase, while Path.read_text()
|
||||
# defaults to the system locale — which crashes on non-UTF-8 Windows
|
||||
# locales (e.g. GBK) as soon as the file contains any non-ASCII byte.
|
||||
content = env_path.read_text(encoding="utf-8")
|
||||
# Check for common issues
|
||||
content = env_path.read_text()
|
||||
if _has_provider_env_config(content):
|
||||
check_ok("API key or custom endpoint configured")
|
||||
else:
|
||||
|
||||
+12
-153
@@ -10,7 +10,6 @@ import shutil
|
||||
import signal
|
||||
import subprocess
|
||||
import sys
|
||||
import textwrap
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
@@ -60,13 +59,6 @@ class GatewayRuntimeSnapshot:
|
||||
def has_process_service_mismatch(self) -> bool:
|
||||
return self.service_installed and self.running and not self.service_running
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ProfileGatewayProcess:
|
||||
profile: str
|
||||
path: Path
|
||||
pid: int
|
||||
|
||||
def _get_service_pids() -> set:
|
||||
"""Return PIDs currently managed by systemd or launchd gateway services.
|
||||
|
||||
@@ -188,7 +180,7 @@ def _graceful_restart_via_sigusr1(pid: int, drain_timeout: float) -> bool:
|
||||
|
||||
SIGUSR1 is wired in gateway/run.py to ``request_restart(via_service=True)``
|
||||
which drains in-flight agent runs (up to ``agent.restart_drain_timeout``
|
||||
seconds), then exits with code 75. Both systemd (``Restart=always``
|
||||
seconds), then exits with code 75. Both systemd (``Restart=on-failure``
|
||||
+ ``RestartForceExitStatus=75``) and launchd (``KeepAlive.SuccessfulExit
|
||||
= false``) relaunch the process after the graceful exit.
|
||||
|
||||
@@ -237,26 +229,6 @@ def _graceful_restart_via_sigusr1(pid: int, drain_timeout: float) -> bool:
|
||||
return False
|
||||
|
||||
|
||||
def _get_ancestor_pids() -> set[int]:
|
||||
"""Return the set of PIDs in the current process's ancestor chain.
|
||||
|
||||
Walks from the current PID up to PID 1 (init) so that process-table scans
|
||||
never match the calling CLI process or any of its parents. This prevents
|
||||
``hermes gateway status`` from falsely counting the ``hermes`` CLI that
|
||||
invoked it as a running gateway instance (see #13242).
|
||||
"""
|
||||
ancestors: set[int] = set()
|
||||
pid = os.getpid()
|
||||
# Cap iterations to avoid infinite loops on exotic platforms.
|
||||
for _ in range(64):
|
||||
ancestors.add(pid)
|
||||
parent = _get_parent_pid(pid)
|
||||
if parent is None or parent <= 0 or parent in ancestors:
|
||||
break
|
||||
pid = parent
|
||||
return ancestors
|
||||
|
||||
|
||||
def _append_unique_pid(pids: list[int], pid: int | None, exclude_pids: set[int]) -> None:
|
||||
if pid is None or pid <= 0:
|
||||
return
|
||||
@@ -272,10 +244,6 @@ def _scan_gateway_pids(exclude_pids: set[int], all_profiles: bool = False) -> li
|
||||
a live gateway when the PID file is stale/missing, and ``--all`` sweeps can
|
||||
discover gateways outside the current profile.
|
||||
"""
|
||||
# Exclude the entire ancestor chain so the CLI process that invoked this
|
||||
# scan (e.g. ``hermes gateway status``) is never mistaken for a running
|
||||
# gateway. See #13242.
|
||||
exclude_pids = exclude_pids | _get_ancestor_pids()
|
||||
pids: list[int] = []
|
||||
patterns = [
|
||||
"hermes_cli.main gateway",
|
||||
@@ -403,83 +371,6 @@ def find_gateway_pids(exclude_pids: set | None = None, all_profiles: bool = Fals
|
||||
return pids
|
||||
|
||||
|
||||
def find_profile_gateway_processes(
|
||||
exclude_pids: set | None = None,
|
||||
) -> list[ProfileGatewayProcess]:
|
||||
"""Return running gateway PIDs mapped to Hermes profiles via PID files."""
|
||||
_exclude = set(exclude_pids or set())
|
||||
processes: list[ProfileGatewayProcess] = []
|
||||
try:
|
||||
from gateway.status import get_running_pid
|
||||
from hermes_cli.profiles import list_profiles
|
||||
except Exception:
|
||||
return processes
|
||||
|
||||
seen: set[int] = set()
|
||||
for profile in list_profiles():
|
||||
try:
|
||||
pid = get_running_pid(profile.path / "gateway.pid", cleanup_stale=False)
|
||||
except Exception:
|
||||
continue
|
||||
if pid is None or pid <= 0 or pid in _exclude or pid in seen:
|
||||
continue
|
||||
seen.add(pid)
|
||||
processes.append(ProfileGatewayProcess(profile=profile.name, path=profile.path, pid=pid))
|
||||
return processes
|
||||
|
||||
|
||||
def _gateway_run_args_for_profile(profile: str) -> list[str]:
|
||||
args = [get_python_path(), "-m", "hermes_cli.main"]
|
||||
if profile != "default":
|
||||
args.extend(["--profile", profile])
|
||||
args.extend(["gateway", "run", "--replace"])
|
||||
return args
|
||||
|
||||
|
||||
def launch_detached_profile_gateway_restart(profile: str, old_pid: int) -> bool:
|
||||
"""Relaunch a manually-run profile gateway after its current PID exits."""
|
||||
if old_pid <= 0:
|
||||
return False
|
||||
|
||||
watcher = textwrap.dedent(
|
||||
"""
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
|
||||
pid = int(sys.argv[1])
|
||||
cmd = sys.argv[2:]
|
||||
deadline = time.monotonic() + 120
|
||||
while time.monotonic() < deadline:
|
||||
try:
|
||||
os.kill(pid, 0)
|
||||
except ProcessLookupError:
|
||||
break
|
||||
except PermissionError:
|
||||
pass
|
||||
time.sleep(0.2)
|
||||
subprocess.Popen(
|
||||
cmd,
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL,
|
||||
start_new_session=True,
|
||||
)
|
||||
"""
|
||||
).strip()
|
||||
|
||||
try:
|
||||
subprocess.Popen(
|
||||
[sys.executable, "-c", watcher, str(old_pid), *_gateway_run_args_for_profile(profile)],
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL,
|
||||
start_new_session=True,
|
||||
)
|
||||
except OSError:
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def _probe_systemd_service_running(system: bool = False) -> tuple[bool, bool]:
|
||||
selected_system = _select_systemd_scope(system)
|
||||
unit_exists = get_systemd_unit_path(system=selected_system).exists()
|
||||
@@ -714,32 +605,6 @@ def _print_gateway_process_mismatch(snapshot: GatewayRuntimeSnapshot) -> None:
|
||||
print(" can refuse to start another copy until this process stops.")
|
||||
|
||||
|
||||
def _print_other_profiles_gateway_status() -> None:
|
||||
"""Print a summary of gateway status across all profiles.
|
||||
|
||||
Shown at the bottom of ``hermes gateway status`` output so users with
|
||||
multiple profiles can tell at a glance which gateways are running and
|
||||
avoid confusing another profile's process with the current one.
|
||||
"""
|
||||
try:
|
||||
from hermes_cli.profiles import get_active_profile_name
|
||||
|
||||
current = get_active_profile_name()
|
||||
other_processes = [
|
||||
p for p in find_profile_gateway_processes()
|
||||
if p.profile != current
|
||||
]
|
||||
if not other_processes:
|
||||
return
|
||||
|
||||
print()
|
||||
print("Other profiles:")
|
||||
for proc in other_processes:
|
||||
print(f" ✓ {proc.profile:<16s} — PID {proc.pid}")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def kill_gateway_processes(force: bool = False, exclude_pids: set | None = None,
|
||||
all_profiles: bool = False) -> int:
|
||||
"""Kill any running gateway processes. Returns count killed.
|
||||
@@ -1705,7 +1570,8 @@ def generate_systemd_unit(system: bool = False, run_as_user: str | None = None)
|
||||
Description={SERVICE_DESCRIPTION}
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
StartLimitIntervalSec=0
|
||||
StartLimitIntervalSec=600
|
||||
StartLimitBurst=5
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
@@ -1719,10 +1585,8 @@ Environment="LOGNAME={username}"
|
||||
Environment="PATH={sane_path}"
|
||||
Environment="VIRTUAL_ENV={venv_dir}"
|
||||
Environment="HERMES_HOME={hermes_home}"
|
||||
Restart=always
|
||||
RestartSec=60
|
||||
RestartMaxDelaySec=300
|
||||
RestartSteps=5
|
||||
Restart=on-failure
|
||||
RestartSec=30
|
||||
RestartForceExitStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}
|
||||
KillMode=mixed
|
||||
KillSignal=SIGTERM
|
||||
@@ -1742,9 +1606,9 @@ WantedBy=multi-user.target
|
||||
sane_path = ":".join(path_entries)
|
||||
return f"""[Unit]
|
||||
Description={SERVICE_DESCRIPTION}
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
StartLimitIntervalSec=0
|
||||
After=network.target
|
||||
StartLimitIntervalSec=600
|
||||
StartLimitBurst=5
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
@@ -1753,10 +1617,8 @@ WorkingDirectory={working_dir}
|
||||
Environment="PATH={sane_path}"
|
||||
Environment="VIRTUAL_ENV={venv_dir}"
|
||||
Environment="HERMES_HOME={hermes_home}"
|
||||
Restart=always
|
||||
RestartSec=60
|
||||
RestartMaxDelaySec=300
|
||||
RestartSteps=5
|
||||
Restart=on-failure
|
||||
RestartSec=30
|
||||
RestartForceExitStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}
|
||||
KillMode=mixed
|
||||
KillSignal=SIGTERM
|
||||
@@ -2504,7 +2366,7 @@ def run_gateway(verbose: int = 0, quiet: bool = False, replace: bool = False):
|
||||
print()
|
||||
|
||||
# Exit with code 1 if gateway fails to connect any platform,
|
||||
# so systemd Restart=always will retry on transient errors
|
||||
# so systemd Restart=on-failure will retry on transient errors
|
||||
verbosity = None if quiet else verbose
|
||||
try:
|
||||
success = asyncio.run(start_gateway(replace=replace, verbosity=verbosity))
|
||||
@@ -4506,9 +4368,6 @@ def _gateway_command_inner(args):
|
||||
print(" hermes gateway install # Install as user service")
|
||||
print(" sudo hermes gateway install --system # Install as boot-time system service")
|
||||
|
||||
# Show other profiles' gateway status for multi-profile awareness
|
||||
_print_other_profiles_gateway_status()
|
||||
|
||||
elif subcmd == "migrate-legacy":
|
||||
# Stop, disable, and remove legacy Hermes gateway unit files from
|
||||
# pre-rename installs (e.g. hermes.service). Profile units and
|
||||
@@ -4518,4 +4377,4 @@ def _gateway_command_inner(args):
|
||||
if not supports_systemd_services() and not is_macos():
|
||||
print("Legacy unit migration only applies to systemd-based Linux hosts.")
|
||||
return
|
||||
remove_legacy_hermes_units(interactive=not yes, dry_run=dry_run)
|
||||
remove_legacy_hermes_units(interactive=not yes, dry_run=dry_run)
|
||||
@@ -1,535 +0,0 @@
|
||||
"""Persistent session goals — the Ralph loop for Hermes.
|
||||
|
||||
A goal is a free-form user objective that stays active across turns. After
|
||||
each turn completes, a small judge call asks an auxiliary model "is this
|
||||
goal satisfied by the assistant's last response?". If not, Hermes feeds a
|
||||
continuation prompt back into the same session and keeps working until the
|
||||
goal is done, turn budget is exhausted, the user pauses/clears it, or the
|
||||
user sends a new message (which takes priority and pauses the goal loop).
|
||||
|
||||
State is persisted in SessionDB's ``state_meta`` table keyed by
|
||||
``goal:<session_id>`` so ``/resume`` picks it up.
|
||||
|
||||
Design notes / invariants:
|
||||
|
||||
- The continuation prompt is just a normal user message appended to the
|
||||
session via ``run_conversation``. No system-prompt mutation, no toolset
|
||||
swap — prompt caching stays intact.
|
||||
- Judge failures are fail-OPEN: ``continue``. A broken judge must not wedge
|
||||
progress; the turn budget is the backstop.
|
||||
- When a real user message arrives mid-loop it preempts the continuation
|
||||
prompt and also pauses the goal loop for that turn (we still re-judge
|
||||
after, so if the user's message happens to complete the goal the judge
|
||||
will say ``done``).
|
||||
- This module has zero hard dependency on ``cli.HermesCLI`` or the gateway
|
||||
runner — both wire the same ``GoalManager`` in.
|
||||
|
||||
Nothing in this module touches the agent's system prompt or toolset.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
import time
|
||||
from dataclasses import dataclass, asdict
|
||||
from typing import Any, Dict, Optional, Tuple
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
# ──────────────────────────────────────────────────────────────────────
|
||||
# Constants & defaults
|
||||
# ──────────────────────────────────────────────────────────────────────
|
||||
|
||||
DEFAULT_MAX_TURNS = 20
|
||||
DEFAULT_JUDGE_TIMEOUT = 30.0
|
||||
# Cap how much of the last response + recent messages we send to the judge.
|
||||
_JUDGE_RESPONSE_SNIPPET_CHARS = 4000
|
||||
|
||||
|
||||
CONTINUATION_PROMPT_TEMPLATE = (
|
||||
"[Continuing toward your standing goal]\n"
|
||||
"Goal: {goal}\n\n"
|
||||
"Continue working toward this goal. Take the next concrete step. "
|
||||
"If you believe the goal is complete, state so explicitly and stop. "
|
||||
"If you are blocked and need input from the user, say so clearly and stop."
|
||||
)
|
||||
|
||||
|
||||
JUDGE_SYSTEM_PROMPT = (
|
||||
"You are a strict judge evaluating whether an autonomous agent has "
|
||||
"achieved a user's stated goal. You receive the goal text and the "
|
||||
"agent's most recent response. Your only job is to decide whether "
|
||||
"the goal is fully satisfied based on that response.\n\n"
|
||||
"A goal is DONE only when:\n"
|
||||
"- The response explicitly confirms the goal was completed, OR\n"
|
||||
"- The response clearly shows the final deliverable was produced, OR\n"
|
||||
"- The response explains the goal is unachievable / blocked / needs "
|
||||
"user input (treat this as DONE with reason describing the block).\n\n"
|
||||
"Otherwise the goal is NOT done — CONTINUE.\n\n"
|
||||
"Reply ONLY with a single JSON object on one line:\n"
|
||||
'{\"done\": <true|false>, \"reason\": \"<one-sentence rationale>\"}'
|
||||
)
|
||||
|
||||
|
||||
JUDGE_USER_PROMPT_TEMPLATE = (
|
||||
"Goal:\n{goal}\n\n"
|
||||
"Agent's most recent response:\n{response}\n\n"
|
||||
"Is the goal satisfied?"
|
||||
)
|
||||
|
||||
|
||||
# ──────────────────────────────────────────────────────────────────────
|
||||
# Dataclass
|
||||
# ──────────────────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
@dataclass
|
||||
class GoalState:
|
||||
"""Serializable goal state stored per session."""
|
||||
|
||||
goal: str
|
||||
status: str = "active" # active | paused | done | cleared
|
||||
turns_used: int = 0
|
||||
max_turns: int = DEFAULT_MAX_TURNS
|
||||
created_at: float = 0.0
|
||||
last_turn_at: float = 0.0
|
||||
last_verdict: Optional[str] = None # "done" | "continue" | "skipped"
|
||||
last_reason: Optional[str] = None
|
||||
paused_reason: Optional[str] = None # why we auto-paused (budget, etc.)
|
||||
|
||||
def to_json(self) -> str:
|
||||
return json.dumps(asdict(self), ensure_ascii=False)
|
||||
|
||||
@classmethod
|
||||
def from_json(cls, raw: str) -> "GoalState":
|
||||
data = json.loads(raw)
|
||||
return cls(
|
||||
goal=data.get("goal", ""),
|
||||
status=data.get("status", "active"),
|
||||
turns_used=int(data.get("turns_used", 0) or 0),
|
||||
max_turns=int(data.get("max_turns", DEFAULT_MAX_TURNS) or DEFAULT_MAX_TURNS),
|
||||
created_at=float(data.get("created_at", 0.0) or 0.0),
|
||||
last_turn_at=float(data.get("last_turn_at", 0.0) or 0.0),
|
||||
last_verdict=data.get("last_verdict"),
|
||||
last_reason=data.get("last_reason"),
|
||||
paused_reason=data.get("paused_reason"),
|
||||
)
|
||||
|
||||
|
||||
# ──────────────────────────────────────────────────────────────────────
|
||||
# Persistence (SessionDB state_meta)
|
||||
# ──────────────────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
def _meta_key(session_id: str) -> str:
|
||||
return f"goal:{session_id}"
|
||||
|
||||
|
||||
_DB_CACHE: Dict[str, Any] = {}
|
||||
|
||||
|
||||
def _get_session_db() -> Optional[Any]:
|
||||
"""Return a SessionDB instance for the current HERMES_HOME.
|
||||
|
||||
SessionDB has no built-in singleton, but opening a new connection per
|
||||
/goal call would thrash the file. We cache one instance per
|
||||
``hermes_home`` path so profile switches still pick up the right DB.
|
||||
Defensive against import/instantiation failures so tests and
|
||||
non-standard launchers can still use the GoalManager.
|
||||
"""
|
||||
try:
|
||||
from hermes_constants import get_hermes_home
|
||||
from hermes_state import SessionDB
|
||||
|
||||
home = str(get_hermes_home())
|
||||
except Exception as exc: # pragma: no cover
|
||||
logger.debug("GoalManager: SessionDB bootstrap failed (%s)", exc)
|
||||
return None
|
||||
|
||||
cached = _DB_CACHE.get(home)
|
||||
if cached is not None:
|
||||
return cached
|
||||
try:
|
||||
db = SessionDB()
|
||||
except Exception as exc: # pragma: no cover
|
||||
logger.debug("GoalManager: SessionDB() raised (%s)", exc)
|
||||
return None
|
||||
_DB_CACHE[home] = db
|
||||
return db
|
||||
|
||||
|
||||
def load_goal(session_id: str) -> Optional[GoalState]:
|
||||
"""Load the goal for a session, or None if none exists."""
|
||||
if not session_id:
|
||||
return None
|
||||
db = _get_session_db()
|
||||
if db is None:
|
||||
return None
|
||||
try:
|
||||
raw = db.get_meta(_meta_key(session_id))
|
||||
except Exception as exc:
|
||||
logger.debug("GoalManager: get_meta failed: %s", exc)
|
||||
return None
|
||||
if not raw:
|
||||
return None
|
||||
try:
|
||||
return GoalState.from_json(raw)
|
||||
except Exception as exc:
|
||||
logger.warning("GoalManager: could not parse stored goal for %s: %s", session_id, exc)
|
||||
return None
|
||||
|
||||
|
||||
def save_goal(session_id: str, state: GoalState) -> None:
|
||||
"""Persist a goal to SessionDB. No-op if DB unavailable."""
|
||||
if not session_id:
|
||||
return
|
||||
db = _get_session_db()
|
||||
if db is None:
|
||||
return
|
||||
try:
|
||||
db.set_meta(_meta_key(session_id), state.to_json())
|
||||
except Exception as exc:
|
||||
logger.debug("GoalManager: set_meta failed: %s", exc)
|
||||
|
||||
|
||||
def clear_goal(session_id: str) -> None:
|
||||
"""Mark a goal cleared in the DB (preserved for audit, status=cleared)."""
|
||||
state = load_goal(session_id)
|
||||
if state is None:
|
||||
return
|
||||
state.status = "cleared"
|
||||
save_goal(session_id, state)
|
||||
|
||||
|
||||
# ──────────────────────────────────────────────────────────────────────
|
||||
# Judge
|
||||
# ──────────────────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
def _truncate(text: str, limit: int) -> str:
|
||||
if not text:
|
||||
return ""
|
||||
if len(text) <= limit:
|
||||
return text
|
||||
return text[:limit] + "… [truncated]"
|
||||
|
||||
|
||||
_JSON_OBJECT_RE = re.compile(r"\{.*?\}", re.DOTALL)
|
||||
|
||||
|
||||
def _parse_judge_response(raw: str) -> Tuple[bool, str]:
|
||||
"""Parse the judge's reply. Fail-open to ``(False, "<reason>")``.
|
||||
|
||||
Returns ``(done, reason)``.
|
||||
"""
|
||||
if not raw:
|
||||
return False, "judge returned empty response"
|
||||
|
||||
text = raw.strip()
|
||||
|
||||
# Strip markdown code fences the model may wrap JSON in.
|
||||
if text.startswith("```"):
|
||||
text = text.strip("`")
|
||||
# Peel off leading json/JSON/etc tag
|
||||
nl = text.find("\n")
|
||||
if nl != -1:
|
||||
text = text[nl + 1:]
|
||||
|
||||
# First try: parse the whole blob.
|
||||
data: Optional[Dict[str, Any]] = None
|
||||
try:
|
||||
data = json.loads(text)
|
||||
except Exception:
|
||||
# Second try: pull the first JSON object out.
|
||||
match = _JSON_OBJECT_RE.search(text)
|
||||
if match:
|
||||
try:
|
||||
data = json.loads(match.group(0))
|
||||
except Exception:
|
||||
data = None
|
||||
|
||||
if not isinstance(data, dict):
|
||||
return False, f"judge reply was not JSON: {_truncate(raw, 200)!r}"
|
||||
|
||||
done_val = data.get("done")
|
||||
if isinstance(done_val, str):
|
||||
done = done_val.strip().lower() in ("true", "yes", "1", "done")
|
||||
else:
|
||||
done = bool(done_val)
|
||||
reason = str(data.get("reason") or "").strip()
|
||||
if not reason:
|
||||
reason = "no reason provided"
|
||||
return done, reason
|
||||
|
||||
|
||||
def judge_goal(
|
||||
goal: str,
|
||||
last_response: str,
|
||||
*,
|
||||
timeout: float = DEFAULT_JUDGE_TIMEOUT,
|
||||
) -> Tuple[str, str]:
|
||||
"""Ask the auxiliary model whether the goal is satisfied.
|
||||
|
||||
Returns ``(verdict, reason)`` where verdict is ``"done"``, ``"continue"``,
|
||||
or ``"skipped"`` (when the judge couldn't be reached).
|
||||
|
||||
This is deliberately fail-open: any error returns ``("continue", "...")``
|
||||
so a broken judge doesn't wedge progress — the turn budget is the
|
||||
backstop.
|
||||
"""
|
||||
if not goal.strip():
|
||||
return "skipped", "empty goal"
|
||||
if not last_response.strip():
|
||||
# No substantive reply this turn — almost certainly not done yet.
|
||||
return "continue", "empty response (nothing to evaluate)"
|
||||
|
||||
try:
|
||||
from agent.auxiliary_client import get_text_auxiliary_client
|
||||
except Exception as exc:
|
||||
logger.debug("goal judge: auxiliary client import failed: %s", exc)
|
||||
return "continue", "auxiliary client unavailable"
|
||||
|
||||
try:
|
||||
client, model = get_text_auxiliary_client("goal_judge")
|
||||
except Exception as exc:
|
||||
logger.debug("goal judge: get_text_auxiliary_client failed: %s", exc)
|
||||
return "continue", "auxiliary client unavailable"
|
||||
|
||||
if client is None or not model:
|
||||
return "continue", "no auxiliary client configured"
|
||||
|
||||
prompt = JUDGE_USER_PROMPT_TEMPLATE.format(
|
||||
goal=_truncate(goal, 2000),
|
||||
response=_truncate(last_response, _JUDGE_RESPONSE_SNIPPET_CHARS),
|
||||
)
|
||||
|
||||
try:
|
||||
resp = client.chat.completions.create(
|
||||
model=model,
|
||||
messages=[
|
||||
{"role": "system", "content": JUDGE_SYSTEM_PROMPT},
|
||||
{"role": "user", "content": prompt},
|
||||
],
|
||||
temperature=0,
|
||||
max_tokens=200,
|
||||
timeout=timeout,
|
||||
)
|
||||
except Exception as exc:
|
||||
logger.info("goal judge: API call failed (%s) — falling through to continue", exc)
|
||||
return "continue", f"judge error: {type(exc).__name__}"
|
||||
|
||||
try:
|
||||
raw = resp.choices[0].message.content or ""
|
||||
except Exception:
|
||||
raw = ""
|
||||
|
||||
done, reason = _parse_judge_response(raw)
|
||||
verdict = "done" if done else "continue"
|
||||
logger.info("goal judge: verdict=%s reason=%s", verdict, _truncate(reason, 120))
|
||||
return verdict, reason
|
||||
|
||||
|
||||
# ──────────────────────────────────────────────────────────────────────
|
||||
# GoalManager — the orchestration surface CLI + gateway talk to
|
||||
# ──────────────────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
class GoalManager:
|
||||
"""Per-session goal state + continuation decisions.
|
||||
|
||||
The CLI and gateway each hold one ``GoalManager`` per live session.
|
||||
|
||||
Methods:
|
||||
|
||||
- ``set(goal)`` — start a new standing goal.
|
||||
- ``clear()`` — remove the active goal.
|
||||
- ``pause()`` / ``resume()`` — explicit user controls.
|
||||
- ``status()`` — printable one-liner.
|
||||
- ``evaluate_after_turn(last_response)`` — call the judge, update state,
|
||||
and return a decision dict the caller uses to drive the next turn.
|
||||
- ``next_continuation_prompt()`` — the canonical user-role message to
|
||||
feed back into ``run_conversation``.
|
||||
"""
|
||||
|
||||
def __init__(self, session_id: str, *, default_max_turns: int = DEFAULT_MAX_TURNS):
|
||||
self.session_id = session_id
|
||||
self.default_max_turns = int(default_max_turns or DEFAULT_MAX_TURNS)
|
||||
self._state: Optional[GoalState] = load_goal(session_id)
|
||||
|
||||
# --- introspection ------------------------------------------------
|
||||
|
||||
@property
|
||||
def state(self) -> Optional[GoalState]:
|
||||
return self._state
|
||||
|
||||
def is_active(self) -> bool:
|
||||
return self._state is not None and self._state.status == "active"
|
||||
|
||||
def has_goal(self) -> bool:
|
||||
return self._state is not None and self._state.status in ("active", "paused")
|
||||
|
||||
def status_line(self) -> str:
|
||||
s = self._state
|
||||
if s is None or s.status in ("cleared",):
|
||||
return "No active goal. Set one with /goal <text>."
|
||||
turns = f"{s.turns_used}/{s.max_turns} turns"
|
||||
if s.status == "active":
|
||||
return f"⊙ Goal (active, {turns}): {s.goal}"
|
||||
if s.status == "paused":
|
||||
extra = f" — {s.paused_reason}" if s.paused_reason else ""
|
||||
return f"⏸ Goal (paused, {turns}{extra}): {s.goal}"
|
||||
if s.status == "done":
|
||||
return f"✓ Goal done ({turns}): {s.goal}"
|
||||
return f"Goal ({s.status}, {turns}): {s.goal}"
|
||||
|
||||
# --- mutation -----------------------------------------------------
|
||||
|
||||
def set(self, goal: str, *, max_turns: Optional[int] = None) -> GoalState:
|
||||
goal = (goal or "").strip()
|
||||
if not goal:
|
||||
raise ValueError("goal text is empty")
|
||||
state = GoalState(
|
||||
goal=goal,
|
||||
status="active",
|
||||
turns_used=0,
|
||||
max_turns=int(max_turns) if max_turns else self.default_max_turns,
|
||||
created_at=time.time(),
|
||||
last_turn_at=0.0,
|
||||
)
|
||||
self._state = state
|
||||
save_goal(self.session_id, state)
|
||||
return state
|
||||
|
||||
def pause(self, reason: str = "user-paused") -> Optional[GoalState]:
|
||||
if not self._state:
|
||||
return None
|
||||
self._state.status = "paused"
|
||||
self._state.paused_reason = reason
|
||||
save_goal(self.session_id, self._state)
|
||||
return self._state
|
||||
|
||||
def resume(self, *, reset_budget: bool = True) -> Optional[GoalState]:
|
||||
if not self._state:
|
||||
return None
|
||||
self._state.status = "active"
|
||||
self._state.paused_reason = None
|
||||
if reset_budget:
|
||||
self._state.turns_used = 0
|
||||
save_goal(self.session_id, self._state)
|
||||
return self._state
|
||||
|
||||
def clear(self) -> None:
|
||||
if self._state is None:
|
||||
return
|
||||
self._state.status = "cleared"
|
||||
save_goal(self.session_id, self._state)
|
||||
self._state = None
|
||||
|
||||
def mark_done(self, reason: str) -> None:
|
||||
if not self._state:
|
||||
return
|
||||
self._state.status = "done"
|
||||
self._state.last_verdict = "done"
|
||||
self._state.last_reason = reason
|
||||
save_goal(self.session_id, self._state)
|
||||
|
||||
# --- the main entry point called after every turn -----------------
|
||||
|
||||
def evaluate_after_turn(
|
||||
self,
|
||||
last_response: str,
|
||||
*,
|
||||
user_initiated: bool = True,
|
||||
) -> Dict[str, Any]:
|
||||
"""Run the judge and update state. Return a decision dict.
|
||||
|
||||
``user_initiated`` distinguishes a real user prompt (True) from a
|
||||
continuation prompt we fed ourselves (False). Both increment
|
||||
``turns_used`` because both consume model budget.
|
||||
|
||||
Decision keys:
|
||||
- ``status``: current goal status after update
|
||||
- ``should_continue``: bool — caller should fire another turn
|
||||
- ``continuation_prompt``: str or None
|
||||
- ``verdict``: "done" | "continue" | "skipped" | "inactive"
|
||||
- ``reason``: str
|
||||
- ``message``: user-visible one-liner to print/send
|
||||
"""
|
||||
state = self._state
|
||||
if state is None or state.status != "active":
|
||||
return {
|
||||
"status": state.status if state else None,
|
||||
"should_continue": False,
|
||||
"continuation_prompt": None,
|
||||
"verdict": "inactive",
|
||||
"reason": "no active goal",
|
||||
"message": "",
|
||||
}
|
||||
|
||||
# Count the turn that just finished.
|
||||
state.turns_used += 1
|
||||
state.last_turn_at = time.time()
|
||||
|
||||
verdict, reason = judge_goal(state.goal, last_response)
|
||||
state.last_verdict = verdict
|
||||
state.last_reason = reason
|
||||
|
||||
if verdict == "done":
|
||||
state.status = "done"
|
||||
save_goal(self.session_id, state)
|
||||
return {
|
||||
"status": "done",
|
||||
"should_continue": False,
|
||||
"continuation_prompt": None,
|
||||
"verdict": "done",
|
||||
"reason": reason,
|
||||
"message": f"✓ Goal achieved: {reason}",
|
||||
}
|
||||
|
||||
if state.turns_used >= state.max_turns:
|
||||
state.status = "paused"
|
||||
state.paused_reason = f"turn budget exhausted ({state.turns_used}/{state.max_turns})"
|
||||
save_goal(self.session_id, state)
|
||||
return {
|
||||
"status": "paused",
|
||||
"should_continue": False,
|
||||
"continuation_prompt": None,
|
||||
"verdict": "continue",
|
||||
"reason": reason,
|
||||
"message": (
|
||||
f"⏸ Goal paused — {state.turns_used}/{state.max_turns} turns used. "
|
||||
"Use /goal resume to keep going, or /goal clear to stop."
|
||||
),
|
||||
}
|
||||
|
||||
save_goal(self.session_id, state)
|
||||
return {
|
||||
"status": "active",
|
||||
"should_continue": True,
|
||||
"continuation_prompt": self.next_continuation_prompt(),
|
||||
"verdict": "continue",
|
||||
"reason": reason,
|
||||
"message": (
|
||||
f"↻ Continuing toward goal ({state.turns_used}/{state.max_turns}): {reason}"
|
||||
),
|
||||
}
|
||||
|
||||
def next_continuation_prompt(self) -> Optional[str]:
|
||||
if not self._state or self._state.status != "active":
|
||||
return None
|
||||
return CONTINUATION_PROMPT_TEMPLATE.format(goal=self._state.goal)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"GoalState",
|
||||
"GoalManager",
|
||||
"CONTINUATION_PROMPT_TEMPLATE",
|
||||
"DEFAULT_MAX_TURNS",
|
||||
"load_goal",
|
||||
"save_goal",
|
||||
"clear_goal",
|
||||
"judge_goal",
|
||||
]
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
+31
-199
@@ -289,7 +289,7 @@ def _has_any_provider_configured() -> bool:
|
||||
env_file = get_env_path()
|
||||
if env_file.exists():
|
||||
try:
|
||||
for line in env_file.read_text(encoding="utf-8").splitlines():
|
||||
for line in env_file.read_text().splitlines():
|
||||
line = line.strip()
|
||||
if line.startswith("#") or "=" not in line:
|
||||
continue
|
||||
@@ -800,8 +800,6 @@ def _print_tui_exit_summary(session_id: Optional[str], active_session_file: Opti
|
||||
|
||||
title = db.get_session_title(target)
|
||||
message_count = int(session.get("message_count") or 0)
|
||||
if message_count == 0:
|
||||
return # No real conversation — don't show resume info
|
||||
input_tokens = int(session.get("input_tokens") or 0)
|
||||
output_tokens = int(session.get("output_tokens") or 0)
|
||||
cache_read_tokens = int(session.get("cache_read_tokens") or 0)
|
||||
@@ -837,17 +835,17 @@ def _print_tui_exit_summary(session_id: Optional[str], active_session_file: Opti
|
||||
)
|
||||
|
||||
|
||||
_NPM_LOCK_RUNTIME_KEYS = frozenset({"ideallyInert", "peer"})
|
||||
"""Lockfile fields npm writes non-deterministically at install time.
|
||||
_NPM_LOCK_RUNTIME_KEYS = frozenset({"ideallyInert"})
|
||||
_TUI_PREBUILT_MARKER = ".hermes-prebuilt-tui"
|
||||
|
||||
``ideallyInert`` is npm's runtime annotation for packages it skipped installing
|
||||
(per-platform opt-outs). ``peer`` is dropped from the hidden ``.package-lock.json``
|
||||
on dev-dependencies that are *also* declared as peers — the canonical
|
||||
``package-lock.json`` records the dual role, but npm 9's actualized tree strips
|
||||
it. Neither key represents a real skew between what was declared and what was
|
||||
installed, so we exclude them from the comparison in :func:`_tui_need_npm_install`
|
||||
to avoid false-positive reinstalls on every launch.
|
||||
"""
|
||||
|
||||
def _tui_prebuilt_ready(root: Path) -> bool:
|
||||
return (
|
||||
(root / _TUI_PREBUILT_MARKER).is_file()
|
||||
and (root / "dist" / "entry.js").is_file()
|
||||
and (root / "node_modules" / "@hermes" / "ink" / "package.json").is_file()
|
||||
and (root / "packages" / "hermes-ink" / "dist" / "ink-bundle.js").is_file()
|
||||
)
|
||||
|
||||
|
||||
def _tui_need_npm_install(root: Path) -> bool:
|
||||
@@ -870,6 +868,9 @@ def _tui_need_npm_install(root: Path) -> bool:
|
||||
we'd rather not force a reinstall for them. Falls back to mtime
|
||||
comparison if either lockfile is unparseable.
|
||||
"""
|
||||
if _tui_prebuilt_ready(root):
|
||||
return False
|
||||
|
||||
ink = root / "node_modules" / "@hermes" / "ink" / "package.json"
|
||||
if not ink.is_file():
|
||||
return True
|
||||
@@ -923,6 +924,8 @@ def _find_bundled_tui(tui_dir: Path) -> Optional[Path]:
|
||||
|
||||
|
||||
def _tui_build_needed(tui_dir: Path) -> bool:
|
||||
if _tui_prebuilt_ready(tui_dir):
|
||||
return False
|
||||
if _hermes_ink_bundle_stale(tui_dir):
|
||||
return True
|
||||
entry = tui_dir / "dist" / "entry.js"
|
||||
@@ -1052,21 +1055,17 @@ def _make_tui_argv(tui_dir: Path, tui_dev: bool) -> tuple[list[str], Path]:
|
||||
if _tui_need_npm_install(tui_dir):
|
||||
if not os.environ.get("HERMES_QUIET"):
|
||||
print("Installing TUI dependencies…")
|
||||
# Capture stdout as well as stderr — some npm errors (notably EACCES on a
|
||||
# root-owned node_modules in containers) are emitted on stdout, and a
|
||||
# bare "npm install failed." with no preview defeats debugging. We keep
|
||||
# the failure-only print path so a successful install stays silent.
|
||||
result = subprocess.run(
|
||||
[npm, "install", "--silent", "--no-fund", "--no-audit", "--progress=false"],
|
||||
cwd=str(tui_dir),
|
||||
stdout=subprocess.PIPE,
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.PIPE,
|
||||
text=True,
|
||||
env={**os.environ, "CI": "1"},
|
||||
)
|
||||
if result.returncode != 0:
|
||||
combined = f"{result.stdout or ''}\n{result.stderr or ''}".strip()
|
||||
preview = "\n".join(combined.splitlines()[-30:])
|
||||
err = (result.stderr or "").strip()
|
||||
preview = "\n".join(err.splitlines()[-30:])
|
||||
print("npm install failed.")
|
||||
if preview:
|
||||
print(preview)
|
||||
@@ -5057,13 +5056,6 @@ def cmd_slack(args):
|
||||
return 1
|
||||
|
||||
|
||||
def cmd_kanban(args):
|
||||
"""Multi-profile collaboration board."""
|
||||
from hermes_cli.kanban import kanban_command
|
||||
|
||||
return kanban_command(args)
|
||||
|
||||
|
||||
def cmd_hooks(args):
|
||||
"""Shell-hook inspection and management."""
|
||||
from hermes_cli.hooks import hooks_command
|
||||
@@ -5447,45 +5439,6 @@ def _find_stale_dashboard_pids() -> list[int]:
|
||||
return dashboard_pids
|
||||
|
||||
|
||||
def _print_curator_first_run_notice() -> None:
|
||||
"""Print a short heads-up about the skill curator after `hermes update`.
|
||||
|
||||
Only fires when the curator is enabled AND has no recorded run yet, which
|
||||
is exactly the window where the gateway ticker used to fire Curator
|
||||
against a fresh skill library immediately after an update. We defer the
|
||||
first real pass by one ``interval_hours``; this notice tells the user how
|
||||
to preview or disable before then. Silent on steady state.
|
||||
"""
|
||||
try:
|
||||
from agent import curator
|
||||
except Exception:
|
||||
return
|
||||
try:
|
||||
if not curator.is_enabled():
|
||||
return
|
||||
state = curator.load_state()
|
||||
except Exception:
|
||||
return
|
||||
if state.get("last_run_at"):
|
||||
# Curator has run before (real or already seeded) — no notice needed.
|
||||
return
|
||||
try:
|
||||
hours = curator.get_interval_hours()
|
||||
except Exception:
|
||||
hours = 24 * 7
|
||||
days = max(1, hours // 24)
|
||||
print()
|
||||
print("ℹ Skill curator")
|
||||
print(
|
||||
f" Background skill maintenance is enabled. First pass is deferred "
|
||||
f"~{days}d after installation; only agent-created skills are in "
|
||||
f"scope and nothing is ever auto-deleted (archive is recoverable)."
|
||||
)
|
||||
print(" Preview now: hermes curator run --dry-run")
|
||||
print(" Pause it: hermes curator pause")
|
||||
print(" Docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/curator")
|
||||
|
||||
|
||||
def _kill_stale_dashboard_processes(
|
||||
reason: str = "the running backend no longer matches the updated frontend",
|
||||
) -> None:
|
||||
@@ -5723,10 +5676,6 @@ def _update_via_zip(args):
|
||||
|
||||
print()
|
||||
print("✓ Update complete!")
|
||||
try:
|
||||
_print_curator_first_run_notice()
|
||||
except Exception as e:
|
||||
logger.debug("Curator first-run notice failed: %s", e)
|
||||
_kill_stale_dashboard_processes()
|
||||
|
||||
|
||||
@@ -6732,7 +6681,6 @@ def _cmd_update_impl(args, gateway_mode: bool):
|
||||
if gateway_mode
|
||||
else None
|
||||
)
|
||||
assume_yes = bool(getattr(args, "yes", False))
|
||||
|
||||
print("⚕ Updating Hermes Agent...")
|
||||
print()
|
||||
@@ -6852,10 +6800,8 @@ def _cmd_update_impl(args, gateway_mode: bool):
|
||||
else:
|
||||
auto_stash_ref = _stash_local_changes_if_needed(git_cmd, PROJECT_ROOT)
|
||||
|
||||
prompt_for_restore = (
|
||||
auto_stash_ref is not None
|
||||
and not assume_yes
|
||||
and (gateway_mode or (sys.stdin.isatty() and sys.stdout.isatty()))
|
||||
prompt_for_restore = auto_stash_ref is not None and (
|
||||
gateway_mode or (sys.stdin.isatty() and sys.stdout.isatty())
|
||||
)
|
||||
|
||||
# Check if there are updates
|
||||
@@ -7116,10 +7062,7 @@ def _cmd_update_impl(args, gateway_mode: bool):
|
||||
print(f" ℹ️ {len(missing_config)} new config option(s) available")
|
||||
|
||||
print()
|
||||
if assume_yes:
|
||||
print(" ℹ --yes: auto-applying config migration (skipping API-key prompts).")
|
||||
response = "y"
|
||||
elif gateway_mode:
|
||||
if gateway_mode:
|
||||
response = (
|
||||
_gateway_prompt(
|
||||
"Would you like to configure new options now? [Y/n]", "n"
|
||||
@@ -7145,17 +7088,14 @@ def _cmd_update_impl(args, gateway_mode: bool):
|
||||
|
||||
if response in ("", "y", "yes"):
|
||||
print()
|
||||
# In gateway mode OR under --yes, run auto-migrations only (no
|
||||
# input() prompts for API keys which would hang the detached
|
||||
# process / defeat the point of --yes).
|
||||
results = migrate_config(
|
||||
interactive=not (gateway_mode or assume_yes), quiet=False
|
||||
)
|
||||
# In gateway mode, run auto-migrations only (no input() prompts
|
||||
# for API keys which would hang the detached process).
|
||||
results = migrate_config(interactive=not gateway_mode, quiet=False)
|
||||
|
||||
if results["env_added"] or results["config_added"]:
|
||||
print()
|
||||
print("✓ Configuration updated!")
|
||||
if (gateway_mode or assume_yes) and missing_env:
|
||||
if gateway_mode and missing_env:
|
||||
print(" ℹ API keys require manual entry: hermes config migrate")
|
||||
else:
|
||||
print()
|
||||
@@ -7166,15 +7106,6 @@ def _cmd_update_impl(args, gateway_mode: bool):
|
||||
print()
|
||||
print("✓ Update complete!")
|
||||
|
||||
# Curator first-run heads-up. Only prints when curator is enabled AND
|
||||
# has never run — i.e. the window where the ticker would otherwise
|
||||
# have fired against a fresh skill library. Kept silent on steady
|
||||
# state so we don't nag.
|
||||
try:
|
||||
_print_curator_first_run_notice()
|
||||
except Exception as e:
|
||||
logger.debug("Curator first-run notice failed: %s", e)
|
||||
|
||||
# Repair RHEL-family root installs where /usr/local/bin isn't on PATH
|
||||
# for non-login interactive shells. No-op on every other platform.
|
||||
try:
|
||||
@@ -7214,8 +7145,6 @@ def _cmd_update_impl(args, gateway_mode: bool):
|
||||
supports_systemd_services,
|
||||
_ensure_user_systemd_env,
|
||||
find_gateway_pids,
|
||||
find_profile_gateway_processes,
|
||||
launch_detached_profile_gateway_restart,
|
||||
_get_service_pids,
|
||||
_graceful_restart_via_sigusr1,
|
||||
)
|
||||
@@ -7319,7 +7248,6 @@ def _cmd_update_impl(args, gateway_mode: bool):
|
||||
|
||||
restarted_services = []
|
||||
killed_pids = set()
|
||||
relaunched_profiles = []
|
||||
|
||||
# --- Systemd services (Linux) ---
|
||||
# Discover all hermes-gateway* units (default + profiles)
|
||||
@@ -7509,33 +7437,7 @@ def _cmd_update_impl(args, gateway_mode: bool):
|
||||
manual_pids = find_gateway_pids(
|
||||
exclude_pids=service_pids, all_profiles=True
|
||||
)
|
||||
profile_processes = {
|
||||
proc.pid: proc
|
||||
for proc in find_profile_gateway_processes(exclude_pids=service_pids)
|
||||
if proc.pid in manual_pids
|
||||
}
|
||||
for pid, proc in profile_processes.items():
|
||||
if not launch_detached_profile_gateway_restart(proc.profile, pid):
|
||||
continue
|
||||
# Prefer a graceful SIGUSR1 drain so in-flight agent runs
|
||||
# finish before the watcher respawns the gateway. If the
|
||||
# gateway doesn't support SIGUSR1 or doesn't exit within
|
||||
# the drain budget, fall back to SIGTERM — the watcher
|
||||
# still sees the exit and relaunches either way.
|
||||
drained = _graceful_restart_via_sigusr1(
|
||||
pid, drain_timeout=_drain_budget,
|
||||
)
|
||||
if not drained:
|
||||
try:
|
||||
os.kill(pid, _signal.SIGTERM)
|
||||
except (ProcessLookupError, PermissionError):
|
||||
pass
|
||||
killed_pids.add(pid)
|
||||
relaunched_profiles.append(proc.profile)
|
||||
|
||||
for pid in manual_pids:
|
||||
if pid in profile_processes:
|
||||
continue
|
||||
try:
|
||||
os.kill(pid, _signal.SIGTERM)
|
||||
killed_pids.add(pid)
|
||||
@@ -7546,14 +7448,11 @@ def _cmd_update_impl(args, gateway_mode: bool):
|
||||
print()
|
||||
for svc in restarted_services:
|
||||
print(f" ✓ Restarted {svc}")
|
||||
if relaunched_profiles:
|
||||
names = ", ".join(relaunched_profiles)
|
||||
print(f" ✓ Restarting manual gateway profile(s): {names}")
|
||||
unmapped_count = len(killed_pids) - len(relaunched_profiles)
|
||||
if unmapped_count:
|
||||
print(f" → Stopped {unmapped_count} manual gateway process(es)")
|
||||
if killed_pids:
|
||||
print(f" → Stopped {len(killed_pids)} manual gateway process(es)")
|
||||
print(" Restart manually: hermes gateway run")
|
||||
if unmapped_count > 1:
|
||||
# Also restart for each profile if needed
|
||||
if len(killed_pids) > 1:
|
||||
print(
|
||||
" (or: hermes -p <profile> gateway run for each profile)"
|
||||
)
|
||||
@@ -7562,42 +7461,6 @@ def _cmd_update_impl(args, gateway_mode: bool):
|
||||
# No gateways were running — nothing to do
|
||||
pass
|
||||
|
||||
# --- Post-restart survivor sweep -----------------------------
|
||||
# Issue #17648: some gateways ignore SIGTERM (stuck drain,
|
||||
# blocked I/O, PID dead but zombie). The detached profile
|
||||
# watchers wait 120s for the old PID to exit — if it never
|
||||
# does, no respawn happens and the user keeps hitting
|
||||
# ImportError against a stale sys.modules. Give the
|
||||
# graceful paths a brief window to complete, then SIGKILL
|
||||
# any remaining pre-update PIDs so the watcher / service
|
||||
# manager can relaunch with fresh code.
|
||||
try:
|
||||
_time.sleep(3.0)
|
||||
_service_pids_after = _get_service_pids()
|
||||
_surviving = find_gateway_pids(
|
||||
exclude_pids=_service_pids_after, all_profiles=True,
|
||||
)
|
||||
# Scope to PIDs we already tried to kill during this
|
||||
# update (killed_pids). Anything new is a gateway that
|
||||
# started AFTER our restart attempt — respecting user
|
||||
# intent, we don't kill those.
|
||||
_stuck = [pid for pid in _surviving if pid in killed_pids]
|
||||
if _stuck:
|
||||
print()
|
||||
print(
|
||||
f" ⚠ {len(_stuck)} gateway process(es) ignored SIGTERM — force-killing"
|
||||
)
|
||||
for pid in _stuck:
|
||||
try:
|
||||
os.kill(pid, _signal.SIGKILL)
|
||||
except (ProcessLookupError, PermissionError):
|
||||
pass
|
||||
# Give the OS a beat to reap the processes so the
|
||||
# watchers see them exit and respawn.
|
||||
_time.sleep(1.5)
|
||||
except Exception as _sweep_exc:
|
||||
logger.debug("Post-restart survivor sweep failed: %s", _sweep_exc)
|
||||
|
||||
except Exception as e:
|
||||
logger.debug("Gateway restart during update failed: %s", e)
|
||||
|
||||
@@ -7834,7 +7697,7 @@ def cmd_profile(args):
|
||||
if clone_all:
|
||||
print(f"Full copy from {source_label}.")
|
||||
else:
|
||||
print(f"Cloned config, .env, SOUL.md, and skills from {source_label}.")
|
||||
print(f"Cloned config, .env, SOUL.md from {source_label}.")
|
||||
|
||||
# Auto-clone Honcho config for the new profile (only with --clone/--clone-all)
|
||||
if clone or clone_all:
|
||||
@@ -8474,12 +8337,6 @@ def main():
|
||||
)
|
||||
slack_parser.set_defaults(func=cmd_slack)
|
||||
|
||||
# =========================================================================
|
||||
# send command — pipe shell-script output to any configured platform
|
||||
# =========================================================================
|
||||
from hermes_cli.send_cmd import register_send_subparser
|
||||
register_send_subparser(subparsers)
|
||||
|
||||
# =========================================================================
|
||||
# login command
|
||||
# =========================================================================
|
||||
@@ -8798,13 +8655,6 @@ def main():
|
||||
|
||||
webhook_parser.set_defaults(func=cmd_webhook)
|
||||
|
||||
# =========================================================================
|
||||
# kanban command — multi-profile collaboration board
|
||||
# =========================================================================
|
||||
from hermes_cli.kanban import build_parser as _build_kanban_parser
|
||||
kanban_parser = _build_kanban_parser(subparsers)
|
||||
kanban_parser.set_defaults(func=cmd_kanban)
|
||||
|
||||
# =========================================================================
|
||||
# hooks command — shell-hook inspection and management
|
||||
# =========================================================================
|
||||
@@ -8911,7 +8761,6 @@ Examples:
|
||||
hermes debug share --lines 500 Include more log lines
|
||||
hermes debug share --expire 30 Keep paste for 30 days
|
||||
hermes debug share --local Print report locally (no upload)
|
||||
hermes debug share --no-redact Disable upload-time secret redaction
|
||||
hermes debug delete <url> Delete a previously uploaded paste
|
||||
""",
|
||||
)
|
||||
@@ -8937,16 +8786,6 @@ Examples:
|
||||
action="store_true",
|
||||
help="Print the report locally instead of uploading",
|
||||
)
|
||||
share_parser.add_argument(
|
||||
"--no-redact",
|
||||
action="store_true",
|
||||
help=(
|
||||
"Disable upload-time secret redaction (default: redact). Logs "
|
||||
"are normally run through agent.redact.redact_sensitive_text "
|
||||
"with force=True before upload so credentials are not leaked "
|
||||
"into the public paste service."
|
||||
),
|
||||
)
|
||||
delete_parser = debug_sub.add_parser(
|
||||
"delete",
|
||||
help="Delete a paste uploaded by 'hermes debug share'",
|
||||
@@ -10023,13 +9862,6 @@ Examples:
|
||||
default=False,
|
||||
help="Force a pre-update backup for this run (off by default; overrides updates.pre_update_backup)",
|
||||
)
|
||||
update_parser.add_argument(
|
||||
"--yes",
|
||||
"-y",
|
||||
action="store_true",
|
||||
default=False,
|
||||
help="Assume yes for interactive prompts (config migration, stash restore). API-key entry is skipped; run 'hermes config migrate' separately for those.",
|
||||
)
|
||||
update_parser.set_defaults(func=cmd_update)
|
||||
|
||||
# =========================================================================
|
||||
|
||||
@@ -361,7 +361,7 @@ def _write_env_vars(env_path: Path, env_writes: dict) -> None:
|
||||
|
||||
existing_lines = []
|
||||
if env_path.exists():
|
||||
existing_lines = env_path.read_text(encoding="utf-8").splitlines()
|
||||
existing_lines = env_path.read_text().splitlines()
|
||||
|
||||
updated_keys = set()
|
||||
new_lines = []
|
||||
|
||||
+16
-81
@@ -891,37 +891,12 @@ def switch_model(
|
||||
if not validation.get("accepted"):
|
||||
override = False
|
||||
if user_providers:
|
||||
# user_providers is a dict: {provider_slug: config_dict}
|
||||
for slug, cfg in user_providers.items():
|
||||
if slug == target_provider:
|
||||
cfg_models = cfg.get("models", {})
|
||||
# Direct membership works for dict (keys) and list (strings)
|
||||
if new_model in cfg_models:
|
||||
override = True
|
||||
break
|
||||
# Also accept if models is a list of dicts with 'name' field
|
||||
if isinstance(cfg_models, list):
|
||||
if any(m.get("name") == new_model for m in cfg_models if isinstance(m, dict)):
|
||||
override = True
|
||||
break
|
||||
# Also check custom_providers list — models declared there should be accepted
|
||||
# even if the remote /v1/models endpoint doesn't list them.
|
||||
if not override and custom_providers and isinstance(custom_providers, list):
|
||||
for entry in custom_providers:
|
||||
if not isinstance(entry, dict):
|
||||
continue
|
||||
# Match by provider slug (custom:<name>) or by base_url
|
||||
entry_name = entry.get("name", "")
|
||||
entry_slug = f"custom:{entry_name}" if entry_name else ""
|
||||
entry_url = entry.get("base_url", "")
|
||||
if entry_slug == target_provider or entry_url == base_url:
|
||||
# Check if the requested model matches the entry's model
|
||||
entry_model = entry.get("model", "")
|
||||
entry_models = entry.get("models", {})
|
||||
if new_model == entry_model:
|
||||
override = True
|
||||
break
|
||||
if isinstance(entry_models, dict) and new_model in entry_models:
|
||||
for up in user_providers:
|
||||
if isinstance(up, dict) and up.get("provider") == target_provider:
|
||||
cfg_models = up.get("models", [])
|
||||
if new_model in cfg_models or any(
|
||||
m.get("name") == new_model for m in cfg_models if isinstance(m, dict)
|
||||
):
|
||||
override = True
|
||||
break
|
||||
if override:
|
||||
@@ -1077,45 +1052,6 @@ def list_authenticated_providers(
|
||||
if normed:
|
||||
_builtin_endpoints.add(normed)
|
||||
|
||||
def _has_fast_aws_sdk_signal() -> bool:
|
||||
"""Return True when explicit AWS auth config is present.
|
||||
|
||||
This intentionally avoids botocore's full credential chain. Provider
|
||||
picker/model-switch discovery can run for non-Bedrock providers, and
|
||||
botocore may otherwise probe EC2 IMDS (169.254.169.254) on local
|
||||
machines before returning no credentials.
|
||||
"""
|
||||
if os.environ.get("AWS_BEARER_TOKEN_BEDROCK", "").strip():
|
||||
return True
|
||||
if (
|
||||
os.environ.get("AWS_ACCESS_KEY_ID", "").strip()
|
||||
and os.environ.get("AWS_SECRET_ACCESS_KEY", "").strip()
|
||||
):
|
||||
return True
|
||||
return any(
|
||||
os.environ.get(name, "").strip()
|
||||
for name in (
|
||||
"AWS_PROFILE",
|
||||
"AWS_CONTAINER_CREDENTIALS_RELATIVE_URI",
|
||||
"AWS_CONTAINER_CREDENTIALS_FULL_URI",
|
||||
"AWS_WEB_IDENTITY_TOKEN_FILE",
|
||||
)
|
||||
)
|
||||
|
||||
def _has_aws_sdk_creds_for_listing(slug: str) -> bool:
|
||||
"""Credential check for AWS SDK providers in non-runtime discovery."""
|
||||
slug_norm = str(slug or "").strip().lower()
|
||||
current_norm = str(current_provider or "").strip().lower()
|
||||
if _has_fast_aws_sdk_signal():
|
||||
return True
|
||||
if slug_norm != current_norm:
|
||||
return False
|
||||
try:
|
||||
from agent.bedrock_adapter import has_aws_credentials
|
||||
return bool(has_aws_credentials())
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
data = fetch_models_dev()
|
||||
|
||||
# Build curated model lists keyed by hermes provider ID
|
||||
@@ -1243,9 +1179,7 @@ def list_authenticated_providers(
|
||||
|
||||
# Check if credentials exist
|
||||
has_creds = False
|
||||
if overlay.auth_type == "aws_sdk":
|
||||
has_creds = _has_aws_sdk_creds_for_listing(hermes_slug)
|
||||
elif overlay.extra_env_vars:
|
||||
if overlay.extra_env_vars:
|
||||
has_creds = any(os.environ.get(ev) for ev in overlay.extra_env_vars)
|
||||
# Also check api_key_env_vars from PROVIDER_REGISTRY for api_key auth_type
|
||||
if not has_creds and overlay.auth_type == "api_key":
|
||||
@@ -1385,7 +1319,11 @@ def list_authenticated_providers(
|
||||
# credentials come from the boto3 credential chain (env vars,
|
||||
# ~/.aws/credentials, instance roles, etc.)
|
||||
if not _cp_has_creds and _cp_config and getattr(_cp_config, "auth_type", "") == "aws_sdk":
|
||||
_cp_has_creds = _has_aws_sdk_creds_for_listing(_cp.slug)
|
||||
try:
|
||||
from agent.bedrock_adapter import has_aws_credentials
|
||||
_cp_has_creds = has_aws_credentials()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
if not _cp_has_creds:
|
||||
continue
|
||||
@@ -1474,17 +1412,14 @@ def list_authenticated_providers(
|
||||
models_list = list(fb)
|
||||
|
||||
# Prefer the endpoint's live /models list when credentials are
|
||||
# available, unless the provider explicitly opts out via
|
||||
# discover_models: false (e.g. dedicated endpoints that expose
|
||||
# the entire aggregator catalog via /models).
|
||||
# available. This keeps OpenAI-compatible relays (for example CRS)
|
||||
# in sync when the server catalog changes without requiring the
|
||||
# user to mirror every model into config.yaml.
|
||||
api_key = str(ep_cfg.get("api_key", "") or "").strip()
|
||||
if not api_key:
|
||||
key_env = str(ep_cfg.get("key_env", "") or "").strip()
|
||||
api_key = os.environ.get(key_env, "").strip() if key_env else ""
|
||||
discover = ep_cfg.get("discover_models", True)
|
||||
if isinstance(discover, str):
|
||||
discover = discover.lower() not in ("false", "no", "0")
|
||||
if api_url and api_key and discover:
|
||||
if api_url and api_key:
|
||||
try:
|
||||
from hermes_cli.models import fetch_api_models
|
||||
live_models = fetch_api_models(api_key, api_url)
|
||||
|
||||
@@ -40,7 +40,6 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
|
||||
("anthropic/claude-sonnet-4.5", ""),
|
||||
("anthropic/claude-haiku-4.5", ""),
|
||||
("openrouter/elephant-alpha", "free"),
|
||||
("openrouter/owl-alpha", "free"),
|
||||
("openai/gpt-5.5", ""),
|
||||
("openai/gpt-5.4-mini", ""),
|
||||
("xiaomi/mimo-v2.5-pro", ""),
|
||||
@@ -774,6 +773,7 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
|
||||
ProviderEntry("nous", "Nous Portal", "Nous Portal (Nous Research subscription)"),
|
||||
ProviderEntry("openrouter", "OpenRouter", "OpenRouter (100+ models, pay-per-use)"),
|
||||
ProviderEntry("lmstudio", "LM Studio", "LM Studio (local desktop app with built-in model server)"),
|
||||
ProviderEntry("ai-gateway", "Vercel AI Gateway", "Vercel AI Gateway (200+ models, $5 free credit, no markup)"),
|
||||
ProviderEntry("anthropic", "Anthropic", "Anthropic (Claude models — API key or Claude Code)"),
|
||||
ProviderEntry("openai-codex", "OpenAI Codex", "OpenAI Codex"),
|
||||
ProviderEntry("xiaomi", "Xiaomi MiMo", "Xiaomi MiMo (MiMo-V2.5 and V2 models — pro, omni, flash)"),
|
||||
@@ -803,7 +803,6 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
|
||||
ProviderEntry("opencode-go", "OpenCode Go", "OpenCode Go (open models, $10/month subscription)"),
|
||||
ProviderEntry("bedrock", "AWS Bedrock", "AWS Bedrock (Claude, Nova, Llama, DeepSeek — IAM or API key)"),
|
||||
ProviderEntry("azure-foundry", "Azure Foundry", "Azure Foundry (OpenAI-style or Anthropic-style endpoint — your Azure AI deployment)"),
|
||||
ProviderEntry("ai-gateway", "Vercel AI Gateway", "Vercel AI Gateway"),
|
||||
]
|
||||
|
||||
# Derived dicts — used throughout the codebase
|
||||
@@ -3087,7 +3086,7 @@ def validate_requested_model(
|
||||
"message": f"Model `{requested}` was not found in LM Studio's model listing.",
|
||||
}
|
||||
|
||||
if normalized == "custom" or normalized.startswith("custom:"):
|
||||
if normalized == "custom":
|
||||
# Try probing with correct auth for the api_mode.
|
||||
if api_mode == "anthropic_messages":
|
||||
probe = probe_api_models(api_key, base_url, api_mode=api_mode)
|
||||
|
||||
@@ -33,15 +33,12 @@ so plugin-defined tools appear alongside the built-in tools.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import importlib
|
||||
import importlib.metadata
|
||||
import importlib.util
|
||||
import inspect
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
import threading
|
||||
import types
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
@@ -1229,55 +1226,6 @@ def get_plugin_command_handler(name: str) -> Optional[Callable]:
|
||||
return entry["handler"] if entry else None
|
||||
|
||||
|
||||
_PLUGIN_COMMAND_AWAIT_TIMEOUT_SECS = 30.0
|
||||
|
||||
|
||||
def resolve_plugin_command_result(result: Any) -> Any:
|
||||
"""Resolve a plugin command return value, awaiting async handlers when needed.
|
||||
|
||||
Sync CLI/TUI dispatch sites call plugin handlers from plain functions.
|
||||
If a handler is async, await it directly when no loop is running; if
|
||||
we're already inside an active loop, run it in a helper thread with its
|
||||
own loop so the caller still gets a concrete result synchronously. The
|
||||
threaded path is bounded by a 30s timeout so a hung async handler cannot
|
||||
wedge the terminal indefinitely.
|
||||
"""
|
||||
if not inspect.isawaitable(result):
|
||||
return result
|
||||
|
||||
try:
|
||||
asyncio.get_running_loop()
|
||||
except RuntimeError:
|
||||
return asyncio.run(result)
|
||||
|
||||
outcome: Dict[str, Any] = {}
|
||||
failure: Dict[str, BaseException] = {}
|
||||
done = threading.Event()
|
||||
|
||||
def _runner() -> None:
|
||||
try:
|
||||
outcome["value"] = asyncio.run(result)
|
||||
except BaseException as exc: # pragma: no cover - re-raised below
|
||||
failure["exc"] = exc
|
||||
finally:
|
||||
done.set()
|
||||
|
||||
thread = threading.Thread(
|
||||
target=_runner,
|
||||
name="hermes-plugin-command-await",
|
||||
daemon=True,
|
||||
)
|
||||
thread.start()
|
||||
if not done.wait(timeout=_PLUGIN_COMMAND_AWAIT_TIMEOUT_SECS):
|
||||
raise TimeoutError(
|
||||
"Plugin command async handler did not complete within "
|
||||
f"{_PLUGIN_COMMAND_AWAIT_TIMEOUT_SECS:.0f}s"
|
||||
)
|
||||
if "exc" in failure:
|
||||
raise failure["exc"]
|
||||
return outcome.get("value")
|
||||
|
||||
|
||||
def get_plugin_commands() -> Dict[str, dict]:
|
||||
"""Return the full plugin commands dict (name → {handler, description, plugin}).
|
||||
|
||||
|
||||
+113
-378
@@ -15,18 +15,13 @@ import shutil
|
||||
import subprocess
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from typing import Any, Optional
|
||||
from typing import Optional
|
||||
|
||||
from hermes_constants import get_hermes_home
|
||||
from hermes_cli.config import cfg_get
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class PluginOperationError(Exception):
|
||||
"""Recoverable plugin install/update failure (CLI exits; HTTP maps to 4xx)."""
|
||||
|
||||
|
||||
# Minimum manifest version this installer understands.
|
||||
# Plugins may declare ``manifest_version: 1`` in plugin.yaml;
|
||||
# future breaking changes to the manifest schema bump this.
|
||||
@@ -155,24 +150,6 @@ def _copy_example_files(plugin_dir: Path, console) -> None:
|
||||
)
|
||||
|
||||
|
||||
def _missing_requires_env_names(manifest: dict) -> list[str]:
|
||||
"""Return declared ``requires_env`` names that are unset in ``~/.hermes/.env``."""
|
||||
requires_env = manifest.get("requires_env") or []
|
||||
if not requires_env:
|
||||
return []
|
||||
|
||||
from hermes_cli.config import get_env_value
|
||||
|
||||
env_specs: list[dict] = []
|
||||
for entry in requires_env:
|
||||
if isinstance(entry, str):
|
||||
env_specs.append({"name": entry})
|
||||
elif isinstance(entry, dict) and entry.get("name"):
|
||||
env_specs.append(entry)
|
||||
|
||||
return [s["name"] for s in env_specs if s.get("name") and not get_env_value(s["name"])]
|
||||
|
||||
|
||||
def _prompt_plugin_env_vars(manifest: dict, console) -> None:
|
||||
"""Prompt for required environment variables declared in plugin.yaml.
|
||||
|
||||
@@ -306,95 +283,6 @@ def _require_installed_plugin(name: str, plugins_dir: Path, console) -> Path:
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def _install_plugin_core(identifier: str, *, force: bool) -> tuple[Path, dict, str]:
|
||||
"""Clone Git plugin into ``~/.hermes/plugins``.
|
||||
|
||||
Returns ``(target_dir, installed_manifest, canonical_name)``.
|
||||
Raises ``PluginOperationError`` on failure.
|
||||
"""
|
||||
import tempfile
|
||||
|
||||
try:
|
||||
git_url = _resolve_git_url(identifier)
|
||||
except ValueError as e:
|
||||
raise PluginOperationError(str(e)) from e
|
||||
|
||||
plugins_dir = _plugins_dir()
|
||||
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
tmp_target = Path(tmp) / "plugin"
|
||||
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["git", "clone", "--depth", "1", git_url, str(tmp_target)],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=60,
|
||||
)
|
||||
except FileNotFoundError as e:
|
||||
raise PluginOperationError(
|
||||
"git is not installed or not in PATH.",
|
||||
) from e
|
||||
except subprocess.TimeoutExpired as e:
|
||||
raise PluginOperationError(
|
||||
"Git clone timed out after 60 seconds.",
|
||||
) from e
|
||||
|
||||
if result.returncode != 0:
|
||||
err = (result.stderr or result.stdout or "").strip()
|
||||
raise PluginOperationError(f"Git clone failed:\n{err}")
|
||||
|
||||
manifest = _read_manifest(tmp_target)
|
||||
plugin_name = manifest.get("name") or _repo_name_from_url(git_url)
|
||||
|
||||
try:
|
||||
target = _sanitize_plugin_name(plugin_name, plugins_dir)
|
||||
except ValueError as e:
|
||||
raise PluginOperationError(str(e)) from e
|
||||
|
||||
mv = manifest.get("manifest_version")
|
||||
if mv is not None:
|
||||
try:
|
||||
mv_int = int(mv)
|
||||
except (ValueError, TypeError):
|
||||
raise PluginOperationError(
|
||||
f"Plugin '{plugin_name}' has invalid manifest_version "
|
||||
f"'{mv}' (expected an integer).",
|
||||
) from None
|
||||
if mv_int > _SUPPORTED_MANIFEST_VERSION:
|
||||
from hermes_cli.config import recommended_update_command
|
||||
|
||||
raise PluginOperationError(
|
||||
f"Plugin '{plugin_name}' requires manifest_version {mv}, "
|
||||
f"but this installer only supports up to {_SUPPORTED_MANIFEST_VERSION}. "
|
||||
f"Run {recommended_update_command()} to update Hermes.",
|
||||
) from None
|
||||
|
||||
if target.exists():
|
||||
if not force:
|
||||
raise PluginOperationError(
|
||||
f"Plugin '{plugin_name}' already exists. Use force reinstall "
|
||||
f"or run `hermes plugins update {plugin_name}`.",
|
||||
)
|
||||
shutil.rmtree(target)
|
||||
|
||||
shutil.move(str(tmp_target), str(target))
|
||||
|
||||
has_yaml = (target / "plugin.yaml").exists() or (target / "plugin.yml").exists()
|
||||
if not has_yaml and not (target / "__init__.py").exists():
|
||||
logger.warning(
|
||||
"%s has no plugin.yaml / __init__.py; may not be a valid plugin",
|
||||
plugin_name,
|
||||
)
|
||||
|
||||
from rich.console import Console
|
||||
|
||||
_copy_example_files(target, Console())
|
||||
installed_manifest = _read_manifest(target)
|
||||
installed_name = installed_manifest.get("name") or target.name
|
||||
return target, installed_manifest, installed_name
|
||||
|
||||
|
||||
def cmd_install(
|
||||
identifier: str,
|
||||
force: bool = False,
|
||||
@@ -405,6 +293,7 @@ def cmd_install(
|
||||
After install, prompt "Enable now? [y/N]" unless *enable* is provided
|
||||
(True = auto-enable without prompting, False = install disabled).
|
||||
"""
|
||||
import tempfile
|
||||
from rich.console import Console
|
||||
|
||||
console = Console()
|
||||
@@ -415,41 +304,114 @@ def cmd_install(
|
||||
console.print(f"[red]Error:[/red] {e}")
|
||||
sys.exit(1)
|
||||
|
||||
# Warn about insecure / local URL schemes
|
||||
if git_url.startswith(("http://", "file://")):
|
||||
console.print(
|
||||
"[yellow]Warning:[/yellow] Using insecure/local URL scheme. "
|
||||
"Consider using https:// or git@ for production installs.",
|
||||
"Consider using https:// or git@ for production installs."
|
||||
)
|
||||
|
||||
console.print(f"[dim]Cloning {git_url}...[/dim]")
|
||||
plugins_dir = _plugins_dir()
|
||||
|
||||
try:
|
||||
target, installed_manifest, installed_name = _install_plugin_core(
|
||||
identifier,
|
||||
force=force,
|
||||
)
|
||||
except PluginOperationError as e:
|
||||
console.print(f"[red]Error:[/red] {e}")
|
||||
sys.exit(1)
|
||||
# Clone into a temp directory first so we can read plugin.yaml for the name
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
tmp_target = Path(tmp) / "plugin"
|
||||
console.print(f"[dim]Cloning {git_url}...[/dim]")
|
||||
|
||||
if not (target / "plugin.yaml").exists() and not (target / "plugin.yml").exists() and not (
|
||||
target / "__init__.py"
|
||||
).exists():
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["git", "clone", "--depth", "1", git_url, str(tmp_target)],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=60,
|
||||
)
|
||||
except FileNotFoundError:
|
||||
console.print("[red]Error:[/red] git is not installed or not in PATH.")
|
||||
sys.exit(1)
|
||||
except subprocess.TimeoutExpired:
|
||||
console.print("[red]Error:[/red] Git clone timed out after 60 seconds.")
|
||||
sys.exit(1)
|
||||
|
||||
if result.returncode != 0:
|
||||
console.print(
|
||||
f"[red]Error:[/red] Git clone failed:\n{result.stderr.strip()}"
|
||||
)
|
||||
sys.exit(1)
|
||||
|
||||
# Read manifest
|
||||
manifest = _read_manifest(tmp_target)
|
||||
plugin_name = manifest.get("name") or _repo_name_from_url(git_url)
|
||||
|
||||
# Sanitize plugin name against path traversal
|
||||
try:
|
||||
target = _sanitize_plugin_name(plugin_name, plugins_dir)
|
||||
except ValueError as e:
|
||||
console.print(f"[red]Error:[/red] {e}")
|
||||
sys.exit(1)
|
||||
|
||||
# Check manifest_version compatibility
|
||||
mv = manifest.get("manifest_version")
|
||||
if mv is not None:
|
||||
try:
|
||||
mv_int = int(mv)
|
||||
except (ValueError, TypeError):
|
||||
console.print(
|
||||
f"[red]Error:[/red] Plugin '{plugin_name}' has invalid "
|
||||
f"manifest_version '{mv}' (expected an integer)."
|
||||
)
|
||||
sys.exit(1)
|
||||
if mv_int > _SUPPORTED_MANIFEST_VERSION:
|
||||
from hermes_cli.config import recommended_update_command
|
||||
console.print(
|
||||
f"[red]Error:[/red] Plugin '{plugin_name}' requires manifest_version "
|
||||
f"{mv}, but this installer only supports up to {_SUPPORTED_MANIFEST_VERSION}.\n"
|
||||
f"Run [bold]{recommended_update_command()}[/bold] to get a newer installer."
|
||||
)
|
||||
sys.exit(1)
|
||||
|
||||
if target.exists():
|
||||
if not force:
|
||||
console.print(
|
||||
f"[red]Error:[/red] Plugin '{plugin_name}' already exists at {target}.\n"
|
||||
f"Use [bold]--force[/bold] to remove and reinstall, or "
|
||||
f"[bold]hermes plugins update {plugin_name}[/bold] to pull latest."
|
||||
)
|
||||
sys.exit(1)
|
||||
console.print(f"[dim] Removing existing {plugin_name}...[/dim]")
|
||||
shutil.rmtree(target)
|
||||
|
||||
# Move from temp to final location
|
||||
shutil.move(str(tmp_target), str(target))
|
||||
|
||||
# Validate it looks like a plugin
|
||||
if not (target / "plugin.yaml").exists() and not (target / "__init__.py").exists():
|
||||
console.print(
|
||||
f"[yellow]Warning:[/yellow] {installed_name} doesn't contain plugin.yaml "
|
||||
f"or __init__.py. It may not be a valid Hermes plugin.",
|
||||
f"[yellow]Warning:[/yellow] {plugin_name} doesn't contain plugin.yaml "
|
||||
f"or __init__.py. It may not be a valid Hermes plugin."
|
||||
)
|
||||
|
||||
# Copy .example files to their real names (e.g. config.yaml.example → config.yaml)
|
||||
_copy_example_files(target, console)
|
||||
|
||||
# Re-read manifest from installed location (for env var prompting)
|
||||
installed_manifest = _read_manifest(target)
|
||||
|
||||
# Prompt for required environment variables before showing after-install docs
|
||||
_prompt_plugin_env_vars(installed_manifest, console)
|
||||
|
||||
_display_after_install(target, identifier)
|
||||
|
||||
# Determine the canonical plugin name for enable-list bookkeeping.
|
||||
installed_name = installed_manifest.get("name") or target.name
|
||||
|
||||
# Decide whether to enable: explicit flag > interactive prompt > default off
|
||||
should_enable = enable
|
||||
if should_enable is None:
|
||||
# Interactive prompt unless stdin isn't a TTY (scripted install).
|
||||
if sys.stdin.isatty() and sys.stdout.isatty():
|
||||
try:
|
||||
answer = input(
|
||||
f" Enable '{installed_name}' now? [y/N]: ",
|
||||
f" Enable '{installed_name}' now? [y/N]: "
|
||||
).strip().lower()
|
||||
should_enable = answer in ("y", "yes")
|
||||
except (EOFError, KeyboardInterrupt):
|
||||
@@ -465,12 +427,12 @@ def cmd_install(
|
||||
_save_enabled_set(enabled)
|
||||
_save_disabled_set(disabled)
|
||||
console.print(
|
||||
f"[green]✓[/green] Plugin [bold]{installed_name}[/bold] enabled.",
|
||||
f"[green]✓[/green] Plugin [bold]{installed_name}[/bold] enabled."
|
||||
)
|
||||
else:
|
||||
console.print(
|
||||
f"[dim]Plugin installed but not enabled. "
|
||||
f"Run `hermes plugins enable {installed_name}` to activate.[/dim]",
|
||||
f"Run `hermes plugins enable {installed_name}` to activate.[/dim]"
|
||||
)
|
||||
|
||||
console.print("[dim]Restart the gateway for the plugin to take effect:[/dim]")
|
||||
@@ -500,22 +462,36 @@ def cmd_update(name: str) -> None:
|
||||
|
||||
console.print(f"[dim]Updating {name}...[/dim]")
|
||||
|
||||
ok, output = _git_pull_plugin_dir(target)
|
||||
if not ok:
|
||||
console.print(f"[red]Error:[/red] {output}")
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["git", "pull", "--ff-only"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=60,
|
||||
cwd=str(target),
|
||||
)
|
||||
except FileNotFoundError:
|
||||
console.print("[red]Error:[/red] git is not installed or not in PATH.")
|
||||
sys.exit(1)
|
||||
except subprocess.TimeoutExpired:
|
||||
console.print("[red]Error:[/red] Git pull timed out after 60 seconds.")
|
||||
sys.exit(1)
|
||||
|
||||
if result.returncode != 0:
|
||||
console.print(f"[red]Error:[/red] Git pull failed:\n{result.stderr.strip()}")
|
||||
sys.exit(1)
|
||||
|
||||
# Copy any new .example files
|
||||
_copy_example_files(target, console)
|
||||
|
||||
out = output.strip()
|
||||
if "Already up to date" in out:
|
||||
output = result.stdout.strip()
|
||||
if "Already up to date" in output:
|
||||
console.print(
|
||||
f"[green]✓[/green] Plugin [bold]{name}[/bold] is already up to date."
|
||||
)
|
||||
else:
|
||||
console.print(f"[green]✓[/green] Plugin [bold]{name}[/bold] updated.")
|
||||
console.print(f"[dim]{out}[/dim]")
|
||||
console.print(f"[dim]{output}[/dim]")
|
||||
|
||||
|
||||
def cmd_remove(name: str) -> None:
|
||||
@@ -1268,247 +1244,6 @@ def _run_composite_fallback(plugin_names, plugin_labels, plugin_selected,
|
||||
print()
|
||||
|
||||
|
||||
def dashboard_install_plugin(
|
||||
identifier: str,
|
||||
*,
|
||||
force: bool,
|
||||
enable: bool,
|
||||
) -> dict[str, Any]:
|
||||
"""Non-interactive install for the web dashboard. Returns a JSON-serializable dict."""
|
||||
warnings: list[str] = []
|
||||
try:
|
||||
git_url = _resolve_git_url(identifier)
|
||||
if git_url.startswith(("http://", "file://")):
|
||||
warnings.append(
|
||||
"Insecure URL scheme; prefer https:// or git@ for production installs.",
|
||||
)
|
||||
except ValueError:
|
||||
pass
|
||||
|
||||
try:
|
||||
target, installed_manifest, installed_name = _install_plugin_core(
|
||||
identifier,
|
||||
force=force,
|
||||
)
|
||||
except PluginOperationError as exc:
|
||||
return {"ok": False, "error": str(exc)}
|
||||
|
||||
missing_env = _missing_requires_env_names(installed_manifest)
|
||||
if enable:
|
||||
en = _get_enabled_set()
|
||||
dis = _get_disabled_set()
|
||||
en.add(installed_name)
|
||||
dis.discard(installed_name)
|
||||
_save_enabled_set(en)
|
||||
_save_disabled_set(dis)
|
||||
|
||||
hint: str | None = None
|
||||
ap = target / "after-install.md"
|
||||
if ap.exists():
|
||||
hint = str(ap)
|
||||
|
||||
return {
|
||||
"ok": True,
|
||||
"plugin_name": installed_name,
|
||||
"warnings": warnings,
|
||||
"missing_env": missing_env,
|
||||
"after_install_path": hint,
|
||||
"enabled": enable,
|
||||
}
|
||||
|
||||
|
||||
def _get_plugin_toolset_key(name: str) -> Optional[str]:
|
||||
"""Return the toolset key a plugin registers its tools under, or None.
|
||||
|
||||
Queries the live tool registry — the plugin must already be loaded.
|
||||
Falls back to reading ``provides_tools`` from plugin.yaml and looking
|
||||
up the toolset from the registry for the first tool name found.
|
||||
"""
|
||||
try:
|
||||
from tools.registry import registry
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
# Check the plugin manager for tools this plugin registered
|
||||
try:
|
||||
from hermes_cli.plugins import discover_plugins, get_plugin_manager
|
||||
discover_plugins() # idempotent — ensures plugins are loaded
|
||||
manager = get_plugin_manager()
|
||||
for _key, loaded in manager._plugins.items():
|
||||
if loaded.manifest.name == name or _key == name:
|
||||
for tool_name in loaded.tools_registered:
|
||||
entry = registry.get_entry(tool_name)
|
||||
if entry and entry.toolset:
|
||||
return entry.toolset
|
||||
break
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Fallback: read provides_tools from manifest on disk and query registry
|
||||
try:
|
||||
from hermes_cli.plugins import get_bundled_plugins_dir
|
||||
for base in (get_bundled_plugins_dir(), _plugins_dir()):
|
||||
if not base.is_dir():
|
||||
continue
|
||||
candidate = base / name
|
||||
if candidate.is_dir():
|
||||
manifest = _read_manifest(candidate)
|
||||
for tool_name in manifest.get("provides_tools") or []:
|
||||
entry = registry.get_entry(tool_name)
|
||||
if entry and entry.toolset:
|
||||
return entry.toolset
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def _toggle_plugin_toolset(name: str, *, enable: bool) -> None:
|
||||
"""Add or remove a plugin's toolset from platform_toolsets for all platforms.
|
||||
|
||||
Only acts if the plugin actually provides tools (has a toolset key).
|
||||
"""
|
||||
toolset_key = _get_plugin_toolset_key(name)
|
||||
if not toolset_key:
|
||||
return
|
||||
|
||||
from hermes_cli.config import load_config, save_config
|
||||
|
||||
config = load_config()
|
||||
platform_toolsets = config.get("platform_toolsets")
|
||||
if not isinstance(platform_toolsets, dict):
|
||||
platform_toolsets = {}
|
||||
config["platform_toolsets"] = platform_toolsets
|
||||
|
||||
changed = False
|
||||
for platform, ts_list in platform_toolsets.items():
|
||||
if not isinstance(ts_list, list):
|
||||
continue
|
||||
if enable:
|
||||
if toolset_key not in ts_list:
|
||||
ts_list.append(toolset_key)
|
||||
changed = True
|
||||
else:
|
||||
if toolset_key in ts_list:
|
||||
ts_list.remove(toolset_key)
|
||||
changed = True
|
||||
|
||||
# If enabling and no platforms have toolset lists yet, add to "cli" at minimum
|
||||
if enable and not changed and not platform_toolsets:
|
||||
platform_toolsets["cli"] = [toolset_key]
|
||||
changed = True
|
||||
|
||||
if changed:
|
||||
save_config(config)
|
||||
|
||||
|
||||
def dashboard_set_agent_plugin_enabled(name: str, *, enabled: bool) -> dict[str, Any]:
|
||||
"""Enable or disable a plugin in ``config.yaml`` (runtime allow/deny lists).
|
||||
|
||||
For plugins that provide tools (toolsets), also toggles the toolset in
|
||||
``platform_toolsets`` so the agent actually sees the tools in sessions.
|
||||
"""
|
||||
if not _plugin_exists(name):
|
||||
return {"ok": False, "error": f"Plugin '{name}' is not installed or bundled."}
|
||||
|
||||
en = _get_enabled_set()
|
||||
dis = _get_disabled_set()
|
||||
|
||||
if enabled:
|
||||
if name in en and name not in dis:
|
||||
return {"ok": True, "name": name, "unchanged": True}
|
||||
en.add(name)
|
||||
dis.discard(name)
|
||||
_save_enabled_set(en)
|
||||
_save_disabled_set(dis)
|
||||
_toggle_plugin_toolset(name, enable=True)
|
||||
return {"ok": True, "name": name, "unchanged": False}
|
||||
|
||||
if name not in en and name in dis:
|
||||
return {"ok": True, "name": name, "unchanged": True}
|
||||
|
||||
en.discard(name)
|
||||
dis.add(name)
|
||||
_save_enabled_set(en)
|
||||
_save_disabled_set(dis)
|
||||
_toggle_plugin_toolset(name, enable=False)
|
||||
return {"ok": True, "name": name, "unchanged": False}
|
||||
|
||||
|
||||
def _user_installed_plugin_dir(name: str) -> Optional[Path]:
|
||||
"""Resolved path under ``~/.hermes/plugins/<name>`` if it exists."""
|
||||
plugins_dir = _plugins_dir()
|
||||
try:
|
||||
target = _sanitize_plugin_name(name, plugins_dir)
|
||||
except ValueError:
|
||||
return None
|
||||
return target if target.is_dir() else None
|
||||
|
||||
|
||||
def dashboard_update_user_plugin(name: str) -> dict[str, Any]:
|
||||
"""``git pull`` inside ``~/.hermes/plugins/<name>``."""
|
||||
target = _user_installed_plugin_dir(name)
|
||||
if target is None:
|
||||
return {
|
||||
"ok": False,
|
||||
"error": f"Plugin '{name}' was not found under {_plugins_dir()}.",
|
||||
}
|
||||
|
||||
if not (target / ".git").exists():
|
||||
return {
|
||||
"ok": False,
|
||||
"error": f"Plugin '{name}' is not a git checkout; cannot pull updates.",
|
||||
}
|
||||
|
||||
ok, msg = _git_pull_plugin_dir(target)
|
||||
if not ok:
|
||||
return {"ok": False, "error": msg}
|
||||
|
||||
from rich.console import Console
|
||||
|
||||
_copy_example_files(target, Console())
|
||||
unchanged = "Already up to date" in msg
|
||||
return {"ok": True, "name": name, "output": msg, "unchanged": unchanged}
|
||||
|
||||
|
||||
def _git_pull_plugin_dir(target: Path) -> tuple[bool, str]:
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["git", "pull", "--ff-only"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=60,
|
||||
cwd=str(target),
|
||||
)
|
||||
except FileNotFoundError:
|
||||
return False, "git is not installed or not in PATH."
|
||||
except subprocess.TimeoutExpired:
|
||||
return False, "Git pull timed out after 60 seconds."
|
||||
|
||||
if result.returncode != 0:
|
||||
err = (result.stderr or "").strip() or result.stdout.strip()
|
||||
return False, err or "git pull failed."
|
||||
return True, result.stdout.strip()
|
||||
|
||||
|
||||
def dashboard_remove_user_plugin(name: str) -> dict[str, Any]:
|
||||
"""Delete a plugin tree under ``~/.hermes/plugins/`` only."""
|
||||
plugins_dir = _plugins_dir()
|
||||
for n, _ver, _d, src, _path in _discover_all_plugins():
|
||||
if n == name and src == "bundled":
|
||||
return {"ok": False, "error": "Bundled plugins cannot be removed from the dashboard."}
|
||||
|
||||
target = _user_installed_plugin_dir(name)
|
||||
if target is None:
|
||||
return {
|
||||
"ok": False,
|
||||
"error": f"Plugin '{name}' was not found under {plugins_dir}.",
|
||||
}
|
||||
|
||||
shutil.rmtree(target)
|
||||
return {"ok": True, "name": name}
|
||||
|
||||
|
||||
def plugins_command(args) -> None:
|
||||
"""Dispatch hermes plugins subcommands."""
|
||||
action = getattr(args, "plugins_action", None)
|
||||
|
||||
+2
-11
@@ -11,7 +11,7 @@ zero migration needed.
|
||||
Usage::
|
||||
|
||||
hermes profile create coder # fresh profile + bundled skills
|
||||
hermes profile create coder --clone # also copy config, .env, SOUL.md, skills
|
||||
hermes profile create coder --clone # also copy config, .env, SOUL.md
|
||||
hermes profile create coder --clone-all # full copy of source profile
|
||||
coder chat # use via wrapper alias
|
||||
hermes -p coder chat # or via flag
|
||||
@@ -411,8 +411,7 @@ def create_profile(
|
||||
clone_all:
|
||||
If True, do a full copytree of the source (all state).
|
||||
clone_config:
|
||||
If True, copy config files (config.yaml, .env, SOUL.md), installed
|
||||
skills, and selected profile identity files from the source profile.
|
||||
If True, copy only config files (config.yaml, .env, SOUL.md).
|
||||
no_alias:
|
||||
If True, skip wrapper script creation.
|
||||
|
||||
@@ -470,14 +469,6 @@ def create_profile(
|
||||
if src.exists():
|
||||
shutil.copy2(src, profile_dir / filename)
|
||||
|
||||
# Clone installed skills from the source profile. The dashboard's
|
||||
# "clone from default" flow is expected to preserve both bundled
|
||||
# and user-installed skills so the new profile immediately has the
|
||||
# same agent capabilities as the source profile.
|
||||
source_skills = source_dir / "skills"
|
||||
if source_skills.is_dir():
|
||||
shutil.copytree(source_skills, profile_dir / "skills", dirs_exist_ok=True)
|
||||
|
||||
# Clone memory and other subdirectory files
|
||||
for relpath in _CLONE_SUBDIR_FILES:
|
||||
src = source_dir / relpath
|
||||
|
||||
@@ -358,20 +358,11 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
|
||||
return None
|
||||
if not requested_norm.startswith("custom:"):
|
||||
try:
|
||||
canonical = auth_mod.resolve_provider(requested_norm)
|
||||
auth_mod.resolve_provider(requested_norm)
|
||||
except AuthError:
|
||||
pass
|
||||
else:
|
||||
# A user-declared ``custom_providers`` entry whose name matches
|
||||
# only an *alias* (``kimi`` → built-in ``kimi-coding``) is the
|
||||
# user's intended target — alias rewriting would otherwise hijack
|
||||
# the request. We only defer to the built-in when the raw name is
|
||||
# the canonical provider itself (``nous``, ``openrouter``, …) so
|
||||
# accidentally shadowing a canonical provider still resolves to
|
||||
# the built-in. See tests/hermes_cli/test_runtime_provider_resolution.py
|
||||
# ``test_named_custom_provider_does_not_shadow_builtin_provider``.
|
||||
if (canonical or "").strip().lower() == requested_norm:
|
||||
return None
|
||||
return None
|
||||
|
||||
config = load_config()
|
||||
|
||||
|
||||
@@ -1,445 +0,0 @@
|
||||
"""CLI subcommand: ``hermes send`` — pipe text from shell scripts to any
|
||||
configured messaging platform (Telegram, Discord, Slack, Signal, SMS, etc.).
|
||||
|
||||
This is a thin wrapper around ``tools.send_message_tool.send_message_tool``
|
||||
that exposes its functionality as a standalone CLI entry point so ops
|
||||
scripts, cron jobs, CI hooks, and monitoring daemons can reuse the gateway's
|
||||
already-configured credentials without having to reimplement each platform's
|
||||
REST API client.
|
||||
|
||||
Design notes:
|
||||
|
||||
* No LLM, no agent loop — the subcommand just resolves arguments, reads the
|
||||
message body, calls the shared tool function, and prints/returns the
|
||||
result. It is intentionally fast, cheap, and side-effect-only.
|
||||
* For platforms that send via bot token (Telegram, Discord, Slack, Signal,
|
||||
SMS, WhatsApp-CloudAPI, …) no running gateway is required. The tool
|
||||
talks directly to each platform's REST endpoint. For platforms that rely
|
||||
on a persistent adapter connection (plugin platforms, Matrix in some
|
||||
modes, …) a live gateway is needed; the underlying tool surfaces that
|
||||
error to the caller.
|
||||
* Exit codes follow the classic Unix convention:
|
||||
0 — delivery (or list) succeeded
|
||||
1 — delivery failed at the platform level
|
||||
2 — usage / argument / config error (argparse already uses 2)
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
|
||||
_USAGE_EXIT = 2
|
||||
_FAILURE_EXIT = 1
|
||||
_SUCCESS_EXIT = 0
|
||||
|
||||
|
||||
def _read_message_body(
|
||||
positional: Optional[str],
|
||||
file_path: Optional[str],
|
||||
) -> Optional[str]:
|
||||
"""Resolve the message body from (in order):
|
||||
|
||||
1. An explicit positional message argument.
|
||||
2. ``--file PATH`` or ``--file -`` (where ``-`` means stdin).
|
||||
3. Piped stdin when it is not attached to a TTY.
|
||||
|
||||
Returns ``None`` when nothing is available — callers must treat that as
|
||||
a usage error.
|
||||
"""
|
||||
if positional:
|
||||
return positional
|
||||
|
||||
if file_path:
|
||||
if file_path == "-":
|
||||
return sys.stdin.read()
|
||||
try:
|
||||
return Path(file_path).read_text()
|
||||
except OSError as exc:
|
||||
print(f"hermes send: cannot read {file_path}: {exc}", file=sys.stderr)
|
||||
sys.exit(_USAGE_EXIT)
|
||||
|
||||
# Piped input: only consume stdin when it is not a TTY. Reading from a
|
||||
# TTY would block the user in a half-broken "type your message" state,
|
||||
# which is a poor default for an ops CLI.
|
||||
if not sys.stdin.isatty():
|
||||
data = sys.stdin.read()
|
||||
if data:
|
||||
return data
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def _resolve_target(arg_to: Optional[str]) -> Optional[str]:
|
||||
"""Return a cleaned ``--to`` value, or ``None`` when nothing is set."""
|
||||
if arg_to and arg_to.strip():
|
||||
return arg_to.strip()
|
||||
return None
|
||||
|
||||
|
||||
def _emit_result(
|
||||
result_json: str,
|
||||
*,
|
||||
json_mode: bool,
|
||||
quiet: bool,
|
||||
) -> int:
|
||||
"""Print the tool result in the requested format and return the exit code.
|
||||
|
||||
The underlying ``send_message_tool`` always returns a JSON string. We
|
||||
parse it, decide success/failure, and format accordingly.
|
||||
"""
|
||||
try:
|
||||
payload = json.loads(result_json) if result_json else {}
|
||||
except json.JSONDecodeError:
|
||||
# Shouldn't happen with the shared tool, but be defensive — pass the
|
||||
# raw string through so the user can still see what went wrong.
|
||||
payload = {"error": "invalid JSON from send_message_tool", "raw": result_json}
|
||||
|
||||
if json_mode:
|
||||
print(json.dumps(payload, indent=2))
|
||||
elif quiet:
|
||||
pass
|
||||
else:
|
||||
if payload.get("error"):
|
||||
print(f"hermes send: {payload['error']}", file=sys.stderr)
|
||||
elif payload.get("success"):
|
||||
note = payload.get("note")
|
||||
if note:
|
||||
print(note)
|
||||
else:
|
||||
print("sent")
|
||||
else:
|
||||
# Unknown shape — dump it so nothing is silently dropped.
|
||||
print(json.dumps(payload, indent=2))
|
||||
|
||||
if payload.get("error"):
|
||||
return _FAILURE_EXIT
|
||||
if payload.get("skipped"):
|
||||
return _SUCCESS_EXIT
|
||||
if payload.get("success"):
|
||||
return _SUCCESS_EXIT
|
||||
# Unknown / unexpected — treat as failure so scripts notice.
|
||||
return _FAILURE_EXIT
|
||||
|
||||
|
||||
def _list_targets(platform_filter: Optional[str], *, json_mode: bool) -> int:
|
||||
"""Print the channel directory (all configured targets across platforms).
|
||||
|
||||
Uses ``load_directory()`` for structured JSON output and
|
||||
``format_directory_for_display()`` for the human-readable rendering that
|
||||
the send_message tool itself shows to the model — keeps the two surfaces
|
||||
identical.
|
||||
"""
|
||||
try:
|
||||
from gateway.channel_directory import (
|
||||
format_directory_for_display,
|
||||
load_directory,
|
||||
)
|
||||
except Exception as exc:
|
||||
print(f"hermes send: failed to load channel directory: {exc}", file=sys.stderr)
|
||||
return _FAILURE_EXIT
|
||||
|
||||
try:
|
||||
raw = load_directory()
|
||||
except Exception as exc:
|
||||
print(f"hermes send: failed to read channel directory: {exc}", file=sys.stderr)
|
||||
return _FAILURE_EXIT
|
||||
|
||||
platforms = dict(raw.get("platforms") or {})
|
||||
|
||||
if platform_filter:
|
||||
key = platform_filter.strip().lower()
|
||||
filtered = {k: v for k, v in platforms.items() if k.lower() == key}
|
||||
if not filtered:
|
||||
print(
|
||||
f"hermes send: no targets found for platform '{platform_filter}'. "
|
||||
f"Configured: {', '.join(sorted(platforms)) or '(none)'}",
|
||||
file=sys.stderr,
|
||||
)
|
||||
return _FAILURE_EXIT
|
||||
platforms = filtered
|
||||
|
||||
if json_mode:
|
||||
print(json.dumps({"platforms": platforms}, indent=2, default=str))
|
||||
return _SUCCESS_EXIT
|
||||
|
||||
if not any(platforms.values()):
|
||||
print("No messaging platforms configured or no channels discovered yet.")
|
||||
print("Set one up with `hermes gateway setup`, or run the gateway once so")
|
||||
print("channel discovery can populate ~/.hermes/channel_directory.json.")
|
||||
return _SUCCESS_EXIT
|
||||
|
||||
# Human display — when unfiltered, reuse the shared formatter the agent
|
||||
# already sees. When filtered, build a minimal view ourselves.
|
||||
if platform_filter is None:
|
||||
print(format_directory_for_display())
|
||||
return _SUCCESS_EXIT
|
||||
|
||||
for plat_name in sorted(platforms):
|
||||
channels = platforms[plat_name]
|
||||
print(f"{plat_name}:")
|
||||
if not channels:
|
||||
print(" (no channels discovered yet)")
|
||||
continue
|
||||
for ch in channels:
|
||||
name = ch.get("name", "?")
|
||||
chat_id = ch.get("id") or ch.get("chat_id") or ""
|
||||
suffix = f" [{chat_id}]" if chat_id and chat_id != name else ""
|
||||
print(f" {plat_name}:{name}{suffix}")
|
||||
print()
|
||||
|
||||
return _SUCCESS_EXIT
|
||||
|
||||
|
||||
def _load_hermes_env() -> None:
|
||||
"""Populate ``os.environ`` from ``~/.hermes/.env`` AND bridge top-level
|
||||
``config.yaml`` keys into the environment so the underlying gateway
|
||||
config loader sees platform credentials and home channel IDs.
|
||||
|
||||
``send_message_tool`` reads tokens and home-channel IDs via
|
||||
``os.getenv(...)`` on each call. The gateway process does two things at
|
||||
startup that ``hermes send`` must replicate when invoked standalone:
|
||||
|
||||
1. ``load_dotenv(~/.hermes/.env)`` — brings bot tokens into the env.
|
||||
2. Bridge top-level simple values from ``~/.hermes/config.yaml`` into
|
||||
``os.environ`` (without overriding existing env vars). This is where
|
||||
``TELEGRAM_HOME_CHANNEL`` and friends live when the user saved them
|
||||
via ``hermes config set``.
|
||||
|
||||
See ``gateway/run.py`` for the canonical version of this bridge — we
|
||||
intentionally reimplement the minimum needed here so ``hermes send``
|
||||
doesn't pull in the full gateway module just to resolve a home channel.
|
||||
"""
|
||||
# Step 1: dotenv
|
||||
try:
|
||||
from dotenv import load_dotenv
|
||||
except Exception:
|
||||
load_dotenv = None # type: ignore[assignment]
|
||||
|
||||
try:
|
||||
from hermes_cli.config import get_hermes_home
|
||||
home = get_hermes_home()
|
||||
except Exception:
|
||||
return
|
||||
|
||||
env_path = home / ".env"
|
||||
if load_dotenv and env_path.exists():
|
||||
try:
|
||||
load_dotenv(str(env_path), override=True, encoding="utf-8")
|
||||
except UnicodeDecodeError:
|
||||
try:
|
||||
load_dotenv(str(env_path), override=True, encoding="latin-1")
|
||||
except Exception:
|
||||
pass
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Step 2: bridge top-level config.yaml values into the environment so
|
||||
# gateway.config.load_gateway_config() sees them. Scalars only; don't
|
||||
# override values already in the env.
|
||||
import os
|
||||
config_path = home / "config.yaml"
|
||||
if not config_path.exists():
|
||||
return
|
||||
|
||||
try:
|
||||
import yaml # type: ignore[import-not-found]
|
||||
except Exception:
|
||||
return
|
||||
|
||||
try:
|
||||
with open(config_path, "r", encoding="utf-8") as fh:
|
||||
raw = yaml.safe_load(fh) or {}
|
||||
except Exception:
|
||||
return
|
||||
|
||||
try:
|
||||
from hermes_cli.config import _expand_env_vars
|
||||
raw = _expand_env_vars(raw)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
if not isinstance(raw, dict):
|
||||
return
|
||||
|
||||
for key, val in raw.items():
|
||||
if not isinstance(val, (str, int, float, bool)):
|
||||
continue
|
||||
if key in os.environ:
|
||||
continue
|
||||
os.environ[key] = str(val)
|
||||
|
||||
|
||||
def cmd_send(args: argparse.Namespace) -> None:
|
||||
"""Entry point wired into the top-level argparse dispatcher."""
|
||||
|
||||
# Bridge ~/.hermes/.env and ~/.hermes/config.yaml into os.environ so the
|
||||
# gateway config loader (invoked downstream by send_message_tool and by
|
||||
# the channel directory) can see platform credentials and home channels.
|
||||
_load_hermes_env()
|
||||
|
||||
# --list short-circuits everything else.
|
||||
if getattr(args, "list_targets", False):
|
||||
# When `--list telegram` is used, argparse stores "telegram" in the
|
||||
# `message` positional (since list_targets takes no argument).
|
||||
platform_filter = getattr(args, "message", None)
|
||||
exit_code = _list_targets(platform_filter, json_mode=getattr(args, "json", False))
|
||||
sys.exit(exit_code)
|
||||
|
||||
target = _resolve_target(getattr(args, "to", None))
|
||||
if not target:
|
||||
print(
|
||||
"hermes send: --to PLATFORM[:channel[:thread]] is required\n"
|
||||
"Examples:\n"
|
||||
" hermes send --to telegram \"hello\"\n"
|
||||
" hermes send --to discord:#ops --file report.md\n"
|
||||
" hermes send --list # list available targets",
|
||||
file=sys.stderr,
|
||||
)
|
||||
sys.exit(_USAGE_EXIT)
|
||||
|
||||
message = _read_message_body(
|
||||
getattr(args, "message", None),
|
||||
getattr(args, "file", None),
|
||||
)
|
||||
if message is None or not message.strip():
|
||||
print(
|
||||
"hermes send: no message provided. Pass text as a positional "
|
||||
"argument, use --file PATH, or pipe data via stdin.",
|
||||
file=sys.stderr,
|
||||
)
|
||||
sys.exit(_USAGE_EXIT)
|
||||
|
||||
# Optional: prepend a subject line. Useful for alerting scripts that
|
||||
# want a consistent header without inlining it into every call.
|
||||
subject = getattr(args, "subject", None)
|
||||
if subject:
|
||||
message = f"{subject}\n\n{message.lstrip()}"
|
||||
|
||||
# Import lazily so `hermes send --help` stays fast and does not pull in
|
||||
# the full tool registry / gateway config stack.
|
||||
from tools.send_message_tool import send_message_tool
|
||||
|
||||
# send_message_tool auto-loads gateway config + env and routes to the
|
||||
# appropriate platform adapter (bot-token path for Telegram/Discord/Slack/
|
||||
# Signal/SMS/WhatsApp; live-adapter path for plugin platforms).
|
||||
#
|
||||
# It expects the standard tool-call dict and returns a JSON string.
|
||||
tool_args = {
|
||||
"action": "send",
|
||||
"target": target,
|
||||
"message": message,
|
||||
}
|
||||
|
||||
result = send_message_tool(tool_args)
|
||||
exit_code = _emit_result(
|
||||
result,
|
||||
json_mode=getattr(args, "json", False),
|
||||
quiet=getattr(args, "quiet", False),
|
||||
)
|
||||
sys.exit(exit_code)
|
||||
|
||||
|
||||
def register_send_subparser(subparsers) -> argparse.ArgumentParser:
|
||||
"""Create the ``send`` subparser and return it.
|
||||
|
||||
Kept as a standalone function so the top-level parser builder can wire
|
||||
it in next to the other messaging subcommands without cluttering
|
||||
``_parser.py`` or ``main.py``.
|
||||
"""
|
||||
parser = subparsers.add_parser(
|
||||
"send",
|
||||
help="Send a message to a configured platform (scripts, cron jobs, CI).",
|
||||
description=(
|
||||
"Pipe text from any shell script to any messaging platform Hermes "
|
||||
"is already configured for. Reuses the gateway's platform "
|
||||
"credentials (~/.hermes/.env + ~/.hermes/config.yaml) — no LLM, "
|
||||
"no agent loop, no running gateway required for bot-token "
|
||||
"platforms like Telegram/Discord/Slack/Signal."
|
||||
),
|
||||
epilog=(
|
||||
"Examples:\n"
|
||||
" hermes send --to telegram \"deploy finished\"\n"
|
||||
" echo \"RAM 92%\" | hermes send --to telegram:-1001234567890\n"
|
||||
" hermes send --to discord:#ops --file /tmp/report.md\n"
|
||||
" hermes send --to slack:#eng --subject \"[CI]\" --file build.log\n"
|
||||
" hermes send --list # all platforms\n"
|
||||
" hermes send --list telegram # filter by platform\n"
|
||||
"\n"
|
||||
"Exit codes: 0 ok, 1 delivery/backend error, 2 usage error."
|
||||
),
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"-t",
|
||||
"--to",
|
||||
metavar="TARGET",
|
||||
default=None,
|
||||
help=(
|
||||
"Delivery target. Format: 'platform' (home channel), "
|
||||
"'platform:chat_id', 'platform:chat_id:thread_id', or "
|
||||
"'platform:#channel-name'. Examples: telegram, "
|
||||
"telegram:-1001234567890:17585, discord:#ops, slack:C0123ABCD, "
|
||||
"signal:+15551234567."
|
||||
),
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"message",
|
||||
nargs="?",
|
||||
default=None,
|
||||
help="Message text. If omitted, read from --file or stdin.",
|
||||
)
|
||||
|
||||
# Legacy / convenience positional removed — use --to for clarity.
|
||||
|
||||
parser.add_argument(
|
||||
"-f",
|
||||
"--file",
|
||||
metavar="PATH",
|
||||
default=None,
|
||||
help="Read message body from PATH. Use '-' to force stdin.",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"-s",
|
||||
"--subject",
|
||||
metavar="LINE",
|
||||
default=None,
|
||||
help="Prepend a subject/header line before the message body.",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"-l",
|
||||
"--list",
|
||||
dest="list_targets",
|
||||
action="store_true",
|
||||
default=False,
|
||||
help="List available targets. Optional positional filter: `hermes send --list telegram`.",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"-q",
|
||||
"--quiet",
|
||||
action="store_true",
|
||||
default=False,
|
||||
help="Suppress stdout on success (exit code only).",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--json",
|
||||
action="store_true",
|
||||
default=False,
|
||||
help="Emit raw JSON result instead of human-readable output.",
|
||||
)
|
||||
|
||||
parser.set_defaults(func=cmd_send)
|
||||
return parser
|
||||
|
||||
|
||||
__all__ = ["cmd_send", "register_send_subparser"]
|
||||
+12
-55
@@ -1190,13 +1190,6 @@ def _setup_tts_provider(config: dict):
|
||||
"Falling back to Edge TTS."
|
||||
)
|
||||
selected = "edge"
|
||||
if selected == "xai":
|
||||
print()
|
||||
voice_id = prompt("xAI voice_id (Enter for 'eve', or paste a custom voice ID)")
|
||||
if voice_id and voice_id.strip():
|
||||
config.setdefault("tts", {}).setdefault("xai", {})["voice_id"] = voice_id.strip()
|
||||
print_success(f"xAI voice_id set to: {voice_id.strip()}")
|
||||
|
||||
|
||||
elif selected == "minimax":
|
||||
existing = get_env_value("MINIMAX_API_KEY")
|
||||
@@ -1328,13 +1321,15 @@ def setup_terminal_backend(config: dict):
|
||||
print_success("Terminal backend: Local")
|
||||
print_info("Commands run directly on this machine.")
|
||||
|
||||
# Gateway/cron working directory
|
||||
# CWD for messaging
|
||||
print()
|
||||
print_info("Gateway working directory:")
|
||||
print_info(" Used by Telegram/Discord/cron sessions.")
|
||||
print_info(" CLI/TUI always uses your launch directory instead.")
|
||||
print_info("Working directory for messaging sessions:")
|
||||
print_info(" When using Hermes via Telegram/Discord, this is where")
|
||||
print_info(
|
||||
" the agent starts. CLI mode always starts in the current directory."
|
||||
)
|
||||
current_cwd = cfg_get(config, "terminal", "cwd", default="")
|
||||
cwd = prompt(" Gateway working directory", current_cwd or str(Path.home()))
|
||||
cwd = prompt(" Messaging working directory", current_cwd or str(Path.home()))
|
||||
if cwd:
|
||||
config["terminal"]["cwd"] = cwd
|
||||
|
||||
@@ -1648,11 +1643,7 @@ def setup_terminal_backend(config: dict):
|
||||
def _apply_default_agent_settings(config: dict):
|
||||
"""Apply recommended defaults for all agent settings without prompting."""
|
||||
config.setdefault("agent", {})["max_turns"] = 90
|
||||
# config.yaml is the authoritative source for max_turns; the gateway
|
||||
# bridges it into HERMES_MAX_ITERATIONS at startup. We no longer write
|
||||
# to .env to avoid the dual-source inconsistency that caused the
|
||||
# 60-vs-500 bug (stale .env entry silently shadowing config.yaml).
|
||||
remove_env_value("HERMES_MAX_ITERATIONS")
|
||||
save_env_value("HERMES_MAX_ITERATIONS", "90")
|
||||
|
||||
config.setdefault("display", {})["tool_progress"] = "all"
|
||||
|
||||
@@ -1682,10 +1673,9 @@ def setup_agent_settings(config: dict):
|
||||
print()
|
||||
|
||||
# ── Max Iterations ──
|
||||
# config.yaml is authoritative; read from there. If a legacy .env
|
||||
# entry is still around (from pre-PR#18413 setups), prefer the
|
||||
# config value so we don't surface a stale number to the user.
|
||||
current_max = str(cfg_get(config, "agent", "max_turns", default=90))
|
||||
current_max = get_env_value("HERMES_MAX_ITERATIONS") or str(
|
||||
cfg_get(config, "agent", "max_turns", default=90)
|
||||
)
|
||||
print_info("Maximum tool-calling iterations per conversation.")
|
||||
print_info("Higher = more complex tasks, but costs more tokens.")
|
||||
print_info(
|
||||
@@ -1696,13 +1686,9 @@ def setup_agent_settings(config: dict):
|
||||
try:
|
||||
max_iter = int(max_iter_str)
|
||||
if max_iter > 0:
|
||||
# Write to config.yaml (authoritative) only. Also clean up any
|
||||
# stale .env entry from earlier setup runs — the gateway's
|
||||
# bridge in gateway/run.py now unconditionally derives
|
||||
# HERMES_MAX_ITERATIONS from agent.max_turns at startup.
|
||||
save_env_value("HERMES_MAX_ITERATIONS", str(max_iter))
|
||||
config.setdefault("agent", {})["max_turns"] = max_iter
|
||||
config.pop("max_turns", None)
|
||||
remove_env_value("HERMES_MAX_ITERATIONS")
|
||||
print_success(f"Max iterations set to {max_iter}")
|
||||
except ValueError:
|
||||
print_warning("Invalid number, keeping current value")
|
||||
@@ -2047,16 +2033,6 @@ def _setup_slack():
|
||||
print_warning("⚠️ No Slack allowlist set - unpaired users will be denied by default.")
|
||||
print_info(" Set SLACK_ALLOW_ALL_USERS=true or GATEWAY_ALLOW_ALL_USERS=true only if you intentionally want open workspace access.")
|
||||
|
||||
print()
|
||||
print_info("📬 Home Channel: where Hermes delivers cron job results,")
|
||||
print_info(" cross-platform messages, and notifications.")
|
||||
print_info(" To get a channel ID: open the channel in Slack, then right-click")
|
||||
print_info(" the channel name → Copy link — the ID starts with C (e.g. C01ABC2DE3F).")
|
||||
print_info(" You can also set this later by typing /set-home in a Slack channel.")
|
||||
home_channel = prompt("Home channel ID (leave empty to set later with /set-home)")
|
||||
if home_channel:
|
||||
save_env_value("SLACK_HOME_CHANNEL", home_channel.strip())
|
||||
|
||||
|
||||
def _write_slack_manifest_and_instruct():
|
||||
"""Generate the Slack manifest, write it under HERMES_HOME, and print
|
||||
@@ -3003,21 +2979,6 @@ def run_setup_wizard(args):
|
||||
config = load_config()
|
||||
hermes_home = get_hermes_home()
|
||||
|
||||
# Back up existing config before setup modifies it (#3522)
|
||||
config_path = get_config_path()
|
||||
if config_path.exists():
|
||||
from datetime import datetime as _dt
|
||||
_backup_path = config_path.with_suffix(
|
||||
f".yaml.bak.{_dt.now().strftime('%Y%m%d_%H%M%S')}"
|
||||
)
|
||||
try:
|
||||
import shutil
|
||||
shutil.copy2(config_path, _backup_path)
|
||||
except Exception:
|
||||
_backup_path = None
|
||||
else:
|
||||
_backup_path = None
|
||||
|
||||
# Detect non-interactive environments (headless SSH, Docker, CI/CD)
|
||||
non_interactive = getattr(args, 'non_interactive', False)
|
||||
if not non_interactive and not is_interactive_stdin():
|
||||
@@ -3187,10 +3148,6 @@ def run_setup_wizard(args):
|
||||
|
||||
# Save and show summary
|
||||
save_config(config)
|
||||
if _backup_path and _backup_path.exists():
|
||||
print_info(f"Previous config backed up to: {_backup_path}")
|
||||
print_info("If setup changed a value you customized, restore it with:")
|
||||
print_info(f" cp {_backup_path} {config_path}")
|
||||
_print_setup_summary(config, hermes_home)
|
||||
|
||||
_offer_launch_chat()
|
||||
|
||||
@@ -18,7 +18,6 @@ for reinstall when scopes/commands change.
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
@@ -129,7 +128,7 @@ def slack_manifest_command(args) -> int:
|
||||
|
||||
target = Path(get_hermes_home()) / "slack-manifest.json"
|
||||
except Exception:
|
||||
target = Path(os.environ.get("HERMES_HOME") or str(Path.home() / ".hermes")) / "slack-manifest.json"
|
||||
target = Path.home() / ".hermes" / "slack-manifest.json"
|
||||
else:
|
||||
target = Path(write_target).expanduser()
|
||||
target.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
@@ -125,7 +125,6 @@ def show_status(args):
|
||||
keys = {
|
||||
"OpenRouter": "OPENROUTER_API_KEY",
|
||||
"OpenAI": "OPENAI_API_KEY",
|
||||
"NVIDIA": "NVIDIA_API_KEY",
|
||||
"Z.AI/GLM": "GLM_API_KEY",
|
||||
"Kimi": "KIMI_API_KEY",
|
||||
"StepFun Step Plan": "STEPFUN_API_KEY",
|
||||
|
||||
@@ -56,7 +56,6 @@ CONFIGURABLE_TOOLSETS = [
|
||||
("file", "📁 File Operations", "read, write, patch, search"),
|
||||
("code_execution", "⚡ Code Execution", "execute_code"),
|
||||
("vision", "👁️ Vision / Image Analysis", "vision_analyze"),
|
||||
("video", "🎬 Video Analysis", "video_analyze (requires video-capable model)"),
|
||||
("image_gen", "🎨 Image Generation", "image_generate"),
|
||||
("moa", "🧠 Mixture of Agents", "mixture_of_agents"),
|
||||
("tts", "🔊 Text-to-Speech", "text_to_speech"),
|
||||
@@ -79,7 +78,7 @@ CONFIGURABLE_TOOLSETS = [
|
||||
# Toolsets that are OFF by default for new installs.
|
||||
# They're still in _HERMES_CORE_TOOLS (available at runtime if enabled),
|
||||
# but the setup checklist won't pre-select them for first-time users.
|
||||
_DEFAULT_OFF_TOOLSETS = {"moa", "homeassistant", "rl", "spotify", "discord", "discord_admin", "video"}
|
||||
_DEFAULT_OFF_TOOLSETS = {"moa", "homeassistant", "rl", "spotify", "discord", "discord_admin"}
|
||||
|
||||
# Platform-scoped toolsets: only appear in the `hermes tools` checklist for
|
||||
# these platforms, and only resolve/save for these platforms. A toolset
|
||||
@@ -1823,7 +1822,7 @@ def _reconfigure_tool(config: dict):
|
||||
cat = TOOL_CATEGORIES.get(ts_key)
|
||||
reqs = TOOLSET_ENV_REQUIREMENTS.get(ts_key)
|
||||
if cat or reqs:
|
||||
if _toolset_has_keys(ts_key, config) or _toolset_enabled_for_reconfigure(ts_key, config):
|
||||
if _toolset_has_keys(ts_key, config):
|
||||
configurable.append((ts_key, ts_label))
|
||||
|
||||
if not configurable:
|
||||
@@ -1849,28 +1848,6 @@ def _reconfigure_tool(config: dict):
|
||||
save_config(config)
|
||||
|
||||
|
||||
def _toolset_enabled_for_reconfigure(ts_key: str, config: dict) -> bool:
|
||||
"""Return True if a configurable toolset is enabled anywhere.
|
||||
|
||||
Reconfigure must include enabled-but-unconfigured categories so users can
|
||||
finish provider/API-key setup without disabling and re-enabling the toolset.
|
||||
"""
|
||||
for platform in PLATFORMS:
|
||||
if not _toolset_allowed_for_platform(ts_key, platform):
|
||||
continue
|
||||
try:
|
||||
enabled = _get_platform_tools(
|
||||
config,
|
||||
platform,
|
||||
include_default_mcp_servers=False,
|
||||
)
|
||||
except Exception:
|
||||
continue
|
||||
if ts_key in enabled:
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def _configure_tool_category_for_reconfig(ts_key: str, cat: dict, config: dict):
|
||||
"""Reconfigure a tool category - provider selection + API key update."""
|
||||
icon = cat.get("icon", "")
|
||||
|
||||
+10
-553
@@ -345,7 +345,6 @@ _CATEGORY_MERGE: Dict[str, str] = {
|
||||
"dashboard": "display",
|
||||
"code_execution": "agent",
|
||||
"prompt_caching": "agent",
|
||||
"goals": "agent",
|
||||
# Only `telegram.reactions` currently lives under telegram — fold it in
|
||||
# with the other messaging-platform config (discord) so it isn't an
|
||||
# orphan tab of one field.
|
||||
@@ -470,23 +469,10 @@ except (ValueError, TypeError):
|
||||
)
|
||||
_GATEWAY_HEALTH_TIMEOUT = 3.0
|
||||
|
||||
# DEPRECATED (scheduled for removal): GATEWAY_HEALTH_URL / GATEWAY_HEALTH_TIMEOUT.
|
||||
# Cross-container / cross-host gateway liveness detection will be folded into a
|
||||
# first-class dashboard config key so it's no longer Docker-adjacent lore buried
|
||||
# in env vars. The env vars still work for now so existing Compose deployments
|
||||
# don't break. Do not add new callers — wire new uses through the planned
|
||||
# config surface.
|
||||
|
||||
|
||||
def _probe_gateway_health() -> tuple[bool, dict | None]:
|
||||
"""Probe the gateway via its HTTP health endpoint (cross-container).
|
||||
|
||||
.. deprecated::
|
||||
Driven by the deprecated ``GATEWAY_HEALTH_URL`` /
|
||||
``GATEWAY_HEALTH_TIMEOUT`` env vars. Scheduled for removal alongside
|
||||
a move to a first-class dashboard config key. See
|
||||
:data:`_GATEWAY_HEALTH_URL` for context.
|
||||
|
||||
Uses ``/health/detailed`` first (returns full state), falling back to
|
||||
the simpler ``/health`` endpoint. Returns ``(is_alive, body_dict)``.
|
||||
|
||||
@@ -2358,254 +2344,6 @@ async def delete_cron_job(job_id: str):
|
||||
return {"ok": True}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Profile management endpoints (minimal — list/create/rename/delete + SOUL.md)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class ProfileCreate(BaseModel):
|
||||
name: str
|
||||
clone_from_default: bool = False
|
||||
|
||||
|
||||
class ProfileRename(BaseModel):
|
||||
new_name: str
|
||||
|
||||
|
||||
class ProfileSoulUpdate(BaseModel):
|
||||
content: str
|
||||
|
||||
|
||||
def _profile_attr(info, name: str, default: Any = None) -> Any:
|
||||
try:
|
||||
return getattr(info, name)
|
||||
except Exception:
|
||||
return default
|
||||
|
||||
|
||||
def _profile_to_dict(info) -> Dict[str, Any]:
|
||||
return {
|
||||
"name": _profile_attr(info, "name", ""),
|
||||
"path": str(_profile_attr(info, "path", "")),
|
||||
"is_default": bool(_profile_attr(info, "is_default", False)),
|
||||
"model": _profile_attr(info, "model"),
|
||||
"provider": _profile_attr(info, "provider"),
|
||||
"has_env": bool(_profile_attr(info, "has_env", False)),
|
||||
"skill_count": int(_profile_attr(info, "skill_count", 0) or 0),
|
||||
}
|
||||
|
||||
|
||||
def _fallback_profile_dicts(profiles_mod) -> List[Dict[str, Any]]:
|
||||
def _safe(callable_, default):
|
||||
try:
|
||||
return callable_()
|
||||
except Exception:
|
||||
return default
|
||||
|
||||
profiles: List[Dict[str, Any]] = []
|
||||
default_home = profiles_mod._get_default_hermes_home()
|
||||
if default_home.is_dir():
|
||||
model, provider = _safe(lambda: profiles_mod._read_config_model(default_home), (None, None))
|
||||
profiles.append({
|
||||
"name": "default",
|
||||
"path": str(default_home),
|
||||
"is_default": True,
|
||||
"model": model,
|
||||
"provider": provider,
|
||||
"has_env": (default_home / ".env").exists(),
|
||||
"skill_count": _safe(lambda: profiles_mod._count_skills(default_home), 0),
|
||||
})
|
||||
|
||||
profiles_root = profiles_mod._get_profiles_root()
|
||||
if profiles_root.is_dir():
|
||||
for entry in sorted(profiles_root.iterdir()):
|
||||
if not entry.is_dir() or not profiles_mod._PROFILE_ID_RE.match(entry.name):
|
||||
continue
|
||||
model, provider = _safe(lambda entry=entry: profiles_mod._read_config_model(entry), (None, None))
|
||||
profiles.append({
|
||||
"name": entry.name,
|
||||
"path": str(entry),
|
||||
"is_default": False,
|
||||
"model": model,
|
||||
"provider": provider,
|
||||
"has_env": (entry / ".env").exists(),
|
||||
"skill_count": _safe(lambda entry=entry: profiles_mod._count_skills(entry), 0),
|
||||
})
|
||||
|
||||
return profiles
|
||||
|
||||
|
||||
def _resolve_profile_dir(name: str) -> Path:
|
||||
"""Validate ``name`` and resolve to its directory or raise an HTTPException."""
|
||||
from hermes_cli import profiles as profiles_mod
|
||||
try:
|
||||
profiles_mod.validate_profile_name(name)
|
||||
except ValueError as e:
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
if not profiles_mod.profile_exists(name):
|
||||
raise HTTPException(status_code=404, detail=f"Profile '{name}' does not exist.")
|
||||
return profiles_mod.get_profile_dir(name)
|
||||
|
||||
|
||||
def _profile_setup_command(name: str) -> str:
|
||||
"""Return the shell command used to configure a profile in the CLI."""
|
||||
_resolve_profile_dir(name)
|
||||
return "hermes setup" if name == "default" else f"{name} setup"
|
||||
|
||||
|
||||
@app.get("/api/profiles")
|
||||
async def list_profiles_endpoint():
|
||||
from hermes_cli import profiles as profiles_mod
|
||||
try:
|
||||
return {"profiles": [_profile_to_dict(p) for p in profiles_mod.list_profiles()]}
|
||||
except Exception:
|
||||
_log.exception("GET /api/profiles failed; falling back to profile directory scan")
|
||||
return {"profiles": _fallback_profile_dicts(profiles_mod)}
|
||||
|
||||
|
||||
@app.post("/api/profiles")
|
||||
async def create_profile_endpoint(body: ProfileCreate):
|
||||
from hermes_cli import profiles as profiles_mod
|
||||
try:
|
||||
path = profiles_mod.create_profile(
|
||||
name=body.name,
|
||||
clone_from="default" if body.clone_from_default else None,
|
||||
clone_config=body.clone_from_default,
|
||||
)
|
||||
# Match the CLI's profile-create flow: fresh named profiles get the
|
||||
# bundled skills installed. When cloning from default, create_profile()
|
||||
# has already copied the source profile's skills, including any
|
||||
# user-installed skills.
|
||||
if not body.clone_from_default:
|
||||
profiles_mod.seed_profile_skills(path, quiet=True)
|
||||
|
||||
# Match the CLI's profile-create flow: named profiles should get a
|
||||
# wrapper in ~/.local/bin when the alias is safe to create.
|
||||
collision = profiles_mod.check_alias_collision(body.name)
|
||||
if not collision:
|
||||
profiles_mod.create_wrapper_script(body.name)
|
||||
except (ValueError, FileExistsError, FileNotFoundError) as e:
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
except Exception as e:
|
||||
_log.exception("POST /api/profiles failed")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
return {"ok": True, "name": body.name, "path": str(path)}
|
||||
|
||||
|
||||
@app.get("/api/profiles/{name}/setup-command")
|
||||
async def get_profile_setup_command(name: str):
|
||||
return {"command": _profile_setup_command(name)}
|
||||
|
||||
|
||||
@app.post("/api/profiles/{name}/open-terminal")
|
||||
async def open_profile_terminal_endpoint(name: str):
|
||||
try:
|
||||
command = _profile_setup_command(name)
|
||||
|
||||
if sys.platform.startswith("win"):
|
||||
subprocess.Popen(["cmd.exe", "/c", "start", "", command])
|
||||
elif sys.platform == "darwin":
|
||||
escaped = command.replace("\\", "\\\\").replace('"', '\\"')
|
||||
applescript = (
|
||||
'tell application "Terminal"\n'
|
||||
"activate\n"
|
||||
f'do script "{escaped}"\n'
|
||||
"end tell"
|
||||
)
|
||||
subprocess.Popen(["osascript", "-e", applescript])
|
||||
else:
|
||||
terminal_commands = [
|
||||
("x-terminal-emulator", ["x-terminal-emulator", "-e", "sh", "-lc", command]),
|
||||
("gnome-terminal", ["gnome-terminal", "--", "sh", "-lc", command]),
|
||||
("konsole", ["konsole", "-e", "sh", "-lc", command]),
|
||||
("xfce4-terminal", ["xfce4-terminal", "-e", f"sh -lc '{command}'"]),
|
||||
("mate-terminal", ["mate-terminal", "-e", f"sh -lc '{command}'"]),
|
||||
("lxterminal", ["lxterminal", "-e", f"sh -lc '{command}'"]),
|
||||
("tilix", ["tilix", "-e", "sh", "-lc", command]),
|
||||
("alacritty", ["alacritty", "-e", "sh", "-lc", command]),
|
||||
("kitty", ["kitty", "sh", "-lc", command]),
|
||||
("xterm", ["xterm", "-e", "sh", "-lc", command]),
|
||||
]
|
||||
for executable, popen_args in terminal_commands:
|
||||
if subprocess.call(
|
||||
["which", executable],
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL,
|
||||
) == 0:
|
||||
subprocess.Popen(popen_args)
|
||||
break
|
||||
else:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail="No supported terminal emulator found",
|
||||
)
|
||||
except FileNotFoundError as e:
|
||||
raise HTTPException(status_code=404, detail=str(e))
|
||||
except ValueError as e:
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
_log.exception("POST /api/profiles/%s/open-terminal failed", name)
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
return {"ok": True, "command": command}
|
||||
|
||||
|
||||
@app.patch("/api/profiles/{name}")
|
||||
async def rename_profile_endpoint(name: str, body: ProfileRename):
|
||||
from hermes_cli import profiles as profiles_mod
|
||||
try:
|
||||
path = profiles_mod.rename_profile(name, body.new_name)
|
||||
except FileNotFoundError as e:
|
||||
raise HTTPException(status_code=404, detail=str(e))
|
||||
except (ValueError, FileExistsError) as e:
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
except Exception as e:
|
||||
_log.exception("PATCH /api/profiles/%s failed", name)
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
return {"ok": True, "name": body.new_name, "path": str(path)}
|
||||
|
||||
|
||||
@app.delete("/api/profiles/{name}")
|
||||
async def delete_profile_endpoint(name: str):
|
||||
"""Delete a profile. The dashboard collects the user's confirmation in
|
||||
its own dialog before this request, so we always pass ``yes=True`` to
|
||||
skip the CLI's interactive prompt."""
|
||||
from hermes_cli import profiles as profiles_mod
|
||||
try:
|
||||
path = profiles_mod.delete_profile(name, yes=True)
|
||||
except FileNotFoundError as e:
|
||||
raise HTTPException(status_code=404, detail=str(e))
|
||||
except ValueError as e:
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
except Exception as e:
|
||||
_log.exception("DELETE /api/profiles/%s failed", name)
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
return {"ok": True, "path": str(path)}
|
||||
|
||||
|
||||
@app.get("/api/profiles/{name}/soul")
|
||||
async def get_profile_soul(name: str):
|
||||
soul_path = _resolve_profile_dir(name) / "SOUL.md"
|
||||
if soul_path.exists():
|
||||
try:
|
||||
return {"content": soul_path.read_text(encoding="utf-8"), "exists": True}
|
||||
except OSError as e:
|
||||
raise HTTPException(status_code=500, detail=f"Could not read SOUL.md: {e}")
|
||||
return {"content": "", "exists": False}
|
||||
|
||||
|
||||
@app.put("/api/profiles/{name}/soul")
|
||||
async def update_profile_soul(name: str, body: ProfileSoulUpdate):
|
||||
soul_path = _resolve_profile_dir(name) / "SOUL.md"
|
||||
try:
|
||||
soul_path.write_text(body.content, encoding="utf-8")
|
||||
except OSError as e:
|
||||
_log.exception("PUT /api/profiles/%s/soul failed", name)
|
||||
raise HTTPException(status_code=500, detail=f"Could not write SOUL.md: {e}")
|
||||
return {"ok": True}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Skills & Tools endpoints
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -2895,25 +2633,6 @@ _VALID_CHANNEL_RE = re.compile(r"^[A-Za-z0-9._-]{1,128}$")
|
||||
# loopback so tests don't need to rewrite request scope.
|
||||
_LOOPBACK_HOSTS = frozenset({"127.0.0.1", "::1", "localhost", "testclient"})
|
||||
|
||||
|
||||
def _is_public_bind() -> bool:
|
||||
"""True when bound to all-interfaces (operator used --insecure)."""
|
||||
return getattr(app.state, "bound_host", "") in ("0.0.0.0", "::")
|
||||
|
||||
|
||||
def _ws_client_is_allowed(ws: "WebSocket") -> bool:
|
||||
"""Check if the WebSocket client IP is acceptable.
|
||||
|
||||
Allows loopback always; allows any IP when bound to all-interfaces
|
||||
(--insecure mode, guarded by session token auth).
|
||||
"""
|
||||
if _is_public_bind():
|
||||
return True
|
||||
client_host = ws.client.host if ws.client else ""
|
||||
if not client_host:
|
||||
return True
|
||||
return client_host in _LOOPBACK_HOSTS
|
||||
|
||||
# Per-channel subscriber registry used by /api/pub (PTY-side gateway → dashboard)
|
||||
# and /api/events (dashboard → browser sidebar). Keyed by an opaque channel id
|
||||
# the chat tab generates on mount; entries auto-evict when the last subscriber
|
||||
@@ -3004,7 +2723,8 @@ async def pty_ws(ws: WebSocket) -> None:
|
||||
await ws.close(code=4401)
|
||||
return
|
||||
|
||||
if not _ws_client_is_allowed(ws):
|
||||
client_host = ws.client.host if ws.client else ""
|
||||
if client_host and client_host not in _LOOPBACK_HOSTS:
|
||||
await ws.close(code=4403)
|
||||
return
|
||||
|
||||
@@ -3111,7 +2831,8 @@ async def gateway_ws(ws: WebSocket) -> None:
|
||||
await ws.close(code=4401)
|
||||
return
|
||||
|
||||
if not _ws_client_is_allowed(ws):
|
||||
client_host = ws.client.host if ws.client else ""
|
||||
if client_host and client_host not in _LOOPBACK_HOSTS:
|
||||
await ws.close(code=4403)
|
||||
return
|
||||
|
||||
@@ -3143,7 +2864,8 @@ async def pub_ws(ws: WebSocket) -> None:
|
||||
await ws.close(code=4401)
|
||||
return
|
||||
|
||||
if not _ws_client_is_allowed(ws):
|
||||
client_host = ws.client.host if ws.client else ""
|
||||
if client_host and client_host not in _LOOPBACK_HOSTS:
|
||||
await ws.close(code=4403)
|
||||
return
|
||||
|
||||
@@ -3172,7 +2894,8 @@ async def events_ws(ws: WebSocket) -> None:
|
||||
await ws.close(code=4401)
|
||||
return
|
||||
|
||||
if not _ws_client_is_allowed(ws):
|
||||
client_host = ws.client.host if ws.client else ""
|
||||
if client_host and client_host not in _LOOPBACK_HOSTS:
|
||||
await ws.close(code=4403)
|
||||
return
|
||||
|
||||
@@ -3646,16 +3369,12 @@ def _get_dashboard_plugins(force_rescan: bool = False) -> list:
|
||||
|
||||
@app.get("/api/dashboard/plugins")
|
||||
async def get_dashboard_plugins():
|
||||
"""Return discovered dashboard plugins (excludes user-hidden ones)."""
|
||||
"""Return discovered dashboard plugins."""
|
||||
plugins = _get_dashboard_plugins()
|
||||
# Read user's hidden plugins list from config.
|
||||
config = load_config()
|
||||
hidden: list = cfg_get(config, "dashboard", "hidden_plugins", default=[]) or []
|
||||
# Strip internal fields before sending to frontend and filter out hidden.
|
||||
# Strip internal fields before sending to frontend.
|
||||
return [
|
||||
{k: v for k, v in p.items() if not k.startswith("_")}
|
||||
for p in plugins
|
||||
if p["name"] not in hidden
|
||||
]
|
||||
|
||||
|
||||
@@ -3666,268 +3385,6 @@ async def rescan_dashboard_plugins():
|
||||
return {"ok": True, "count": len(plugins)}
|
||||
|
||||
|
||||
class _AgentPluginInstallBody(BaseModel):
|
||||
identifier: str
|
||||
force: bool = False
|
||||
enable: bool = True
|
||||
|
||||
|
||||
def _strip_dashboard_manifest(p: Dict[str, Any]) -> Dict[str, Any]:
|
||||
return {k: v for k, v in p.items() if not k.startswith("_")}
|
||||
|
||||
|
||||
def _merged_plugins_hub() -> Dict[str, Any]:
|
||||
"""Agent discovery + dashboard manifests + optional provider picker metadata."""
|
||||
from hermes_cli.plugins_cmd import (
|
||||
_discover_all_plugins,
|
||||
_get_current_context_engine,
|
||||
_get_current_memory_provider,
|
||||
_discover_context_engines,
|
||||
_discover_memory_providers,
|
||||
_get_disabled_set,
|
||||
_get_enabled_set,
|
||||
_read_manifest as _read_plugin_manifest_at,
|
||||
)
|
||||
|
||||
dashboard_list = _get_dashboard_plugins()
|
||||
dash_by_name = {str(p["name"]): p for p in dashboard_list}
|
||||
|
||||
disabled_set = _get_disabled_set()
|
||||
enabled_set = _get_enabled_set()
|
||||
|
||||
# Read user-hidden plugins from config for the user_hidden field.
|
||||
config = load_config()
|
||||
hidden_plugins: list = cfg_get(config, "dashboard", "hidden_plugins", default=[]) or []
|
||||
|
||||
plugins_root_resolved = (get_hermes_home() / "plugins").resolve()
|
||||
rows: List[Dict[str, Any]] = []
|
||||
|
||||
for name, version, description, source, dir_str in _discover_all_plugins():
|
||||
if name in disabled_set:
|
||||
runtime_status = "disabled"
|
||||
elif name in enabled_set:
|
||||
runtime_status = "enabled"
|
||||
else:
|
||||
runtime_status = "inactive"
|
||||
|
||||
dir_path = Path(dir_str)
|
||||
dm = dash_by_name.get(name)
|
||||
has_dash_manifest = dm is not None or (dir_path / "dashboard" / "manifest.json").exists()
|
||||
|
||||
under_user_tree = False
|
||||
try:
|
||||
dir_path.resolve().relative_to(plugins_root_resolved)
|
||||
under_user_tree = True
|
||||
except ValueError:
|
||||
pass
|
||||
|
||||
can_remove_update = (
|
||||
source in ("user", "git") and under_user_tree and Path(dir_str).is_dir()
|
||||
)
|
||||
|
||||
# Check if this plugin provides tools that require auth
|
||||
auth_required = False
|
||||
auth_command = ""
|
||||
manifest_data = _read_plugin_manifest_at(dir_path)
|
||||
provides_tools = manifest_data.get("provides_tools") or []
|
||||
if provides_tools:
|
||||
try:
|
||||
from tools.registry import registry
|
||||
for tname in provides_tools:
|
||||
entry = registry.get_entry(tname)
|
||||
if entry and entry.check_fn and not entry.check_fn():
|
||||
auth_required = True
|
||||
auth_command = f"hermes auth {name}"
|
||||
break
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
rows.append({
|
||||
"name": name,
|
||||
"version": version or "",
|
||||
"description": description or "",
|
||||
"source": source,
|
||||
"runtime_status": runtime_status,
|
||||
"has_dashboard_manifest": has_dash_manifest,
|
||||
"dashboard_manifest": _strip_dashboard_manifest(dm) if dm else None,
|
||||
"path": dir_str,
|
||||
"can_remove": can_remove_update,
|
||||
"can_update_git": can_remove_update and (Path(dir_str) / ".git").exists(),
|
||||
"auth_required": auth_required,
|
||||
"auth_command": auth_command,
|
||||
"user_hidden": name in hidden_plugins,
|
||||
})
|
||||
|
||||
agent_names = {r["name"] for r in rows}
|
||||
orphan_dashboard = [
|
||||
_strip_dashboard_manifest(p)
|
||||
for p in dashboard_list
|
||||
if str(p["name"]) not in agent_names
|
||||
]
|
||||
|
||||
memory_providers: List[Dict[str, str]] = []
|
||||
try:
|
||||
for n, desc in _discover_memory_providers():
|
||||
memory_providers.append({"name": n, "description": desc})
|
||||
except Exception:
|
||||
memory_providers = []
|
||||
|
||||
context_engines: List[Dict[str, str]] = []
|
||||
try:
|
||||
for n, desc in _discover_context_engines():
|
||||
context_engines.append({"name": n, "description": desc})
|
||||
except Exception:
|
||||
context_engines = []
|
||||
|
||||
return {
|
||||
"plugins": rows,
|
||||
"orphan_dashboard_plugins": orphan_dashboard,
|
||||
"providers": {
|
||||
"memory_provider": _get_current_memory_provider() or "",
|
||||
"memory_options": memory_providers,
|
||||
"context_engine": _get_current_context_engine(),
|
||||
"context_options": context_engines,
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
@app.get("/api/dashboard/plugins/hub")
|
||||
async def get_plugins_hub(request: Request):
|
||||
"""Unified agent plugins + dashboard extension metadata (session protected)."""
|
||||
_require_token(request)
|
||||
try:
|
||||
return _merged_plugins_hub()
|
||||
except Exception as exc:
|
||||
_log.warning("plugins/hub failed: %s", exc)
|
||||
raise HTTPException(status_code=500, detail="Failed to build plugins hub.") from exc
|
||||
|
||||
|
||||
@app.post("/api/dashboard/agent-plugins/install")
|
||||
async def post_agent_plugin_install(request: Request, body: _AgentPluginInstallBody):
|
||||
_require_token(request)
|
||||
from hermes_cli.plugins_cmd import dashboard_install_plugin
|
||||
|
||||
result = dashboard_install_plugin(
|
||||
body.identifier.strip(),
|
||||
force=body.force,
|
||||
enable=body.enable,
|
||||
)
|
||||
if not result.get("ok"):
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=result.get("error") or "Install failed.",
|
||||
)
|
||||
_get_dashboard_plugins(force_rescan=True)
|
||||
# Strip internal paths from the response
|
||||
result.pop("after_install_path", None)
|
||||
return result
|
||||
|
||||
|
||||
def _validate_plugin_name(name: str) -> str:
|
||||
"""Reject path-traversal attempts in plugin name URL parameters."""
|
||||
if not name or "/" in name or "\\" in name or ".." in name:
|
||||
raise HTTPException(status_code=400, detail="Invalid plugin name.")
|
||||
return name
|
||||
|
||||
|
||||
@app.post("/api/dashboard/agent-plugins/{name}/enable")
|
||||
async def post_agent_plugin_enable(request: Request, name: str):
|
||||
_require_token(request)
|
||||
name = _validate_plugin_name(name)
|
||||
from hermes_cli.plugins_cmd import dashboard_set_agent_plugin_enabled
|
||||
|
||||
result = dashboard_set_agent_plugin_enabled(name, enabled=True)
|
||||
if not result.get("ok"):
|
||||
raise HTTPException(status_code=400, detail=result.get("error") or "Enable failed.")
|
||||
return result
|
||||
|
||||
|
||||
@app.post("/api/dashboard/agent-plugins/{name}/disable")
|
||||
async def post_agent_plugin_disable(request: Request, name: str):
|
||||
_require_token(request)
|
||||
name = _validate_plugin_name(name)
|
||||
from hermes_cli.plugins_cmd import dashboard_set_agent_plugin_enabled
|
||||
|
||||
result = dashboard_set_agent_plugin_enabled(name, enabled=False)
|
||||
if not result.get("ok"):
|
||||
raise HTTPException(status_code=400, detail=result.get("error") or "Disable failed.")
|
||||
return result
|
||||
|
||||
|
||||
@app.post("/api/dashboard/agent-plugins/{name}/update")
|
||||
async def post_agent_plugin_update(request: Request, name: str):
|
||||
_require_token(request)
|
||||
name = _validate_plugin_name(name)
|
||||
from hermes_cli.plugins_cmd import dashboard_update_user_plugin
|
||||
|
||||
result = dashboard_update_user_plugin(name)
|
||||
if not result.get("ok"):
|
||||
raise HTTPException(status_code=400, detail=result.get("error") or "Update failed.")
|
||||
_get_dashboard_plugins(force_rescan=True)
|
||||
return result
|
||||
|
||||
|
||||
@app.delete("/api/dashboard/agent-plugins/{name}")
|
||||
async def delete_agent_plugin(request: Request, name: str):
|
||||
_require_token(request)
|
||||
name = _validate_plugin_name(name)
|
||||
from hermes_cli.plugins_cmd import dashboard_remove_user_plugin
|
||||
|
||||
result = dashboard_remove_user_plugin(name)
|
||||
if not result.get("ok"):
|
||||
raise HTTPException(status_code=400, detail=result.get("error") or "Remove failed.")
|
||||
_get_dashboard_plugins(force_rescan=True)
|
||||
return result
|
||||
|
||||
|
||||
class _PluginProvidersPutBody(BaseModel):
|
||||
memory_provider: Optional[str] = None
|
||||
context_engine: Optional[str] = None
|
||||
|
||||
|
||||
@app.put("/api/dashboard/plugin-providers")
|
||||
async def put_plugin_providers(request: Request, body: _PluginProvidersPutBody):
|
||||
"""Persist memory provider / context engine selection (writes config.yaml)."""
|
||||
_require_token(request)
|
||||
from hermes_cli.plugins_cmd import (
|
||||
_save_context_engine,
|
||||
_save_memory_provider,
|
||||
)
|
||||
|
||||
if body.memory_provider is not None:
|
||||
_save_memory_provider(body.memory_provider)
|
||||
if body.context_engine is not None:
|
||||
_save_context_engine(body.context_engine)
|
||||
return {"ok": True}
|
||||
|
||||
|
||||
class _PluginVisibilityBody(BaseModel):
|
||||
hidden: bool
|
||||
|
||||
|
||||
@app.post("/api/dashboard/plugins/{name}/visibility")
|
||||
async def post_plugin_visibility(request: Request, name: str, body: _PluginVisibilityBody):
|
||||
"""Toggle a plugin's sidebar visibility (persists to config.yaml dashboard.hidden_plugins)."""
|
||||
_require_token(request)
|
||||
name = _validate_plugin_name(name)
|
||||
|
||||
config = load_config()
|
||||
if "dashboard" not in config or not isinstance(config.get("dashboard"), dict):
|
||||
config["dashboard"] = {}
|
||||
hidden_list: list = config["dashboard"].get("hidden_plugins") or []
|
||||
if not isinstance(hidden_list, list):
|
||||
hidden_list = []
|
||||
|
||||
if body.hidden and name not in hidden_list:
|
||||
hidden_list.append(name)
|
||||
elif not body.hidden and name in hidden_list:
|
||||
hidden_list.remove(name)
|
||||
|
||||
config["dashboard"]["hidden_plugins"] = hidden_list
|
||||
save_config(config)
|
||||
return {"ok": True, "name": name, "hidden": body.hidden}
|
||||
|
||||
|
||||
@app.get("/dashboard-plugins/{plugin_name}/{file_path:path}")
|
||||
async def serve_plugin_asset(plugin_name: str, file_path: str):
|
||||
"""Serve static assets from a dashboard plugin directory.
|
||||
|
||||
+1
-51
@@ -8,64 +8,14 @@ import os
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
_profile_fallback_warned: bool = False
|
||||
|
||||
|
||||
def get_hermes_home() -> Path:
|
||||
"""Return the Hermes home directory (default: ~/.hermes).
|
||||
|
||||
Reads HERMES_HOME env var, falls back to ~/.hermes.
|
||||
This is the single source of truth — all other copies should import this.
|
||||
|
||||
When ``HERMES_HOME`` is unset but an ``active_profile`` file indicates
|
||||
a non-default profile is active, logs a loud one-shot warning to
|
||||
``errors.log`` so cross-profile data corruption is diagnosable instead
|
||||
of silent. Behavior is unchanged otherwise — we still return
|
||||
``~/.hermes`` — because raising here would brick 30+ module-level
|
||||
callers that import this at load time. Subprocess spawners are
|
||||
expected to propagate ``HERMES_HOME`` explicitly (see the systemd
|
||||
template in ``hermes_cli/gateway.py`` and the kanban dispatcher in
|
||||
``hermes_cli/kanban_db.py``). See https://github.com/NousResearch/hermes-agent/issues/18594.
|
||||
"""
|
||||
val = os.environ.get("HERMES_HOME", "").strip()
|
||||
if val:
|
||||
return Path(val)
|
||||
|
||||
# Guard: if a non-default profile is sticky-active, warn once that
|
||||
# the fallback to the default profile is almost certainly wrong.
|
||||
global _profile_fallback_warned
|
||||
if not _profile_fallback_warned:
|
||||
try:
|
||||
# Inline the default-root resolution from get_default_hermes_root()
|
||||
# to stay import-safe (this function is called from module scope
|
||||
# in 30+ files; we cannot afford to trigger logging setup here).
|
||||
active_path = (Path.home() / ".hermes" / "active_profile")
|
||||
active = active_path.read_text().strip() if active_path.exists() else ""
|
||||
except (UnicodeDecodeError, OSError):
|
||||
active = ""
|
||||
if active and active != "default":
|
||||
_profile_fallback_warned = True
|
||||
# Write directly to stderr. We intentionally do NOT route this
|
||||
# through ``logging`` because (a) this function is called at
|
||||
# module-import time from 30+ sites, often before logging is
|
||||
# configured, and (b) root-logger propagation would double-emit
|
||||
# on consoles where a StreamHandler is already attached.
|
||||
import sys
|
||||
msg = (
|
||||
f"[HERMES_HOME fallback] HERMES_HOME is unset but active "
|
||||
f"profile is {active!r}. Falling back to ~/.hermes, which "
|
||||
f"is the DEFAULT profile — not {active!r}. Any data this "
|
||||
f"process writes will land in the wrong profile. The "
|
||||
f"subprocess spawner should pass HERMES_HOME explicitly "
|
||||
f"(see issue #18594)."
|
||||
)
|
||||
try:
|
||||
sys.stderr.write(msg + "\n")
|
||||
sys.stderr.flush()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return Path.home() / ".hermes"
|
||||
return Path(val) if val else Path.home() / ".hermes"
|
||||
|
||||
|
||||
def get_default_hermes_root() -> Path:
|
||||
|
||||
+45
-199
@@ -514,7 +514,7 @@ class SessionDB:
|
||||
# Session lifecycle
|
||||
# =========================================================================
|
||||
|
||||
def _insert_session_row(
|
||||
def create_session(
|
||||
self,
|
||||
session_id: str,
|
||||
source: str,
|
||||
@@ -523,8 +523,8 @@ class SessionDB:
|
||||
system_prompt: str = None,
|
||||
user_id: str = None,
|
||||
parent_session_id: str = None,
|
||||
) -> None:
|
||||
"""Shared INSERT OR IGNORE for session rows."""
|
||||
) -> str:
|
||||
"""Create a new session record. Returns the session_id."""
|
||||
def _do(conn):
|
||||
conn.execute(
|
||||
"""INSERT OR IGNORE INTO sessions (id, source, user_id, model, model_config,
|
||||
@@ -542,11 +542,8 @@ class SessionDB:
|
||||
),
|
||||
)
|
||||
self._execute_write(_do)
|
||||
|
||||
def create_session(self, session_id: str, source: str, **kwargs) -> str:
|
||||
"""Create a new session record. Returns the session_id."""
|
||||
self._insert_session_row(session_id, source, **kwargs)
|
||||
return session_id
|
||||
|
||||
def end_session(self, session_id: str, end_reason: str) -> None:
|
||||
"""Mark a session as ended.
|
||||
|
||||
@@ -682,41 +679,21 @@ class SessionDB:
|
||||
session_id: str,
|
||||
source: str = "unknown",
|
||||
model: str = None,
|
||||
**kwargs,
|
||||
) -> str:
|
||||
"""Ensure a session row exists (INSERT OR IGNORE). Accepts optional kwargs."""
|
||||
self._insert_session_row(session_id, source, model=model, **kwargs)
|
||||
return session_id
|
||||
|
||||
def prune_empty_ghost_sessions(self, sessions_dir: "Optional[Path]" = None) -> int:
|
||||
"""Remove empty TUI ghost sessions (no messages, no title, >24hr old)."""
|
||||
cutoff = time.time() - 86400 # Only sessions older than 24 hours
|
||||
) -> None:
|
||||
"""Ensure a session row exists, creating it with minimal metadata if absent.
|
||||
|
||||
Used by _flush_messages_to_session_db to recover from a failed
|
||||
create_session() call (e.g. transient SQLite lock at agent startup).
|
||||
INSERT OR IGNORE is safe to call even when the row already exists.
|
||||
"""
|
||||
def _do(conn):
|
||||
rows = conn.execute("""
|
||||
SELECT id FROM sessions
|
||||
WHERE source = 'tui'
|
||||
AND title IS NULL
|
||||
AND ended_at IS NOT NULL
|
||||
AND started_at < ?
|
||||
AND NOT EXISTS (
|
||||
SELECT 1 FROM messages WHERE messages.session_id = sessions.id
|
||||
)
|
||||
""", (cutoff,)).fetchall()
|
||||
ids = [r[0] if isinstance(r, (tuple, list)) else r["id"] for r in rows]
|
||||
if ids:
|
||||
placeholders = ",".join("?" * len(ids))
|
||||
conn.execute(
|
||||
f"DELETE FROM sessions WHERE id IN ({placeholders})", ids
|
||||
)
|
||||
return ids
|
||||
|
||||
removed_ids = self._execute_write(_do) or []
|
||||
# Clean up any on-disk session files (belt-and-suspenders)
|
||||
if sessions_dir and removed_ids:
|
||||
for sid in removed_ids:
|
||||
self._remove_session_files(sessions_dir, sid)
|
||||
return len(removed_ids)
|
||||
conn.execute(
|
||||
"""INSERT OR IGNORE INTO sessions
|
||||
(id, source, model, started_at)
|
||||
VALUES (?, ?, ?, ?)""",
|
||||
(session_id, source, model, time.time()),
|
||||
)
|
||||
self._execute_write(_do)
|
||||
|
||||
def get_session(self, session_id: str) -> Optional[Dict[str, Any]]:
|
||||
"""Get a session by ID."""
|
||||
@@ -956,7 +933,6 @@ class SessionDB:
|
||||
offset: int = 0,
|
||||
include_children: bool = False,
|
||||
project_compression_tips: bool = True,
|
||||
order_by_last_active: bool = False,
|
||||
) -> List[Dict[str, Any]]:
|
||||
"""List sessions with preview (first user message) and last active timestamp.
|
||||
|
||||
@@ -976,14 +952,6 @@ class SessionDB:
|
||||
compressed continuations from being invisible to users while keeping
|
||||
delegate subagents and branches hidden. Pass ``False`` to return the
|
||||
raw root rows (useful for admin/debug UIs).
|
||||
|
||||
Pass ``order_by_last_active=True`` to sort by most-recent activity
|
||||
instead of original conversation start time. For compression chains,
|
||||
the "most-recent activity" is taken from the live tip (not the root),
|
||||
so an old conversation that was compressed and continued recently
|
||||
surfaces in the correct slot. Ordering is computed at SQL level via
|
||||
a recursive CTE that walks compression-continuation edges, so LIMIT
|
||||
and OFFSET still apply efficiently.
|
||||
"""
|
||||
where_clauses = []
|
||||
params = []
|
||||
@@ -1011,80 +979,25 @@ class SessionDB:
|
||||
params.extend(exclude_sources)
|
||||
|
||||
where_sql = f"WHERE {' AND '.join(where_clauses)}" if where_clauses else ""
|
||||
if order_by_last_active:
|
||||
# Compute effective_last_active by walking each surfaced session's
|
||||
# compression-continuation chain forward in SQL and taking the MAX
|
||||
# timestamp across the chain. This lets us ORDER BY + LIMIT at SQL
|
||||
# level instead of fetching every row and sorting in Python, while
|
||||
# still surfacing old compression roots whose live tip is fresh.
|
||||
#
|
||||
# The CTE seeds from rows the outer WHERE admits (roots + branch
|
||||
# children), then recursively joins forward through
|
||||
# compression-continuation edges using the same criteria as
|
||||
# get_compression_tip (parent.end_reason='compression' AND
|
||||
# child.started_at >= parent.ended_at).
|
||||
query = f"""
|
||||
WITH RECURSIVE chain(root_id, cur_id) AS (
|
||||
SELECT s.id, s.id FROM sessions s {where_sql}
|
||||
UNION ALL
|
||||
SELECT c.root_id, child.id
|
||||
FROM chain c
|
||||
JOIN sessions parent ON parent.id = c.cur_id
|
||||
JOIN sessions child ON child.parent_session_id = c.cur_id
|
||||
WHERE parent.end_reason = 'compression'
|
||||
AND child.started_at >= parent.ended_at
|
||||
),
|
||||
chain_max AS (
|
||||
SELECT
|
||||
root_id,
|
||||
MAX(COALESCE(
|
||||
(SELECT MAX(m.timestamp) FROM messages m WHERE m.session_id = cur_id),
|
||||
(SELECT started_at FROM sessions ss WHERE ss.id = cur_id)
|
||||
)) AS effective_last_active
|
||||
FROM chain
|
||||
GROUP BY root_id
|
||||
)
|
||||
SELECT s.*,
|
||||
COALESCE(
|
||||
(SELECT SUBSTR(REPLACE(REPLACE(m.content, X'0A', ' '), X'0D', ' '), 1, 63)
|
||||
FROM messages m
|
||||
WHERE m.session_id = s.id AND m.role = 'user' AND m.content IS NOT NULL
|
||||
ORDER BY m.timestamp, m.id LIMIT 1),
|
||||
''
|
||||
) AS _preview_raw,
|
||||
COALESCE(
|
||||
(SELECT MAX(m2.timestamp) FROM messages m2 WHERE m2.session_id = s.id),
|
||||
s.started_at
|
||||
) AS last_active,
|
||||
COALESCE(cm.effective_last_active, s.started_at) AS _effective_last_active
|
||||
FROM sessions s
|
||||
LEFT JOIN chain_max cm ON cm.root_id = s.id
|
||||
{where_sql}
|
||||
ORDER BY _effective_last_active DESC, s.started_at DESC, s.id DESC
|
||||
LIMIT ? OFFSET ?
|
||||
"""
|
||||
# WHERE params apply twice (CTE seed + outer select).
|
||||
params = params + params + [limit, offset]
|
||||
else:
|
||||
query = f"""
|
||||
SELECT s.*,
|
||||
COALESCE(
|
||||
(SELECT SUBSTR(REPLACE(REPLACE(m.content, X'0A', ' '), X'0D', ' '), 1, 63)
|
||||
FROM messages m
|
||||
WHERE m.session_id = s.id AND m.role = 'user' AND m.content IS NOT NULL
|
||||
ORDER BY m.timestamp, m.id LIMIT 1),
|
||||
''
|
||||
) AS _preview_raw,
|
||||
COALESCE(
|
||||
(SELECT MAX(m2.timestamp) FROM messages m2 WHERE m2.session_id = s.id),
|
||||
s.started_at
|
||||
) AS last_active
|
||||
FROM sessions s
|
||||
{where_sql}
|
||||
ORDER BY s.started_at DESC
|
||||
LIMIT ? OFFSET ?
|
||||
"""
|
||||
params.extend([limit, offset])
|
||||
query = f"""
|
||||
SELECT s.*,
|
||||
COALESCE(
|
||||
(SELECT SUBSTR(REPLACE(REPLACE(m.content, X'0A', ' '), X'0D', ' '), 1, 63)
|
||||
FROM messages m
|
||||
WHERE m.session_id = s.id AND m.role = 'user' AND m.content IS NOT NULL
|
||||
ORDER BY m.timestamp, m.id LIMIT 1),
|
||||
''
|
||||
) AS _preview_raw,
|
||||
COALESCE(
|
||||
(SELECT MAX(m2.timestamp) FROM messages m2 WHERE m2.session_id = s.id),
|
||||
s.started_at
|
||||
) AS last_active
|
||||
FROM sessions s
|
||||
{where_sql}
|
||||
ORDER BY s.started_at DESC
|
||||
LIMIT ? OFFSET ?
|
||||
"""
|
||||
params.extend([limit, offset])
|
||||
with self._lock:
|
||||
cursor = self._conn.execute(query, params)
|
||||
rows = cursor.fetchall()
|
||||
@@ -1098,8 +1011,6 @@ class SessionDB:
|
||||
s["preview"] = text + ("..." if len(raw) > 60 else "")
|
||||
else:
|
||||
s["preview"] = ""
|
||||
# Drop the internal ordering column so callers see a clean dict.
|
||||
s.pop("_effective_last_active", None)
|
||||
sessions.append(s)
|
||||
|
||||
# Project compression roots forward to their tips. Each row whose
|
||||
@@ -1177,48 +1088,6 @@ class SessionDB:
|
||||
# Message storage
|
||||
# =========================================================================
|
||||
|
||||
# Sentinel prefix used to distinguish JSON-encoded structured content
|
||||
# (multimodal messages: lists of parts like text + image_url) from plain
|
||||
# string content. The NUL byte is not legal in normal text, so this
|
||||
# cannot collide with real user content.
|
||||
_CONTENT_JSON_PREFIX = "\x00json:"
|
||||
|
||||
@classmethod
|
||||
def _encode_content(cls, content: Any) -> Any:
|
||||
"""Serialize structured (list/dict) message content for sqlite.
|
||||
|
||||
sqlite3 can only bind ``str``, ``bytes``, ``int``, ``float``, and ``None``
|
||||
to query parameters. Multimodal messages have ``content`` as a list of
|
||||
parts (``[{"type": "text", ...}, {"type": "image_url", ...}]``), which
|
||||
raises ``ProgrammingError: Error binding parameter N: type 'list' is
|
||||
not supported`` when bound directly.
|
||||
|
||||
Returns the value unchanged when it's already a safe scalar, or a
|
||||
sentinel-prefixed JSON string for lists/dicts. Paired with
|
||||
:meth:`_decode_content` on read.
|
||||
"""
|
||||
if content is None or isinstance(content, (str, bytes, int, float)):
|
||||
return content
|
||||
try:
|
||||
return cls._CONTENT_JSON_PREFIX + json.dumps(content)
|
||||
except (TypeError, ValueError):
|
||||
# Last-resort fallback: stringify so persistence never fails.
|
||||
return str(content)
|
||||
|
||||
@classmethod
|
||||
def _decode_content(cls, content: Any) -> Any:
|
||||
"""Reverse :meth:`_encode_content`; returns scalars unchanged."""
|
||||
if isinstance(content, str) and content.startswith(cls._CONTENT_JSON_PREFIX):
|
||||
try:
|
||||
return json.loads(content[len(cls._CONTENT_JSON_PREFIX):])
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
logger.warning(
|
||||
"Failed to decode JSON-encoded message content; "
|
||||
"returning raw string"
|
||||
)
|
||||
return content
|
||||
return content
|
||||
|
||||
def append_message(
|
||||
self,
|
||||
session_id: str,
|
||||
@@ -1255,9 +1124,6 @@ class SessionDB:
|
||||
if codex_message_items else None
|
||||
)
|
||||
tool_calls_json = json.dumps(tool_calls) if tool_calls else None
|
||||
# Multimodal content (list of parts) must be JSON-encoded: sqlite3
|
||||
# cannot bind list/dict parameters directly.
|
||||
stored_content = self._encode_content(content)
|
||||
|
||||
# Pre-compute tool call count
|
||||
num_tool_calls = 0
|
||||
@@ -1274,7 +1140,7 @@ class SessionDB:
|
||||
(
|
||||
session_id,
|
||||
role,
|
||||
stored_content,
|
||||
content,
|
||||
tool_call_id,
|
||||
tool_calls_json,
|
||||
tool_name,
|
||||
@@ -1357,7 +1223,7 @@ class SessionDB:
|
||||
(
|
||||
session_id,
|
||||
role,
|
||||
self._encode_content(msg.get("content")),
|
||||
msg.get("content"),
|
||||
msg.get("tool_call_id"),
|
||||
tool_calls_json,
|
||||
msg.get("tool_name"),
|
||||
@@ -1396,8 +1262,6 @@ class SessionDB:
|
||||
result = []
|
||||
for row in rows:
|
||||
msg = dict(row)
|
||||
if "content" in msg:
|
||||
msg["content"] = self._decode_content(msg["content"])
|
||||
if msg.get("tool_calls"):
|
||||
try:
|
||||
msg["tool_calls"] = json.loads(msg["tool_calls"])
|
||||
@@ -1487,15 +1351,15 @@ class SessionDB:
|
||||
placeholders = ",".join("?" for _ in session_ids)
|
||||
rows = self._conn.execute(
|
||||
"SELECT role, content, tool_call_id, tool_calls, tool_name, "
|
||||
"finish_reason, reasoning, reasoning_content, reasoning_details, "
|
||||
"codex_reasoning_items, codex_message_items "
|
||||
"reasoning, reasoning_content, reasoning_details, codex_reasoning_items, "
|
||||
"codex_message_items "
|
||||
f"FROM messages WHERE session_id IN ({placeholders}) ORDER BY timestamp, id",
|
||||
tuple(session_ids),
|
||||
).fetchall()
|
||||
|
||||
messages = []
|
||||
for row in rows:
|
||||
content = self._decode_content(row["content"])
|
||||
content = row["content"]
|
||||
if row["role"] in {"user", "assistant"} and isinstance(content, str):
|
||||
content = sanitize_context(content).strip()
|
||||
msg = {"role": row["role"], "content": content}
|
||||
@@ -1513,8 +1377,6 @@ class SessionDB:
|
||||
# that replay reasoning (OpenRouter, OpenAI, Nous) receive
|
||||
# coherent multi-turn reasoning context.
|
||||
if row["role"] == "assistant":
|
||||
if row["finish_reason"]:
|
||||
msg["finish_reason"] = row["finish_reason"]
|
||||
if row["reasoning"]:
|
||||
msg["reasoning"] = row["reasoning"]
|
||||
if row["reasoning_content"] is not None:
|
||||
@@ -1882,26 +1744,10 @@ class SessionDB:
|
||||
)""",
|
||||
(match["id"], match["id"]),
|
||||
)
|
||||
context_msgs = []
|
||||
for r in ctx_cursor.fetchall():
|
||||
raw = r["content"]
|
||||
decoded = self._decode_content(raw)
|
||||
# Multimodal context: render a compact text-only
|
||||
# summary for search previews.
|
||||
if isinstance(decoded, list):
|
||||
text_parts = [
|
||||
p.get("text", "") for p in decoded
|
||||
if isinstance(p, dict) and p.get("type") == "text"
|
||||
]
|
||||
text = " ".join(t for t in text_parts if t).strip()
|
||||
preview = text or "[multimodal content]"
|
||||
elif isinstance(decoded, str):
|
||||
preview = decoded
|
||||
else:
|
||||
preview = ""
|
||||
context_msgs.append(
|
||||
{"role": r["role"], "content": preview[:200]}
|
||||
)
|
||||
context_msgs = [
|
||||
{"role": r["role"], "content": (r["content"] or "")[:200]}
|
||||
for r in ctx_cursor.fetchall()
|
||||
]
|
||||
match["context"] = context_msgs
|
||||
except Exception:
|
||||
match["context"] = []
|
||||
|
||||
+6
-7
@@ -356,17 +356,12 @@ def _compute_tool_definitions(
|
||||
else:
|
||||
if not quiet_mode:
|
||||
print(f"⚠️ Unknown toolset: {toolset_name}")
|
||||
else:
|
||||
# Default: start with everything
|
||||
|
||||
elif disabled_toolsets:
|
||||
from toolsets import get_all_toolsets
|
||||
for ts_name in get_all_toolsets():
|
||||
tools_to_include.update(resolve_toolset(ts_name))
|
||||
|
||||
# Always apply disabled toolsets as a subtraction step at the end.
|
||||
# This ensures that even if a composite toolset (like hermes-cli)
|
||||
# is enabled, any tools belonging to a disabled toolset are strictly
|
||||
# stripped out. See issue #17309.
|
||||
if disabled_toolsets:
|
||||
for toolset_name in disabled_toolsets:
|
||||
if validate_toolset(toolset_name):
|
||||
resolved = resolve_toolset(toolset_name)
|
||||
@@ -381,6 +376,10 @@ def _compute_tool_definitions(
|
||||
else:
|
||||
if not quiet_mode:
|
||||
print(f"⚠️ Unknown toolset: {toolset_name}")
|
||||
else:
|
||||
from toolsets import get_all_toolsets
|
||||
for ts_name in get_all_toolsets():
|
||||
tools_to_include.update(resolve_toolset(ts_name))
|
||||
|
||||
# Plugin-registered tools are now resolved through the normal toolset
|
||||
# path — validate_toolset() / resolve_toolset() / get_all_toolsets()
|
||||
|
||||
+1
-1
@@ -163,7 +163,7 @@
|
||||
for entry in "''${ENTRIES[@]}"; do
|
||||
IFS=":" read -r ATTR FOLDER NIX_FILE <<< "$entry"
|
||||
echo "==> .#$ATTR ($FOLDER -> $NIX_FILE)"
|
||||
OUTPUT=$(nix build ".#$ATTR.npmDeps" --no-link --print-build-logs 2>&1)
|
||||
OUTPUT=$(nix build ".#$ATTR.npmDeps" --no-link --rebuild --print-build-logs 2>&1)
|
||||
STATUS=$?
|
||||
if [ "$STATUS" -eq 0 ]; then
|
||||
echo " ok"
|
||||
|
||||
+1
-1
@@ -4,7 +4,7 @@ let
|
||||
src = ../ui-tui;
|
||||
npmDeps = pkgs.fetchNpmDeps {
|
||||
inherit src;
|
||||
hash = "sha256-a/HGI9OgVcTnZrMXA7xFMGnFoVxyHe95fulVz+WNYB0=";
|
||||
hash = "sha256-Chz+NW9NXqboXHOa6PKwf5bhAkkcFtKNhvKWwg2XSPc=";
|
||||
};
|
||||
|
||||
npm = hermesNpmLib.mkNpmPassthru { folder = "ui-tui"; attr = "tui"; pname = "hermes-tui"; };
|
||||
|
||||
@@ -1,206 +0,0 @@
|
||||
---
|
||||
name: kanban-video-orchestrator
|
||||
description: Plan, set up, and monitor a multi-agent video production pipeline backed by Hermes Kanban. Use when the user wants to make ANY video — narrative film, product/marketing, music video, explainer, ASCII/terminal art, abstract/generative loop, comic, 3D, real-time/installation — and the work warrants decomposition into specialized profiles (writer, designer, animator, renderer, voice, editor, etc.) coordinated through a kanban board. Performs adaptive discovery to scope the brief, designs an appropriate team for the requested style, generates the setup script that creates Hermes profiles + initial kanban task, then helps monitor execution and intervene when tasks stall or fail. Routes scenes to whichever Hermes rendering / audio / design skill fits each beat (`ascii-video`, `manim-video`, `p5js`, `comfyui`, `touchdesigner-mcp`, `blender-mcp`, `pixel-art`, `baoyu-comic`, `claude-design`, `excalidraw`, `songsee`, `heartmula`, …) plus external APIs for TTS, image-gen, and image-to-video as needed.
|
||||
version: 1.0.0
|
||||
author: [SHL0MS, alt-glitch]
|
||||
license: MIT
|
||||
metadata:
|
||||
hermes:
|
||||
tags: [video, kanban, multi-agent, orchestration, production-pipeline]
|
||||
related_skills: [kanban-orchestrator, kanban-worker, ascii-video, manim-video, p5js, comfyui, touchdesigner-mcp, blender-mcp, pixel-art, ascii-art, songwriting-and-ai-music, heartmula, songsee, spotify, youtube-content, claude-design, excalidraw, architecture-diagram, concept-diagrams, baoyu-comic, baoyu-infographic, humanizer, gif-search, meme-generation]
|
||||
credits: |
|
||||
The single-project workspace layout, profile-config patching pattern,
|
||||
SOUL.md-per-profile model, TEAM.md task-graph convention, and
|
||||
`--workspace dir:<path>` discipline are adapted from alt-glitch's
|
||||
original multi-agent video pipeline at
|
||||
https://github.com/NousResearch/kanban-video-pipeline.
|
||||
---
|
||||
|
||||
# Kanban Video Orchestrator
|
||||
|
||||
Wrap any video request — from a 15-second product teaser to a 5-minute narrative
|
||||
short to a music video to an ASCII loop — in a Hermes Kanban pipeline that
|
||||
decomposes the work to specialized agent profiles.
|
||||
|
||||
This skill does **not** render anything itself. It is a meta-pipeline that:
|
||||
|
||||
1. **Scopes** the request through targeted discovery
|
||||
2. **Designs** an appropriate team (which roles, which tools per role) based on the style
|
||||
3. **Generates** a setup script that creates Hermes profiles, project workspace, and the initial kanban task
|
||||
4. **Hands off** to the director profile, which decomposes via the kanban
|
||||
5. **Monitors** execution, helps intervene when tasks stall or fail
|
||||
|
||||
The actual rendering happens inside the kanban once it's running, via whichever
|
||||
existing skills + tools fit the scenes — `ascii-video`, `manim-video`, `p5js`,
|
||||
`comfyui`, `touchdesigner-mcp`, `blender-mcp`, `songwriting-and-ai-music`,
|
||||
`heartmula`, external APIs, or plain Python with PIL + ffmpeg.
|
||||
|
||||
## When NOT to use this skill
|
||||
|
||||
- The video is one continuous procedural project that needs no specialists. Just write the code directly.
|
||||
- The user wants a quick one-shot conversion (e.g. "convert this mp4 to a GIF") — use ffmpeg directly.
|
||||
- The output is a static image, GIF, or audio-only artifact — use the matching specific skill (`ascii-art`, `gifs`, `meme-generation`, `songwriting-and-ai-music`).
|
||||
- The work fits a single existing skill cleanly (e.g. a pure ASCII video — just use `ascii-video`).
|
||||
|
||||
## Workflow
|
||||
|
||||
```
|
||||
DISCOVER → BRIEF → TEAM DESIGN → SETUP → EXECUTE → MONITOR
|
||||
```
|
||||
|
||||
### Step 1 — Discover (ask the right questions)
|
||||
|
||||
The discovery process is **adaptive**: ask only what is actually needed. Always
|
||||
start with three questions to identify the broad shape:
|
||||
|
||||
- **What is the video?** (one-sentence brief)
|
||||
- **How long?** (5-30s teaser / 30-90s short / 90s-3min explainer / 3-10min film / longer)
|
||||
- **What aspect ratio + target platform?** (1:1 / 9:16 / 16:9; X, IG, YouTube, internal, etc.)
|
||||
|
||||
From the answer, classify the style category. The style determines which
|
||||
follow-up questions to ask. **Do not ask all questions at once.** Ask 2-4 at a
|
||||
time, listen, then proceed. Make reasonable assumptions whenever the user
|
||||
implies an answer.
|
||||
|
||||
For complete intake patterns and per-style question banks, see
|
||||
**[references/intake.md](references/intake.md)**.
|
||||
|
||||
### Step 2 — Brief
|
||||
|
||||
Once enough is known, produce a structured `brief.md` using the template in
|
||||
`assets/brief.md.tmpl`. Stages:
|
||||
|
||||
1. **Concept** — the one-sentence pitch + emotional north star
|
||||
2. **Scope** — duration, aspect, platform, deadline
|
||||
3. **Style** — visual references, brand constraints, tone
|
||||
4. **Scenes** — beat-by-beat breakdown (durations, content, target tool)
|
||||
5. **Audio** — narration / music / SFX / silent (per scene if needed)
|
||||
6. **Deliverables** — file format, resolution, optional alternates (vertical cut, GIF, etc.)
|
||||
|
||||
Show the brief to the user for confirmation before designing the team. **The
|
||||
brief is the contract** — every downstream task references it.
|
||||
|
||||
### Step 3 — Team design
|
||||
|
||||
Pick role archetypes from the library that fit this video. **Compose, don't
|
||||
clone.** Most videos need 4-7 profiles. The director is always present; the
|
||||
rest are picked by what the brief actually requires.
|
||||
|
||||
For the role library and per-style team compositions, see
|
||||
**[references/role-archetypes.md](references/role-archetypes.md)**.
|
||||
|
||||
For mapping role → which Hermes skills + toolsets it loads, see
|
||||
**[references/tool-matrix.md](references/tool-matrix.md)**.
|
||||
|
||||
### Step 4 — Setup
|
||||
|
||||
Generate a setup script (`setup.sh`) and run it. The script:
|
||||
|
||||
1. Creates the project workspace (`~/projects/video-pipeline/<slug>/`)
|
||||
2. Copies any provided assets into `taste/`, `audio/`, `assets/`
|
||||
3. Creates each Hermes profile via `hermes profile create --clone`
|
||||
4. Writes per-profile `SOUL.md` (personality + role definition)
|
||||
5. Configures profile YAML (toolsets, always_load skills, cwd)
|
||||
6. Writes `brief.md`, `TEAM.md`, and `taste/` content
|
||||
7. Fires the initial `hermes kanban create` task assigned to the director
|
||||
|
||||
Use `scripts/bootstrap_pipeline.py` to generate setup.sh from a brief +
|
||||
team-design JSON. See **[references/kanban-setup.md](references/kanban-setup.md)**
|
||||
for the setup script structure, profile config patterns, and the critical
|
||||
"shared workspace" rule.
|
||||
|
||||
### Step 5 — Execute
|
||||
|
||||
Run `setup.sh`. Then provide the user with monitoring commands:
|
||||
|
||||
```bash
|
||||
hermes kanban watch --tenant <project-tenant> # live events
|
||||
hermes kanban list --tenant <project-tenant> # board snapshot
|
||||
hermes dashboard # visual board UI
|
||||
```
|
||||
|
||||
The director profile takes over from here, decomposing the work and routing
|
||||
tasks to specialist profiles via the kanban toolset.
|
||||
|
||||
### Step 6 — Monitor and intervene
|
||||
|
||||
Stay engaged — the kanban runs autonomously but a stuck task or bad output
|
||||
needs human (or AI) judgment.
|
||||
|
||||
Monitoring patterns: poll `kanban list` periodically, inspect any RUNNING task
|
||||
that exceeds its expected duration with `kanban show <id>`, and check
|
||||
heartbeats. When a worker's output fails review, the standard interventions are:
|
||||
|
||||
1. Comment on the worker's task with specific feedback (`kanban_comment`)
|
||||
2. Create a re-run task with the original as parent
|
||||
3. Adjust the brief's scope and let the director re-decompose
|
||||
|
||||
For diagnostic patterns, intervention recipes, and the "task is stuck"
|
||||
playbook, see **[references/monitoring.md](references/monitoring.md)**.
|
||||
|
||||
## Reference: worked examples
|
||||
|
||||
Six concrete pipelines covering very different video styles — narrative film,
|
||||
product/marketing, music video, math/algorithm explainer, ASCII video, real-time
|
||||
installation — showing how the same workflow yields very different teams and
|
||||
task graphs. See **[references/examples.md](references/examples.md)**.
|
||||
|
||||
## Critical rules
|
||||
|
||||
1. **Discovery before action.** Never start generating a brief or team without
|
||||
asking at least the three baseline questions. A bad brief cascades through
|
||||
the entire pipeline.
|
||||
|
||||
2. **Match the team to the video.** Don't reuse the same 4-profile setup for
|
||||
every job. A music video that doesn't have a beat-analysis profile will
|
||||
misfire. A narrative film that doesn't have a writer profile will produce
|
||||
incoherent scenes. See `references/role-archetypes.md`.
|
||||
|
||||
3. **One workspace per project.** All profiles for a given video share the same
|
||||
`dir:` workspace. Tasks pass artifacts via shared filesystem and structured
|
||||
handoffs. **Every** `kanban_create` call passes
|
||||
`workspace_kind="dir"` + `workspace_path="<absolute project path>"`.
|
||||
|
||||
4. **Tenant every project.** Use a project-specific tenant
|
||||
(`--tenant <project-slug>`). Keeps the dashboard scoped and prevents
|
||||
cross-pollination with other ongoing kanbans.
|
||||
|
||||
5. **Respect existing skills.** When a scene fits an existing skill, the
|
||||
relevant renderer should load that skill via `--skill <name>` on its task
|
||||
or `always_load` in its profile. Do not re-derive what a skill already
|
||||
provides.
|
||||
|
||||
6. **The director never executes.** Even with the full `kanban + terminal +
|
||||
file` toolset, the director's `SOUL.md` rules forbid it from executing
|
||||
work itself. It decomposes and routes only — every concrete task becomes
|
||||
a `hermes kanban create` call to a specialist profile. The
|
||||
`kanban-orchestrator` skill spells this out further.
|
||||
|
||||
7. **Don't over-decompose.** A 30-second product video does NOT need 20 tasks.
|
||||
Aim for the smallest task graph that still parallelizes well and exposes the
|
||||
right human-review gates.
|
||||
|
||||
8. **Verify API keys BEFORE firing.** External APIs (TTS, image-gen,
|
||||
image-to-video) need keys in `~/.hermes/.env` or the user's secret store.
|
||||
A worker that hits a missing-key error wastes a task slot. The setup
|
||||
script's `check_key` helper aborts cleanly if a required key is missing.
|
||||
|
||||
## File map
|
||||
|
||||
```
|
||||
SKILL.md ← this file (workflow + rules)
|
||||
references/
|
||||
intake.md ← discovery question banks per style
|
||||
role-archetypes.md ← role library (writer, designer, animator, …)
|
||||
tool-matrix.md ← skill + toolset mapping per role
|
||||
kanban-setup.md ← setup script structure & profile config
|
||||
monitoring.md ← watch + intervene patterns
|
||||
examples.md ← six worked pipelines
|
||||
assets/
|
||||
brief.md.tmpl ← brief skeleton
|
||||
setup.sh.tmpl ← setup script skeleton
|
||||
soul.md.tmpl ← profile personality skeleton
|
||||
scripts/
|
||||
bootstrap_pipeline.py ← generate setup.sh from brief + team JSON
|
||||
monitor.py ← polling + intervention helpers
|
||||
```
|
||||
@@ -1,79 +0,0 @@
|
||||
# Video Brief — {{TITLE}}
|
||||
|
||||
> Slug: `{{SLUG}}` · Tenant: `{{TENANT}}` · Project workspace: `{{WORKSPACE}}`
|
||||
|
||||
## 1. Concept
|
||||
|
||||
**One-line pitch.** {{ONE_LINE_PITCH}}
|
||||
|
||||
**Emotional north star.** {{EMOTIONAL_NORTH_STAR}}
|
||||
*(What should the viewer feel walking away?)*
|
||||
|
||||
## 2. Scope
|
||||
|
||||
| | |
|
||||
|---|---|
|
||||
| Duration | {{DURATION_S}} seconds |
|
||||
| Aspect ratio | {{ASPECT}} |
|
||||
| Resolution | {{RESOLUTION}} |
|
||||
| Frame rate | {{FPS}} fps |
|
||||
| Target platforms | {{PLATFORMS}} |
|
||||
| Deadline | {{DEADLINE}} |
|
||||
| Quality bar | {{QUALITY_BAR}} *(rough draft / polished / archival)* |
|
||||
|
||||
## 3. Style
|
||||
|
||||
**Visual references.** {{VISUAL_REFS}}
|
||||
|
||||
**Tone.** {{TONE}}
|
||||
|
||||
**Brand constraints.** {{BRAND_CONSTRAINTS}}
|
||||
*(colors, typography, motion language; or "n/a")*
|
||||
|
||||
**Aesthetic rules.**
|
||||
{{AESTHETIC_RULES}}
|
||||
|
||||
## 4. Scenes
|
||||
|
||||
Beat-by-beat breakdown. Each scene gets a row.
|
||||
|
||||
| # | Time | Content | Target tool / skill | Audio | Notes |
|
||||
|---|------|---------|---------------------|-------|-------|
|
||||
| 1 | 0:00–0:0X | {{SCENE_1_CONTENT}} | {{SCENE_1_TOOL}} | {{SCENE_1_AUDIO}} | {{SCENE_1_NOTES}} |
|
||||
| 2 | 0:0X–0:0Y | ... | ... | ... | ... |
|
||||
|
||||
## 5. Audio
|
||||
|
||||
**Approach.** {{AUDIO_APPROACH}}
|
||||
*(narration / music-only / synced to track / silent / mixed)*
|
||||
|
||||
**Voiceover.** {{VO_DETAILS}}
|
||||
*(provider, voice, language, script source — "n/a" if no VO)*
|
||||
|
||||
**Music.** {{MUSIC_DETAILS}}
|
||||
*(provided track path / commission via Suno / commission via heartmula /
|
||||
license-free / "n/a")*
|
||||
|
||||
**SFX.** {{SFX_DETAILS}}
|
||||
*(generated, library, or "n/a")*
|
||||
|
||||
## 6. Deliverables
|
||||
|
||||
| Format | Resolution | Notes |
|
||||
|--------|-----------|-------|
|
||||
| {{PRIMARY_FORMAT}} | {{PRIMARY_RES}} | The main output |
|
||||
| {{ALT_FORMAT_1}} | {{ALT_RES_1}} | {{ALT_NOTES_1}} |
|
||||
|
||||
**Final filename.** `output/final.mp4`
|
||||
*(plus optional `output/final-9x16.mp4`, `output/captions.srt`, etc.)*
|
||||
|
||||
## 7. Constraints
|
||||
|
||||
- API keys required: {{API_KEYS_REQUIRED}}
|
||||
- External dependencies: {{EXT_DEPS}}
|
||||
- Source assets to incorporate: {{SOURCE_ASSETS}}
|
||||
|
||||
---
|
||||
|
||||
**This brief is the contract. The director and every downstream profile read
|
||||
it. If the brief changes, the kanban must be re-fired — don't edit live.**
|
||||
@@ -1,185 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# ═══════════════════════════════════════════════════════════════════════
|
||||
# Video Pipeline Setup — {{TITLE}}
|
||||
#
|
||||
# Generated by kanban-video-orchestrator skill.
|
||||
#
|
||||
# Slug: {{SLUG}}
|
||||
# Workspace: {{WORKSPACE}}
|
||||
# Tenant: {{TENANT}}
|
||||
# ═══════════════════════════════════════════════════════════════════════
|
||||
set -euo pipefail
|
||||
|
||||
PROJECT_SLUG="{{SLUG}}"
|
||||
WORKSPACE="$HOME/projects/video-pipeline/${PROJECT_SLUG}"
|
||||
TENANT="{{TENANT}}"
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# 1. Verify required API keys
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
echo "═══ Checking required API keys ═══"
|
||||
|
||||
check_key() {
|
||||
local var="$1"
|
||||
local kc_account="${2:-hermes}"
|
||||
local kc_service="${3:-$1}"
|
||||
if grep -q "^${var}=" "$HOME/.hermes/.env" 2>/dev/null && \
|
||||
[ -n "$(grep "^${var}=" "$HOME/.hermes/.env" | cut -d= -f2-)" ]; then
|
||||
echo " ✓ ${var} (env)"
|
||||
return 0
|
||||
fi
|
||||
if command -v security >/dev/null 2>&1 && \
|
||||
security find-generic-password -a "${kc_account}" -s "${kc_service}" -w >/dev/null 2>&1; then
|
||||
echo " ✓ ${var} (Keychain ${kc_account}/${kc_service})"
|
||||
return 0
|
||||
fi
|
||||
echo " ✗ ${var} not set in ~/.hermes/.env or Keychain (${kc_account}/${kc_service})"
|
||||
return 1
|
||||
}
|
||||
|
||||
# Customize this list per project — only check keys actually used:
|
||||
{{KEY_CHECKS}}
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# 2. Create project workspace
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
echo "═══ Creating project workspace ═══"
|
||||
mkdir -p "$WORKSPACE"/{taste,audio/{voiceover,sfx},assets,scenes,checkpoints,tools,output}
|
||||
{{SCENE_DIRS}}
|
||||
echo " ✓ $WORKSPACE"
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# 3. Create Hermes profiles
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
echo "═══ Creating Hermes profiles ═══"
|
||||
|
||||
{{PROFILE_CREATE_COMMANDS}}
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# 4. Configure profiles (toolsets, skills, cwd)
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
echo "═══ Configuring profiles ═══"
|
||||
|
||||
configure_profile() {
|
||||
local profile="$1"
|
||||
local toolsets_json="$2" # JSON array string, e.g. '["kanban","terminal","file"]'
|
||||
local skills_json="$3" # JSON array string, e.g. '["kanban-worker","ascii-video"]'
|
||||
python3 - "$profile" "$toolsets_json" "$skills_json" "$WORKSPACE" <<'PY'
|
||||
"""Patch a Hermes profile config.yaml using PyYAML so we don't depend on the
|
||||
exact default-config string format. Validates the patch took effect and exits
|
||||
non-zero if anything's off."""
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
|
||||
try:
|
||||
import yaml
|
||||
except ImportError:
|
||||
print("ERROR: PyYAML required. pip install pyyaml", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
profile, toolsets_json, skills_json, workspace = sys.argv[1:5]
|
||||
toolsets = json.loads(toolsets_json)
|
||||
skills = json.loads(skills_json)
|
||||
|
||||
p = os.path.expanduser(f"~/.hermes/profiles/{profile}/config.yaml")
|
||||
if not os.path.exists(p):
|
||||
print(f" ✗ profile config not found: {p}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
with open(p) as f:
|
||||
cfg = yaml.safe_load(f) or {}
|
||||
|
||||
# Apply our changes — only the keys we actually want to set.
|
||||
cfg["toolsets"] = toolsets
|
||||
cfg.setdefault("skills", {})
|
||||
cfg["skills"]["always_load"] = skills
|
||||
|
||||
# Note: we do NOT touch cfg["approvals"] — that's a security-sensitive
|
||||
# setting (manual confirmation of tool calls). Workspace cwd is overridden
|
||||
# per-task by `--workspace dir:<path>` on `hermes kanban create`, so we
|
||||
# don't need to mutate cfg["terminal"]["cwd"] either.
|
||||
|
||||
with open(p, "w") as f:
|
||||
yaml.safe_dump(cfg, f, sort_keys=False)
|
||||
|
||||
# Validate
|
||||
with open(p) as f:
|
||||
after = yaml.safe_load(f)
|
||||
errors = []
|
||||
if after.get("toolsets") != toolsets:
|
||||
errors.append(f"toolsets mismatch: {after.get('toolsets')!r}")
|
||||
if after.get("skills", {}).get("always_load") != skills:
|
||||
errors.append(f"skills.always_load mismatch: {after.get('skills', {}).get('always_load')!r}")
|
||||
if errors:
|
||||
print(f" ✗ {profile}: " + "; ".join(errors), file=sys.stderr)
|
||||
sys.exit(1)
|
||||
PY
|
||||
if [ $? -ne 0 ]; then
|
||||
echo " ✗ failed to configure ${profile}" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo " ✓ ${profile}"
|
||||
}
|
||||
|
||||
{{PROFILE_CONFIG_COMMANDS}}
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# 5. Write SOUL.md per profile
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
echo "═══ Writing profile personalities ═══"
|
||||
|
||||
{{SOUL_WRITES}}
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# 6. Copy brief, TEAM.md, and any provided assets
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
echo "═══ Writing brief + taste ═══"
|
||||
|
||||
cat > "$WORKSPACE/brief.md" <<'BRIEF_EOF'
|
||||
{{BRIEF_CONTENTS}}
|
||||
BRIEF_EOF
|
||||
|
||||
cat > "$WORKSPACE/TEAM.md" <<'TEAM_EOF'
|
||||
{{TEAM_CONTENTS}}
|
||||
TEAM_EOF
|
||||
|
||||
{{TASTE_WRITES}}
|
||||
|
||||
{{ASSET_COPIES}}
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# 7. Fire the initial kanban task
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
echo "═══ Firing initial kanban task ═══"
|
||||
|
||||
hermes kanban create "Direct production of {{TITLE}}" \
|
||||
--assignee director \
|
||||
--workspace dir:"$WORKSPACE" \
|
||||
--tenant "$TENANT" \
|
||||
--priority 2 \
|
||||
--max-runtime 4h \
|
||||
--body "$(cat <<EOF
|
||||
Read brief.md, TEAM.md, and taste/.
|
||||
|
||||
Decompose into the team graph defined in TEAM.md.
|
||||
|
||||
All child tasks MUST use:
|
||||
workspace_kind="dir"
|
||||
workspace_path="$WORKSPACE"
|
||||
tenant="$TENANT"
|
||||
|
||||
Do not execute the work yourself — route every concrete subtask to the
|
||||
appropriate profile via kanban_create.
|
||||
EOF
|
||||
)"
|
||||
|
||||
echo ""
|
||||
echo "═══ Setup complete ═══"
|
||||
echo ""
|
||||
echo "Monitor with:"
|
||||
echo " hermes kanban watch --tenant $TENANT"
|
||||
echo " hermes kanban list --tenant $TENANT"
|
||||
echo " hermes dashboard"
|
||||
echo ""
|
||||
echo "Workspace: $WORKSPACE"
|
||||
@@ -1,38 +0,0 @@
|
||||
# {{ROLE_NAME}}
|
||||
|
||||
You are the **{{ROLE_NAME}}** for this video production.
|
||||
|
||||
## Project context
|
||||
|
||||
- **Brief:** read `brief.md` in your CWD
|
||||
- **Team graph:** read `TEAM.md` in your CWD
|
||||
- **Style spec:** read `taste/brand-guide.md` and `taste/emotional-dna.md` in
|
||||
your CWD
|
||||
|
||||
## What you do
|
||||
|
||||
{{ROLE_RESPONSIBILITIES}}
|
||||
|
||||
## Inputs you read
|
||||
|
||||
{{INPUTS_READ}}
|
||||
|
||||
## Outputs you produce
|
||||
|
||||
{{OUTPUTS_PRODUCED}}
|
||||
|
||||
## Tools and skills available
|
||||
|
||||
- **Toolsets:** {{TOOLSETS}}
|
||||
- **Skills loaded:** {{SKILLS}}
|
||||
- **External APIs / CLIs:** {{EXTERNAL_TOOLS}}
|
||||
|
||||
## Rules
|
||||
|
||||
{{ROLE_RULES}}
|
||||
|
||||
{{COMMON_RULES}}
|
||||
|
||||
## Common reference commands
|
||||
|
||||
{{COMMON_COMMANDS}}
|
||||
@@ -1,227 +0,0 @@
|
||||
# Worked Examples
|
||||
|
||||
Six concrete pipelines covering different video styles. Each shows the team
|
||||
composition, task graph, and skill/tool choices the orchestrator would make
|
||||
for that brief. **These are illustrative, not templates** — adapt to the
|
||||
actual brief.
|
||||
|
||||
## Example 1 — Narrative short film (text-to-image → image-to-video → cut)
|
||||
|
||||
**Brief:** A 90-second noir-style short. A detective walks through a rainy
|
||||
city. Voiceover narration. AI-generated visuals.
|
||||
|
||||
**Team:**
|
||||
- `director` — vision, decomposition, approval
|
||||
- `writer` — script + voiceover copy (loads `humanizer` for natural voice)
|
||||
- `storyboarder` — beat-by-beat shot list (loads `excalidraw`)
|
||||
- `image-generator` — generates each shot's still via local ComfyUI workflows
|
||||
(loads `comfyui`)
|
||||
- `image-to-video-generator` — animates each still (Runway/Kling, OR
|
||||
ComfyUI's AnimateDiff/WAN workflows via `comfyui`)
|
||||
- `voice-talent` — narration via ElevenLabs
|
||||
- `audio-mixer` — VO + ambient pad
|
||||
- `editor` — assembly + transitions
|
||||
- `reviewer` — final QA
|
||||
|
||||
**Task graph:**
|
||||
```
|
||||
T0 director decompose
|
||||
T1 writer script + voiceover.md (parent: T0)
|
||||
T2 storyboarder shot list with framing per beat (parent: T1)
|
||||
T3 image-generator one still per shot (~12 shots) (parent: T2)
|
||||
T4 image-to-video animate each still (parent: T3)
|
||||
T5 voice-talent generate narration audio (parent: T1)
|
||||
T6 audio-mixer mix VO + ambient (parent: T5)
|
||||
T7 editor cut + transitions + audio mux (parents: T4, T6)
|
||||
T8 reviewer final QA (parent: T7)
|
||||
```
|
||||
|
||||
**Key choices:**
|
||||
- Local ComfyUI via `comfyui` skill is preferred over external API for
|
||||
cost/control — but external APIs are fine if ComfyUI isn't installed
|
||||
- `editor` profile is ffmpeg-only, no Hermes skill required beyond
|
||||
`kanban-worker`
|
||||
- Storyboarder produces `storyboard.excalidraw` alongside the markdown
|
||||
|
||||
## Example 2 — Product / marketing teaser
|
||||
|
||||
**Brief:** A 30-second product teaser for a developer tool. Shows code +
|
||||
terminal + UI screen recordings, voiceover, CTA at end. Square 1:1.
|
||||
|
||||
**Team:**
|
||||
- `director`
|
||||
- `copywriter` — taglines, voiceover script, CTA (loads `humanizer`)
|
||||
- `concept-artist` — style frames (loads `claude-design` for UI mockups)
|
||||
- `renderer-motion-graphics` — animated UI sequences (Remotion CLI)
|
||||
- `renderer-ascii` — terminal-style demo scenes (loads `ascii-video`)
|
||||
- `voice-talent` — VO via ElevenLabs
|
||||
- `editor` — assembly + brand-color treatment
|
||||
- `audio-mixer` — VO + light music bed
|
||||
- `captioner` — burned subtitles for muted-autoplay platforms
|
||||
- `masterer` — produces 1:1 + 9:16 + 16:9 variants
|
||||
|
||||
**Task graph:**
|
||||
```
|
||||
T0 director decompose
|
||||
T1 copywriter copy.md + cta + vo script (parent: T0)
|
||||
T2 concept-artist visual-spec.md + style frames (parent: T1)
|
||||
T3a renderer-motion-graphics scene 1: UI sequence (parent: T2)
|
||||
T3b renderer-ascii scene 2: terminal demo (parent: T2)
|
||||
T3c renderer-motion-graphics scene 3: feature highlight (parent: T2)
|
||||
T3d renderer-motion-graphics scene 4: CTA card (parent: T2)
|
||||
T4 voice-talent narration (parent: T1)
|
||||
T5 audio-mixer VO + music bed (parent: T4)
|
||||
T6 editor cut + transitions (parents: T3*, T5)
|
||||
T7 captioner SRT + burned subtitles (parent: T6)
|
||||
T8 masterer 1:1, 9:16, 16:9 variants (parent: T7)
|
||||
```
|
||||
|
||||
**Key choices:**
|
||||
- Multiple specialized renderers (motion-graphics + ASCII) coexist
|
||||
- Captioner is included because muted autoplay is the norm on social
|
||||
- `claude-design` skill for UI mockups maps directly to the product video idiom
|
||||
|
||||
## Example 3 — Music video (synced to provided track)
|
||||
|
||||
**Brief:** A 3-minute music video for a provided lo-fi hip-hop track. Visuals
|
||||
should pulse with the beat. Generative + ASCII hybrid. Vertical 9:16.
|
||||
|
||||
**Team:**
|
||||
- `director`
|
||||
- `music-supervisor` — analyze track, emit `audio/beats.json` (loads `songsee`)
|
||||
- `storyboarder` — beat-aligned shot list (loads `excalidraw`)
|
||||
- `renderer-ascii` — ASCII scenes synced to bass kicks (loads `ascii-video`)
|
||||
- `renderer-p5js` — generative particle scenes synced to highs (loads `p5js`)
|
||||
- `editor` — beat-cut assembly using `beats.json`
|
||||
- `reviewer` — sync QA
|
||||
|
||||
**Task graph:**
|
||||
```
|
||||
T0 director decompose
|
||||
T1 music-supervisor analyze track → beats.json + spectrogram (parent: T0)
|
||||
T2 storyboarder shot list aligned to beats (parents: T1, T0)
|
||||
T3a renderer-ascii scene 1: bass-driven ASCII (parent: T2)
|
||||
T3b renderer-p5js scene 2: high-end particle field (parent: T2)
|
||||
... (more scenes)
|
||||
T4 editor cut to beats + mux track (parents: T3*, T1)
|
||||
T5 reviewer sync QA + final approval (parent: T4)
|
||||
```
|
||||
|
||||
**Key choices:**
|
||||
- `music-supervisor` runs FIRST — `beats.json` gates the renderers
|
||||
- `editor` uses `beats.json` directly to align cuts to bass kicks
|
||||
- No voice-talent — music is the audio
|
||||
- Two specialized renderers (`ascii-video` + `p5js`) for visual variety
|
||||
|
||||
## Example 4 — Math/algorithm explainer
|
||||
|
||||
**Brief:** A 2-minute explainer of an algorithm. 3Blue1Brown-style. Animated
|
||||
diagrams, equations, narration. Square 1:1.
|
||||
|
||||
**Team:**
|
||||
- `director`
|
||||
- `writer` — narration script (loads `humanizer`)
|
||||
- `cinematographer` — visual spec (loads `manim-video`)
|
||||
- `renderer-manim` — all animated scenes (loads `manim-video`)
|
||||
- `voice-talent` — narration via ElevenLabs
|
||||
- `editor` — assembly + audio mux
|
||||
- `captioner` — burned subtitles
|
||||
|
||||
**Task graph:**
|
||||
```
|
||||
T0 director decompose
|
||||
T1 writer script + narration (parent: T0)
|
||||
T2 cinematographer visual spec for all scenes (parent: T1)
|
||||
T3a-Tn renderer-manim scenes 1..N (parents: T2)
|
||||
T4 voice-talent narration audio (parent: T1)
|
||||
T5 editor cut + mux (parents: T3*, T4)
|
||||
T6 captioner SRT + burn (parent: T5)
|
||||
```
|
||||
|
||||
**Key choices:**
|
||||
- `manim-video` skill drives both the cinematographer (visual language) and
|
||||
the renderer (actual scene production)
|
||||
- The `manim-video` skill's reference docs (animation-design-thinking,
|
||||
scene-planning, equations) auto-load when needed via the renderer's pinned skill
|
||||
|
||||
## Example 5 — ASCII video, music-track-only
|
||||
|
||||
**Brief:** A 60-second pure-ASCII video reactive to an existing track. No
|
||||
voiceover, no other tools. Square 1:1.
|
||||
|
||||
**Team:**
|
||||
- `director`
|
||||
- `music-supervisor` — track analysis (loads `songsee`)
|
||||
- `renderer-ascii` — all visuals (loads `ascii-video`)
|
||||
- `editor` — assembly + audio mux
|
||||
|
||||
**Task graph:**
|
||||
```
|
||||
T0 director decompose
|
||||
T1 music-supervisor analyze track (parent: T0)
|
||||
T2a renderer-ascii scene 1 (parents: T1, T0)
|
||||
T2b renderer-ascii scene 2 (parents: T1, T0)
|
||||
T2c renderer-ascii scene 3 (parents: T1, T0)
|
||||
T3 editor stitch + mux audio (parents: T2*)
|
||||
```
|
||||
|
||||
**Key choices:**
|
||||
- Minimal team (4 profiles) for a focused single-tool project
|
||||
- No reviewer — short experimental piece, director approves directly
|
||||
- All scenes run through one `renderer-ascii` profile because the `ascii-video`
|
||||
skill covers everything
|
||||
|
||||
This example illustrates the rule: **don't over-decompose**. Three scenes
|
||||
through one renderer is fine. Don't spawn three renderer profiles.
|
||||
|
||||
## Example 6 — Real-time / installation art
|
||||
|
||||
**Brief:** A 2-minute audio-reactive visual for a gallery installation. Driven
|
||||
by an audio input feed. TouchDesigner-based. 16:9 4K.
|
||||
|
||||
**Team:**
|
||||
- `director`
|
||||
- `cinematographer` — visual language spec (loads `touchdesigner-mcp`)
|
||||
- `renderer-touchdesigner` — all visuals + record-to-disk
|
||||
(loads `touchdesigner-mcp`)
|
||||
- `audio-mixer` — final loudness pass on the captured audio (optional if
|
||||
pre-mixed source)
|
||||
- `editor` — assemble final clip from TouchDesigner recording
|
||||
- `reviewer` — visual QA
|
||||
|
||||
**Task graph:**
|
||||
```
|
||||
T0 director decompose
|
||||
T1 cinematographer TD operator graph spec (parent: T0)
|
||||
T2 renderer-touchdesigner build TD network + record output (parent: T1)
|
||||
T3 editor trim + audio mux (parent: T2)
|
||||
T4 reviewer final QA (parent: T3)
|
||||
```
|
||||
|
||||
**Key choices:**
|
||||
- `touchdesigner-mcp` controls a running TouchDesigner instance — the
|
||||
cinematographer designs the operator graph, renderer builds it
|
||||
- Output is a recording from the running TD network, not a render-to-frames
|
||||
process; editor mostly just trims
|
||||
|
||||
## Pattern recognition
|
||||
|
||||
When the user describes a video, look for these signals to map to an example:
|
||||
|
||||
- **Plot, characters, scripted dialogue** → Example 1 (narrative)
|
||||
- **Specific product, CTA, brand colors, voiceover** → Example 2 (marketing)
|
||||
- **Track file provided, "synced to music"** → Example 3 (music video)
|
||||
- **"Explain how X works", math/algorithm/concept walkthrough** → Example 4 (manim explainer)
|
||||
- **Terminal aesthetic, ASCII, retro pixel** → Example 5 (ASCII)
|
||||
- **"Audio-reactive", "real-time", "installation"** → Example 6 (TouchDesigner)
|
||||
- **Comic-style narrative** → use `renderer-comic` (`baoyu-comic` skill)
|
||||
- **Retro game / pixel-art aesthetic** → use `renderer-pixel` (`pixel-art` skill)
|
||||
- **3D scene, photoreal environment** → use `renderer-3d` (`blender-mcp`)
|
||||
- **Generative art, particle system, shader** → use `renderer-p5js` (`p5js`)
|
||||
- **AI-generated photoreal stills + animation** → use `renderer-comfyui`
|
||||
(`comfyui`) for both stills and image-to-video
|
||||
- **"video about how the system works", recursive demo** → composable from
|
||||
any of the above; the recursion is a rendering technique, not a style
|
||||
|
||||
The actual team should be derived from the specific brief — these examples are
|
||||
starting points, not endpoints.
|
||||
@@ -1,166 +0,0 @@
|
||||
# Intake — Discovery Question Banks
|
||||
|
||||
The discovery process is **adaptive**. Always start with three baseline
|
||||
questions to identify the broad style category, then drill into a per-style
|
||||
question bank. Ask 2-4 questions at a time, listen, then proceed. Make
|
||||
reasonable assumptions whenever the user implies an answer.
|
||||
|
||||
## Tier 0 — Baseline (always ask)
|
||||
|
||||
1. **What is the video?** — One-sentence pitch
|
||||
2. **How long?** — Approximate duration
|
||||
3. **Aspect ratio + target platform?** — 16:9 / 9:16 / 1:1 / 4:5; X, IG, YouTube, internal, etc.
|
||||
|
||||
From these answers, classify the style category and pick the relevant Tier 1
|
||||
follow-ups. **Do not** continue asking until you have at least these three.
|
||||
|
||||
## Style classification
|
||||
|
||||
Map the brief to one of these archetypes (or a hybrid):
|
||||
|
||||
| Archetype | Tells |
|
||||
|-----------|-------|
|
||||
| **Narrative film** | Plot, characters, scenes-with-events, dialogue, location |
|
||||
| **Product / marketing** | A specific product or feature being shown / sold; CTA at end |
|
||||
| **Music video** | A specific track exists; visuals sync to music |
|
||||
| **Explainer / educational** | A concept being taught; voiceover-driven |
|
||||
| **Tutorial / changelog** | Software demo, terminal-heavy, technical |
|
||||
| **ASCII / terminal art** | Retro terminal aesthetic explicit, character-grid |
|
||||
| **Abstract / loop** | Generative, no plot, often perfect-loop |
|
||||
| **Documentary / interview cut** | Real footage, transcription-driven |
|
||||
| **Real-time / installation** | Audio-reactive, gallery installation, VJ output |
|
||||
|
||||
If ambiguous, **ask** which category fits — don't guess. Hybrids are common
|
||||
(e.g., a product video with a narrative arc); decompose into the dominant
|
||||
mode + secondary modifiers.
|
||||
|
||||
**Recursive / meta** ("a video that shows its own production") is a
|
||||
*rendering technique*, not a separate style — compose it from any of the
|
||||
above by adding a two-pass render step where pass 2 uses pass 1's output as
|
||||
texture inside the final scene.
|
||||
|
||||
## Tier 1 — Per-style follow-ups
|
||||
|
||||
### Narrative film
|
||||
|
||||
- **Setting / world?** — When and where the story takes place
|
||||
- **Characters?** — How many, archetypes, who carries dialogue
|
||||
- **Beat list or full script?** — Has the user written the story or do we draft it
|
||||
- **Dialogue language?** — Spoken lines, on-screen subs only, silent
|
||||
- **Visual generation approach?** — Text-to-image (FAL/Midjourney/Imagen) →
|
||||
image-to-video (Runway/Kling), 3D animation (Blender), 2D animation,
|
||||
procedural, or hybrid
|
||||
- **Voice approach?** — TTS (which voice), recorded VO, no dialogue
|
||||
- **Music / score?** — Commissioned (via `songwriting-and-ai-music` Suno
|
||||
prompts, or local `heartmula`), licensed track provided, silent
|
||||
|
||||
### Product / marketing
|
||||
|
||||
- **Product?** — Name, what it does, key feature being shown
|
||||
- **Target audience?** — Who's watching, what they care about
|
||||
- **CTA?** — Visit URL, install, sign up, etc.
|
||||
- **Tone?** — Serious, playful, technical, premium, edgy
|
||||
- **Brand assets available?** — Logo files, color palette, fonts, existing footage
|
||||
- **Animation style?** — Motion graphics (Remotion / AE-style), screen recording,
|
||||
generative, illustrated
|
||||
- **Voiceover?** — Yes (which voice / language) or text-only
|
||||
- **Music?** — Track provided, license-free needed, custom-composed
|
||||
|
||||
### Music video
|
||||
|
||||
- **Track file?** — Path to the audio (essential — we'll analyze BPM + beats)
|
||||
- **Track length to use?** — Full song or a section
|
||||
- **Genre / energy?** — Tells what visual rhythm and density to use
|
||||
- **Lyric / narrative content?** — Are there lyrics to render on screen,
|
||||
or is it purely visual?
|
||||
- **Visual reference style?** — Existing music videos / artists for reference
|
||||
- **Performer footage?** — None, has clips, will provide
|
||||
- **Visual generation approach?** — Per-beat generative, edit-driven cuts of stock
|
||||
footage, illustrated, hybrid
|
||||
|
||||
### Explainer / educational
|
||||
|
||||
- **What concept is being taught?** — One-sentence concept, key takeaway
|
||||
- **Audience expertise?** — Beginner / intermediate / expert
|
||||
- **Diagram density?** — Heavy math / formulas / code / abstract concepts
|
||||
- **Voiceover?** — TTS / recorded / on-screen text only
|
||||
- **Tool preference?** — `manim-video` (math), `p5js` (generative),
|
||||
Remotion (UI motion graphics), `comfyui` (AI-generated visuals),
|
||||
`ascii-video` (technical/retro), hybrid
|
||||
- **Pacing?** — Fast and dense (3Blue1Brown) or slow and contemplative
|
||||
|
||||
### Tutorial / changelog / software demo
|
||||
|
||||
- **Software being demonstrated?** — Name, what it does
|
||||
- **Demo script?** — Sequence of commands / screens to show
|
||||
- **Terminal-only or with GUI?**
|
||||
- **Voiceover for narration?**
|
||||
- **Diagram support needed?** — Often these benefit from a diagram skill
|
||||
alongside the screen-capture/render step (`excalidraw`,
|
||||
`architecture-diagram`, `concept-diagrams`)
|
||||
|
||||
### ASCII / terminal art
|
||||
|
||||
- **Source material?** — Generative / driven by audio / converting existing
|
||||
video / static image starting point
|
||||
- **Color palette?** — Brand-driven (gold/black/blue), Matrix green, full
|
||||
rainbow, monochrome
|
||||
- **Audio reactivity?** — None / loose mood / tight beat sync / FFT-driven
|
||||
- **Character set?** — ASCII only / Unicode block-drawing / mystic glyphs
|
||||
- **Loop or narrative?** — Perfect loop or one-shot
|
||||
|
||||
### Abstract / loop
|
||||
|
||||
- **Mood / emotion?** — One word that captures the feel
|
||||
- **Motion type?** — Zoom-into-itself, particle drift, wave, geometric, organic
|
||||
- **Loop required?** — Perfect loop (Droste-style) or just satisfying ending
|
||||
- **Audio?** — Silent, ambient pad, beat-synced
|
||||
|
||||
### Documentary / interview cut
|
||||
|
||||
- **Source footage?** — Provided clips, length per clip
|
||||
- **Transcript / subtitles?** — Provided or to be generated
|
||||
- **Story structure?** — Chronological / thematic / arc
|
||||
- **B-roll approach?** — Generated, stock library, none
|
||||
|
||||
### Real-time / installation
|
||||
|
||||
- **Output environment?** — Gallery wall, projector, screen, web embed
|
||||
- **Audio source?** — Live audio input, pre-recorded track, both
|
||||
- **Reactivity tightness?** — Mood-level (loose) vs. tight beat-sync vs. live
|
||||
parameter control
|
||||
- **Tool preference?** — `touchdesigner-mcp` for full TD operator graphs;
|
||||
`p5js` for web-canvas; `comfyui` for generative-AI fed by audio features
|
||||
|
||||
## Tier 2 — Always ask near the end
|
||||
|
||||
- **Brand assets path?** — Where logo / color palette / fonts / music library lives
|
||||
- **Output format requirements?** — Codec preference, target file size, accepted
|
||||
alternates (vertical cut, GIF, audio-only)
|
||||
- **Deadline?** — Affects task `max_runtime_seconds` and acceptable scope
|
||||
- **Quality bar?** — Rough draft for review / polished final / archival
|
||||
- **Existing footage / assets to reuse?** — Anything that should appear, not just inform
|
||||
|
||||
## Reasonable assumption defaults
|
||||
|
||||
When the user under-specifies, fill in these defaults rather than asking:
|
||||
|
||||
| Question | Default |
|
||||
|----------|---------|
|
||||
| Frame rate | 30 fps for X / IG; 60 fps for tutorials/explainers; 24 fps for narrative film |
|
||||
| Resolution | 1080×1080 for square, 1920×1080 for 16:9, 1080×1920 for 9:16 |
|
||||
| Codec | H.264 / yuv420p, CRF 18 |
|
||||
| Audio codec | AAC 192 kbps |
|
||||
| Voice | Provider's mid-range neutral voice unless brand calls for distinctive timbre |
|
||||
| Music | Silent (require user to specify if music is wanted) |
|
||||
| Captions | On for explainer/tutorial; off for narrative/abstract unless requested |
|
||||
| Quality bar | Polished final unless user says draft |
|
||||
|
||||
State the assumption explicitly: *"Assuming 30fps and AAC audio unless you say otherwise — proceed?"*
|
||||
|
||||
## Anti-patterns
|
||||
|
||||
- **Asking 10 questions at once.** Maximum 4 per turn.
|
||||
- **Asking for things the brief already implies.** If the user said "music video for my track," do not ask "is there a track?"
|
||||
- **Failing to classify before drilling in.** Tier-1 questions depend on classification; mixing them up wastes turns.
|
||||
- **Treating "make a video" as enough to proceed.** Always confirm the three baseline questions.
|
||||
@@ -1,276 +0,0 @@
|
||||
# Kanban Setup — Project Bootstrap & Profile Configuration
|
||||
|
||||
Once the brief is locked and the team is designed, the next step is producing
|
||||
the actual `setup.sh` that creates the project workspace, configures Hermes
|
||||
profiles, and fires the initial kanban task.
|
||||
|
||||
This file documents the patterns. The companion script
|
||||
`scripts/bootstrap_pipeline.py` automates most of it from a structured input
|
||||
JSON.
|
||||
|
||||
> **Credit:** the single-project-workspace layout, profile-config patching
|
||||
> approach, SOUL.md-per-profile convention, and `--workspace dir:<path>` rule
|
||||
> are adapted from alt-glitch's original multi-agent video pipeline:
|
||||
> [NousResearch/kanban-video-pipeline](https://github.com/NousResearch/kanban-video-pipeline).
|
||||
> This skill generalizes those patterns across video styles and replaces the
|
||||
> string-replacement config patcher with a PyYAML-based one.
|
||||
|
||||
## Project workspace structure
|
||||
|
||||
Every video project gets one workspace under `~/projects/video-pipeline/<slug>/`:
|
||||
|
||||
```
|
||||
~/projects/video-pipeline/<slug>/
|
||||
├── brief.md ← the contract; all tasks reference
|
||||
├── TEAM.md ← team composition + task graph (director reads this)
|
||||
├── taste/
|
||||
│ ├── brand-guide.md ← color, typography, motion rules
|
||||
│ ├── emotional-dna.md ← what the piece should FEEL like
|
||||
│ └── style-frames/ ← optional: visual references
|
||||
├── audio/
|
||||
│ ├── track.mp3 ← provided music (if any)
|
||||
│ ├── voiceover/ ← per-line TTS clips
|
||||
│ └── sfx/ ← sound effects
|
||||
├── assets/
|
||||
│ ├── logos/
|
||||
│ ├── fonts/
|
||||
│ └── existing-footage/ ← reusable provided clips
|
||||
├── scenes/
|
||||
│ ├── scene-01/
|
||||
│ │ ├── VISUAL_SPEC.md ← cinematographer's per-scene spec
|
||||
│ │ ├── render.py ← renderer's code (or sketch.html, etc.)
|
||||
│ │ ├── checkpoints/ ← preview frames for QA
|
||||
│ │ └── clip.mp4 ← the deliverable for this scene
|
||||
│ ├── scene-02/...
|
||||
│ └── ...
|
||||
├── checkpoints/ ← global review frames
|
||||
├── tools/ ← optional project-local helpers
|
||||
└── output/
|
||||
├── final.mp4 ← stitched + audio
|
||||
├── final-noaudio.mp4
|
||||
├── final-9x16.mp4 ← optional: vertical alternate
|
||||
└── captions.srt ← optional: subtitle file
|
||||
```
|
||||
|
||||
**The slug** is derived from the brief title: lowercase, hyphen-separated.
|
||||
Example: `q3-product-teaser`, `ascii-mood-loop`, `interview-cut-2026-q1`.
|
||||
|
||||
## The setup.sh script
|
||||
|
||||
The setup script does six things in order:
|
||||
|
||||
1. **Create workspace tree** — all directories above
|
||||
2. **Create profiles** — `hermes profile create <name> --clone`
|
||||
3. **Configure profiles** — patch each profile's
|
||||
`~/.hermes/profiles/<name>/config.yaml` to set toolsets, always_load skills,
|
||||
and `cwd`
|
||||
4. **Write SOUL.md per profile** — the personality + role definition
|
||||
5. **Copy any provided assets + write `brief.md`, `TEAM.md`, and `taste/`**
|
||||
6. **Fire the initial kanban task** — `hermes kanban create` assigned to the director
|
||||
|
||||
See `assets/setup.sh.tmpl` for the skeleton.
|
||||
|
||||
### Profile creation pattern
|
||||
|
||||
```bash
|
||||
hermes profile create director --clone 2>/dev/null || true
|
||||
```
|
||||
|
||||
The `--clone` flag clones from the active profile (preserving model, base
|
||||
config). The `|| true` makes the script idempotent — re-running won't error if
|
||||
the profile already exists.
|
||||
|
||||
### Profile config patching
|
||||
|
||||
Each profile has a YAML config at `~/.hermes/profiles/<name>/config.yaml`. The
|
||||
setup script edits exactly two keys:
|
||||
|
||||
1. `toolsets:` — replace the default with the role's required toolsets
|
||||
2. `skills.always_load:` — list the role's must-load skills (may be empty)
|
||||
|
||||
**Do NOT** modify `approvals.mode` (controls user-confirmation of tool calls
|
||||
— a security setting that must stay as the user configured it). **Do NOT**
|
||||
modify `terminal.cwd` — the kanban dispatcher overrides cwd per-task via
|
||||
`--workspace dir:<path>`, so the profile's cwd is irrelevant to the kanban
|
||||
work and changing it could break the user's interactive use of the profile.
|
||||
|
||||
Use **PyYAML**, not string replacement, so the patch is robust against
|
||||
default-config schema drift:
|
||||
|
||||
```bash
|
||||
configure_profile() {
|
||||
local profile="$1"
|
||||
local toolsets_json="$2" # JSON array, e.g. '["kanban","terminal","file"]'
|
||||
local skills_json="$3" # JSON array, e.g. '["kanban-worker","ascii-video"]'
|
||||
python3 - "$profile" "$toolsets_json" "$skills_json" <<'PY'
|
||||
import json, os, sys, yaml
|
||||
profile, ts_json, sk_json = sys.argv[1:4]
|
||||
p = os.path.expanduser(f"~/.hermes/profiles/{profile}/config.yaml")
|
||||
with open(p) as f:
|
||||
cfg = yaml.safe_load(f) or {}
|
||||
cfg["toolsets"] = json.loads(ts_json)
|
||||
cfg.setdefault("skills", {})["always_load"] = json.loads(sk_json)
|
||||
with open(p, "w") as f:
|
||||
yaml.safe_dump(cfg, f, sort_keys=False)
|
||||
PY
|
||||
}
|
||||
```
|
||||
|
||||
PyYAML must be installed in the user's Python (it ships with most Hermes
|
||||
installs). If absent: `pip install pyyaml`.
|
||||
|
||||
The setup script should also **validate** the patch by re-reading the file
|
||||
and comparing — see `assets/setup.sh.tmpl` for the validation pattern.
|
||||
|
||||
### SOUL.md per profile
|
||||
|
||||
Each profile gets a `SOUL.md` at `~/.hermes/profiles/<name>/SOUL.md` that
|
||||
defines its role, voice, and rules. See `assets/soul.md.tmpl` for the
|
||||
template. Customize per role and per project.
|
||||
|
||||
The director's SOUL.md should be the most opinionated — its voice flavors
|
||||
the entire production. **Critical content for the director's SOUL.md:**
|
||||
|
||||
- **Anti-temptation rules:** "Do not execute the work yourself. For every
|
||||
concrete task, create a kanban task and assign it. Decompose, route, comment,
|
||||
approve — that's the whole job." (The `kanban-orchestrator` skill provides
|
||||
the deeper playbook; load it.)
|
||||
- **Decomposition steps:** Read `brief.md`, `TEAM.md`, `taste/`. Use the team
|
||||
graph in `TEAM.md` to fan out tasks.
|
||||
- **The workspace_path rule** (see below).
|
||||
|
||||
Other profiles' SOUL.md is briefer; mostly mechanical: who you are, what you
|
||||
read, what you produce, what skills/tools to use, where to write outputs.
|
||||
Most non-director profiles should `always_load: kanban-worker` for the
|
||||
deeper-than-baseline kanban guidance.
|
||||
|
||||
### Initial kanban task
|
||||
|
||||
The final action of setup.sh is firing the kanban:
|
||||
|
||||
```bash
|
||||
hermes kanban create "Direct production of <video title>" \
|
||||
--assignee director \
|
||||
--workspace dir:"$HOME/projects/video-pipeline/${PROJECT_SLUG}" \
|
||||
--tenant ${PROJECT_SLUG} \
|
||||
--priority 2 \
|
||||
--max-runtime 4h \
|
||||
--body "$(cat <<EOF
|
||||
Read brief.md, TEAM.md, and taste/.
|
||||
Decompose into the team graph defined in TEAM.md.
|
||||
All child tasks MUST use:
|
||||
workspace_kind="dir"
|
||||
workspace_path="$HOME/projects/video-pipeline/${PROJECT_SLUG}"
|
||||
tenant="${PROJECT_SLUG}"
|
||||
EOF
|
||||
)"
|
||||
```
|
||||
|
||||
The `--workspace dir:<path>` flag is **critical** — it tells the kanban that
|
||||
all child tasks share this workspace. Skipping or using `worktree` will
|
||||
isolate profiles and break artifact sharing.
|
||||
|
||||
## The TEAM.md file
|
||||
|
||||
Alongside `brief.md`, write a `TEAM.md` that the director reads. It documents
|
||||
the team composition + task graph the orchestrator should follow. This
|
||||
removes ambiguity and prevents the director from inventing extra steps.
|
||||
|
||||
Example structure (for an ASCII video with a music supervisor and editor):
|
||||
|
||||
```markdown
|
||||
# Team & Task Graph — <video title>
|
||||
|
||||
## Team
|
||||
|
||||
- `director` (this profile) — vision, decomposition, approval
|
||||
- `cinematographer` — visual spec, quality review (loads `ascii-video`)
|
||||
- `renderer-ascii` — ASCII scenes (loads `ascii-video`)
|
||||
- `music-supervisor` — track analysis (loads `songsee`)
|
||||
- `voice-talent` — narration (uses ElevenLabs API)
|
||||
- `audio-mixer` — final mix (ffmpeg)
|
||||
- `editor` — assembly (ffmpeg)
|
||||
- `reviewer` — final QA gate
|
||||
|
||||
## Task Graph
|
||||
|
||||
T0: this task — decompose
|
||||
│
|
||||
├── T1: cinematographer "Design visual language" (parent: T0)
|
||||
│ │
|
||||
│ ├── T2a: renderer-ascii "Scene 1 — title card" (parent: T1)
|
||||
│ ├── T2b: renderer-ascii "Scene 2 — main beat" (parent: T1)
|
||||
│ ├── T2c: renderer-ascii "Scene 3 — outro" (parent: T1)
|
||||
│
|
||||
├── T3: music-supervisor "Analyze track + emit beats.json" (parent: T0)
|
||||
│
|
||||
├── T4: voice-talent "Generate narration" (parent: T0)
|
||||
│
|
||||
├── T5: audio-mixer "Mix VO + bg music" (parents: T3, T4)
|
||||
│
|
||||
├── T6: editor "Assemble cut + mux audio" (parents: T2*, T5)
|
||||
│
|
||||
└── T7: reviewer "Final QA" (parent: T6)
|
||||
```
|
||||
|
||||
The director turns this into actual `kanban_create` calls.
|
||||
|
||||
## API-key prerequisites check
|
||||
|
||||
Before firing the kanban, verify required keys are available. Check both
|
||||
`~/.hermes/.env` and macOS Keychain (if on macOS):
|
||||
|
||||
```bash
|
||||
check_key() {
|
||||
local var="$1"
|
||||
local kc_account="$2"
|
||||
local kc_service="$3"
|
||||
if grep -q "^${var}=" ~/.hermes/.env 2>/dev/null && \
|
||||
[ -n "$(grep "^${var}=" ~/.hermes/.env | cut -d= -f2-)" ]; then
|
||||
return 0
|
||||
fi
|
||||
if command -v security >/dev/null 2>&1 && \
|
||||
security find-generic-password -a "${kc_account}" -s "${kc_service}" -w >/dev/null 2>&1; then
|
||||
return 0
|
||||
fi
|
||||
echo "ERROR: ${var} not set in ~/.hermes/.env or Keychain (${kc_account}/${kc_service})"
|
||||
return 1
|
||||
}
|
||||
|
||||
check_key ELEVENLABS_API_KEY hermes ELEVENLABS_API_KEY || exit 1
|
||||
check_key OPENROUTER_API_KEY hermes OPENROUTER_API_KEY || exit 1
|
||||
# ...
|
||||
```
|
||||
|
||||
If a key is missing, the script aborts with a clear message rather than
|
||||
firing a kanban that will hit credential errors mid-execution.
|
||||
|
||||
## Critical rules
|
||||
|
||||
1. **`workspace_kind="dir"` + `workspace_path="<absolute>"` on every kanban_create.** Otherwise profiles can't share artifacts.
|
||||
|
||||
2. **Tenant every task.** `--tenant <project-slug>` keeps the dashboard scoped
|
||||
and prevents cross-pollination with other ongoing kanbans.
|
||||
|
||||
3. **Idempotency keys.** For tasks that should not duplicate on re-run (e.g.,
|
||||
setup creating profiles), use the `idempotency_key` argument or check
|
||||
existence first.
|
||||
|
||||
4. **`max_runtime_seconds` per task.** Renderers that get stuck eat compute.
|
||||
Standard defaults:
|
||||
- Renderer task: 1800s (30min)
|
||||
- Editor task: 600s (10min)
|
||||
- Voice-talent task: 300s (5min)
|
||||
- Image-generator task: 600s (10min)
|
||||
- Image-to-video-generator task: 900s (15min)
|
||||
|
||||
5. **Heartbeats for long renders.** Tasks expected to run >5min should emit
|
||||
`kanban_heartbeat` periodically with progress. Renderers should report
|
||||
frame counts; the editor should report assembly progress.
|
||||
|
||||
6. **The `audio/` and `taste/` dirs are populated BEFORE firing the kanban.**
|
||||
Don't ask the director's pipeline to source these — copy at setup time.
|
||||
|
||||
7. **`brief.md` is read-only after setup.** If the brief changes during
|
||||
execution, that's a significant pivot — re-fire the kanban rather than edit
|
||||
live.
|
||||
@@ -1,180 +0,0 @@
|
||||
# Monitoring — Watch the Pipeline + Intervene
|
||||
|
||||
After `setup.sh` fires the kanban, the work runs autonomously. The role of
|
||||
this skill in the execution phase is to help the user (and the AI overseeing
|
||||
the session) detect problems early and intervene effectively.
|
||||
|
||||
## Live monitoring commands
|
||||
|
||||
```bash
|
||||
# Live event stream — task spawns, status changes, heartbeats, completions
|
||||
hermes kanban watch --tenant <project-slug>
|
||||
|
||||
# Snapshot of the board
|
||||
hermes kanban list --tenant <project-slug>
|
||||
hermes kanban list --tenant <project-slug> --json # machine-readable
|
||||
|
||||
# Per-status counts + oldest-ready age
|
||||
hermes kanban stats --tenant <project-slug>
|
||||
|
||||
# Visual dashboard (browser)
|
||||
hermes dashboard
|
||||
|
||||
# Inspect a specific task (includes comments + events)
|
||||
hermes kanban show <task-id>
|
||||
|
||||
# Follow a single task's event stream
|
||||
hermes kanban tail <task-id>
|
||||
```
|
||||
|
||||
Verify available subcommands with `hermes kanban --help` — the kanban CLI
|
||||
ships with `init / create / list / show / assign / link / unlink / claim /
|
||||
comment / complete / block / unblock / archive / tail / dispatch / watch /
|
||||
stats / heartbeat / log / runs / context / gc`.
|
||||
|
||||
The companion `scripts/monitor.py` polls the kanban via the CLI and surfaces
|
||||
common issues (stuck tasks, missing heartbeats, repeated retries, dependency
|
||||
deadlocks).
|
||||
|
||||
## What to watch for
|
||||
|
||||
### Healthy pipeline indicators
|
||||
|
||||
- Tasks transition `READY → RUNNING → DONE` in roughly the expected order
|
||||
- Renderers emit periodic `kanban_heartbeat` events with progress (e.g. "frame
|
||||
240/720")
|
||||
- Each task's runtime is well under its `max_runtime_seconds` cap
|
||||
- No task accumulates more than 1 retry
|
||||
- Dependency arrows resolve (children unblock as parents complete)
|
||||
|
||||
### Warning signs
|
||||
|
||||
| Symptom | Likely cause | Action |
|
||||
|---------|--------------|--------|
|
||||
| Task RUNNING but no heartbeat in 2+ min | Worker stuck, infinite loop, blocked on input | `hermes kanban show <id>` — read the worker's last events. The dispatcher SIGTERMs tasks that exceed their `max-runtime`; if you need to stop one earlier, `hermes kanban block <id>` then `hermes kanban archive <id>`, and create a re-run task. |
|
||||
| Same task retried 2+ times | Reproducible failure (missing key, bad spec, broken tool) | `hermes kanban show <id>` to read failure events. Fix root cause before re-running. |
|
||||
| RUNNING longer than max_runtime | Task is slow but progressing OR genuinely stuck | Check heartbeats with `hermes kanban tail <id>`. If progressing, the dispatcher will SIGTERM eventually anyway — raise `max-runtime` on a re-created task. |
|
||||
| Child task READY but parents still RUNNING for >2× expected | Cascade slow, dependency miswired | Check the dependency graph. Inspect the parent: sometimes it completed but its handoff fields (summary, metadata) were empty so the child has nothing to consume. |
|
||||
| New tasks not appearing | Director is hung in decomposition | Inspect director task with `kanban show`. Often a malformed `kanban_create` call. |
|
||||
| Specialist tasks completing instantly | Decomposition created tasks without bodies | Director didn't pass enough context. Re-create with explicit body content. |
|
||||
| Tasks created but never picked up | Profile not running, or tenant mismatch, or dispatcher not running | Check `hermes profile list` (profile exists?), `hermes status` (gateway/dispatcher up?), and verify tenant. |
|
||||
| Specific renderer task fails → review note → renderer redoes → fails again | Brief is asking for the impossible | Pivot the brief, not the renderer. |
|
||||
|
||||
## Intervention recipes
|
||||
|
||||
### Rejecting bad output
|
||||
|
||||
When a renderer ships a clip that doesn't pass review:
|
||||
|
||||
```bash
|
||||
# 1. Comment on the renderer's task with specific feedback
|
||||
hermes kanban comment <renderer-task-id> "Scene 3 looks too sparse \
|
||||
— increase visual density. Tighten color palette to brand spec."
|
||||
|
||||
# 2. Create a re-render task with the original as parent
|
||||
hermes kanban create "Scene 3 — re-render with feedback" \
|
||||
--assignee renderer-ascii \
|
||||
--parent <renderer-task-id> \
|
||||
--workspace dir:"$HOME/projects/video-pipeline/<slug>" \
|
||||
--tenant <slug> \
|
||||
--skill ascii-video \
|
||||
--max-runtime 30m
|
||||
```
|
||||
|
||||
### Adding a new dependency mid-flight
|
||||
|
||||
When the editor needs an asset that wasn't originally planned (e.g., a captions
|
||||
file):
|
||||
|
||||
```bash
|
||||
# 1. Create the new task and capture its id
|
||||
NEW_TASK_ID=$(hermes kanban create "Generate SRT captions from voiceover" \
|
||||
--assignee captioner \
|
||||
--workspace dir:"$HOME/projects/video-pipeline/<slug>" \
|
||||
--tenant <slug> \
|
||||
--json | python3 -c "import json,sys;print(json.load(sys.stdin)['id'])")
|
||||
|
||||
# 2. Wire it as a parent of the editor's task with `kanban link`
|
||||
hermes kanban link "$NEW_TASK_ID" <editor-task-id>
|
||||
```
|
||||
|
||||
`kanban link` takes `parent_id child_id` (parent first). Use `kanban unlink`
|
||||
to remove a dependency.
|
||||
|
||||
### Stopping a worker that's stuck
|
||||
|
||||
The kanban dispatcher will SIGTERM (then SIGKILL) any task that exceeds its
|
||||
`--max-runtime` automatically. To stop one sooner:
|
||||
|
||||
```bash
|
||||
# Mark blocked so the dispatcher leaves it alone, then archive
|
||||
hermes kanban block <task-id>
|
||||
hermes kanban archive <task-id>
|
||||
|
||||
# Diagnose what happened
|
||||
hermes kanban show <task-id> # task body, comments, recent events
|
||||
hermes kanban tail <task-id> # follow the live event stream
|
||||
hermes kanban log <task-id> # worker process log
|
||||
```
|
||||
|
||||
After stopping, decide: fix root cause + re-create the task, or skip and
|
||||
adjust dependent tasks.
|
||||
|
||||
### Pivoting the brief
|
||||
|
||||
If during execution the user wants something fundamentally different:
|
||||
|
||||
1. Cancel the active director task and all RUNNING children
|
||||
2. Edit `brief.md` and `TEAM.md`
|
||||
3. Re-fire the initial `hermes kanban create` for the director
|
||||
|
||||
Don't try to "edit while running" — the kanban's audit trail makes a clean
|
||||
pivot more legible than mid-stream changes.
|
||||
|
||||
## Periodic check-in script
|
||||
|
||||
A simple polling pattern for hands-off monitoring:
|
||||
|
||||
```bash
|
||||
while true; do
|
||||
clear
|
||||
hermes kanban list --tenant <slug>
|
||||
echo "---"
|
||||
hermes kanban stats --tenant <slug>
|
||||
sleep 30
|
||||
done
|
||||
```
|
||||
|
||||
For a live event feed, run `hermes kanban watch --tenant <slug>` in a
|
||||
separate terminal — it streams task lifecycle events as they happen.
|
||||
|
||||
For automated intervention (auto-restart stuck tasks, auto-create re-render on
|
||||
review failure), see the `scripts/monitor.py` patterns.
|
||||
|
||||
## When to call it done
|
||||
|
||||
The pipeline is finished when:
|
||||
|
||||
1. All RENDER tasks complete and pass review
|
||||
2. The editor's `output/final.mp4` exists and `ffprobe` confirms expected
|
||||
duration + streams
|
||||
3. The reviewer (if present) has approved
|
||||
4. Optional masterer variants exist
|
||||
|
||||
At this point, present the final.mp4 path to the user along with any review
|
||||
notes. Do NOT delete the workspace — the user may want to iterate on a single
|
||||
scene without re-running the whole pipeline.
|
||||
|
||||
## Common gotchas
|
||||
|
||||
- **Tenant mismatches.** A task created with the wrong tenant won't appear in
|
||||
monitoring. Always pass `--tenant <slug>` consistently.
|
||||
- **Profile process not running.** Tasks queue indefinitely in READY if no
|
||||
worker for that profile is online. Check `hermes profile list` and start
|
||||
any missing profiles.
|
||||
- **Workspace permissions.** All profiles need read+write to the workspace
|
||||
directory. `chmod -R u+rw <workspace>` if any worker reports permission
|
||||
errors.
|
||||
- **Audio/visual sync.** The editor's clip stitching must match the
|
||||
renderer's actual output durations. Don't hardcode scene durations in
|
||||
the editor — read from the renderer's handoff metadata.
|
||||
@@ -1,298 +0,0 @@
|
||||
# Role Archetypes
|
||||
|
||||
The library of role archetypes for video production. **Compose a team from this
|
||||
list, don't clone a fixed roster.** Most videos need 4-7 profiles. The director
|
||||
is always present; everything else is conditional on the brief.
|
||||
|
||||
Each role's profile name is by convention `kebab-case` (e.g. `creative-director`,
|
||||
`image-generator`). Multiple instances of the same role get descriptive suffixes
|
||||
when they need different focus (e.g., `renderer-ascii`, `renderer-3d`).
|
||||
|
||||
For toolset + skill mapping per role, see [tool-matrix.md](tool-matrix.md).
|
||||
|
||||
## Always present
|
||||
|
||||
### director
|
||||
|
||||
The vision-holder. Reads the brief and brand guide, decomposes into a task
|
||||
graph, comments to steer creative direction, approves the final cut.
|
||||
|
||||
- **Toolsets:** kanban, terminal, file
|
||||
- **Skills:** `kanban-orchestrator`. The kanban plugin auto-injects baseline
|
||||
orchestration guidance for free; `kanban-orchestrator` is the deeper
|
||||
decomposition playbook. Add `creative-ideation` if the brief is wide-open
|
||||
and needs framing help.
|
||||
- **Personality:** Tied to the brand voice — see `assets/soul.md.tmpl`
|
||||
|
||||
The director has the same toolset as everyone else, but its `SOUL.md` rules
|
||||
**forbid** execution. The "decompose, don't execute" discipline is enforced
|
||||
by personality + the kanban-orchestrator skill, not by missing tools.
|
||||
|
||||
## Pre-production roles
|
||||
|
||||
Pick based on what the brief needs.
|
||||
|
||||
### writer / screenwriter
|
||||
|
||||
Writes scripts, dialogue, voiceover copy, narration. Use for any video with
|
||||
spoken or written words beyond a tagline.
|
||||
|
||||
- **Toolsets:** kanban, file
|
||||
- **Skills:** `kanban-worker`, `humanizer` (post-process to strip AI-tells)
|
||||
- **Outputs:** `script.md`, `narration.md`, `dialogue/scene-NN.md`
|
||||
|
||||
### copywriter
|
||||
|
||||
Like `writer` but specifically for marketing copy: taglines, CTAs, voiceover
|
||||
scripts for product videos.
|
||||
|
||||
- **Toolsets:** kanban, file
|
||||
- **Skills:** `kanban-worker`, `humanizer`
|
||||
- **Outputs:** `copy.md`
|
||||
|
||||
### concept-artist / visual-designer
|
||||
|
||||
Develops the visual identity: mood board, style frames, color palette
|
||||
rationale, typography choices. Produces a `visual-spec.md` that all generators
|
||||
follow. Often produces still reference frames using image-generation APIs or
|
||||
local skills.
|
||||
|
||||
- **Toolsets:** kanban, terminal, file
|
||||
- **Skills:** `kanban-worker` plus any project-specific design skill —
|
||||
`claude-design` (UI/web), `sketch` (quick mockup variants),
|
||||
`popular-web-designs` (matching known web aesthetic), `pixel-art` (retro),
|
||||
`ascii-art` (terminal/retro), `excalidraw` (hand-drawn frames),
|
||||
`design-md` (text-based design docs)
|
||||
- **Outputs:** `visual-spec.md`, `taste/style-frames/*.png`
|
||||
|
||||
### storyboarder
|
||||
|
||||
Maps the brief to a beat-by-beat shot list with timing. Critical for narrative
|
||||
film and music video. Often pairs with a diagramming tool.
|
||||
|
||||
- **Toolsets:** kanban, file
|
||||
- **Skills:** `kanban-worker` plus a diagram skill — `excalidraw` (sketch),
|
||||
`architecture-diagram` (technical/system), `concept-diagrams` (educational/
|
||||
scientific)
|
||||
- **Outputs:** `storyboard.md` with one row per scene/shot, optional
|
||||
storyboard sketches
|
||||
|
||||
### cinematographer / dp
|
||||
|
||||
Designs the visual language: framing, color, motion, transitions. Reviews
|
||||
generator output for visual consistency. Hands off per-scene `VISUAL_SPEC.md`.
|
||||
|
||||
- **Toolsets:** kanban, terminal, file, video, vision
|
||||
- **Skills:** `kanban-worker` plus the visual skill that matches the project
|
||||
(e.g., `ascii-video` for ASCII work, `manim-video` for explainers,
|
||||
`touchdesigner-mcp` for real-time visuals, etc.)
|
||||
- **Outputs:** `scenes/scene-NN/VISUAL_SPEC.md`, review comments on renderer
|
||||
tasks
|
||||
- **Reviews via:** `video_analyze` (sends full clip to multimodal LLM for
|
||||
native review), `vision_analyze` for spot-checking frames, ffprobe summaries
|
||||
|
||||
## Production roles
|
||||
|
||||
### renderer (generic)
|
||||
|
||||
A worker that produces visual content for one or more scenes. Loaded with
|
||||
whichever creative skill fits the scene's style. Multiple renderers can run in
|
||||
parallel, each pinned to a different skill via `always_load` in their profile
|
||||
or `--skill` on the task.
|
||||
|
||||
- **Toolsets:** kanban, terminal, file
|
||||
- **Skills:** one creative skill (see specialized variants below)
|
||||
- **Outputs:** `scenes/scene-NN/clip.mp4`
|
||||
|
||||
### Specialized renderer variants
|
||||
|
||||
When scenes need very different tools, create specialized renderer profiles
|
||||
instead of overloading one. Each loads a different creative skill.
|
||||
|
||||
| Variant | Skill | Best for |
|
||||
|---------|-------|----------|
|
||||
| `renderer-ascii` | `ascii-video` | Terminal aesthetic, retro pixel, audio-reactive grid, video-to-ASCII conversion |
|
||||
| `renderer-manim` | `manim-video` | Math, algorithms, 3Blue1Brown-style explainers, equation derivations |
|
||||
| `renderer-p5js` | `p5js` | Generative art, particles, shaders, organic motion, web-canvas content |
|
||||
| `renderer-comfyui` | `comfyui` | AI-generated stills + video using local ComfyUI workflows (img-to-img, img-to-video, etc.) |
|
||||
| `renderer-touchdesigner` | `touchdesigner-mcp` | Real-time, audio-reactive, installation art, VJ-style content |
|
||||
| `renderer-3d` | `blender-mcp` *(optional)* | 3D modeling, animation, photoreal environments, character animation |
|
||||
| `renderer-pixel` | `pixel-art` | Retro game aesthetic with era-correct palettes |
|
||||
| `renderer-comic` | `baoyu-comic` | Knowledge-comic style narrative scenes |
|
||||
| `renderer-meme` | `meme-generation` *(optional)* | Meme-style stills for satirical/social content |
|
||||
| `renderer-procedural` | (none — Python with PIL + ffmpeg directly) | Custom procedural content where no skill fits |
|
||||
| `renderer-video` | (external image-to-video API: Runway / Kling / Luma) | Animating still images in narrative film |
|
||||
| `renderer-motion-graphics` | (external — Remotion CLI) | Motion graphics, kinetic typography, UI animations |
|
||||
|
||||
For external-API renderers, the profile holds the API client logic; only
|
||||
`kanban-worker` is loaded, plus the terminal toolset and the API key.
|
||||
|
||||
### image-generator
|
||||
|
||||
Specifically for text-to-image generation. Often produces stills that go to
|
||||
`renderer-video` for animation.
|
||||
|
||||
- **Toolsets:** kanban, terminal, file
|
||||
- **Skills:** `kanban-worker`, optionally `comfyui` (drives a local
|
||||
ComfyUI install for image generation)
|
||||
- **External APIs (alternative to local ComfyUI):** FAL, Replicate, OpenAI
|
||||
Images, Midjourney
|
||||
- **Outputs:** `scenes/scene-NN/stills/*.png`
|
||||
|
||||
### image-to-video-generator
|
||||
|
||||
Takes still images and animates them via Runway/Kling/Luma APIs, or via
|
||||
ComfyUI's image-to-video workflows locally. Almost always follows
|
||||
`image-generator` in narrative film pipelines.
|
||||
|
||||
- **Toolsets:** kanban, terminal, file
|
||||
- **Skills:** `kanban-worker`, optionally `comfyui` (for local image-to-video
|
||||
workflows like AnimateDiff or WAN)
|
||||
- **External APIs:** Runway, Kling, Luma, Pika
|
||||
- **Outputs:** `scenes/scene-NN/clip.mp4`
|
||||
|
||||
### music-supervisor
|
||||
|
||||
Sources, analyzes, and prepares the music track. For music videos, also
|
||||
produces a beat/BPM map and key-moment timestamps. Uses `songsee` for
|
||||
spectrograms when the editor or renderer needs a visual reference of the
|
||||
audio's energy.
|
||||
|
||||
- **Toolsets:** kanban, terminal, file
|
||||
- **Skills:** `kanban-worker`, `songsee` (audio visualization), plus one of:
|
||||
- `songwriting-and-ai-music` — when commissioning lyrics + Suno prompts
|
||||
- `heartmula` — when generating music with the open-source local model
|
||||
- `spotify` — when sourcing existing tracks
|
||||
- **Outputs:** `audio/track.mp3`, `audio/beats.json`, optional
|
||||
`audio/track-spectrogram.png`
|
||||
|
||||
### voice-talent / narrator
|
||||
|
||||
Generates voiceover audio. Calls a TTS API directly; no Hermes skill required
|
||||
beyond `kanban-worker`. The user can also supply pre-recorded VO instead of
|
||||
generation.
|
||||
|
||||
- **Toolsets:** kanban, terminal, file
|
||||
- **Skills:** `kanban-worker`
|
||||
- **External APIs:** ElevenLabs, OpenAI TTS, etc.
|
||||
- **Outputs:** `audio/voiceover/line-NN.mp3`, `audio/voiceover/timeline.mp3`
|
||||
|
||||
### foley / sfx-designer
|
||||
|
||||
Sound effects and ambient design. Often optional unless the brief calls for
|
||||
sound design specifically.
|
||||
|
||||
- **Toolsets:** kanban, terminal, file
|
||||
- **Skills:** `kanban-worker`, `songsee` for audio-feature visualization when
|
||||
designing to a track
|
||||
- **Outputs:** `audio/sfx/*.mp3`
|
||||
|
||||
## Post-production roles
|
||||
|
||||
### editor
|
||||
|
||||
Assembles the final cut from clips. Uses ffmpeg for stitching, fades,
|
||||
transitions. Reviews each clip for pacing and quality before assembly.
|
||||
|
||||
- **Toolsets:** kanban, terminal, file
|
||||
- **Skills:** `kanban-worker`
|
||||
- **External tools:** ffmpeg, ffprobe
|
||||
- **Outputs:** `output/final.mp4`, `output/final-noaudio.mp4`
|
||||
|
||||
### colorist
|
||||
|
||||
Color grading. Usually optional — if the renderers already produce
|
||||
brand-consistent output and the editor just stitches, the colorist is overkill.
|
||||
Worth including for narrative film with hero shots.
|
||||
|
||||
- **Toolsets:** kanban, terminal, file
|
||||
- **Skills:** `kanban-worker`
|
||||
- **Outputs:** `output/final-graded.mp4`
|
||||
|
||||
### audio-mixer
|
||||
|
||||
Mixes voiceover + music + SFX into a final audio track. Sets levels, ducks
|
||||
music under VO, normalizes loudness (LUFS).
|
||||
|
||||
- **Toolsets:** kanban, terminal, file
|
||||
- **Skills:** `kanban-worker`
|
||||
- **External tools:** ffmpeg with `loudnorm` filter, optional `sox`
|
||||
- **Outputs:** `audio/final-mix.mp3`
|
||||
|
||||
### captioner
|
||||
|
||||
Burns subtitles into the video, generates SRT, handles accessibility. Can also
|
||||
generate captions from audio via Whisper.
|
||||
|
||||
- **Toolsets:** kanban, terminal, file
|
||||
- **Skills:** `kanban-worker`
|
||||
- **External tools:** Whisper (CLI or API), ffmpeg subtitle filters
|
||||
- **Outputs:** `output/captions.srt`, `output/final-captioned.mp4`
|
||||
|
||||
### masterer
|
||||
|
||||
Final encode + format variants. Produces deliverables for each platform target
|
||||
(square for IG, vertical for TikTok, full HD for YouTube, etc.).
|
||||
|
||||
- **Toolsets:** kanban, terminal, file
|
||||
- **Skills:** `kanban-worker`
|
||||
- **Outputs:** `output/final-1080.mp4`, `output/final-9x16.mp4`, etc.
|
||||
|
||||
## QA roles
|
||||
|
||||
### reviewer
|
||||
|
||||
A neutral quality gate. Reads the brief, watches the cut, comments
|
||||
specifically on what's off (pacing, sync, brand alignment, technical
|
||||
quality). Distinct from the cinematographer (who reviews visuals during
|
||||
production) and the editor (who reviews for assembly).
|
||||
|
||||
- **Toolsets:** kanban, terminal, file, video, vision
|
||||
- **Skills:** `kanban-worker`
|
||||
- **Review tools:** `video_analyze` (native clip review via multimodal LLM),
|
||||
`vision_analyze` (frame/thumbnail review), ffprobe
|
||||
- **Outputs:** `review-notes.md`, comments on tasks
|
||||
|
||||
### brand-cop
|
||||
|
||||
Reviews specifically for brand compliance — colors, typography, voice. Use
|
||||
when the brand guidelines are detailed and a generic reviewer might miss
|
||||
violations.
|
||||
|
||||
- **Toolsets:** kanban, file
|
||||
- **Skills:** `kanban-worker`
|
||||
- **Outputs:** comments + `brand-review.md`
|
||||
|
||||
## Composing teams — heuristics
|
||||
|
||||
- **Always:** director + at least one renderer + editor.
|
||||
- **Add writer** if scripted dialogue / narration / on-screen text exceeds a
|
||||
tagline.
|
||||
- **Add storyboarder** if the brief has more than 5 distinct beats and the
|
||||
director hasn't already laid out a beat list.
|
||||
- **Add cinematographer** if multiple renderer instances need consistent
|
||||
visual language. (For a single-tool video, the renderer's own skill spec
|
||||
is enough.)
|
||||
- **Add image-generator + image-to-video-generator pair** for narrative film
|
||||
with photorealistic visuals.
|
||||
- **Add music-supervisor** when music is provided and rhythm matters
|
||||
(music videos always; explainers sometimes).
|
||||
- **Add voice-talent** for any voiceover / narrative dialogue.
|
||||
- **Add audio-mixer** when there are 2+ audio sources (VO + music, music + SFX).
|
||||
- **Add captioner** for accessibility-priority projects (explainer, tutorial,
|
||||
any platform that defaults to muted playback).
|
||||
- **Add reviewer** for high-stakes projects. Skip for quick experimental loops.
|
||||
- **Add masterer** when multiple platform deliverables are needed.
|
||||
|
||||
## Anti-patterns
|
||||
|
||||
- **One renderer doing everything.** If scenes use very different tools
|
||||
(ASCII + 3D + motion graphics), use specialized renderer variants. The
|
||||
renderer loads ONE creative skill at a time; mixing styles in a single
|
||||
renderer causes thrashing.
|
||||
- **A separate profile per scene.** No. Profiles are per-role, not per-scene.
|
||||
Eight scenes use one or two renderer profiles, not eight.
|
||||
- **A "general" profile that does everything.** Worse than no specialization.
|
||||
The kanban routing breaks down if every task fits every profile.
|
||||
- **No reviewer for important deliverables.** Saves an hour of pipeline time
|
||||
but ships flaws.
|
||||
@@ -1,317 +0,0 @@
|
||||
# Tool Matrix — Skills + Toolsets per Role
|
||||
|
||||
Maps each role archetype to the Hermes skills it should `always_load` and the
|
||||
toolsets it needs. Only references skills that ship in the public hermes-agent
|
||||
repository (under `skills/` or `optional-skills/`). External APIs and CLIs are
|
||||
called from the terminal toolset; they don't appear in `always_load`.
|
||||
|
||||
## Hermes skills relevant to video production
|
||||
|
||||
### Visual / rendering skills (`hermes-agent/skills/creative/`)
|
||||
|
||||
| Skill | What it does | Best fit for |
|
||||
|-------|--------------|--------------|
|
||||
| `ascii-video` | Production pipeline for ASCII art video — generative, audio-reactive, video-to-ASCII | Renderer for ASCII / terminal / retro pixel content; cinematographer for ASCII projects |
|
||||
| `ascii-art` | Static ASCII art generation | Concept artist for ASCII style frames; secondary tool for ASCII renderer |
|
||||
| `manim-video` | Manim CE animations — math, algorithms, 3Blue1Brown-style explainers | Renderer for math, algorithm walkthroughs, technical concept explainers |
|
||||
| `p5js` | p5.js sketches — generative art, shaders, interactive, 3D | Renderer for generative art, particle systems, organic motion, web-canvas content |
|
||||
| `comfyui` | Generate images, video, audio with ComfyUI workflows (image-to-image, image-to-video, etc.) | image-generator, image-to-video-generator, or general renderer for AI-generated content |
|
||||
| `touchdesigner-mcp` | Control a running TouchDesigner instance — real-time visuals, audio-reactive installation art, VJ | Renderer for real-time/audio-reactive content; installation art; live performance |
|
||||
| `blender-mcp` *(optional)* | Control Blender 4.3+ via MCP — 3D modeling, animation, rendering | Renderer for 3D scenes, photoreal environments, character animation |
|
||||
| `pixel-art` | Pixel art with era palettes (NES, Game Boy, PICO-8) | Renderer for retro game aesthetic; concept artist for pixel-style frames |
|
||||
| `baoyu-comic` | Knowledge-comic generation (educational, biography, tutorial) | Renderer for comic-style narrative; explainer in panel form |
|
||||
| `baoyu-infographic` | Infographic generation | Renderer for data-driven explainer scenes |
|
||||
| `meme-generation` *(optional)* | Generate meme images by overlaying text on templates | Generator for satirical/social content; meme-style stills |
|
||||
|
||||
### Design / pre-production skills (`hermes-agent/skills/creative/`)
|
||||
|
||||
| Skill | What it does | Best fit for |
|
||||
|-------|--------------|--------------|
|
||||
| `claude-design` | Design one-off HTML artifacts (landing, deck, prototype) | Concept artist for product video style frames; storyboarder for UI-heavy content |
|
||||
| `design-md` | Design markdown docs | Concept artist documenting visual specs |
|
||||
| `popular-web-designs` | Reference patterns for popular web designs | Concept artist; cinematographer when matching a known UI aesthetic |
|
||||
| `sketch` | Throwaway HTML mockups (2-3 design variants to compare) | Concept artist exploring directions; storyboarder for UI flows |
|
||||
| `excalidraw` | Excalidraw-style hand-drawn diagrams | Storyboarder; concept artist for sketch-style frames |
|
||||
| `architecture-diagram` | Software architecture diagrams | Storyboarder for technical content; explainer scenes about systems |
|
||||
| `concept-diagrams` *(optional)* | Flat, minimal SVG diagrams (educational visual language; physics, chemistry, math, anatomy, etc.) | Renderer / storyboarder for explainer scenes with clean educational diagrams |
|
||||
| `pretext` | Mathematical/scientific content authoring | Writer / cinematographer for technical-explainer pretexts |
|
||||
| `creative-ideation` | Constraint-driven project ideation | Director / cinematographer when the brief is wide-open and needs framing |
|
||||
| `humanizer` | Strip AI-isms from text, add real voice | Writer / copywriter post-process to avoid AI-tells in scripts and VO copy |
|
||||
|
||||
### Audio / media skills (`hermes-agent/skills/creative/` + `skills/media/`)
|
||||
|
||||
| Skill | What it does | Best fit for |
|
||||
|-------|--------------|--------------|
|
||||
| `songwriting-and-ai-music` | Songwriting craft + Suno prompt patterns | Music supervisor when commissioning a track via Suno |
|
||||
| `heartmula` | Open-source music generation (Apache-2.0, Suno-like) | Music supervisor generating bespoke tracks without external APIs |
|
||||
| `songsee` | Spectrograms, mel/chroma/MFCC of audio files | Music supervisor analyzing tracks; foley-designer designing to a beat; editor visualizing a mix |
|
||||
| `spotify` | Spotify control — play, search, queue, manage playlists | Music supervisor sourcing existing tracks; reference research |
|
||||
| `youtube-content` | Fetch transcripts + transform to chapters/summaries/posts | Documentary cut, content adaptation, research for explainers |
|
||||
| `gif-search` | Find existing GIFs | Editor / concept artist sourcing references |
|
||||
| `gifs` | GIF tooling | Masterer producing GIF deliverables |
|
||||
|
||||
### Kanban infrastructure (`hermes-agent/skills/devops/`)
|
||||
|
||||
| Skill | What it does | When to load |
|
||||
|-------|--------------|--------------|
|
||||
| `kanban-orchestrator` | Decomposition playbook + anti-temptation rules for orchestrator profiles | Director only |
|
||||
| `kanban-worker` | Pitfalls, examples, edge cases for kanban workers (deeper than auto-injected guidance) | Any profile — load when handling tricky multi-step workflows |
|
||||
|
||||
The kanban plugin auto-injects baseline orchestration guidance into every
|
||||
worker's system prompt — the `kanban_create` fan-out pattern, claim/handoff
|
||||
lifecycle, and the "decompose, don't execute" rule for orchestrators.
|
||||
`kanban-orchestrator` and `kanban-worker` are deeper playbooks loaded when a
|
||||
profile needs them.
|
||||
|
||||
## External tools (called from terminal toolset)
|
||||
|
||||
These are **not** Hermes skills but external CLIs / APIs that profiles invoke.
|
||||
They don't appear in `always_load`; instead the role's terminal commands hit
|
||||
them directly.
|
||||
|
||||
| Tool | What it does | Profile that uses it |
|
||||
|------|--------------|----------------------|
|
||||
| `ffmpeg` | Video / audio encode, splice, mux | renderer, editor, audio-mixer, masterer |
|
||||
| `ffprobe` | Inspect media | All media-touching profiles |
|
||||
| Whisper (CLI or API) | Speech-to-text for captions | captioner |
|
||||
| Text-to-image API (FAL / Replicate / OpenAI / Midjourney) | Stills generation | image-generator (alternative to local `comfyui`) |
|
||||
| Image-to-video API (Runway / Kling / Luma / Pika) | Animate stills | image-to-video-generator |
|
||||
| Text-to-speech API (ElevenLabs / OpenAI TTS / etc.) | Voiceover generation | voice-talent |
|
||||
| Suno API or web | Track composition (paired with `songwriting-and-ai-music`) | music-supervisor |
|
||||
| Remotion CLI (`npx remotion render`) | React-based motion graphics | renderer-motion-graphics |
|
||||
| Manim CE (`manim`) | Math animation render (driven by `manim-video` skill's recipes) | renderer-manim |
|
||||
| Blender (`blender -b`) | 3D rendering (alternative to `blender-mcp`) | renderer-3d |
|
||||
|
||||
## Built-in Hermes tools for media review
|
||||
|
||||
These are native Hermes tools — not invoked via terminal but through their own
|
||||
toolsets. Enable them per-profile by adding the toolset to the profile config.
|
||||
|
||||
| Tool | Toolset | What it does | Profile that uses it |
|
||||
|------|---------|--------------|----------------------|
|
||||
| `video_analyze` | `video` (opt-in — `hermes tools enable video`) | Native video understanding — sends full clip to a multimodal LLM (Gemini via OpenRouter) for review without frame extraction. Supports mp4, webm, mov, avi, mkv. 50 MB cap. Model: `AUXILIARY_VIDEO_MODEL` env → `AUXILIARY_VISION_MODEL` fallback. | reviewer, cinematographer, editor |
|
||||
| `vision_analyze` | `vision` (core — enabled by default) | Image/frame analysis — review stills, thumbnails, exported frames. Already available to all profiles without opt-in. | reviewer, cinematographer, concept-artist |
|
||||
|
||||
## Standard toolset configurations per role
|
||||
|
||||
### director
|
||||
|
||||
```yaml
|
||||
toolsets:
|
||||
- kanban
|
||||
- terminal
|
||||
- file
|
||||
skills:
|
||||
always_load:
|
||||
- kanban-orchestrator
|
||||
```
|
||||
|
||||
The director's terminal access is conventional but the SOUL.md rules forbid
|
||||
execution. Audit logs catch violations.
|
||||
|
||||
### writer / copywriter
|
||||
|
||||
```yaml
|
||||
toolsets:
|
||||
- kanban
|
||||
- file
|
||||
skills:
|
||||
always_load:
|
||||
- kanban-worker
|
||||
- humanizer # post-process scripts to strip AI-tells
|
||||
```
|
||||
|
||||
No terminal — writers don't need it.
|
||||
|
||||
### concept-artist
|
||||
|
||||
```yaml
|
||||
toolsets:
|
||||
- kanban
|
||||
- terminal
|
||||
- file
|
||||
skills:
|
||||
always_load:
|
||||
- kanban-worker
|
||||
# plus one or more (style-dependent):
|
||||
# - claude-design (UI / web product video)
|
||||
# - sketch (quick mockup variants)
|
||||
# - excalidraw (hand-drawn frames)
|
||||
# - ascii-art (ASCII style frames)
|
||||
# - pixel-art (retro/game aesthetic)
|
||||
# - popular-web-designs (matching known web aesthetic)
|
||||
# - design-md (text-based design docs)
|
||||
```
|
||||
|
||||
### storyboarder
|
||||
|
||||
```yaml
|
||||
toolsets:
|
||||
- kanban
|
||||
- file
|
||||
skills:
|
||||
always_load:
|
||||
- kanban-worker
|
||||
# one of:
|
||||
# - excalidraw (sketch storyboards)
|
||||
# - architecture-diagram (technical/system content)
|
||||
# - concept-diagrams (educational / scientific content)
|
||||
```
|
||||
|
||||
### cinematographer
|
||||
|
||||
```yaml
|
||||
toolsets:
|
||||
- kanban
|
||||
- terminal
|
||||
- file
|
||||
- video # video_analyze — review full clips natively
|
||||
- vision # vision_analyze — review stills / exported frames
|
||||
skills:
|
||||
always_load:
|
||||
- kanban-worker
|
||||
# the visual skill that matches the project, e.g.:
|
||||
# - ascii-video (ASCII projects)
|
||||
# - manim-video (math/explainer)
|
||||
# - p5js (generative)
|
||||
# - comfyui (AI-generated visuals)
|
||||
# - blender-mcp (3D)
|
||||
# - touchdesigner-mcp (real-time/installation)
|
||||
```
|
||||
|
||||
### renderer (specialized variants)
|
||||
|
||||
```yaml
|
||||
toolsets:
|
||||
- kanban
|
||||
- terminal
|
||||
- file
|
||||
skills:
|
||||
always_load:
|
||||
- kanban-worker
|
||||
# ONE skill per renderer variant (or empty for external-API renderers):
|
||||
# - ascii-video (renderer-ascii)
|
||||
# - manim-video (renderer-manim)
|
||||
# - p5js (renderer-p5js)
|
||||
# - comfyui (renderer-comfyui — img/video AI gen)
|
||||
# - touchdesigner-mcp (renderer-touchdesigner)
|
||||
# - blender-mcp (renderer-3d)
|
||||
# - pixel-art (renderer-pixel)
|
||||
# - baoyu-comic (renderer-comic)
|
||||
# - meme-generation (renderer-meme)
|
||||
```
|
||||
|
||||
For external-API renderers (image-to-video-generator using Runway, voice-talent
|
||||
using ElevenLabs, renderer-motion-graphics using Remotion), `always_load` only
|
||||
contains `kanban-worker` — the role's work is API-driven and the API key +
|
||||
terminal commands suffice.
|
||||
|
||||
For multi-skill renderer setups (rare — usually one variant per skill is
|
||||
cleaner) use `--skill <name>` on individual `kanban_create` calls to override
|
||||
which skill loads for that specific task.
|
||||
|
||||
### image-generator / image-to-video-generator / voice-talent
|
||||
|
||||
```yaml
|
||||
toolsets:
|
||||
- kanban
|
||||
- terminal
|
||||
- file
|
||||
skills:
|
||||
always_load:
|
||||
- kanban-worker
|
||||
# for image-generator that drives ComfyUI locally:
|
||||
# - comfyui
|
||||
env_required:
|
||||
# populate based on the chosen API:
|
||||
- FAL_KEY # or REPLICATE_API_TOKEN, OPENAI_API_KEY for image-gen
|
||||
- RUNWAY_API_KEY # or KLING_API_KEY, LUMA_API_KEY for image-to-video
|
||||
- ELEVENLABS_API_KEY # or OPENAI_API_KEY for TTS
|
||||
```
|
||||
|
||||
If the user's setup has ComfyUI installed locally, the `comfyui` skill can
|
||||
replace the external image-gen API entirely (cheaper, more control, supports
|
||||
custom workflows for image-to-video too).
|
||||
|
||||
### music-supervisor
|
||||
|
||||
```yaml
|
||||
toolsets:
|
||||
- kanban
|
||||
- terminal
|
||||
- file
|
||||
skills:
|
||||
always_load:
|
||||
- kanban-worker
|
||||
- songsee # spectrograms / audio analysis
|
||||
# plus (depending on what the project needs):
|
||||
# - songwriting-and-ai-music (commissioning Suno tracks)
|
||||
# - heartmula (commissioning open-source local generation)
|
||||
# - spotify (sourcing existing tracks)
|
||||
```
|
||||
|
||||
### editor / audio-mixer / captioner / masterer
|
||||
|
||||
```yaml
|
||||
toolsets:
|
||||
- kanban
|
||||
- terminal
|
||||
- file
|
||||
- video # video_analyze — editor reviews assembled cuts natively
|
||||
- vision # vision_analyze — spot-check frames
|
||||
skills:
|
||||
always_load:
|
||||
- kanban-worker
|
||||
```
|
||||
|
||||
These are mostly ffmpeg-driven; no special skill needed beyond `kanban-worker`.
|
||||
For captioner add Whisper invocation patterns to the SOUL.md.
|
||||
|
||||
### reviewer / brand-cop
|
||||
|
||||
```yaml
|
||||
toolsets:
|
||||
- kanban
|
||||
- terminal # for media inspection (ffprobe, etc.)
|
||||
- file
|
||||
- video # video_analyze — review full clips natively
|
||||
- vision # vision_analyze — review stills / exported frames
|
||||
skills:
|
||||
always_load:
|
||||
- kanban-worker
|
||||
```
|
||||
|
||||
## API key requirements
|
||||
|
||||
Track these in the project setup. The setup script should verify each required
|
||||
key is present in `~/.hermes/.env` (or macOS Keychain) before firing the kanban.
|
||||
|
||||
| Service | Env var | Used by |
|
||||
|---------|---------|---------|
|
||||
| ElevenLabs | `ELEVENLABS_API_KEY` | voice-talent |
|
||||
| OpenAI | `OPENAI_API_KEY` | image-generator (DALL-E), voice-talent (TTS) |
|
||||
| OpenRouter | `OPENROUTER_API_KEY` | reviewer, cinematographer, editor (`video_analyze` routes through `AUXILIARY_VIDEO_MODEL` → OpenRouter) |
|
||||
| FAL | `FAL_KEY` | image-generator (FAL flux models) |
|
||||
| Replicate | `REPLICATE_API_TOKEN` | image-generator (alternate provider) |
|
||||
| Runway | `RUNWAY_API_KEY` | image-to-video-generator |
|
||||
| Kling | `KLING_API_KEY` | image-to-video-generator (alternate) |
|
||||
| Luma | `LUMA_API_KEY` | image-to-video-generator (alternate) |
|
||||
| Suno | `SUNO_API_KEY` | music-supervisor (paired with `songwriting-and-ai-music`) |
|
||||
| Spotify | `SPOTIFY_CLIENT_ID` + `SPOTIFY_CLIENT_SECRET` | music-supervisor (paired with `spotify` skill) |
|
||||
| Anthropic | `ANTHROPIC_API_KEY` | every Hermes profile (Claude) |
|
||||
|
||||
If a key is missing, prompt the user to add it. Storage methods, in order of
|
||||
preference: macOS Keychain → `~/.hermes/.env` → environment variable.
|
||||
|
||||
## Skill version pinning
|
||||
|
||||
If a specific skill version is desired, pass it via the per-task
|
||||
`--skill <name>=<version>` flag. The default is whatever's installed.
|
||||
|
||||
## Adding a new skill to the matrix
|
||||
|
||||
When a new Hermes-public video skill ships:
|
||||
|
||||
1. Add a row to the relevant table at the top of this file
|
||||
2. If it warrants a specialized renderer variant, add to `role-archetypes.md`
|
||||
3. Update relevant per-style examples in `examples.md`
|
||||
@@ -1,501 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Bootstrap a video production kanban from a structured plan JSON.
|
||||
|
||||
Reads a plan.json describing the team + brief, expands templates from
|
||||
../assets/, and writes a setup.sh that creates Hermes profiles and fires the
|
||||
initial kanban task.
|
||||
|
||||
Profile-config patching, SOUL.md-per-profile, TEAM.md task-graph convention,
|
||||
and the `hermes kanban create --workspace dir:` initial-task pattern are
|
||||
adapted from alt-glitch's NousResearch/kanban-video-pipeline.
|
||||
|
||||
Usage:
|
||||
bootstrap_pipeline.py plan.json [--out setup.sh]
|
||||
|
||||
The plan.json schema is documented inline below — see the `validate_plan`
|
||||
function. A minimal example:
|
||||
|
||||
{
|
||||
"title": "Q3 Product Teaser",
|
||||
"slug": "q3-product-teaser",
|
||||
"tenant": "q3-product-teaser",
|
||||
"duration_s": 30,
|
||||
"aspect": "1:1",
|
||||
"resolution": "1080x1080",
|
||||
"fps": 30,
|
||||
"team": [
|
||||
{
|
||||
"profile": "director",
|
||||
"role": "director",
|
||||
"toolsets": ["kanban", "terminal", "file"],
|
||||
"skills": [],
|
||||
"responsibilities": "...",
|
||||
"inputs": "brief.md, TEAM.md, taste/",
|
||||
"outputs": "kanban tasks for the team"
|
||||
},
|
||||
...
|
||||
],
|
||||
"scenes": [
|
||||
{"n": 1, "time": "0:00-0:08", "content": "...", "tool": "renderer-ascii"},
|
||||
...
|
||||
],
|
||||
"audio": {"approach": "voiceover + music bed", "vo": "ElevenLabs Lily",
|
||||
"music": "license-free", "sfx": "n/a"},
|
||||
"deliverables": [
|
||||
{"format": "mp4", "resolution": "1080x1080", "notes": "primary"}
|
||||
],
|
||||
"api_keys_required": ["ELEVENLABS_API_KEY", "OPENROUTER_API_KEY"],
|
||||
"brief_extra": {
|
||||
"concept_one_liner": "...",
|
||||
"emotional_north_star": "...",
|
||||
"visual_refs": "...",
|
||||
"tone": "...",
|
||||
"brand_constraints": "..."
|
||||
}
|
||||
}
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
ASSETS_DIR = Path(__file__).resolve().parent.parent / "assets"
|
||||
|
||||
|
||||
def load_template(name: str) -> str:
|
||||
return (ASSETS_DIR / name).read_text()
|
||||
|
||||
|
||||
PROFILE_NAME_RE = re.compile(r"^[a-z0-9][a-z0-9_-]{0,63}$")
|
||||
SLUG_RE = re.compile(r"^[a-z0-9][a-z0-9-]+$")
|
||||
|
||||
|
||||
def validate_plan(plan: dict) -> list[str]:
|
||||
"""Return a list of validation error strings; empty list = valid."""
|
||||
errors = []
|
||||
required_top = ["title", "slug", "tenant", "duration_s", "aspect",
|
||||
"resolution", "fps", "team", "scenes", "audio",
|
||||
"deliverables"]
|
||||
for k in required_top:
|
||||
if k not in plan:
|
||||
errors.append(f"missing required key: {k}")
|
||||
|
||||
if "team" in plan:
|
||||
if not isinstance(plan["team"], list) or not plan["team"]:
|
||||
errors.append("team must be a non-empty list")
|
||||
else:
|
||||
roles = [t.get("role") for t in plan["team"]]
|
||||
if "director" not in roles:
|
||||
errors.append("team must include a director role")
|
||||
seen_profiles = set()
|
||||
for i, t in enumerate(plan["team"]):
|
||||
for k in ["profile", "role", "toolsets", "skills",
|
||||
"responsibilities"]:
|
||||
if k not in t:
|
||||
errors.append(f"team[{i}] missing {k}")
|
||||
# Profile name must match Hermes's regex (lowercase
|
||||
# alphanumeric + hyphens + underscores, up to 64 chars).
|
||||
if "profile" in t:
|
||||
if not PROFILE_NAME_RE.match(t["profile"]):
|
||||
errors.append(
|
||||
f"team[{i}].profile {t['profile']!r} must match "
|
||||
f"[a-z0-9][a-z0-9_-]{{0,63}} per Hermes profile rules"
|
||||
)
|
||||
if t["profile"] in seen_profiles:
|
||||
errors.append(
|
||||
f"team[{i}].profile {t['profile']!r} is duplicated"
|
||||
)
|
||||
seen_profiles.add(t["profile"])
|
||||
# Toolsets / skills must be lists, not strings.
|
||||
if "toolsets" in t and not isinstance(t["toolsets"], list):
|
||||
errors.append(
|
||||
f"team[{i}].toolsets must be a list of strings"
|
||||
)
|
||||
if "skills" in t and not isinstance(t["skills"], list):
|
||||
errors.append(
|
||||
f"team[{i}].skills must be a list of strings"
|
||||
)
|
||||
|
||||
if "slug" in plan:
|
||||
if not SLUG_RE.match(plan["slug"]):
|
||||
errors.append("slug must be lowercase, hyphenated, "
|
||||
"starting with [a-z0-9]")
|
||||
|
||||
return errors
|
||||
|
||||
|
||||
def render_brief(plan: dict) -> str:
|
||||
"""Render brief.md from the plan."""
|
||||
tmpl = load_template("brief.md.tmpl")
|
||||
extra = plan.get("brief_extra", {})
|
||||
|
||||
# Scene table rows
|
||||
scene_rows = []
|
||||
for s in plan["scenes"]:
|
||||
scene_rows.append(
|
||||
f"| {s.get('n', '?')} | {s.get('time', '?')} | "
|
||||
f"{s.get('content', '')} | {s.get('tool', '')} | "
|
||||
f"{s.get('audio', '')} | {s.get('notes', '')} |"
|
||||
)
|
||||
scene_table = "\n".join(scene_rows) if scene_rows else "_(none yet)_"
|
||||
|
||||
# Deliverable rows
|
||||
deliv_rows = []
|
||||
for d in plan["deliverables"]:
|
||||
deliv_rows.append(
|
||||
f"| {d.get('format', '?')} | {d.get('resolution', '?')} | "
|
||||
f"{d.get('notes', '')} |"
|
||||
)
|
||||
deliv_table = "\n".join(deliv_rows) if deliv_rows else "_(none)_"
|
||||
|
||||
# Replacements (single-pass)
|
||||
replacements = {
|
||||
"TITLE": plan["title"],
|
||||
"SLUG": plan["slug"],
|
||||
"TENANT": plan["tenant"],
|
||||
"WORKSPACE": f"~/projects/video-pipeline/{plan['slug']}",
|
||||
"ONE_LINE_PITCH": extra.get("concept_one_liner", "_(TBD)_"),
|
||||
"EMOTIONAL_NORTH_STAR": extra.get("emotional_north_star", "_(TBD)_"),
|
||||
"DURATION_S": str(plan["duration_s"]),
|
||||
"ASPECT": plan["aspect"],
|
||||
"RESOLUTION": plan["resolution"],
|
||||
"FPS": str(plan["fps"]),
|
||||
"PLATFORMS": extra.get("platforms", "_(TBD)_"),
|
||||
"DEADLINE": extra.get("deadline", "_(none)_"),
|
||||
"QUALITY_BAR": extra.get("quality_bar", "polished"),
|
||||
"VISUAL_REFS": extra.get("visual_refs", "_(none)_"),
|
||||
"TONE": extra.get("tone", "_(TBD)_"),
|
||||
"BRAND_CONSTRAINTS": extra.get("brand_constraints", "_(none)_"),
|
||||
"AESTHETIC_RULES": extra.get("aesthetic_rules", "_(TBD)_"),
|
||||
"AUDIO_APPROACH": plan["audio"].get("approach", "_(TBD)_"),
|
||||
"VO_DETAILS": plan["audio"].get("vo", "_(n/a)_"),
|
||||
"MUSIC_DETAILS": plan["audio"].get("music", "_(n/a)_"),
|
||||
"SFX_DETAILS": plan["audio"].get("sfx", "_(n/a)_"),
|
||||
"PRIMARY_FORMAT": plan["deliverables"][0]["format"],
|
||||
"PRIMARY_RES": plan["deliverables"][0]["resolution"],
|
||||
"ALT_FORMAT_1": (plan["deliverables"][1]["format"]
|
||||
if len(plan["deliverables"]) > 1 else "_(none)_"),
|
||||
"ALT_RES_1": (plan["deliverables"][1]["resolution"]
|
||||
if len(plan["deliverables"]) > 1 else ""),
|
||||
"ALT_NOTES_1": (plan["deliverables"][1].get("notes", "")
|
||||
if len(plan["deliverables"]) > 1 else ""),
|
||||
"API_KEYS_REQUIRED": ", ".join(plan.get("api_keys_required", [])) or "none",
|
||||
"EXT_DEPS": extra.get("ext_deps", "ffmpeg, Python 3.11+"),
|
||||
"SOURCE_ASSETS": extra.get("source_assets", "_(none)_"),
|
||||
}
|
||||
out = tmpl
|
||||
for k, v in replacements.items():
|
||||
out = out.replace("{{" + k + "}}", str(v))
|
||||
|
||||
# Scene + deliv tables: replace the placeholder row in the template
|
||||
out = re.sub(
|
||||
r"\|\s*1\s*\|\s*0:00–0:0X.+?\n\|\s*2\s*\|.+?\n",
|
||||
scene_table + "\n",
|
||||
out, flags=re.DOTALL,
|
||||
)
|
||||
return out
|
||||
|
||||
|
||||
def render_team_md(plan: dict) -> str:
|
||||
"""Render TEAM.md from the team list + scene → tool mapping."""
|
||||
lines = [f"# Team & Task Graph — {plan['title']}", "", "## Team", ""]
|
||||
for t in plan["team"]:
|
||||
skills = (
|
||||
f"loads `{', '.join(t['skills'])}`"
|
||||
if t["skills"] else "no skills required"
|
||||
)
|
||||
lines.append(
|
||||
f"- `{t['profile']}` — {t['responsibilities']} ({skills})"
|
||||
)
|
||||
lines.extend(["", "## Task Graph", "", "```"])
|
||||
|
||||
# Build a simple task graph based on conventions
|
||||
profiles_by_role = {t["role"]: t["profile"] for t in plan["team"]}
|
||||
director = profiles_by_role.get("director", "director")
|
||||
lines.append(f"T0 {director} — decompose")
|
||||
|
||||
next_id = 1
|
||||
parents_for_renderer: list[str] = ["T0"]
|
||||
|
||||
if "cinematographer" in profiles_by_role:
|
||||
cid = f"T{next_id}"
|
||||
lines.append(
|
||||
f"{cid:5} {profiles_by_role['cinematographer']} — visual spec for all scenes (parent: T0)"
|
||||
)
|
||||
parents_for_renderer = [cid]
|
||||
next_id += 1
|
||||
|
||||
if "music-supervisor" in profiles_by_role:
|
||||
cid = f"T{next_id}"
|
||||
lines.append(
|
||||
f"{cid:5} {profiles_by_role['music-supervisor']} — track analysis + beats.json (parent: T0)"
|
||||
)
|
||||
next_id += 1
|
||||
ms_id = cid
|
||||
else:
|
||||
ms_id = None
|
||||
|
||||
# Scenes
|
||||
scene_ids = []
|
||||
for s in plan["scenes"]:
|
||||
cid = f"T{next_id}"
|
||||
renderer_profile = s.get("tool") or "renderer"
|
||||
# Lookup the actual profile name
|
||||
for t in plan["team"]:
|
||||
if t["role"] == renderer_profile or t["profile"] == renderer_profile:
|
||||
renderer_profile = t["profile"]
|
||||
break
|
||||
parents = parents_for_renderer + ([ms_id] if ms_id else [])
|
||||
parent_str = ", ".join(parents)
|
||||
lines.append(
|
||||
f"{cid:5} {renderer_profile} — scene {s.get('n', '?')}: "
|
||||
f"{s.get('content', '')[:50]} (parents: {parent_str})"
|
||||
)
|
||||
scene_ids.append(cid)
|
||||
next_id += 1
|
||||
|
||||
# VO + audio mix
|
||||
if "voice-talent" in profiles_by_role:
|
||||
vo_id = f"T{next_id}"
|
||||
lines.append(f"{vo_id:5} {profiles_by_role['voice-talent']} — narration (parent: T0)")
|
||||
next_id += 1
|
||||
else:
|
||||
vo_id = None
|
||||
|
||||
if "audio-mixer" in profiles_by_role:
|
||||
am_id = f"T{next_id}"
|
||||
am_parents = [p for p in [ms_id, vo_id] if p]
|
||||
lines.append(
|
||||
f"{am_id:5} {profiles_by_role['audio-mixer']} — mix audio (parents: {', '.join(am_parents)})"
|
||||
)
|
||||
next_id += 1
|
||||
else:
|
||||
am_id = None
|
||||
|
||||
# Editor
|
||||
if "editor" in profiles_by_role:
|
||||
ed_id = f"T{next_id}"
|
||||
ed_parents = scene_ids + [p for p in [am_id, vo_id, ms_id] if p and p not in scene_ids]
|
||||
lines.append(
|
||||
f"{ed_id:5} {profiles_by_role['editor']} — assemble + mux (parents: {', '.join(ed_parents)})"
|
||||
)
|
||||
next_id += 1
|
||||
else:
|
||||
ed_id = None
|
||||
|
||||
# Captioner
|
||||
if "captioner" in profiles_by_role and ed_id:
|
||||
cap_id = f"T{next_id}"
|
||||
lines.append(
|
||||
f"{cap_id:5} {profiles_by_role['captioner']} — SRT + burn (parent: {ed_id})"
|
||||
)
|
||||
next_id += 1
|
||||
last = cap_id
|
||||
else:
|
||||
last = ed_id
|
||||
|
||||
# Reviewer
|
||||
if "reviewer" in profiles_by_role and last:
|
||||
rv_id = f"T{next_id}"
|
||||
lines.append(
|
||||
f"{rv_id:5} {profiles_by_role['reviewer']} — final QA (parent: {last})"
|
||||
)
|
||||
|
||||
lines.append("```")
|
||||
lines.extend([
|
||||
"",
|
||||
"## Per-task workspace requirement",
|
||||
"",
|
||||
f"All `kanban_create` calls MUST pass:",
|
||||
f"```",
|
||||
f'workspace_kind="dir"',
|
||||
f'workspace_path="$HOME/projects/video-pipeline/{plan["slug"]}"',
|
||||
f'tenant="{plan["tenant"]}"',
|
||||
f"```",
|
||||
])
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def render_setup_sh(plan: dict, brief_md: str, team_md: str) -> str:
|
||||
"""Render setup.sh from the plan."""
|
||||
tmpl = load_template("setup.sh.tmpl")
|
||||
|
||||
# API key checks
|
||||
key_checks = []
|
||||
for key in plan.get("api_keys_required", []):
|
||||
key_checks.append(f'check_key {key} hermes {key} || exit 1')
|
||||
key_checks_str = "\n".join(key_checks) if key_checks else "# (no API keys required)"
|
||||
|
||||
# Scene dirs
|
||||
scene_dir_lines = []
|
||||
for s in plan["scenes"]:
|
||||
n = s.get("n", "?")
|
||||
scene_dir_lines.append(f'mkdir -p "$WORKSPACE/scenes/scene-{n:02d}"/checkpoints')
|
||||
scene_dirs = "\n".join(scene_dir_lines) if scene_dir_lines else ""
|
||||
|
||||
# Profile create
|
||||
profile_creates = []
|
||||
for t in plan["team"]:
|
||||
profile_creates.append(
|
||||
f'hermes profile create {t["profile"]} --clone 2>/dev/null || true'
|
||||
)
|
||||
|
||||
# Profile config — emit JSON arrays so the bash function can pass them
|
||||
# safely through to the Python YAML patcher.
|
||||
profile_configs = []
|
||||
for t in plan["team"]:
|
||||
ts_json = json.dumps(t["toolsets"])
|
||||
sk_json = json.dumps(t["skills"])
|
||||
# Use single-quoted bash strings; JSON only contains "/[/], no single
|
||||
# quotes, so this is safe.
|
||||
profile_configs.append(
|
||||
f"configure_profile {t['profile']!r} {ts_json!r} {sk_json!r}"
|
||||
)
|
||||
|
||||
# SOUL writes — uses heredocs per profile
|
||||
soul_writes = []
|
||||
for t in plan["team"]:
|
||||
soul_writes.append(
|
||||
f'cat > "$HOME/.hermes/profiles/{t["profile"]}/SOUL.md" <<\'SOUL_EOF\'\n'
|
||||
f"{render_soul_md(t, plan)}\n"
|
||||
f"SOUL_EOF\n"
|
||||
f'echo " ✓ SOUL.md for {t["profile"]}"'
|
||||
)
|
||||
|
||||
# Taste writes (placeholder; real content optional)
|
||||
taste_writes = (
|
||||
'cat > "$WORKSPACE/taste/brand-guide.md" <<\'TASTE_EOF\'\n'
|
||||
'# Brand Guide\n\n'
|
||||
'_(Populate with project-specific colors, typography, motion rules)_\n'
|
||||
'TASTE_EOF\n'
|
||||
'cat > "$WORKSPACE/taste/emotional-dna.md" <<\'DNA_EOF\'\n'
|
||||
'# Emotional DNA\n\n'
|
||||
'_(What this piece should FEEL like — populate from the brief.)_\n'
|
||||
'DNA_EOF'
|
||||
)
|
||||
|
||||
# Asset copies — leave empty by default; user fills in
|
||||
asset_copies = "# Add cp/rsync commands here for any provided assets"
|
||||
|
||||
out = tmpl
|
||||
out = out.replace("{{TITLE}}", plan["title"])
|
||||
out = out.replace("{{SLUG}}", plan["slug"])
|
||||
out = out.replace("{{TENANT}}", plan["tenant"])
|
||||
out = out.replace("{{WORKSPACE}}", f"~/projects/video-pipeline/{plan['slug']}")
|
||||
out = out.replace("{{KEY_CHECKS}}", key_checks_str)
|
||||
out = out.replace("{{SCENE_DIRS}}", scene_dirs)
|
||||
out = out.replace("{{PROFILE_CREATE_COMMANDS}}", "\n".join(profile_creates))
|
||||
out = out.replace("{{PROFILE_CONFIG_COMMANDS}}", "\n".join(profile_configs))
|
||||
out = out.replace("{{SOUL_WRITES}}", "\n".join(soul_writes))
|
||||
out = out.replace("{{BRIEF_CONTENTS}}", brief_md)
|
||||
out = out.replace("{{TEAM_CONTENTS}}", team_md)
|
||||
out = out.replace("{{TASTE_WRITES}}", taste_writes)
|
||||
out = out.replace("{{ASSET_COPIES}}", asset_copies)
|
||||
|
||||
return out
|
||||
|
||||
|
||||
def render_soul_md(team_member: dict, plan: dict) -> str:
|
||||
"""Render a profile's SOUL.md from a team member dict + plan context."""
|
||||
tmpl = load_template("soul.md.tmpl")
|
||||
role = team_member["role"]
|
||||
|
||||
common_rules = (
|
||||
"- **Read the brief and team graph** before doing anything else.\n"
|
||||
"- **Pass `workspace_kind=\"dir\"` and `workspace_path` on every "
|
||||
"`kanban_create` call.** This keeps the team in one shared workspace.\n"
|
||||
f"- **Use tenant `{plan['tenant']}`** on every kanban call.\n"
|
||||
"- **Write outputs to predictable paths.** Other profiles depend on "
|
||||
"your filename conventions.\n"
|
||||
"- **Emit heartbeats** during long-running work. Renderers should "
|
||||
"report frame counts; editors should report assembly progress.\n"
|
||||
)
|
||||
|
||||
if role == "director":
|
||||
common_rules += (
|
||||
"- **Do not execute the work yourself.** For every concrete task, "
|
||||
"create a kanban task and assign it to the appropriate profile.\n"
|
||||
"- **Decompose, route, comment, approve — that's the whole job.**\n"
|
||||
"- **Read TEAM.md** for the canonical task graph. Do not invent "
|
||||
"new roles unless the brief truly demands it.\n"
|
||||
"- **Load the `kanban-orchestrator` skill** for the deeper "
|
||||
"decomposition playbook beyond the auto-injected baseline.\n"
|
||||
)
|
||||
|
||||
common_commands = (
|
||||
"```bash\n"
|
||||
"# Inspect a clip\n"
|
||||
"ffprobe -v quiet -show_entries format=duration -show_entries "
|
||||
"stream=codec_name,width,height,r_frame_rate <file.mp4>\n"
|
||||
"\n"
|
||||
"# Extract a frame for QA\n"
|
||||
"ffmpeg -y -i <input.mp4> -vf \"select='eq(n,30)'\" -vsync vfr <out.png>\n"
|
||||
"```"
|
||||
)
|
||||
|
||||
out = tmpl
|
||||
out = out.replace("{{ROLE_NAME}}", role)
|
||||
out = out.replace("{{ROLE_RESPONSIBILITIES}}", team_member["responsibilities"])
|
||||
out = out.replace("{{INPUTS_READ}}", team_member.get("inputs", "_(see brief)_"))
|
||||
out = out.replace("{{OUTPUTS_PRODUCED}}", team_member.get("outputs", "_(see brief)_"))
|
||||
out = out.replace("{{TOOLSETS}}", ", ".join(team_member["toolsets"]))
|
||||
out = out.replace(
|
||||
"{{SKILLS}}",
|
||||
", ".join(team_member["skills"]) if team_member["skills"] else "(none)"
|
||||
)
|
||||
out = out.replace(
|
||||
"{{EXTERNAL_TOOLS}}",
|
||||
team_member.get("external_tools", "ffmpeg, ffprobe (via terminal)")
|
||||
)
|
||||
out = out.replace(
|
||||
"{{ROLE_RULES}}",
|
||||
team_member.get("role_rules", "_(see TEAM.md and brief.md)_")
|
||||
)
|
||||
out = out.replace("{{COMMON_RULES}}", common_rules)
|
||||
out = out.replace("{{COMMON_COMMANDS}}", common_commands)
|
||||
return out
|
||||
|
||||
|
||||
def main():
|
||||
ap = argparse.ArgumentParser(description=__doc__,
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter)
|
||||
ap.add_argument("plan_json", help="Path to plan.json")
|
||||
ap.add_argument("--out", default="setup.sh",
|
||||
help="Output path for setup.sh (default: ./setup.sh)")
|
||||
ap.add_argument("--brief-out", default=None,
|
||||
help="Write brief.md alongside (default: skipped)")
|
||||
ap.add_argument("--team-out", default=None,
|
||||
help="Write TEAM.md alongside (default: skipped)")
|
||||
args = ap.parse_args()
|
||||
|
||||
plan = json.loads(Path(args.plan_json).read_text())
|
||||
errors = validate_plan(plan)
|
||||
if errors:
|
||||
print("Plan validation failed:", file=sys.stderr)
|
||||
for e in errors:
|
||||
print(f" - {e}", file=sys.stderr)
|
||||
sys.exit(2)
|
||||
|
||||
brief = render_brief(plan)
|
||||
team = render_team_md(plan)
|
||||
setup = render_setup_sh(plan, brief, team)
|
||||
|
||||
Path(args.out).write_text(setup)
|
||||
os.chmod(args.out, 0o755)
|
||||
print(f"Wrote {args.out}")
|
||||
|
||||
if args.brief_out:
|
||||
Path(args.brief_out).write_text(brief)
|
||||
print(f"Wrote {args.brief_out}")
|
||||
if args.team_out:
|
||||
Path(args.team_out).write_text(team)
|
||||
print(f"Wrote {args.team_out}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,195 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Monitor a running video-production kanban. Polls `hermes kanban list` and
|
||||
`events` for a tenant and surfaces issues (stuck tasks, missing heartbeats,
|
||||
repeated retries, dependency deadlocks).
|
||||
|
||||
Usage:
|
||||
monitor.py --tenant <project-slug> [--interval 30]
|
||||
|
||||
Outputs a periodic snapshot to stdout. Sends alerts via stderr when issues
|
||||
are detected. Designed to run alongside the kanban — kill with Ctrl-C when
|
||||
you're satisfied (or scripted to stop on completion).
|
||||
|
||||
This is best-effort observability. It does not auto-restart tasks; intervention
|
||||
decisions should remain human/AI-overseen.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import shutil
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
from collections import defaultdict
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
|
||||
def hermes_available() -> bool:
|
||||
return shutil.which("hermes") is not None
|
||||
|
||||
|
||||
def kanban_list(tenant: str) -> list[dict]:
|
||||
"""Returns parsed task rows. Falls back to plain stdout parsing if JSON
|
||||
output isn't supported by the installed hermes CLI."""
|
||||
try:
|
||||
out = subprocess.run(
|
||||
["hermes", "kanban", "list", "--tenant", tenant, "--json"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
if out.returncode == 0 and out.stdout.strip().startswith("["):
|
||||
return json.loads(out.stdout)
|
||||
except (FileNotFoundError, json.JSONDecodeError):
|
||||
pass
|
||||
# Fallback: textual parse of `hermes kanban list`
|
||||
out = subprocess.run(
|
||||
["hermes", "kanban", "list", "--tenant", tenant],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
rows = []
|
||||
for line in out.stdout.splitlines():
|
||||
line = line.strip()
|
||||
if not line or line.startswith("#") or "STATUS" in line.upper():
|
||||
continue
|
||||
parts = line.split()
|
||||
if len(parts) >= 4 and parts[0].startswith("t_"):
|
||||
rows.append({
|
||||
"id": parts[0],
|
||||
"status": parts[1] if len(parts) > 1 else "?",
|
||||
"assignee": parts[2] if len(parts) > 2 else "?",
|
||||
"title": " ".join(parts[3:]) if len(parts) > 3 else "",
|
||||
"started_at": None,
|
||||
"heartbeat_at": None,
|
||||
"max_runtime_s": None,
|
||||
})
|
||||
return rows
|
||||
|
||||
|
||||
def kanban_show(task_id: str) -> dict | None:
|
||||
out = subprocess.run(
|
||||
["hermes", "kanban", "show", task_id, "--json"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
if out.returncode != 0:
|
||||
return None
|
||||
try:
|
||||
return json.loads(out.stdout)
|
||||
except json.JSONDecodeError:
|
||||
return None
|
||||
|
||||
|
||||
def detect_issues(tasks: list[dict]) -> list[str]:
|
||||
"""Return a list of issue strings, one per concern."""
|
||||
now = datetime.now()
|
||||
issues: list[str] = []
|
||||
by_status = defaultdict(list)
|
||||
for t in tasks:
|
||||
by_status[t.get("status", "?")].append(t)
|
||||
|
||||
# Stuck tasks: RUNNING with no heartbeat in 2 min
|
||||
for t in by_status.get("running", []) + by_status.get("RUNNING", []):
|
||||
hb = t.get("heartbeat_at")
|
||||
if not hb:
|
||||
continue
|
||||
try:
|
||||
hb_dt = datetime.fromisoformat(str(hb).rstrip("Z"))
|
||||
except ValueError:
|
||||
continue
|
||||
if now - hb_dt > timedelta(minutes=2):
|
||||
issues.append(
|
||||
f"STUCK: {t['id']} ({t.get('assignee', '?')}) — "
|
||||
f"no heartbeat in {(now - hb_dt).total_seconds():.0f}s"
|
||||
)
|
||||
|
||||
# Tasks exceeding max_runtime
|
||||
for t in by_status.get("running", []) + by_status.get("RUNNING", []):
|
||||
started = t.get("started_at")
|
||||
max_rt = t.get("max_runtime_s")
|
||||
if not started or not max_rt:
|
||||
continue
|
||||
try:
|
||||
started_dt = datetime.fromisoformat(str(started).rstrip("Z"))
|
||||
except ValueError:
|
||||
continue
|
||||
elapsed = (now - started_dt).total_seconds()
|
||||
if elapsed > max_rt:
|
||||
issues.append(
|
||||
f"OVERTIME: {t['id']} ({t.get('assignee', '?')}) — "
|
||||
f"running {elapsed:.0f}s, cap was {max_rt}s"
|
||||
)
|
||||
|
||||
# Repeated retries
|
||||
for t in tasks:
|
||||
retries = t.get("retries", 0)
|
||||
if retries and retries >= 2:
|
||||
issues.append(
|
||||
f"FLAPPING: {t['id']} ({t.get('assignee', '?')}) — "
|
||||
f"retried {retries}× — fix root cause before next run"
|
||||
)
|
||||
|
||||
return issues
|
||||
|
||||
|
||||
def snapshot(tenant: str) -> tuple[list[dict], list[str]]:
|
||||
tasks = kanban_list(tenant)
|
||||
issues = detect_issues(tasks)
|
||||
return tasks, issues
|
||||
|
||||
|
||||
def print_snapshot(tasks: list[dict], issues: list[str]):
|
||||
counts = defaultdict(int)
|
||||
for t in tasks:
|
||||
counts[str(t.get("status", "?")).lower()] += 1
|
||||
|
||||
print(f"\n[{datetime.now().strftime('%H:%M:%S')}] "
|
||||
f"Total: {len(tasks)} | "
|
||||
+ " | ".join(f"{k}: {v}" for k, v in sorted(counts.items())))
|
||||
|
||||
for t in tasks:
|
||||
bar = "✓" if str(t.get("status", "")).lower() == "done" else \
|
||||
"▶" if str(t.get("status", "")).lower() == "running" else \
|
||||
"·" if str(t.get("status", "")).lower() == "ready" else \
|
||||
"✗" if str(t.get("status", "")).lower() == "failed" else "?"
|
||||
print(f" {bar} {t.get('id', '?'):14} {t.get('assignee', '?'):20} "
|
||||
f"{t.get('title', '')[:60]}")
|
||||
|
||||
if issues:
|
||||
print("\n ⚠ ISSUES:", file=sys.stderr)
|
||||
for i in issues:
|
||||
print(f" {i}", file=sys.stderr)
|
||||
|
||||
|
||||
def main():
|
||||
ap = argparse.ArgumentParser(description=__doc__,
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter)
|
||||
ap.add_argument("--tenant", required=True,
|
||||
help="Project tenant slug to monitor")
|
||||
ap.add_argument("--interval", type=int, default=30,
|
||||
help="Poll interval in seconds (default: 30)")
|
||||
ap.add_argument("--once", action="store_true",
|
||||
help="Print one snapshot and exit (no polling loop)")
|
||||
args = ap.parse_args()
|
||||
|
||||
if not hermes_available():
|
||||
print("ERROR: 'hermes' CLI not found in PATH", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
if args.once:
|
||||
tasks, issues = snapshot(args.tenant)
|
||||
print_snapshot(tasks, issues)
|
||||
sys.exit(0 if not issues else 2)
|
||||
|
||||
print(f"Monitoring tenant '{args.tenant}' every {args.interval}s. "
|
||||
"Ctrl-C to exit.")
|
||||
try:
|
||||
while True:
|
||||
tasks, issues = snapshot(args.tenant)
|
||||
print_snapshot(tasks, issues)
|
||||
time.sleep(args.interval)
|
||||
except KeyboardInterrupt:
|
||||
print("\nStopped.")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -2960,7 +2960,7 @@ class Migrator:
|
||||
def parse_args() -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(description="Migrate OpenClaw user state into Hermes Agent.")
|
||||
parser.add_argument("--source", default=str(Path.home() / ".openclaw"), help="OpenClaw home directory")
|
||||
parser.add_argument("--target", default=os.environ.get("HERMES_HOME") or str(Path.home() / ".hermes"), help="Hermes home directory")
|
||||
parser.add_argument("--target", default=str(Path.home() / ".hermes"), help="Hermes home directory")
|
||||
parser.add_argument(
|
||||
"--workspace-target",
|
||||
help="Optional workspace root where the workspace instructions file should be copied",
|
||||
|
||||
@@ -1,217 +0,0 @@
|
||||
---
|
||||
name: here.now
|
||||
description: Publish static sites to {slug}.here.now and store private files in cloud Drives for agent-to-agent handoff.
|
||||
version: 1.15.3
|
||||
author: here.now
|
||||
license: MIT
|
||||
prerequisites:
|
||||
commands: [curl, file, jq]
|
||||
platforms: [macos, linux]
|
||||
metadata:
|
||||
hermes:
|
||||
tags: [here.now, herenow, publish, deploy, hosting, static-site, web, share, URL, drive, storage]
|
||||
homepage: https://here.now
|
||||
requires_toolsets: [terminal]
|
||||
---
|
||||
|
||||
# here.now
|
||||
|
||||
here.now lets agents publish websites and store private files in cloud Drives.
|
||||
|
||||
Use here.now for two jobs:
|
||||
|
||||
- **Sites**: publish websites and files at `{slug}.here.now`.
|
||||
- **Drives**: store private agent files in cloud folders.
|
||||
|
||||
## Current docs
|
||||
|
||||
**Before answering questions about here.now capabilities, features, or workflows, read the current docs:**
|
||||
|
||||
→ **https://here.now/docs**
|
||||
|
||||
Read the docs:
|
||||
|
||||
- at the first here.now-related interaction in a conversation
|
||||
- any time the user asks how to do something
|
||||
- any time the user asks what is possible, supported, or recommended
|
||||
- before telling the user a feature is unsupported
|
||||
|
||||
Topics that require current docs (do not rely on local skill text alone):
|
||||
|
||||
- Drives and Drive sharing
|
||||
- custom domains
|
||||
- payments and payment gating
|
||||
- forking
|
||||
- proxy routes and service variables
|
||||
- handles and links
|
||||
- limits and quotas
|
||||
- SPA routing
|
||||
- error handling and remediation
|
||||
- feature availability
|
||||
|
||||
**If docs and live API behavior disagree, trust the live API behavior.**
|
||||
|
||||
If the docs fetch fails or times out, continue with the local skill and live API/script output. Prefer live API behavior for active operations.
|
||||
|
||||
## Requirements
|
||||
|
||||
- Required binaries: `curl`, `file`, `jq`
|
||||
- Optional environment variable: `$HERENOW_API_KEY`
|
||||
- Optional Drive token variable: `$HERENOW_DRIVE_TOKEN`
|
||||
- Optional credentials file: `~/.herenow/credentials`
|
||||
- Skill helper paths:
|
||||
- `${HERMES_SKILL_DIR}/scripts/publish.sh` for publishing sites
|
||||
- `${HERMES_SKILL_DIR}/scripts/drive.sh` for private Drive storage
|
||||
|
||||
## Create a site
|
||||
|
||||
```bash
|
||||
PUBLISH="${HERMES_SKILL_DIR}/scripts/publish.sh"
|
||||
bash "$PUBLISH" {file-or-dir} --client hermes
|
||||
```
|
||||
|
||||
Outputs the live URL (e.g. `https://bright-canvas-a7k2.here.now/`).
|
||||
|
||||
Under the hood this is a three-step flow: create/update -> upload files -> finalize. A site is not live until finalize succeeds.
|
||||
|
||||
Without an API key this creates an **anonymous site** that expires in 24 hours.
|
||||
With a saved API key, the site is permanent.
|
||||
|
||||
**File structure:** For HTML sites, place `index.html` at the root of the directory you publish, not inside a subdirectory. The directory's contents become the site root. For example, publish `my-site/` where `my-site/index.html` exists — don't publish a parent folder that contains `my-site/`.
|
||||
|
||||
You can also publish raw files without any HTML. Single files get a rich auto-viewer (images, PDF, video, audio). Multiple files get an auto-generated directory listing with folder navigation and an image gallery.
|
||||
|
||||
## Update an existing site
|
||||
|
||||
```bash
|
||||
PUBLISH="${HERMES_SKILL_DIR}/scripts/publish.sh"
|
||||
bash "$PUBLISH" {file-or-dir} --slug {slug} --client hermes
|
||||
```
|
||||
|
||||
The script auto-loads the `claimToken` from `.herenow/state.json` when updating anonymous sites. Pass `--claim-token {token}` to override.
|
||||
|
||||
Authenticated updates require a saved API key.
|
||||
|
||||
## Use a Drive
|
||||
|
||||
Use a Drive when the user wants private cloud storage for agent files: documents, context, memory, plans, assets, media, research, code, and anything else that should persist without being published as a website.
|
||||
|
||||
Every signed-in account has a default Drive named `My Drive`.
|
||||
|
||||
```bash
|
||||
DRIVE="${HERMES_SKILL_DIR}/scripts/drive.sh"
|
||||
bash "$DRIVE" default
|
||||
bash "$DRIVE" ls "My Drive"
|
||||
bash "$DRIVE" put "My Drive" notes/today.md --from ./notes/today.md
|
||||
bash "$DRIVE" cat "My Drive" notes/today.md
|
||||
bash "$DRIVE" share "My Drive" --perms write --prefix notes/ --ttl 7d
|
||||
```
|
||||
|
||||
Use scoped Drive tokens for agent-to-agent handoff. If you receive a `herenow_drive` share block, use its `token` as `Authorization: Bearer <token>` against `api_base`, respect `pathPrefix` when present, and preserve ETags on writes. A `pathPrefix` of `null` means full-Drive access. If the skill is available, prefer `drive.sh`; otherwise call the listed API operations directly.
|
||||
|
||||
## API key storage
|
||||
|
||||
The publish script reads the API key from these sources (first match wins):
|
||||
|
||||
1. `--api-key {key}` flag (CI/scripting only — avoid in interactive use)
|
||||
2. `$HERENOW_API_KEY` environment variable
|
||||
3. `~/.herenow/credentials` file (recommended for agents)
|
||||
|
||||
To store a key, write it to the credentials file:
|
||||
|
||||
```bash
|
||||
mkdir -p ~/.herenow && echo "{API_KEY}" > ~/.herenow/credentials && chmod 600 ~/.herenow/credentials
|
||||
```
|
||||
|
||||
**IMPORTANT**: After receiving an API key, save it immediately — run the command above yourself. Do not ask the user to run it manually. Avoid passing the key via CLI flags (e.g. `--api-key`) in interactive sessions; the credentials file is the preferred storage method.
|
||||
|
||||
Never commit credentials or local state files (`~/.herenow/credentials`, `.herenow/state.json`) to source control.
|
||||
|
||||
## Getting an API key
|
||||
|
||||
To upgrade from anonymous (24h) to permanent sites:
|
||||
|
||||
1. Ask the user for their email address.
|
||||
2. Request a one-time sign-in code:
|
||||
|
||||
```bash
|
||||
curl -sS https://here.now/api/auth/agent/request-code \
|
||||
-H "content-type: application/json" \
|
||||
-d '{"email": "user@example.com"}'
|
||||
```
|
||||
|
||||
3. Tell the user: "Check your inbox for a sign-in code from here.now and paste it here."
|
||||
4. Verify the code and get the API key:
|
||||
|
||||
```bash
|
||||
curl -sS https://here.now/api/auth/agent/verify-code \
|
||||
-H "content-type: application/json" \
|
||||
-d '{"email":"user@example.com","code":"ABCD-2345"}'
|
||||
```
|
||||
|
||||
5. Save the returned `apiKey` yourself (do not ask the user to do this):
|
||||
|
||||
```bash
|
||||
mkdir -p ~/.herenow && echo "{API_KEY}" > ~/.herenow/credentials && chmod 600 ~/.herenow/credentials
|
||||
```
|
||||
|
||||
## State file
|
||||
|
||||
After every site create/update, the script writes to `.herenow/state.json` in the working directory:
|
||||
|
||||
```json
|
||||
{
|
||||
"publishes": {
|
||||
"bright-canvas-a7k2": {
|
||||
"siteUrl": "https://bright-canvas-a7k2.here.now/",
|
||||
"claimToken": "abc123",
|
||||
"claimUrl": "https://here.now/claim?slug=bright-canvas-a7k2&token=abc123",
|
||||
"expiresAt": "2026-02-18T01:00:00.000Z"
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Before creating or updating sites, you may check this file to find prior slugs.
|
||||
Treat `.herenow/state.json` as internal cache only.
|
||||
Never present this local file path as a URL, and never use it as source of truth for auth mode, expiry, or claim URL.
|
||||
|
||||
## What to tell the user
|
||||
|
||||
For published sites:
|
||||
|
||||
- Always share the `siteUrl` from the current script run.
|
||||
- Read and follow `publish_result.*` lines from script stderr to determine auth mode.
|
||||
- When `publish_result.auth_mode=authenticated`: tell the user the site is **permanent** and saved to their account. No claim URL is needed.
|
||||
- When `publish_result.auth_mode=anonymous`: tell the user the site **expires in 24 hours**. Share the claim URL (if `publish_result.claim_url` is non-empty and starts with `https://`) so they can keep it permanently. Warn that claim tokens are only returned once and cannot be recovered.
|
||||
- Never tell the user to inspect `.herenow/state.json` for claim URLs or auth status.
|
||||
|
||||
For Drives:
|
||||
|
||||
- Do not describe Drive files as public URLs.
|
||||
- Tell the user Drive contents are private unless shared with a scoped token.
|
||||
- When sharing access with another agent, prefer a scoped token with a narrow `pathPrefix` and short TTL.
|
||||
|
||||
## publish.sh options
|
||||
|
||||
| Flag | Description |
|
||||
| ---------------------- | -------------------------------------------- |
|
||||
| `--slug {slug}` | Update an existing site instead of creating |
|
||||
| `--claim-token {token}`| Override claim token for anonymous updates |
|
||||
| `--title {text}` | Viewer title (non-HTML sites) |
|
||||
| `--description {text}` | Viewer description |
|
||||
| `--ttl {seconds}` | Set expiry (authenticated only) |
|
||||
| `--client {name}` | Agent name for attribution (e.g. `hermes`) |
|
||||
| `--base-url {url}` | API base URL (default: `https://here.now`) |
|
||||
| `--allow-nonherenow-base-url` | Allow sending auth to non-default `--base-url` |
|
||||
| `--api-key {key}` | API key override (prefer credentials file) |
|
||||
| `--spa` | Enable SPA routing (serve index.html for unknown paths) |
|
||||
| `--forkable` | Allow others to fork this site |
|
||||
|
||||
## Beyond publish.sh
|
||||
|
||||
For Drive operations, use `drive.sh` or the Drive API. For broader account and site management — delete, metadata, passwords, payments, domains, handles, links, variables, proxy routes, forking, duplication, and more — see the current docs:
|
||||
|
||||
→ **https://here.now/docs**
|
||||
|
||||
Full docs: https://here.now/docs
|
||||
@@ -1,406 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
BASE_URL="https://here.now"
|
||||
CREDENTIALS_FILE="$HOME/.herenow/credentials"
|
||||
API_KEY="${HERENOW_API_KEY:-}"
|
||||
DRIVE_TOKEN="${HERENOW_DRIVE_TOKEN:-}"
|
||||
ALLOW_NON_HERENOW_BASE_URL=0
|
||||
MAX_FILE_BYTES=$((500 * 1024 * 1024))
|
||||
|
||||
usage() {
|
||||
cat <<'USAGE'
|
||||
Usage: drive.sh [global options] <command> [args]
|
||||
|
||||
Global options:
|
||||
--api-key <key> Account API key (or $HERENOW_API_KEY / ~/.herenow/credentials)
|
||||
--token <drv_live_...> Drive token (or $HERENOW_DRIVE_TOKEN)
|
||||
--base-url <url> API base (default: https://here.now)
|
||||
--allow-nonherenow-base-url
|
||||
|
||||
Commands:
|
||||
create [name] [--default]
|
||||
default
|
||||
ls
|
||||
ls <drive> [prefix]
|
||||
cat <drive> <path>
|
||||
put <drive> <path> --from <local-file>
|
||||
import <drive> <prefix> --from <local-folder> [--dry-run]
|
||||
export <drive> <prefix> --to <local-folder> [--dry-run]
|
||||
rm <drive> <path> [--recursive --confirm <path>]
|
||||
share <drive> --perms read|write [--prefix notes/] [--ttl 30d] [--label text] [--manage-tokens]
|
||||
tokens <drive>
|
||||
revoke <drive> <tokenId>
|
||||
delete <drive> --confirm "<drive name>"
|
||||
USAGE
|
||||
exit 1
|
||||
}
|
||||
|
||||
die() { echo "error: $1" >&2; exit 1; }
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
SKILL_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"
|
||||
BUNDLED_JQ="${SKILL_DIR}/bin/jq"
|
||||
|
||||
if [[ -x "$BUNDLED_JQ" ]]; then
|
||||
JQ_BIN="$BUNDLED_JQ"
|
||||
elif command -v jq >/dev/null 2>&1; then
|
||||
JQ_BIN="$(command -v jq)"
|
||||
else
|
||||
die "requires jq"
|
||||
fi
|
||||
|
||||
for cmd in curl file; do
|
||||
command -v "$cmd" >/dev/null 2>&1 || die "requires $cmd"
|
||||
done
|
||||
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
--api-key) API_KEY="$2"; shift 2 ;;
|
||||
--token) DRIVE_TOKEN="$2"; shift 2 ;;
|
||||
--base-url) BASE_URL="$2"; shift 2 ;;
|
||||
--allow-nonherenow-base-url) ALLOW_NON_HERENOW_BASE_URL=1; shift ;;
|
||||
--help|-h) usage ;;
|
||||
--*) die "unknown global option: $1" ;;
|
||||
*) break ;;
|
||||
esac
|
||||
done
|
||||
|
||||
CMD="${1:-}"
|
||||
[[ -n "$CMD" ]] || usage
|
||||
shift || true
|
||||
|
||||
if [[ -z "$API_KEY" && -z "$DRIVE_TOKEN" && -f "$CREDENTIALS_FILE" ]]; then
|
||||
API_KEY=$(tr -d '[:space:]' < "$CREDENTIALS_FILE")
|
||||
fi
|
||||
|
||||
BASE_URL="${BASE_URL%/}"
|
||||
if [[ "$BASE_URL" != "https://here.now" && "$ALLOW_NON_HERENOW_BASE_URL" -ne 1 ]]; then
|
||||
if [[ -n "$API_KEY" || -n "$DRIVE_TOKEN" ]]; then
|
||||
die "refusing to send credentials to non-default base URL; pass --allow-nonherenow-base-url to override"
|
||||
fi
|
||||
fi
|
||||
|
||||
auth_header=()
|
||||
if [[ -n "$DRIVE_TOKEN" ]]; then
|
||||
auth_header=(-H "authorization: Bearer $DRIVE_TOKEN")
|
||||
elif [[ -n "$API_KEY" ]]; then
|
||||
auth_header=(-H "authorization: Bearer $API_KEY")
|
||||
else
|
||||
die "missing credentials; set HERENOW_API_KEY, HERENOW_DRIVE_TOKEN, or ~/.herenow/credentials"
|
||||
fi
|
||||
|
||||
compute_sha256() {
|
||||
local f="$1"
|
||||
if command -v sha256sum >/dev/null 2>&1; then
|
||||
sha256sum "$f" | cut -d' ' -f1
|
||||
else
|
||||
shasum -a 256 "$f" | cut -d' ' -f1
|
||||
fi
|
||||
}
|
||||
|
||||
guess_content_type() {
|
||||
local f="$1"
|
||||
case "${f##*.}" in
|
||||
html|htm) echo "text/html; charset=utf-8" ;;
|
||||
css) echo "text/css; charset=utf-8" ;;
|
||||
js|mjs) echo "text/javascript; charset=utf-8" ;;
|
||||
json) echo "application/json; charset=utf-8" ;;
|
||||
md|txt) echo "text/plain; charset=utf-8" ;;
|
||||
svg) echo "image/svg+xml" ;;
|
||||
png) echo "image/png" ;;
|
||||
jpg|jpeg) echo "image/jpeg" ;;
|
||||
gif) echo "image/gif" ;;
|
||||
webp) echo "image/webp" ;;
|
||||
pdf) echo "application/pdf" ;;
|
||||
*) file --brief --mime-type "$f" 2>/dev/null || echo "application/octet-stream" ;;
|
||||
esac
|
||||
}
|
||||
|
||||
api_json() {
|
||||
local method="$1"; shift
|
||||
local url="$1"; shift
|
||||
local body="${1:-}"
|
||||
local tmp
|
||||
tmp=$(mktemp)
|
||||
local code
|
||||
if [[ -n "$body" ]]; then
|
||||
code=$(curl -sS -o "$tmp" -w "%{http_code}" -X "$method" "$url" "${auth_header[@]}" -H "content-type: application/json" -d "$body")
|
||||
else
|
||||
code=$(curl -sS -o "$tmp" -w "%{http_code}" -X "$method" "$url" "${auth_header[@]}")
|
||||
fi
|
||||
if [[ "$code" -lt 200 || "$code" -ge 300 ]]; then
|
||||
local err
|
||||
err=$("$JQ_BIN" -r '.error // empty' "$tmp" 2>/dev/null || true)
|
||||
[[ -n "$err" ]] || err="$(cat "$tmp")"
|
||||
rm -f "$tmp"
|
||||
die "HTTP $code: $err"
|
||||
fi
|
||||
cat "$tmp"
|
||||
rm -f "$tmp"
|
||||
}
|
||||
|
||||
urlenc() {
|
||||
"$JQ_BIN" -nr --arg v "$1" '$v|@uri'
|
||||
}
|
||||
|
||||
urlenc_path() {
|
||||
local path="$1"
|
||||
local out=""
|
||||
local part
|
||||
IFS='/' read -r -a parts <<< "$path"
|
||||
for part in "${parts[@]}"; do
|
||||
[[ -n "$out" ]] && out="$out/"
|
||||
out="$out$(urlenc "$part")"
|
||||
done
|
||||
echo "$out"
|
||||
}
|
||||
|
||||
resolve_drive() {
|
||||
local name="$1"
|
||||
if [[ "$name" == drv_* ]]; then
|
||||
echo "$name"
|
||||
return
|
||||
fi
|
||||
if [[ -n "$DRIVE_TOKEN" ]]; then
|
||||
die "drive tokens must reference drives by drv_ id; use account credentials to resolve drive names"
|
||||
fi
|
||||
if [[ "$name" == "default" || "$name" == "my-drive" || "$name" == "My Drive" ]]; then
|
||||
api_json GET "$BASE_URL/api/v1/drives/default" | "$JQ_BIN" -r '.drive.id'
|
||||
return
|
||||
fi
|
||||
local rows count
|
||||
rows=$(api_json GET "$BASE_URL/api/v1/drives" | "$JQ_BIN" --arg n "$name" '[.drives[] | select(.name == $n)]')
|
||||
count=$(echo "$rows" | "$JQ_BIN" 'length')
|
||||
[[ "$count" -eq 1 ]] || die "drive name '$name' matched $count drives; use a drv_ id"
|
||||
echo "$rows" | "$JQ_BIN" -r '.[0].id'
|
||||
}
|
||||
|
||||
drive_head() {
|
||||
local id="$1"
|
||||
api_json GET "$BASE_URL/api/v1/drives/$id" | "$JQ_BIN" -r '.drive.headVersionId // .headVersionId // empty'
|
||||
}
|
||||
|
||||
file_meta() {
|
||||
local id="$1"
|
||||
local path="$2"
|
||||
local prefix
|
||||
prefix=$(urlenc "$path")
|
||||
api_json GET "$BASE_URL/api/v1/drives/$id/files?prefix=$prefix&limit=200" | "$JQ_BIN" -c --arg p "$path" '.files[]? | select(.path == $p)' | head -n 1
|
||||
}
|
||||
|
||||
put_file() {
|
||||
local drive="$1"; shift
|
||||
local path="$1"; shift
|
||||
local local_file=""
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
--from) local_file="$2"; shift 2 ;;
|
||||
*) die "unexpected put argument: $1" ;;
|
||||
esac
|
||||
done
|
||||
[[ -f "$local_file" ]] || die "--from must be a file"
|
||||
local id sz ct sha meta body upload upload_url upload_id http_code
|
||||
id=$(resolve_drive "$drive")
|
||||
sz=$(wc -c < "$local_file" | tr -d ' ')
|
||||
[[ "$sz" -le "$MAX_FILE_BYTES" ]] || die "$path exceeds the $MAX_FILE_BYTES byte Drive file limit"
|
||||
ct=$(guess_content_type "$local_file")
|
||||
sha=$(compute_sha256 "$local_file")
|
||||
meta=$(file_meta "$id" "$path" || true)
|
||||
body=$("$JQ_BIN" -n --arg p "$path" --argjson s "$sz" --arg c "$ct" --arg sha "$sha" \
|
||||
'{path:$p,size:$s,contentType:$c,sha256:$sha}')
|
||||
if [[ -n "$meta" ]]; then
|
||||
etag=$(echo "$meta" | "$JQ_BIN" -r '.etag')
|
||||
body=$(echo "$body" | "$JQ_BIN" --arg e "$etag" '.ifMatch = $e')
|
||||
else
|
||||
body=$(echo "$body" | "$JQ_BIN" '.ifNoneMatch = "*"')
|
||||
fi
|
||||
upload=$(api_json POST "$BASE_URL/api/v1/drives/$id/files/uploads" "$body")
|
||||
upload_url=$(echo "$upload" | "$JQ_BIN" -r '.uploadUrl')
|
||||
upload_id=$(echo "$upload" | "$JQ_BIN" -r '.uploadId')
|
||||
http_code=$(curl -sS -o /dev/null -w "%{http_code}" -X PUT "$upload_url" -H "Content-Type: $ct" --data-binary "@$local_file")
|
||||
[[ "$http_code" -ge 200 && "$http_code" -lt 300 ]] || die "upload failed for $path (HTTP $http_code)"
|
||||
api_json POST "$BASE_URL/api/v1/drives/$id/files/finalize" "$("$JQ_BIN" -n --arg u "$upload_id" '{uploadId:$u}')" | "$JQ_BIN" .
|
||||
}
|
||||
|
||||
case "$CMD" in
|
||||
create)
|
||||
name=""
|
||||
is_default="false"
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
--default) is_default="true"; shift ;;
|
||||
*) [[ -z "$name" ]] && name="$1" || die "unexpected argument: $1"; shift ;;
|
||||
esac
|
||||
done
|
||||
body=$("$JQ_BIN" -n --arg n "$name" --argjson d "$is_default" '{isDefault:$d} + (if $n == "" then {} else {name:$n} end)')
|
||||
api_json POST "$BASE_URL/api/v1/drives" "$body" | "$JQ_BIN" .
|
||||
;;
|
||||
default)
|
||||
api_json GET "$BASE_URL/api/v1/drives/default" | "$JQ_BIN" .
|
||||
;;
|
||||
ls)
|
||||
if [[ $# -eq 0 ]]; then
|
||||
[[ -z "$DRIVE_TOKEN" ]] || die "drive tokens cannot list drives; pass a drv_ id"
|
||||
api_json GET "$BASE_URL/api/v1/drives" | "$JQ_BIN" .
|
||||
else
|
||||
id=$(resolve_drive "$1")
|
||||
prefix="${2:-}"
|
||||
api_json GET "$BASE_URL/api/v1/drives/$id/files?prefix=$(urlenc "$prefix")" | "$JQ_BIN" .
|
||||
fi
|
||||
;;
|
||||
cat)
|
||||
[[ $# -eq 2 ]] || die "usage: drive.sh cat <drive> <path>"
|
||||
id=$(resolve_drive "$1")
|
||||
curl -fsS "$BASE_URL/api/v1/drives/$id/files/$(urlenc_path "$2")" "${auth_header[@]}"
|
||||
;;
|
||||
put)
|
||||
[[ $# -ge 2 ]] || die "usage: drive.sh put <drive> <path> --from <local-file>"
|
||||
put_file "$@"
|
||||
;;
|
||||
import)
|
||||
[[ $# -ge 2 ]] || die "usage: drive.sh import <drive> <prefix> --from <local-folder> [--dry-run]"
|
||||
drive="$1"; prefix="${2%/}"; shift 2
|
||||
from=""; dry=0
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
--from) from="$2"; shift 2 ;;
|
||||
--dry-run) dry=1; shift ;;
|
||||
*) die "unexpected import argument: $1" ;;
|
||||
esac
|
||||
done
|
||||
[[ -d "$from" ]] || die "--from must be a folder"
|
||||
uploaded=0
|
||||
skipped=0
|
||||
failed=0
|
||||
planned=0
|
||||
while IFS= read -r -d '' f; do
|
||||
rel="${f#$from/}"
|
||||
[[ "$rel" == .git/* || "$rel" == node_modules/* || "$rel" == ".DS_Store" || "$rel" == */.DS_Store ]] && continue
|
||||
planned=$((planned + 1))
|
||||
sz=$(wc -c < "$f" | tr -d ' ')
|
||||
if [[ "$sz" -gt "$MAX_FILE_BYTES" ]]; then
|
||||
echo "skip oversized $f ($sz bytes > $MAX_FILE_BYTES)" >&2
|
||||
skipped=$((skipped + 1))
|
||||
continue
|
||||
fi
|
||||
dest="$rel"
|
||||
[[ -n "$prefix" ]] && dest="$prefix/$rel"
|
||||
if [[ "$dry" -eq 1 ]]; then
|
||||
echo "upload $f -> $dest"
|
||||
skipped=$((skipped + 1))
|
||||
else
|
||||
if (put_file "$drive" "$dest" --from "$f" >/dev/null); then
|
||||
uploaded=$((uploaded + 1))
|
||||
else
|
||||
failed=$((failed + 1))
|
||||
fi
|
||||
fi
|
||||
done < <(find "$from" -type f -print0 | sort -z)
|
||||
echo "planned=$planned uploaded=$uploaded skipped=$skipped failed=$failed"
|
||||
[[ "$failed" -eq 0 ]] || exit 1
|
||||
;;
|
||||
export)
|
||||
[[ $# -ge 2 ]] || die "usage: drive.sh export <drive> <prefix> --to <local-folder> [--dry-run]"
|
||||
id=$(resolve_drive "$1"); prefix="${2%/}"; shift 2
|
||||
to=""; dry=0
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
--to) to="$2"; shift 2 ;;
|
||||
--dry-run) dry=1; shift ;;
|
||||
*) die "unexpected export argument: $1" ;;
|
||||
esac
|
||||
done
|
||||
[[ -n "$to" ]] || die "--to is required"
|
||||
cursor=""
|
||||
total=0
|
||||
while true; do
|
||||
url="$BASE_URL/api/v1/drives/$id/files?prefix=$(urlenc "$prefix")&limit=200"
|
||||
[[ -n "$cursor" ]] && url="$url&cursor=$(urlenc "$cursor")"
|
||||
files=$(api_json GET "$url")
|
||||
while IFS= read -r p; do
|
||||
[[ -n "$p" ]] || continue
|
||||
rel="$p"
|
||||
[[ -n "$prefix" ]] && rel="${p#$prefix/}"
|
||||
out="$to/$rel"
|
||||
if [[ "$dry" -eq 1 ]]; then
|
||||
echo "download $p -> $out"
|
||||
else
|
||||
mkdir -p "$(dirname "$out")"
|
||||
curl -fsS "$BASE_URL/api/v1/drives/$id/files/$(urlenc_path "$p")" "${auth_header[@]}" -o "$out"
|
||||
fi
|
||||
total=$((total + 1))
|
||||
done < <(echo "$files" | "$JQ_BIN" -r '.files[].path')
|
||||
cursor=$(echo "$files" | "$JQ_BIN" -r '.nextCursor // empty')
|
||||
[[ -n "$cursor" ]] || break
|
||||
done
|
||||
echo "files=$total"
|
||||
;;
|
||||
rm)
|
||||
[[ $# -ge 2 ]] || die "usage: drive.sh rm <drive> <path> [--recursive --confirm <path>]"
|
||||
id=$(resolve_drive "$1"); path="$2"; shift 2
|
||||
recursive=0; confirm=""
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
--recursive) recursive=1; shift ;;
|
||||
--confirm) confirm="$2"; shift 2 ;;
|
||||
*) die "unexpected rm argument: $1" ;;
|
||||
esac
|
||||
done
|
||||
if [[ "$recursive" -eq 1 ]]; then
|
||||
[[ "$confirm" == "$path" ]] || die "recursive delete requires --confirm '$path'"
|
||||
head=$(drive_head "$id")
|
||||
api_json DELETE "$BASE_URL/api/v1/drives/$id/files/$(urlenc_path "$path")?recursive=true&baseVersionId=$(urlenc "$head")" | "$JQ_BIN" .
|
||||
else
|
||||
meta=$(file_meta "$id" "$path")
|
||||
etag=$(echo "$meta" | "$JQ_BIN" -r '.etag')
|
||||
curl -fsS -X DELETE "$BASE_URL/api/v1/drives/$id/files/$(urlenc_path "$path")" "${auth_header[@]}" -H "If-Match: $etag" | "$JQ_BIN" .
|
||||
fi
|
||||
;;
|
||||
share)
|
||||
[[ $# -ge 1 ]] || die "usage: drive.sh share <drive> --perms read|write [--prefix notes/] [--ttl 30d] [--label text] [--manage-tokens]"
|
||||
id=$(resolve_drive "$1"); shift
|
||||
perms="write"; prefix=""; ttl=""; label=""; manage_tokens="false"
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
--perms) perms="$2"; shift 2 ;;
|
||||
--prefix) prefix="$2"; shift 2 ;;
|
||||
--ttl) ttl="$2"; shift 2 ;;
|
||||
--label) label="$2"; shift 2 ;;
|
||||
--manage-tokens) manage_tokens="true"; shift ;;
|
||||
*) die "unexpected share argument: $1" ;;
|
||||
esac
|
||||
done
|
||||
body=$("$JQ_BIN" -n --arg p "$perms" --arg pp "$prefix" --arg ttl "$ttl" --arg label "$label" --argjson mt "$manage_tokens" \
|
||||
'{perms:$p} + (if $mt then {manageTokens:true} else {} end) + (if $ttl == "" then {} else {ttl:$ttl} end) + (if $pp == "" then {} else {pathPrefix:$pp} end) + (if $label == "" then {} else {label:$label} end)')
|
||||
api_json POST "$BASE_URL/api/v1/drives/$id/tokens" "$body" | "$JQ_BIN" -r '.shareBlock'
|
||||
;;
|
||||
tokens)
|
||||
[[ $# -eq 1 ]] || die "usage: drive.sh tokens <drive>"
|
||||
id=$(resolve_drive "$1")
|
||||
api_json GET "$BASE_URL/api/v1/drives/$id/tokens" | "$JQ_BIN" .
|
||||
;;
|
||||
revoke)
|
||||
[[ $# -eq 2 ]] || die "usage: drive.sh revoke <drive> <tokenId>"
|
||||
id=$(resolve_drive "$1")
|
||||
api_json DELETE "$BASE_URL/api/v1/drives/$id/tokens/$2" | "$JQ_BIN" .
|
||||
;;
|
||||
delete)
|
||||
[[ $# -ge 1 ]] || die "usage: drive.sh delete <drive> --confirm <drive name>"
|
||||
id=$(resolve_drive "$1"); shift
|
||||
confirm=""
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
--confirm) confirm="$2"; shift 2 ;;
|
||||
*) die "unexpected delete argument: $1" ;;
|
||||
esac
|
||||
done
|
||||
drive=$(api_json GET "$BASE_URL/api/v1/drives/$id")
|
||||
name=$(echo "$drive" | "$JQ_BIN" -r '.drive.name')
|
||||
[[ "$confirm" == "$name" ]] || die "delete requires --confirm '$name'"
|
||||
api_json DELETE "$BASE_URL/api/v1/drives/$id" | "$JQ_BIN" .
|
||||
;;
|
||||
*)
|
||||
die "unknown command: $CMD"
|
||||
;;
|
||||
esac
|
||||
@@ -1,445 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
BASE_URL="https://here.now"
|
||||
CREDENTIALS_FILE="$HOME/.herenow/credentials"
|
||||
API_KEY="${HERENOW_API_KEY:-}"
|
||||
API_KEY_SOURCE="none"
|
||||
if [[ -n "${HERENOW_API_KEY:-}" ]]; then
|
||||
API_KEY_SOURCE="env"
|
||||
fi
|
||||
ALLOW_NON_HERENOW_BASE_URL=0
|
||||
SLUG=""
|
||||
CLAIM_TOKEN=""
|
||||
TITLE=""
|
||||
DESCRIPTION=""
|
||||
TTL=""
|
||||
CLIENT=""
|
||||
TARGET=""
|
||||
FORKABLE=""
|
||||
SPA_MODE=""
|
||||
FROM_DRIVE=""
|
||||
DRIVE_VERSION=""
|
||||
|
||||
usage() {
|
||||
cat <<'USAGE'
|
||||
Usage: publish.sh <file-or-dir> [options]
|
||||
|
||||
Options:
|
||||
--api-key <key> API key (or set $HERENOW_API_KEY)
|
||||
--slug <slug> Update existing publish
|
||||
--claim-token <token> Claim token for anonymous updates
|
||||
--title <text> Viewer title
|
||||
--description <text> Viewer description
|
||||
--ttl <seconds> Expiry (authenticated only)
|
||||
--client <name> Agent name for attribution (e.g. cursor, claude-code)
|
||||
--forkable Allow others to fork this site
|
||||
--spa Enable SPA routing
|
||||
--from-drive <drv_...> Publish a Drive snapshot instead of local files
|
||||
--version <dv_...> Drive version for --from-drive (default: current head)
|
||||
--base-url <url> API base (default: https://here.now)
|
||||
--allow-nonherenow-base-url
|
||||
Allow auth requests to non-default API base URL
|
||||
USAGE
|
||||
exit 1
|
||||
}
|
||||
|
||||
die() { echo "error: $1" >&2; exit 1; }
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
SKILL_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"
|
||||
BUNDLED_JQ="${SKILL_DIR}/bin/jq"
|
||||
|
||||
if [[ -x "$BUNDLED_JQ" ]]; then
|
||||
JQ_BIN="$BUNDLED_JQ"
|
||||
elif command -v jq >/dev/null 2>&1; then
|
||||
JQ_BIN="$(command -v jq)"
|
||||
else
|
||||
die "requires jq"
|
||||
fi
|
||||
|
||||
for cmd in curl file; do
|
||||
command -v "$cmd" >/dev/null 2>&1 || die "requires $cmd"
|
||||
done
|
||||
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
--api-key) API_KEY="$2"; API_KEY_SOURCE="flag"; shift 2 ;;
|
||||
--slug) SLUG="$2"; shift 2 ;;
|
||||
--claim-token) CLAIM_TOKEN="$2"; shift 2 ;;
|
||||
--title) TITLE="$2"; shift 2 ;;
|
||||
--description) DESCRIPTION="$2"; shift 2 ;;
|
||||
--ttl) TTL="$2"; shift 2 ;;
|
||||
--client) CLIENT="$2"; shift 2 ;;
|
||||
--base-url) BASE_URL="$2"; shift 2 ;;
|
||||
--allow-nonherenow-base-url) ALLOW_NON_HERENOW_BASE_URL=1; shift ;;
|
||||
--forkable) FORKABLE="true"; shift ;;
|
||||
--spa) SPA_MODE="true"; shift ;;
|
||||
--from-drive) FROM_DRIVE="$2"; shift 2 ;;
|
||||
--version) DRIVE_VERSION="$2"; shift 2 ;;
|
||||
--help|-h) usage ;;
|
||||
-*) die "unknown option: $1" ;;
|
||||
*) [[ -z "$TARGET" ]] && TARGET="$1" || die "unexpected argument: $1"; shift ;;
|
||||
esac
|
||||
done
|
||||
|
||||
if [[ -n "$FROM_DRIVE" ]]; then
|
||||
[[ -z "$TARGET" ]] || die "--from-drive does not accept a local file-or-dir argument"
|
||||
else
|
||||
[[ -n "$TARGET" ]] || usage
|
||||
[[ -e "$TARGET" ]] || die "path does not exist: $TARGET"
|
||||
fi
|
||||
|
||||
# Load API key from credentials file if not provided via flag or env
|
||||
if [[ -z "$API_KEY" && -f "$CREDENTIALS_FILE" ]]; then
|
||||
API_KEY=$(cat "$CREDENTIALS_FILE" | tr -d '[:space:]')
|
||||
[[ -n "$API_KEY" ]] && API_KEY_SOURCE="credentials"
|
||||
fi
|
||||
|
||||
BASE_URL="${BASE_URL%/}"
|
||||
STATE_DIR=".herenow"
|
||||
STATE_FILE="$STATE_DIR/state.json"
|
||||
|
||||
# Safety guard: avoid accidentally sending bearer auth to arbitrary endpoints.
|
||||
if [[ -n "$API_KEY" && "$BASE_URL" != "https://here.now" && "$ALLOW_NON_HERENOW_BASE_URL" -ne 1 ]]; then
|
||||
die "refusing to send API key to non-default base URL; pass --allow-nonherenow-base-url to override"
|
||||
fi
|
||||
|
||||
# Auto-load claim token from state file for anonymous updates
|
||||
if [[ -n "$SLUG" && -z "$CLAIM_TOKEN" && -z "$API_KEY" && -f "$STATE_FILE" ]]; then
|
||||
CLAIM_TOKEN=$("$JQ_BIN" -r --arg s "$SLUG" '.publishes[$s].claimToken // empty' "$STATE_FILE" 2>/dev/null || true)
|
||||
fi
|
||||
|
||||
if [[ -n "$FROM_DRIVE" ]]; then
|
||||
[[ -n "$API_KEY" ]] || die "--from-drive requires an account API key"
|
||||
BODY=$("$JQ_BIN" -n --arg d "$FROM_DRIVE" '{driveId:$d}')
|
||||
[[ -n "$DRIVE_VERSION" ]] && BODY=$(echo "$BODY" | "$JQ_BIN" --arg v "$DRIVE_VERSION" '.versionId = $v')
|
||||
[[ -n "$SLUG" ]] && BODY=$(echo "$BODY" | "$JQ_BIN" --arg s "$SLUG" '.slug = $s')
|
||||
if [[ -n "$TITLE" || -n "$DESCRIPTION" ]]; then
|
||||
viewer="{}"
|
||||
[[ -n "$TITLE" ]] && viewer=$(echo "$viewer" | "$JQ_BIN" --arg t "$TITLE" '.title = $t')
|
||||
[[ -n "$DESCRIPTION" ]] && viewer=$(echo "$viewer" | "$JQ_BIN" --arg d "$DESCRIPTION" '.description = $d')
|
||||
BODY=$(echo "$BODY" | "$JQ_BIN" --argjson v "$viewer" '.viewer = $v')
|
||||
fi
|
||||
[[ "$FORKABLE" == "true" ]] && BODY=$(echo "$BODY" | "$JQ_BIN" '.forkable = true')
|
||||
[[ "$SPA_MODE" == "true" ]] && BODY=$(echo "$BODY" | "$JQ_BIN" '.spaMode = true')
|
||||
CLIENT_HEADER_VALUE="here-now-publish-sh"
|
||||
if [[ -n "$CLIENT" ]]; then
|
||||
normalized_client=$(echo "$CLIENT" | tr '[:upper:]' '[:lower:]' | tr -cs 'a-z0-9._-' '-')
|
||||
normalized_client="${normalized_client#-}"
|
||||
normalized_client="${normalized_client%-}"
|
||||
if [[ -n "$normalized_client" ]]; then
|
||||
CLIENT_HEADER_VALUE="${normalized_client}/publish-sh"
|
||||
fi
|
||||
fi
|
||||
|
||||
echo "publishing from Drive..." >&2
|
||||
RESPONSE=$(curl -sS -X POST "$BASE_URL/api/v1/publish/from-drive" \
|
||||
-H "authorization: Bearer $API_KEY" \
|
||||
-H "x-herenow-client: $CLIENT_HEADER_VALUE" \
|
||||
-H "content-type: application/json" \
|
||||
-d "$BODY")
|
||||
if echo "$RESPONSE" | "$JQ_BIN" -e '.error' >/dev/null 2>&1; then
|
||||
err=$(echo "$RESPONSE" | "$JQ_BIN" -r '.error')
|
||||
die "$err"
|
||||
fi
|
||||
SITE_URL=$(echo "$RESPONSE" | "$JQ_BIN" -r '.siteUrl')
|
||||
OUT_SLUG=$(echo "$RESPONSE" | "$JQ_BIN" -r '.slug')
|
||||
CURRENT_VERSION=$(echo "$RESPONSE" | "$JQ_BIN" -r '.currentVersionId')
|
||||
DRIVE_VERSION_OUT=$(echo "$RESPONSE" | "$JQ_BIN" -r '.driveVersionId')
|
||||
echo "$SITE_URL"
|
||||
echo "" >&2
|
||||
echo "publish_result.site_url=$SITE_URL" >&2
|
||||
echo "publish_result.slug=$OUT_SLUG" >&2
|
||||
echo "publish_result.action=from_drive" >&2
|
||||
echo "publish_result.auth_mode=authenticated" >&2
|
||||
echo "publish_result.api_key_source=$API_KEY_SOURCE" >&2
|
||||
echo "publish_result.persistence=permanent" >&2
|
||||
echo "publish_result.drive_id=$FROM_DRIVE" >&2
|
||||
echo "publish_result.drive_version_id=$DRIVE_VERSION_OUT" >&2
|
||||
echo "publish_result.current_version_id=$CURRENT_VERSION" >&2
|
||||
exit 0
|
||||
fi
|
||||
|
||||
compute_sha256() {
|
||||
local f="$1"
|
||||
if command -v sha256sum >/dev/null 2>&1; then
|
||||
sha256sum "$f" | cut -d' ' -f1
|
||||
else
|
||||
shasum -a 256 "$f" | cut -d' ' -f1
|
||||
fi
|
||||
}
|
||||
|
||||
guess_content_type() {
|
||||
local f="$1"
|
||||
case "${f##*.}" in
|
||||
html|htm) echo "text/html; charset=utf-8" ;;
|
||||
css) echo "text/css; charset=utf-8" ;;
|
||||
js|mjs) echo "text/javascript; charset=utf-8" ;;
|
||||
json) echo "application/json; charset=utf-8" ;;
|
||||
md|txt) echo "text/plain; charset=utf-8" ;;
|
||||
svg) echo "image/svg+xml" ;;
|
||||
png) echo "image/png" ;;
|
||||
jpg|jpeg) echo "image/jpeg" ;;
|
||||
gif) echo "image/gif" ;;
|
||||
webp) echo "image/webp" ;;
|
||||
pdf) echo "application/pdf" ;;
|
||||
mp4) echo "video/mp4" ;;
|
||||
mov) echo "video/quicktime" ;;
|
||||
mp3) echo "audio/mpeg" ;;
|
||||
wav) echo "audio/wav" ;;
|
||||
xml) echo "application/xml" ;;
|
||||
woff2) echo "font/woff2" ;;
|
||||
woff) echo "font/woff" ;;
|
||||
ttf) echo "font/ttf" ;;
|
||||
ico) echo "image/x-icon" ;;
|
||||
*)
|
||||
local detected
|
||||
detected=$(file --brief --mime-type "$f" 2>/dev/null || echo "application/octet-stream")
|
||||
echo "$detected"
|
||||
;;
|
||||
esac
|
||||
}
|
||||
|
||||
# Build file manifest as JSON array
|
||||
FILES_JSON="[]"
|
||||
|
||||
if [[ -f "$TARGET" ]]; then
|
||||
sz=$(wc -c < "$TARGET" | tr -d ' ')
|
||||
ct=$(guess_content_type "$TARGET")
|
||||
bn=$(basename "$TARGET")
|
||||
h=$(compute_sha256 "$TARGET")
|
||||
FILES_JSON=$("$JQ_BIN" -n --arg p "$bn" --argjson s "$sz" --arg c "$ct" --arg h "$h" \
|
||||
'[{"path":$p,"size":$s,"contentType":$c,"hash":$h}]')
|
||||
FILE_MAP=$("$JQ_BIN" -n --arg p "$bn" --arg a "$(cd "$(dirname "$TARGET")" && pwd)/$(basename "$TARGET")" \
|
||||
'{($p):$a}')
|
||||
elif [[ -d "$TARGET" ]]; then
|
||||
FILE_MAP="{}"
|
||||
while IFS= read -r -d '' f; do
|
||||
rel="${f#$TARGET/}"
|
||||
[[ "$rel" == ".DS_Store" ]] && continue
|
||||
[[ "$(basename "$rel")" == ".DS_Store" ]] && continue
|
||||
[[ "$rel" == ".herenow/fork-meta.json" ]] && continue
|
||||
sz=$(wc -c < "$f" | tr -d ' ')
|
||||
ct=$(guess_content_type "$f")
|
||||
h=$(compute_sha256 "$f")
|
||||
abs=$(cd "$(dirname "$f")" && pwd)/$(basename "$f")
|
||||
FILES_JSON=$(echo "$FILES_JSON" | "$JQ_BIN" --arg p "$rel" --argjson s "$sz" --arg c "$ct" --arg h "$h" \
|
||||
'. + [{"path":$p,"size":$s,"contentType":$c,"hash":$h}]')
|
||||
FILE_MAP=$(echo "$FILE_MAP" | "$JQ_BIN" --arg p "$rel" --arg a "$abs" '. + {($p):$a}')
|
||||
done < <(find "$TARGET" -type f -print0 | sort -z)
|
||||
else
|
||||
die "not a file or directory: $TARGET"
|
||||
fi
|
||||
|
||||
file_count=$(echo "$FILES_JSON" | "$JQ_BIN" 'length')
|
||||
[[ "$file_count" -gt 0 ]] || die "no files found"
|
||||
|
||||
# Read fork-meta.json defaults if present and no explicit flags given
|
||||
FORK_META=""
|
||||
if [[ -d "$TARGET" ]]; then
|
||||
FORK_META_PATH="$TARGET/.herenow/fork-meta.json"
|
||||
if [[ -f "$FORK_META_PATH" ]]; then
|
||||
FORK_META=$(cat "$FORK_META_PATH")
|
||||
if [[ -z "$FORKABLE" ]]; then
|
||||
FORKABLE=$("$JQ_BIN" -r '.forkable // empty' <<< "$FORK_META" 2>/dev/null || true)
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
# Build request body
|
||||
BODY=$(echo "$FILES_JSON" | "$JQ_BIN" '{files: .}')
|
||||
|
||||
if [[ -n "$TTL" ]]; then
|
||||
BODY=$(echo "$BODY" | "$JQ_BIN" --argjson t "$TTL" '.ttlSeconds = $t')
|
||||
fi
|
||||
|
||||
if [[ -n "$TITLE" || -n "$DESCRIPTION" ]]; then
|
||||
viewer="{}"
|
||||
[[ -n "$TITLE" ]] && viewer=$(echo "$viewer" | "$JQ_BIN" --arg t "$TITLE" '.title = $t')
|
||||
[[ -n "$DESCRIPTION" ]] && viewer=$(echo "$viewer" | "$JQ_BIN" --arg d "$DESCRIPTION" '.description = $d')
|
||||
BODY=$(echo "$BODY" | "$JQ_BIN" --argjson v "$viewer" '.viewer = $v')
|
||||
fi
|
||||
|
||||
if [[ -n "$CLAIM_TOKEN" && -n "$SLUG" && -z "$API_KEY" ]]; then
|
||||
BODY=$(echo "$BODY" | "$JQ_BIN" --arg ct "$CLAIM_TOKEN" '.claimToken = $ct')
|
||||
fi
|
||||
|
||||
if [[ "$FORKABLE" == "true" ]]; then
|
||||
BODY=$(echo "$BODY" | "$JQ_BIN" '.forkable = true')
|
||||
fi
|
||||
|
||||
if [[ "$SPA_MODE" == "true" ]]; then
|
||||
BODY=$(echo "$BODY" | "$JQ_BIN" '.spaMode = true')
|
||||
fi
|
||||
|
||||
# Determine endpoint and method
|
||||
if [[ -n "$SLUG" ]]; then
|
||||
URL="$BASE_URL/api/v1/publish/$SLUG"
|
||||
METHOD="PUT"
|
||||
else
|
||||
URL="$BASE_URL/api/v1/publish"
|
||||
METHOD="POST"
|
||||
fi
|
||||
|
||||
# Build auth header
|
||||
AUTH_ARGS=()
|
||||
if [[ -n "$API_KEY" ]]; then
|
||||
AUTH_ARGS=(-H "authorization: Bearer $API_KEY")
|
||||
fi
|
||||
|
||||
AUTH_MODE="anonymous"
|
||||
if [[ -n "$API_KEY" ]]; then
|
||||
AUTH_MODE="authenticated"
|
||||
fi
|
||||
|
||||
CLIENT_HEADER_VALUE="here-now-publish-sh"
|
||||
if [[ -n "$CLIENT" ]]; then
|
||||
normalized_client=$(echo "$CLIENT" | tr '[:upper:]' '[:lower:]' | tr -cs 'a-z0-9._-' '-')
|
||||
normalized_client="${normalized_client#-}"
|
||||
normalized_client="${normalized_client%-}"
|
||||
if [[ -n "$normalized_client" ]]; then
|
||||
CLIENT_HEADER_VALUE="${normalized_client}/publish-sh"
|
||||
fi
|
||||
fi
|
||||
CLIENT_ARGS=(-H "x-herenow-client: $CLIENT_HEADER_VALUE")
|
||||
|
||||
# Step 1: Create/update publish
|
||||
echo "creating publish ($file_count files)..." >&2
|
||||
RESPONSE=$(curl -sS -X "$METHOD" "$URL" \
|
||||
"${AUTH_ARGS[@]+"${AUTH_ARGS[@]}"}" \
|
||||
"${CLIENT_ARGS[@]+"${CLIENT_ARGS[@]}"}" \
|
||||
-H "content-type: application/json" \
|
||||
-d "$BODY")
|
||||
|
||||
# Check for errors
|
||||
if echo "$RESPONSE" | "$JQ_BIN" -e '.error' >/dev/null 2>&1; then
|
||||
err=$(echo "$RESPONSE" | "$JQ_BIN" -r '.error')
|
||||
details=$(echo "$RESPONSE" | "$JQ_BIN" -r '.details // empty')
|
||||
die "$err${details:+ ($details)}"
|
||||
fi
|
||||
|
||||
OUT_SLUG=$(echo "$RESPONSE" | "$JQ_BIN" -r '.slug')
|
||||
VERSION_ID=$(echo "$RESPONSE" | "$JQ_BIN" -r '.upload.versionId')
|
||||
FINALIZE_URL=$(echo "$RESPONSE" | "$JQ_BIN" -r '.upload.finalizeUrl')
|
||||
SITE_URL=$(echo "$RESPONSE" | "$JQ_BIN" -r '.siteUrl')
|
||||
UPLOAD_COUNT=$(echo "$RESPONSE" | "$JQ_BIN" '.upload.uploads | length')
|
||||
SKIPPED_COUNT=$(echo "$RESPONSE" | "$JQ_BIN" '.upload.skipped // [] | length')
|
||||
|
||||
[[ "$OUT_SLUG" != "null" ]] || die "unexpected response: $RESPONSE"
|
||||
|
||||
# Step 2: Upload files (skipped files are unchanged from previous version)
|
||||
if [[ "$SKIPPED_COUNT" -gt 0 ]]; then
|
||||
echo "uploading $UPLOAD_COUNT files ($SKIPPED_COUNT unchanged, skipped)..." >&2
|
||||
else
|
||||
echo "uploading $UPLOAD_COUNT files..." >&2
|
||||
fi
|
||||
upload_errors=0
|
||||
|
||||
for i in $(seq 0 $((UPLOAD_COUNT - 1))); do
|
||||
upload_path=$(echo "$RESPONSE" | "$JQ_BIN" -r ".upload.uploads[$i].path")
|
||||
upload_url=$(echo "$RESPONSE" | "$JQ_BIN" -r ".upload.uploads[$i].url")
|
||||
upload_ct=$(echo "$RESPONSE" | "$JQ_BIN" -r ".upload.uploads[$i].headers[\"Content-Type\"] // empty")
|
||||
|
||||
if [[ -f "$TARGET" && ! -d "$TARGET" ]]; then
|
||||
local_file="$TARGET"
|
||||
else
|
||||
local_file=$(echo "$FILE_MAP" | "$JQ_BIN" -r --arg p "$upload_path" '.[$p]')
|
||||
fi
|
||||
|
||||
if [[ ! -f "$local_file" ]]; then
|
||||
echo "warning: missing local file for $upload_path" >&2
|
||||
upload_errors=$((upload_errors + 1))
|
||||
continue
|
||||
fi
|
||||
|
||||
ct_args=()
|
||||
[[ -n "$upload_ct" ]] && ct_args=(-H "Content-Type: $upload_ct")
|
||||
|
||||
http_code=$(curl -sS -o /dev/null -w "%{http_code}" -X PUT "$upload_url" \
|
||||
"${ct_args[@]+"${ct_args[@]}"}" \
|
||||
--data-binary "@$local_file")
|
||||
|
||||
if [[ "$http_code" -lt 200 || "$http_code" -ge 300 ]]; then
|
||||
echo "warning: upload failed for $upload_path (HTTP $http_code)" >&2
|
||||
upload_errors=$((upload_errors + 1))
|
||||
fi
|
||||
done
|
||||
|
||||
[[ "$upload_errors" -eq 0 ]] || die "$upload_errors file(s) failed to upload"
|
||||
|
||||
# Step 3: Finalize
|
||||
echo "finalizing..." >&2
|
||||
FIN_RESPONSE=$(curl -sS -X POST "$FINALIZE_URL" \
|
||||
"${AUTH_ARGS[@]+"${AUTH_ARGS[@]}"}" \
|
||||
"${CLIENT_ARGS[@]+"${CLIENT_ARGS[@]}"}" \
|
||||
-H "content-type: application/json" \
|
||||
-d "{\"versionId\":\"$VERSION_ID\"}")
|
||||
|
||||
if echo "$FIN_RESPONSE" | "$JQ_BIN" -e '.error' >/dev/null 2>&1; then
|
||||
err=$(echo "$FIN_RESPONSE" | "$JQ_BIN" -r '.error')
|
||||
die "finalize failed: $err"
|
||||
fi
|
||||
|
||||
# Save state
|
||||
mkdir -p "$STATE_DIR"
|
||||
if [[ -f "$STATE_FILE" ]]; then
|
||||
STATE=$(cat "$STATE_FILE")
|
||||
else
|
||||
STATE='{"publishes":{}}'
|
||||
fi
|
||||
|
||||
entry=$("$JQ_BIN" -n --arg s "$SITE_URL" '{siteUrl: $s}')
|
||||
|
||||
RESPONSE_CLAIM_TOKEN=$(echo "$RESPONSE" | "$JQ_BIN" -r '.claimToken // empty')
|
||||
RESPONSE_CLAIM_URL=$(echo "$RESPONSE" | "$JQ_BIN" -r '.claimUrl // empty')
|
||||
RESPONSE_EXPIRES=$(echo "$RESPONSE" | "$JQ_BIN" -r '.expiresAt // empty')
|
||||
|
||||
[[ -n "$RESPONSE_CLAIM_TOKEN" ]] && entry=$(echo "$entry" | "$JQ_BIN" --arg v "$RESPONSE_CLAIM_TOKEN" '.claimToken = $v')
|
||||
[[ -n "$RESPONSE_CLAIM_URL" ]] && entry=$(echo "$entry" | "$JQ_BIN" --arg v "$RESPONSE_CLAIM_URL" '.claimUrl = $v')
|
||||
[[ -n "$RESPONSE_EXPIRES" ]] && entry=$(echo "$entry" | "$JQ_BIN" --arg v "$RESPONSE_EXPIRES" '.expiresAt = $v')
|
||||
|
||||
STATE=$(echo "$STATE" | "$JQ_BIN" --arg slug "$OUT_SLUG" --argjson e "$entry" '.publishes[$slug] = $e')
|
||||
echo "$STATE" | "$JQ_BIN" '.' > "$STATE_FILE"
|
||||
|
||||
# Output
|
||||
echo "$SITE_URL"
|
||||
|
||||
PERSISTENCE="permanent"
|
||||
if [[ "$AUTH_MODE" == "anonymous" ]]; then
|
||||
PERSISTENCE="expires_24h"
|
||||
elif [[ -n "$RESPONSE_EXPIRES" ]]; then
|
||||
PERSISTENCE="expires_at"
|
||||
fi
|
||||
|
||||
SAFE_CLAIM_URL=""
|
||||
if [[ -n "$RESPONSE_CLAIM_URL" && "$RESPONSE_CLAIM_URL" == https://* ]]; then
|
||||
SAFE_CLAIM_URL="$RESPONSE_CLAIM_URL"
|
||||
fi
|
||||
|
||||
ACTION="create"
|
||||
if [[ -n "$SLUG" ]]; then
|
||||
ACTION="update"
|
||||
fi
|
||||
|
||||
echo "" >&2
|
||||
echo "publish_result.site_url=$SITE_URL" >&2
|
||||
echo "publish_result.slug=$OUT_SLUG" >&2
|
||||
echo "publish_result.action=$ACTION" >&2
|
||||
echo "publish_result.auth_mode=$AUTH_MODE" >&2
|
||||
echo "publish_result.api_key_source=$API_KEY_SOURCE" >&2
|
||||
echo "publish_result.persistence=$PERSISTENCE" >&2
|
||||
echo "publish_result.expires_at=$RESPONSE_EXPIRES" >&2
|
||||
echo "publish_result.claim_url=$SAFE_CLAIM_URL" >&2
|
||||
|
||||
if [[ "$AUTH_MODE" == "authenticated" ]]; then
|
||||
echo "authenticated publish (permanent, saved to your account)" >&2
|
||||
else
|
||||
echo "anonymous publish (expires in 24h)" >&2
|
||||
if [[ -n "$SAFE_CLAIM_URL" ]]; then
|
||||
echo "claim URL: $SAFE_CLAIM_URL" >&2
|
||||
fi
|
||||
if [[ -n "$RESPONSE_CLAIM_TOKEN" ]]; then
|
||||
echo "claim token saved to $STATE_FILE" >&2
|
||||
fi
|
||||
fi
|
||||
@@ -1,372 +0,0 @@
|
||||
---
|
||||
name: shopify
|
||||
description: Shopify Admin & Storefront GraphQL APIs via curl. Products, orders, customers, inventory, metafields.
|
||||
version: 1.0.0
|
||||
author: community
|
||||
license: MIT
|
||||
prerequisites:
|
||||
env_vars: [SHOPIFY_ACCESS_TOKEN, SHOPIFY_STORE_DOMAIN]
|
||||
commands: [curl, jq]
|
||||
required_environment_variables:
|
||||
- name: SHOPIFY_ACCESS_TOKEN
|
||||
prompt: Shopify Admin API access token (starts with shpat_)
|
||||
help: "Shopify admin → Settings → Apps and sales channels → Develop apps → Create an app → API credentials. Token shown ONCE on install."
|
||||
- name: SHOPIFY_STORE_DOMAIN
|
||||
prompt: Your shop subdomain without protocol (e.g. my-store.myshopify.com)
|
||||
help: "The permanent myshopify.com domain, not your custom domain."
|
||||
- name: SHOPIFY_API_VERSION
|
||||
prompt: Shopify API version (default 2026-01)
|
||||
help: "Stable quarterly version. Override if you need an older one."
|
||||
metadata:
|
||||
hermes:
|
||||
tags: [Shopify, E-commerce, Commerce, API, GraphQL]
|
||||
related_skills: [airtable, xurl]
|
||||
homepage: https://shopify.dev/docs/api/admin-graphql
|
||||
---
|
||||
|
||||
# Shopify — Admin & Storefront GraphQL APIs
|
||||
|
||||
Work with Shopify stores directly through `curl`: list products, manage inventory, pull orders, update customers, read metafields. No SDK, no app framework — just the GraphQL endpoint and a custom-app access token.
|
||||
|
||||
The REST Admin API is legacy since 2024-04 and only receives security fixes. **Use GraphQL Admin** for all admin work. Use **Storefront GraphQL** for read-only customer-facing queries (products, collections, cart).
|
||||
|
||||
## Prerequisites
|
||||
|
||||
1. In Shopify admin: **Settings → Apps and sales channels → Develop apps → Create an app**.
|
||||
2. Click **Configure Admin API scopes**, select what you need (examples below), save.
|
||||
3. **Install app** → the Admin API access token appears ONCE. Copy it immediately — Shopify will never show it again. Tokens start with `shpat_`.
|
||||
4. Save to `~/.hermes/.env`:
|
||||
```
|
||||
SHOPIFY_ACCESS_TOKEN=shpat_xxxxxxxxxxxxxxxxxxxx
|
||||
SHOPIFY_STORE_DOMAIN=my-store.myshopify.com
|
||||
SHOPIFY_API_VERSION=2026-01
|
||||
```
|
||||
|
||||
> **Heads up:** As of January 1, 2026, new "legacy custom apps" created in the Shopify admin are gone. New setups should use the **Dev Dashboard** (`shopify.dev/docs/apps/build/dev-dashboard`). Existing admin-created apps keep working. If the user's shop has no existing custom app and it's after 2026-01-01, direct them to Dev Dashboard instead of the admin flow.
|
||||
|
||||
Common scopes by task:
|
||||
- Products / collections: `read_products`, `write_products`
|
||||
- Inventory: `read_inventory`, `write_inventory`, `read_locations`
|
||||
- Orders: `read_orders`, `write_orders` (30 most recent without `read_all_orders`)
|
||||
- Customers: `read_customers`, `write_customers`
|
||||
- Draft orders: `read_draft_orders`, `write_draft_orders`
|
||||
- Fulfillments: `read_fulfillments`, `write_fulfillments`
|
||||
- Metafields / metaobjects: covered by the matching resource scopes
|
||||
|
||||
## API Basics
|
||||
|
||||
- **Endpoint:** `https://$SHOPIFY_STORE_DOMAIN/admin/api/$SHOPIFY_API_VERSION/graphql.json`
|
||||
- **Auth header:** `X-Shopify-Access-Token: $SHOPIFY_ACCESS_TOKEN` (NOT `Authorization: Bearer`)
|
||||
- **Method:** always `POST`, always `Content-Type: application/json`, body is `{"query": "...", "variables": {...}}`
|
||||
- **HTTP 200 does not mean success.** GraphQL returns errors in a top-level `errors` array and per-field `userErrors`. Always check both.
|
||||
- **IDs are GID strings:** `gid://shopify/Product/10079467700516`, `gid://shopify/Variant/...`, `gid://shopify/Order/...`. Pass these verbatim — don't strip the prefix.
|
||||
- **Rate limit:** calculated via query cost (leaky bucket). Each response has `extensions.cost` with `requestedQueryCost`, `actualQueryCost`, `throttleStatus.{currentlyAvailable, maximumAvailable, restoreRate}`. Back off when `currentlyAvailable` drops below your next query's cost. Standard shops = 100 points bucket, 50/s restore; Plus = 1000/100.
|
||||
|
||||
Base curl pattern (reusable):
|
||||
|
||||
```bash
|
||||
shop_gql() {
|
||||
local query="$1"
|
||||
local variables="${2:-{}}"
|
||||
curl -sS -X POST \
|
||||
"https://${SHOPIFY_STORE_DOMAIN}/admin/api/${SHOPIFY_API_VERSION:-2026-01}/graphql.json" \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "X-Shopify-Access-Token: ${SHOPIFY_ACCESS_TOKEN}" \
|
||||
--data "$(jq -nc --arg q "$query" --argjson v "$variables" '{query: $q, variables: $v}')"
|
||||
}
|
||||
```
|
||||
|
||||
Pipe through `jq` for readable output. `-sS` keeps errors visible but hides the progress bar.
|
||||
|
||||
## Discovery
|
||||
|
||||
### Shop info + current API version
|
||||
```bash
|
||||
shop_gql '{ shop { name myshopifyDomain primaryDomain { url } currencyCode plan { displayName } } }' | jq
|
||||
```
|
||||
|
||||
### List all supported API versions
|
||||
```bash
|
||||
shop_gql '{ publicApiVersions { handle supported } }' | jq '.data.publicApiVersions[] | select(.supported)'
|
||||
```
|
||||
|
||||
## Products
|
||||
|
||||
### Search products (first 20 matching query)
|
||||
```bash
|
||||
shop_gql '
|
||||
query($q: String!) {
|
||||
products(first: 20, query: $q) {
|
||||
edges { node { id title handle status totalInventory variants(first: 5) { edges { node { id sku price inventoryQuantity } } } } }
|
||||
pageInfo { hasNextPage endCursor }
|
||||
}
|
||||
}' '{"q":"hoodie status:active"}' | jq
|
||||
```
|
||||
|
||||
Query syntax supports `title:`, `sku:`, `vendor:`, `product_type:`, `status:active`, `tag:`, `created_at:>2025-01-01`. Full grammar: https://shopify.dev/docs/api/usage/search-syntax
|
||||
|
||||
### Paginate products (cursor)
|
||||
```bash
|
||||
shop_gql '
|
||||
query($cursor: String) {
|
||||
products(first: 100, after: $cursor) {
|
||||
edges { cursor node { id handle } }
|
||||
pageInfo { hasNextPage endCursor }
|
||||
}
|
||||
}' '{"cursor":null}'
|
||||
# subsequent calls: pass the previous endCursor
|
||||
```
|
||||
|
||||
### Get a product with variants + metafields
|
||||
```bash
|
||||
shop_gql '
|
||||
query($id: ID!) {
|
||||
product(id: $id) {
|
||||
id title handle descriptionHtml tags status
|
||||
variants(first: 20) { edges { node { id sku price compareAtPrice inventoryQuantity selectedOptions { name value } } } }
|
||||
metafields(first: 20) { edges { node { namespace key type value } } }
|
||||
}
|
||||
}' '{"id":"gid://shopify/Product/10079467700516"}' | jq
|
||||
```
|
||||
|
||||
### Create a product with one variant
|
||||
```bash
|
||||
shop_gql '
|
||||
mutation($input: ProductCreateInput!) {
|
||||
productCreate(product: $input) {
|
||||
product { id handle }
|
||||
userErrors { field message }
|
||||
}
|
||||
}' '{"input":{"title":"Test Hoodie","status":"DRAFT","vendor":"Hermes","productType":"Apparel","tags":["test"]}}'
|
||||
```
|
||||
|
||||
Variants now have their own mutations in recent versions:
|
||||
|
||||
```bash
|
||||
# Add variants after creating the product
|
||||
shop_gql '
|
||||
mutation($productId: ID!, $variants: [ProductVariantsBulkInput!]!) {
|
||||
productVariantsBulkCreate(productId: $productId, variants: $variants) {
|
||||
productVariants { id sku price }
|
||||
userErrors { field message }
|
||||
}
|
||||
}' '{"productId":"gid://shopify/Product/...","variants":[{"optionValues":[{"optionName":"Size","name":"M"}],"price":"49.00","inventoryItem":{"sku":"HD-M","tracked":true}}]}'
|
||||
```
|
||||
|
||||
### Update price / SKU
|
||||
```bash
|
||||
shop_gql '
|
||||
mutation($productId: ID!, $variants: [ProductVariantsBulkInput!]!) {
|
||||
productVariantsBulkUpdate(productId: $productId, variants: $variants) {
|
||||
productVariants { id sku price }
|
||||
userErrors { field message }
|
||||
}
|
||||
}' '{"productId":"gid://shopify/Product/...","variants":[{"id":"gid://shopify/ProductVariant/...","price":"55.00"}]}'
|
||||
```
|
||||
|
||||
## Orders
|
||||
|
||||
### List recent orders (last 30 by default without `read_all_orders`)
|
||||
```bash
|
||||
shop_gql '
|
||||
{
|
||||
orders(first: 20, reverse: true, query: "financial_status:paid") {
|
||||
edges { node {
|
||||
id name createdAt displayFinancialStatus displayFulfillmentStatus
|
||||
totalPriceSet { shopMoney { amount currencyCode } }
|
||||
customer { id displayName email }
|
||||
lineItems(first: 10) { edges { node { title quantity sku } } }
|
||||
} }
|
||||
}
|
||||
}' | jq
|
||||
```
|
||||
|
||||
Useful order query filters: `financial_status:paid|pending|refunded`, `fulfillment_status:unfulfilled|fulfilled`, `created_at:>2025-01-01`, `tag:gift`, `email:foo@example.com`.
|
||||
|
||||
### Fetch a single order with shipping address
|
||||
```bash
|
||||
shop_gql '
|
||||
query($id: ID!) {
|
||||
order(id: $id) {
|
||||
id name email
|
||||
shippingAddress { name address1 address2 city province country zip phone }
|
||||
lineItems(first: 50) { edges { node { title quantity variant { sku } originalUnitPriceSet { shopMoney { amount currencyCode } } } } }
|
||||
transactions { id kind status amountSet { shopMoney { amount currencyCode } } }
|
||||
}
|
||||
}' '{"id":"gid://shopify/Order/...."}' | jq
|
||||
```
|
||||
|
||||
## Customers
|
||||
|
||||
```bash
|
||||
# Search
|
||||
shop_gql '
|
||||
{
|
||||
customers(first: 10, query: "email:*@example.com") {
|
||||
edges { node { id email displayName numberOfOrders amountSpent { amount currencyCode } } }
|
||||
}
|
||||
}'
|
||||
|
||||
# Create
|
||||
shop_gql '
|
||||
mutation($input: CustomerInput!) {
|
||||
customerCreate(input: $input) {
|
||||
customer { id email }
|
||||
userErrors { field message }
|
||||
}
|
||||
}' '{"input":{"email":"test@example.com","firstName":"Test","lastName":"User","tags":["api-created"]}}'
|
||||
```
|
||||
|
||||
## Inventory
|
||||
|
||||
Inventory lives on **inventory items** tied to variants, quantities tracked per **location**.
|
||||
|
||||
```bash
|
||||
# Get inventory for a variant across all locations
|
||||
shop_gql '
|
||||
query($id: ID!) {
|
||||
productVariant(id: $id) {
|
||||
id sku
|
||||
inventoryItem {
|
||||
id tracked
|
||||
inventoryLevels(first: 10) {
|
||||
edges { node { location { id name } quantities(names: ["available","on_hand","committed"]) { name quantity } } }
|
||||
}
|
||||
}
|
||||
}
|
||||
}' '{"id":"gid://shopify/ProductVariant/..."}'
|
||||
```
|
||||
|
||||
Adjust stock (delta) — uses `inventoryAdjustQuantities`:
|
||||
|
||||
```bash
|
||||
shop_gql '
|
||||
mutation($input: InventoryAdjustQuantitiesInput!) {
|
||||
inventoryAdjustQuantities(input: $input) {
|
||||
inventoryAdjustmentGroup { reason changes { name delta } }
|
||||
userErrors { field message }
|
||||
}
|
||||
}' '{
|
||||
"input": {
|
||||
"reason": "correction",
|
||||
"name": "available",
|
||||
"changes": [{"delta": 5, "inventoryItemId": "gid://shopify/InventoryItem/...", "locationId": "gid://shopify/Location/..."}]
|
||||
}
|
||||
}'
|
||||
```
|
||||
|
||||
Set absolute stock (not delta) — `inventorySetQuantities`:
|
||||
|
||||
```bash
|
||||
shop_gql '
|
||||
mutation($input: InventorySetQuantitiesInput!) {
|
||||
inventorySetQuantities(input: $input) {
|
||||
inventoryAdjustmentGroup { id }
|
||||
userErrors { field message }
|
||||
}
|
||||
}' '{"input":{"reason":"correction","name":"available","ignoreCompareQuantity":true,"quantities":[{"inventoryItemId":"gid://shopify/InventoryItem/...","locationId":"gid://shopify/Location/...","quantity":100}]}}'
|
||||
```
|
||||
|
||||
## Metafields & Metaobjects
|
||||
|
||||
Metafields attach custom data to resources (products, customers, orders, shop).
|
||||
|
||||
```bash
|
||||
# Read
|
||||
shop_gql '
|
||||
query($id: ID!) {
|
||||
product(id: $id) {
|
||||
metafields(first: 10, namespace: "custom") {
|
||||
edges { node { key type value } }
|
||||
}
|
||||
}
|
||||
}' '{"id":"gid://shopify/Product/..."}'
|
||||
|
||||
# Write (works for any owner type)
|
||||
shop_gql '
|
||||
mutation($metafields: [MetafieldsSetInput!]!) {
|
||||
metafieldsSet(metafields: $metafields) {
|
||||
metafields { id key namespace }
|
||||
userErrors { field message code }
|
||||
}
|
||||
}' '{"metafields":[{"ownerId":"gid://shopify/Product/...","namespace":"custom","key":"care_instructions","type":"multi_line_text_field","value":"Wash cold. Tumble dry low."}]}'
|
||||
```
|
||||
|
||||
## Storefront API (public read-only)
|
||||
|
||||
Different endpoint, different token, used for customer-facing apps/hydrogen-style headless setups. Headers differ:
|
||||
|
||||
- **Endpoint:** `https://$SHOPIFY_STORE_DOMAIN/api/$SHOPIFY_API_VERSION/graphql.json`
|
||||
- **Auth header (public):** `X-Shopify-Storefront-Access-Token: <public token>` — embeddable in browser
|
||||
- **Auth header (private):** `Shopify-Storefront-Private-Token: <private token>` — server-only
|
||||
|
||||
```bash
|
||||
curl -sS -X POST \
|
||||
"https://${SHOPIFY_STORE_DOMAIN}/api/${SHOPIFY_API_VERSION:-2026-01}/graphql.json" \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "X-Shopify-Storefront-Access-Token: ${SHOPIFY_STOREFRONT_TOKEN}" \
|
||||
-d '{"query":"{ shop { name } products(first: 5) { edges { node { id title handle } } } }"}' | jq
|
||||
```
|
||||
|
||||
## Bulk Operations
|
||||
|
||||
For dumps larger than rate limits allow (full product catalog, all orders for a year):
|
||||
|
||||
```bash
|
||||
# 1. Start bulk query
|
||||
shop_gql '
|
||||
mutation {
|
||||
bulkOperationRunQuery(query: """
|
||||
{ products { edges { node { id title handle variants { edges { node { sku price } } } } } } }
|
||||
""") {
|
||||
bulkOperation { id status }
|
||||
userErrors { field message }
|
||||
}
|
||||
}'
|
||||
|
||||
# 2. Poll status
|
||||
shop_gql '{ currentBulkOperation { id status errorCode objectCount fileSize url partialDataUrl } }'
|
||||
|
||||
# 3. When status=COMPLETED, download the JSONL file
|
||||
curl -sS "$URL" > products.jsonl
|
||||
```
|
||||
|
||||
Each JSONL line is a node, and nested connections are emitted as separate lines with `__parentId`. Reassemble client-side if needed.
|
||||
|
||||
## Webhooks
|
||||
|
||||
Subscribe to events so you don't have to poll:
|
||||
|
||||
```bash
|
||||
shop_gql '
|
||||
mutation($topic: WebhookSubscriptionTopic!, $sub: WebhookSubscriptionInput!) {
|
||||
webhookSubscriptionCreate(topic: $topic, webhookSubscription: $sub) {
|
||||
webhookSubscription { id topic endpoint { __typename ... on WebhookHttpEndpoint { callbackUrl } } }
|
||||
userErrors { field message }
|
||||
}
|
||||
}' '{"topic":"ORDERS_CREATE","sub":{"callbackUrl":"https://example.com/webhook","format":"JSON"}}'
|
||||
```
|
||||
|
||||
Verify incoming webhook HMAC using the app's client secret (not the access token):
|
||||
|
||||
```bash
|
||||
echo -n "$REQUEST_BODY" | openssl dgst -sha256 -hmac "$APP_SECRET" -binary | base64
|
||||
# Compare to X-Shopify-Hmac-Sha256 header
|
||||
```
|
||||
|
||||
## Pitfalls
|
||||
|
||||
- **REST endpoints still exist but are frozen.** Don't write new integrations against `/admin/api/.../products.json`. Use GraphQL.
|
||||
- **Token format check.** Admin tokens start with `shpat_`. Storefront public tokens with `shpua_`. If you have one and the wrong header, every request returns 401 without a useful error body.
|
||||
- **403 with a valid token = missing scope.** Shopify returns `{"errors":[{"message":"Access denied for ..."}]}`. Re-configure Admin API scopes on the app, then reinstall to regenerate the token.
|
||||
- **`userErrors` is empty != success.** Also check `data.<mutation>.<resource>` is non-null. Some failures populate neither — inspect the whole response.
|
||||
- **GID vs numeric ID.** Legacy REST gave numeric IDs; GraphQL wants full GID strings. To convert: `gid://shopify/Product/<numeric>`.
|
||||
- **Rate limit surprise.** A single `products(first: 250)` with deep nesting can cost 1000+ points and throttle immediately on a standard-plan shop. Start narrow, read `extensions.cost`, adjust.
|
||||
- **Pagination order.** `products(first: N, reverse: true)` sorts by `id DESC`, not `created_at`. Use `sortKey: CREATED_AT, reverse: true` for "newest first."
|
||||
- **`read_all_orders` for historical data.** Without it, `orders(...)` silently caps at the 60-day window. You won't get an error, just fewer results than expected. For Shopify Plus merchants with many orders, request this scope via the app's protected-data settings.
|
||||
- **Currencies are strings.** Amounts come back as `"49.00"` not `49.0`. Don't `jq tonumber` blindly if you care about zero-padding.
|
||||
- **Multi-currency Money fields** have `shopMoney` (store's currency) AND `presentmentMoney` (customer's). Pick one consistently.
|
||||
|
||||
## Safety
|
||||
|
||||
Mutations in Shopify are real — they create products, charge refunds, cancel orders, ship fulfillments. Before running `productDelete`, `orderCancel`, `refundCreate`, or any bulk mutation: state clearly what the change is, on which shop, and confirm with the user. There is no staging clone of production data unless the user has a separate dev store.
|
||||
@@ -43,7 +43,7 @@ class NodeServer:
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
host: str = "127.0.0.1",
|
||||
host: str = "0.0.0.0",
|
||||
port: int = 18789,
|
||||
token_path: Optional[Path] = None,
|
||||
display_name: str = "hermes-meet-node",
|
||||
@@ -76,13 +76,6 @@ class NodeServer:
|
||||
json.dumps({"token": tok, "generated_at": time.time()}, indent=2),
|
||||
encoding="utf-8",
|
||||
)
|
||||
# Restrict to owner-read-write only — the token grants full RPC
|
||||
# access to the meet bot (start, transcribe, speak in meetings).
|
||||
try:
|
||||
tmp.chmod(0o600)
|
||||
except (OSError, NotImplementedError):
|
||||
# Best-effort on non-POSIX filesystems; mode is set on POSIX.
|
||||
pass
|
||||
tmp.replace(self.token_path)
|
||||
self._token = tok
|
||||
return tok
|
||||
|
||||
@@ -12,14 +12,6 @@ import time
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional, Set
|
||||
|
||||
try:
|
||||
from hermes_constants import get_hermes_home
|
||||
except ImportError:
|
||||
import os as _os
|
||||
def get_hermes_home() -> Path: # type: ignore[misc]
|
||||
val = (_os.environ.get("HERMES_HOME") or "").strip()
|
||||
return Path(val) if val else Path.home() / ".hermes"
|
||||
|
||||
try:
|
||||
from fastapi import APIRouter
|
||||
except Exception: # Allows local unit tests without dashboard dependencies.
|
||||
@@ -143,15 +135,15 @@ ACHIEVEMENTS: List[Dict[str, Any]] = [
|
||||
|
||||
|
||||
def state_path() -> Path:
|
||||
return get_hermes_home() / "plugins" / "hermes-achievements" / "state.json"
|
||||
return Path.home() / ".hermes" / "plugins" / "hermes-achievements" / "state.json"
|
||||
|
||||
|
||||
def snapshot_path() -> Path:
|
||||
return get_hermes_home() / "plugins" / "hermes-achievements" / "scan_snapshot.json"
|
||||
return Path.home() / ".hermes" / "plugins" / "hermes-achievements" / "scan_snapshot.json"
|
||||
|
||||
|
||||
def checkpoint_path() -> Path:
|
||||
return get_hermes_home() / "plugins" / "hermes-achievements" / "scan_checkpoint.json"
|
||||
return Path.home() / ".hermes" / "plugins" / "hermes-achievements" / "scan_checkpoint.json"
|
||||
|
||||
|
||||
def load_state() -> Dict[str, Any]:
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user