Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 teknium1
|
872211b258 |
@@ -29,13 +29,9 @@ runs:
|
||||
- name: hermes --help
|
||||
shell: bash
|
||||
run: |
|
||||
# Use the image's real ENTRYPOINT (/init + main-wrapper.sh) so
|
||||
# this exercises the actual production startup path. PR #30136
|
||||
# review caught that an --entrypoint override here had been
|
||||
# silently neutered by the s6-overlay migration — stage2-hook
|
||||
# ignores its CMD args, so the smoke test was a no-op.
|
||||
docker run --rm \
|
||||
-v /tmp/hermes-test:/opt/data \
|
||||
--entrypoint /opt/hermes/docker/entrypoint.sh \
|
||||
"${{ inputs.image }}" --help
|
||||
|
||||
- name: hermes dashboard --help
|
||||
@@ -47,4 +43,5 @@ runs:
|
||||
# installed package.
|
||||
docker run --rm \
|
||||
-v /tmp/hermes-test:/opt/data \
|
||||
--entrypoint /opt/hermes/docker/entrypoint.sh \
|
||||
"${{ inputs.image }}" dashboard --help
|
||||
|
||||
@@ -11,6 +11,13 @@ runs:
|
||||
using: composite
|
||||
steps:
|
||||
- uses: DeterminateSystems/nix-installer-action@ef8a148080ab6020fd15196c2084a2eea5ff2d25 # v22
|
||||
with:
|
||||
# Authenticate api.github.com tarball fetches so transitive flake inputs
|
||||
# (e.g. nix-community/pyproject.nix pinned via uv2nix/build-system-pkgs)
|
||||
# don't hit anonymous 401/rate-limit errors. GITHUB_TOKEN is auto-issued
|
||||
# per workflow run and scoped read-only for fork PRs.
|
||||
extra-conf: |
|
||||
access-tokens = github.com=${{ github.token }}
|
||||
- uses: cachix/cachix-action@1eb2ef646ac0255473d23a5907ad7b04ce94065c # v17
|
||||
with:
|
||||
name: hermes-agent
|
||||
|
||||
@@ -1,68 +0,0 @@
|
||||
name: Docker / shell lint
|
||||
|
||||
# Lints the container build inputs: Dockerfile (via hadolint) and any shell
|
||||
# scripts under docker/ (via shellcheck). These catch the class of regression
|
||||
# the behavioral docker-publish smoke test can't — unquoted variable
|
||||
# expansions, silently-failing RUN commands, etc.
|
||||
#
|
||||
# Rules and ignores are documented in .hadolint.yaml at the repo root.
|
||||
# shellcheck severity is pinned to `error` so SC1091-style "can't follow
|
||||
# sourced script" info-level warnings don't fail the job — the .venv
|
||||
# activate script doesn't exist at lint time.
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
paths:
|
||||
- Dockerfile
|
||||
- docker/**
|
||||
- .hadolint.yaml
|
||||
- .github/workflows/docker-lint.yml
|
||||
pull_request:
|
||||
branches: [main]
|
||||
paths:
|
||||
- Dockerfile
|
||||
- docker/**
|
||||
- .hadolint.yaml
|
||||
- .github/workflows/docker-lint.yml
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
concurrency:
|
||||
group: docker-lint-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
hadolint:
|
||||
name: Lint Dockerfile (hadolint)
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 5
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
|
||||
- name: hadolint
|
||||
uses: hadolint/hadolint-action@54c9adbab1582c2ef04b2016b760714a4bfde3cf # v3.1.0
|
||||
with:
|
||||
dockerfile: Dockerfile
|
||||
config: .hadolint.yaml
|
||||
failure-threshold: warning
|
||||
|
||||
shellcheck:
|
||||
name: Lint docker/ shell scripts (shellcheck)
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 5
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
|
||||
- name: shellcheck
|
||||
uses: ludeeus/action-shellcheck@00cae500b08a931fb5698e11e79bfbd38e612a38 # v2.0.0
|
||||
env:
|
||||
# Severity = error: SC1091 (can't follow sourced script) is info-
|
||||
# level and would otherwise fail when the venv activate script
|
||||
# doesn't exist at lint time.
|
||||
SHELLCHECK_OPTS: --severity=error
|
||||
with:
|
||||
scandir: ./docker
|
||||
@@ -80,56 +80,6 @@ jobs:
|
||||
with:
|
||||
image: ${{ env.IMAGE_NAME }}:test
|
||||
|
||||
# ---------------------------------------------------------------------
|
||||
# Run the docker-integration test suite against the freshly-built
|
||||
# image already loaded into the local daemon (`:test`). These tests
|
||||
# are excluded from the sharded `tests.yml :: test` matrix on purpose
|
||||
# (see `_SKIP_PARTS` in scripts/run_tests_parallel.py) because each
|
||||
# shard would otherwise reach the session-scoped ``built_image``
|
||||
# fixture in ``tests/docker/conftest.py`` and start a 3-7min
|
||||
# ``docker build`` under a 180s pytest-timeout cap — guaranteed to
|
||||
# die in fixture setup.
|
||||
#
|
||||
# Piggybacking here avoids a second image build: the smoke test
|
||||
# already proved the image loads + runs, so the daemon has it under
|
||||
# `${IMAGE_NAME}:test` and we just point ``HERMES_TEST_IMAGE`` at
|
||||
# that. The fixture's ``HERMES_TEST_IMAGE`` branch (see
|
||||
# tests/docker/conftest.py:62-63) short-circuits the rebuild.
|
||||
#
|
||||
# Why this job and not a standalone one: the image is 5GB+; passing
|
||||
# it between jobs via ``docker save``/``upload-artifact`` is slower
|
||||
# than the build itself. Reusing the existing daemon state is the
|
||||
# cheapest path to coverage on every PR that touches docker code.
|
||||
# ---------------------------------------------------------------------
|
||||
- name: Install uv (for docker tests)
|
||||
uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86 # v5
|
||||
|
||||
- name: Set up Python 3.11 (for docker tests)
|
||||
run: uv python install 3.11
|
||||
|
||||
- name: Install Python dependencies (for docker tests)
|
||||
run: |
|
||||
uv venv .venv --python 3.11
|
||||
source .venv/bin/activate
|
||||
# ``dev`` extra pulls in pytest, pytest-asyncio, pytest-timeout —
|
||||
# everything tests/docker/ needs. We deliberately avoid ``all``
|
||||
# here because the docker tests only drive the container via
|
||||
# subprocess and don't import hermes_agent's optional deps.
|
||||
uv pip install -e ".[dev]"
|
||||
|
||||
- name: Run docker integration tests
|
||||
env:
|
||||
# Skip rebuild; use the image already loaded by the build step.
|
||||
HERMES_TEST_IMAGE: ${{ env.IMAGE_NAME }}:test
|
||||
# Match the policy in tests.yml :: test job — no accidental
|
||||
# real-API calls from inside the harness.
|
||||
OPENROUTER_API_KEY: ""
|
||||
OPENAI_API_KEY: ""
|
||||
NOUS_API_KEY: ""
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pytest tests/docker/ -v --tb=short
|
||||
|
||||
- name: Log in to Docker Hub
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
|
||||
uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4.1.0
|
||||
|
||||
@@ -1,36 +0,0 @@
|
||||
# hadolint configuration for the Hermes Agent Dockerfile.
|
||||
# See https://github.com/hadolint/hadolint#configure for rules.
|
||||
#
|
||||
# We want hadolint to surface NEW Dockerfile lint regressions, but we
|
||||
# don't want to rewrite the existing image to silence rules that are
|
||||
# either intentional or pragmatic tradeoffs for this project. Each
|
||||
# ignore below has a one-line justification.
|
||||
failure-threshold: warning
|
||||
|
||||
ignored:
|
||||
# Pin versions in apt get install. We intentionally don't pin common
|
||||
# tools (curl, git, openssh-client, etc.) — security updates flow in
|
||||
# via the periodic base-image rebuild, and pinning would lock us to
|
||||
# superseded patch releases. Same rationale as nearly every distro-
|
||||
# base official image (python, node, debian).
|
||||
- DL3008
|
||||
# Use WORKDIR to switch to a directory. The image uses `(cd web && …)`
|
||||
# / `(cd ../ui-tui && …)` inline subshells for one-off build steps
|
||||
# because they don't affect later RUN commands; promoting them to
|
||||
# full WORKDIR switches with restores would obscure intent.
|
||||
- DL3003
|
||||
# Multiple consecutive RUN instructions. The `touch README.md` + `uv
|
||||
# sync` split is intentional — `touch` is cheap, `uv sync` is the
|
||||
# expensive layer-cached step we want isolated, and merging them
|
||||
# would invalidate the cache for trivial changes.
|
||||
- DL3059
|
||||
# Last USER should not be root. /init (s6-overlay) runs as root so the
|
||||
# stage2 hook can usermod/groupmod and chown the data volume per
|
||||
# HERMES_UID at runtime; each supervised service then drops to the
|
||||
# hermes user via `s6-setuidgid`.
|
||||
- DL3002
|
||||
|
||||
# Require explicit base-image pins (SHA256) — we already do this.
|
||||
trustedRegistries:
|
||||
- docker.io
|
||||
- ghcr.io
|
||||
+10
-114
@@ -1,4 +1,5 @@
|
||||
FROM ghcr.io/astral-sh/uv:0.11.6-python3.13-trixie@sha256:b3c543b6c4f23a5f2df22866bd7857e5d304b67a564f4feab6ac22044dde719b AS uv_source
|
||||
FROM tianon/gosu:1.19-trixie@sha256:3b176695959c71e123eb390d427efc665eeb561b1540e82679c15e992006b8b9 AS gosu_source
|
||||
FROM debian:13.4
|
||||
|
||||
# Disable Python stdout buffering to ensure logs are printed immediately
|
||||
@@ -8,68 +9,18 @@ ENV PYTHONUNBUFFERED=1
|
||||
# install survives the /opt/data volume overlay at runtime.
|
||||
ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
|
||||
|
||||
# Install system dependencies in one layer, clear APT cache.
|
||||
# tini was previously PID 1 to reap orphaned zombie processes (MCP stdio
|
||||
# subprocesses, git, bun, etc.) that would otherwise accumulate when hermes
|
||||
# ran as PID 1. See #15012. Phase 2 of the s6-overlay supervision plan
|
||||
# replaces tini with s6-overlay's /init (PID 1 = s6-svscan), which reaps
|
||||
# zombies non-blockingly on SIGCHLD and additionally supervises the main
|
||||
# hermes process, the dashboard, and per-profile gateways.
|
||||
# Install system dependencies in one layer, clear APT cache
|
||||
# tini reaps orphaned zombie processes (MCP stdio subprocesses, git, bun, etc.)
|
||||
# that would otherwise accumulate when hermes runs as PID 1. See #15012.
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
build-essential curl nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli xz-utils && \
|
||||
build-essential curl nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli tini && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# ---------- s6-overlay install ----------
|
||||
# s6-overlay provides supervision for the main hermes process, the dashboard,
|
||||
# and per-profile gateways. /init becomes PID 1 below — see ENTRYPOINT.
|
||||
#
|
||||
# Multi-arch: BuildKit auto-populates TARGETARCH (amd64 / arm64). s6-overlay
|
||||
# uses tarball names keyed on the kernel arch string (x86_64 / aarch64), so
|
||||
# we map between them inline. The noarch + symlinks tarballs are
|
||||
# architecture-independent and reused as-is.
|
||||
#
|
||||
# We use `curl` instead of `ADD` for the per-arch tarball because `ADD`
|
||||
# evaluates its URL at parse time, before any ARG / TARGETARCH substitution
|
||||
# — splitting one URL per arch into two ADDs would download both on every
|
||||
# build and leave dead bytes in the cache. A single curl + arch-keyed URL
|
||||
# is simpler and cache-friendlier.
|
||||
#
|
||||
# Supply-chain integrity: every tarball is checksum-verified against the
|
||||
# upstream-published SHA256. To bump S6_OVERLAY_VERSION, fetch the four
|
||||
# `.sha256` files from the corresponding release and update the ARGs. The
|
||||
# checksum lookup happens during build, so a compromised release artifact
|
||||
# fails the build loudly instead of silently producing a tampered image.
|
||||
ARG TARGETARCH
|
||||
ARG S6_OVERLAY_VERSION=3.2.3.0
|
||||
ARG S6_OVERLAY_NOARCH_SHA256=b720f9d9340efc8bb07528b9743813c836e4b02f8693d90241f047998b4c53cf
|
||||
ARG S6_OVERLAY_X86_64_SHA256=a93f02882c6ed46b21e7adb5c0add86154f01236c93cd82c7d682722e8840563
|
||||
ARG S6_OVERLAY_AARCH64_SHA256=0952056ff913482163cc30e35b2e944b507ba1025d78f5becbb89367bf344581
|
||||
ARG S6_OVERLAY_SYMLINKS_SHA256=a60dc5235de3ecbcf874b9c1f18d73263ab99b289b9329aa950e8729c4789f0e
|
||||
ADD https://github.com/just-containers/s6-overlay/releases/download/v${S6_OVERLAY_VERSION}/s6-overlay-noarch.tar.xz /tmp/
|
||||
ADD https://github.com/just-containers/s6-overlay/releases/download/v${S6_OVERLAY_VERSION}/s6-overlay-symlinks-noarch.tar.xz /tmp/
|
||||
RUN set -eu; \
|
||||
case "${TARGETARCH:-amd64}" in \
|
||||
amd64) s6_arch="x86_64"; s6_arch_sha="${S6_OVERLAY_X86_64_SHA256}" ;; \
|
||||
arm64) s6_arch="aarch64"; s6_arch_sha="${S6_OVERLAY_AARCH64_SHA256}" ;; \
|
||||
*) echo "Unsupported TARGETARCH=${TARGETARCH} for s6-overlay" >&2; exit 1 ;; \
|
||||
esac; \
|
||||
curl -fsSL --retry 3 -o /tmp/s6-overlay-arch.tar.xz \
|
||||
"https://github.com/just-containers/s6-overlay/releases/download/v${S6_OVERLAY_VERSION}/s6-overlay-${s6_arch}.tar.xz"; \
|
||||
{ \
|
||||
printf '%s %s\n' "${S6_OVERLAY_NOARCH_SHA256}" /tmp/s6-overlay-noarch.tar.xz; \
|
||||
printf '%s %s\n' "${s6_arch_sha}" /tmp/s6-overlay-arch.tar.xz; \
|
||||
printf '%s %s\n' "${S6_OVERLAY_SYMLINKS_SHA256}" /tmp/s6-overlay-symlinks-noarch.tar.xz; \
|
||||
} > /tmp/s6-overlay.sha256; \
|
||||
sha256sum -c /tmp/s6-overlay.sha256; \
|
||||
tar -C / -Jxpf /tmp/s6-overlay-noarch.tar.xz; \
|
||||
tar -C / -Jxpf /tmp/s6-overlay-arch.tar.xz; \
|
||||
tar -C / -Jxpf /tmp/s6-overlay-symlinks-noarch.tar.xz; \
|
||||
rm /tmp/s6-overlay-*.tar.xz /tmp/s6-overlay.sha256
|
||||
|
||||
# Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
|
||||
RUN useradd -u 10000 -m -d /opt/data hermes
|
||||
|
||||
COPY --chmod=0755 --from=gosu_source /gosu /usr/local/bin/
|
||||
COPY --chmod=0755 --from=uv_source /usr/local/bin/uv /usr/local/bin/uvx /usr/local/bin/
|
||||
|
||||
WORKDIR /opt/hermes
|
||||
@@ -152,73 +103,18 @@ RUN cd web && npm run build && \
|
||||
USER root
|
||||
RUN chmod -R a+rX /opt/hermes && \
|
||||
chown -R hermes:hermes /opt/hermes/.venv /opt/hermes/ui-tui /opt/hermes/node_modules
|
||||
# Start as root so the s6-overlay stage2 hook can usermod/groupmod and chown
|
||||
# the data volume. Each supervised service then drops to the hermes user via
|
||||
# `s6-setuidgid hermes` in its run script. If HERMES_UID is unset, services
|
||||
# run as the default hermes user (UID 10000).
|
||||
# Start as root so the entrypoint can usermod/groupmod + gosu.
|
||||
# If HERMES_UID is unset, the entrypoint drops to the default hermes user (10000).
|
||||
|
||||
# ---------- Link hermes-agent itself (editable) ----------
|
||||
# Deps are already installed in the cached layer above; `--no-deps` makes
|
||||
# this a fast (~1s) egg-link creation with no resolution or downloads.
|
||||
RUN uv pip install --no-cache-dir --no-deps -e "."
|
||||
|
||||
# ---------- s6-overlay service wiring ----------
|
||||
# Static services declared at build time: main-hermes + dashboard.
|
||||
# Per-profile gateway services are registered dynamically at runtime by
|
||||
# the profile create/delete hooks (Phase 4); they live under
|
||||
# /run/service/ (tmpfs) and are reconciled on container restart by
|
||||
# /etc/cont-init.d/02-reconcile-profiles (Phase 4 Task 4.0).
|
||||
COPY docker/s6-rc.d/ /etc/s6-overlay/s6-rc.d/
|
||||
|
||||
# stage2-hook handles UID/GID remap, volume chown, config seeding,
|
||||
# skills sync — all the work the old entrypoint.sh did before
|
||||
# `exec hermes`. Wired in as cont-init.d/01- so it
|
||||
# runs before user services start.
|
||||
#
|
||||
# 02-reconcile-profiles re-creates per-profile gateway s6 service
|
||||
# slots from $HERMES_HOME/profiles/<name>/ after a container restart
|
||||
# (the /run/service/ scandir is tmpfs and wiped on restart). Phase 4.
|
||||
RUN mkdir -p /etc/cont-init.d && \
|
||||
printf '#!/bin/sh\nexec /opt/hermes/docker/stage2-hook.sh\n' \
|
||||
> /etc/cont-init.d/01-hermes-setup && \
|
||||
chmod +x /etc/cont-init.d/01-hermes-setup
|
||||
COPY --chmod=0755 docker/cont-init.d/015-supervise-perms /etc/cont-init.d/015-supervise-perms
|
||||
COPY --chmod=0755 docker/cont-init.d/02-reconcile-profiles /etc/cont-init.d/02-reconcile-profiles
|
||||
|
||||
# ---------- Runtime ----------
|
||||
ENV HERMES_WEB_DIST=/opt/hermes/hermes_cli/web_dist
|
||||
ENV HERMES_HOME=/opt/data
|
||||
# Pre-s6 entrypoint.sh did `source .venv/bin/activate` which exported
|
||||
# the venv bin onto PATH; Architecture B's main-wrapper.sh does the
|
||||
# same for the container's main process, but `docker exec` and our
|
||||
# cont-init.d scripts don't pass through the wrapper. Expose the venv
|
||||
# bin globally so `docker exec <container> hermes ...` and any
|
||||
# subprocess that doesn't activate the venv first still find hermes.
|
||||
ENV PATH="/opt/hermes/.venv/bin:/opt/data/.local/bin:${PATH}"
|
||||
ENV PATH="/opt/data/.local/bin:${PATH}"
|
||||
RUN mkdir -p /opt/data
|
||||
VOLUME [ "/opt/data" ]
|
||||
|
||||
# s6-overlay's /init is PID 1. It sets up the supervision tree, runs
|
||||
# /etc/cont-init.d/* (our stage2 hook), starts s6-rc services
|
||||
# declared in /etc/s6-overlay/s6-rc.d/, then exec's its remaining
|
||||
# argv as the container's "main program" with stdin/stdout/stderr
|
||||
# inherited (this is what makes interactive --tui work). When the
|
||||
# main program exits, /init begins stage 3 shutdown and the container
|
||||
# exits with the program's exit code. Replaces tini — see Phase 2 of
|
||||
# docs/plans/2026-05-07-s6-overlay-dynamic-subagent-gateways.md.
|
||||
#
|
||||
# We use the ENTRYPOINT+CMD split rather than CMD alone so the
|
||||
# wrapper is prepended to user-supplied args automatically:
|
||||
#
|
||||
# docker run <image> → /init main-wrapper.sh (CMD default)
|
||||
# docker run <image> chat -q "hi" → /init main-wrapper.sh chat -q hi
|
||||
# docker run <image> sleep infinity → /init main-wrapper.sh sleep infinity
|
||||
# docker run <image> --tui → /init main-wrapper.sh --tui
|
||||
#
|
||||
# main-wrapper.sh handles arg routing (bare-exec vs. hermes
|
||||
# subcommand vs. no-args), drops to the hermes user via s6-setuidgid,
|
||||
# and exec's the final program so its exit code becomes the container
|
||||
# exit code. Without the wrapper-as-ENTRYPOINT, leading-dash args
|
||||
# like `--version` would be intercepted by /init's POSIX shell.
|
||||
ENTRYPOINT [ "/init", "/opt/hermes/docker/main-wrapper.sh" ]
|
||||
CMD [ ]
|
||||
ENTRYPOINT [ "/usr/bin/tini", "-g", "--", "/opt/hermes/docker/entrypoint.sh" ]
|
||||
|
||||
@@ -79,27 +79,6 @@ hermes doctor # Diagnose any issues
|
||||
|
||||
📖 **[Full documentation →](https://hermes-agent.nousresearch.com/docs/)**
|
||||
|
||||
---
|
||||
|
||||
## Skip the API-key collection — Nous Portal
|
||||
|
||||
Hermes works with whatever provider you want — that's not changing. But if you'd rather not collect five separate API keys for the model, web search, image generation, TTS, and a cloud browser, **[Nous Portal](https://portal.nousresearch.com)** covers all of them under one subscription:
|
||||
|
||||
- **300+ models** — pick any of them with `/model <name>`
|
||||
- **Tool Gateway** — web search (Firecrawl), image generation (FAL), text-to-speech (OpenAI), cloud browser (Browser Use), all routed through your sub. No extra accounts.
|
||||
|
||||
One command from a fresh install:
|
||||
|
||||
```bash
|
||||
hermes setup --portal
|
||||
```
|
||||
|
||||
That logs you in via OAuth, sets Nous as your provider, and turns on the Tool Gateway. Check what's wired up any time with `hermes portal status`. Full details on the [Tool Gateway docs page](https://hermes-agent.nousresearch.com/docs/user-guide/features/tool-gateway).
|
||||
|
||||
You can still bring your own keys per-tool whenever you want — the gateway is per-backend, not all-or-nothing.
|
||||
|
||||
---
|
||||
|
||||
## CLI vs Messaging Quick Reference
|
||||
|
||||
Hermes has two entry points: start the terminal UI with `hermes`, or run the gateway and talk to it from Telegram, Discord, Slack, WhatsApp, Signal, or Email. Once you're in a conversation, many slash commands are shared across both interfaces.
|
||||
|
||||
@@ -65,27 +65,6 @@ hermes doctor # 诊断问题
|
||||
|
||||
📖 **[完整文档 →](https://hermes-agent.nousresearch.com/docs/)**
|
||||
|
||||
---
|
||||
|
||||
## 省去到处收集 API Key — Nous Portal
|
||||
|
||||
Hermes 始终允许你使用任意服务商，这点不会改变。但如果你不想为模型、网页搜索、图像生成、TTS、云浏览器分别去申请五个不同的 API Key，**[Nous Portal](https://portal.nousresearch.com)** 用一个订阅就能覆盖全部：
|
||||
|
||||
- **300+ 模型** — 用 `/model <name>` 随时切换
|
||||
- **Tool Gateway** — 网页搜索（Firecrawl）、图像生成（FAL）、文本转语音（OpenAI）、云浏览器（Browser Use），全部通过订阅托管。无需额外注册任何账户。
|
||||
|
||||
全新安装时一条命令即可：
|
||||
|
||||
```bash
|
||||
hermes setup --portal
|
||||
```
|
||||
|
||||
它会通过 OAuth 登录、把 Nous 设为推理服务商，并启用 Tool Gateway。随时用 `hermes portal status` 查看路由状态。完整说明见 [Tool Gateway 文档](https://hermes-agent.nousresearch.com/docs/user-guide/features/tool-gateway)。
|
||||
|
||||
你随时可以按工具单独切回自己的 API Key — Gateway 是按工具粒度生效的，不是一刀切。
|
||||
|
||||
---
|
||||
|
||||
## CLI 与消息平台 快速对照
|
||||
|
||||
Hermes 有两种入口：用 `hermes` 启动终端 UI，或运行网关从 Telegram、Discord、Slack、WhatsApp、Signal 或 Email 与之对话。进入对话后，许多斜杠命令在两种界面中通用。
|
||||
|
||||
@@ -1534,11 +1534,7 @@ 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 or result.get("response_transformed")):
|
||||
# Deliver the final response when streaming did not already send it,
|
||||
# or when a plugin hook transformed the response after streaming
|
||||
# finished (e.g. transform_llm_output) — otherwise the appended /
|
||||
# rewritten text never reaches the client.
|
||||
if final_response and conn and not streamed_message:
|
||||
update = acp.update_agent_message_text(final_response)
|
||||
await conn.session_update(session_id, update)
|
||||
|
||||
|
||||
+8
-7
@@ -976,14 +976,16 @@ def init_agent(
|
||||
|
||||
# Expose session ID to tools (terminal, execute_code) so agents can
|
||||
# reference their own session for --resume commands, cross-session
|
||||
# coordination, and logging. Keep the ContextVar and os.environ
|
||||
# fallback synchronized because different tool paths still read both.
|
||||
# coordination, and logging. Uses the ContextVar system from
|
||||
# session_context.py for concurrency safety (gateway runs multiple
|
||||
# sessions in one process). Also writes os.environ as fallback for
|
||||
# CLI mode where ContextVars aren't used.
|
||||
os.environ["HERMES_SESSION_ID"] = agent.session_id
|
||||
try:
|
||||
from gateway.session_context import set_current_session_id
|
||||
|
||||
set_current_session_id(agent.session_id)
|
||||
from gateway.session_context import _SESSION_ID
|
||||
_SESSION_ID.set(agent.session_id)
|
||||
except Exception:
|
||||
os.environ["HERMES_SESSION_ID"] = agent.session_id
|
||||
pass # CLI/test mode — ContextVar not needed
|
||||
|
||||
# Session logs go into ~/.hermes/sessions/ alongside gateway sessions
|
||||
hermes_home = get_hermes_home()
|
||||
@@ -1427,7 +1429,6 @@ def init_agent(
|
||||
base_url=agent.base_url,
|
||||
api_key=getattr(agent, "api_key", ""),
|
||||
provider=agent.provider,
|
||||
api_mode=agent.api_mode,
|
||||
)
|
||||
if not agent.quiet_mode:
|
||||
_ra().logger.info("Using context engine: %s", _selected_engine.name)
|
||||
|
||||
@@ -132,7 +132,7 @@ def convert_to_trajectory_format(agent, messages: List[Dict[str, Any]], user_que
|
||||
except json.JSONDecodeError:
|
||||
# This shouldn't happen since we validate and retry during conversation,
|
||||
# but if it does, log warning and use empty dict
|
||||
logger.warning(f"Unexpected invalid JSON in trajectory conversion: {tool_call['function']['arguments'][:100]}")
|
||||
logging.warning(f"Unexpected invalid JSON in trajectory conversion: {tool_call['function']['arguments'][:100]}")
|
||||
arguments = {}
|
||||
|
||||
tool_call_json = {
|
||||
@@ -617,28 +617,9 @@ def recover_with_credential_pool(
|
||||
# existing entitlement keyword set in ``_is_entitlement_failure``.
|
||||
# Any 403 against ``xai-oauth`` is treated as entitlement here so
|
||||
# the refresh loop can't spin in those cases either.
|
||||
#
|
||||
# Exception (#29344): xAI's ``[WKE=unauthenticated:...]`` suffix and
|
||||
# the ``OAuth2 access token could not be validated`` phrasing are
|
||||
# xAI's authoritative "this is a stale token, not entitlement"
|
||||
# signal. When either fires we must NOT apply the catch-all
|
||||
# override — refresh is the recoverable path for these bodies, and
|
||||
# blanket-classifying them as entitlement was the bug that left
|
||||
# long-running TUI sessions stuck on stale tokens until the user
|
||||
# exited and reopened.
|
||||
is_entitlement = agent._is_entitlement_failure(error_context, status_code)
|
||||
if not is_entitlement and status_code == 403 and (agent.provider or "") == "xai-oauth":
|
||||
_disambiguator_haystack = " ".join(
|
||||
str(error_context.get(k) or "").lower()
|
||||
for k in ("message", "reason", "code", "error")
|
||||
if isinstance(error_context, dict)
|
||||
)
|
||||
_is_xai_auth_failure = (
|
||||
"[wke=unauthenticated:" in _disambiguator_haystack
|
||||
or "oauth2 access token could not be validated" in _disambiguator_haystack
|
||||
)
|
||||
if not _is_xai_auth_failure:
|
||||
is_entitlement = True
|
||||
is_entitlement = True
|
||||
if is_entitlement:
|
||||
_ra().logger.info(
|
||||
"Credential %s — entitlement-shaped 403 from %s; "
|
||||
@@ -747,7 +728,7 @@ def try_recover_primary_transport(
|
||||
time.sleep(wait_time)
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.warning("Primary transport recovery failed: %s", e)
|
||||
logging.warning("Primary transport recovery failed: %s", e)
|
||||
return False
|
||||
|
||||
# ── End provider fallback ──────────────────────────────────────────────
|
||||
@@ -910,20 +891,19 @@ def restore_primary_runtime(agent) -> bool:
|
||||
base_url=rt["compressor_base_url"],
|
||||
api_key=rt["compressor_api_key"],
|
||||
provider=rt["compressor_provider"],
|
||||
api_mode=rt.get("compressor_api_mode", ""),
|
||||
)
|
||||
|
||||
# ── Reset fallback chain for the new turn ──
|
||||
agent._fallback_activated = False
|
||||
agent._fallback_index = 0
|
||||
|
||||
logger.info(
|
||||
logging.info(
|
||||
"Primary runtime restored for new turn: %s (%s)",
|
||||
agent.model, agent.provider,
|
||||
)
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.warning("Failed to restore primary runtime: %s", e)
|
||||
logging.warning("Failed to restore primary runtime: %s", e)
|
||||
return False
|
||||
|
||||
# Which error types indicate a transient transport failure worth
|
||||
@@ -1094,7 +1074,7 @@ def dump_api_request_debug(
|
||||
return dump_file
|
||||
except Exception as dump_error:
|
||||
if agent.verbose_logging:
|
||||
logger.warning(f"Failed to dump API request debug payload: {dump_error}")
|
||||
logging.warning(f"Failed to dump API request debug payload: {dump_error}")
|
||||
return None
|
||||
|
||||
|
||||
@@ -1479,7 +1459,6 @@ def switch_model(agent, new_model, new_provider, api_key='', base_url='', api_mo
|
||||
"compressor_api_key": getattr(_cc, "api_key", "") if _cc else "",
|
||||
"compressor_provider": getattr(_cc, "provider", agent.provider) if _cc else agent.provider,
|
||||
"compressor_context_length": _cc.context_length if _cc else 0,
|
||||
"compressor_api_mode": getattr(_cc, "api_mode", agent.api_mode) if _cc else agent.api_mode,
|
||||
"compressor_threshold_tokens": _cc.threshold_tokens if _cc else 0,
|
||||
}
|
||||
if api_mode == "anthropic_messages":
|
||||
@@ -1511,7 +1490,7 @@ def switch_model(agent, new_model, new_provider, api_key='', base_url='', api_mo
|
||||
agent._fallback_chain = fallback_chain
|
||||
agent._fallback_model = fallback_chain[0] if fallback_chain else None
|
||||
|
||||
logger.info(
|
||||
logging.info(
|
||||
"Model switched in-place: %s (%s) -> %s (%s)",
|
||||
old_model, old_provider, new_model, new_provider,
|
||||
)
|
||||
|
||||
@@ -2122,13 +2122,9 @@ def build_anthropic_kwargs(
|
||||
block["text"] = text
|
||||
|
||||
# 3. Prefix tool names with mcp_ (Claude Code convention)
|
||||
# Skip names that already begin with the marker — native MCP server
|
||||
# tools (from mcp_servers: in config.yaml) are registered under their
|
||||
# full mcp_<server>_<tool> name and would double-prefix otherwise,
|
||||
# breaking round-trip registry lookup in normalize_response. GH-25255.
|
||||
if anthropic_tools:
|
||||
for tool in anthropic_tools:
|
||||
if "name" in tool and not tool["name"].startswith(_MCP_TOOL_PREFIX):
|
||||
if "name" in tool:
|
||||
tool["name"] = _MCP_TOOL_PREFIX + tool["name"]
|
||||
|
||||
# 4. Prefix tool names in message history (tool_use and tool_result blocks)
|
||||
|
||||
+2
-116
@@ -3730,37 +3730,6 @@ _VISION_AUTO_PROVIDER_ORDER = (
|
||||
)
|
||||
|
||||
|
||||
def _main_model_supports_vision(provider: str, model: Optional[str]) -> bool:
|
||||
"""Return True when ``provider``/``model`` is known to accept image input.
|
||||
|
||||
Used by the vision auto-detect chain to skip the user's main provider
|
||||
when it's known to be text-only (e.g. DeepSeek, gpt-oss without vision).
|
||||
Without this guard, ``resolve_vision_provider_client(provider="auto")``
|
||||
would happily return the main-provider client and any subsequent image
|
||||
payload would surface as a cryptic provider-side error
|
||||
(``unknown variant `image_url`, expected `text```, #31179).
|
||||
|
||||
Returns True when capability lookup is unknown — preserves the historical
|
||||
behaviour of attempting the call, so providers we haven't catalogued yet
|
||||
don't silently regress to text-only.
|
||||
"""
|
||||
try:
|
||||
from agent.image_routing import _lookup_supports_vision
|
||||
from hermes_cli.config import load_config
|
||||
except ImportError:
|
||||
return True
|
||||
try:
|
||||
supports = _lookup_supports_vision(provider, model, load_config())
|
||||
except Exception: # pragma: no cover - defensive
|
||||
return True
|
||||
if supports is None:
|
||||
# No capability data — keep current behaviour and let the call attempt
|
||||
# happen rather than silently skipping. This avoids false-positive
|
||||
# skips for new/custom providers.
|
||||
return True
|
||||
return bool(supports)
|
||||
|
||||
|
||||
def _normalize_vision_provider(provider: Optional[str]) -> str:
|
||||
return _normalize_aux_provider(provider)
|
||||
|
||||
@@ -3901,23 +3870,6 @@ def resolve_vision_provider_client(
|
||||
"vision support) — falling through to aggregator chain",
|
||||
main_provider,
|
||||
)
|
||||
elif not _main_model_supports_vision(main_provider, vision_model):
|
||||
# The main model is known to be text-only (e.g. DeepSeek V4,
|
||||
# gpt-oss-120b without vision). Building a client and sending
|
||||
# an image would produce a cryptic provider-side error like
|
||||
# ``unknown variant `image_url`, expected `text``` (#31179).
|
||||
# Fall through to the aggregator chain instead.
|
||||
#
|
||||
# Only log the provider name (not the model) — mirrors the
|
||||
# sibling _PROVIDERS_WITHOUT_VISION branch above, and avoids
|
||||
# CodeQL py/clear-text-logging-sensitive-data heuristic false
|
||||
# positives on multi-value interpolations.
|
||||
logger.debug(
|
||||
"Vision auto-detect: skipping main provider %s "
|
||||
"(reports no vision capability) — falling through to "
|
||||
"aggregator chain",
|
||||
main_provider,
|
||||
)
|
||||
else:
|
||||
rpc_client, rpc_model = resolve_provider_client(
|
||||
main_provider, vision_model,
|
||||
@@ -4329,23 +4281,6 @@ def _get_cached_client(
|
||||
return client, model or default_model
|
||||
|
||||
|
||||
# Aliases that target direct REST APIs not modeled as first-class providers
|
||||
# in PROVIDER_REGISTRY. Used for ``auxiliary.<task>.provider`` so users can
|
||||
# write the obvious name and have it resolve to a working ``custom`` endpoint
|
||||
# without needing to know our internal provider IDs.
|
||||
#
|
||||
# Why these specifically: PROVIDER_REGISTRY has ``openai-codex`` (OAuth) and
|
||||
# ``custom`` (manual base_url + OPENAI_API_KEY) but no plain ``openai`` for
|
||||
# direct API-key access. Users predictably type ``provider: openai`` and
|
||||
# expect it to use OPENAI_API_KEY against api.openai.com. Previously this
|
||||
# silently fell back to the user's main provider, sending OpenAI model names
|
||||
# to e.g. DeepSeek and producing cryptic ``unknown variant 'image_url'``
|
||||
# errors (issue #31179).
|
||||
_AUX_DIRECT_API_BASE_URLS: Dict[str, str] = {
|
||||
"openai": "https://api.openai.com/v1",
|
||||
}
|
||||
|
||||
|
||||
def _resolve_task_provider_model(
|
||||
task: str = None,
|
||||
provider: str = None,
|
||||
@@ -4382,25 +4317,6 @@ def _resolve_task_provider_model(
|
||||
resolved_model = model or cfg_model
|
||||
resolved_api_mode = cfg_api_mode
|
||||
|
||||
# Convenience aliases for direct API-key endpoints that aren't first-class
|
||||
# providers (e.g. ``provider: openai`` → custom + api.openai.com/v1).
|
||||
# Applied to both explicit args and config-derived values. When the user
|
||||
# has already supplied a base_url we keep their endpoint but still rewrite
|
||||
# the provider to ``custom`` so resolution doesn't hit the
|
||||
# PROVIDER_REGISTRY-only path (which has no ``openai`` entry).
|
||||
def _expand_direct_api_alias(prov: Optional[str], existing_base: Optional[str]) -> Tuple[Optional[str], Optional[str]]:
|
||||
if not prov:
|
||||
return prov, existing_base
|
||||
target_base = _AUX_DIRECT_API_BASE_URLS.get(prov.strip().lower())
|
||||
if target_base is None:
|
||||
return prov, existing_base
|
||||
return "custom", existing_base or target_base
|
||||
|
||||
if provider:
|
||||
provider, base_url = _expand_direct_api_alias(provider, base_url)
|
||||
if cfg_provider:
|
||||
cfg_provider, cfg_base_url = _expand_direct_api_alias(cfg_provider, cfg_base_url)
|
||||
|
||||
if base_url:
|
||||
return "custom", resolved_model, base_url, api_key, resolved_api_mode
|
||||
if provider:
|
||||
@@ -4428,17 +4344,7 @@ _DEFAULT_AUX_TIMEOUT = 30.0
|
||||
|
||||
|
||||
def _get_auxiliary_task_config(task: str) -> Dict[str, Any]:
|
||||
"""Return the config dict for auxiliary.<task>, or {} when unavailable.
|
||||
|
||||
For plugin-registered auxiliary tasks (see
|
||||
:meth:`hermes_cli.plugins.PluginContext.register_auxiliary_task`) the
|
||||
plugin's declared *defaults* are layered underneath the user's config
|
||||
so an unconfigured plugin task still works:
|
||||
|
||||
plugin defaults ← config.yaml auxiliary.<task> (user wins)
|
||||
|
||||
Built-in tasks ignore this path (their defaults live in DEFAULT_CONFIG).
|
||||
"""
|
||||
"""Return the config dict for auxiliary.<task>, or {} when unavailable."""
|
||||
if not task:
|
||||
return {}
|
||||
try:
|
||||
@@ -4448,27 +4354,7 @@ def _get_auxiliary_task_config(task: str) -> Dict[str, Any]:
|
||||
return {}
|
||||
aux = config.get("auxiliary", {}) if isinstance(config, dict) else {}
|
||||
task_config = aux.get(task, {}) if isinstance(aux, dict) else {}
|
||||
if not isinstance(task_config, dict):
|
||||
task_config = {}
|
||||
|
||||
# Layer plugin-declared defaults underneath user config so
|
||||
# ctx.register_auxiliary_task(defaults={...}) takes effect without
|
||||
# forcing the user to write config.yaml entries.
|
||||
try:
|
||||
from hermes_cli.plugins import get_plugin_auxiliary_tasks
|
||||
for _entry in get_plugin_auxiliary_tasks():
|
||||
if _entry.get("key") == task:
|
||||
_defaults = _entry.get("defaults") or {}
|
||||
if isinstance(_defaults, dict):
|
||||
merged = dict(_defaults)
|
||||
merged.update(task_config)
|
||||
return merged
|
||||
break
|
||||
except Exception:
|
||||
# Plugin discovery failure must not break aux task config reads.
|
||||
pass
|
||||
|
||||
return task_config
|
||||
return task_config if isinstance(task_config, dict) else {}
|
||||
|
||||
|
||||
def _get_task_timeout(task: str, default: float = _DEFAULT_AUX_TIMEOUT) -> float:
|
||||
|
||||
@@ -115,10 +115,7 @@ _SKILL_REVIEW_PROMPT = (
|
||||
"Protected skills (DO NOT edit these):\n"
|
||||
" • Bundled skills (shipped with Hermes, e.g. 'hermes-agent').\n"
|
||||
" • Hub-installed skills (installed via 'hermes skills install').\n"
|
||||
"Pinned skills (marked via 'hermes curator pin') CAN be improved — "
|
||||
"pin only blocks deletion/archive/consolidation by the curator, not "
|
||||
"content updates. Patch them when a pitfall or missing step turns up, "
|
||||
"same as any other agent-created skill.\n"
|
||||
" • Pinned skills (marked via 'hermes curator pin').\n"
|
||||
"If the only skills that need updating are protected, say\n"
|
||||
"'Nothing to save.' and stop.\n\n"
|
||||
"Do NOT capture (these become persistent self-imposed constraints "
|
||||
@@ -201,10 +198,7 @@ _COMBINED_REVIEW_PROMPT = (
|
||||
"Protected skills (DO NOT edit these):\n"
|
||||
" • Bundled skills (shipped with Hermes, e.g. 'hermes-agent').\n"
|
||||
" • Hub-installed skills (installed via 'hermes skills install').\n"
|
||||
"Pinned skills (marked via 'hermes curator pin') CAN be improved — "
|
||||
"pin only blocks deletion/archive/consolidation by the curator, not "
|
||||
"content updates. Patch them when a pitfall or missing step turns up, "
|
||||
"same as any other agent-created skill.\n"
|
||||
" • Pinned skills (marked via 'hermes curator pin').\n"
|
||||
"If the only skills that need updating are protected, say\n"
|
||||
"'Nothing to save.' and stop.\n\n"
|
||||
"Do NOT capture as skills (these become persistent self-imposed "
|
||||
|
||||
@@ -757,7 +757,7 @@ def try_activate_fallback(agent, reason: "FailoverReason | None" = None) -> bool
|
||||
current_base_url = str(getattr(agent, "base_url", "") or "").rstrip("/").lower()
|
||||
fb_base_url_for_dedup = (fb.get("base_url") or "").strip().rstrip("/").lower()
|
||||
if fb_provider == current_provider and fb_model == current_model:
|
||||
logger.warning(
|
||||
logging.warning(
|
||||
"Fallback skip: chain entry %s/%s matches current provider/model",
|
||||
fb_provider, fb_model,
|
||||
)
|
||||
@@ -768,7 +768,7 @@ def try_activate_fallback(agent, reason: "FailoverReason | None" = None) -> bool
|
||||
and fb_base_url_for_dedup == current_base_url
|
||||
and fb_model == current_model
|
||||
):
|
||||
logger.warning(
|
||||
logging.warning(
|
||||
"Fallback skip: chain entry base_url %s matches current backend",
|
||||
fb_base_url_for_dedup,
|
||||
)
|
||||
@@ -800,7 +800,7 @@ def try_activate_fallback(agent, reason: "FailoverReason | None" = None) -> bool
|
||||
explicit_base_url=fb_base_url_hint,
|
||||
explicit_api_key=fb_api_key_hint)
|
||||
if fb_client is None:
|
||||
logger.warning(
|
||||
logging.warning(
|
||||
"Fallback to %s failed: provider not configured",
|
||||
fb_provider)
|
||||
return agent._try_activate_fallback() # try next in chain
|
||||
@@ -940,20 +940,19 @@ def try_activate_fallback(agent, reason: "FailoverReason | None" = None) -> bool
|
||||
base_url=agent.base_url,
|
||||
api_key=getattr(agent, "api_key", ""), # callable preserved → call_llm
|
||||
provider=agent.provider,
|
||||
api_mode=agent.api_mode,
|
||||
)
|
||||
|
||||
agent._emit_status(
|
||||
f"🔄 Primary model failed — switching to fallback: "
|
||||
f"{fb_model} via {fb_provider}"
|
||||
)
|
||||
logger.info(
|
||||
logging.info(
|
||||
"Fallback activated: %s → %s (%s)",
|
||||
old_model, fb_model, fb_provider,
|
||||
)
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error("Failed to activate fallback %s: %s", fb_model, e)
|
||||
logging.error("Failed to activate fallback %s: %s", fb_model, e)
|
||||
return agent._try_activate_fallback() # try next in chain
|
||||
|
||||
|
||||
@@ -1169,7 +1168,7 @@ def handle_max_iterations(agent, messages: list, api_call_count: int) -> str:
|
||||
final_response = "I reached the iteration limit and couldn't generate a summary."
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to get summary response: {e}")
|
||||
logging.warning(f"Failed to get summary response: {e}")
|
||||
final_response = f"I reached the maximum iterations ({agent.max_iterations}) but couldn't summarize. Error: {str(e)}"
|
||||
|
||||
return final_response
|
||||
@@ -1198,12 +1197,12 @@ def cleanup_task_resources(agent, task_id: str) -> None:
|
||||
_ra().cleanup_vm(task_id)
|
||||
except Exception as e:
|
||||
if agent.verbose_logging:
|
||||
logger.warning(f"Failed to cleanup VM for task {task_id}: {e}")
|
||||
logging.warning(f"Failed to cleanup VM for task {task_id}: {e}")
|
||||
try:
|
||||
_ra().cleanup_browser(task_id)
|
||||
except Exception as e:
|
||||
if agent.verbose_logging:
|
||||
logger.warning(f"Failed to cleanup browser for task {task_id}: {e}")
|
||||
logging.warning(f"Failed to cleanup browser for task {task_id}: {e}")
|
||||
|
||||
|
||||
|
||||
@@ -2077,21 +2076,8 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
|
||||
# Streaming failed AFTER some tokens were already delivered to
|
||||
# the platform. Re-raising would let the outer retry loop make
|
||||
# a new API call, creating a duplicate message. Return a
|
||||
# partial response stub instead and let the outer loop decide:
|
||||
#
|
||||
# - text-only partials → finish_reason="length" so the
|
||||
# conversation loop persists the partial assistant content
|
||||
# and asks the model to continue from where the stream
|
||||
# died (issue #30963: partial stop misclassified as a
|
||||
# clean completion was exiting the loop with budget
|
||||
# remaining and an unfinished goal).
|
||||
#
|
||||
# - partial mid-tool-call → finish_reason="stop" stays.
|
||||
# The user-visible warning we append says "Ask me to
|
||||
# retry if you want to continue", so the agent should
|
||||
# hand control back rather than auto-retry a tool call
|
||||
# that may have side-effects.
|
||||
#
|
||||
# partial "stop" response instead so the outer loop treats this
|
||||
# turn as complete (no retry, no fallback).
|
||||
# Recover whatever content was already streamed to the user.
|
||||
# _current_streamed_assistant_text accumulates text fired
|
||||
# through _fire_stream_delta, so it has exactly what the
|
||||
@@ -2129,17 +2115,14 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
|
||||
"of text; surfaced warning to user: %s",
|
||||
_partial_names, len(_partial_text or ""), result["error"],
|
||||
)
|
||||
_stub_finish_reason = "stop"
|
||||
else:
|
||||
logger.warning(
|
||||
"Partial stream delivered before error; returning "
|
||||
"length-truncated stub with %s chars of recovered "
|
||||
"content so the loop can continue from where the "
|
||||
"stream died: %s",
|
||||
"Partial stream delivered before error; returning stub "
|
||||
"response with %s chars of recovered content to prevent "
|
||||
"duplicate messages: %s",
|
||||
len(_partial_text or ""),
|
||||
result["error"],
|
||||
)
|
||||
_stub_finish_reason = "length"
|
||||
_stub_msg = SimpleNamespace(
|
||||
role="assistant", content=_partial_text, tool_calls=None,
|
||||
reasoning_content=None,
|
||||
@@ -2148,7 +2131,7 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
|
||||
id="partial-stream-stub",
|
||||
model=getattr(agent, "model", "unknown"),
|
||||
choices=[SimpleNamespace(
|
||||
index=0, message=_stub_msg, finish_reason=_stub_finish_reason,
|
||||
index=0, message=_stub_msg, finish_reason="stop",
|
||||
)],
|
||||
usage=None,
|
||||
)
|
||||
|
||||
@@ -609,7 +609,6 @@ class ContextCompressor(ContextEngine):
|
||||
"""Update tracked token usage from API response."""
|
||||
self.last_prompt_tokens = usage.get("prompt_tokens", 0)
|
||||
self.last_completion_tokens = usage.get("completion_tokens", 0)
|
||||
self.last_total_tokens = usage.get("total_tokens", self.last_prompt_tokens + self.last_completion_tokens)
|
||||
|
||||
def should_compress(self, prompt_tokens: int = None) -> bool:
|
||||
"""Check if context exceeds the compression threshold.
|
||||
@@ -898,7 +897,7 @@ class ContextCompressor(ContextEngine):
|
||||
into the warning log.
|
||||
"""
|
||||
self._summary_model_fallen_back = True
|
||||
logger.warning(
|
||||
logging.warning(
|
||||
"Summary model '%s' %s (%s). "
|
||||
"Falling back to main model '%s' for compression.",
|
||||
self.summary_model, reason, e, self.model,
|
||||
@@ -1087,7 +1086,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
|
||||
# No provider configured — long cooldown, unlikely to self-resolve
|
||||
self._summary_failure_cooldown_until = time.monotonic() + _SUMMARY_FAILURE_COOLDOWN_SECONDS
|
||||
self._last_summary_error = "no auxiliary LLM provider configured"
|
||||
logger.warning("Context compression: no provider available for "
|
||||
logging.warning("Context compression: no provider available for "
|
||||
"summary. Middle turns will be dropped without summary "
|
||||
"for %d seconds.",
|
||||
_SUMMARY_FAILURE_COOLDOWN_SECONDS)
|
||||
@@ -1183,7 +1182,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
|
||||
if len(err_text) > 220:
|
||||
err_text = err_text[:217].rstrip() + "..."
|
||||
self._last_summary_error = err_text
|
||||
logger.warning(
|
||||
logging.warning(
|
||||
"Failed to generate context summary: %s. "
|
||||
"Further summary attempts paused for %d seconds.",
|
||||
e,
|
||||
|
||||
@@ -200,7 +200,6 @@ class ContextEngine(ABC):
|
||||
base_url: str = "",
|
||||
api_key: str = "",
|
||||
provider: str = "",
|
||||
api_mode: str = "",
|
||||
) -> None:
|
||||
"""Called when the user switches models or on fallback activation.
|
||||
|
||||
|
||||
@@ -381,12 +381,12 @@ def compress_context(
|
||||
agent._session_db.end_session(agent.session_id, "compression")
|
||||
old_session_id = agent.session_id
|
||||
agent.session_id = f"{datetime.now().strftime('%Y%m%d_%H%M%S')}_{uuid.uuid4().hex[:6]}"
|
||||
os.environ["HERMES_SESSION_ID"] = agent.session_id
|
||||
try:
|
||||
from gateway.session_context import set_current_session_id
|
||||
|
||||
set_current_session_id(agent.session_id)
|
||||
from gateway.session_context import _SESSION_ID
|
||||
_SESSION_ID.set(agent.session_id)
|
||||
except Exception:
|
||||
os.environ["HERMES_SESSION_ID"] = agent.session_id
|
||||
pass
|
||||
agent._session_db_created = False
|
||||
agent._session_db.create_session(
|
||||
session_id=agent.session_id,
|
||||
|
||||
+24
-91
@@ -1183,7 +1183,7 @@ def run_conversation(
|
||||
else str(_codex_error_obj) if _codex_error_obj
|
||||
else f"Responses API returned status '{_codex_resp_status}'"
|
||||
)
|
||||
logger.warning(
|
||||
logging.warning(
|
||||
"Codex response status='%s' (error=%s). Routing to fallback. %s",
|
||||
_codex_resp_status, _codex_error_msg,
|
||||
agent._client_log_context(),
|
||||
@@ -1335,7 +1335,7 @@ def run_conversation(
|
||||
primary_recovery_attempted = False
|
||||
continue
|
||||
agent._emit_status(f"❌ Max retries ({max_retries}) exceeded for invalid responses. Giving up.")
|
||||
logger.error(f"{agent.log_prefix}Invalid API response after {max_retries} retries.")
|
||||
logging.error(f"{agent.log_prefix}Invalid API response after {max_retries} retries.")
|
||||
agent._persist_session(messages, conversation_history)
|
||||
return {
|
||||
"messages": messages,
|
||||
@@ -1348,7 +1348,7 @@ def run_conversation(
|
||||
# Backoff before retry — jittered exponential: 5s base, 120s cap
|
||||
wait_time = jittered_backoff(retry_count, base_delay=5.0, max_delay=120.0)
|
||||
agent._vprint(f"{agent.log_prefix}⏳ Retrying in {wait_time:.1f}s ({_failure_hint})...", force=True)
|
||||
logger.warning(f"Invalid API response (retry {retry_count}/{max_retries}): {', '.join(error_details)} | Provider: {provider_name}")
|
||||
logging.warning(f"Invalid API response (retry {retry_count}/{max_retries}): {', '.join(error_details)} | Provider: {provider_name}")
|
||||
|
||||
# Sleep in small increments to stay responsive to interrupts
|
||||
sleep_end = time.time() + wait_time
|
||||
@@ -1414,18 +1414,7 @@ def run_conversation(
|
||||
finish_reason = "length"
|
||||
|
||||
if finish_reason == "length":
|
||||
if getattr(response, "id", "") == "partial-stream-stub":
|
||||
agent._vprint(
|
||||
f"{agent.log_prefix}⚠️ Stream interrupted by network error "
|
||||
f"(finish_reason='length' on partial-stream-stub)",
|
||||
force=True,
|
||||
)
|
||||
else:
|
||||
agent._vprint(
|
||||
f"{agent.log_prefix}⚠️ Response truncated "
|
||||
f"(finish_reason='length') - model hit max output tokens",
|
||||
force=True,
|
||||
)
|
||||
agent._vprint(f"{agent.log_prefix}⚠️ Response truncated (finish_reason='length') - model hit max output tokens", force=True)
|
||||
|
||||
# Normalize the truncated response to a single OpenAI-style
|
||||
# message shape so text-continuation and tool-call retry
|
||||
@@ -1518,40 +1507,17 @@ def run_conversation(
|
||||
truncated_response_parts.append(assistant_message.content)
|
||||
|
||||
if length_continue_retries < 3:
|
||||
# Distinguish a real output-token truncation
|
||||
# from a partial-stream-stub network error
|
||||
# (#30963). Same continuation machinery,
|
||||
# but the prompt has to tell the truth or
|
||||
# the model goes off rails ("I wasn't
|
||||
# truncated, I'm done").
|
||||
_is_partial_stream_stub = (
|
||||
getattr(response, "id", "") == "partial-stream-stub"
|
||||
agent._vprint(
|
||||
f"{agent.log_prefix}↻ Requesting continuation "
|
||||
f"({length_continue_retries}/3)..."
|
||||
)
|
||||
if _is_partial_stream_stub:
|
||||
agent._vprint(
|
||||
f"{agent.log_prefix}↻ Stream interrupted — "
|
||||
f"requesting continuation "
|
||||
f"({length_continue_retries}/3)..."
|
||||
)
|
||||
_continue_content = (
|
||||
"[System: The previous response was cut off by a "
|
||||
"network error mid-stream. Continue exactly where "
|
||||
"you left off. Do not restart or repeat prior text. "
|
||||
"Finish the answer directly.]"
|
||||
)
|
||||
else:
|
||||
agent._vprint(
|
||||
f"{agent.log_prefix}↻ Requesting continuation "
|
||||
f"({length_continue_retries}/3)..."
|
||||
)
|
||||
_continue_content = (
|
||||
continue_msg = {
|
||||
"role": "user",
|
||||
"content": (
|
||||
"[System: Your previous response was truncated by the output "
|
||||
"length limit. Continue exactly where you left off. Do not "
|
||||
"restart or repeat prior text. Finish the answer directly.]"
|
||||
)
|
||||
continue_msg = {
|
||||
"role": "user",
|
||||
"content": _continue_content,
|
||||
),
|
||||
}
|
||||
messages.append(continue_msg)
|
||||
agent._session_messages = messages
|
||||
@@ -2259,7 +2225,7 @@ def run_conversation(
|
||||
f"stripped all thinking blocks, retrying...",
|
||||
force=True,
|
||||
)
|
||||
logger.warning(
|
||||
logging.warning(
|
||||
"%sThinking block signature recovery: stripped "
|
||||
"reasoning_details from %d messages",
|
||||
agent.log_prefix, len(messages),
|
||||
@@ -2284,7 +2250,7 @@ def run_conversation(
|
||||
from tools.schema_sanitizer import strip_pattern_and_format
|
||||
_, _stripped = strip_pattern_and_format(agent.tools)
|
||||
except Exception as _strip_exc: # pragma: no cover — defensive
|
||||
logger.warning(
|
||||
logging.warning(
|
||||
"%sllama.cpp grammar recovery: strip helper failed: %s",
|
||||
agent.log_prefix, _strip_exc,
|
||||
)
|
||||
@@ -2295,7 +2261,7 @@ def run_conversation(
|
||||
f"stripped {_stripped} pattern/format keyword(s), retrying...",
|
||||
force=True,
|
||||
)
|
||||
logger.warning(
|
||||
logging.warning(
|
||||
"%sllama.cpp grammar recovery: stripped %d "
|
||||
"pattern/format keyword(s) from tool schemas",
|
||||
agent.log_prefix, _stripped,
|
||||
@@ -2303,7 +2269,7 @@ def run_conversation(
|
||||
continue
|
||||
# No keywords found to strip — fall through to normal
|
||||
# retry path rather than loop forever on the same error.
|
||||
logger.warning(
|
||||
logging.warning(
|
||||
"%sllama.cpp grammar error but no pattern/format "
|
||||
"keywords to strip — falling through to normal retry",
|
||||
agent.log_prefix,
|
||||
@@ -2404,7 +2370,6 @@ def run_conversation(
|
||||
base_url=agent.base_url,
|
||||
api_key=getattr(agent, "api_key", ""),
|
||||
provider=agent.provider,
|
||||
api_mode=agent.api_mode,
|
||||
)
|
||||
# Context probing flags — only set on built-in
|
||||
# compressor (plugin engines manage their own).
|
||||
@@ -2518,7 +2483,7 @@ def run_conversation(
|
||||
error_context=error_context,
|
||||
)
|
||||
else:
|
||||
logger.info(
|
||||
logging.info(
|
||||
"Nous 429 looks like upstream capacity "
|
||||
"(no exhausted bucket in headers or "
|
||||
"last-known state) -- not tripping "
|
||||
@@ -2578,7 +2543,7 @@ def run_conversation(
|
||||
if compression_attempts > max_compression_attempts:
|
||||
agent._vprint(f"{agent.log_prefix}❌ Max compression attempts ({max_compression_attempts}) reached for payload-too-large error.", force=True)
|
||||
agent._vprint(f"{agent.log_prefix} 💡 Try /new to start a fresh conversation, or /compress to retry compression.", force=True)
|
||||
logger.error(f"{agent.log_prefix}413 compression failed after {max_compression_attempts} attempts.")
|
||||
logging.error(f"{agent.log_prefix}413 compression failed after {max_compression_attempts} attempts.")
|
||||
agent._persist_session(messages, conversation_history)
|
||||
return {
|
||||
"messages": messages,
|
||||
@@ -2609,7 +2574,7 @@ def run_conversation(
|
||||
else:
|
||||
agent._vprint(f"{agent.log_prefix}❌ Payload too large and cannot compress further.", force=True)
|
||||
agent._vprint(f"{agent.log_prefix} 💡 Try /new to start a fresh conversation, or /compress to retry compression.", force=True)
|
||||
logger.error(f"{agent.log_prefix}413 payload too large. Cannot compress further.")
|
||||
logging.error(f"{agent.log_prefix}413 payload too large. Cannot compress further.")
|
||||
agent._persist_session(messages, conversation_history)
|
||||
return {
|
||||
"messages": messages,
|
||||
@@ -2662,7 +2627,7 @@ def run_conversation(
|
||||
if compression_attempts > max_compression_attempts:
|
||||
agent._vprint(f"{agent.log_prefix}❌ Max compression attempts ({max_compression_attempts}) reached.", force=True)
|
||||
agent._vprint(f"{agent.log_prefix} 💡 Try /new to start a fresh conversation, or /compress to retry compression.", force=True)
|
||||
logger.error(f"{agent.log_prefix}Context compression failed after {max_compression_attempts} attempts.")
|
||||
logging.error(f"{agent.log_prefix}Context compression failed after {max_compression_attempts} attempts.")
|
||||
agent._persist_session(messages, conversation_history)
|
||||
return {
|
||||
"messages": messages,
|
||||
@@ -2714,7 +2679,6 @@ def run_conversation(
|
||||
base_url=agent.base_url,
|
||||
api_key=getattr(agent, "api_key", ""),
|
||||
provider=agent.provider,
|
||||
api_mode=agent.api_mode,
|
||||
)
|
||||
# Context probing flags — only set on built-in
|
||||
# compressor (plugin engines manage their own).
|
||||
@@ -2736,7 +2700,7 @@ def run_conversation(
|
||||
if compression_attempts > max_compression_attempts:
|
||||
agent._vprint(f"{agent.log_prefix}❌ Max compression attempts ({max_compression_attempts}) reached.", force=True)
|
||||
agent._vprint(f"{agent.log_prefix} 💡 Try /new to start a fresh conversation, or /compress to retry compression.", force=True)
|
||||
logger.error(f"{agent.log_prefix}Context compression failed after {max_compression_attempts} attempts.")
|
||||
logging.error(f"{agent.log_prefix}Context compression failed after {max_compression_attempts} attempts.")
|
||||
agent._persist_session(messages, conversation_history)
|
||||
return {
|
||||
"messages": messages,
|
||||
@@ -2769,7 +2733,7 @@ def run_conversation(
|
||||
# Can't compress further and already at minimum tier
|
||||
agent._vprint(f"{agent.log_prefix}❌ Context length exceeded and cannot compress further.", force=True)
|
||||
agent._vprint(f"{agent.log_prefix} 💡 The conversation has accumulated too much content. Try /new to start fresh, or /compress to manually trigger compression.", force=True)
|
||||
logger.error(f"{agent.log_prefix}Context length exceeded: {approx_tokens:,} tokens. Cannot compress further.")
|
||||
logging.error(f"{agent.log_prefix}Context length exceeded: {approx_tokens:,} tokens. Cannot compress further.")
|
||||
agent._persist_session(messages, conversation_history)
|
||||
return {
|
||||
"messages": messages,
|
||||
@@ -2806,21 +2770,6 @@ def run_conversation(
|
||||
# retryable=True mapping takes effect instead.
|
||||
and not isinstance(api_error, ssl.SSLError)
|
||||
)
|
||||
# ``FailoverReason.billing`` (HTTP 402) is NOT in this
|
||||
# exclusion set. By the time we reach this block:
|
||||
# • credential-pool rotation (line ~2031) has already
|
||||
# fired for billing and either ``continue``d or
|
||||
# returned (False, ...) — pool is exhausted or absent.
|
||||
# • the eager-fallback branch above (line ~2422) also
|
||||
# fires on billing and ``continue``s if a fallback
|
||||
# provider is configured.
|
||||
# Falling through to here means BOTH recovery paths
|
||||
# gave up. Treating 402 as retryable from this point
|
||||
# just burns more paid requests against a depleted
|
||||
# balance with no recovery mechanism left — see #31273
|
||||
# (real-world: ~$40 in 48h on a 24/7 gateway). Aborting
|
||||
# mirrors how 401/403 (also ``should_fallback=True``)
|
||||
# already behave once their recovery paths have failed.
|
||||
is_client_error = (
|
||||
is_local_validation_error
|
||||
or (
|
||||
@@ -2828,6 +2777,7 @@ def run_conversation(
|
||||
and not classified.should_compress
|
||||
and classified.reason not in {
|
||||
FailoverReason.rate_limit,
|
||||
FailoverReason.billing,
|
||||
FailoverReason.overloaded,
|
||||
FailoverReason.context_overflow,
|
||||
FailoverReason.payload_too_large,
|
||||
@@ -2876,7 +2826,7 @@ def run_conversation(
|
||||
agent._vprint(f"{agent.log_prefix} • Check credits: https://openrouter.ai/settings/credits", force=True)
|
||||
else:
|
||||
agent._vprint(f"{agent.log_prefix} 💡 This type of error won't be fixed by retrying.", force=True)
|
||||
logger.error(f"{agent.log_prefix}Non-retryable client error: {api_error}")
|
||||
logging.error(f"{agent.log_prefix}Non-retryable client error: {api_error}")
|
||||
# Skip session persistence when the error is likely
|
||||
# context-overflow related (status 400 + large session).
|
||||
# Persisting the failed user message would make the
|
||||
@@ -2953,7 +2903,7 @@ def run_conversation(
|
||||
force=True,
|
||||
)
|
||||
|
||||
logger.error(
|
||||
logging.error(
|
||||
"%sAPI call failed after %s retries. %s | provider=%s model=%s msgs=%s tokens=~%s",
|
||||
agent.log_prefix, max_retries, _final_summary,
|
||||
_provider, _model, len(api_messages), f"{approx_tokens:,}",
|
||||
@@ -3484,19 +3434,6 @@ def run_conversation(
|
||||
f"⚠️ Tool guardrail halted {decision.tool_name}: {decision.code}"
|
||||
)
|
||||
messages.append({"role": "assistant", "content": final_response})
|
||||
# Emit the halt message to the client so it's not
|
||||
# indistinguishable from a crash. The stream display
|
||||
# was flushed (callback(None)) before tool execution,
|
||||
# but the callback is still alive — fire the text
|
||||
# through it so SSE/TUI clients see the explanation.
|
||||
if final_response:
|
||||
agent._safe_print(f"\n{final_response}\n")
|
||||
if agent.stream_delta_callback:
|
||||
try:
|
||||
agent.stream_delta_callback(final_response)
|
||||
agent.stream_delta_callback(None)
|
||||
except Exception:
|
||||
pass
|
||||
break
|
||||
|
||||
# Reset per-turn retry counters after successful tool
|
||||
@@ -4092,8 +4029,6 @@ def run_conversation(
|
||||
except Exception as _ver_err:
|
||||
logger.debug("file-mutation verifier footer failed: %s", _ver_err)
|
||||
|
||||
_response_transformed = False
|
||||
|
||||
# Plugin hook: transform_llm_output
|
||||
# Fired once per turn after the tool-calling loop completes.
|
||||
# Plugins can transform the LLM's output text before it's returned.
|
||||
@@ -4111,7 +4046,6 @@ def run_conversation(
|
||||
for _hook_result in _transform_results:
|
||||
if isinstance(_hook_result, str) and _hook_result:
|
||||
final_response = _hook_result
|
||||
_response_transformed = True
|
||||
break # First non-empty string wins
|
||||
except Exception as exc:
|
||||
logger.warning("transform_llm_output hook failed: %s", exc)
|
||||
@@ -4163,7 +4097,6 @@ def run_conversation(
|
||||
"failed": failed,
|
||||
"partial": False, # True only when stopped due to invalid tool calls
|
||||
"interrupted": interrupted,
|
||||
"response_transformed": _response_transformed,
|
||||
"response_previewed": getattr(agent, "_response_was_previewed", False),
|
||||
"model": agent.model,
|
||||
"provider": agent.provider,
|
||||
|
||||
+6
-56
@@ -787,65 +787,33 @@ class KawaiiSpinner:
|
||||
# Cute tool message (completion line that replaces the spinner)
|
||||
# =========================================================================
|
||||
|
||||
_ERROR_SUFFIX_MAX_LEN = 48
|
||||
|
||||
|
||||
def _trim_error(msg: str) -> str:
|
||||
"""Shrink an error message for inline display in a tool status line.
|
||||
|
||||
Strips overly long absolute paths down to just the filename so the
|
||||
suffix stays readable on narrow terminals.
|
||||
"""
|
||||
msg = msg.strip()
|
||||
# Common case: "File not found: /very/long/absolute/path/foo.py"
|
||||
if "File not found:" in msg:
|
||||
_, _, tail = msg.partition("File not found:")
|
||||
tail = tail.strip()
|
||||
if "/" in tail:
|
||||
msg = f"File not found: {tail.rsplit('/', 1)[-1]}"
|
||||
if len(msg) > _ERROR_SUFFIX_MAX_LEN:
|
||||
msg = msg[: _ERROR_SUFFIX_MAX_LEN - 3] + "..."
|
||||
return msg
|
||||
|
||||
|
||||
def _detect_tool_failure(tool_name: str, result: str | None) -> tuple[bool, str]:
|
||||
"""Inspect a tool result string for signs of failure.
|
||||
|
||||
Returns ``(is_failure, suffix)`` where *suffix* is a short informational
|
||||
tag like ``" [exit 1]"`` for terminal failures, ``" [full]"`` for memory
|
||||
overflow, or a trimmed error message (``" [File not found: foo.py]"``).
|
||||
On success returns ``(False, "")``.
|
||||
Returns ``(is_failure, suffix)`` where *suffix* is an informational tag
|
||||
like ``" [exit 1]"`` for terminal failures, or ``" [error]"`` for generic
|
||||
failures. On success, returns ``(False, "")``.
|
||||
"""
|
||||
if result is None:
|
||||
return False, ""
|
||||
if file_mutation_result_landed(tool_name, result):
|
||||
return False, ""
|
||||
|
||||
data = safe_json_loads(result)
|
||||
|
||||
# Terminal: non-zero exit code is the canonical failure signal.
|
||||
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:
|
||||
err_msg = data.get("error")
|
||||
if err_msg:
|
||||
return True, f" [{_trim_error(str(err_msg))}]"
|
||||
return True, f" [exit {exit_code}]"
|
||||
return False, ""
|
||||
|
||||
# Memory: distinguish "store full" from real errors.
|
||||
# Memory-specific: distinguish "full" from real errors
|
||||
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]"
|
||||
|
||||
# Structured error in JSON result (any tool that surfaces {"error": ...}).
|
||||
if isinstance(data, dict):
|
||||
err = data.get("error") or data.get("message")
|
||||
if err and (data.get("success") is False or "error" in data):
|
||||
return True, f" [{_trim_error(str(err))}]"
|
||||
|
||||
# Generic heuristic for non-terminal tools
|
||||
# Multimodal tool results (dicts with _multimodal=True) are not strings —
|
||||
# treat them as successes since failures would be JSON-encoded strings.
|
||||
@@ -953,29 +921,11 @@ def get_cute_tool_message(
|
||||
if tool_name == "todo":
|
||||
todos_arg = args.get("todos")
|
||||
merge = args.get("merge", False)
|
||||
# Parse result for completion progress
|
||||
total = 0
|
||||
done = 0
|
||||
if result:
|
||||
try:
|
||||
data = safe_json_loads(result)
|
||||
if data:
|
||||
s = data.get("summary", {})
|
||||
total = s.get("total", 0)
|
||||
done = s.get("completed", 0)
|
||||
except Exception:
|
||||
pass
|
||||
if todos_arg is None:
|
||||
if total > 0:
|
||||
return _wrap(f"┊ 📋 plan {done}/{total} task(s) {dur}")
|
||||
return _wrap(f"┊ 📋 plan reading tasks {dur}")
|
||||
elif merge:
|
||||
if total > 0 and done > 0:
|
||||
return _wrap(f"┊ 📋 plan update {done}/{total} ✓ {dur}")
|
||||
return _wrap(f"┊ 📋 plan update {len(todos_arg)} task(s) {dur}")
|
||||
else:
|
||||
if total > 0 and done > 0:
|
||||
return _wrap(f"┊ 📋 plan {done}/{total} task(s) {dur}")
|
||||
return _wrap(f"┊ 📋 plan {len(todos_arg)} task(s) {dur}")
|
||||
if tool_name == "session_search":
|
||||
return _wrap(f"┊ 🔍 recall \"{_trunc(args.get('query', ''), 35)}\" {dur}")
|
||||
|
||||
@@ -240,24 +240,6 @@ _MODEL_NOT_FOUND_PATTERNS = [
|
||||
"unsupported model",
|
||||
]
|
||||
|
||||
# Request-validation patterns — the request is malformed and will fail
|
||||
# identically on every retry. Some OpenAI-compatible gateways (notably
|
||||
# codex.nekos.me) return these as 5xx instead of the standard 4xx, which
|
||||
# makes the generic "5xx → retryable server_error" rule misfire: the retry
|
||||
# loop hammers the same deterministic rejection 3+ times, then the
|
||||
# transport-recovery path resets the counter and does it again, producing
|
||||
# a request flood. When a 5xx body carries one of these unambiguous
|
||||
# request-validation signals, classify as a non-retryable format_error so
|
||||
# the loop fails fast and falls back instead of looping.
|
||||
_REQUEST_VALIDATION_PATTERNS = [
|
||||
"unknown parameter",
|
||||
"unsupported parameter",
|
||||
"unrecognized request argument",
|
||||
"invalid_request_error",
|
||||
"unknown_parameter",
|
||||
"unsupported_parameter",
|
||||
]
|
||||
|
||||
# OpenRouter aggregator policy-block patterns.
|
||||
#
|
||||
# When a user's OpenRouter account privacy setting (or a per-request
|
||||
@@ -763,23 +745,6 @@ def _classify_by_status(
|
||||
)
|
||||
|
||||
if status_code in {500, 502}:
|
||||
# Some OpenAI-compatible gateways return request-validation errors
|
||||
# with a 5xx status (codex.nekos.me returns 502 for unknown/
|
||||
# unsupported parameters). These are deterministic — every retry
|
||||
# gets the identical rejection — so the generic "5xx → retryable
|
||||
# server_error" rule turns one bad request into a retry flood.
|
||||
# Detect the unambiguous request-validation signals (in either the
|
||||
# message text or the structured error code) and fail fast.
|
||||
if (
|
||||
any(p in error_msg for p in _REQUEST_VALIDATION_PATTERNS)
|
||||
or error_code.lower() in {"invalid_request_error", "unknown_parameter",
|
||||
"unsupported_parameter"}
|
||||
):
|
||||
return result_fn(
|
||||
FailoverReason.format_error,
|
||||
retryable=False,
|
||||
should_fallback=True,
|
||||
)
|
||||
return result_fn(FailoverReason.server_error, retryable=True)
|
||||
|
||||
if status_code in {503, 529}:
|
||||
|
||||
@@ -127,12 +127,6 @@ def is_write_denied(path: str) -> bool:
|
||||
return True
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
pairing_real = os.path.realpath(os.path.join(base_real, "pairing"))
|
||||
if resolved == pairing_real or resolved.startswith(pairing_real + os.sep):
|
||||
return True
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
safe_root = get_safe_write_root()
|
||||
if safe_root and not (resolved == safe_root or resolved.startswith(safe_root + os.sep)):
|
||||
@@ -260,148 +254,3 @@ def get_read_block_error(path: str) -> Optional[str]:
|
||||
)
|
||||
|
||||
return None
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Cross-profile write guard (#TBD)
|
||||
#
|
||||
# Hermes profiles are separate HERMES_HOME dirs under
|
||||
# ``<root>/profiles/<name>/``. Each profile has its own skills/, plugins/,
|
||||
# cron/, memories/. When an agent runs under one profile, writing into
|
||||
# ANOTHER profile's directories is almost always wrong — those skills /
|
||||
# plugins / cron jobs / memories affect a different session the user runs
|
||||
# from a different shell.
|
||||
#
|
||||
# Soft guard, NOT a security boundary: the agent runs as the same OS user
|
||||
# and has unrestricted terminal access, so this returns a warning the model
|
||||
# can choose to honor or override with ``cross_profile=True``. Same shape
|
||||
# as the dangerous-command approval flow — the agent is told the boundary
|
||||
# exists, and explicit user direction is required to cross it.
|
||||
#
|
||||
# Reference: May 2026 incident where a hermes-security profile session
|
||||
# edited skills under both ``~/.hermes/profiles/hermes-security/skills/``
|
||||
# AND ``~/.hermes/skills/`` (the default profile's skills) without realizing
|
||||
# the second path belonged to a different profile.
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Profile-scoped directories under HERMES_HOME / <root> / <root>/profiles/<X>/
|
||||
# that should be guarded. Adding a new area here extends the guard with no
|
||||
# other code change.
|
||||
PROFILE_SCOPED_AREAS = ("skills", "plugins", "cron", "memories")
|
||||
|
||||
|
||||
def _resolve_active_profile_name() -> str:
|
||||
"""Return the active profile name derived from HERMES_HOME.
|
||||
|
||||
``~/.hermes`` -> ``"default"``
|
||||
``~/.hermes/profiles/X`` -> ``"X"``
|
||||
|
||||
Falls back to ``"default"`` on any resolution failure so the guard
|
||||
never raises into the tool path.
|
||||
"""
|
||||
try:
|
||||
home_real = _hermes_home_path().resolve()
|
||||
root_real = _hermes_root_path().resolve()
|
||||
except (OSError, RuntimeError):
|
||||
return "default"
|
||||
profiles_dir = root_real / "profiles"
|
||||
try:
|
||||
rel = home_real.relative_to(profiles_dir)
|
||||
parts = rel.parts
|
||||
if len(parts) >= 1:
|
||||
return parts[0]
|
||||
except ValueError:
|
||||
pass
|
||||
return "default"
|
||||
|
||||
|
||||
def classify_cross_profile_target(path: str) -> Optional[dict]:
|
||||
"""Classify a write target as cross-profile if it lands in another
|
||||
profile's scoped area (skills/plugins/cron/memories).
|
||||
|
||||
Returns ``None`` when the target is outside Hermes scope, or is inside
|
||||
the ACTIVE profile, or doesn't hit a profile-scoped area. Otherwise
|
||||
returns a dict with:
|
||||
|
||||
* ``active_profile``: name of the profile the agent is running as
|
||||
* ``target_profile``: name of the profile the path belongs to
|
||||
* ``area``: which scoped area (``"skills"``, ``"plugins"``, etc.)
|
||||
* ``target_path``: the resolved path string
|
||||
|
||||
The caller decides what to do with the result — surface a warning to
|
||||
the model, prompt the user, or (with explicit consent /
|
||||
``cross_profile=True``) proceed anyway.
|
||||
"""
|
||||
try:
|
||||
target = Path(os.path.expanduser(str(path))).resolve()
|
||||
root_real = _hermes_root_path().resolve()
|
||||
except (OSError, RuntimeError):
|
||||
return None
|
||||
|
||||
target_profile: Optional[str] = None
|
||||
area: Optional[str] = None
|
||||
|
||||
try:
|
||||
rel = target.relative_to(root_real)
|
||||
except ValueError:
|
||||
return None
|
||||
|
||||
parts = rel.parts
|
||||
if not parts:
|
||||
return None
|
||||
|
||||
if parts[0] in PROFILE_SCOPED_AREAS:
|
||||
# ``<root>/<area>/...`` → default profile.
|
||||
target_profile = "default"
|
||||
area = parts[0]
|
||||
elif (
|
||||
parts[0] == "profiles"
|
||||
and len(parts) >= 3
|
||||
and parts[2] in PROFILE_SCOPED_AREAS
|
||||
):
|
||||
# ``<root>/profiles/<name>/<area>/...`` → named profile.
|
||||
target_profile = parts[1]
|
||||
area = parts[2]
|
||||
else:
|
||||
return None
|
||||
|
||||
active_profile = _resolve_active_profile_name()
|
||||
if target_profile == active_profile:
|
||||
# In-profile write — not a cross-profile event.
|
||||
return None
|
||||
|
||||
return {
|
||||
"active_profile": active_profile,
|
||||
"target_profile": target_profile,
|
||||
"area": area,
|
||||
"target_path": str(target),
|
||||
}
|
||||
|
||||
|
||||
def get_cross_profile_warning(path: str) -> Optional[str]:
|
||||
"""Return a model-facing warning string when ``path`` is cross-profile.
|
||||
|
||||
Returns ``None`` when the write is in-scope (same profile) or outside
|
||||
Hermes entirely. Caller is expected to surface the warning to the
|
||||
agent as a tool-result error, NOT to silently allow the write — the
|
||||
agent must either get explicit user direction to proceed, or pass
|
||||
``cross_profile=True`` to its write tool.
|
||||
|
||||
This is defense-in-depth: the terminal tool runs as the same OS user
|
||||
and can write any of these paths without going through this guard.
|
||||
Treat the guard as a confusion-reducer, not a security boundary.
|
||||
"""
|
||||
info = classify_cross_profile_target(path)
|
||||
if info is None:
|
||||
return None
|
||||
return (
|
||||
f"Cross-profile write blocked by soft guard: {info['target_path']} "
|
||||
f"belongs to Hermes profile {info['target_profile']!r}, but the "
|
||||
f"agent is running under profile {info['active_profile']!r}. "
|
||||
f"Editing another profile's {info['area']}/ will affect that "
|
||||
f"profile's future sessions, not the one you are currently in. "
|
||||
f"Confirm with the user before proceeding. To bypass this guard "
|
||||
f"after explicit user direction, retry the call with "
|
||||
f"``cross_profile=True``. (Defense-in-depth — not a security "
|
||||
f"boundary; the terminal tool can still bypass.)"
|
||||
)
|
||||
|
||||
@@ -641,7 +641,7 @@ def fetch_model_metadata(force_refresh: bool = False) -> Dict[str, Dict[str, Any
|
||||
return cache
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to fetch model metadata from OpenRouter: {e}")
|
||||
logging.warning(f"Failed to fetch model metadata from OpenRouter: {e}")
|
||||
return _model_metadata_cache or {}
|
||||
|
||||
|
||||
|
||||
@@ -176,15 +176,6 @@ _URL_USERINFO_RE = re.compile(
|
||||
r"(https?|wss?|ftp)://([^/\s:@]+):([^/\s@]+)@",
|
||||
)
|
||||
|
||||
# HTTP access logs often use a relative request target rather than a full URL:
|
||||
# `"POST /webhook?password=... HTTP/1.1"`. The full-URL redactor above only
|
||||
# sees strings containing `://`, so handle request-target query strings too.
|
||||
_HTTP_REQUEST_TARGET_QUERY_RE = re.compile(
|
||||
r"\b((?:GET|POST|PUT|PATCH|DELETE|HEAD|OPTIONS|TRACE|CONNECT)\s+[^ \t\r\n\"']*?)"
|
||||
r"\?([^ \t\r\n\"']+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
# Form-urlencoded body detection: conservative — only applies when the entire
|
||||
# text looks like a query string (k=v&k=v pattern with no newlines).
|
||||
_FORM_BODY_RE = re.compile(
|
||||
@@ -302,15 +293,6 @@ def _redact_url_userinfo(text: str) -> str:
|
||||
)
|
||||
|
||||
|
||||
def _redact_http_request_target_query_params(text: str) -> str:
|
||||
"""Redact sensitive query params in HTTP access-log request targets."""
|
||||
def _sub(m: re.Match) -> str:
|
||||
prefix = m.group(1)
|
||||
query = _redact_query_string(m.group(2))
|
||||
return f"{prefix}?{query}"
|
||||
return _HTTP_REQUEST_TARGET_QUERY_RE.sub(_sub, text)
|
||||
|
||||
|
||||
def _redact_form_body(text: str) -> str:
|
||||
"""Redact sensitive values in a form-urlencoded body.
|
||||
|
||||
@@ -415,11 +397,6 @@ def redact_sensitive_text(text: str, *, force: bool = False, code_file: bool = F
|
||||
if "?" in text:
|
||||
text = _redact_url_query_params(text)
|
||||
|
||||
# HTTP access logs can contain relative request targets with query params
|
||||
# and no URL scheme, e.g. `"POST /hook?password=... HTTP/1.1"`.
|
||||
if "?" in text and "=" in text and _has_http_method_substring(text):
|
||||
text = _redact_http_request_target_query_params(text)
|
||||
|
||||
# Form-urlencoded bodies (only triggers on clean k=v&k=v inputs).
|
||||
if "&" in text and "=" in text:
|
||||
text = _redact_form_body(text)
|
||||
@@ -479,25 +456,6 @@ def _has_known_prefix_substring(text: str) -> bool:
|
||||
return any(p in text for p in _PREFIX_SUBSTRINGS)
|
||||
|
||||
|
||||
_HTTP_METHOD_SUBSTRINGS = (
|
||||
"GET ",
|
||||
"POST ",
|
||||
"PUT ",
|
||||
"PATCH ",
|
||||
"DELETE ",
|
||||
"HEAD ",
|
||||
"OPTIONS ",
|
||||
"TRACE ",
|
||||
"CONNECT ",
|
||||
)
|
||||
|
||||
|
||||
def _has_http_method_substring(text: str) -> bool:
|
||||
"""Cheap pre-check before scanning for access-log request targets."""
|
||||
upper = text.upper()
|
||||
return any(method in upper for method in _HTTP_METHOD_SUBSTRINGS)
|
||||
|
||||
|
||||
class RedactingFormatter(logging.Formatter):
|
||||
"""Log formatter that redacts secrets from all log messages."""
|
||||
|
||||
|
||||
@@ -70,7 +70,7 @@ _BWS_RUN_TIMEOUT = 30
|
||||
|
||||
# In-process cache so repeated load_hermes_dotenv() calls (CLI startup,
|
||||
# gateway hot-reload, test suites) don't re-fetch from BSM.
|
||||
_CacheKey = Tuple[str, str, str] # (access_token_fingerprint, project_id, server_url)
|
||||
_CacheKey = Tuple[str, str] # (access_token_fingerprint, project_id)
|
||||
_CACHE: Dict[_CacheKey, "_CachedFetch"] = {}
|
||||
|
||||
|
||||
@@ -317,18 +317,11 @@ def fetch_bitwarden_secrets(
|
||||
binary: Optional[Path] = None,
|
||||
cache_ttl_seconds: float = 300,
|
||||
use_cache: bool = True,
|
||||
server_url: str = "",
|
||||
) -> Tuple[Dict[str, str], List[str]]:
|
||||
"""Pull the secrets for ``project_id`` from Bitwarden Secrets Manager.
|
||||
|
||||
Returns ``(secrets_dict, warnings_list)``.
|
||||
|
||||
Set ``server_url`` to point at a non-default Bitwarden region or a
|
||||
self-hosted instance — e.g. ``https://vault.bitwarden.eu`` for EU
|
||||
Cloud accounts. When empty, ``bws`` uses its built-in default
|
||||
(``https://vault.bitwarden.com``, US Cloud). This is plumbed into
|
||||
the subprocess as ``BWS_SERVER_URL``.
|
||||
|
||||
Raises :class:`RuntimeError` for fatal conditions (missing binary,
|
||||
auth failure, unparseable output). Callers in the env_loader path
|
||||
catch this and emit a single warning; callers in the user-facing
|
||||
@@ -339,7 +332,7 @@ def fetch_bitwarden_secrets(
|
||||
if not project_id:
|
||||
raise RuntimeError("Bitwarden project_id is empty")
|
||||
|
||||
cache_key = (_token_fingerprint(access_token), project_id, server_url or "")
|
||||
cache_key = (_token_fingerprint(access_token), project_id)
|
||||
if use_cache:
|
||||
cached = _CACHE.get(cache_key)
|
||||
if cached and cached.is_fresh(cache_ttl_seconds):
|
||||
@@ -354,26 +347,19 @@ def fetch_bitwarden_secrets(
|
||||
"`hermes secrets bitwarden setup`."
|
||||
)
|
||||
|
||||
secrets, warnings = _run_bws_list(bws, access_token, project_id, server_url)
|
||||
secrets, warnings = _run_bws_list(bws, access_token, project_id)
|
||||
_CACHE[cache_key] = _CachedFetch(secrets=secrets, fetched_at=time.time())
|
||||
return secrets, warnings
|
||||
|
||||
|
||||
def _run_bws_list(
|
||||
bws: Path, access_token: str, project_id: str, server_url: str = ""
|
||||
bws: Path, access_token: str, project_id: str
|
||||
) -> Tuple[Dict[str, str], List[str]]:
|
||||
cmd = [str(bws), "secret", "list", project_id, "--output", "json"]
|
||||
env = os.environ.copy()
|
||||
env["BWS_ACCESS_TOKEN"] = access_token
|
||||
# Make sure we're not echoing telemetry / colour codes into json.
|
||||
env.setdefault("NO_COLOR", "1")
|
||||
# Region / self-hosted support. bws defaults to https://vault.bitwarden.com
|
||||
# (US Cloud); EU Cloud users need https://vault.bitwarden.eu, and
|
||||
# self-hosted users need their own URL. When unset, fall back to whatever
|
||||
# BWS_SERVER_URL the caller already had in their shell env (preserved by
|
||||
# the copy above) so manual overrides keep working too.
|
||||
if server_url:
|
||||
env["BWS_SERVER_URL"] = server_url
|
||||
|
||||
try:
|
||||
proc = subprocess.run( # noqa: S603 — bws path is trusted
|
||||
@@ -451,7 +437,6 @@ def apply_bitwarden_secrets(
|
||||
override_existing: bool = False,
|
||||
cache_ttl_seconds: float = 300,
|
||||
auto_install: bool = True,
|
||||
server_url: str = "",
|
||||
) -> FetchResult:
|
||||
"""Pull secrets from BSM and set them on ``os.environ``.
|
||||
|
||||
@@ -459,10 +444,6 @@ def apply_bitwarden_secrets(
|
||||
files have loaded. It is intentionally defensive — any failure
|
||||
returns a :class:`FetchResult` with ``error`` set; it never raises.
|
||||
|
||||
``server_url`` selects the Bitwarden region or self-hosted endpoint
|
||||
(e.g. ``https://vault.bitwarden.eu`` for EU Cloud). Empty string
|
||||
means use ``bws``'s default (US Cloud).
|
||||
|
||||
Parameters mirror the ``secrets.bitwarden.*`` config keys so the
|
||||
caller can just splat the dict in.
|
||||
"""
|
||||
@@ -501,7 +482,6 @@ def apply_bitwarden_secrets(
|
||||
project_id=project_id,
|
||||
binary=binary,
|
||||
cache_ttl_seconds=cache_ttl_seconds,
|
||||
server_url=server_url,
|
||||
)
|
||||
except RuntimeError as exc:
|
||||
result.error = str(exc)
|
||||
|
||||
@@ -205,40 +205,6 @@ def build_system_prompt_parts(agent: Any, system_message: Optional[str] = None)
|
||||
if _env_hints:
|
||||
stable_parts.append(_env_hints)
|
||||
|
||||
# Active-profile hint — names the Hermes profile the agent is running
|
||||
# under so it doesn't conflate ~/.hermes/skills/ (default profile) with
|
||||
# ~/.hermes/profiles/<active>/skills/ (this profile's). Deterministic
|
||||
# for the lifetime of the agent — profile name doesn't change
|
||||
# mid-session, so this doesn't break the prompt cache.
|
||||
# See file_safety._resolve_active_profile_name + classify_cross_profile_target
|
||||
# for the matching tool-side guard.
|
||||
try:
|
||||
from agent.file_safety import _resolve_active_profile_name
|
||||
active_profile = _resolve_active_profile_name()
|
||||
except Exception:
|
||||
active_profile = "default"
|
||||
if active_profile == "default":
|
||||
stable_parts.append(
|
||||
"Active Hermes profile: default. Other profiles (if any) live "
|
||||
"under ~/.hermes/profiles/<name>/. Each profile has its own "
|
||||
"skills/, plugins/, cron/, and memories/ that affect a different "
|
||||
"session than this one. Do not modify another profile's "
|
||||
"skills/plugins/cron/memories unless the user explicitly directs "
|
||||
"you to."
|
||||
)
|
||||
else:
|
||||
stable_parts.append(
|
||||
f"Active Hermes profile: {active_profile}. This session reads "
|
||||
f"and writes ~/.hermes/profiles/{active_profile}/. The default "
|
||||
f"profile's data lives at ~/.hermes/skills/, ~/.hermes/plugins/, "
|
||||
f"~/.hermes/cron/, ~/.hermes/memories/ — those belong to a "
|
||||
f"different session run from a different shell. Do NOT modify "
|
||||
f"another profile's skills/plugins/cron/memories unless the user "
|
||||
f"explicitly directs you to. The cross-profile write guard will "
|
||||
f"refuse such writes by default; pass cross_profile=True only "
|
||||
f"after explicit direction."
|
||||
)
|
||||
|
||||
platform_key = (agent.platform or "").lower().strip()
|
||||
if platform_key in PLATFORM_HINTS:
|
||||
stable_parts.append(PLATFORM_HINTS[platform_key])
|
||||
|
||||
@@ -388,7 +388,6 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
|
||||
agent.tool_progress_callback(
|
||||
"tool.completed", function_name, None, None,
|
||||
duration=tool_duration, is_error=is_error,
|
||||
result=function_result,
|
||||
)
|
||||
except Exception as cb_err:
|
||||
logging.debug(f"Tool progress callback error: {cb_err}")
|
||||
@@ -492,7 +491,7 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
|
||||
try:
|
||||
function_args = json.loads(tool_call.function.arguments)
|
||||
except json.JSONDecodeError as e:
|
||||
logger.warning(f"Unexpected JSON error after validation: {e}")
|
||||
logging.warning(f"Unexpected JSON error after validation: {e}")
|
||||
function_args = {}
|
||||
if not isinstance(function_args, dict):
|
||||
function_args = {}
|
||||
@@ -823,7 +822,6 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
|
||||
agent.tool_progress_callback(
|
||||
"tool.completed", function_name, None, None,
|
||||
duration=tool_duration, is_error=_is_error_result,
|
||||
result=function_result,
|
||||
)
|
||||
except Exception as cb_err:
|
||||
logging.debug(f"Tool progress callback error: {cb_err}")
|
||||
|
||||
@@ -106,17 +106,7 @@ class AnthropicTransport(ProviderTransport):
|
||||
elif block.type == "tool_use":
|
||||
name = block.name
|
||||
if strip_tool_prefix and name.startswith(_MCP_PREFIX):
|
||||
stripped = name[len(_MCP_PREFIX):]
|
||||
# Only strip the mcp_ prefix for OAuth-injected tools
|
||||
# (where Hermes adds the prefix when sending to Anthropic
|
||||
# and must remove it on the way back). Native MCP server
|
||||
# tools (from mcp_servers: in config.yaml) are registered
|
||||
# in the tool registry under their FULL mcp_<server>_<tool>
|
||||
# name and must NOT be stripped. GH-25255.
|
||||
from tools.registry import registry as _tool_registry
|
||||
if (_tool_registry.get_entry(stripped)
|
||||
and not _tool_registry.get_entry(name)):
|
||||
name = stripped
|
||||
name = name[len(_MCP_PREFIX):]
|
||||
tool_calls.append(
|
||||
ToolCall(
|
||||
id=block.id,
|
||||
|
||||
@@ -113,8 +113,9 @@ class ChatCompletionsTransport(ProviderTransport):
|
||||
self, messages: list[dict[str, Any]], **kwargs
|
||||
) -> list[dict[str, Any]]:
|
||||
"""Messages are already in OpenAI format — strip internal fields
|
||||
that strict chat-completions providers reject with HTTP 400/422
|
||||
(or, in the case of some OpenAI-compatible gateways, 5xx):
|
||||
that strict chat-completions providers reject with HTTP 400/422.
|
||||
|
||||
Strips:
|
||||
|
||||
- Codex Responses API fields: ``codex_reasoning_items`` /
|
||||
``codex_message_items`` on the message, ``call_id`` /
|
||||
@@ -126,16 +127,6 @@ class ChatCompletionsTransport(ProviderTransport):
|
||||
``Extra inputs are not permitted, field: 'messages[N].tool_name'``.
|
||||
Permissive providers (OpenRouter, MiniMax) silently ignore the
|
||||
field, which masked the bug for months.
|
||||
- Hermes-internal scaffolding markers — any top-level message key
|
||||
starting with ``_`` (e.g. ``_empty_recovery_synthetic``,
|
||||
``_empty_terminal_sentinel``, ``_thinking_prefill``). These are
|
||||
bookkeeping flags the agent loop attaches to messages so the
|
||||
persistence layer can later strip its own scaffolding; they must
|
||||
never reach the wire. Permissive providers (real OpenAI,
|
||||
Anthropic) silently drop unknown message keys, but strict
|
||||
gateways (e.g. opencode-go, codex.nekos.me) reject with
|
||||
``Extra inputs are not permitted, field: 'messages[N]._empty_recovery_synthetic'``,
|
||||
which then poisons every subsequent request in the session.
|
||||
"""
|
||||
needs_sanitize = False
|
||||
for msg in messages:
|
||||
@@ -148,9 +139,6 @@ class ChatCompletionsTransport(ProviderTransport):
|
||||
):
|
||||
needs_sanitize = True
|
||||
break
|
||||
if any(isinstance(k, str) and k.startswith("_") for k in msg):
|
||||
needs_sanitize = True
|
||||
break
|
||||
tool_calls = msg.get("tool_calls")
|
||||
if isinstance(tool_calls, list):
|
||||
for tc in tool_calls:
|
||||
@@ -172,11 +160,6 @@ class ChatCompletionsTransport(ProviderTransport):
|
||||
msg.pop("codex_reasoning_items", None)
|
||||
msg.pop("codex_message_items", None)
|
||||
msg.pop("tool_name", None)
|
||||
# Drop all Hermes-internal scaffolding markers (``_``-prefixed).
|
||||
# OpenAI's message schema has no ``_``-prefixed fields, so this
|
||||
# is safe and future-proofs against new markers being added.
|
||||
for key in [k for k in msg if isinstance(k, str) and k.startswith("_")]:
|
||||
msg.pop(key, None)
|
||||
tool_calls = msg.get("tool_calls")
|
||||
if isinstance(tool_calls, list):
|
||||
for tc in tool_calls:
|
||||
|
||||
@@ -87,39 +87,6 @@ class TurnResult:
|
||||
_TURN_ABORTED_MARKERS = ("<turn_aborted>", "<turn_aborted/>")
|
||||
|
||||
|
||||
def _coerce_turn_input_text(user_input: Any) -> str:
|
||||
"""Collapse Hermes/OpenAI rich content into app-server text input.
|
||||
|
||||
The current `turn/start` path sends text items only. TUI image attachment
|
||||
can hand us OpenAI-style content parts, so keep the text/path hints and
|
||||
replace opaque image payloads with a small marker instead of putting a
|
||||
Python list into the `text` field.
|
||||
"""
|
||||
if isinstance(user_input, str):
|
||||
return user_input
|
||||
if isinstance(user_input, list):
|
||||
parts: list[str] = []
|
||||
for item in user_input:
|
||||
if isinstance(item, str):
|
||||
if item.strip():
|
||||
parts.append(item)
|
||||
continue
|
||||
if not isinstance(item, dict):
|
||||
if item is not None:
|
||||
parts.append(str(item))
|
||||
continue
|
||||
item_type = item.get("type")
|
||||
if item_type in {"text", "input_text"}:
|
||||
text = item.get("text") or item.get("content") or ""
|
||||
if text:
|
||||
parts.append(str(text))
|
||||
elif item_type in {"image", "image_url", "input_image"}:
|
||||
parts.append("[image attached]")
|
||||
text = "\n\n".join(p for p in parts if p).strip()
|
||||
return text or "What do you see in this image?"
|
||||
return "" if user_input is None else str(user_input)
|
||||
|
||||
|
||||
# Substrings in codex stderr / JSON-RPC error messages that signal the
|
||||
# subprocess died because its OAuth credentials are no longer valid.
|
||||
# Kept conservative: we only redirect users to `codex login` when we're
|
||||
@@ -360,7 +327,7 @@ class CodexAppServerSession:
|
||||
|
||||
def run_turn(
|
||||
self,
|
||||
user_input: Any,
|
||||
user_input: str,
|
||||
*,
|
||||
turn_timeout: float = 600.0,
|
||||
notification_poll_timeout: float = 0.25,
|
||||
@@ -398,8 +365,6 @@ class CodexAppServerSession:
|
||||
self._interrupt_event.clear()
|
||||
projector = CodexEventProjector()
|
||||
|
||||
user_input_text = _coerce_turn_input_text(user_input)
|
||||
|
||||
# Send turn/start with the user input. Text-only for now (codex
|
||||
# supports rich content but Hermes' text path is the common case).
|
||||
try:
|
||||
@@ -407,7 +372,7 @@ class CodexAppServerSession:
|
||||
"turn/start",
|
||||
{
|
||||
"threadId": self._thread_id,
|
||||
"input": [{"type": "text", "text": user_input_text}],
|
||||
"input": [{"type": "text", "text": user_input}],
|
||||
},
|
||||
timeout=10,
|
||||
)
|
||||
|
||||
@@ -39,7 +39,7 @@ model:
|
||||
# LM Studio is first-class and uses provider: "lmstudio".
|
||||
# It works with both no-auth and auth-enabled server modes.
|
||||
#
|
||||
# Can also be overridden for a single invocation with the --provider flag.
|
||||
# Can also be overridden with --provider flag or HERMES_INFERENCE_PROVIDER env var.
|
||||
provider: "auto"
|
||||
|
||||
# API configuration (falls back to OPENROUTER_API_KEY env var)
|
||||
|
||||
@@ -51,8 +51,6 @@ os.environ["HERMES_QUIET"] = "1" # Our own modules
|
||||
|
||||
import yaml
|
||||
|
||||
from hermes_cli.fallback_config import get_fallback_chain
|
||||
|
||||
# prompt_toolkit for fixed input area TUI
|
||||
from prompt_toolkit.history import FileHistory
|
||||
from prompt_toolkit.styles import Style as PTStyle
|
||||
@@ -415,12 +413,6 @@ def load_cli_config() -> Dict[str, Any]:
|
||||
"display": {
|
||||
"compact": False,
|
||||
"resume_display": "full",
|
||||
# Recap tuning for /resume — see hermes_cli/config.py DEFAULT_CONFIG.
|
||||
"resume_exchanges": 10,
|
||||
"resume_max_user_chars": 300,
|
||||
"resume_max_assistant_chars": 200,
|
||||
"resume_max_assistant_lines": 3,
|
||||
"resume_skip_tool_only": True,
|
||||
"show_reasoning": False,
|
||||
"streaming": True,
|
||||
"busy_input_mode": "interrupt",
|
||||
@@ -474,9 +466,7 @@ def load_cli_config() -> Dict[str, Any]:
|
||||
if config_path.exists():
|
||||
try:
|
||||
with open(config_path, "r", encoding="utf-8") as f:
|
||||
from hermes_cli.config import _normalize_root_model_keys
|
||||
|
||||
file_config = _normalize_root_model_keys(yaml.safe_load(f) or {})
|
||||
file_config = yaml.safe_load(f) or {}
|
||||
|
||||
_file_has_terminal_config = "terminal" in file_config
|
||||
|
||||
@@ -497,6 +487,21 @@ def load_cli_config() -> Dict[str, Any]:
|
||||
if "model" in file_config["model"] and "default" not in file_config["model"]:
|
||||
defaults["model"]["default"] = file_config["model"]["model"]
|
||||
|
||||
# Legacy root-level provider/base_url fallback.
|
||||
# Some users (or old code) put provider: / base_url: at the
|
||||
# config root instead of inside the model: section. These are
|
||||
# only used as a FALLBACK when model.provider / model.base_url
|
||||
# is not already set — never as an override. The canonical
|
||||
# location is model.provider (written by `hermes model`).
|
||||
if not defaults["model"].get("provider"):
|
||||
root_provider = file_config.get("provider")
|
||||
if root_provider:
|
||||
defaults["model"]["provider"] = root_provider
|
||||
if not defaults["model"].get("base_url"):
|
||||
root_base_url = file_config.get("base_url")
|
||||
if root_base_url:
|
||||
defaults["model"]["base_url"] = root_base_url
|
||||
|
||||
# Deep merge file_config into defaults.
|
||||
# First: merge keys that exist in both (deep-merge dicts, overwrite scalars)
|
||||
for key in defaults:
|
||||
@@ -768,6 +773,8 @@ from rich.markup import escape as _escape
|
||||
from rich.panel import Panel
|
||||
from rich.text import Text as _RichText
|
||||
|
||||
import fire
|
||||
|
||||
# Import agent and tool systems lazily. Bare interactive startup only needs the
|
||||
# prompt; the full agent/tool registry is initialized on first use.
|
||||
def AIAgent(*args, **kwargs):
|
||||
@@ -809,13 +816,6 @@ def validate_toolset(*args, **kwargs):
|
||||
|
||||
return _validate_toolset(*args, **kwargs)
|
||||
|
||||
|
||||
def _sync_process_session_id(session_id: str) -> None:
|
||||
"""Keep process-local session-id consumers aligned after CLI switches."""
|
||||
from gateway.session_context import set_current_session_id
|
||||
|
||||
set_current_session_id(session_id)
|
||||
|
||||
# Cron job system for scheduled tasks (execution is handled by the gateway)
|
||||
def get_job(*args, **kwargs):
|
||||
from cron import get_job as _get_job
|
||||
@@ -2812,7 +2812,7 @@ class HermesCLI:
|
||||
api_key: str = None,
|
||||
base_url: str = None,
|
||||
max_turns: int = None,
|
||||
verbose: Optional[bool] = None,
|
||||
verbose: bool = False,
|
||||
compact: bool = False,
|
||||
resume: str = None,
|
||||
checkpoints: bool = False,
|
||||
@@ -2863,12 +2863,7 @@ class HermesCLI:
|
||||
else:
|
||||
self.busy_input_mode = "interrupt"
|
||||
|
||||
# self.verbose ONLY controls global DEBUG logging (root logger level).
|
||||
# display.tool_progress="verbose" controls tool-call rendering (full args,
|
||||
# results, think blocks) and is independent — see _apply_logging_levels.
|
||||
# Coupling the two (PR #6a1aa420e) caused all module DEBUG logs to spew
|
||||
# to console whenever a user set tool_progress: verbose in config.
|
||||
self.verbose = bool(verbose) if verbose is not None else False
|
||||
self.verbose = verbose if verbose is not None else (self.tool_progress_mode == "verbose")
|
||||
|
||||
# streaming: stream tokens to the terminal as they arrive (display.streaming in config.yaml)
|
||||
self.streaming_enabled = CLI_CONFIG["display"].get("streaming", False)
|
||||
@@ -3054,9 +3049,12 @@ class HermesCLI:
|
||||
pass
|
||||
|
||||
# Fallback provider chain — tried in order when primary fails after retries.
|
||||
# Merge new ``fallback_providers`` entries with any legacy
|
||||
# ``fallback_model`` entries so old configs still participate.
|
||||
self._fallback_model = get_fallback_chain(CLI_CONFIG)
|
||||
# Supports new list format (fallback_providers) and legacy single-dict (fallback_model).
|
||||
fb = CLI_CONFIG.get("fallback_providers") or CLI_CONFIG.get("fallback_model") or []
|
||||
# Normalize legacy single-dict to a one-element list
|
||||
if isinstance(fb, dict):
|
||||
fb = [fb] if fb.get("provider") and fb.get("model") else []
|
||||
self._fallback_model = fb
|
||||
|
||||
# Signature of the currently-initialised agent's runtime. Used to
|
||||
# rebuild the agent when provider / model / base_url changes across
|
||||
@@ -5094,13 +5092,10 @@ class HermesCLI:
|
||||
if self.resume_display == "minimal":
|
||||
return
|
||||
|
||||
# Read limits from config (with hardcoded defaults)
|
||||
_disp = CLI_CONFIG.get("display", {})
|
||||
MAX_DISPLAY_EXCHANGES = int(_disp.get("resume_exchanges", 10))
|
||||
MAX_USER_LEN = int(_disp.get("resume_max_user_chars", 300))
|
||||
MAX_ASST_LEN = int(_disp.get("resume_max_assistant_chars", 200))
|
||||
MAX_ASST_LINES = int(_disp.get("resume_max_assistant_lines", 3))
|
||||
SKIP_TOOL_ONLY = _disp.get("resume_skip_tool_only", True)
|
||||
MAX_DISPLAY_EXCHANGES = 10 # max user+assistant pairs to show
|
||||
MAX_USER_LEN = 300 # truncate user messages
|
||||
MAX_ASST_LEN = 200 # truncate assistant text
|
||||
MAX_ASST_LINES = 3 # max lines of assistant text
|
||||
|
||||
# Collect displayable entries (skip system, tool-result messages)
|
||||
entries = [] # list of (role, display_text)
|
||||
@@ -5163,10 +5158,6 @@ class HermesCLI:
|
||||
if not parts:
|
||||
# Skip pure-reasoning messages that have no visible output
|
||||
continue
|
||||
# Skip tool-call-only entries when SKIP_TOOL_ONLY is enabled
|
||||
has_text = bool(text)
|
||||
if SKIP_TOOL_ONLY and not has_text and tool_calls:
|
||||
continue
|
||||
entries.append(("assistant", " ".join(parts)))
|
||||
_last_asst_idx = len(entries) - 1
|
||||
_last_asst_full = " ".join(full_parts)
|
||||
@@ -6172,16 +6163,15 @@ class HermesCLI:
|
||||
else:
|
||||
print(" Recent sessions:")
|
||||
print()
|
||||
print(f" {'#':<3} {'Title':<32} {'Preview':<40} {'Last Active':<13} {'ID'}")
|
||||
print(f" {'─' * 3} {'─' * 32} {'─' * 40} {'─' * 13} {'─' * 24}")
|
||||
for idx, session in enumerate(sessions, start=1):
|
||||
title = session.get("title") or "—"
|
||||
print(f" {'Title':<32} {'Preview':<40} {'Last Active':<13} {'ID'}")
|
||||
print(f" {'─' * 32} {'─' * 40} {'─' * 13} {'─' * 24}")
|
||||
for session in sessions:
|
||||
title = (session.get("title") or "—")[:30]
|
||||
preview = (session.get("preview") or "")[:38]
|
||||
last_active = _relative_time(session.get("last_active"))
|
||||
print(f" {idx:<3} {title:<32} {preview:<40} {last_active:<13} {session['id']}")
|
||||
print(f" {title:<32} {preview:<40} {last_active:<13} {session['id']}")
|
||||
print()
|
||||
print(" Use /resume <number>, /resume <session id>, or /resume <session title> to continue.")
|
||||
print(" Example: /resume 2")
|
||||
print(" Use /resume <session id or title> to continue where you left off.")
|
||||
print()
|
||||
return True
|
||||
|
||||
@@ -6292,7 +6282,6 @@ class HermesCLI:
|
||||
self.conversation_history = []
|
||||
self._pending_title = None
|
||||
self._resumed = False
|
||||
_sync_process_session_id(self.session_id)
|
||||
|
||||
if self.agent:
|
||||
self.agent.session_id = self.session_id
|
||||
@@ -6526,7 +6515,7 @@ class HermesCLI:
|
||||
target = parts[1].strip() if len(parts) > 1 else ""
|
||||
|
||||
if not target:
|
||||
_cprint(" Usage: /resume <number|session_id_or_title>")
|
||||
_cprint(" Usage: /resume <session_id_or_title>")
|
||||
if self._show_recent_sessions(reason="resume"):
|
||||
return
|
||||
_cprint(" Tip: Use /history or `hermes sessions list` to find sessions.")
|
||||
@@ -6537,20 +6526,10 @@ class HermesCLI:
|
||||
_cprint(f" {format_session_db_unavailable()}")
|
||||
return
|
||||
|
||||
# Resolve numbered selection, title, or ID
|
||||
if target.isdigit():
|
||||
sessions = self._list_recent_sessions(limit=10)
|
||||
index = int(target)
|
||||
if index < 1 or index > len(sessions):
|
||||
_cprint(f" Resume index {index} is out of range.")
|
||||
_cprint(" Use /resume with no arguments to see available sessions.")
|
||||
return
|
||||
selected = sessions[index - 1]
|
||||
target_id = selected["id"]
|
||||
else:
|
||||
from hermes_cli.main import _resolve_session_by_name_or_id
|
||||
resolved = _resolve_session_by_name_or_id(target)
|
||||
target_id = resolved or target
|
||||
# Resolve title or ID
|
||||
from hermes_cli.main import _resolve_session_by_name_or_id
|
||||
resolved = _resolve_session_by_name_or_id(target)
|
||||
target_id = resolved or target
|
||||
|
||||
session_meta = self._session_db.get_session(target_id)
|
||||
if not session_meta:
|
||||
@@ -6589,7 +6568,6 @@ class HermesCLI:
|
||||
self.session_id = target_id
|
||||
self._resumed = True
|
||||
self._pending_title = None
|
||||
_sync_process_session_id(target_id)
|
||||
|
||||
# Load conversation history (strip transcript-only metadata entries)
|
||||
restored = self._session_db.get_messages_as_conversation(target_id)
|
||||
@@ -6641,7 +6619,6 @@ class HermesCLI:
|
||||
f" ({msg_count} user message{'s' if msg_count != 1 else ''},"
|
||||
f" {len(self.conversation_history)} total)"
|
||||
)
|
||||
self._display_resumed_history()
|
||||
else:
|
||||
_cprint(f" ↻ Resumed session {target_id}{title_part} — no messages, starting fresh.")
|
||||
|
||||
@@ -6764,7 +6741,6 @@ class HermesCLI:
|
||||
self.session_start = now
|
||||
self._pending_title = None
|
||||
self._resumed = True # Prevents auto-title generation
|
||||
_sync_process_session_id(new_session_id)
|
||||
|
||||
# Sync the agent
|
||||
if self.agent:
|
||||
@@ -8126,7 +8102,6 @@ class HermesCLI:
|
||||
"clear",
|
||||
"This clears the screen and starts a new session.\n"
|
||||
"The current conversation history will be discarded.",
|
||||
cmd_original=cmd_original,
|
||||
) is None:
|
||||
return
|
||||
self.new_session(silent=True)
|
||||
@@ -8251,16 +8226,12 @@ class HermesCLI:
|
||||
if not self._handle_handoff_command(cmd_original):
|
||||
return False
|
||||
elif canonical == "new":
|
||||
# Strip inline-skip tokens (now/--yes/-y) before deriving the title
|
||||
# so "/new now My Session" yields title="My Session" instead of
|
||||
# title="now My Session". See _split_destructive_skip.
|
||||
_new_args, _ = self._split_destructive_skip(cmd_original)
|
||||
title = _new_args.strip() or None
|
||||
parts = cmd_original.split(maxsplit=1)
|
||||
title = parts[1].strip() if len(parts) > 1 else None
|
||||
if self._confirm_destructive_slash(
|
||||
"new",
|
||||
"This starts a fresh session.\n"
|
||||
"The current conversation history will be discarded.",
|
||||
cmd_original=cmd_original,
|
||||
) is None:
|
||||
return
|
||||
self.new_session(title=title)
|
||||
@@ -8287,7 +8258,6 @@ class HermesCLI:
|
||||
if self._confirm_destructive_slash(
|
||||
"undo",
|
||||
"This removes the last user/assistant exchange from history.",
|
||||
cmd_original=cmd_original,
|
||||
) is None:
|
||||
return
|
||||
self.undo_last()
|
||||
@@ -9365,23 +9335,18 @@ class HermesCLI:
|
||||
_cprint(" Failed to save runtime_footer setting to config.yaml")
|
||||
|
||||
def _toggle_verbose(self):
|
||||
"""Cycle tool progress mode: off → new → all → verbose → off.
|
||||
|
||||
Tool-progress display (full args / results / think blocks at the
|
||||
``verbose`` step) is INDEPENDENT of global DEBUG logging. Cycling
|
||||
through here does not change ``self.verbose`` or the agent's
|
||||
``verbose_logging`` / ``quiet_mode`` — those remain under the
|
||||
explicit ``-v``/``--verbose`` flag and the ``/verbose-logging``
|
||||
toggle. See PR #6a1aa420e for the history that decoupled them.
|
||||
"""
|
||||
"""Cycle tool progress mode: off → new → all → verbose → off."""
|
||||
cycle = ["off", "new", "all", "verbose"]
|
||||
try:
|
||||
idx = cycle.index(self.tool_progress_mode)
|
||||
except ValueError:
|
||||
idx = 2 # default to "all"
|
||||
self.tool_progress_mode = cycle[(idx + 1) % len(cycle)]
|
||||
self.verbose = self.tool_progress_mode == "verbose"
|
||||
|
||||
if self.agent:
|
||||
self.agent.verbose_logging = self.verbose
|
||||
self.agent.quiet_mode = not self.verbose
|
||||
self.agent.reasoning_callback = self._current_reasoning_callback()
|
||||
|
||||
# Use raw ANSI codes via _cprint so the output is routed through
|
||||
@@ -9393,7 +9358,7 @@ class HermesCLI:
|
||||
"off": f"{_Colors.DIM}Tool progress: OFF{_Colors.RESET} — silent mode, just the final response.",
|
||||
"new": f"{_Colors.YELLOW}Tool progress: NEW{_Colors.RESET} — show each new tool (skip repeats).",
|
||||
"all": f"{_Colors.GREEN}Tool progress: ALL{_Colors.RESET} — show every tool call.",
|
||||
"verbose": f"{_Colors.BOLD}{_Colors.GREEN}Tool progress: VERBOSE{_Colors.RESET} — full args, results, and think blocks.",
|
||||
"verbose": f"{_Colors.BOLD}{_Colors.GREEN}Tool progress: VERBOSE{_Colors.RESET} — full args, results, think blocks, and debug logs.",
|
||||
}
|
||||
_cprint(labels.get(self.tool_progress_mode, ""))
|
||||
|
||||
@@ -9939,49 +9904,7 @@ class HermesCLI:
|
||||
if _reload_thread.is_alive():
|
||||
print(" ⚠️ MCP reload timed out (30s). Some servers may not have reconnected.")
|
||||
|
||||
# Inline-skip tokens that bypass the destructive-slash confirmation modal.
|
||||
# Matches the escape-hatch pattern users on broken modal platforms
|
||||
# (currently native Windows PowerShell — issue #30768) need to self-serve
|
||||
# without having to flip approvals.destructive_slash_confirm in config.
|
||||
_DESTRUCTIVE_SKIP_TOKENS = frozenset({"now", "--yes", "-y"})
|
||||
|
||||
@classmethod
|
||||
def _split_destructive_skip(cls, cmd_text: Optional[str]) -> tuple[str, bool]:
|
||||
"""Split inline-skip tokens out of a destructive slash command.
|
||||
|
||||
Returns ``(remainder, skip)`` where ``remainder`` is the original
|
||||
text with the command word and any recognized skip tokens removed,
|
||||
and ``skip`` is True iff at least one skip token was found.
|
||||
|
||||
Examples:
|
||||
"/reset now" -> ("", True)
|
||||
"/reset --yes My title" -> ("My title", True)
|
||||
"/new My title" -> ("My title", False)
|
||||
"/clear" -> ("", False)
|
||||
"""
|
||||
if not cmd_text:
|
||||
return "", False
|
||||
tokens = cmd_text.strip().split()
|
||||
if not tokens:
|
||||
return "", False
|
||||
# Drop leading "/cmd" word — callers pass the full command text.
|
||||
if tokens[0].startswith("/"):
|
||||
tokens = tokens[1:]
|
||||
skip = False
|
||||
kept: list[str] = []
|
||||
for tok in tokens:
|
||||
if tok.lower() in cls._DESTRUCTIVE_SKIP_TOKENS:
|
||||
skip = True
|
||||
continue
|
||||
kept.append(tok)
|
||||
return " ".join(kept), skip
|
||||
|
||||
def _confirm_destructive_slash(
|
||||
self,
|
||||
command: str,
|
||||
detail: str,
|
||||
cmd_original: Optional[str] = None,
|
||||
) -> Optional[str]:
|
||||
def _confirm_destructive_slash(self, command: str, detail: str) -> Optional[str]:
|
||||
"""Prompt the user to confirm a destructive session slash command.
|
||||
|
||||
Used by ``/clear``, ``/new``/``/reset``, and ``/undo`` before they
|
||||
@@ -9997,24 +9920,9 @@ class HermesCLI:
|
||||
gate is off the function returns ``"once"`` immediately without
|
||||
prompting.
|
||||
|
||||
Inline-skip: if ``cmd_original`` contains ``now``, ``--yes``, or
|
||||
``-y`` as an argument (e.g. ``/reset now``, ``/new --yes My title``),
|
||||
the modal is bypassed and ``"once"`` is returned immediately. This is
|
||||
an escape hatch for platforms where the prompt_toolkit modal hangs
|
||||
(issue #30768 — native Windows PowerShell). Callers are responsible
|
||||
for stripping the skip tokens from any remaining argument parsing
|
||||
(see :meth:`_split_destructive_skip`).
|
||||
|
||||
Returns ``"once"``, ``"always"``, or ``None`` (cancelled). Callers
|
||||
proceed with the destructive action when the result is non-None.
|
||||
"""
|
||||
# Inline-skip escape hatch — works regardless of platform/modal state.
|
||||
# See class-level _DESTRUCTIVE_SKIP_TOKENS for the accepted tokens.
|
||||
if cmd_original:
|
||||
_, _skip = self._split_destructive_skip(cmd_original)
|
||||
if _skip:
|
||||
return "once"
|
||||
|
||||
# Gate check — respects prior "Always Approve" clicks.
|
||||
try:
|
||||
cfg = load_cli_config()
|
||||
@@ -10349,7 +10257,9 @@ class HermesCLI:
|
||||
self._last_scrollback_tool = function_name
|
||||
try:
|
||||
from agent.display import get_cute_tool_message
|
||||
line = get_cute_tool_message(function_name, stored_args, duration, result=kwargs.get("result"))
|
||||
line = get_cute_tool_message(function_name, stored_args, duration)
|
||||
if is_error:
|
||||
line = f"{line} [error]"
|
||||
_cprint(f" {line}")
|
||||
except Exception:
|
||||
pass
|
||||
@@ -14522,7 +14432,7 @@ def main(
|
||||
api_key: str = None,
|
||||
base_url: str = None,
|
||||
max_turns: int = None,
|
||||
verbose: Optional[bool] = None,
|
||||
verbose: bool = False,
|
||||
quiet: bool = False,
|
||||
compact: bool = False,
|
||||
list_tools: bool = False,
|
||||
@@ -14868,6 +14778,4 @@ def main(
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import fire
|
||||
|
||||
fire.Fire(main)
|
||||
|
||||
+5
-10
@@ -6,22 +6,17 @@
|
||||
#
|
||||
# Set HERMES_UID / HERMES_GID to the host user that owns ~/.hermes so
|
||||
# files created inside the container stay readable/writable on the host.
|
||||
# The s6-overlay stage2 hook remaps the internal `hermes` user to these
|
||||
# values via usermod/groupmod; each supervised service then drops to that
|
||||
# user via `s6-setuidgid`.
|
||||
# The entrypoint remaps the internal `hermes` user to these values via
|
||||
# usermod/groupmod + gosu.
|
||||
#
|
||||
# Security notes:
|
||||
# - The dashboard service binds to 127.0.0.1 by default. It stores API
|
||||
# keys; exposing it on LAN without auth is unsafe. If you want remote
|
||||
# access, use an SSH tunnel or put it behind a reverse proxy that
|
||||
# adds authentication — do NOT pass --insecure --host 0.0.0.0.
|
||||
# - If you override entrypoint, keep `/init` as the first command in
|
||||
# the chain (or let docker use the image's default ENTRYPOINT,
|
||||
# which is `["/init", "/opt/hermes/docker/main-wrapper.sh"]`).
|
||||
# `/init` is s6-overlay's PID 1 — it runs the cont-init.d scripts
|
||||
# (chown, profile reconcile, dashboard toggle) and sets up the
|
||||
# supervision tree before any service starts. Bypassing it skips
|
||||
# all of that setup and the gateway will not work correctly.
|
||||
# - If you override entrypoint, keep /opt/hermes/docker/entrypoint.sh in
|
||||
# the command chain. It drops root to the hermes user before gateway
|
||||
# files such as gateway.lock are created.
|
||||
# - The gateway's API server is off unless you uncomment API_SERVER_KEY
|
||||
# and API_SERVER_HOST. See docs/user-guide/api-server.md before doing
|
||||
# this on an internet-facing host.
|
||||
|
||||
@@ -1,90 +0,0 @@
|
||||
#!/command/with-contenv sh
|
||||
# shellcheck shell=sh
|
||||
# Make supervise/ trees for ALL declared s6 services queryable and
|
||||
# controllable by the unprivileged hermes user (UID 10000).
|
||||
#
|
||||
# Background (PR #30136 review item I4): the entire s6 lifecycle
|
||||
# (s6-svc, s6-svstat, s6-svwait) is dispatched as the hermes user
|
||||
# inside the container (every Hermes runtime path runs under
|
||||
# ``s6-setuidgid hermes``). But s6-supervise creates each service's
|
||||
# ``supervise/`` and top-level ``event/`` directory with mode 0700
|
||||
# owned by its effective UID — which is root, because s6-supervise
|
||||
# is spawned by s6-svscan running as PID 1. So unprivileged clients
|
||||
# get EACCES on every probe / control call against the slot.
|
||||
#
|
||||
# Two fixes, one in each registration path:
|
||||
#
|
||||
# 1. For RUNTIME-registered profile gateways (created via the s6
|
||||
# runtime register hooks in profiles.py): the Python helper
|
||||
# ``_seed_supervise_skeleton`` pre-creates supervise/ + event/ +
|
||||
# supervise/control owned by hermes BEFORE s6-svscanctl -a fires.
|
||||
# s6-supervise's mkdir/mkfifo are EEXIST-safe, so it inherits our
|
||||
# ownership and never tries to chown back to root.
|
||||
#
|
||||
# 2. For STATIC s6-rc services (dashboard, main-hermes) declared at
|
||||
# image-build time under /etc/s6-overlay/s6-rc.d/*: these are
|
||||
# compiled by s6-rc at boot, and s6-supervise spawns BEFORE
|
||||
# cont-init.d gets to run — so by the time we're here, the
|
||||
# supervise/ tree is already there as root:root 0700. We chown
|
||||
# it here. s6-supervise will keep using the same files; it never
|
||||
# re-asserts ownership on a running service.
|
||||
#
|
||||
# This script runs as root after 01-hermes-setup but before
|
||||
# 02-reconcile-profiles, so the chowns are settled before the
|
||||
# Python reconciler walks the scandir. Lexicographic ordering
|
||||
# guarantees this — the suffix is unusual because we want to slot
|
||||
# in between 01 and the existing 02-reconcile-profiles without
|
||||
# renumbering both (which would be a churn-noise patch on its own).
|
||||
|
||||
set -eu
|
||||
|
||||
# /run/s6-rc/servicedirs holds the live, compiled service directories
|
||||
# for every static (s6-rc) service. Symlinks under /run/service/*
|
||||
# point here. Per-service supervise/ + event/ both need hermes
|
||||
# ownership for s6-svstat etc. to work as hermes.
|
||||
SVC_ROOT=/run/s6-rc/servicedirs
|
||||
|
||||
if [ ! -d "$SVC_ROOT" ]; then
|
||||
echo "[supervise-perms] $SVC_ROOT not present; skipping"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
for svc in "$SVC_ROOT"/*; do
|
||||
[ -d "$svc" ] || continue
|
||||
name=$(basename "$svc")
|
||||
|
||||
# Skip s6-overlay-internal services (they need to stay root-only;
|
||||
# the s6rc-* helpers manage the supervision tree itself).
|
||||
case "$name" in
|
||||
s6rc-*|s6-linux-*)
|
||||
continue
|
||||
;;
|
||||
esac
|
||||
|
||||
# supervise/ tree — needed by s6-svstat / s6-svc.
|
||||
if [ -d "$svc/supervise" ]; then
|
||||
chown -R hermes:hermes "$svc/supervise" 2>/dev/null || \
|
||||
echo "[supervise-perms] could not chown $svc/supervise"
|
||||
# 0710 = group searchable. ``s6-svstat`` only needs to openat
|
||||
# status, not list the dir, but giving the hermes group +x is
|
||||
# the minimum that lets group members access the contents.
|
||||
chmod 0710 "$svc/supervise" 2>/dev/null || true
|
||||
# supervise/control is a FIFO that s6-svc writes commands
|
||||
# into; the hermes user needs +w. Owner is already hermes
|
||||
# after the recursive chown above; widen perms to 0660 so
|
||||
# ``s6-svc`` works for any member of the hermes group too.
|
||||
if [ -p "$svc/supervise/control" ]; then
|
||||
chmod 0660 "$svc/supervise/control" 2>/dev/null || true
|
||||
fi
|
||||
fi
|
||||
|
||||
# Top-level event/ dir — s6-svlisten1 / s6-svwait subscribe here.
|
||||
if [ -d "$svc/event" ]; then
|
||||
chown hermes:hermes "$svc/event" 2>/dev/null || \
|
||||
echo "[supervise-perms] could not chown $svc/event"
|
||||
# Preserve s6's 03730 mode (setgid + g+rwx + sticky).
|
||||
chmod 03730 "$svc/event" 2>/dev/null || true
|
||||
fi
|
||||
done
|
||||
|
||||
echo "[supervise-perms] chowned supervise/ trees for static s6-rc services"
|
||||
@@ -1,46 +0,0 @@
|
||||
#!/command/with-contenv sh
|
||||
# shellcheck shell=sh
|
||||
# Container-boot reconciliation of per-profile gateway s6 services.
|
||||
#
|
||||
# Runs as root after 01-hermes-setup (the stage2 hook) has chowned
|
||||
# the volume and seeded $HERMES_HOME, but before s6-rc starts user
|
||||
# services. /etc/cont-init.d/* scripts run in lexicographic order,
|
||||
# so the `02-` prefix guarantees ordering.
|
||||
#
|
||||
# Service directories under /run/service/ live on tmpfs and are
|
||||
# wiped on every container restart. Profile directories under
|
||||
# $HERMES_HOME/profiles/ live on the persistent VOLUME. This script
|
||||
# walks the persistent profiles, recreates the s6 service slots,
|
||||
# and auto-starts only those whose last recorded state was
|
||||
# `running` — see hermes_cli/container_boot.py.
|
||||
#
|
||||
# Phase 4 also needs hermes-user writes to /run/service/ (so the
|
||||
# profile create/delete hooks can register/unregister at runtime),
|
||||
# so we chown the scandir before invoking the reconciler. We
|
||||
# additionally chown the s6-svscan control FIFO so the hermes user
|
||||
# can send rescan signals via ``s6-svscanctl -a``; without this the
|
||||
# entire runtime-registration path is inert under UID 10000 (the
|
||||
# Python wrapper catches the resulting EACCES, prints a warning,
|
||||
# and swallows the failure).
|
||||
set -e
|
||||
|
||||
# Make the dynamic scandir hermes-writable. The directory itself
|
||||
# starts root-owned by s6-overlay.
|
||||
chown hermes:hermes /run/service 2>/dev/null || true
|
||||
|
||||
# Make the svscan control FIFO hermes-writable so s6-svscanctl -a
|
||||
# / -an work for the hermes user. The FIFO is created by s6-svscan
|
||||
# at PID-1 startup, so by the time this cont-init.d script runs it
|
||||
# already exists. Both ``control`` and ``lock`` need to be writable
|
||||
# for the various svscanctl operations; the directory itself stays
|
||||
# root-owned (we only need to touch the two FIFOs/locks inside).
|
||||
if [ -d /run/service/.s6-svscan ]; then
|
||||
for entry in control lock; do
|
||||
if [ -e "/run/service/.s6-svscan/$entry" ]; then
|
||||
chown hermes:hermes "/run/service/.s6-svscan/$entry" 2>/dev/null || true
|
||||
fi
|
||||
done
|
||||
fi
|
||||
|
||||
exec s6-setuidgid hermes /opt/hermes/.venv/bin/python -m hermes_cli.container_boot
|
||||
|
||||
+158
-25
@@ -1,27 +1,160 @@
|
||||
#!/bin/sh
|
||||
# s6-overlay shim. The real logic lives in docker/stage2-hook.sh, invoked
|
||||
# by /etc/cont-init.d/01-hermes-setup (installed by the Dockerfile). This
|
||||
# file exists so external references to docker/entrypoint.sh still work,
|
||||
# but it's no longer the ENTRYPOINT — /init is.
|
||||
#!/bin/bash
|
||||
# Docker/Podman entrypoint: bootstrap config files into the mounted volume, then run hermes.
|
||||
set -e
|
||||
|
||||
HERMES_HOME="${HERMES_HOME:-/opt/data}"
|
||||
INSTALL_DIR="/opt/hermes"
|
||||
|
||||
# --- Privilege dropping via gosu ---
|
||||
# When started as root (the default for Docker, or fakeroot in rootless Podman),
|
||||
# optionally remap the hermes user/group to match host-side ownership, fix volume
|
||||
# permissions, then re-exec as hermes.
|
||||
if [ "$(id -u)" = "0" ]; then
|
||||
if [ -n "$HERMES_UID" ] && [ "$HERMES_UID" != "$(id -u hermes)" ]; then
|
||||
echo "Changing hermes UID to $HERMES_UID"
|
||||
usermod -u "$HERMES_UID" hermes
|
||||
fi
|
||||
|
||||
if [ -n "$HERMES_GID" ] && [ "$HERMES_GID" != "$(id -g hermes)" ]; then
|
||||
echo "Changing hermes GID to $HERMES_GID"
|
||||
# -o allows non-unique GID (e.g. macOS GID 20 "staff" may already exist
|
||||
# as "dialout" in the Debian-based container image)
|
||||
groupmod -o -g "$HERMES_GID" hermes 2>/dev/null || true
|
||||
fi
|
||||
|
||||
# Fix ownership of the data volume. When HERMES_UID remaps the hermes user,
|
||||
# files created by previous runs (under the old UID) become inaccessible.
|
||||
# Always chown -R when UID was remapped; otherwise only if top-level is wrong.
|
||||
actual_hermes_uid=$(id -u hermes)
|
||||
needs_chown=false
|
||||
if [ -n "$HERMES_UID" ] && [ "$HERMES_UID" != "10000" ]; then
|
||||
needs_chown=true
|
||||
elif [ "$(stat -c %u "$HERMES_HOME" 2>/dev/null)" != "$actual_hermes_uid" ]; then
|
||||
needs_chown=true
|
||||
fi
|
||||
if [ "$needs_chown" = true ]; then
|
||||
echo "Fixing ownership of $HERMES_HOME to hermes ($actual_hermes_uid)"
|
||||
# In rootless Podman the container's "root" is mapped to an unprivileged
|
||||
# host UID — chown will fail. That's fine: the volume is already owned
|
||||
# by the mapped user on the host side.
|
||||
chown -R hermes:hermes "$HERMES_HOME" 2>/dev/null || \
|
||||
echo "Warning: chown failed (rootless container?) — continuing anyway"
|
||||
# The .venv must also be re-chowned when UID is remapped, otherwise
|
||||
# lazy_deps.py cannot install platform packages (discord.py, etc.).
|
||||
chown -R hermes:hermes "$INSTALL_DIR/.venv" 2>/dev/null || \
|
||||
echo "Warning: chown .venv failed (rootless container?) — continuing anyway"
|
||||
fi
|
||||
|
||||
# Ensure config.yaml is readable by the hermes runtime user even if it was
|
||||
# edited on the host after initial ownership setup. Must run here (as root)
|
||||
# rather than after the gosu drop, otherwise a non-root caller like
|
||||
# `docker run -u $(id -u):$(id -g)` hits "Operation not permitted" (#15865).
|
||||
if [ -f "$HERMES_HOME/config.yaml" ]; then
|
||||
chown hermes:hermes "$HERMES_HOME/config.yaml" 2>/dev/null || true
|
||||
chmod 640 "$HERMES_HOME/config.yaml" 2>/dev/null || true
|
||||
fi
|
||||
|
||||
echo "Dropping root privileges"
|
||||
exec gosu hermes "$0" "$@"
|
||||
fi
|
||||
|
||||
# --- Running as hermes from here ---
|
||||
source "${INSTALL_DIR}/.venv/bin/activate"
|
||||
|
||||
# Stamp install method for detect_install_method()
|
||||
echo "docker" > "${HERMES_HOME:=/opt/data}/.install_method" 2>/dev/null || true
|
||||
|
||||
# Create essential directory structure. Cache and platform directories
|
||||
# (cache/images, cache/audio, platforms/whatsapp, etc.) are created on
|
||||
# demand by the application — don't pre-create them here so new installs
|
||||
# get the consolidated layout from get_hermes_dir().
|
||||
# The "home/" subdirectory is a per-profile HOME for subprocesses (git,
|
||||
# ssh, gh, npm …). Without it those tools write to /root which is
|
||||
# ephemeral and shared across profiles. See issue #4426.
|
||||
mkdir -p "$HERMES_HOME"/{cron,sessions,logs,hooks,memories,skills,skins,plans,workspace,home}
|
||||
|
||||
# .env
|
||||
if [ ! -f "$HERMES_HOME/.env" ]; then
|
||||
cp "$INSTALL_DIR/.env.example" "$HERMES_HOME/.env"
|
||||
fi
|
||||
|
||||
# config.yaml
|
||||
if [ ! -f "$HERMES_HOME/config.yaml" ]; then
|
||||
cp "$INSTALL_DIR/cli-config.yaml.example" "$HERMES_HOME/config.yaml"
|
||||
fi
|
||||
|
||||
# SOUL.md
|
||||
if [ ! -f "$HERMES_HOME/SOUL.md" ]; then
|
||||
cp "$INSTALL_DIR/docker/SOUL.md" "$HERMES_HOME/SOUL.md"
|
||||
fi
|
||||
|
||||
# auth.json: bootstrap from env on first boot only. Used by orchestrators
|
||||
# (e.g. provisioning a Hermes VPS from an account-management service) that
|
||||
# need to seed the OAuth refresh credential non-interactively, instead of
|
||||
# walking the user through `hermes setup` + the device-flow login dance.
|
||||
# Subsequent token rotations write back to the same file, which lives on a
|
||||
# persistent volume — so this env var is consumed exactly once at first
|
||||
# boot. The `[ ! -f ... ]` guard is critical: without it, a container
|
||||
# restart would clobber a rotated refresh token with the now-stale value
|
||||
# the orchestrator originally seeded.
|
||||
if [ ! -f "$HERMES_HOME/auth.json" ] && [ -n "$HERMES_AUTH_JSON_BOOTSTRAP" ]; then
|
||||
printf '%s' "$HERMES_AUTH_JSON_BOOTSTRAP" > "$HERMES_HOME/auth.json"
|
||||
chmod 600 "$HERMES_HOME/auth.json"
|
||||
fi
|
||||
|
||||
# Sync bundled skills (manifest-based so user edits are preserved)
|
||||
if [ -d "$INSTALL_DIR/skills" ]; then
|
||||
python3 "$INSTALL_DIR/tools/skills_sync.py"
|
||||
fi
|
||||
|
||||
# Optionally start `hermes dashboard` as a side-process.
|
||||
#
|
||||
# When called directly (e.g. by an old wrapper script that hard-coded
|
||||
# docker/entrypoint.sh as the container ENTRYPOINT, or by an external
|
||||
# orchestration script that invokes it inside the container), forward to
|
||||
# the stage2 hook for parity with the pre-s6 entrypoint behavior. The
|
||||
# stage2 hook only handles cont-init bootstrap (UID remap, chown, config
|
||||
# seed, skills sync); it does NOT exec the CMD. Callers that depended
|
||||
# on the pre-s6 contract "entrypoint.sh sets up state then execs hermes"
|
||||
# will see the bootstrap happen but the CMD will not run from this shim.
|
||||
# Toggled by HERMES_DASHBOARD=1 (also accepts "true"/"yes", case-insensitive).
|
||||
# Host/port/TUI can be overridden via:
|
||||
# HERMES_DASHBOARD_HOST (default 0.0.0.0 — exposed outside the container)
|
||||
# HERMES_DASHBOARD_PORT (default 9119, matches `hermes dashboard` default)
|
||||
# HERMES_DASHBOARD_TUI (already honored by `hermes dashboard` itself)
|
||||
#
|
||||
# Deprecation: this shim is preserved for one release cycle to give
|
||||
# downstream users time to migrate their wrappers to the image's real
|
||||
# ENTRYPOINT (`/init`). It will be removed in a future major release.
|
||||
# Surface a warning to stderr so anyone still invoking this path
|
||||
# sees the migration notice in their logs.
|
||||
echo "[hermes] WARNING: docker/entrypoint.sh is a deprecated shim under " \
|
||||
"s6-overlay. The container's real ENTRYPOINT is /init + " \
|
||||
"main-wrapper.sh; this script only runs the stage2 cont-init hook " \
|
||||
"and does NOT exec the CMD. If you hard-coded docker/entrypoint.sh " \
|
||||
"as your ENTRYPOINT, drop the override — docker will use the image's " \
|
||||
"default ENTRYPOINT (/init), which handles bootstrap AND CMD." >&2
|
||||
exec /opt/hermes/docker/stage2-hook.sh "$@"
|
||||
# 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)
|
||||
# docker run <image> chat -q "..." -> exec `hermes chat -q "..."` (legacy wrap)
|
||||
# docker run <image> sleep infinity -> exec `sleep infinity` directly
|
||||
# docker run <image> bash -> exec `bash` directly
|
||||
#
|
||||
# If the first positional arg resolves to an executable on PATH, we assume the
|
||||
# caller wants to run it directly (needed by the launcher which runs long-lived
|
||||
# `sleep infinity` sandbox containers — see tools/environments/docker.py).
|
||||
# Otherwise we treat the args as a hermes subcommand and wrap with `hermes`,
|
||||
# preserving the documented `docker run <image> <subcommand>` behavior.
|
||||
if [ $# -gt 0 ] && command -v "$1" >/dev/null 2>&1; then
|
||||
exec "$@"
|
||||
fi
|
||||
exec hermes "$@"
|
||||
|
||||
@@ -1,30 +0,0 @@
|
||||
#!/bin/sh
|
||||
# /opt/hermes/docker/main-wrapper.sh — wraps the container's CMD with
|
||||
# the same argument-routing logic the pre-s6 entrypoint.sh used. Runs
|
||||
# as /init's "main program" (Docker CMD) so it inherits stdin/stdout/
|
||||
# stderr from the container.
|
||||
#
|
||||
# Routing:
|
||||
# no args → exec `hermes` (the default)
|
||||
# first arg is an executable → exec it directly (sleep, bash, sh, …)
|
||||
# first arg is anything else → exec `hermes <args>` (subcommand passthrough)
|
||||
#
|
||||
# We drop to the hermes user via `s6-setuidgid` so the supervised
|
||||
# workload runs unprivileged (UID 10000 by default).
|
||||
set -e
|
||||
|
||||
cd /opt/data
|
||||
# shellcheck disable=SC1091
|
||||
. /opt/hermes/.venv/bin/activate
|
||||
|
||||
if [ $# -eq 0 ]; then
|
||||
exec s6-setuidgid hermes hermes
|
||||
fi
|
||||
|
||||
if command -v "$1" >/dev/null 2>&1; then
|
||||
# Bare executable — pass through directly.
|
||||
exec s6-setuidgid hermes "$@"
|
||||
fi
|
||||
|
||||
# Hermes subcommand pass-through.
|
||||
exec s6-setuidgid hermes hermes "$@"
|
||||
@@ -1,30 +0,0 @@
|
||||
#!/command/with-contenv sh
|
||||
# shellcheck shell=sh
|
||||
# Dashboard finish script. Companion to ./run.
|
||||
#
|
||||
# When HERMES_DASHBOARD is unset (or falsy), ./run exits 0 immediately.
|
||||
# Without this finish script, s6-supervise would just restart the run
|
||||
# script in a tight loop. By exiting 125 here, we tell s6-supervise
|
||||
# "this service has permanently failed; do not restart" — equivalent
|
||||
# to `s6-svc -O`. The supervise slot reports as down, matching reality
|
||||
# (no dashboard process is running).
|
||||
#
|
||||
# When HERMES_DASHBOARD IS enabled and the run script later exits or
|
||||
# is killed, we want s6-supervise to restart it (the whole point of
|
||||
# supervised lifecycle). So we exit non-125 in that case.
|
||||
|
||||
# Arguments passed to a finish script: $1=run-exit-code, $2=signal-num,
|
||||
# $3=service-dir-name, $4=run-pgid. See servicedir(7).
|
||||
|
||||
case "${HERMES_DASHBOARD:-}" in
|
||||
1|true|TRUE|True|yes|YES|Yes)
|
||||
# Dashboard was enabled — let s6-supervise restart on crash by
|
||||
# exiting non-125. (Pass-through any sensible default.)
|
||||
exit 0
|
||||
;;
|
||||
*)
|
||||
# Dashboard disabled — permanent-failure marker so s6-supervise
|
||||
# leaves the slot in 'down' state and s6-svstat reflects that.
|
||||
exit 125
|
||||
;;
|
||||
esac
|
||||
@@ -1,40 +0,0 @@
|
||||
#!/command/with-contenv sh
|
||||
# shellcheck shell=sh
|
||||
# Dashboard service. Always declared so s6 has a supervised slot; if
|
||||
# HERMES_DASHBOARD isn't truthy the run script exits cleanly and the
|
||||
# companion finish script returns 125 (s6's "permanent failure, do
|
||||
# not restart" marker), so s6-svstat reports the slot as down. See
|
||||
# also docker/s6-rc.d/dashboard/finish.
|
||||
|
||||
case "${HERMES_DASHBOARD:-}" in
|
||||
1|true|TRUE|True|yes|YES|Yes) ;;
|
||||
*)
|
||||
# Exit 0; the finish script will exit 125 → s6-supervise won't
|
||||
# restart us and the slot reports down. Using a clean exit
|
||||
# (rather than `exec sleep infinity`) means s6-svstat reflects
|
||||
# reality: when HERMES_DASHBOARD is unset, the service is NOT
|
||||
# running, just supervised-with-permanent-failure. See PR
|
||||
# #30136 review item I3.
|
||||
exit 0
|
||||
;;
|
||||
esac
|
||||
|
||||
cd /opt/data
|
||||
# shellcheck disable=SC1091
|
||||
. /opt/hermes/.venv/bin/activate
|
||||
|
||||
dash_host="${HERMES_DASHBOARD_HOST:-0.0.0.0}"
|
||||
dash_port="${HERMES_DASHBOARD_PORT:-9119}"
|
||||
|
||||
# Binding to anything other than localhost requires --insecure — the
|
||||
# dashboard refuses otherwise because it exposes API keys. Inside a
|
||||
# container this is the expected deployment.
|
||||
insecure=""
|
||||
case "$dash_host" in
|
||||
127.0.0.1|localhost) ;;
|
||||
*) insecure="--insecure" ;;
|
||||
esac
|
||||
|
||||
# shellcheck disable=SC2086 # word-splitting of $insecure is intentional
|
||||
exec s6-setuidgid hermes hermes dashboard \
|
||||
--host "$dash_host" --port "$dash_port" --no-open $insecure
|
||||
@@ -1 +0,0 @@
|
||||
longrun
|
||||
@@ -1,27 +0,0 @@
|
||||
#!/command/with-contenv sh
|
||||
# shellcheck shell=sh
|
||||
# Main hermes service.
|
||||
#
|
||||
# IMPORTANT — this is NOT how the user's CMD runs.
|
||||
#
|
||||
# We chose Architecture B from the plan: the container's CMD (the bare
|
||||
# command the user passes to `docker run <image> …`) runs as /init's
|
||||
# "main program" via Docker's CMD mechanism, NOT as an s6-supervised
|
||||
# service. This is the canonical s6-overlay pattern for "container
|
||||
# exits when the program exits" semantics, and it lets us preserve
|
||||
# every pre-s6 invocation contract (chat passthrough, sleep infinity,
|
||||
# bash, --tui) without re-implementing argument routing through
|
||||
# /run/s6/container_environment.
|
||||
#
|
||||
# So why does this service exist at all? Two reasons:
|
||||
# 1. s6-rc requires at least one user service for the "user" bundle
|
||||
# to be valid. We can't ship an empty bundle.
|
||||
# 2. Future work may want to supervise a long-lived hermes process
|
||||
# (e.g. for gateway-server containers); having the slot already
|
||||
# wired in keeps that change small.
|
||||
#
|
||||
# For now this service is a no-op: it sleeps forever, doing nothing.
|
||||
# The dashboard runs as a real s6 service alongside it (see
|
||||
# ../dashboard/run) and per-profile gateways register dynamically via
|
||||
# /run/service/ at runtime (Phase 4).
|
||||
exec sleep infinity
|
||||
@@ -1 +0,0 @@
|
||||
longrun
|
||||
@@ -1,134 +0,0 @@
|
||||
#!/bin/sh
|
||||
# s6-overlay stage2 hook — runs as root after the supervision tree is
|
||||
# up but before user services start. Handles UID/GID remap, volume
|
||||
# chown, config seeding, and skills sync.
|
||||
#
|
||||
# Per-service privilege drop happens inside each service's `run` script
|
||||
# (and in main-wrapper.sh) via s6-setuidgid, not here.
|
||||
#
|
||||
# Wired into the image as /etc/cont-init.d/01-hermes-setup by the
|
||||
# Dockerfile. The shim at docker/entrypoint.sh forwards to this script
|
||||
# so external references to docker/entrypoint.sh still work.
|
||||
#
|
||||
# NB: cont-init.d scripts run with no arguments — the user's CMD args
|
||||
# are NOT visible here. That's fine: we use Architecture B (s6-overlay
|
||||
# main-program model), so main-wrapper.sh runs the CMD with full
|
||||
# stdin/stdout/stderr access and handles arg parsing there.
|
||||
|
||||
set -eu
|
||||
|
||||
HERMES_HOME="${HERMES_HOME:-/opt/data}"
|
||||
INSTALL_DIR="/opt/hermes"
|
||||
|
||||
# --- UID/GID remap ---
|
||||
if [ -n "${HERMES_UID:-}" ] && [ "$HERMES_UID" != "$(id -u hermes)" ]; then
|
||||
echo "[stage2] Changing hermes UID to $HERMES_UID"
|
||||
usermod -u "$HERMES_UID" hermes
|
||||
fi
|
||||
if [ -n "${HERMES_GID:-}" ] && [ "$HERMES_GID" != "$(id -g hermes)" ]; then
|
||||
echo "[stage2] Changing hermes GID to $HERMES_GID"
|
||||
# -o allows non-unique GID (e.g. macOS GID 20 "staff" may already
|
||||
# exist as "dialout" in the Debian-based container image).
|
||||
groupmod -o -g "$HERMES_GID" hermes 2>/dev/null || true
|
||||
fi
|
||||
|
||||
# --- Fix ownership of data volume ---
|
||||
actual_hermes_uid=$(id -u hermes)
|
||||
needs_chown=false
|
||||
if [ -n "${HERMES_UID:-}" ] && [ "$HERMES_UID" != "10000" ]; then
|
||||
needs_chown=true
|
||||
elif [ "$(stat -c %u "$HERMES_HOME" 2>/dev/null)" != "$actual_hermes_uid" ]; then
|
||||
needs_chown=true
|
||||
fi
|
||||
if [ "$needs_chown" = true ]; then
|
||||
echo "[stage2] Fixing ownership of $HERMES_HOME to hermes ($actual_hermes_uid)"
|
||||
# In rootless Podman the container's "root" is mapped to an
|
||||
# unprivileged host UID — chown will fail. That's fine: the volume
|
||||
# is already owned by the mapped user on the host side.
|
||||
chown -R hermes:hermes "$HERMES_HOME" 2>/dev/null || \
|
||||
echo "[stage2] Warning: chown failed (rootless container?) — continuing"
|
||||
# The .venv must also be re-chowned when UID is remapped, otherwise
|
||||
# lazy_deps.py cannot install platform packages (discord.py, etc.).
|
||||
chown -R hermes:hermes "$INSTALL_DIR/.venv" 2>/dev/null || \
|
||||
echo "[stage2] Warning: chown .venv failed (rootless container?) — continuing"
|
||||
fi
|
||||
|
||||
# Always reset ownership of $HERMES_HOME/profiles to hermes on every
|
||||
# boot. Profile dirs and files can land owned by root when commands
|
||||
# are invoked via `docker exec <container> hermes …` (which defaults
|
||||
# to root unless `-u` is passed), and that breaks the cont-init
|
||||
# reconciler (02-reconcile-profiles) which runs as hermes and walks
|
||||
# the profiles dir. Idempotent; skipped on rootless containers where
|
||||
# chown would fail.
|
||||
if [ -d "$HERMES_HOME/profiles" ]; then
|
||||
chown -R hermes:hermes "$HERMES_HOME/profiles" 2>/dev/null || true
|
||||
fi
|
||||
|
||||
# --- config.yaml permissions ---
|
||||
# Ensure config.yaml is readable by the hermes runtime user even if it
|
||||
# was edited on the host after initial ownership setup.
|
||||
if [ -f "$HERMES_HOME/config.yaml" ]; then
|
||||
chown hermes:hermes "$HERMES_HOME/config.yaml" 2>/dev/null || true
|
||||
chmod 640 "$HERMES_HOME/config.yaml" 2>/dev/null || true
|
||||
fi
|
||||
|
||||
# --- Seed directory structure as hermes user ---
|
||||
# Run as hermes via s6-setuidgid so dirs end up owned correctly (matters
|
||||
# under rootless Podman where chown back to root would fail).
|
||||
#
|
||||
# Use direct `mkdir -p` invocation (no `sh -c "..."` wrapper) so the
|
||||
# shell isn't a second interpreter — defends against $HERMES_HOME values
|
||||
# containing shell metacharacters. PR #30136 review item O2.
|
||||
s6-setuidgid hermes mkdir -p \
|
||||
"$HERMES_HOME/cron" \
|
||||
"$HERMES_HOME/sessions" \
|
||||
"$HERMES_HOME/logs" \
|
||||
"$HERMES_HOME/hooks" \
|
||||
"$HERMES_HOME/memories" \
|
||||
"$HERMES_HOME/skills" \
|
||||
"$HERMES_HOME/skins" \
|
||||
"$HERMES_HOME/plans" \
|
||||
"$HERMES_HOME/workspace" \
|
||||
"$HERMES_HOME/home"
|
||||
|
||||
# --- Install-method stamp (read by detect_install_method() in hermes status) ---
|
||||
# Preserved from the tini-era entrypoint (PR #27843). Must be written as
|
||||
# the hermes user so ownership matches the file's documented owner.
|
||||
# tee is invoked directly via s6-setuidgid (no `sh -c` wrapper) for the
|
||||
# same shell-metacharacter safety described above.
|
||||
printf 'docker\n' | s6-setuidgid hermes tee "$HERMES_HOME/.install_method" >/dev/null \
|
||||
|| true
|
||||
|
||||
# --- Seed config files (only on first boot) ---
|
||||
seed_one() {
|
||||
dest=$1
|
||||
src=$2
|
||||
if [ ! -f "$HERMES_HOME/$dest" ] && [ -f "$INSTALL_DIR/$src" ]; then
|
||||
s6-setuidgid hermes cp "$INSTALL_DIR/$src" "$HERMES_HOME/$dest"
|
||||
fi
|
||||
}
|
||||
seed_one ".env" ".env.example"
|
||||
seed_one "config.yaml" "cli-config.yaml.example"
|
||||
seed_one "SOUL.md" "docker/SOUL.md"
|
||||
|
||||
# auth.json: bootstrap from env on first boot only. Same semantics as the
|
||||
# pre-s6 entrypoint — the [ ! -f ] guard is critical to avoid clobbering
|
||||
# rotated refresh tokens on container restart.
|
||||
if [ ! -f "$HERMES_HOME/auth.json" ] && [ -n "${HERMES_AUTH_JSON_BOOTSTRAP:-}" ]; then
|
||||
printf '%s' "$HERMES_AUTH_JSON_BOOTSTRAP" > "$HERMES_HOME/auth.json"
|
||||
chown hermes:hermes "$HERMES_HOME/auth.json" 2>/dev/null || true
|
||||
chmod 600 "$HERMES_HOME/auth.json"
|
||||
fi
|
||||
|
||||
# --- Sync bundled skills ---
|
||||
# Invoke the venv's python by absolute path so we don't need a `sh -c`
|
||||
# wrapper to source the activate script. This is safe because
|
||||
# skills_sync.py doesn't depend on any environment exports beyond what
|
||||
# the python binary's own bin-stub already sets up (sys.path is rooted
|
||||
# at the venv's site-packages by virtue of running .venv/bin/python).
|
||||
if [ -d "$INSTALL_DIR/skills" ]; then
|
||||
s6-setuidgid hermes "$INSTALL_DIR/.venv/bin/python" "$INSTALL_DIR/tools/skills_sync.py" \
|
||||
|| echo "[stage2] Warning: skills_sync.py failed; continuing"
|
||||
fi
|
||||
|
||||
echo "[stage2] Setup complete; starting user services"
|
||||
@@ -1,434 +0,0 @@
|
||||
# s6-overlay Supervision for Per-Profile Gateways in Docker — Implementation Plan
|
||||
|
||||
> **Status: shipped.** Phases 0–5 landed via PR
|
||||
> [NousResearch/hermes-agent#30136](https://github.com/NousResearch/hermes-agent/pull/30136)
|
||||
> in May 2026. This document is preserved as a post-implementation reference
|
||||
> for the architecture and the resolved design questions. The phase-by-phase
|
||||
> TDD walkthrough (≈2,800 lines) and the v2/v3 re-validation preambles have
|
||||
> been removed — the canonical implementation history is the PR commit log
|
||||
> (`git log --oneline a957ef083..a6f7171a5 -- 'docker/*' 'hermes_cli/service_manager.py' …`).
|
||||
> Open Questions are collapsed into a single Decision Log table; full
|
||||
> deliberations live in PR review comments.
|
||||
|
||||
**Goal:** Replace `tini` with s6-overlay as PID 1 in the Hermes Docker image so
|
||||
that the main hermes process, the dashboard, and dynamically-created
|
||||
per-profile gateways all run as supervised services (auto-restart on crash,
|
||||
clean shutdown, signal forwarding, zombie reaping). Preserve every existing
|
||||
`docker run …` invocation pattern — including interactive TUI.
|
||||
|
||||
**Architecture:** s6-overlay's `/init` is the container ENTRYPOINT, running
|
||||
s6-svscan as PID 1. Main hermes and the dashboard are declared as static
|
||||
s6-rc services at image build time. Per-profile gateways — which users create
|
||||
*after* the image is built (`hermes profile create coder` →
|
||||
`coder gateway start`) — are registered dynamically by writing service
|
||||
directories under a scandir watched by s6-svscan. A `ServiceManager` protocol
|
||||
abstracts the install/start/stop/restart surface across the init systems we
|
||||
care about (systemd on Linux host, launchd on macOS host, Scheduled Tasks on
|
||||
native Windows host, s6 inside container) and adds a second tier for runtime
|
||||
service registration that only s6 implements.
|
||||
|
||||
**Tech Stack:**
|
||||
|
||||
- [s6-overlay](https://github.com/just-containers/s6-overlay) v3.2.3.0
|
||||
(noarch + per-arch tarballs ~15 MB). SHA256-pinned via build ARGs;
|
||||
multi-arch via `TARGETARCH` (amd64 → `x86_64`, arm64 → `aarch64`).
|
||||
- Debian 13.4 base image (unchanged).
|
||||
- [hadolint](https://github.com/hadolint/hadolint) for the Dockerfile +
|
||||
[shellcheck](https://github.com/koalaman/shellcheck) for entrypoint scripts.
|
||||
- Python subprocess wrappers for `s6-svc`, `s6-svstat`, `s6-svscanctl`.
|
||||
- Existing systemd/launchd/windows surface in `hermes_cli/gateway.py` and
|
||||
`hermes_cli/gateway_windows.py`.
|
||||
|
||||
**Scope:**
|
||||
|
||||
- Container-only (host-side systemd/launchd/windows behavior is preserved,
|
||||
not modified).
|
||||
- s6-overlay only (no pure-Python fallback).
|
||||
- Architecture A (s6 owns PID 1; tini is removed).
|
||||
- Interactive TUI must keep working:
|
||||
`docker run -it --rm nousresearch/hermes-agent:latest --tui`.
|
||||
- Dynamic registration is limited to per-profile gateways — one service per
|
||||
profile, created when a profile is created, torn down when deleted. A
|
||||
`gateway-default` slot is always registered for the root HERMES_HOME
|
||||
profile so `hermes gateway start` (no `-p`) has somewhere to land.
|
||||
|
||||
**Out of scope:**
|
||||
|
||||
- Host-side dynamic supervision (systemd-run / launchd transient plists) —
|
||||
not needed.
|
||||
- Pure-Python supervisor fallback — not needed.
|
||||
- Arbitrary user-defined supervised processes inside the container — only
|
||||
profile gateways.
|
||||
- Migration of existing per-profile systemd unit generation to s6 on the
|
||||
host side.
|
||||
- Non-Docker container runtimes (Podman rootless validated reactively).
|
||||
- UX polish around in-container profile lifecycle (e.g. a nice status view
|
||||
of all supervised profile gateways) — deferred to follow-up.
|
||||
|
||||
---
|
||||
|
||||
## Background From The Codebase
|
||||
|
||||
> **Note on line numbers:** This section refers to functions and structures
|
||||
> by name only. Use `grep -n 'def <name>' <file>` to locate anything below
|
||||
> if you need the current line.
|
||||
|
||||
### Pre-s6 container init (what we replaced)
|
||||
|
||||
The original `Dockerfile` declared
|
||||
`ENTRYPOINT [ "/usr/bin/tini", "-g", "--", "/opt/hermes/docker/entrypoint.sh" ]`.
|
||||
tini was PID 1, reaped zombies, forwarded SIGTERM to the process group. The
|
||||
old `docker/entrypoint.sh`:
|
||||
|
||||
1. `gosu` privilege drop from root → `hermes` UID.
|
||||
2. Copied `.env.example`, `cli-config.yaml.example`, `SOUL.md` into
|
||||
`$HERMES_HOME` if missing.
|
||||
3. Synced bundled skills via `tools/skills_sync.py`.
|
||||
4. Optionally backgrounded `hermes dashboard` in a subshell when
|
||||
`HERMES_DASHBOARD=1` — **not supervised**, no restart.
|
||||
5. `exec hermes "$@"` — tini's sole direct child.
|
||||
|
||||
Known limitations: dashboard crash → stays dead; dashboard fails at startup →
|
||||
silent; gateway crash → dashboard dies too. The May 4, 2026 decision was
|
||||
"leave as is" because nothing in the container needed supervision then.
|
||||
Adding per-profile gateway supervision changed that.
|
||||
|
||||
### ServiceManager surface (what we wrapped, not refactored)
|
||||
|
||||
All init-system logic lives in **`hermes_cli/gateway.py`** (~5,400 LOC at
|
||||
re-validation). The systemd/launchd code is ~1,500 lines of that, plus a
|
||||
separate **`hermes_cli/gateway_windows.py`** (~690 LOC) for Windows
|
||||
Scheduled Tasks.
|
||||
|
||||
| Layer | Systemd functions | Launchd functions | Windows functions |
|
||||
|---|---|---|---|
|
||||
| **Detection** | `supports_systemd_services()`, `_systemd_operational()`, `_wsl_systemd_operational()`, `_container_systemd_operational()` | `is_macos()` | `is_windows()`, `gateway_windows.is_installed()` |
|
||||
| **Paths** | `get_systemd_unit_path(system)`, `get_service_name()` | `get_launchd_plist_path()`, `get_launchd_label()` | `gateway_windows.get_task_name()`, `get_task_script_path()`, `get_startup_entry_path()` |
|
||||
| **Install/lifecycle** | `systemd_install(force, system, run_as_user)`, `systemd_uninstall(system)`, `systemd_start/stop/restart(system)` | `launchd_install(force)`, `launchd_uninstall/start/stop/restart` | `gateway_windows.install/uninstall/start/stop/restart` |
|
||||
| **Probes** | `_probe_systemd_service_running(system)`, `_read_systemd_unit_properties(system)`, `_wait_for_systemd_service_restart`, `_recover_pending_systemd_restart` | `_probe_launchd_service_running()` | `gateway_windows.is_task_registered()`, `_pid_exists` helper |
|
||||
| **D-Bus plumbing** | `_ensure_user_systemd_env`, `_user_systemd_socket_ready`, `_user_systemd_private_socket_path`, `get_systemd_linger_status` | — | — |
|
||||
| **Unit/plist generation** | `generate_systemd_unit(system, run_as_user)`, `systemd_unit_is_current`, `refresh_systemd_unit_if_needed` | plist templating in `launchd_install` | `_build_gateway_cmd_script`, `_build_startup_launcher`, `_write_task_script` |
|
||||
|
||||
Container-relevant callers outside `gateway.py`:
|
||||
|
||||
- `hermes_cli/status.py` — gained an `s6` branch for in-container runs.
|
||||
- `hermes_cli/profiles.py` — `create_profile` / `delete_profile` register and
|
||||
unregister with s6 inside the container (no-op on host).
|
||||
- `hermes_cli/doctor.py` — `_check_gateway_service_linger` skips on s6, and a
|
||||
new "Service Supervisor" section reports main-hermes / dashboard /
|
||||
profile-gateway counts via the ServiceManager.
|
||||
- `hermes_cli/gateway.py::gateway_command` — the
|
||||
`elif is_container():` rejection arms that refused gateway lifecycle
|
||||
operations were removed; the `_dispatch_via_service_manager_if_s6` helper
|
||||
intercepts start/stop/restart and routes them through s6.
|
||||
|
||||
### Per-profile gateway spawning
|
||||
|
||||
`hermes gateway start`, `coder gateway start` (profile alias), and
|
||||
`hermes -p <profile> gateway start` all spawn a gateway process scoped to a
|
||||
given profile. See
|
||||
[Profiles: Running Gateways](https://hermes-agent.nousresearch.com/docs/user-guide/profiles#running-gateways).
|
||||
On host, lifecycle is managed via per-profile systemd units
|
||||
(`hermes-gateway-<profile>.service`); inside the container, an s6 service at
|
||||
`/run/service/gateway-<name>/` is registered when the profile is created and
|
||||
torn down when it's deleted.
|
||||
|
||||
**Persistence across container restart:** `/run/service/` is tmpfs —
|
||||
service registrations are wiped when the container restarts. Profile
|
||||
directories at `/opt/data/profiles/<name>/` live on the persistent VOLUME,
|
||||
and each one records its gateway's last state in `gateway_state.json`.
|
||||
`/etc/cont-init.d/02-reconcile-profiles` walks the persistent profiles on
|
||||
every container boot, recreates the s6 service slots via
|
||||
`hermes_cli/container_boot.py`, and auto-starts those whose last recorded
|
||||
state was `running`. Profiles whose last state was `stopped`,
|
||||
`startup_failed`, `starting`, or absent get their slot recreated in the
|
||||
`down` state and wait for explicit user action. `docker restart` is therefore
|
||||
invisible to a user with running profile gateways: they come back up;
|
||||
stopped ones stay stopped.
|
||||
|
||||
### s6-overlay constraints
|
||||
|
||||
- **Root/non-root model:** `/init` runs as root to set up the supervision
|
||||
tree, install signal handlers, and run the stage2 hook that does
|
||||
`usermod`/`chown`. Each supervised service drops to UID 10000 via
|
||||
`s6-setuidgid hermes` in its `run` script. The per-service `s6-supervise`
|
||||
monitor stays root so it can signal its child regardless of UID. Net
|
||||
effect: hermes and all its subprocesses run as UID 10000 exactly as
|
||||
before; only the supervision tree itself runs as root.
|
||||
- v3.2.3.0 has limited non-root support for running `/init` itself as
|
||||
non-root — some tools (`fix-attrs`, `logutil-service`) assume root. We
|
||||
don't hit this because `/init` runs as root.
|
||||
- Scandir hard cap: `services_max` default 1000, configurable to 160,000.
|
||||
- `/command/with-contenv` sources `/run/s6/container_environment/*` into
|
||||
service env — convenient for passing `HERMES_HOME` etc.
|
||||
- s6 signal semantics: service crash triggers `s6-supervise` restart after
|
||||
1s; override with a `finish` script.
|
||||
- Zombie reaping: PID 1 (s6-svscan) reaps all zombies non-blockingly on
|
||||
SIGCHLD. Any subagent subprocess spawned by the main hermes process is
|
||||
reaped automatically.
|
||||
|
||||
---
|
||||
|
||||
## Key Design Decisions
|
||||
|
||||
### D1. s6-overlay replaces tini entirely
|
||||
|
||||
Container ENTRYPOINT is `/init`, PID 1 is s6-svscan. The main hermes
|
||||
process, the dashboard, and every per-profile gateway run as supervised
|
||||
services. This is a single breaking change to the container contract.
|
||||
|
||||
### D2. Main hermes is an s6 service with container-exit semantics
|
||||
|
||||
The contract "container exits when `hermes` exits" is preserved via a
|
||||
service `finish` script that writes to
|
||||
`/run/s6-linux-init-container-results/exitcode` and calls
|
||||
`/run/s6/basedir/bin/halt`. All five supported invocations work:
|
||||
|
||||
| `docker run <image> …` | Behavior |
|
||||
|---|---|
|
||||
| (no args) | `hermes` with no args, container exits when hermes exits |
|
||||
| `chat -q "..."` | `hermes chat -q "..."`, container exits with hermes exit code |
|
||||
| `sleep infinity` | `sleep infinity` directly (long-lived sandbox mode) |
|
||||
| `bash` | interactive `bash` directly |
|
||||
| `docker run -it … --tui` | interactive Ink TUI with real TTY — see D9 |
|
||||
|
||||
`docker/main-wrapper.sh` detects whether `$1` is an executable on PATH and
|
||||
routes either to "run this as a one-shot main service" or "wrap with
|
||||
hermes".
|
||||
|
||||
### D3. Static services at build time; dynamic (per-profile) services at runtime
|
||||
|
||||
s6 offers two mechanisms:
|
||||
|
||||
- **s6-rc** (declarative, compile-then-swap): used for main hermes and the
|
||||
dashboard — they're known at image build time.
|
||||
- **scandir** (drop a directory + `s6-svscanctl -a`): used for per-profile
|
||||
gateways — profiles are user-created after the image is built.
|
||||
|
||||
Per-profile gateway service dirs live at `/run/service/gateway-<profile>/`
|
||||
(tmpfs, hermes-writable). s6-svscan picks them up on rescan.
|
||||
|
||||
### D4. ServiceManager protocol with two methods for runtime registration
|
||||
|
||||
Host paths (systemd, launchd, Windows Scheduled Tasks) need only
|
||||
install/start/stop/restart of pre-declared services. Inside the container,
|
||||
we additionally need to register services at runtime when a profile is
|
||||
created. The protocol exposes this directly:
|
||||
|
||||
```python
|
||||
class ServiceManager(Protocol):
|
||||
kind: ServiceManagerKind # "systemd" | "launchd" | "windows" | "s6" | "none"
|
||||
|
||||
# Lifecycle of an already-declared service
|
||||
def start(self, name: str) -> None: ...
|
||||
def stop(self, name: str) -> None: ...
|
||||
def restart(self, name: str) -> None: ...
|
||||
def is_running(self, name: str) -> bool: ...
|
||||
|
||||
# Runtime registration (container-only; hosts raise NotImplementedError)
|
||||
def supports_runtime_registration(self) -> bool: ...
|
||||
def register_profile_gateway(
|
||||
self, profile: str, *,
|
||||
extra_env: dict[str, str] | None = None,
|
||||
) -> None: ...
|
||||
def unregister_profile_gateway(self, profile: str) -> None: ...
|
||||
def list_profile_gateways(self) -> list[str]: ...
|
||||
```
|
||||
|
||||
Systemd, launchd, and Windows backends raise `NotImplementedError` on the
|
||||
registration methods. Only the s6 backend implements them. Callers check
|
||||
`supports_runtime_registration()` before calling.
|
||||
|
||||
The scope is intentionally narrow: it's specifically "register/unregister a
|
||||
profile gateway," not a general-purpose process-management API.
|
||||
|
||||
### D5. Per-profile gateway service spec is fixed, not user-provided
|
||||
|
||||
Every profile gateway has the same command shape
|
||||
(`hermes -p <profile> gateway run`, or `hermes gateway run` for the default
|
||||
profile). The s6 backend generates the `run` script from a fixed template
|
||||
given the profile name — no arbitrary command list. This keeps the API
|
||||
surface tight and prevents callers from accidentally registering
|
||||
non-gateway services.
|
||||
|
||||
Port selection is governed by the profile's `config.yaml`
|
||||
(`[gateway] port = …`) — the single source of truth. (The original plan
|
||||
proposed a Python-side SHA-256 port allocator with a 600-port range; it was
|
||||
retired during PR review because it was dead code through the entire stack.)
|
||||
|
||||
### D6. Add detect_service_manager() alongside supports_systemd_services()
|
||||
|
||||
`supports_systemd_services()` stays as-is (host code paths unchanged). A new
|
||||
`detect_service_manager() -> Literal["systemd", "launchd", "windows", "s6", "none"]`
|
||||
composes existing detection functions (`is_macos()`, `is_windows()`,
|
||||
`supports_systemd_services()`, `is_container()` + `_s6_running()`) and adds
|
||||
an s6 branch for container detection. Host call sites continue to use the
|
||||
existing functions; container-only code (the profile hooks) uses the new one.
|
||||
|
||||
`_s6_running()` probes `/proc/1/comm` (world-readable) and
|
||||
`/run/s6/basedir`. The earlier `/proc/1/exe` probe was root-only readable
|
||||
and silently failed for the unprivileged hermes user (UID 10000), making
|
||||
the entire runtime-registration path inert in production — caught in PR
|
||||
review.
|
||||
|
||||
### D7. Wrap existing systemd/launchd/windows functions, don't rewrite them
|
||||
|
||||
`SystemdServiceManager` / `LaunchdServiceManager` / `WindowsServiceManager`
|
||||
are thin adapters over the existing `systemd_*` / `launchd_*` module-level
|
||||
functions in `hermes_cli/gateway.py` and the
|
||||
`gateway_windows.install/uninstall/start/stop/restart/is_installed`
|
||||
functions in `hermes_cli/gateway_windows.py`. We get the abstraction
|
||||
without rewriting ~2,200 LOC of working code.
|
||||
|
||||
### D8. Profile create/delete hooks register/unregister the s6 service
|
||||
|
||||
When `hermes profile create <name>` runs inside the container, the
|
||||
profile-creation code path calls
|
||||
`ServiceManager.register_profile_gateway(<name>)` if
|
||||
`supports_runtime_registration()` is True. When `hermes profile delete
|
||||
<name>` runs, it calls `unregister_profile_gateway(<name>)`. On host, both
|
||||
calls are no-ops (registration not supported; existing systemd unit
|
||||
generation continues to handle install/uninstall).
|
||||
|
||||
Existing per-profile `hermes -p <profile> gateway start/stop/restart` CLI
|
||||
commands continue to work — in the container they dispatch to
|
||||
`ServiceManager.start/stop/restart("gateway-<profile>")`, which translates
|
||||
to `s6-svc -u`/`-d`/`-t` on the service dir.
|
||||
|
||||
`hermes gateway start` (no `-p`) targets a special `gateway-default` slot
|
||||
that's always registered by the cont-init reconciler. Its run script omits
|
||||
the `-p` flag and runs against the root `$HERMES_HOME` profile.
|
||||
|
||||
`--all` lifecycle (`hermes gateway stop --all`, `... restart --all`)
|
||||
iterates `mgr.list_profile_gateways()` through s6 so s6's `want up`/`want
|
||||
down` flips correctly. Without this, `--all` fell through to `pkill`
|
||||
followed by s6-supervise auto-restart — net effect: kick instead of stop.
|
||||
|
||||
### D9. Interactive TUI bypasses s6 service-mode and runs as CMD for TTY passthrough
|
||||
|
||||
`docker run -it --rm <image> --tui` needs a real TTY connected to container
|
||||
stdin/stdout for Ink raw-mode keyboard input, cursor control, and SIGWINCH.
|
||||
Running the TUI as a normal s6 service fails because s6-supervise
|
||||
disconnects service stdio from the container TTY (documented:
|
||||
[s6-overlay#230](https://github.com/just-containers/s6-overlay/issues/230)).
|
||||
|
||||
**The pattern:** s6-overlay's `/init` execs a CMD as the container's "main
|
||||
program" after the supervision tree is up. The CMD inherits
|
||||
stdin/stdout/stderr from `/init` — which in `-it` mode is the container
|
||||
TTY. The stage2 hook detects the TUI case and short-circuits the
|
||||
main-hermes service so the hermes CMD becomes that main program.
|
||||
|
||||
```sh
|
||||
# In docker/stage2-hook.sh
|
||||
_is_tui_invocation() {
|
||||
for arg in "$@"; do
|
||||
case "$arg" in --tui|-T) return 0 ;; esac
|
||||
done
|
||||
case "${HERMES_TUI:-}" in 1|true|TRUE|yes) return 0 ;; esac
|
||||
if [ -t 0 ] && [ $# -eq 0 ]; then return 0; fi
|
||||
return 1
|
||||
}
|
||||
```
|
||||
|
||||
And in `docker/s6-rc.d/main-hermes/run`:
|
||||
|
||||
```sh
|
||||
if [ -f /var/run/s6/container_environment/HERMES_TUI_MODE ]; then
|
||||
exec sleep infinity # s6-overlay will exec CMD as the TTY-connected main
|
||||
fi
|
||||
exec s6-setuidgid hermes hermes ${HERMES_ARGS:-}
|
||||
```
|
||||
|
||||
In TUI mode main hermes is effectively unsupervised (same as the pre-s6
|
||||
behavior with tini — acceptable because the user is interactively
|
||||
present). Dashboard and profile gateways still get full s6 supervision via
|
||||
their separate services.
|
||||
|
||||
The integration test `test_tty_passthrough_to_container` uses `tput cols`
|
||||
and `COLUMNS=123` as the probe.
|
||||
|
||||
---
|
||||
|
||||
## Risk Register
|
||||
|
||||
| Risk | Likelihood | Impact | Mitigation |
|
||||
|---|---|---|---|
|
||||
| Phase 2 breaks a downstream user's Dockerfile that `FROM`s ours | Medium | Medium | Release notes call out ENTRYPOINT change; the test harness (`tests/docker/`) gives high confidence in behavior parity |
|
||||
| TUI TTY passthrough fails on some Docker versions | Low | High | Harness includes `test_tty_passthrough_to_container` as a hard gate; fallback plan = s6-fdholder ([s6-overlay#230](https://github.com/just-containers/s6-overlay/issues/230) Solution 2) |
|
||||
| s6-overlay non-root quirks (logutil-service, fix-attrs) bite us | Low | Low | Supervisor runs as root, services drop — sidesteps these issues |
|
||||
| Podman rootless UID mapping confuses s6 | Medium | Low | Documented as supported, fix reactively; a Podman + Docker environment is stood up for validation |
|
||||
| Test harness is flaky (docker daemon issues, timing) | Medium | Low | Generous timeouts; skip when docker unavailable; polling helpers replace fixed sleeps in `test_container_restart.py` |
|
||||
| Profile gateway crash loop masks a real config error | Low | Medium | s6 `finish` script `max_restarts` cap (planned follow-up); operators see crash-looping logs in `$HERMES_HOME/logs/gateways/<profile>/` |
|
||||
| Dockerfile+entrypoint drift from linter (hadolint/shellcheck) reveals latent bugs | Low | Low | CI lint jobs catch them; fix or document ignore with rationale |
|
||||
| Stale `gateway.pid` from a dead container collides with an unrelated live PID in the restarted container | Low | Medium | Cont-init reconciliation removes `gateway.pid` and `processes.json` from every profile dir on boot, before any new gateway starts |
|
||||
| `docker restart` silently loses per-profile gateway registrations (tmpfs scandir wiped) | High (without mitigation) | High | Cont-init reconciliation re-registers from persistent `$HERMES_HOME/profiles/` and auto-starts those last seen `running`; outcome recorded to `$HERMES_HOME/logs/container-boot.log` (size-bounded, rotates to `.1` at 256 KiB) |
|
||||
| A `running` gateway that's actually broken auto-restarts into a crash loop after every container restart | Low | Medium | s6 `finish` script `max_restarts` cap (planned); follow-up: `hermes doctor` alerts when N consecutive container restarts ended in `startup_failed` |
|
||||
| `_s6_running()` detection works as root but silently fails for unprivileged hermes user, making runtime-registration path inert | High (without mitigation) | High | **Caught in PR review.** Detection now probes `/proc/1/comm` (world-readable) + `/run/s6/basedir`. Docker integration tests refactored to `docker exec -u hermes` so the realistic runtime user is exercised |
|
||||
| `s6-svscanctl` from hermes hits EACCES on the root-owned control FIFO | Medium | Medium | `02-reconcile-profiles` chowns `/run/service/.s6-svscan/{control,lock}` to hermes after stage1 creates them |
|
||||
| Per-service `supervise/control` FIFO is root-owned by s6-supervise, blocking `s6-svc` from hermes | Known | Medium | Surfaced cleanly as `S6CommandError` (with rc + stderr) instead of raw `CalledProcessError`. Permission fix tracked as a follow-up (small SUID helper, polling chown loop in cont-init.d, or replace `s6-svc` with `down`-marker manipulation) |
|
||||
|
||||
---
|
||||
|
||||
## Decision Log
|
||||
|
||||
| # | Question | Decision |
|
||||
|---|---|---|
|
||||
| OQ1 | Gate Phase 2 behind env var? | Ship directly (Hermes is pre-1.0; users can pin the previous image) |
|
||||
| OQ2 | s6 root model | Root `/init`, drop per-service via `s6-setuidgid hermes` |
|
||||
| OQ3 | Dashboard opt-in mechanism | Always declared as an s6 service; `03-dashboard-toggle` cont-init script writes a `down` marker when `HERMES_DASHBOARD` is unset so `s6-svstat` reports the slot's real state |
|
||||
| OQ4 | Podman rootless | Supported, fix reactively |
|
||||
| OQ5 | Service naming | `gateway-<profile>` (matches pre-existing `hermes-gateway-<profile>.service` systemd convention) |
|
||||
| OQ6 | — (retired; no subagent gateways in scope) | — |
|
||||
| OQ7 | Resource limits per profile gateway | Defer (no per-cgroup limits; rely on the container's overall limit) |
|
||||
| OQ8 | Log persistence | `$HERMES_HOME/logs/gateways/<profile>/`. The log path is sourced from runtime `$HERMES_HOME` via `with-contenv`, NOT Python-substituted at registration time |
|
||||
| OQ9 | TUI passthrough | Trust the documented [s6-overlay#230](https://github.com/just-containers/s6-overlay/issues/230) Solution 1; harness includes a TTY passthrough hard-gate test |
|
||||
|
||||
**Post-merge additions from PR #30136 review:**
|
||||
|
||||
- **Multi-arch tarballs:** `TARGETARCH` mapped to `x86_64` / `aarch64`;
|
||||
per-arch tarball fetched via `curl` because `ADD` doesn't honor BuildKit
|
||||
args.
|
||||
- **SHA256 verification:** all three tarballs (noarch, symlinks, per-arch)
|
||||
pinned via build ARGs and verified with `sha256sum -c` against a single
|
||||
checksum file (avoids hadolint DL4006 piped-shell warning).
|
||||
- **`gateway-default` slot:** always registered by the reconciler so
|
||||
`hermes gateway start` (no `-p`) has somewhere to land.
|
||||
- **Friendly lifecycle errors:** `GatewayNotRegisteredError` and
|
||||
`S6CommandError` translate `CalledProcessError` into actionable CLI
|
||||
messages.
|
||||
- **Atomic publication in the reconciler:** mirrors
|
||||
`register_profile_gateway`'s tmp+rename pattern.
|
||||
- **`container-boot.log` rotation:** 256 KiB soft cap, rotated to `.1`.
|
||||
- **`port` parameter retired:** allocator + kwarg were dead code through
|
||||
the entire stack; `config.yaml` is the single source of truth.
|
||||
|
||||
---
|
||||
|
||||
## Verification Checklist
|
||||
|
||||
- [x] Test harness (`tests/docker/`) passes against the s6 image
|
||||
- [x] hadolint + shellcheck run green in CI
|
||||
- [x] `docker run -it --rm hermes-agent --tui` starts the Ink TUI with
|
||||
working keyboard input, cursor control, and resize (SIGWINCH)
|
||||
- [x] Dashboard crashes are recovered by s6 within ~2s
|
||||
- [x] `hermes profile create test` inside a container creates
|
||||
`/run/service/gateway-test/`
|
||||
- [x] `hermes -p test gateway start` inside a container dispatches through s6
|
||||
- [x] `hermes -p test gateway stop` inside a container cleanly stops via s6
|
||||
- [x] `hermes profile delete test` inside a container removes
|
||||
`/run/service/gateway-test/`
|
||||
- [x] Profile gateway logs persist at
|
||||
`$HERMES_HOME/logs/gateways/test/current`
|
||||
- [x] `hermes status` inside the container shows `Manager: s6`
|
||||
- [x] `hermes gateway start` (no `-p`) inside a container targets
|
||||
`gateway-default` and runs against the root profile
|
||||
- [x] `hermes gateway stop --all` / `... restart --all` iterate every
|
||||
profile gateway under s6 instead of pkill-then-supervise-restart
|
||||
- [x] `docker restart` survives per-profile gateway registrations via the
|
||||
cont-init reconciler; running gateways come back up, stopped ones
|
||||
stay down
|
||||
- [x] Multi-arch image builds for both `linux/amd64` and `linux/arm64`
|
||||
- [x] s6-overlay tarballs are SHA256-verified at build time
|
||||
- [x] No systemd/launchd host-side functions were modified (only wrapped)
|
||||
- [x] `hermes gateway install/start/stop` on Linux host and macOS host
|
||||
behave identically to pre-change
|
||||
+23
-101
@@ -424,9 +424,7 @@ _PLATFORM_CONNECTED_CHECKERS: dict[Platform, Callable[[PlatformConfig], bool]] =
|
||||
Platform.SMS: lambda cfg: bool(os.getenv("TWILIO_ACCOUNT_SID")),
|
||||
Platform.API_SERVER: lambda cfg: True,
|
||||
Platform.WEBHOOK: lambda cfg: True,
|
||||
Platform.MSGRAPH_WEBHOOK: lambda cfg: bool(
|
||||
str(cfg.extra.get("client_state") or "").strip()
|
||||
),
|
||||
Platform.MSGRAPH_WEBHOOK: lambda cfg: True,
|
||||
Platform.FEISHU: lambda cfg: bool(cfg.extra.get("app_id")),
|
||||
Platform.WECOM: lambda cfg: bool(cfg.extra.get("bot_id")),
|
||||
Platform.WECOM_CALLBACK: lambda cfg: bool(
|
||||
@@ -1813,17 +1811,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
# need to seed ``PlatformConfig.extra`` from env vars (e.g. Google Chat's
|
||||
# project_id / subscription_name) can supply ``env_enablement_fn`` on
|
||||
# their PlatformEntry — called here BEFORE adapter construction.
|
||||
#
|
||||
# Enablement gate (#31116): when a plugin registers ``is_connected``
|
||||
# (the "has the user actually configured credentials for this?" check),
|
||||
# we MUST consult it before flipping ``enabled = True``. Otherwise
|
||||
# ``check_fn`` alone — which for adapter plugins typically just
|
||||
# verifies the SDK is importable / lazy-installs it — silently enables
|
||||
# platforms the user never opted into, and the gateway then tries to
|
||||
# connect to Discord / Teams / Google Chat with no token and emits
|
||||
# noisy retry-forever errors. ``_platform_status`` was already fixed
|
||||
# for the same bug class in commit 7849a3d73; this is the runtime
|
||||
# counterpart.
|
||||
try:
|
||||
from hermes_cli.plugins import discover_plugins
|
||||
discover_plugins() # idempotent
|
||||
@@ -1836,99 +1823,34 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
|
||||
logger.debug("check_fn for %s raised: %s", entry.name, e)
|
||||
continue
|
||||
platform = Platform(entry.name)
|
||||
existing_cfg = config.platforms.get(platform)
|
||||
# Seed candidate extras from ``env_enablement_fn`` so plugins
|
||||
# whose ``is_connected`` reads ``config.extra`` (e.g. Google
|
||||
# Chat's ``_is_connected`` checks ``config.extra["project_id"]``)
|
||||
# see the same state they will after enablement. Without this,
|
||||
# Google-Chat-on-env-vars-only setups silently fail the gate
|
||||
# below even though the user is configured. Plugins whose
|
||||
# ``is_connected`` reads env vars directly (Discord, IRC,
|
||||
# Teams, LINE, ntfy, Simplex) are unaffected; this only
|
||||
# restores Google Chat.
|
||||
seed_for_probe = None
|
||||
if platform not in config.platforms:
|
||||
config.platforms[platform] = PlatformConfig()
|
||||
config.platforms[platform].enabled = True
|
||||
# Seed extras from env if the plugin opted in.
|
||||
if entry.env_enablement_fn is not None:
|
||||
try:
|
||||
seed_for_probe = entry.env_enablement_fn()
|
||||
seed = entry.env_enablement_fn()
|
||||
except Exception as e:
|
||||
logger.debug(
|
||||
"env_enablement_fn for %s raised: %s", entry.name, e
|
||||
)
|
||||
seed_for_probe = None
|
||||
|
||||
# Only consult is_connected for platforms that are NOT already
|
||||
# explicitly configured in YAML / env (existing_cfg with
|
||||
# enabled=True means the user wrote it themselves or another
|
||||
# env-var bridge enabled it — keep that decision).
|
||||
if existing_cfg is None or not existing_cfg.enabled:
|
||||
if entry.is_connected is not None:
|
||||
try:
|
||||
# Probe with ``enabled=True`` since we're asking
|
||||
# "would this plugin BE configured if we enabled
|
||||
# it?" not "is it currently enabled?". Google
|
||||
# Chat's ``_is_connected`` short-circuits on
|
||||
# ``config.enabled`` being False, which on the
|
||||
# default ``PlatformConfig()`` would fail the
|
||||
# gate even with proper env vars set.
|
||||
if existing_cfg is not None:
|
||||
probe_cfg = existing_cfg
|
||||
if not probe_cfg.enabled:
|
||||
probe_cfg = PlatformConfig(
|
||||
enabled=True,
|
||||
extra=dict(probe_cfg.extra or {}),
|
||||
)
|
||||
else:
|
||||
probe_cfg = PlatformConfig(enabled=True)
|
||||
if isinstance(seed_for_probe, dict) and seed_for_probe:
|
||||
# Don't mutate ``existing_cfg``; the probe gets
|
||||
# a transient view with env-seeded extras layered
|
||||
# on top of whatever's already there.
|
||||
probe_extra = dict(getattr(probe_cfg, "extra", {}) or {})
|
||||
for k, v in seed_for_probe.items():
|
||||
if k == "home_channel":
|
||||
continue
|
||||
probe_extra.setdefault(k, v)
|
||||
probe_cfg = PlatformConfig(
|
||||
enabled=True,
|
||||
extra=probe_extra,
|
||||
)
|
||||
configured = bool(entry.is_connected(probe_cfg))
|
||||
except Exception as exc:
|
||||
logger.debug(
|
||||
"is_connected for %s raised: %s — skipping enablement",
|
||||
entry.name, exc,
|
||||
seed = None
|
||||
if isinstance(seed, dict) and seed:
|
||||
# Extract the home_channel dict (if provided) so we wire it
|
||||
# up as a proper HomeChannel dataclass. Everything else is
|
||||
# merged into ``extra``.
|
||||
home = seed.pop("home_channel", None)
|
||||
config.platforms[platform].extra.update(seed)
|
||||
if isinstance(home, dict) and home.get("chat_id"):
|
||||
config.platforms[platform].home_channel = HomeChannel(
|
||||
platform=platform,
|
||||
chat_id=str(home["chat_id"]),
|
||||
name=str(home.get("name") or "Home"),
|
||||
thread_id=(
|
||||
str(home["thread_id"])
|
||||
if home.get("thread_id")
|
||||
else None
|
||||
),
|
||||
)
|
||||
configured = False
|
||||
if not configured:
|
||||
logger.debug(
|
||||
"Plugin platform '%s' available but not configured "
|
||||
"(is_connected returned False) — skipping enable",
|
||||
entry.name,
|
||||
)
|
||||
continue
|
||||
if platform not in config.platforms:
|
||||
config.platforms[platform] = PlatformConfig()
|
||||
config.platforms[platform].enabled = True
|
||||
# Commit env-seeded extras onto the now-enabled platform.
|
||||
# We've already called ``env_enablement_fn`` above (for the
|
||||
# probe); reuse that result instead of calling it twice.
|
||||
if isinstance(seed_for_probe, dict) and seed_for_probe:
|
||||
seed = dict(seed_for_probe)
|
||||
# Extract the home_channel dict (if provided) so we wire it
|
||||
# up as a proper HomeChannel dataclass. Everything else is
|
||||
# merged into ``extra``.
|
||||
home = seed.pop("home_channel", None)
|
||||
config.platforms[platform].extra.update(seed)
|
||||
if isinstance(home, dict) and home.get("chat_id"):
|
||||
config.platforms[platform].home_channel = HomeChannel(
|
||||
platform=platform,
|
||||
chat_id=str(home["chat_id"]),
|
||||
name=str(home.get("name") or "Home"),
|
||||
thread_id=(
|
||||
str(home["thread_id"])
|
||||
if home.get("thread_id")
|
||||
else None
|
||||
),
|
||||
)
|
||||
except Exception as e:
|
||||
logger.debug("Plugin platform enable pass failed: %s", e)
|
||||
|
||||
@@ -35,7 +35,6 @@ import re
|
||||
import sqlite3
|
||||
import time
|
||||
import uuid
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
try:
|
||||
@@ -338,12 +337,10 @@ class ResponseStore:
|
||||
db_path = str(get_hermes_home() / "response_store.db")
|
||||
except Exception:
|
||||
db_path = ":memory:"
|
||||
self._db_path: Optional[str] = db_path if db_path != ":memory:" else None
|
||||
try:
|
||||
self._conn = sqlite3.connect(db_path, check_same_thread=False)
|
||||
except Exception:
|
||||
self._conn = sqlite3.connect(":memory:", check_same_thread=False)
|
||||
self._db_path = None
|
||||
# Use shared WAL-fallback helper so response_store.db degrades
|
||||
# gracefully on NFS/SMB/FUSE-mounted HERMES_HOME (same filesystem
|
||||
# issue addressed for state.db/kanban.db — see
|
||||
@@ -364,31 +361,6 @@ class ResponseStore:
|
||||
)"""
|
||||
)
|
||||
self._conn.commit()
|
||||
# response_store.db contains conversation history (tool payloads,
|
||||
# prompts, results). Tighten to owner-only after creation so other
|
||||
# local users on a shared box can't read it. Run once at __init__
|
||||
# rather than after every commit — chmod-on-every-write is wasted
|
||||
# syscalls on a hot path.
|
||||
self._tighten_file_permissions()
|
||||
|
||||
def _tighten_file_permissions(self) -> None:
|
||||
"""Force owner-only permissions on the DB and SQLite sidecars."""
|
||||
if not self._db_path:
|
||||
return
|
||||
for candidate in (
|
||||
Path(self._db_path),
|
||||
Path(f"{self._db_path}-wal"),
|
||||
Path(f"{self._db_path}-shm"),
|
||||
):
|
||||
try:
|
||||
if candidate.exists():
|
||||
candidate.chmod(0o600)
|
||||
except OSError:
|
||||
logger.debug(
|
||||
"Failed to restrict response store permissions for %s",
|
||||
candidate,
|
||||
exc_info=True,
|
||||
)
|
||||
|
||||
def get(self, response_id: str) -> Optional[Dict[str, Any]]:
|
||||
"""Retrieve a stored response by ID (updates access time for LRU)."""
|
||||
|
||||
+25
-228
@@ -15,7 +15,6 @@ import re
|
||||
import socket as _socket
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
import uuid
|
||||
from abc import ABC, abstractmethod
|
||||
from urllib.parse import urlsplit
|
||||
@@ -41,16 +40,6 @@ def _platform_name(platform) -> str:
|
||||
return str(value or "").lower()
|
||||
|
||||
|
||||
def _float_env(name: str, default: float) -> float:
|
||||
raw = os.environ.get(name, "").strip()
|
||||
if not raw:
|
||||
return default
|
||||
try:
|
||||
return float(raw)
|
||||
except (TypeError, ValueError):
|
||||
return default
|
||||
|
||||
|
||||
def _thread_metadata_for_source(source, reply_to_message_id: str | None = None) -> dict | None:
|
||||
"""Build platform-aware thread metadata for adapter sends.
|
||||
|
||||
@@ -1114,14 +1103,6 @@ class MessageEvent:
|
||||
return args
|
||||
|
||||
|
||||
@dataclass
|
||||
class TextDebounceState:
|
||||
event: MessageEvent
|
||||
task: asyncio.Task | None
|
||||
first_ts: float
|
||||
last_ts: float
|
||||
|
||||
|
||||
_PLAINTEXT_GATEWAY_RESTART_PATTERNS: tuple[re.Pattern[str], ...] = (
|
||||
re.compile(r"^(?:please\s+)?restart\s+(?:the\s+)?gateway[.!?\s]*$", re.IGNORECASE),
|
||||
re.compile(r"^(?:please\s+)?restart\s+(?:the\s+)?hermes\s+gateway[.!?\s]*$", re.IGNORECASE),
|
||||
@@ -1417,17 +1398,6 @@ class BasePlatformAdapter(ABC):
|
||||
self._active_sessions: Dict[str, asyncio.Event] = {}
|
||||
self._pending_messages: Dict[str, MessageEvent] = {}
|
||||
self._session_tasks: Dict[str, asyncio.Task] = {}
|
||||
self._busy_text_mode: str = (
|
||||
os.environ.get("HERMES_GATEWAY_BUSY_TEXT_MODE", "queue").strip().lower()
|
||||
or "queue"
|
||||
)
|
||||
self._busy_text_debounce_seconds: float = _float_env(
|
||||
"HERMES_GATEWAY_BUSY_TEXT_DEBOUNCE_SECONDS", 0.35
|
||||
)
|
||||
self._busy_text_hard_cap_seconds: float = _float_env(
|
||||
"HERMES_GATEWAY_BUSY_TEXT_HARD_CAP_SECONDS", 1.0
|
||||
)
|
||||
self._text_debounce: dict[str, TextDebounceState] = {}
|
||||
# Background message-processing tasks spawned by handle_message().
|
||||
# Gateway shutdown cancels these so an old gateway instance doesn't keep
|
||||
# working on a task after --replace or manual restarts.
|
||||
@@ -2755,161 +2725,6 @@ class BasePlatformAdapter(ABC):
|
||||
return f"{existing_text}\n\n{new_text}".strip()
|
||||
return existing_text
|
||||
|
||||
def _text_debounce_store(self) -> dict[str, TextDebounceState]:
|
||||
store = getattr(self, "_text_debounce", None)
|
||||
if store is None:
|
||||
store = {}
|
||||
self._text_debounce = store
|
||||
return store
|
||||
|
||||
def _is_queue_text_debounce_candidate(self, event: MessageEvent) -> bool:
|
||||
"""Return True for normal text eligible for queue-mode debounce."""
|
||||
result = (
|
||||
getattr(self, "_busy_text_mode", "queue") == "queue"
|
||||
and event.message_type == MessageType.TEXT
|
||||
and not getattr(event, "internal", False)
|
||||
and not event.is_command()
|
||||
and bool((event.text or "").strip())
|
||||
)
|
||||
if result:
|
||||
logger.debug(
|
||||
"[%s] Queue-text debounce candidate accepted: session=%s text_len=%d",
|
||||
self.name,
|
||||
getattr(event, "session_key", "?"),
|
||||
len(event.text or ""),
|
||||
)
|
||||
return result
|
||||
|
||||
def _can_merge_text_debounce_events(self, existing: MessageEvent, event: MessageEvent) -> bool:
|
||||
"""Return True when two text debounce events came from the same sender."""
|
||||
|
||||
def _identity(candidate: MessageEvent) -> tuple[str, ...] | None:
|
||||
source = getattr(candidate, "source", None)
|
||||
if source is None:
|
||||
return None
|
||||
platform = _platform_name(getattr(source, "platform", None))
|
||||
sender = getattr(source, "user_id_alt", None) or getattr(source, "user_id", None)
|
||||
if sender:
|
||||
return (platform, str(sender))
|
||||
if getattr(source, "chat_type", None) in {"dm", "private"} and getattr(source, "chat_id", None):
|
||||
return (platform, "dm", str(source.chat_id))
|
||||
return None
|
||||
|
||||
existing_sender = _identity(existing)
|
||||
incoming_sender = _identity(event)
|
||||
return existing_sender is not None and existing_sender == incoming_sender
|
||||
|
||||
def _text_debounce_delay(self, session_key: str) -> float:
|
||||
"""Return bounded busy-text debounce delay for ``session_key``."""
|
||||
state = self._text_debounce_store().get(session_key)
|
||||
if state is None:
|
||||
return 0.0
|
||||
now = time.monotonic()
|
||||
window_deadline = state.last_ts + self._busy_text_debounce_seconds
|
||||
hard_cap_deadline = state.first_ts + self._busy_text_hard_cap_seconds
|
||||
return max(0.0, min(window_deadline, hard_cap_deadline) - now)
|
||||
|
||||
async def _queue_text_debounce(self, session_key: str, event: MessageEvent) -> None:
|
||||
"""Buffer normal queue-mode busy text and schedule a bounded flush."""
|
||||
store = self._text_debounce_store()
|
||||
state = store.get(session_key)
|
||||
|
||||
if state is not None and not self._can_merge_text_debounce_events(state.event, event):
|
||||
# Preserve sender attribution in shared sessions. The current
|
||||
# buffer becomes the next pending turn; the new sender starts a
|
||||
# fresh debounce burst when the pending slot allows it.
|
||||
await self._flush_text_debounce_now(session_key)
|
||||
state = store.get(session_key)
|
||||
if state is not None and not self._can_merge_text_debounce_events(state.event, event):
|
||||
existing_pending = self._pending_messages.get(session_key)
|
||||
if existing_pending is not None and self._can_merge_text_debounce_events(existing_pending, event):
|
||||
merge_pending_message_event(
|
||||
self._pending_messages,
|
||||
session_key,
|
||||
event,
|
||||
merge_text=True,
|
||||
)
|
||||
return
|
||||
|
||||
now = time.monotonic()
|
||||
if state is None:
|
||||
state = TextDebounceState(
|
||||
event=event,
|
||||
task=None,
|
||||
first_ts=now,
|
||||
last_ts=now,
|
||||
)
|
||||
store[session_key] = state
|
||||
else:
|
||||
if event.text:
|
||||
state.event.text = (
|
||||
f"{state.event.text}\n{event.text}"
|
||||
if state.event.text
|
||||
else event.text
|
||||
)
|
||||
latest_message_id = getattr(event, "message_id", None)
|
||||
latest_anchor = latest_message_id or getattr(event, "reply_to_message_id", None)
|
||||
if latest_message_id is not None:
|
||||
state.event.message_id = str(latest_message_id)
|
||||
if latest_anchor is not None and hasattr(state.event, "reply_to_message_id"):
|
||||
state.event.reply_to_message_id = str(latest_anchor)
|
||||
state.last_ts = now
|
||||
|
||||
if state.task is not None and not state.task.done():
|
||||
state.task.cancel()
|
||||
|
||||
delay = self._text_debounce_delay(session_key)
|
||||
state.task = asyncio.create_task(self._flush_text_debounce(session_key, delay))
|
||||
|
||||
async def _flush_text_debounce(self, session_key: str, delay: float) -> None:
|
||||
"""Timer task that flushes the debounced text buffer."""
|
||||
try:
|
||||
await asyncio.sleep(delay)
|
||||
await self._flush_text_debounce_now(session_key)
|
||||
except asyncio.CancelledError:
|
||||
return
|
||||
finally:
|
||||
current = asyncio.current_task()
|
||||
state = self._text_debounce_store().get(session_key)
|
||||
if state is not None and state.task is current:
|
||||
state.task = None
|
||||
|
||||
async def _flush_text_debounce_now(self, session_key: str) -> bool:
|
||||
"""Force-flush one debounced busy-text burst into the pending slot."""
|
||||
store = self._text_debounce_store()
|
||||
state = store.get(session_key)
|
||||
if state is None:
|
||||
return False
|
||||
|
||||
current = asyncio.current_task()
|
||||
if state.task is not None and state.task is not current and not state.task.done():
|
||||
state.task.cancel()
|
||||
state.task = None
|
||||
|
||||
existing_pending = self._pending_messages.get(session_key)
|
||||
if (
|
||||
existing_pending is not None
|
||||
and not self._can_merge_text_debounce_events(existing_pending, state.event)
|
||||
):
|
||||
return False
|
||||
|
||||
state = store.pop(session_key, None)
|
||||
if state is None:
|
||||
return False
|
||||
merge_pending_message_event(
|
||||
self._pending_messages,
|
||||
session_key,
|
||||
state.event,
|
||||
merge_text=True,
|
||||
)
|
||||
return True
|
||||
|
||||
def _discard_text_debounce(self, session_key: str) -> None:
|
||||
"""Cancel and drop pending text debounce state for control commands."""
|
||||
state = self._text_debounce_store().pop(session_key, None)
|
||||
if state is not None and state.task is not None and not state.task.done():
|
||||
state.task.cancel()
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Session task + guard ownership helpers
|
||||
# ------------------------------------------------------------------
|
||||
@@ -2979,7 +2794,6 @@ class BasePlatformAdapter(ABC):
|
||||
self._active_sessions.pop(session_key, None)
|
||||
self._pending_messages.pop(session_key, None)
|
||||
self._session_tasks.pop(session_key, None)
|
||||
self._discard_text_debounce(session_key)
|
||||
return True
|
||||
|
||||
def _start_session_processing(
|
||||
@@ -3061,7 +2875,6 @@ class BasePlatformAdapter(ABC):
|
||||
)
|
||||
if discard_pending:
|
||||
self._pending_messages.pop(session_key, None)
|
||||
self._discard_text_debounce(session_key)
|
||||
if release_guard:
|
||||
self._release_session_guard(session_key)
|
||||
|
||||
@@ -3076,7 +2889,6 @@ class BasePlatformAdapter(ABC):
|
||||
command-scoped guard, then — if a follow-up message landed while the
|
||||
command was running — spawns a fresh processing task for it.
|
||||
"""
|
||||
await self._flush_text_debounce_now(session_key)
|
||||
pending_event = self._pending_messages.pop(session_key, None)
|
||||
self._release_session_guard(session_key, guard=command_guard)
|
||||
if pending_event is None:
|
||||
@@ -3208,7 +3020,6 @@ class BasePlatformAdapter(ABC):
|
||||
# through the dedicated handoff path that serializes
|
||||
# cancellation + runner response + pending drain.
|
||||
if cmd in {"stop", "new", "reset"}:
|
||||
self._discard_text_debounce(session_key)
|
||||
try:
|
||||
await self._dispatch_active_session_command(event, session_key, cmd)
|
||||
except Exception as e:
|
||||
@@ -3253,9 +3064,8 @@ class BasePlatformAdapter(ABC):
|
||||
# clarify-intercept can resolve it and unblock the agent.
|
||||
#
|
||||
# Without this bypass: the message gets queued in
|
||||
# _pending_messages as a follow-up turn instead of reaching the
|
||||
# clarify resolver, leaving the agent blocked and discarding the
|
||||
# user's answer.
|
||||
# _pending_messages AND triggers an interrupt, killing the
|
||||
# agent run mid-clarify and discarding the user's answer.
|
||||
# Same shape as the /approve deadlock fix (PR #4926) — both
|
||||
# cases are "agent thread blocked on Event.wait, message must
|
||||
# reach the resolver before being treated as a new turn."
|
||||
@@ -3314,28 +3124,27 @@ class BasePlatformAdapter(ABC):
|
||||
merge_pending_message_event(self._pending_messages, session_key, event)
|
||||
return # Don't interrupt now - will run after current task completes
|
||||
|
||||
if self._is_queue_text_debounce_candidate(event):
|
||||
logger.debug(
|
||||
"[%s] New text message while session %s is active — "
|
||||
"debouncing follow-up (busy_text_mode=queue, window=%.2fs)",
|
||||
self.name,
|
||||
session_key,
|
||||
self._busy_text_debounce_seconds,
|
||||
)
|
||||
await self._queue_text_debounce(session_key, event)
|
||||
else:
|
||||
logger.debug(
|
||||
"[%s] New message while session %s is active — queuing follow-up "
|
||||
"(no interrupt, will cascade after current turn)",
|
||||
self.name,
|
||||
session_key,
|
||||
)
|
||||
merge_pending_message_event(
|
||||
self._pending_messages,
|
||||
session_key,
|
||||
event,
|
||||
merge_text=event.message_type == MessageType.TEXT,
|
||||
)
|
||||
# Default behavior for non-photo follow-ups: interrupt the running agent.
|
||||
#
|
||||
# Use merge_text=True so rapid TEXT follow-ups (#4469) accumulate
|
||||
# into the single pending slot instead of clobbering each other.
|
||||
# Without merging, three rapid messages "A", "B", "C" land like:
|
||||
# _pending_messages[k] = A (interrupts)
|
||||
# _pending_messages[k] = B (replaces A before consumer reads)
|
||||
# _pending_messages[k] = C (replaces B)
|
||||
# ...and only "C" reaches the next turn. merge_pending_message_event
|
||||
# already does the right thing for photo/media bursts; the
|
||||
# ``merge_text=True`` flag extends that to plain TEXT events.
|
||||
# Same shape as the Telegram bursty-grace path in gateway/run.py.
|
||||
logger.debug("[%s] New message while session %s is active — triggering interrupt", self.name, session_key)
|
||||
merge_pending_message_event(
|
||||
self._pending_messages,
|
||||
session_key,
|
||||
event,
|
||||
merge_text=True,
|
||||
)
|
||||
# Signal the interrupt (the processing task checks this)
|
||||
self._active_sessions[session_key].set()
|
||||
return # Don't process now - will be handled after current task finishes
|
||||
|
||||
# Mark session as active BEFORE spawning background task to close
|
||||
@@ -3689,15 +3498,10 @@ class BasePlatformAdapter(ABC):
|
||||
ProcessingOutcome.SUCCESS if processing_ok else ProcessingOutcome.FAILURE,
|
||||
)
|
||||
|
||||
# The active drain owns debounce state. If a queue-mode timer has
|
||||
# not fired yet, force-flush into _pending_messages here and let
|
||||
# this task hand off the follow-up.
|
||||
await self._flush_text_debounce_now(session_key)
|
||||
|
||||
# Check if there's a pending message that was queued during our processing
|
||||
if session_key in self._pending_messages:
|
||||
pending_event = self._pending_messages.pop(session_key)
|
||||
logger.debug("[%s] Processing queued follow-up message", self.name)
|
||||
logger.debug("[%s] Processing queued message from interrupt", self.name)
|
||||
# Keep the _active_sessions entry live across the turn chain
|
||||
# and only CLEAR the interrupt Event — do NOT delete the entry.
|
||||
# If we deleted here, a concurrent inbound message arriving
|
||||
@@ -3706,7 +3510,7 @@ class BasePlatformAdapter(ABC):
|
||||
# with the recursive drain below. Two agents on one
|
||||
# session_key = duplicate responses, duplicate tool calls.
|
||||
# Clearing the Event keeps the guard live so follow-ups take
|
||||
# the busy-handler path as intended.
|
||||
# the busy-handler path (queue + interrupt) as intended.
|
||||
_active = self._active_sessions.get(session_key)
|
||||
if _active is not None:
|
||||
_active.clear()
|
||||
@@ -3799,9 +3603,6 @@ class BasePlatformAdapter(ABC):
|
||||
await self.stop_typing(event.source.chat_id)
|
||||
except Exception:
|
||||
pass
|
||||
# Final drain/release boundary: force-flush any timer that missed
|
||||
# the in-band drain before deciding whether the guard can clear.
|
||||
await self._flush_text_debounce_now(session_key)
|
||||
# Late-arrival drain: a message may have arrived during the
|
||||
# cleanup awaits above (typing_task cancel, stop_typing). Such
|
||||
# messages passed the Level-1 guard (entry still live, Event
|
||||
@@ -3921,10 +3722,6 @@ class BasePlatformAdapter(ABC):
|
||||
self._session_tasks.clear()
|
||||
self._pending_messages.clear()
|
||||
self._active_sessions.clear()
|
||||
for state in list(self._text_debounce_store().values()):
|
||||
if state.task is not None and not state.task.done():
|
||||
state.task.cancel()
|
||||
self._text_debounce_store().clear()
|
||||
|
||||
def has_pending_interrupt(self, session_key: str) -> bool:
|
||||
"""Check if there's a pending interrupt for a session."""
|
||||
|
||||
@@ -189,10 +189,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
|
||||
app = web.Application()
|
||||
app.router.add_get("/health", lambda _: web.Response(text="ok"))
|
||||
app.router.add_post(self.webhook_path, self._handle_webhook)
|
||||
# The webhook auth value is carried in the query string because the
|
||||
# BlueBubbles webhook API cannot send custom headers. Do not let
|
||||
# aiohttp access logs write that request target to agent.log.
|
||||
self._runner = web.AppRunner(app, access_log=None)
|
||||
self._runner = web.AppRunner(app)
|
||||
await self._runner.setup()
|
||||
site = web.TCPSite(self._runner, self.webhook_host, self.webhook_port)
|
||||
await site.start()
|
||||
@@ -245,14 +242,6 @@ class BlueBubblesAdapter(BasePlatformAdapter):
|
||||
return f"{base}?password={quote(self.password, safe='')}"
|
||||
return base
|
||||
|
||||
@property
|
||||
def _webhook_register_url_for_log(self) -> str:
|
||||
"""Webhook registration URL safe for logs."""
|
||||
base = self._webhook_url
|
||||
if self.password:
|
||||
return f"{base}?password=***"
|
||||
return base
|
||||
|
||||
async def _find_registered_webhooks(self, url: str) -> list:
|
||||
"""Return list of BB webhook entries matching *url*."""
|
||||
try:
|
||||
@@ -280,8 +269,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
|
||||
existing = await self._find_registered_webhooks(webhook_url)
|
||||
if existing:
|
||||
logger.info(
|
||||
"[bluebubbles] webhook already registered: %s",
|
||||
self._webhook_register_url_for_log,
|
||||
"[bluebubbles] webhook already registered: %s", webhook_url
|
||||
)
|
||||
return True
|
||||
|
||||
@@ -296,7 +284,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
|
||||
if 200 <= status < 300:
|
||||
logger.info(
|
||||
"[bluebubbles] webhook registered with server: %s",
|
||||
self._webhook_register_url_for_log,
|
||||
webhook_url,
|
||||
)
|
||||
return True
|
||||
else:
|
||||
@@ -336,8 +324,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
|
||||
removed = True
|
||||
if removed:
|
||||
logger.info(
|
||||
"[bluebubbles] webhook unregistered: %s",
|
||||
self._webhook_register_url_for_log,
|
||||
"[bluebubbles] webhook unregistered: %s", webhook_url
|
||||
)
|
||||
except Exception as exc:
|
||||
logger.debug(
|
||||
@@ -947,3 +934,4 @@ class BlueBubblesAdapter(BasePlatformAdapter):
|
||||
asyncio.create_task(self.mark_read(session_chat_id))
|
||||
|
||||
return web.Response(text="ok")
|
||||
|
||||
|
||||
@@ -358,19 +358,6 @@ class DingTalkAdapter(BasePlatformAdapter):
|
||||
await asyncio.gather(*self._bg_tasks, return_exceptions=True)
|
||||
self._bg_tasks.clear()
|
||||
|
||||
# Finalize any open streaming cards before the HTTP client closes so
|
||||
# they don't stay stuck in streaming state on DingTalk's UI after
|
||||
# a gateway restart. _close_streaming_siblings handles its own
|
||||
# per-card exceptions; the outer try is a safety net for token fetch.
|
||||
for _chat_id in list(self._streaming_cards):
|
||||
try:
|
||||
await self._close_streaming_siblings(_chat_id)
|
||||
except Exception as _exc:
|
||||
logger.debug(
|
||||
"[%s] Failed to finalize streaming card on disconnect for %s: %s",
|
||||
self.name, _chat_id, _exc,
|
||||
)
|
||||
|
||||
if self._http_client:
|
||||
await self._http_client.aclose()
|
||||
self._http_client = None
|
||||
|
||||
+10
-72
@@ -1514,10 +1514,8 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
connection_mode=str(
|
||||
extra.get("connection_mode") or os.getenv("FEISHU_CONNECTION_MODE", "websocket")
|
||||
).strip().lower(),
|
||||
encrypt_key=str(extra.get("encrypt_key") or os.getenv("FEISHU_ENCRYPT_KEY", "")).strip(),
|
||||
verification_token=str(
|
||||
extra.get("verification_token") or os.getenv("FEISHU_VERIFICATION_TOKEN", "")
|
||||
).strip(),
|
||||
encrypt_key=os.getenv("FEISHU_ENCRYPT_KEY", "").strip(),
|
||||
verification_token=os.getenv("FEISHU_VERIFICATION_TOKEN", "").strip(),
|
||||
group_policy=os.getenv("FEISHU_GROUP_POLICY", "allowlist").strip().lower(),
|
||||
allowed_group_users=frozenset(
|
||||
item.strip()
|
||||
@@ -1644,11 +1642,6 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
self._connection_mode,
|
||||
)
|
||||
return False
|
||||
if self._connection_mode == "webhook" and not (self._verification_token or self._encrypt_key):
|
||||
logger.error(
|
||||
"[Feishu] Webhook mode requires FEISHU_VERIFICATION_TOKEN or FEISHU_ENCRYPT_KEY."
|
||||
)
|
||||
return False
|
||||
|
||||
try:
|
||||
self._app_lock_identity = self._app_id
|
||||
@@ -2570,44 +2563,13 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
if approval_id is None:
|
||||
logger.debug("[Feishu] Card action missing approval_id, ignoring")
|
||||
return P2CardActionTriggerResponse() if P2CardActionTriggerResponse else None
|
||||
state = self._approval_state.get(approval_id)
|
||||
if not state:
|
||||
logger.debug("[Feishu] Approval %s already resolved or unknown", approval_id)
|
||||
return P2CardActionTriggerResponse() if P2CardActionTriggerResponse else None
|
||||
choice = _APPROVAL_CHOICE_MAP.get(action_value.get("hermes_action"), "deny")
|
||||
|
||||
operator = getattr(event, "operator", None)
|
||||
open_id = str(getattr(operator, "open_id", "") or "")
|
||||
sender_id = SimpleNamespace(open_id=open_id, user_id=str(getattr(operator, "user_id", "") or ""))
|
||||
if not self._allow_group_message(sender_id, state.get("chat_id", ""), is_bot=False):
|
||||
logger.warning("[Feishu] Unauthorized approval click by %s", open_id or "<unknown>")
|
||||
return P2CardActionTriggerResponse() if P2CardActionTriggerResponse else None
|
||||
|
||||
callback_chat_id = str(getattr(getattr(event, "context", None), "open_chat_id", "") or "")
|
||||
expected_chat_id = str(state.get("chat_id", "") or "")
|
||||
if callback_chat_id and expected_chat_id and callback_chat_id != expected_chat_id:
|
||||
logger.warning(
|
||||
"[Feishu] Approval callback chat mismatch for %s (expected=%s, got=%s)",
|
||||
approval_id,
|
||||
expected_chat_id,
|
||||
callback_chat_id,
|
||||
)
|
||||
return P2CardActionTriggerResponse() if P2CardActionTriggerResponse else None
|
||||
|
||||
user_name = self._get_cached_sender_name(open_id) or open_id
|
||||
|
||||
chat_context = getattr(event, "context", None)
|
||||
chat_id = str(getattr(chat_context, "open_chat_id", "") or "")
|
||||
if not self._submit_on_loop(
|
||||
loop,
|
||||
self._resolve_approval(
|
||||
approval_id=approval_id,
|
||||
choice=choice,
|
||||
user_name=user_name,
|
||||
open_id=open_id,
|
||||
chat_id=chat_id,
|
||||
),
|
||||
):
|
||||
if not self._submit_on_loop(loop, self._resolve_approval(approval_id, choice, user_name)):
|
||||
return P2CardActionTriggerResponse() if P2CardActionTriggerResponse else None
|
||||
|
||||
if P2CardActionTriggerResponse is None:
|
||||
@@ -2655,33 +2617,11 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
response.card = card
|
||||
return response
|
||||
|
||||
async def _resolve_approval(
|
||||
self,
|
||||
approval_id: Any,
|
||||
choice: str,
|
||||
user_name: str,
|
||||
*,
|
||||
open_id: str = "",
|
||||
chat_id: str = "",
|
||||
) -> None:
|
||||
async def _resolve_approval(self, approval_id: Any, choice: str, user_name: str) -> None:
|
||||
"""Pop approval state and unblock the waiting agent thread."""
|
||||
state = self._approval_state.get(approval_id)
|
||||
if not state:
|
||||
logger.debug("[Feishu] Approval %s already resolved or unknown", approval_id)
|
||||
return
|
||||
if not self._is_interactive_operator_authorized(open_id):
|
||||
logger.warning("[Feishu] Unauthorized approval click by %s for approval %s", open_id or "<unknown>", approval_id)
|
||||
return
|
||||
expected_chat_id = str(state.get("chat_id", "") or "")
|
||||
if expected_chat_id and chat_id and expected_chat_id != chat_id:
|
||||
logger.warning(
|
||||
"[Feishu] Approval %s chat mismatch (expected=%s, got=%s)",
|
||||
approval_id, expected_chat_id, chat_id,
|
||||
)
|
||||
return
|
||||
state = self._approval_state.pop(approval_id, None)
|
||||
if not state:
|
||||
logger.debug("[Feishu] Approval %s already resolved while validating callback", approval_id)
|
||||
logger.debug("[Feishu] Approval %s already resolved or unknown", approval_id)
|
||||
return
|
||||
try:
|
||||
from tools.approval import resolve_gateway_approval
|
||||
@@ -3289,6 +3229,11 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
self._record_webhook_anomaly(remote_ip, "400")
|
||||
return web.json_response({"code": 400, "msg": "invalid json"}, status=400)
|
||||
|
||||
# URL verification challenge — respond before other checks so that Feishu's
|
||||
# subscription setup works even before encrypt_key is wired.
|
||||
if payload.get("type") == "url_verification":
|
||||
return web.json_response({"challenge": payload.get("challenge", "")})
|
||||
|
||||
# Verification token check — second layer of defence beyond signature (matches openclaw).
|
||||
if self._verification_token:
|
||||
header = payload.get("header") or {}
|
||||
@@ -3298,13 +3243,6 @@ class FeishuAdapter(BasePlatformAdapter):
|
||||
self._record_webhook_anomaly(remote_ip, "401-token")
|
||||
return web.Response(status=401, text="Invalid verification token")
|
||||
|
||||
# URL verification challenge — Feishu includes the verification token in
|
||||
# challenge requests. Validate the token (above) before reflecting the
|
||||
# challenge so an unauthenticated remote request cannot prove endpoint
|
||||
# control by getting attacker-supplied challenge data echoed back.
|
||||
if payload.get("type") == "url_verification":
|
||||
return web.json_response({"challenge": payload.get("challenge", "")})
|
||||
|
||||
# Timing-safe signature verification (only enforced when encrypt_key is set).
|
||||
if self._encrypt_key and not self._is_webhook_signature_valid(request.headers, body_bytes):
|
||||
logger.warning("[Feishu] Webhook rejected: invalid signature from %s", remote_ip)
|
||||
|
||||
@@ -138,8 +138,7 @@ _OUTBOUND_MENTION_RE = re.compile(
|
||||
)
|
||||
|
||||
_E2EE_INSTALL_HINT = (
|
||||
"Install with: pip install 'mautrix[encryption]' asyncpg aiosqlite "
|
||||
"(requires libolm C library)"
|
||||
"Install with: pip install 'mautrix[encryption]' (requires libolm C library)"
|
||||
)
|
||||
|
||||
_MATRIX_IMAGE_FILENAME_EXTS = frozenset({
|
||||
@@ -215,22 +214,9 @@ def _create_matrix_session(proxy_url: str | None):
|
||||
|
||||
|
||||
def _check_e2ee_deps() -> bool:
|
||||
"""Return True if mautrix E2EE dependencies are available.
|
||||
|
||||
Verifies python-olm (via mautrix.crypto.OlmMachine), the SQLite crypto
|
||||
store backend (mautrix.crypto.store.asyncpg.PgCryptoStore — yes, the
|
||||
PgCryptoStore class also drives the sqlite backend in mautrix 0.21),
|
||||
and the database drivers actually used at connect time (``asyncpg`` for
|
||||
the underlying upgrade_table machinery, ``aiosqlite`` for the
|
||||
``sqlite:///`` URL we pass to ``Database.create``). Without all four,
|
||||
encrypted rooms fail at connect time with a confusing
|
||||
``No module named 'asyncpg'`` (#31116).
|
||||
"""
|
||||
"""Return True if mautrix E2EE dependencies (python-olm) are available."""
|
||||
try:
|
||||
from mautrix.crypto import OlmMachine # noqa: F401
|
||||
from mautrix.crypto.store.asyncpg import PgCryptoStore # noqa: F401
|
||||
import asyncpg # noqa: F401
|
||||
import aiosqlite # noqa: F401
|
||||
|
||||
return True
|
||||
except (ImportError, AttributeError):
|
||||
@@ -240,13 +226,8 @@ def _check_e2ee_deps() -> bool:
|
||||
def check_matrix_requirements() -> bool:
|
||||
"""Return True if the Matrix adapter can be used.
|
||||
|
||||
Lazy-installs the full ``platform.matrix`` feature group via
|
||||
``tools.lazy_deps.ensure_and_bind`` whenever any of the declared
|
||||
packages (mautrix, Markdown, aiosqlite, asyncpg, aiohttp-socks) is
|
||||
missing — not just mautrix itself. Previously this short-circuited on
|
||||
``import mautrix``, which left the other four packages uninstalled
|
||||
forever and broke E2EE connect with ``No module named 'asyncpg'``
|
||||
(#31116). Rebinds module-level type globals on success.
|
||||
Lazy-installs mautrix via ``tools.lazy_deps.ensure("platform.matrix")``
|
||||
on first call if not present. Rebinds all module-level type globals on success.
|
||||
"""
|
||||
token = os.getenv("MATRIX_ACCESS_TOKEN", "")
|
||||
password = os.getenv("MATRIX_PASSWORD", "")
|
||||
@@ -258,20 +239,9 @@ def check_matrix_requirements() -> bool:
|
||||
if not homeserver:
|
||||
logger.warning("Matrix: MATRIX_HOMESERVER not set")
|
||||
return False
|
||||
|
||||
# Check whether any package in the platform.matrix feature group is
|
||||
# missing. ``feature_missing`` is cheap (per-spec importlib.metadata
|
||||
# lookups) and correctly handles ``mautrix[encryption]`` by stripping
|
||||
# the extras marker before checking the bare package.
|
||||
try:
|
||||
from tools.lazy_deps import feature_missing, ensure_and_bind
|
||||
missing = feature_missing("platform.matrix")
|
||||
except Exception as exc: # pragma: no cover — defensive
|
||||
logger.debug("Matrix: lazy_deps lookup failed: %s", exc)
|
||||
missing = ()
|
||||
ensure_and_bind = None # type: ignore[assignment]
|
||||
|
||||
if missing or ensure_and_bind is None:
|
||||
import mautrix # noqa: F401
|
||||
except ImportError:
|
||||
def _import():
|
||||
from mautrix.types import (
|
||||
ContentURI, EventID, EventType, PaginationDirection,
|
||||
@@ -291,14 +261,10 @@ def check_matrix_requirements() -> bool:
|
||||
"UserID": UserID,
|
||||
}
|
||||
|
||||
if ensure_and_bind is None:
|
||||
return False
|
||||
from tools.lazy_deps import ensure_and_bind
|
||||
if not ensure_and_bind("platform.matrix", _import, globals(), prompt=False):
|
||||
logger.warning(
|
||||
"Matrix: required packages not installed (%s). "
|
||||
"Run: pip install 'mautrix[encryption]' asyncpg aiosqlite "
|
||||
"Markdown aiohttp-socks",
|
||||
", ".join(missing) if missing else "platform.matrix",
|
||||
"Matrix: mautrix not installed. Run: pip install 'mautrix[encryption]'"
|
||||
)
|
||||
return False
|
||||
|
||||
|
||||
@@ -133,12 +133,6 @@ class MSGraphWebhookAdapter(BasePlatformAdapter):
|
||||
self._notification_scheduler = scheduler
|
||||
|
||||
async def connect(self) -> bool:
|
||||
if self._client_state is None:
|
||||
logger.error(
|
||||
"[msgraph_webhook] Refusing to start without extra.client_state configured"
|
||||
)
|
||||
return False
|
||||
|
||||
app = web.Application()
|
||||
app.router.add_get(self._health_path, self._handle_health)
|
||||
app.router.add_get(self._webhook_path, self._handle_validation)
|
||||
@@ -316,7 +310,7 @@ class MSGraphWebhookAdapter(BasePlatformAdapter):
|
||||
"""
|
||||
expected = self._client_state
|
||||
if expected is None:
|
||||
return False
|
||||
return True
|
||||
provided = self._string_or_none(notification.get("clientState"))
|
||||
if provided is None:
|
||||
return False
|
||||
|
||||
@@ -1054,46 +1054,6 @@ class QQAdapter(BasePlatformAdapter):
|
||||
"deny": "deny",
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _parse_gateway_session_key(session_key: str) -> Optional[Dict[str, str]]:
|
||||
"""Parse ``agent:main:<platform>:<chat_type>:<chat_id>[:<user_id>]``."""
|
||||
parts = str(session_key or "").split(":")
|
||||
if len(parts) < 5 or parts[0] != "agent" or parts[1] != "main":
|
||||
return None
|
||||
parsed = {
|
||||
"platform": parts[2],
|
||||
"chat_type": parts[3],
|
||||
"chat_id": parts[4],
|
||||
}
|
||||
if len(parts) > 5:
|
||||
parsed["user_id"] = parts[5]
|
||||
return parsed
|
||||
|
||||
def _is_authorized_interaction_for_session(
|
||||
self,
|
||||
event: InteractionEvent,
|
||||
session_key: str,
|
||||
) -> bool:
|
||||
"""Authorize approval/update interactions against session + operator."""
|
||||
parsed = self._parse_gateway_session_key(session_key)
|
||||
operator = str(event.operator_openid or "").strip()
|
||||
if not parsed or parsed.get("platform") != "qqbot" or not operator:
|
||||
return False
|
||||
|
||||
chat_type = parsed.get("chat_type", "")
|
||||
chat_id = parsed.get("chat_id", "")
|
||||
if chat_type == "c2c":
|
||||
return bool(chat_id) and operator == chat_id
|
||||
|
||||
if chat_type in {"group", "guild"}:
|
||||
event_chat = str(event.group_openid or event.guild_id or "").strip()
|
||||
if not event_chat or event_chat != chat_id:
|
||||
return False
|
||||
session_user = str(parsed.get("user_id", "")).strip()
|
||||
return bool(session_user) and operator == session_user
|
||||
|
||||
return False
|
||||
|
||||
async def _default_interaction_dispatch(
|
||||
self,
|
||||
event: InteractionEvent,
|
||||
@@ -1127,13 +1087,6 @@ class QQAdapter(BasePlatformAdapter):
|
||||
self._log_tag, decision, session_key,
|
||||
)
|
||||
return
|
||||
if not self._is_authorized_interaction_for_session(event, session_key):
|
||||
logger.warning(
|
||||
"[%s] Rejected unauthorized approval click for session %s "
|
||||
"(operator=%s)",
|
||||
self._log_tag, session_key, event.operator_openid,
|
||||
)
|
||||
return
|
||||
try:
|
||||
# Import lazily to keep the adapter importable in tests that
|
||||
# don't exercise the approval subsystem.
|
||||
@@ -1154,13 +1107,6 @@ class QQAdapter(BasePlatformAdapter):
|
||||
|
||||
update_answer = parse_update_prompt_button_data(button_data)
|
||||
if update_answer is not None:
|
||||
update_session_key = f"agent:main:qqbot:{event.scene}:{event.group_openid or event.guild_id or event.user_openid}"
|
||||
if not self._is_authorized_interaction_for_session(event, update_session_key):
|
||||
logger.warning(
|
||||
"[%s] Rejected unauthorized update prompt click (operator=%s)",
|
||||
self._log_tag, event.operator_openid,
|
||||
)
|
||||
return
|
||||
self._write_update_response(update_answer, event.operator_openid)
|
||||
return
|
||||
|
||||
|
||||
@@ -429,13 +429,6 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
self._polling_conflict_count: int = 0
|
||||
self._polling_network_error_count: int = 0
|
||||
self._polling_error_callback_ref = None
|
||||
# After sustained reconnect storms the PTB httpx pool can return
|
||||
# SendResult(success=True) for sends that never actually transmit.
|
||||
# _handle_polling_network_error sets this; _verify_polling_after_reconnect
|
||||
# clears it once getMe() confirms the Bot client is healthy.
|
||||
# While True, send() short-circuits to a failure so callers
|
||||
# (cron live-adapter branch) fall through to standalone delivery.
|
||||
self._send_path_degraded: bool = False
|
||||
# DM Topics: map of topic_name -> message_thread_id (populated at startup)
|
||||
self._dm_topics: Dict[str, int] = {}
|
||||
# Track forum chats where we've already registered bot commands
|
||||
@@ -475,10 +468,6 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
# "all" — every message triggers a push notification (legacy
|
||||
# behavior; opt-in via display.platforms.telegram.notifications).
|
||||
self._notifications_mode: str = "important"
|
||||
# send_or_update_status() bookkeeping: {(chat_id, status_key) -> bot message_id}
|
||||
# Tracks status bubbles owned by this adapter so subsequent calls with the
|
||||
# same key edit the same message instead of appending new ones (#30045).
|
||||
self._status_message_ids: Dict[tuple, str] = {}
|
||||
|
||||
def _notification_kwargs(
|
||||
self, metadata: Optional[Dict[str, Any]]
|
||||
@@ -881,7 +870,6 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
MAX_DELAY = 60
|
||||
|
||||
self._polling_network_error_count += 1
|
||||
self._send_path_degraded = True
|
||||
attempt = self._polling_network_error_count
|
||||
|
||||
if attempt > MAX_NETWORK_RETRIES:
|
||||
@@ -979,7 +967,6 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
|
||||
try:
|
||||
await asyncio.wait_for(self._app.bot.get_me(), PROBE_TIMEOUT)
|
||||
self._send_path_degraded = False
|
||||
except Exception as probe_err:
|
||||
logger.warning(
|
||||
"[%s] Polling heartbeat probe failed %ds after reconnect: %s",
|
||||
@@ -1692,11 +1679,7 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
"""Send a message to a Telegram chat."""
|
||||
if not self._bot:
|
||||
return SendResult(success=False, error="Not connected")
|
||||
|
||||
# getattr() — tests build adapters via object.__new__() (no __init__).
|
||||
if getattr(self, "_send_path_degraded", False):
|
||||
return SendResult(success=False, error="send_path_degraded", retryable=True)
|
||||
|
||||
|
||||
# Skip whitespace-only text to prevent Telegram 400 empty-text errors.
|
||||
if not content or not content.strip():
|
||||
return SendResult(success=True, message_id=None)
|
||||
@@ -1925,40 +1908,6 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
is_connect_timeout = self._looks_like_connect_timeout(e)
|
||||
return SendResult(success=False, error=str(e), retryable=(is_connect_timeout or not is_timeout))
|
||||
|
||||
async def send_or_update_status(
|
||||
self,
|
||||
chat_id: str,
|
||||
status_key: str,
|
||||
content: str,
|
||||
*,
|
||||
metadata: Optional[Dict[str, Any]] = None,
|
||||
) -> SendResult:
|
||||
"""Send a status message, or edit the previous one with the same key.
|
||||
|
||||
Issue #30045: progress/status callbacks (context-pressure, lifecycle,
|
||||
compression, etc.) used to append a fresh bubble on every call. With
|
||||
this method, the first call sends and the message id is remembered;
|
||||
subsequent calls with the same (chat_id, status_key) edit that same
|
||||
message in place. If the edit fails (message deleted, too old, etc.)
|
||||
we drop the cached id and send fresh.
|
||||
"""
|
||||
key = (str(chat_id), str(status_key))
|
||||
cached_id = self._status_message_ids.get(key)
|
||||
if cached_id is not None:
|
||||
result = await self.edit_message(
|
||||
chat_id, cached_id, content, finalize=True, metadata=metadata,
|
||||
)
|
||||
if result.success:
|
||||
if result.message_id:
|
||||
self._status_message_ids[key] = str(result.message_id)
|
||||
return result
|
||||
# Edit failed — clear the cached id and fall through to a fresh send.
|
||||
self._status_message_ids.pop(key, None)
|
||||
result = await self.send(chat_id, content, metadata=metadata)
|
||||
if result.success and result.message_id:
|
||||
self._status_message_ids[key] = str(result.message_id)
|
||||
return result
|
||||
|
||||
async def edit_message(
|
||||
self,
|
||||
chat_id: str,
|
||||
@@ -4644,12 +4593,6 @@ class TelegramAdapter(BasePlatformAdapter):
|
||||
shared_source = self._telegram_group_observe_shared_source(event.source)
|
||||
observe_prompt = self._telegram_group_observe_channel_prompt()
|
||||
channel_prompt = f"{event.channel_prompt}\n\n{observe_prompt}" if event.channel_prompt else observe_prompt
|
||||
if event.message_type == MessageType.COMMAND:
|
||||
return dataclasses.replace(
|
||||
event,
|
||||
source=shared_source,
|
||||
channel_prompt=channel_prompt,
|
||||
)
|
||||
return dataclasses.replace(
|
||||
event,
|
||||
text=self._telegram_group_observe_attributed_text(event),
|
||||
|
||||
@@ -27,8 +27,6 @@ Security:
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import base64
|
||||
import binascii
|
||||
import hashlib
|
||||
import hmac
|
||||
import json
|
||||
@@ -328,17 +326,6 @@ class WebhookAdapter(BasePlatformAdapter):
|
||||
_INSECURE_NO_AUTH,
|
||||
)
|
||||
continue
|
||||
if (
|
||||
effective_secret == _INSECURE_NO_AUTH
|
||||
and not _is_loopback_host(self._host)
|
||||
):
|
||||
logger.warning(
|
||||
"[webhook] Dynamic route '%s' skipped: INSECURE_NO_AUTH "
|
||||
"is only allowed on loopback hosts. Current host: '%s'.",
|
||||
k,
|
||||
self._host,
|
||||
)
|
||||
continue
|
||||
new_dynamic[k] = v
|
||||
self._dynamic_routes = new_dynamic
|
||||
self._routes = {**self._dynamic_routes, **self._static_routes}
|
||||
@@ -379,21 +366,9 @@ class WebhookAdapter(BasePlatformAdapter):
|
||||
logger.error("[webhook] Failed to read body: %s", e)
|
||||
return web.json_response({"error": "Bad request"}, status=400)
|
||||
|
||||
# Validate HMAC signature FIRST (skip only for the explicit local-test
|
||||
# INSECURE_NO_AUTH mode). Missing/empty secrets must fail closed here,
|
||||
# not only during connect(), so direct handler reuse cannot turn a
|
||||
# network webhook route into an unauthenticated agent-dispatch surface.
|
||||
# Validate HMAC signature FIRST (skip for INSECURE_NO_AUTH testing mode)
|
||||
secret = route_config.get("secret", self._global_secret)
|
||||
if not secret:
|
||||
logger.error(
|
||||
"[webhook] Route %s has no HMAC secret; refusing request",
|
||||
route_name,
|
||||
)
|
||||
return web.json_response(
|
||||
{"error": "Webhook route is missing an HMAC secret"},
|
||||
status=403,
|
||||
)
|
||||
if secret != _INSECURE_NO_AUTH:
|
||||
if secret and secret != _INSECURE_NO_AUTH:
|
||||
if not self._validate_signature(request, raw_body, secret):
|
||||
logger.warning(
|
||||
"[webhook] Invalid signature for route %s", route_name
|
||||
@@ -433,7 +408,6 @@ class WebhookAdapter(BasePlatformAdapter):
|
||||
request.headers.get("X-GitHub-Event", "")
|
||||
or request.headers.get("X-GitLab-Event", "")
|
||||
or payload.get("event_type", "")
|
||||
or payload.get("type", "")
|
||||
or "unknown"
|
||||
)
|
||||
allowed_events = route_config.get("events", [])
|
||||
@@ -486,10 +460,7 @@ class WebhookAdapter(BasePlatformAdapter):
|
||||
# Build a unique delivery ID
|
||||
delivery_id = request.headers.get(
|
||||
"X-GitHub-Delivery",
|
||||
request.headers.get(
|
||||
"svix-id",
|
||||
request.headers.get("X-Request-ID", str(int(time.time() * 1000))),
|
||||
),
|
||||
request.headers.get("X-Request-ID", str(int(time.time() * 1000))),
|
||||
)
|
||||
|
||||
# ── Idempotency ─────────────────────────────────────────
|
||||
@@ -634,32 +605,7 @@ class WebhookAdapter(BasePlatformAdapter):
|
||||
def _validate_signature(
|
||||
self, request: "web.Request", body: bytes, secret: str
|
||||
) -> bool:
|
||||
"""Validate webhook signature (GitHub, GitLab, Svix, generic HMAC-SHA256)."""
|
||||
def _header(name: str) -> str:
|
||||
return (
|
||||
request.headers.get(name, "")
|
||||
or request.headers.get(name.lower(), "")
|
||||
or request.headers.get(name.upper(), "")
|
||||
)
|
||||
|
||||
# Svix / AgentMail:
|
||||
# svix-id: msg_...
|
||||
# svix-timestamp: unix seconds
|
||||
# svix-signature: v1,<base64-hmac> [v1,<base64-hmac> ...]
|
||||
# Signed content is: "{id}.{timestamp}.{raw_body}". Svix secrets
|
||||
# usually start with "whsec_" and the remainder is base64-encoded.
|
||||
svix_id = _header("svix-id")
|
||||
svix_timestamp = _header("svix-timestamp")
|
||||
svix_signature = _header("svix-signature")
|
||||
if svix_id or svix_timestamp or svix_signature:
|
||||
return self._validate_svix_signature(
|
||||
body=body,
|
||||
secret=secret,
|
||||
msg_id=svix_id,
|
||||
timestamp=svix_timestamp,
|
||||
signature_header=svix_signature,
|
||||
)
|
||||
|
||||
"""Validate webhook signature (GitHub, GitLab, generic HMAC-SHA256)."""
|
||||
# GitHub: X-Hub-Signature-256 = sha256=<hex>
|
||||
gh_sig = request.headers.get("X-Hub-Signature-256", "")
|
||||
if gh_sig:
|
||||
@@ -687,56 +633,6 @@ class WebhookAdapter(BasePlatformAdapter):
|
||||
)
|
||||
return False
|
||||
|
||||
def _validate_svix_signature(
|
||||
self,
|
||||
body: bytes,
|
||||
secret: str,
|
||||
msg_id: str,
|
||||
timestamp: str,
|
||||
signature_header: str,
|
||||
tolerance_seconds: int = 300,
|
||||
) -> bool:
|
||||
"""Validate Svix-compatible signatures used by AgentMail webhooks."""
|
||||
if not (msg_id and timestamp and signature_header and secret):
|
||||
return False
|
||||
|
||||
try:
|
||||
ts = int(timestamp)
|
||||
except (TypeError, ValueError):
|
||||
return False
|
||||
if abs(int(time.time()) - ts) > tolerance_seconds:
|
||||
logger.warning("[webhook] Svix signature timestamp outside replay window")
|
||||
return False
|
||||
|
||||
if secret.startswith("whsec_"):
|
||||
encoded_secret = secret.removeprefix("whsec_")
|
||||
try:
|
||||
key = base64.b64decode(encoded_secret, validate=True)
|
||||
except (binascii.Error, ValueError):
|
||||
logger.debug("[webhook] Invalid whsec_ Svix signing secret")
|
||||
return False
|
||||
else:
|
||||
# Be permissive for providers that document Svix-style headers but
|
||||
# hand out raw shared secrets rather than whsec_ base64 secrets.
|
||||
logger.debug("[webhook] Validating Svix-style signature with raw secret")
|
||||
key = secret.encode()
|
||||
|
||||
signed_content = msg_id.encode() + b"." + timestamp.encode() + b"." + body
|
||||
expected = base64.b64encode(
|
||||
hmac.new(key, signed_content, hashlib.sha256).digest()
|
||||
).decode()
|
||||
|
||||
# Svix can send multiple signatures separated by spaces during secret
|
||||
# rotation. Each entry is formatted as "vN,<base64>".
|
||||
for part in signature_header.split():
|
||||
try:
|
||||
version, signature = part.split(",", 1)
|
||||
except ValueError:
|
||||
continue
|
||||
if version == "v1" and hmac.compare_digest(signature, expected):
|
||||
return True
|
||||
return False
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Prompt rendering
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@@ -616,18 +616,6 @@ class WeComAdapter(BasePlatformAdapter):
|
||||
else:
|
||||
delay = self._text_batch_delay_seconds
|
||||
await asyncio.sleep(delay)
|
||||
# Guard against the cancel-delivery race: when the sleep timer
|
||||
# fires just before cancel() is called, CPython sets
|
||||
# Task._must_cancel but cannot cancel the already-done sleep
|
||||
# future, so CancelledError is delivered at the *next* await
|
||||
# (handle_message) rather than here. By that point this task
|
||||
# has already popped the merged event, so the superseding task
|
||||
# sees an empty batch and silently drops the message.
|
||||
# This check is synchronous — no await between the sleep and
|
||||
# the pop — so no other coroutine can modify the task registry
|
||||
# in between.
|
||||
if self._pending_text_batch_tasks.get(key) is not current_task:
|
||||
return
|
||||
event = self._pending_text_batches.pop(key, None)
|
||||
if not event:
|
||||
return
|
||||
|
||||
@@ -187,6 +187,7 @@ class WecomCallbackAdapter(BasePlatformAdapter):
|
||||
app = self._resolve_app_for_chat(chat_id)
|
||||
touser = chat_id.split(":", 1)[1] if ":" in chat_id else chat_id
|
||||
try:
|
||||
token = await self._get_access_token(app)
|
||||
payload = {
|
||||
"touser": touser,
|
||||
"msgtype": "text",
|
||||
@@ -194,31 +195,18 @@ class WecomCallbackAdapter(BasePlatformAdapter):
|
||||
"text": {"content": content[:2048]},
|
||||
"safe": 0,
|
||||
}
|
||||
for _attempt in range(2):
|
||||
token = await self._get_access_token(app)
|
||||
resp = await self._http_client.post(
|
||||
f"https://qyapi.weixin.qq.com/cgi-bin/message/send?access_token={token}",
|
||||
json=payload,
|
||||
)
|
||||
data = resp.json()
|
||||
errcode = data.get("errcode")
|
||||
if errcode in {40001, 42001} and _attempt == 0:
|
||||
# WeCom rejected the token — evict the cached entry so
|
||||
# the next _get_access_token call forces a fresh fetch.
|
||||
logger.warning(
|
||||
"[WecomCallback] Token rejected for app '%s' (errcode=%s), refreshing",
|
||||
app.get("name", "default"), errcode,
|
||||
)
|
||||
self._access_tokens.pop(app["name"], None)
|
||||
continue
|
||||
if errcode != 0:
|
||||
return SendResult(success=False, error=str(data))
|
||||
return SendResult(
|
||||
success=True,
|
||||
message_id=str(data.get("msgid", "")),
|
||||
raw_response=data,
|
||||
)
|
||||
return SendResult(success=False, error="send failed after token refresh")
|
||||
resp = await self._http_client.post(
|
||||
f"https://qyapi.weixin.qq.com/cgi-bin/message/send?access_token={token}",
|
||||
json=payload,
|
||||
)
|
||||
data = resp.json()
|
||||
if data.get("errcode") != 0:
|
||||
return SendResult(success=False, error=str(data))
|
||||
return SendResult(
|
||||
success=True,
|
||||
message_id=str(data.get("msgid", "")),
|
||||
raw_response=data,
|
||||
)
|
||||
except Exception as exc:
|
||||
return SendResult(success=False, error=str(exc))
|
||||
|
||||
|
||||
+84
-250
@@ -54,7 +54,6 @@ from agent.account_usage import fetch_account_usage, render_account_usage_lines
|
||||
from agent.async_utils import safe_schedule_threadsafe
|
||||
from agent.i18n import t
|
||||
from hermes_cli.config import cfg_get
|
||||
from hermes_cli.fallback_config import get_fallback_chain
|
||||
|
||||
# --- Agent cache tuning ---------------------------------------------------
|
||||
# Bounds the per-session AIAgent cache to prevent unbounded growth in
|
||||
@@ -139,85 +138,6 @@ def _gateway_platform_value(platform: Any) -> str:
|
||||
return str(getattr(platform, "value", platform) or "").strip().lower()
|
||||
|
||||
|
||||
def _is_transient_network_error(exc: BaseException) -> bool:
|
||||
"""Return True for transient network errors safe to log + swallow.
|
||||
|
||||
The crash class targeted by #31066 / #31110: an unhandled Telegram
|
||||
``TimedOut`` (or peer ``NetworkError`` / ``httpx`` connection error)
|
||||
propagating to the event loop and killing the entire gateway
|
||||
process. These are by definition transient — the next poll cycle or
|
||||
user action recovers — so they must never crash the process.
|
||||
|
||||
Walk the exception cause chain so wrapped errors (e.g. PTB's
|
||||
``NetworkError`` wrapping ``httpx.ConnectError``) are still
|
||||
classified. The chain is bounded to avoid pathological cycles.
|
||||
"""
|
||||
seen: set[int] = set()
|
||||
cur: Optional[BaseException] = exc
|
||||
depth = 0
|
||||
transient_class_names = {
|
||||
"TimedOut",
|
||||
"NetworkError",
|
||||
"ReadError",
|
||||
"WriteError",
|
||||
"ConnectError",
|
||||
"ConnectTimeout",
|
||||
"ReadTimeout",
|
||||
"WriteTimeout",
|
||||
"PoolTimeout",
|
||||
"RemoteProtocolError",
|
||||
"ServerDisconnectedError",
|
||||
"ClientConnectorError",
|
||||
"ClientOSError",
|
||||
}
|
||||
while cur is not None and depth < 12:
|
||||
ident = id(cur)
|
||||
if ident in seen:
|
||||
break
|
||||
seen.add(ident)
|
||||
depth += 1
|
||||
name = type(cur).__name__
|
||||
if name in transient_class_names:
|
||||
return True
|
||||
cur = cur.__cause__ or cur.__context__
|
||||
return False
|
||||
|
||||
|
||||
def _gateway_loop_exception_handler(
|
||||
loop: "asyncio.AbstractEventLoop", context: Dict[str, Any]
|
||||
) -> None:
|
||||
"""Loop-level safety net for transient network errors.
|
||||
|
||||
Installed once during :func:`start_gateway`. Catches the
|
||||
``telegram.error.TimedOut`` crash class (issues #31066 / #31110)
|
||||
and any peer transient network error before it can kill the
|
||||
gateway process. Logs at WARNING with full traceback so the
|
||||
originating call site stays diagnosable; non-transient errors
|
||||
are forwarded to the default loop handler so real bugs still
|
||||
surface.
|
||||
"""
|
||||
exc = context.get("exception")
|
||||
if exc is not None and _is_transient_network_error(exc):
|
||||
message = context.get("message") or "transient network error"
|
||||
task = context.get("future") or context.get("task")
|
||||
task_name = ""
|
||||
if task is not None:
|
||||
try:
|
||||
task_name = task.get_name() if hasattr(task, "get_name") else repr(task)
|
||||
except Exception:
|
||||
task_name = repr(task)
|
||||
logger.warning(
|
||||
"Gateway swallowed transient network error from %s: %s: %s",
|
||||
task_name or "<unknown task>",
|
||||
type(exc).__name__,
|
||||
exc,
|
||||
exc_info=(type(exc), exc, exc.__traceback__),
|
||||
)
|
||||
return
|
||||
# Fall back to the default handler for anything we don't recognise.
|
||||
loop.default_exception_handler(context)
|
||||
|
||||
|
||||
def _redact_gateway_user_facing_secrets(text: str) -> str:
|
||||
"""Best-effort secret redaction before text can leave the gateway."""
|
||||
redacted = str(text or "")
|
||||
@@ -318,19 +238,6 @@ def _prepare_gateway_status_message(platform: Any, event_type: str, message: str
|
||||
return text
|
||||
|
||||
|
||||
async def _send_or_update_status_coro(adapter, chat_id, status_key, content, metadata):
|
||||
"""Route a status message through adapter.send_or_update_status when supported.
|
||||
|
||||
Issue #30045: adapters that implement send_or_update_status (currently
|
||||
Telegram) edit the previous bubble for the same status_key instead of
|
||||
appending a new one. Adapters without the method fall back to plain send.
|
||||
"""
|
||||
sender = getattr(adapter, "send_or_update_status", None)
|
||||
if callable(sender):
|
||||
return await sender(chat_id, status_key, content, metadata=metadata)
|
||||
return await adapter.send(chat_id, content, metadata=metadata)
|
||||
|
||||
|
||||
def _telegramize_command_mentions(text: str, platform: Any) -> str:
|
||||
"""Rewrite slash-command mentions to Telegram-valid command names.
|
||||
|
||||
@@ -853,29 +760,31 @@ if _config_path.exists():
|
||||
os.environ[_env_var] = str(_val)
|
||||
# Compression config is read directly from config.yaml by run_agent.py
|
||||
# and auxiliary_client.py — no env var bridging needed.
|
||||
# Auxiliary model/direct-endpoint overrides (vision, web_extract,
|
||||
# approval, plus any plugin-registered auxiliary tasks).
|
||||
# Each task has provider/model/base_url/api_key; bridge non-default
|
||||
# values to env vars named AUXILIARY_<KEY_UPPER>_*. The legacy
|
||||
# hard-coded list (vision/web_extract/approval) is replaced by a
|
||||
# dynamic loop so plugin-registered tasks benefit from the same
|
||||
# config→env bridging without core knowing about each one.
|
||||
# Auxiliary model/direct-endpoint overrides (vision, web_extract).
|
||||
# Each task has provider/model/base_url/api_key; bridge non-default values to env vars.
|
||||
_auxiliary_cfg = _cfg.get("auxiliary", {})
|
||||
if _auxiliary_cfg and isinstance(_auxiliary_cfg, dict):
|
||||
# Built-in tasks that previously had explicit env-var bridging.
|
||||
# Kept here as the canonical bridged set; plugin tasks are added
|
||||
# below via the plugin auxiliary registry.
|
||||
_aux_bridged_keys = {"vision", "web_extract", "approval"}
|
||||
try:
|
||||
from hermes_cli.plugins import get_plugin_auxiliary_tasks
|
||||
for _entry in get_plugin_auxiliary_tasks():
|
||||
_aux_bridged_keys.add(_entry["key"])
|
||||
except Exception:
|
||||
# Plugin discovery failure must not break gateway startup;
|
||||
# built-in bridging stays intact.
|
||||
pass
|
||||
|
||||
for _task_key in _aux_bridged_keys:
|
||||
_aux_task_env = {
|
||||
"vision": {
|
||||
"provider": "AUXILIARY_VISION_PROVIDER",
|
||||
"model": "AUXILIARY_VISION_MODEL",
|
||||
"base_url": "AUXILIARY_VISION_BASE_URL",
|
||||
"api_key": "AUXILIARY_VISION_API_KEY",
|
||||
},
|
||||
"web_extract": {
|
||||
"provider": "AUXILIARY_WEB_EXTRACT_PROVIDER",
|
||||
"model": "AUXILIARY_WEB_EXTRACT_MODEL",
|
||||
"base_url": "AUXILIARY_WEB_EXTRACT_BASE_URL",
|
||||
"api_key": "AUXILIARY_WEB_EXTRACT_API_KEY",
|
||||
},
|
||||
"approval": {
|
||||
"provider": "AUXILIARY_APPROVAL_PROVIDER",
|
||||
"model": "AUXILIARY_APPROVAL_MODEL",
|
||||
"base_url": "AUXILIARY_APPROVAL_BASE_URL",
|
||||
"api_key": "AUXILIARY_APPROVAL_API_KEY",
|
||||
},
|
||||
}
|
||||
for _task_key, _env_map in _aux_task_env.items():
|
||||
_task_cfg = _auxiliary_cfg.get(_task_key, {})
|
||||
if not isinstance(_task_cfg, dict):
|
||||
continue
|
||||
@@ -883,15 +792,14 @@ if _config_path.exists():
|
||||
_model = str(_task_cfg.get("model", "")).strip()
|
||||
_base_url = str(_task_cfg.get("base_url", "")).strip()
|
||||
_api_key = str(_task_cfg.get("api_key", "")).strip()
|
||||
_upper = _task_key.upper()
|
||||
if _prov and _prov != "auto":
|
||||
os.environ[f"AUXILIARY_{_upper}_PROVIDER"] = _prov
|
||||
os.environ[_env_map["provider"]] = _prov
|
||||
if _model:
|
||||
os.environ[f"AUXILIARY_{_upper}_MODEL"] = _model
|
||||
os.environ[_env_map["model"]] = _model
|
||||
if _base_url:
|
||||
os.environ[f"AUXILIARY_{_upper}_BASE_URL"] = _base_url
|
||||
os.environ[_env_map["base_url"]] = _base_url
|
||||
if _api_key:
|
||||
os.environ[f"AUXILIARY_{_upper}_API_KEY"] = _api_key
|
||||
os.environ[_env_map["api_key"]] = _api_key
|
||||
# config.yaml is the documented, authoritative source for these
|
||||
# settings — it unconditionally wins over .env values. Previously
|
||||
# the guards below read `if X not in os.environ` and let stale
|
||||
@@ -918,8 +826,6 @@ if _config_path.exists():
|
||||
if _display_cfg and isinstance(_display_cfg, dict):
|
||||
if "busy_input_mode" in _display_cfg:
|
||||
os.environ["HERMES_GATEWAY_BUSY_INPUT_MODE"] = str(_display_cfg["busy_input_mode"])
|
||||
if "busy_text_mode" in _display_cfg:
|
||||
os.environ["HERMES_GATEWAY_BUSY_TEXT_MODE"] = str(_display_cfg["busy_text_mode"])
|
||||
if "busy_ack_enabled" in _display_cfg:
|
||||
os.environ["HERMES_GATEWAY_BUSY_ACK_ENABLED"] = str(_display_cfg["busy_ack_enabled"])
|
||||
# Timezone: bridge config.yaml → HERMES_TIMEZONE env var.
|
||||
@@ -1043,12 +949,6 @@ _AGENT_PENDING_SENTINEL = object()
|
||||
def _resolve_runtime_agent_kwargs() -> dict:
|
||||
"""Resolve provider credentials for gateway-created AIAgent instances.
|
||||
|
||||
Provider is read from ``config.yaml`` ``model.provider`` (the single
|
||||
source of truth). ``resolve_runtime_provider()`` falls through to env
|
||||
var lookups internally for legacy compatibility, but the gateway does
|
||||
not consult environment variables for behavioral config — config.yaml
|
||||
is authoritative.
|
||||
|
||||
If the primary provider fails with an authentication error, attempt to
|
||||
resolve credentials using the fallback provider chain from config.yaml
|
||||
before giving up.
|
||||
@@ -1060,7 +960,9 @@ def _resolve_runtime_agent_kwargs() -> dict:
|
||||
from hermes_cli.auth import AuthError
|
||||
|
||||
try:
|
||||
runtime = resolve_runtime_provider()
|
||||
runtime = resolve_runtime_provider(
|
||||
requested=os.getenv("HERMES_INFERENCE_PROVIDER"),
|
||||
)
|
||||
except AuthError as auth_exc:
|
||||
# Primary provider auth failed (expired token, revoked key, etc.).
|
||||
# Try the fallback provider chain before raising.
|
||||
@@ -1093,10 +995,14 @@ def _try_resolve_fallback_provider() -> dict | None:
|
||||
return None
|
||||
with open(cfg_path, encoding="utf-8") as _f:
|
||||
cfg = _y.safe_load(_f) or {}
|
||||
fb_list = get_fallback_chain(cfg)
|
||||
if not fb_list:
|
||||
fb = cfg.get("fallback_providers") or cfg.get("fallback_model")
|
||||
if not fb:
|
||||
return None
|
||||
# Normalize to list
|
||||
fb_list = fb if isinstance(fb, list) else [fb]
|
||||
for entry in fb_list:
|
||||
if not isinstance(entry, dict):
|
||||
continue
|
||||
try:
|
||||
explicit_api_key = entry.get("api_key")
|
||||
if not explicit_api_key:
|
||||
@@ -1635,7 +1541,6 @@ class GatewayRunner:
|
||||
# blow up on attribute access.
|
||||
_running_agents_ts: Dict[str, float] = {}
|
||||
_busy_input_mode: str = "interrupt"
|
||||
_busy_text_mode: str = "interrupt"
|
||||
_restart_drain_timeout: float = DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
|
||||
_exit_code: Optional[int] = None
|
||||
_draining: bool = False
|
||||
@@ -1662,7 +1567,6 @@ class GatewayRunner:
|
||||
self._service_tier = self._load_service_tier()
|
||||
self._show_reasoning = self._load_show_reasoning()
|
||||
self._busy_input_mode = self._load_busy_input_mode()
|
||||
self._busy_text_mode = self._load_busy_text_mode()
|
||||
self._restart_drain_timeout = self._load_restart_drain_timeout()
|
||||
self._provider_routing = self._load_provider_routing()
|
||||
self._fallback_model = self._load_fallback_model()
|
||||
@@ -2272,14 +2176,13 @@ class GatewayRunner:
|
||||
) -> Optional[str]:
|
||||
"""Pin DM-topic routing to the user's last-active topic.
|
||||
|
||||
Telegram can omit ``message_thread_id`` or surface General (``1``)
|
||||
for some topic-mode DM replies. In those lobby-shaped cases, keep the
|
||||
conversation attached to the user's most-recent bound topic.
|
||||
|
||||
Do not rewrite a non-lobby, previously-unbound thread id: a newly
|
||||
created Telegram DM topic is also "unknown" until the first inbound
|
||||
message is recorded, and rewriting it would send that brand-new topic's
|
||||
answer into an older lane. Returns None to leave the source alone.
|
||||
Telegram fragments topic-mode DMs two ways: a Reply on a message
|
||||
in another topic delivers ``message_thread_id`` for *that* topic,
|
||||
and ``_build_message_event`` strips the thread_id on plain replies
|
||||
(#3206 — needed for non-topic users). Both route the user to the
|
||||
wrong session. When topic mode is on, rewrite the thread_id to the
|
||||
user's most-recent binding if the inbound id is missing/General or
|
||||
not a known topic for this chat. Returns None to leave it alone.
|
||||
"""
|
||||
if (
|
||||
source.platform != Platform.TELEGRAM
|
||||
@@ -2289,14 +2192,6 @@ class GatewayRunner:
|
||||
or not self._telegram_topic_mode_enabled(source)
|
||||
):
|
||||
return None
|
||||
inbound = str(source.thread_id or "")
|
||||
is_lobby = not inbound or inbound in self._TELEGRAM_GENERAL_TOPIC_IDS
|
||||
if not is_lobby:
|
||||
# A non-lobby, unknown thread_id is most likely the first message in
|
||||
# a brand-new Telegram DM topic. Preserve it so it can be recorded
|
||||
# as a new independent lane below instead of hijacking the latest
|
||||
# existing topic binding.
|
||||
return None
|
||||
session_db = getattr(self, "_session_db", None)
|
||||
if session_db is None:
|
||||
return None
|
||||
@@ -2309,6 +2204,11 @@ class GatewayRunner:
|
||||
return None
|
||||
if not bindings:
|
||||
return None
|
||||
inbound = str(source.thread_id or "")
|
||||
is_lobby = not inbound or inbound in self._TELEGRAM_GENERAL_TOPIC_IDS
|
||||
known = {str(b.get("thread_id") or "") for b in bindings}
|
||||
if not is_lobby and inbound in known:
|
||||
return None
|
||||
user_id = str(source.user_id)
|
||||
for b in bindings: # newest-first
|
||||
if str(b.get("user_id") or "") == user_id:
|
||||
@@ -2913,17 +2813,6 @@ class GatewayRunner:
|
||||
return "steer"
|
||||
return "interrupt"
|
||||
|
||||
@staticmethod
|
||||
def _load_busy_text_mode() -> str:
|
||||
"""Load normal busy TEXT follow-up behavior from config/env."""
|
||||
mode = os.getenv("HERMES_GATEWAY_BUSY_TEXT_MODE", "").strip().lower()
|
||||
if not mode:
|
||||
cfg = _load_gateway_runtime_config()
|
||||
mode = str(cfg_get(cfg, "display", "busy_text_mode", default="") or "").strip().lower()
|
||||
if mode == "interrupt":
|
||||
return "interrupt"
|
||||
return "queue"
|
||||
|
||||
@staticmethod
|
||||
def _load_restart_drain_timeout() -> float:
|
||||
"""Load graceful gateway restart/stop drain timeout in seconds."""
|
||||
@@ -2986,12 +2875,12 @@ class GatewayRunner:
|
||||
return {}
|
||||
|
||||
@staticmethod
|
||||
def _load_fallback_model() -> list | None:
|
||||
def _load_fallback_model() -> list | dict | None:
|
||||
"""Load fallback provider chain from config.yaml.
|
||||
|
||||
Returns the merged effective chain from ``fallback_providers`` plus any
|
||||
legacy ``fallback_model`` entries. ``fallback_providers`` stays first
|
||||
when both keys are present.
|
||||
Returns a list of provider dicts (``fallback_providers``), a single
|
||||
dict (legacy ``fallback_model``), or None if not configured.
|
||||
AIAgent.__init__ normalizes both formats into a chain.
|
||||
"""
|
||||
try:
|
||||
import yaml as _y
|
||||
@@ -2999,7 +2888,7 @@ class GatewayRunner:
|
||||
if cfg_path.exists():
|
||||
with open(cfg_path, encoding="utf-8") as _f:
|
||||
cfg = _y.safe_load(_f) or {}
|
||||
fb = get_fallback_chain(cfg)
|
||||
fb = cfg.get("fallback_providers") or cfg.get("fallback_model") or None
|
||||
if fb:
|
||||
return fb
|
||||
except Exception:
|
||||
@@ -3071,19 +2960,11 @@ class GatewayRunner:
|
||||
|
||||
running_agent = self._running_agents.get(session_key)
|
||||
|
||||
effective_mode = self._busy_input_mode
|
||||
busy_text_mode = getattr(self, "_busy_text_mode", "queue")
|
||||
if (
|
||||
event.message_type == MessageType.TEXT
|
||||
and busy_text_mode == "queue"
|
||||
and effective_mode != "steer"
|
||||
):
|
||||
return False
|
||||
|
||||
# Steer mode: inject mid-run via running_agent.steer() instead of
|
||||
# queueing + interrupting. If the agent isn't running yet
|
||||
# (sentinel) or lacks steer(), or the payload is empty, fall back
|
||||
# to queue semantics so nothing is lost.
|
||||
effective_mode = self._busy_input_mode
|
||||
steered = False
|
||||
if effective_mode == "steer":
|
||||
steer_text = (event.text or "").strip()
|
||||
@@ -3108,12 +2989,7 @@ class GatewayRunner:
|
||||
# successful steer — the text already landed inside the run and
|
||||
# must NOT also be replayed as a next-turn user message.
|
||||
if not steered:
|
||||
merge_pending_message_event(
|
||||
adapter._pending_messages,
|
||||
session_key,
|
||||
event,
|
||||
merge_text=event.message_type == MessageType.TEXT,
|
||||
)
|
||||
merge_pending_message_event(adapter._pending_messages, session_key, event)
|
||||
|
||||
is_queue_mode = effective_mode == "queue"
|
||||
is_steer_mode = effective_mode == "steer"
|
||||
@@ -4045,7 +3921,6 @@ class GatewayRunner:
|
||||
adapter.set_fatal_error_handler(self._handle_adapter_fatal_error)
|
||||
adapter.set_session_store(self.session_store)
|
||||
adapter.set_busy_session_handler(self._handle_active_session_busy_message)
|
||||
adapter._busy_text_mode = self._busy_text_mode
|
||||
|
||||
# Try to connect
|
||||
logger.info("Connecting to %s...", platform.value)
|
||||
@@ -5658,7 +5533,6 @@ class GatewayRunner:
|
||||
adapter.set_fatal_error_handler(self._handle_adapter_fatal_error)
|
||||
adapter.set_session_store(self.session_store)
|
||||
adapter.set_busy_session_handler(self._handle_active_session_busy_message)
|
||||
adapter._busy_text_mode = self._busy_text_mode
|
||||
|
||||
success = await self._connect_adapter_with_timeout(adapter, platform)
|
||||
if success:
|
||||
@@ -6412,6 +6286,18 @@ class GatewayRunner:
|
||||
if allow_bots_var and os.getenv(allow_bots_var, "none").lower().strip() in {"mentions", "all"}:
|
||||
return True
|
||||
|
||||
# Discord role-based access (DISCORD_ALLOWED_ROLES): the adapter's
|
||||
# on_message pre-filter already verified role membership — if the
|
||||
# message reached here, the user passed that check. Authorize
|
||||
# directly to avoid the "no allowlists configured" branch below
|
||||
# rejecting role-only setups where DISCORD_ALLOWED_USERS is empty
|
||||
# (issue #7871).
|
||||
if (
|
||||
source.platform == Platform.DISCORD
|
||||
and os.getenv("DISCORD_ALLOWED_ROLES", "").strip()
|
||||
):
|
||||
return True
|
||||
|
||||
# Check pairing store (always checked, regardless of allowlists)
|
||||
platform_name = source.platform.value if source.platform else ""
|
||||
if self.pairing_store.is_approved(platform_name, user_id):
|
||||
@@ -12741,7 +12627,7 @@ class GatewayRunner:
|
||||
return t("gateway.title.current_no_title", session_id=session_id)
|
||||
|
||||
async def _handle_resume_command(self, event: MessageEvent) -> str:
|
||||
"""Handle /resume command — list or switch to a previous session."""
|
||||
"""Handle /resume command — switch to a previously-named session."""
|
||||
if not self._session_db:
|
||||
from hermes_state import format_session_db_unavailable
|
||||
return format_session_db_unavailable(prefix=t("gateway.shared.session_db_unavailable_prefix"))
|
||||
@@ -12750,44 +12636,30 @@ class GatewayRunner:
|
||||
session_key = self._session_key_for_source(source)
|
||||
name = event.get_command_args().strip()
|
||||
|
||||
def _list_titled_sessions() -> list[dict]:
|
||||
user_source = source.platform.value if source.platform else None
|
||||
sessions = self._session_db.list_sessions_rich(source=user_source, limit=10)
|
||||
return [s for s in sessions if s.get("title")][:10]
|
||||
|
||||
if not name:
|
||||
# List recent titled sessions for this user/platform
|
||||
try:
|
||||
titled = _list_titled_sessions()
|
||||
user_source = source.platform.value if source.platform else None
|
||||
sessions = self._session_db.list_sessions_rich(
|
||||
source=user_source, limit=10
|
||||
)
|
||||
titled = [s for s in sessions if s.get("title")]
|
||||
if not titled:
|
||||
return t("gateway.resume.no_named_sessions")
|
||||
lines = [t("gateway.resume.list_header")]
|
||||
for idx, s in enumerate(titled[:10], start=1):
|
||||
for s in titled[:10]:
|
||||
title = s["title"]
|
||||
preview = s.get("preview", "")[:40]
|
||||
preview_part = t("gateway.resume.list_preview_suffix", preview=preview) if preview else ""
|
||||
lines.append(t("gateway.resume.list_item_numbered", index=idx, title=title, preview_part=preview_part))
|
||||
lines.append(t("gateway.resume.list_footer_numbered"))
|
||||
lines.append(t("gateway.resume.list_item", title=title, preview_part=preview_part))
|
||||
lines.append(t("gateway.resume.list_footer"))
|
||||
return "\n".join(lines)
|
||||
except Exception as e:
|
||||
logger.debug("Failed to list titled sessions: %s", e)
|
||||
return t("gateway.resume.list_failed", error=e)
|
||||
|
||||
# Resolve a numbered choice or a title to a session ID.
|
||||
if name.isdigit():
|
||||
try:
|
||||
titled = _list_titled_sessions()
|
||||
except Exception as e:
|
||||
logger.debug("Failed to list titled sessions for numeric resume: %s", e)
|
||||
return t("gateway.resume.list_failed", error=e)
|
||||
index = int(name)
|
||||
if index < 1 or index > len(titled):
|
||||
return t("gateway.resume.out_of_range", index=index)
|
||||
target = titled[index - 1]
|
||||
target_id = target.get("id")
|
||||
name = target.get("title") or name
|
||||
else:
|
||||
target_id = self._session_db.resolve_session_by_title(name)
|
||||
# Resolve the name to a session ID.
|
||||
target_id = self._session_db.resolve_session_by_title(name)
|
||||
if not target_id:
|
||||
return t("gateway.resume.not_found", name=name)
|
||||
# Compression creates child continuations that hold the live transcript.
|
||||
@@ -16269,7 +16141,11 @@ class GatewayRunner:
|
||||
)
|
||||
return
|
||||
_fut = safe_schedule_threadsafe(
|
||||
_send_or_update_status_coro(_status_adapter, _status_chat_id, event_type, prepared_message, _status_thread_metadata),
|
||||
_status_adapter.send(
|
||||
_status_chat_id,
|
||||
prepared_message,
|
||||
metadata=_status_thread_metadata,
|
||||
),
|
||||
_loop_for_step,
|
||||
logger=logger,
|
||||
log_message=f"status_callback ({event_type}) scheduling error",
|
||||
@@ -17138,7 +17014,6 @@ class GatewayRunner:
|
||||
"context_length": _context_length,
|
||||
"session_id": effective_session_id,
|
||||
"response_previewed": result.get("response_previewed", False),
|
||||
"response_transformed": result.get("response_transformed", False),
|
||||
}
|
||||
|
||||
# Start progress message sender if enabled
|
||||
@@ -17776,11 +17651,7 @@ class GatewayRunner:
|
||||
_content_delivered = bool(
|
||||
_sc and getattr(_sc, "final_content_delivered", False)
|
||||
)
|
||||
# Plugin hooks (e.g. transform_llm_output) may have appended content
|
||||
# after streaming finished — when the response was transformed, always
|
||||
# send the final version so the appended content reaches the client.
|
||||
_transformed = bool(response.get("response_transformed"))
|
||||
if not _is_empty_sentinel and not _transformed and (_streamed or _previewed or _content_delivered):
|
||||
if not _is_empty_sentinel and (_streamed or _previewed or _content_delivered):
|
||||
logger.info(
|
||||
"Suppressing normal final send for session %s: final delivery already confirmed (streamed=%s previewed=%s content_delivered=%s).",
|
||||
session_key or "?",
|
||||
@@ -17789,28 +17660,6 @@ class GatewayRunner:
|
||||
_content_delivered,
|
||||
)
|
||||
response["already_sent"] = True
|
||||
elif not _is_empty_sentinel and _transformed and _sc is not None:
|
||||
# Plugin hooks transformed the response after streaming — edit the
|
||||
# existing streamed message instead of sending a duplicate.
|
||||
_sc_msg_id = _sc.message_id
|
||||
if _sc_msg_id:
|
||||
try:
|
||||
await _sc.adapter.edit_message(
|
||||
chat_id=source.chat_id,
|
||||
message_id=_sc_msg_id,
|
||||
content=response["final_response"],
|
||||
finalize=True,
|
||||
)
|
||||
response["already_sent"] = True
|
||||
logger.info(
|
||||
"Edited streamed message %s for session %s to include plugin-transformed content.",
|
||||
_sc_msg_id, session_key or "?",
|
||||
)
|
||||
except Exception as _edit_err:
|
||||
logger.warning(
|
||||
"Failed to edit streamed message for session %s: %s",
|
||||
session_key or "?", _edit_err,
|
||||
)
|
||||
|
||||
# Schedule deletion of tracked temporary progress bubbles after the
|
||||
# final response lands. Failed runs skip this so bubbles remain as
|
||||
@@ -18237,21 +18086,6 @@ async def start_gateway(config: Optional[GatewayConfig] = None, replace: bool =
|
||||
runner.request_restart(detached=False, via_service=True)
|
||||
|
||||
loop = asyncio.get_running_loop()
|
||||
|
||||
# Install a loop-level exception handler that swallows transient
|
||||
# network errors from background tasks. Issues #31066 / #31110:
|
||||
# an unhandled ``telegram.error.TimedOut`` (or peer NetworkError /
|
||||
# httpx connection error) in any awaited coroutine would propagate
|
||||
# to the loop and kill the gateway process, taking down every
|
||||
# profile attached to the same runner. systemd then restarts the
|
||||
# service after ~5s but the active conversation turn is lost.
|
||||
#
|
||||
# The fix is intentionally narrow: only well-known transient
|
||||
# network errors are swallowed (and logged with full traceback so
|
||||
# the originating call site is still discoverable). Anything else
|
||||
# is forwarded to the default handler so real bugs still surface.
|
||||
loop.set_exception_handler(_gateway_loop_exception_handler)
|
||||
|
||||
if threading.current_thread() is threading.main_thread():
|
||||
for sig in (signal.SIGINT, signal.SIGTERM):
|
||||
try:
|
||||
|
||||
@@ -83,21 +83,6 @@ _VAR_MAP = {
|
||||
}
|
||||
|
||||
|
||||
def set_current_session_id(session_id: str) -> None:
|
||||
"""Synchronize ``HERMES_SESSION_ID`` across ContextVar and ``os.environ``.
|
||||
|
||||
Long-lived single-process entrypoints like the CLI can rotate sessions via
|
||||
``/new``, ``/resume``, ``/branch``, or compression splits without
|
||||
reconstructing the entire agent. Tools still consult
|
||||
``get_session_env("HERMES_SESSION_ID")`` with an ``os.environ`` fallback,
|
||||
so both storage paths must move together when the active session changes.
|
||||
"""
|
||||
import os
|
||||
|
||||
os.environ["HERMES_SESSION_ID"] = session_id
|
||||
_SESSION_ID.set(session_id)
|
||||
|
||||
|
||||
def set_session_vars(
|
||||
platform: str = "",
|
||||
chat_id: str = "",
|
||||
|
||||
@@ -192,11 +192,6 @@ class GatewayStreamConsumer:
|
||||
"""True when the stream consumer delivered the final assistant reply."""
|
||||
return self._final_response_sent
|
||||
|
||||
@property
|
||||
def message_id(self) -> str | None:
|
||||
"""The Discord/chat message ID of the last-sent or edited message."""
|
||||
return self._message_id
|
||||
|
||||
@property
|
||||
def final_content_delivered(self) -> bool:
|
||||
"""True when the final response content reached the user, even if
|
||||
|
||||
@@ -129,8 +129,7 @@ def build_top_level_parser():
|
||||
default=None,
|
||||
help=(
|
||||
"Provider override for this invocation (e.g. openrouter, anthropic). "
|
||||
"Applies to -z/--oneshot and --tui. The persistent provider lives in config.yaml "
|
||||
"under model.provider — use `hermes setup` or edit the file to change it."
|
||||
"Applies to -z/--oneshot and --tui. Also settable via HERMES_INFERENCE_PROVIDER env var."
|
||||
),
|
||||
)
|
||||
parser.add_argument(
|
||||
@@ -269,11 +268,7 @@ def build_top_level_parser():
|
||||
help="Inference provider (default: auto). Built-in or a user-defined name from `providers:` in config.yaml.",
|
||||
)
|
||||
chat_parser.add_argument(
|
||||
"-v",
|
||||
"--verbose",
|
||||
action="store_true",
|
||||
default=argparse.SUPPRESS,
|
||||
help="Verbose output",
|
||||
"-v", "--verbose", action="store_true", help="Verbose output"
|
||||
)
|
||||
chat_parser.add_argument(
|
||||
"-Q",
|
||||
|
||||
+1
-5
@@ -553,7 +553,6 @@ _PLACEHOLDER_SECRET_VALUES = {
|
||||
"***",
|
||||
"changeme",
|
||||
"your_api_key",
|
||||
"your_api_key_here",
|
||||
"your-api-key",
|
||||
"placeholder",
|
||||
"example",
|
||||
@@ -2066,10 +2065,7 @@ def resolve_qwen_runtime_credentials(
|
||||
def get_qwen_auth_status() -> Dict[str, Any]:
|
||||
auth_path = _qwen_cli_auth_path()
|
||||
try:
|
||||
# Validate the runtime credentials, including refresh when the cached
|
||||
# CLI token is expired. Otherwise stale tokens show up as "logged in"
|
||||
# and `hermes model` walks users into a broken Qwen setup flow.
|
||||
creds = resolve_qwen_runtime_credentials(refresh_if_expiring=True)
|
||||
creds = resolve_qwen_runtime_credentials(refresh_if_expiring=False)
|
||||
return {
|
||||
"logged_in": True,
|
||||
"auth_file": str(auth_path),
|
||||
|
||||
@@ -164,7 +164,7 @@ COMMAND_REGISTRY: list[CommandDef] = [
|
||||
cli_only=True),
|
||||
CommandDef("skills", "Search, install, inspect, or manage skills",
|
||||
"Tools & Skills", cli_only=True,
|
||||
subcommands=("search", "browse", "inspect", "install", "audit")),
|
||||
subcommands=("search", "browse", "inspect", "install")),
|
||||
CommandDef("bundles", "List skill bundles (aliases /<name> for multiple skills)",
|
||||
"Tools & Skills"),
|
||||
CommandDef("cron", "Manage scheduled tasks", "Tools & Skills",
|
||||
|
||||
+1
-23
@@ -658,8 +658,7 @@ DEFAULT_CONFIG = {
|
||||
# are owned by your host user instead of root, which avoids needing
|
||||
# `sudo chown` after container runs. Default off to preserve behavior
|
||||
# for images whose entrypoints expect to start as root (e.g. the
|
||||
# bundled Hermes image, which drops to the `hermes` user via
|
||||
# s6-setuidgid inside each supervised service).
|
||||
# bundled Hermes image, which drops to the `hermes` user via gosu).
|
||||
# When on, SETUID/SETGID caps are omitted from the container since
|
||||
# no privilege drop is needed.
|
||||
"docker_run_as_host_user": False,
|
||||
@@ -1009,19 +1008,6 @@ DEFAULT_CONFIG = {
|
||||
"compact": False,
|
||||
"personality": "kawaii",
|
||||
"resume_display": "full",
|
||||
# Recap tuning for /resume and startup resume. The defaults match the
|
||||
# historical hardcoded values; expose them as config so power users can
|
||||
# widen or tighten the snapshot to taste.
|
||||
"resume_exchanges": 10, # max user+assistant pairs to show
|
||||
"resume_max_user_chars": 300, # truncate user message text
|
||||
"resume_max_assistant_chars": 200, # truncate non-last assistant text
|
||||
"resume_max_assistant_lines": 3, # truncate non-last assistant lines
|
||||
# When True (default), assistant entries that are *only* tool calls
|
||||
# (no visible text) are skipped in the recap. This prevents the recap
|
||||
# from being dominated by `[2 tool calls: terminal, read_file]` lines
|
||||
# when an exchange was tool-heavy. Set False to restore the legacy
|
||||
# behavior of showing tool-call summaries inline.
|
||||
"resume_skip_tool_only": True,
|
||||
"busy_input_mode": "interrupt", # interrupt | queue | steer
|
||||
# When true, `hermes --tui` auto-resumes the most recent human-
|
||||
# facing session on launch instead of forging a fresh one.
|
||||
@@ -1789,14 +1775,6 @@ DEFAULT_CONFIG = {
|
||||
# ~/.hermes/bin/ on first use. When False you must install
|
||||
# bws yourself and have it on PATH.
|
||||
"auto_install": True,
|
||||
# Bitwarden region / self-hosted endpoint. Empty string
|
||||
# means use the bws CLI default (US Cloud,
|
||||
# https://vault.bitwarden.com). Set to
|
||||
# https://vault.bitwarden.eu for EU Cloud, or your own URL
|
||||
# for self-hosted Bitwarden. Plumbed into the bws subprocess
|
||||
# as BWS_SERVER_URL. Prompted for during
|
||||
# `hermes secrets bitwarden setup`.
|
||||
"server_url": "",
|
||||
},
|
||||
},
|
||||
|
||||
|
||||
@@ -1,325 +0,0 @@
|
||||
"""Container-boot reconciliation of per-profile gateway s6 services.
|
||||
|
||||
Service directories under /run/service/ live on **tmpfs** and are wiped
|
||||
on every container restart. Profile directories under
|
||||
``$HERMES_HOME/profiles/<name>/`` live on the persistent VOLUME, and
|
||||
each one records its gateway's last state in ``gateway_state.json``.
|
||||
This module bridges the two: on every container boot, walk the
|
||||
persistent profiles, recreate the s6 service slots, and auto-start
|
||||
only those whose last recorded state was ``running``.
|
||||
|
||||
Wired into the image as /etc/cont-init.d/02-reconcile-profiles by the
|
||||
Dockerfile (Phase 4 Task 4.0). Runs as root after 01-hermes-setup
|
||||
(the stage2 hook) has chowned the volume and seeded $HERMES_HOME, but
|
||||
before s6-rc starts user services.
|
||||
|
||||
Without this module, every ``docker restart`` would silently wipe
|
||||
every per-profile gateway, even though the user's profiles still
|
||||
exist on disk.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import Literal
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
# Only this prior state triggers automatic restart. Everything else
|
||||
# (startup_failed, starting, stopped, missing) registers the slot in
|
||||
# the down state and waits for explicit user action — this avoids the
|
||||
# crash-loop where a broken gateway keeps being restarted across
|
||||
# `docker restart` cycles.
|
||||
_AUTOSTART_STATES = frozenset({"running"})
|
||||
|
||||
# Stale runtime files we sweep before recreating service slots. These
|
||||
# all hold container-namespaced state (PIDs, process tables) that's
|
||||
# garbage post-restart — a numerically-equal PID in the new container
|
||||
# is a different process. See the Risk Register in the plan.
|
||||
_STALE_RUNTIME_FILES = ("gateway.pid", "processes.json")
|
||||
|
||||
ReconcileActionLabel = Literal["started", "registered", "skipped"]
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ReconcileAction:
|
||||
"""One profile's outcome from a single reconciliation pass."""
|
||||
profile: str
|
||||
prior_state: str | None
|
||||
action: ReconcileActionLabel
|
||||
|
||||
|
||||
def reconcile_profile_gateways(
|
||||
*,
|
||||
hermes_home: Path,
|
||||
scandir: Path,
|
||||
dry_run: bool = False,
|
||||
) -> list[ReconcileAction]:
|
||||
"""Recreate s6 service registrations for every persistent profile.
|
||||
|
||||
Always registers a ``gateway-default`` slot for the root profile
|
||||
(the implicit profile that lives at the top of ``$HERMES_HOME``,
|
||||
not under ``profiles/``). The dispatcher in ``hermes_cli.gateway``
|
||||
maps an empty profile suffix to ``gateway-default``, so this slot
|
||||
is what ``hermes gateway start`` (no ``-p``) targets. Without it,
|
||||
bare ``hermes gateway start`` inside the container would land on
|
||||
``s6-svc -u /run/service/gateway-default`` → uncaught
|
||||
``CalledProcessError`` → traceback to the user (PR #30136 review).
|
||||
|
||||
The default slot's prior state is read from
|
||||
``$HERMES_HOME/gateway_state.json`` (sibling to the profile root,
|
||||
not under ``profiles/``); stale runtime files there are swept the
|
||||
same way as for named profiles.
|
||||
|
||||
Args:
|
||||
hermes_home: The container's HERMES_HOME (typically /opt/data).
|
||||
Profiles live under ``<hermes_home>/profiles/<name>/``;
|
||||
the default profile lives at ``<hermes_home>`` itself.
|
||||
scandir: The s6 dynamic scandir (typically /run/service). Service
|
||||
directories are created at ``<scandir>/gateway-<profile>/``.
|
||||
dry_run: When True, walk and return the action list without
|
||||
touching the filesystem. For tests and `--dry-run` debug.
|
||||
|
||||
Returns:
|
||||
One :class:`ReconcileAction` per profile, in this order:
|
||||
``default`` first, then named profiles in directory order.
|
||||
"""
|
||||
actions: list[ReconcileAction] = []
|
||||
|
||||
# Default profile — always register, even if nothing has ever
|
||||
# populated the root profile dir. The slot exists so
|
||||
# ``hermes gateway start`` (no ``-p``) has somewhere to land;
|
||||
# auto-up only when the prior state was "running" (same rule as
|
||||
# named profiles).
|
||||
default_prior_state = _read_prior_state(hermes_home)
|
||||
default_should_start = default_prior_state in _AUTOSTART_STATES
|
||||
if not dry_run:
|
||||
_cleanup_stale_runtime_files(hermes_home)
|
||||
_register_service(scandir, "default", start=default_should_start)
|
||||
actions.append(ReconcileAction(
|
||||
profile="default",
|
||||
prior_state=default_prior_state,
|
||||
action="started" if default_should_start else "registered",
|
||||
))
|
||||
|
||||
profiles_root = hermes_home / "profiles"
|
||||
if profiles_root.is_dir():
|
||||
for entry in sorted(profiles_root.iterdir()):
|
||||
if not entry.is_dir():
|
||||
continue
|
||||
# SOUL.md is always seeded by `hermes profile create` (config.yaml
|
||||
# is not — that comes later via `hermes setup`). Use it as the
|
||||
# "real profile" marker so stray dirs (backups, manual mkdir)
|
||||
# aren't picked up.
|
||||
if not (entry / "SOUL.md").exists():
|
||||
continue
|
||||
# The "default" service name is reserved for the root
|
||||
# profile (above) — if a user has somehow created a
|
||||
# ``profiles/default/`` directory, skip it to avoid the
|
||||
# slot collision. Their gateway would still be reachable
|
||||
# via ``hermes -p default-named gateway start`` if they
|
||||
# rename the directory; we don't try to disambiguate here.
|
||||
if entry.name == "default":
|
||||
log.warning(
|
||||
"profiles/default/ exists — skipping to avoid colliding "
|
||||
"with the reserved root-profile s6 slot",
|
||||
)
|
||||
continue
|
||||
|
||||
prior_state = _read_prior_state(entry)
|
||||
should_start = prior_state in _AUTOSTART_STATES
|
||||
|
||||
if not dry_run:
|
||||
_cleanup_stale_runtime_files(entry)
|
||||
_register_service(scandir, entry.name, start=should_start)
|
||||
|
||||
actions.append(ReconcileAction(
|
||||
profile=entry.name,
|
||||
prior_state=prior_state,
|
||||
action="started" if should_start else "registered",
|
||||
))
|
||||
|
||||
if not dry_run:
|
||||
_write_reconcile_log(hermes_home, actions)
|
||||
return actions
|
||||
|
||||
|
||||
def _read_prior_state(profile_dir: Path) -> str | None:
|
||||
"""Read gateway_state.json's ``gateway_state`` field, or None if
|
||||
missing or unparseable. Unparseable counts as "no prior state" so
|
||||
we don't bork the whole reconciliation on a corrupt file."""
|
||||
state_file = profile_dir / "gateway_state.json"
|
||||
if not state_file.exists():
|
||||
return None
|
||||
try:
|
||||
return json.loads(state_file.read_text()).get("gateway_state")
|
||||
except (OSError, json.JSONDecodeError):
|
||||
log.warning(
|
||||
"could not read %s; treating as no prior state", state_file,
|
||||
)
|
||||
return None
|
||||
|
||||
|
||||
def _cleanup_stale_runtime_files(profile_dir: Path) -> None:
|
||||
"""Remove gateway.pid and processes.json — they reference PIDs in
|
||||
the dead container's process namespace and would otherwise confuse
|
||||
the newly-started gateway's process-mismatch checks."""
|
||||
for name in _STALE_RUNTIME_FILES:
|
||||
(profile_dir / name).unlink(missing_ok=True)
|
||||
|
||||
|
||||
def _register_service(scandir: Path, profile: str, *, start: bool) -> None:
|
||||
"""Recreate the s6 service slot for one profile.
|
||||
|
||||
Mirrors the rendering in :func:`S6ServiceManager.register_profile_gateway`,
|
||||
but here we control the start state directly via the ``down`` marker
|
||||
file (s6-svscan honors it on rescan). Cannot use the manager
|
||||
directly because the cont-init.d phase runs as root before
|
||||
s6-svscan starts scanning the dynamic scandir — the manager's
|
||||
``s6-svscanctl -a`` call would fail with no control socket.
|
||||
|
||||
Atomicity: build the new layout in a sibling temp directory and
|
||||
rename it into place via :meth:`Path.replace`. This matches
|
||||
:meth:`S6ServiceManager.register_profile_gateway` (PR #30136
|
||||
review item O4) — even though cont-init.d runs before s6-svscan
|
||||
starts scanning, an atomic publication keeps the contract uniform
|
||||
between the two registration paths and protects against a
|
||||
half-populated dir if the script is interrupted mid-write.
|
||||
"""
|
||||
import shutil
|
||||
|
||||
from hermes_cli.service_manager import (
|
||||
S6ServiceManager,
|
||||
_seed_supervise_skeleton,
|
||||
validate_profile_name,
|
||||
)
|
||||
|
||||
validate_profile_name(profile)
|
||||
service_dir = scandir / f"gateway-{profile}"
|
||||
tmp_dir = service_dir.with_name(service_dir.name + ".tmp")
|
||||
|
||||
# Wipe any leftover tmp from a previous interrupted run.
|
||||
if tmp_dir.exists():
|
||||
shutil.rmtree(tmp_dir, ignore_errors=True)
|
||||
tmp_dir.mkdir(parents=True)
|
||||
|
||||
try:
|
||||
(tmp_dir / "type").write_text("longrun\n")
|
||||
|
||||
# Reuse the manager's run-script rendering — single source of
|
||||
# truth so register_profile_gateway and reconcile_profile_gateways
|
||||
# stay consistent. extra_env is empty here; users who need
|
||||
# per-profile env can set it via the profile's config.yaml
|
||||
# (which the gateway itself loads).
|
||||
run = tmp_dir / "run"
|
||||
run.write_text(S6ServiceManager._render_run_script(profile, extra_env={}))
|
||||
run.chmod(0o755)
|
||||
|
||||
# Persistent log rotation (OQ8-C).
|
||||
log_subdir = tmp_dir / "log"
|
||||
log_subdir.mkdir()
|
||||
log_run = log_subdir / "run"
|
||||
log_run.write_text(S6ServiceManager._render_log_run(profile))
|
||||
log_run.chmod(0o755)
|
||||
|
||||
# The presence of a `down` file tells s6-supervise to NOT
|
||||
# start the service when s6-svscan picks it up. User brings
|
||||
# it up explicitly with `hermes -p <profile> gateway start`
|
||||
# (which routes through the Phase 4
|
||||
# _dispatch_via_service_manager_if_s6 helper to `s6-svc -u`).
|
||||
if not start:
|
||||
(tmp_dir / "down").touch()
|
||||
|
||||
# Pre-create the supervise/ skeleton with hermes ownership
|
||||
# BEFORE we publish the slot. Mirrors the same pre-creation
|
||||
# step in S6ServiceManager.register_profile_gateway — when
|
||||
# s6-svscan picks the published slot up, the s6-supervise it
|
||||
# spawns will EEXIST our dirs/FIFOs and inherit hermes
|
||||
# ownership, so runtime s6-svc / s6-svstat / s6-svwait calls
|
||||
# (all dispatched as the hermes user) won't hit EACCES. See
|
||||
# ``_seed_supervise_skeleton`` in service_manager.py for the
|
||||
# full rationale.
|
||||
_seed_supervise_skeleton(tmp_dir)
|
||||
|
||||
# Publish atomically. Path.replace handles the existing-target
|
||||
# case the same way os.rename does on POSIX: the target is
|
||||
# silently replaced, so a previous reconcile pass's slot is
|
||||
# cleanly overwritten in one operation.
|
||||
if service_dir.exists():
|
||||
shutil.rmtree(service_dir)
|
||||
tmp_dir.replace(service_dir)
|
||||
except Exception:
|
||||
shutil.rmtree(tmp_dir, ignore_errors=True)
|
||||
raise
|
||||
|
||||
|
||||
def _write_reconcile_log(
|
||||
hermes_home: Path, actions: list[ReconcileAction],
|
||||
) -> None:
|
||||
"""Append one line per profile to $HERMES_HOME/logs/container-boot.log.
|
||||
|
||||
Operators inspect this to debug "why didn't my profile come back
|
||||
up". Keeping a separate log file (vs. mixing into agent.log) lets
|
||||
troubleshooters grep for "profile=foo" without wading through
|
||||
unrelated activity.
|
||||
|
||||
Size-bounded: when the file exceeds ``_LOG_ROTATE_BYTES``
|
||||
(defaults to 256 KiB ≈ 3000 reconcile lines), the current file
|
||||
is renamed to ``container-boot.log.1`` (replacing any previous
|
||||
rotation) before the new entries are appended. This gives long-
|
||||
lived containers a soft cap of ~512 KiB across the two files
|
||||
without pulling in logrotate or s6-log machinery just for this
|
||||
one append-only file (PR #30136 review item O3).
|
||||
"""
|
||||
import time
|
||||
log_dir = hermes_home / "logs"
|
||||
log_dir.mkdir(parents=True, exist_ok=True)
|
||||
log_path = log_dir / "container-boot.log"
|
||||
|
||||
# Rotate before opening to append, so the new entries always land
|
||||
# in a fresh file when we crossed the threshold last time.
|
||||
try:
|
||||
if log_path.exists() and log_path.stat().st_size >= _LOG_ROTATE_BYTES:
|
||||
log_path.replace(log_dir / "container-boot.log.1")
|
||||
except OSError as exc:
|
||||
# Rotation failure is non-fatal — keep appending to the
|
||||
# existing file rather than losing the entry entirely.
|
||||
log.warning("could not rotate %s: %s", log_path, exc)
|
||||
|
||||
ts = time.strftime("%Y-%m-%dT%H:%M:%S%z")
|
||||
with log_path.open("a", encoding="utf-8") as f:
|
||||
for a in actions:
|
||||
f.write(
|
||||
f"{ts} profile={a.profile} prior_state={a.prior_state} "
|
||||
f"action={a.action}\n"
|
||||
)
|
||||
|
||||
|
||||
# 256 KiB soft cap on container-boot.log; rotated to .1 when crossed.
|
||||
# At ~80 B per reconcile-action line this is ~3000 lines, or about a
|
||||
# year of daily reboots on a 5-profile container. Two files = ~512 KiB
|
||||
# worst case. Tuned for visibility (small enough to grep / cat without
|
||||
# scrolling forever) more than space (the persistent volume has GB).
|
||||
_LOG_ROTATE_BYTES = 256 * 1024
|
||||
|
||||
|
||||
def main() -> int:
|
||||
"""Entry point invoked from /etc/cont-init.d/02-reconcile-profiles."""
|
||||
hermes_home = Path(os.environ.get("HERMES_HOME", "/opt/data"))
|
||||
scandir = Path(os.environ.get("S6_PROFILE_GATEWAY_SCANDIR", "/run/service"))
|
||||
actions = reconcile_profile_gateways(
|
||||
hermes_home=hermes_home, scandir=scandir,
|
||||
)
|
||||
for a in actions:
|
||||
print(
|
||||
f"reconcile: profile={a.profile} "
|
||||
f"prior_state={a.prior_state} action={a.action}"
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
+1
-9
@@ -14,7 +14,6 @@ Currently supports:
|
||||
import io
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
import sys
|
||||
import time
|
||||
import urllib.error
|
||||
@@ -37,12 +36,6 @@ _REDACTION_BANNER = (
|
||||
"run with --no-redact to disable]\n"
|
||||
)
|
||||
|
||||
_EMAIL_ADDRESS_RE = re.compile(
|
||||
r"(?<![A-Za-z0-9._%+-])"
|
||||
r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}"
|
||||
r"(?![A-Za-z0-9._%+-])"
|
||||
)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Paste services — try paste.rs first, dpaste.com as fallback.
|
||||
@@ -405,8 +398,7 @@ def _redact_log_text(text: str) -> str:
|
||||
return text
|
||||
from agent.redact import redact_sensitive_text
|
||||
|
||||
text = redact_sensitive_text(text, force=True)
|
||||
return _EMAIL_ADDRESS_RE.sub("[REDACTED_EMAIL]", text)
|
||||
return redact_sensitive_text(text, force=True)
|
||||
|
||||
|
||||
def _capture_log_snapshot(
|
||||
|
||||
+1
-85
@@ -207,69 +207,14 @@ def _fail_and_issue(text: str, detail: str, fix: str, issues: list[str]) -> None
|
||||
issues.append(fix)
|
||||
|
||||
|
||||
def _check_s6_supervision(issues: list[str]) -> None:
|
||||
"""Inside a container under our s6 /init, surface what s6 sees.
|
||||
|
||||
Runs as a counterpart to :func:`_check_gateway_service_linger` for
|
||||
the systemd-on-host case. No-op everywhere except in the s6
|
||||
container so host runs aren't cluttered with irrelevant output.
|
||||
|
||||
Reports:
|
||||
- Whether the main-hermes and dashboard static services are up
|
||||
- How many per-profile gateway slots are registered (via
|
||||
``S6ServiceManager.list_profile_gateways()``) and how many are
|
||||
currently supervised as ``up``
|
||||
"""
|
||||
try:
|
||||
from hermes_cli.service_manager import (
|
||||
S6ServiceManager,
|
||||
detect_service_manager,
|
||||
)
|
||||
except Exception:
|
||||
return
|
||||
|
||||
if detect_service_manager() != "s6":
|
||||
return
|
||||
|
||||
_section("s6 Supervision")
|
||||
|
||||
mgr = S6ServiceManager()
|
||||
|
||||
# Static services. They live under /run/service/ via s6-rc symlinks,
|
||||
# so the same s6-svstat probe works.
|
||||
for static in ("main-hermes", "dashboard"):
|
||||
if mgr.is_running(static):
|
||||
check_ok(f"{static}: up")
|
||||
else:
|
||||
check_info(f"{static}: down (expected if not enabled via env)")
|
||||
|
||||
profiles = mgr.list_profile_gateways()
|
||||
if not profiles:
|
||||
check_info("No per-profile gateways registered yet — create one with `hermes profile create <name>`")
|
||||
return
|
||||
|
||||
up_count = sum(1 for p in profiles if mgr.is_running(f"gateway-{p}"))
|
||||
check_ok(
|
||||
f"Per-profile gateways: {up_count}/{len(profiles)} supervised up"
|
||||
+ (f" ({', '.join(sorted(profiles))})" if len(profiles) <= 8 else "")
|
||||
)
|
||||
|
||||
|
||||
def _check_gateway_service_linger(issues: list[str]) -> None:
|
||||
"""Warn when a systemd user gateway service will stop after logout.
|
||||
|
||||
Skipped inside a container running under s6 — the linger concept
|
||||
(user-systemd surviving SSH logout) doesn't apply there, and the
|
||||
s6 supervision state is surfaced separately by
|
||||
``_check_s6_supervision``.
|
||||
"""
|
||||
"""Warn when a systemd user gateway service will stop after logout."""
|
||||
try:
|
||||
from hermes_cli.gateway import (
|
||||
get_systemd_linger_status,
|
||||
get_systemd_unit_path,
|
||||
is_linux,
|
||||
)
|
||||
from hermes_cli.service_manager import detect_service_manager
|
||||
except Exception as e:
|
||||
check_warn("Gateway service linger", f"(could not import gateway helpers: {e})")
|
||||
return
|
||||
@@ -277,12 +222,6 @@ def _check_gateway_service_linger(issues: list[str]) -> None:
|
||||
if not is_linux():
|
||||
return
|
||||
|
||||
# Inside a container under our s6 /init, _check_s6_supervision
|
||||
# reports the live supervision state; the linger warning would be
|
||||
# confusing here (no systemd, no logout, no "lingering" concept).
|
||||
if detect_service_manager() == "s6":
|
||||
return
|
||||
|
||||
unit_path = get_systemd_unit_path()
|
||||
if not unit_path.exists():
|
||||
return
|
||||
@@ -1045,7 +984,6 @@ def run_doctor(args):
|
||||
pass
|
||||
|
||||
_check_gateway_service_linger(issues)
|
||||
_check_s6_supervision(issues)
|
||||
|
||||
if sys.platform != "win32":
|
||||
_section("Command Installation")
|
||||
@@ -1138,26 +1076,6 @@ def run_doctor(args):
|
||||
|
||||
# Docker (optional)
|
||||
terminal_env = os.getenv("TERMINAL_ENV", "local")
|
||||
try:
|
||||
from hermes_constants import is_container as _is_container
|
||||
running_in_container = _is_container()
|
||||
except Exception:
|
||||
running_in_container = False
|
||||
|
||||
if running_in_container:
|
||||
# Inside our container the Docker terminal backend is not
|
||||
# configured by default (Docker-in-Docker isn't set up); the
|
||||
# local backend is the intended one. Skip the noisy "docker
|
||||
# not found" warning. If the user has explicitly chosen
|
||||
# TERMINAL_ENV=docker inside the container they likely mounted
|
||||
# /var/run/docker.sock, so fall through to the normal check.
|
||||
if terminal_env != "docker":
|
||||
check_info(
|
||||
"Running inside a container — using local terminal backend "
|
||||
"(docker-in-docker is not configured by default)"
|
||||
)
|
||||
# Skip to next section; Docker isn't relevant here.
|
||||
terminal_env = "local"
|
||||
if terminal_env == "docker":
|
||||
if _safe_which("docker"):
|
||||
# Check if docker daemon is running
|
||||
@@ -1180,8 +1098,6 @@ def run_doctor(args):
|
||||
check_ok("docker", "(optional)")
|
||||
elif _is_termux():
|
||||
check_info("Docker backend is not available inside Termux (expected on Android)")
|
||||
elif running_in_container:
|
||||
pass # already explained above
|
||||
else:
|
||||
check_warn("docker not found", "(optional)")
|
||||
|
||||
|
||||
@@ -140,10 +140,6 @@ def _sanitize_env_file_if_needed(path: Path) -> None:
|
||||
This produces mangled values — e.g. a bot token duplicated 8×
|
||||
(see #8908).
|
||||
|
||||
Also strips embedded null bytes which crash ``os.environ[k] = v``
|
||||
with ``ValueError: embedded null byte`` — typically introduced by
|
||||
copy-pasting API keys from terminals or rich-text editors.
|
||||
|
||||
We delegate to ``hermes_cli.config._sanitize_env_lines`` which
|
||||
already knows all valid Hermes env-var names and can split
|
||||
concatenated lines correctly.
|
||||
@@ -159,11 +155,7 @@ def _sanitize_env_file_if_needed(path: Path) -> None:
|
||||
try:
|
||||
with open(path, **read_kw) as f:
|
||||
original = f.readlines()
|
||||
# Strip null bytes before _sanitize_env_lines so they never
|
||||
# reach python-dotenv (which passes them to os.environ and
|
||||
# crashes with ValueError).
|
||||
stripped = [line.replace("\x00", "") for line in original]
|
||||
sanitized = _sanitize_env_lines(stripped)
|
||||
sanitized = _sanitize_env_lines(original)
|
||||
if sanitized != original:
|
||||
import tempfile
|
||||
fd, tmp = tempfile.mkstemp(
|
||||
@@ -252,7 +244,6 @@ def _apply_external_secret_sources(home_path: Path) -> None:
|
||||
override_existing=bool(bw_cfg.get("override_existing", False)),
|
||||
cache_ttl_seconds=float(bw_cfg.get("cache_ttl_seconds", 300)),
|
||||
auto_install=bool(bw_cfg.get("auto_install", True)),
|
||||
server_url=str(bw_cfg.get("server_url", "") or "").strip(),
|
||||
)
|
||||
|
||||
if result.applied:
|
||||
|
||||
@@ -21,8 +21,6 @@ from __future__ import annotations
|
||||
import copy
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
from hermes_cli.fallback_config import get_fallback_chain
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Helpers
|
||||
@@ -32,11 +30,20 @@ def _read_chain(config: Dict[str, Any]) -> List[Dict[str, Any]]:
|
||||
"""Return the normalized fallback chain as a list of dicts.
|
||||
|
||||
Accepts both the new list format (``fallback_providers``) and the legacy
|
||||
``fallback_model`` format. When both are present, the effective chain is
|
||||
merged with ``fallback_providers`` entries kept first. The returned list is
|
||||
always a fresh copy — callers can mutate without touching the config dict.
|
||||
single-dict format (``fallback_model``). The returned list is always a
|
||||
fresh copy — callers can mutate without touching the config dict.
|
||||
"""
|
||||
return get_fallback_chain(config)
|
||||
chain = config.get("fallback_providers") or []
|
||||
if isinstance(chain, list):
|
||||
result = [dict(e) for e in chain if isinstance(e, dict) and e.get("provider") and e.get("model")]
|
||||
if result:
|
||||
return result
|
||||
legacy = config.get("fallback_model")
|
||||
if isinstance(legacy, dict) and legacy.get("provider") and legacy.get("model"):
|
||||
return [dict(legacy)]
|
||||
if isinstance(legacy, list):
|
||||
return [dict(e) for e in legacy if isinstance(e, dict) and e.get("provider") and e.get("model")]
|
||||
return []
|
||||
|
||||
|
||||
def _write_chain(config: Dict[str, Any], chain: List[Dict[str, Any]]) -> None:
|
||||
|
||||
@@ -1,72 +0,0 @@
|
||||
"""Helpers for reading the effective fallback provider chain from config."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
|
||||
def _normalized_base_url(value: Any) -> str:
|
||||
if not isinstance(value, str):
|
||||
return ""
|
||||
return value.strip().rstrip("/")
|
||||
|
||||
|
||||
def _iter_fallback_entries(raw: Any) -> list[dict[str, Any]]:
|
||||
if isinstance(raw, dict):
|
||||
candidates = [raw]
|
||||
elif isinstance(raw, list):
|
||||
candidates = raw
|
||||
else:
|
||||
return []
|
||||
|
||||
entries: list[dict[str, Any]] = []
|
||||
for entry in candidates:
|
||||
if not isinstance(entry, dict):
|
||||
continue
|
||||
provider = str(entry.get("provider") or "").strip()
|
||||
model = str(entry.get("model") or "").strip()
|
||||
if not provider or not model:
|
||||
continue
|
||||
|
||||
normalized = dict(entry)
|
||||
normalized["provider"] = provider
|
||||
normalized["model"] = model
|
||||
|
||||
base_url = _normalized_base_url(entry.get("base_url"))
|
||||
if base_url:
|
||||
normalized["base_url"] = base_url
|
||||
|
||||
entries.append(normalized)
|
||||
return entries
|
||||
|
||||
|
||||
def _entry_identity(entry: dict[str, Any]) -> tuple[str, str, str]:
|
||||
return (
|
||||
str(entry.get("provider") or "").strip().lower(),
|
||||
str(entry.get("model") or "").strip().lower(),
|
||||
_normalized_base_url(entry.get("base_url")).lower(),
|
||||
)
|
||||
|
||||
|
||||
def get_fallback_chain(config: dict[str, Any] | None) -> list[dict[str, Any]]:
|
||||
"""Return the effective fallback chain merged across old and new config keys.
|
||||
|
||||
``fallback_providers`` remains the primary source of truth and keeps its
|
||||
order. Legacy ``fallback_model`` entries are appended afterwards unless
|
||||
they target the same provider/model/base_url route as an earlier entry.
|
||||
The returned list always contains fresh dict copies.
|
||||
"""
|
||||
|
||||
config = config or {}
|
||||
chain: list[dict[str, Any]] = []
|
||||
seen: set[tuple[str, str, str]] = set()
|
||||
|
||||
for key in ("fallback_providers", "fallback_model"):
|
||||
for entry in _iter_fallback_entries(config.get(key)):
|
||||
identity = _entry_identity(entry)
|
||||
if identity in seen:
|
||||
continue
|
||||
seen.add(identity)
|
||||
chain.append(entry)
|
||||
|
||||
return chain
|
||||
+5
-179
@@ -981,18 +981,6 @@ def get_gateway_runtime_snapshot(system: bool = False) -> GatewayRuntimeSnapshot
|
||||
from hermes_constants import is_container
|
||||
|
||||
if is_linux() and is_container():
|
||||
# Phase 4: report s6 supervision when running under our /init.
|
||||
# Other container runtimes (or containers built before Phase 2)
|
||||
# still get the original "docker (foreground)" label.
|
||||
try:
|
||||
from hermes_cli.service_manager import detect_service_manager
|
||||
if detect_service_manager() == "s6":
|
||||
return GatewayRuntimeSnapshot(
|
||||
manager="s6 (container supervisor)",
|
||||
gateway_pids=gateway_pids,
|
||||
)
|
||||
except Exception:
|
||||
pass # Fall through to the legacy label on any detection error.
|
||||
return GatewayRuntimeSnapshot(
|
||||
manager="docker (foreground)",
|
||||
gateway_pids=gateway_pids,
|
||||
@@ -1214,17 +1202,7 @@ def _systemd_operational(system: bool = False) -> bool:
|
||||
|
||||
|
||||
def _container_systemd_operational() -> bool:
|
||||
"""Return True when a container exposes working user or system systemd.
|
||||
|
||||
This is NOT our Hermes Docker image — that one runs s6-overlay as
|
||||
PID 1 (since Phase 2 of the s6-overlay supervision plan) and is
|
||||
detected via ``service_manager.detect_service_manager() == "s6"``.
|
||||
This function handles the "container managed by something else"
|
||||
case: systemd-nspawn, certain k8s pods, containers built FROM
|
||||
systemd-bearing distros where the user has wired systemd as their
|
||||
init. In those environments systemctl behaves identically to the
|
||||
host case, so we fall through to the normal systemd code paths.
|
||||
"""
|
||||
"""Return True when a container exposes working user or system systemd."""
|
||||
if _systemd_operational(system=False):
|
||||
return True
|
||||
if _systemd_operational(system=True):
|
||||
@@ -4020,11 +3998,15 @@ def _setup_dingtalk():
|
||||
client_id, client_secret = result
|
||||
save_env_value("DINGTALK_CLIENT_ID", client_id)
|
||||
save_env_value("DINGTALK_CLIENT_SECRET", client_secret)
|
||||
save_env_value("DINGTALK_ALLOW_ALL_USERS", "true")
|
||||
print()
|
||||
print_success(f"{emoji} {label} configured via QR scan!")
|
||||
else:
|
||||
# ── Manual entry ──
|
||||
_setup_standard_platform(dingtalk_platform)
|
||||
# Also enable allow-all by default for convenience
|
||||
if get_env_value("DINGTALK_CLIENT_ID"):
|
||||
save_env_value("DINGTALK_ALLOW_ALL_USERS", "true")
|
||||
|
||||
|
||||
def _setup_wecom():
|
||||
@@ -5025,108 +5007,6 @@ def gateway_setup():
|
||||
# Main Command Handler
|
||||
# =============================================================================
|
||||
|
||||
def _dispatch_via_service_manager_if_s6(
|
||||
action: str, profile: str | None = None,
|
||||
) -> bool:
|
||||
"""If we're in a container with s6, dispatch gateway lifecycle via s6.
|
||||
|
||||
Returns True iff dispatched (caller should ``return``); False
|
||||
otherwise — caller continues with the host-side code path.
|
||||
|
||||
``action`` is one of ``start`` / ``stop`` / ``restart``. The
|
||||
profile defaults to the current one (resolved via ``_profile_arg``).
|
||||
The s6 service slot was created either by the Phase 4 profile-create
|
||||
hook or by the container-boot reconciler (cont-init.d/02-…). If it
|
||||
doesn't exist or s6 returns an error, the named errors from
|
||||
:mod:`hermes_cli.service_manager` are caught and surfaced as
|
||||
actionable CLI messages (no raw ``CalledProcessError`` traceback).
|
||||
"""
|
||||
from hermes_cli.service_manager import (
|
||||
GatewayNotRegisteredError,
|
||||
S6CommandError,
|
||||
detect_service_manager,
|
||||
get_service_manager,
|
||||
)
|
||||
|
||||
if detect_service_manager() != "s6":
|
||||
return False
|
||||
if profile is None:
|
||||
# _profile_suffix() returns the bare profile name for
|
||||
# HERMES_HOME=<root>/profiles/<name>, "" for the default root,
|
||||
# or a hash for unrelated paths. Map "" → "default" so the
|
||||
# default-profile gateway is reachable as gateway-default.
|
||||
profile = _profile_suffix() or "default"
|
||||
mgr = get_service_manager()
|
||||
service_name = f"gateway-{profile}"
|
||||
try:
|
||||
if action == "start":
|
||||
mgr.start(service_name)
|
||||
elif action == "stop":
|
||||
mgr.stop(service_name)
|
||||
elif action == "restart":
|
||||
mgr.restart(service_name)
|
||||
else:
|
||||
return False
|
||||
except GatewayNotRegisteredError as exc:
|
||||
print(f"✗ {exc}")
|
||||
sys.exit(1)
|
||||
except S6CommandError as exc:
|
||||
print(f"✗ {exc}")
|
||||
sys.exit(1)
|
||||
return True
|
||||
|
||||
|
||||
def _dispatch_all_via_service_manager_if_s6(action: str) -> bool:
|
||||
"""Inside a container with s6, dispatch ``--all`` lifecycle to every
|
||||
registered profile gateway.
|
||||
|
||||
Returns True iff dispatched (caller should ``return``); False
|
||||
otherwise — caller continues with the host-side code path.
|
||||
|
||||
Without this, ``hermes gateway stop --all`` and ``... restart --all``
|
||||
fall through to ``kill_gateway_processes(all_profiles=True)``, which
|
||||
just ``pkill``s every gateway process. s6-supervise observes the
|
||||
crash and restarts each one ~1s later — so ``--all`` ends up
|
||||
*kicking* every gateway instead of *stopping* it. By iterating
|
||||
``list_profile_gateways()`` and sending the lifecycle command
|
||||
through the service manager we get the intended semantics (s6's
|
||||
``want up``/``want down`` flips correctly so supervise stays down
|
||||
after a stop).
|
||||
|
||||
``action`` is one of ``stop`` / ``restart`` (``start --all`` isn't
|
||||
a supported CLI surface).
|
||||
"""
|
||||
from hermes_cli.service_manager import (
|
||||
detect_service_manager,
|
||||
get_service_manager,
|
||||
)
|
||||
|
||||
if detect_service_manager() != "s6":
|
||||
return False
|
||||
if action not in ("stop", "restart"):
|
||||
return False
|
||||
mgr = get_service_manager()
|
||||
profiles = mgr.list_profile_gateways()
|
||||
if not profiles:
|
||||
print("✗ No profile gateways registered under s6")
|
||||
return True
|
||||
fn = mgr.stop if action == "stop" else mgr.restart
|
||||
errors: list[tuple[str, Exception]] = []
|
||||
for profile in profiles:
|
||||
service_name = f"gateway-{profile}"
|
||||
try:
|
||||
fn(service_name)
|
||||
except Exception as exc: # noqa: BLE001 — report and continue
|
||||
errors.append((profile, exc))
|
||||
succeeded = len(profiles) - len(errors)
|
||||
verb = "stopped" if action == "stop" else "restarted"
|
||||
if succeeded:
|
||||
print(f"✓ {verb.capitalize()} {succeeded} profile gateway(s) under s6")
|
||||
for profile, exc in errors:
|
||||
print(f"✗ Could not {action} gateway-{profile}: {exc}")
|
||||
return True
|
||||
|
||||
|
||||
def gateway_command(args):
|
||||
"""Handle gateway subcommands."""
|
||||
try:
|
||||
@@ -5211,21 +5091,6 @@ def _gateway_command_inner(args):
|
||||
print(" nohup hermes gateway run > ~/.hermes/logs/gateway.log 2>&1 & # background")
|
||||
sys.exit(1)
|
||||
elif is_container():
|
||||
# Phase 4: inside a container with s6 the gateway service is
|
||||
# auto-registered when the profile is created (and reconciled
|
||||
# at every container boot). `install` is therefore informational.
|
||||
from hermes_cli.service_manager import detect_service_manager
|
||||
if detect_service_manager() == "s6":
|
||||
print("Per-profile gateways are auto-registered when you create a profile.")
|
||||
print()
|
||||
print(" hermes profile create <name> # creates the s6 service slot")
|
||||
print(" hermes -p <name> gateway start # bring it up via s6")
|
||||
print(" hermes status # see currently-supervised gateways")
|
||||
return
|
||||
# Fallback for pre-s6 containers or other container runtimes
|
||||
# we haven't taught about supervision (Podman without our
|
||||
# /init, k8s plain runs, etc.) — the historical guidance still
|
||||
# applies.
|
||||
print("Service installation is not needed inside a Docker container.")
|
||||
print("The container runtime is your service manager — use Docker restart policies instead:")
|
||||
print()
|
||||
@@ -5256,13 +5121,6 @@ def _gateway_command_inner(args):
|
||||
from hermes_cli import gateway_windows
|
||||
gateway_windows.uninstall()
|
||||
elif is_container():
|
||||
from hermes_cli.service_manager import detect_service_manager
|
||||
if detect_service_manager() == "s6":
|
||||
print("Per-profile gateways are auto-unregistered when you delete the profile.")
|
||||
print()
|
||||
print(" hermes profile delete <name> # tears down the s6 service slot")
|
||||
print(" hermes -p <name> gateway stop # stop without deleting the profile")
|
||||
return
|
||||
print("Service uninstall is not applicable inside a Docker container.")
|
||||
print("To stop the gateway, stop or remove the container:")
|
||||
print()
|
||||
@@ -5277,14 +5135,6 @@ def _gateway_command_inner(args):
|
||||
system = getattr(args, 'system', False)
|
||||
start_all = getattr(args, 'all', False)
|
||||
|
||||
# Phase 4: inside a container with s6, dispatch via the service
|
||||
# manager instead of falling through to systemd/launchd/windows.
|
||||
# `--all` isn't meaningful here (each profile has its own service
|
||||
# slot — start them individually via `hermes -p <name> gateway
|
||||
# start`), so just bring up the current profile's slot.
|
||||
if not start_all and _dispatch_via_service_manager_if_s6("start"):
|
||||
return
|
||||
|
||||
if start_all:
|
||||
# Kill all stale gateway processes across all profiles before starting
|
||||
killed = kill_gateway_processes(all_profiles=True)
|
||||
@@ -5314,11 +5164,6 @@ def _gateway_command_inner(args):
|
||||
print("To enable systemd: add systemd=true to /etc/wsl.conf and run 'wsl --shutdown' from PowerShell.")
|
||||
sys.exit(1)
|
||||
elif is_container():
|
||||
# Reached only when s6 ISN'T running (the early dispatch
|
||||
# above handles the s6 case). Pre-s6 containers or other
|
||||
# container runtimes that don't ship our /init get the
|
||||
# historical guidance: the gateway is the container's main
|
||||
# process, so use docker lifecycle commands.
|
||||
print("Service start is not applicable inside a Docker container.")
|
||||
print("The gateway runs as the container's main process.")
|
||||
print()
|
||||
@@ -5335,15 +5180,6 @@ def _gateway_command_inner(args):
|
||||
stop_all = getattr(args, 'all', False)
|
||||
system = getattr(args, 'system', False)
|
||||
|
||||
# Phase 4: inside a container with s6, dispatch via the service
|
||||
# manager. ``--all`` iterates every registered profile gateway
|
||||
# through s6 (otherwise it would fall through to ``pkill``,
|
||||
# which s6-supervise observes as a crash and immediately restarts).
|
||||
if stop_all and _dispatch_all_via_service_manager_if_s6("stop"):
|
||||
return
|
||||
if not stop_all and _dispatch_via_service_manager_if_s6("stop"):
|
||||
return
|
||||
|
||||
if stop_all:
|
||||
# --all: kill every gateway process on the machine
|
||||
service_available = False
|
||||
@@ -5413,16 +5249,6 @@ def _gateway_command_inner(args):
|
||||
restart_all = getattr(args, 'all', False)
|
||||
service_configured = False
|
||||
|
||||
# Phase 4: inside a container with s6, dispatch via the service
|
||||
# manager (s6-svc -t restarts the supervised process). ``--all``
|
||||
# iterates every registered profile gateway through s6; without
|
||||
# this it would fall through to ``pkill``, which s6-supervise
|
||||
# would observe as a crash and immediately restart anyway.
|
||||
if restart_all and _dispatch_all_via_service_manager_if_s6("restart"):
|
||||
return
|
||||
if not restart_all and _dispatch_via_service_manager_if_s6("restart"):
|
||||
return
|
||||
|
||||
if restart_all:
|
||||
# --all: stop every gateway process across all profiles, then start fresh
|
||||
service_stopped = False
|
||||
|
||||
@@ -550,39 +550,6 @@ def build_parser(parent_subparsers: argparse._SubParsersAction) -> argparse.Argu
|
||||
p_unblock = sub.add_parser("unblock", help="Return one or more blocked/scheduled tasks to ready")
|
||||
p_unblock.add_argument("task_ids", nargs="+")
|
||||
|
||||
p_promote = sub.add_parser(
|
||||
"promote",
|
||||
help="Manually move one or more todo/blocked tasks to ready (recovery path)",
|
||||
)
|
||||
p_promote.add_argument("task_id")
|
||||
p_promote.add_argument(
|
||||
"reason",
|
||||
nargs="*",
|
||||
help="Audit-trail reason (recorded on the task_events row)",
|
||||
)
|
||||
p_promote.add_argument(
|
||||
"--ids",
|
||||
nargs="+",
|
||||
default=None,
|
||||
help="Additional task ids to promote with the same reason (bulk mode)",
|
||||
)
|
||||
p_promote.add_argument(
|
||||
"--force",
|
||||
action="store_true",
|
||||
help="Promote even if parent dependencies are not yet done/archived",
|
||||
)
|
||||
p_promote.add_argument(
|
||||
"--dry-run",
|
||||
action="store_true",
|
||||
help="Validate the promotion without mutating state",
|
||||
)
|
||||
p_promote.add_argument(
|
||||
"--json",
|
||||
dest="json",
|
||||
action="store_true",
|
||||
help="Emit machine-readable JSON result",
|
||||
)
|
||||
|
||||
p_archive = sub.add_parser("archive", help="Archive one or more tasks")
|
||||
p_archive.add_argument("task_ids", nargs="*",
|
||||
help="Task ids to archive (default mode)")
|
||||
@@ -932,7 +899,6 @@ def kanban_command(args: argparse.Namespace) -> int:
|
||||
"block": _cmd_block,
|
||||
"schedule": _cmd_schedule,
|
||||
"unblock": _cmd_unblock,
|
||||
"promote": _cmd_promote,
|
||||
"archive": _cmd_archive,
|
||||
"tail": _cmd_tail,
|
||||
"dispatch": _cmd_dispatch,
|
||||
@@ -1989,57 +1955,6 @@ def _cmd_unblock(args: argparse.Namespace) -> int:
|
||||
return 0 if not failed else 1
|
||||
|
||||
|
||||
def _cmd_promote(args: argparse.Namespace) -> int:
|
||||
reason = " ".join(args.reason).strip() if args.reason else None
|
||||
author = _profile_author()
|
||||
as_json = getattr(args, "json", False)
|
||||
extra_ids = list(getattr(args, "ids", None) or [])
|
||||
# Dedupe while preserving order; positional task_id always first.
|
||||
ids: list[str] = []
|
||||
seen: set[str] = set()
|
||||
for tid in [args.task_id, *extra_ids]:
|
||||
if tid not in seen:
|
||||
ids.append(tid)
|
||||
seen.add(tid)
|
||||
|
||||
results: list[dict[str, object]] = []
|
||||
with kb.connect() as conn:
|
||||
for tid in ids:
|
||||
ok, err = kb.promote_task(
|
||||
conn,
|
||||
tid,
|
||||
actor=author,
|
||||
reason=reason,
|
||||
force=bool(args.force),
|
||||
dry_run=bool(args.dry_run),
|
||||
)
|
||||
results.append({
|
||||
"task_id": tid,
|
||||
"promoted": ok,
|
||||
"dry_run": bool(args.dry_run),
|
||||
"forced": bool(args.force),
|
||||
"reason": reason,
|
||||
"error": err,
|
||||
})
|
||||
|
||||
failed = [r for r in results if not r["promoted"]]
|
||||
if as_json:
|
||||
# Single-id stays a flat object for back-compat; bulk emits a list.
|
||||
payload: object = results[0] if len(results) == 1 else results
|
||||
print(json.dumps(payload, indent=2, ensure_ascii=False))
|
||||
return 0 if not failed else 1
|
||||
|
||||
tag = " (dry)" if args.dry_run else ""
|
||||
label = "Would promote" if args.dry_run else "Promoted"
|
||||
for r in results:
|
||||
if r["promoted"]:
|
||||
suffix = f": {reason}" if reason else ""
|
||||
print(f"{label} {r['task_id']} -> ready{tag}{suffix}")
|
||||
else:
|
||||
print(f"cannot promote {r['task_id']}: {r['error']}", file=sys.stderr)
|
||||
return 0 if not failed else 1
|
||||
|
||||
|
||||
def _cmd_archive(args: argparse.Namespace) -> int:
|
||||
ids = list(args.task_ids or [])
|
||||
purge_ids = list(getattr(args, "purge_ids", None) or [])
|
||||
|
||||
+4
-392
@@ -75,7 +75,6 @@ import json
|
||||
import os
|
||||
import re
|
||||
import secrets
|
||||
import shutil
|
||||
import sqlite3
|
||||
import subprocess
|
||||
import sys
|
||||
@@ -83,7 +82,6 @@ import threading
|
||||
import logging
|
||||
import time
|
||||
from dataclasses import dataclass, field
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from typing import Any, Iterable, Optional
|
||||
|
||||
@@ -1007,131 +1005,6 @@ def _validate_sqlite_header(path: Path) -> None:
|
||||
)
|
||||
|
||||
|
||||
class KanbanDbCorruptError(RuntimeError):
|
||||
"""Raised when an existing kanban DB file fails integrity checks.
|
||||
|
||||
Fail-closed guard against silent recreation of a corrupt board file,
|
||||
which would otherwise destroy the user's tasks. Carries both the
|
||||
original path and the timestamped backup we made before refusing.
|
||||
"""
|
||||
|
||||
def __init__(self, db_path: Path, backup_path: Optional[Path], reason: str):
|
||||
self.db_path = db_path
|
||||
self.backup_path = backup_path
|
||||
self.reason = reason
|
||||
backup_str = str(backup_path) if backup_path is not None else "<backup failed>"
|
||||
super().__init__(
|
||||
f"Refusing to open corrupt kanban DB at {db_path}: {reason}. "
|
||||
f"Original preserved; backup at {backup_str}."
|
||||
)
|
||||
|
||||
|
||||
def _backup_corrupt_db(path: Path) -> Optional[Path]:
|
||||
"""Copy a corrupt DB (and its WAL/SHM sidecars) to a timestamped backup.
|
||||
|
||||
Returns the backup path of the main DB file, or ``None`` if the copy
|
||||
itself failed (the caller still raises loudly in that case).
|
||||
|
||||
Writes are confined to the original DB's parent directory. The
|
||||
backup basename is derived purely from ``path.name``, never from
|
||||
caller-supplied directory segments — no traversal is possible.
|
||||
"""
|
||||
# Resolve once and pin the parent so subsequent path operations cannot
|
||||
# escape it. ``Path.resolve()`` collapses any ``..`` segments and
|
||||
# symlinks, and we only ever write inside ``parent``.
|
||||
resolved = path.resolve()
|
||||
parent = resolved.parent
|
||||
base_name = resolved.name # basename only
|
||||
stamp = datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
candidate = parent / f"{base_name}.corrupt.{stamp}.bak"
|
||||
# Defensive: candidate must still be inside parent after construction.
|
||||
# f-string interpolation of ``base_name`` cannot escape ``parent``
|
||||
# because ``base_name`` is itself a resolved basename, but assert it
|
||||
# anyway so static analyzers can see the containment guarantee.
|
||||
if candidate.parent != parent:
|
||||
return None
|
||||
counter = 0
|
||||
while candidate.exists():
|
||||
counter += 1
|
||||
candidate = parent / f"{base_name}.corrupt.{stamp}.{counter}.bak"
|
||||
if candidate.parent != parent:
|
||||
return None
|
||||
try:
|
||||
shutil.copy2(resolved, candidate)
|
||||
except OSError:
|
||||
return None
|
||||
for suffix in ("-wal", "-shm"):
|
||||
sidecar = parent / (base_name + suffix)
|
||||
if sidecar.parent != parent or not sidecar.exists():
|
||||
continue
|
||||
try:
|
||||
sidecar_backup = parent / (candidate.name + suffix)
|
||||
if sidecar_backup.parent != parent:
|
||||
continue
|
||||
shutil.copy2(sidecar, sidecar_backup)
|
||||
except OSError:
|
||||
pass
|
||||
return candidate
|
||||
|
||||
|
||||
def _guard_existing_db_is_healthy(path: Path) -> None:
|
||||
"""Run ``PRAGMA integrity_check`` on an existing non-empty DB file.
|
||||
|
||||
Opens the probe in read/write mode so SQLite can recover or
|
||||
checkpoint a healthy WAL/hot-journal DB before we declare it
|
||||
corrupt. If the file is malformed, copy it (and any WAL/SHM
|
||||
sidecars) to a timestamped backup and raise
|
||||
:class:`KanbanDbCorruptError` so callers cannot silently recreate
|
||||
the schema on top of a damaged DB.
|
||||
|
||||
Transient lock/busy errors (``sqlite3.OperationalError``) are NOT
|
||||
treated as corruption; they propagate raw so the caller sees a
|
||||
normal lock failure and no spurious ``.corrupt`` backup is made.
|
||||
|
||||
No-op for missing files, zero-byte files (treated as fresh), and
|
||||
paths already proven healthy this process (cache hit).
|
||||
|
||||
Path-trust note: ``path`` arrives via :func:`connect`, which itself
|
||||
resolves it from an explicit ``db_path`` argument, the
|
||||
:func:`kanban_db_path` env-var chain, or the kanban-home default —
|
||||
all sources Hermes treats as user-controlled-but-trusted on the
|
||||
user's own machine. We additionally resolve the path here and
|
||||
confine all filesystem writes to its parent directory so any
|
||||
accidental ``..`` segments are collapsed before any I/O happens.
|
||||
"""
|
||||
# Resolve before any I/O. ``Path.resolve()`` normalizes ``..`` and
|
||||
# symlinks, giving us a canonical path whose parent dir we can pin.
|
||||
try:
|
||||
resolved = path.resolve()
|
||||
except OSError:
|
||||
return
|
||||
try:
|
||||
if not resolved.exists() or resolved.stat().st_size == 0:
|
||||
return
|
||||
except OSError:
|
||||
return
|
||||
if str(resolved) in _INITIALIZED_PATHS:
|
||||
return
|
||||
reason: Optional[str] = None
|
||||
try:
|
||||
probe = sqlite3.connect(str(resolved), timeout=5, isolation_level=None)
|
||||
try:
|
||||
row = probe.execute("PRAGMA integrity_check").fetchone()
|
||||
finally:
|
||||
probe.close()
|
||||
if not row or (row[0] or "").lower() != "ok":
|
||||
reason = f"integrity_check returned {row[0] if row else '<no row>'!r}"
|
||||
except sqlite3.OperationalError:
|
||||
# Lock contention, busy, transient IO — not corruption. Let it propagate.
|
||||
raise
|
||||
except sqlite3.DatabaseError as exc:
|
||||
reason = f"sqlite refused to open file: {exc}"
|
||||
if reason is None:
|
||||
return
|
||||
backup = _backup_corrupt_db(resolved)
|
||||
raise KanbanDbCorruptError(resolved, backup, reason)
|
||||
|
||||
|
||||
def connect(
|
||||
db_path: Optional[Path] = None,
|
||||
*,
|
||||
@@ -1160,13 +1033,7 @@ def connect(
|
||||
else:
|
||||
path = kanban_db_path(board=board)
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
# Cheap byte-level check first — catches the #29507 TLS-overwrite shape
|
||||
# and other invalid-header cases without opening a sqlite connection.
|
||||
_validate_sqlite_header(path)
|
||||
# Full integrity probe — catches corruption past the header (malformed
|
||||
# pages, broken internal metadata). Cached per-path after first success
|
||||
# via _INITIALIZED_PATHS so it only runs once per process per path.
|
||||
_guard_existing_db_is_healthy(path)
|
||||
resolved = str(path.resolve())
|
||||
conn = sqlite3.connect(str(path), isolation_level=None, timeout=30)
|
||||
try:
|
||||
@@ -1651,15 +1518,8 @@ def create_task(
|
||||
now = int(time.time())
|
||||
|
||||
# Resolve workspace_path from board-level default_workdir when the
|
||||
# caller did not specify one explicitly. Board defaults represent
|
||||
# persistent project checkouts, so only persistent workspace kinds may
|
||||
# inherit them. Scratch workspaces are auto-deleted on completion and
|
||||
# must stay under the per-board scratch root created by
|
||||
# ``resolve_workspace``; inheriting ``default_workdir`` for a scratch
|
||||
# task would point cleanup at the user's source tree (#28818). The
|
||||
# containment guard in ``_cleanup_workspace`` is the safety rail, but
|
||||
# we also stop the bad state from being created in the first place.
|
||||
if workspace_path is None and workspace_kind in {"dir", "worktree"}:
|
||||
# caller did not specify one explicitly.
|
||||
if workspace_path is None:
|
||||
board_slug = board if board else get_current_board()
|
||||
board_meta = read_board_metadata(board_slug)
|
||||
board_default = board_meta.get("default_workdir")
|
||||
@@ -3044,81 +2904,6 @@ def complete_task(
|
||||
# Workspace / tmux cleanup
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def _is_managed_scratch_path(p: Path) -> bool:
|
||||
"""Return True iff *p* is a strict descendant of a kanban-managed scratch root.
|
||||
|
||||
A managed root is exclusively a ``workspaces/`` directory — never the
|
||||
broader kanban home, a board root, or sibling subtrees like ``logs/`` or
|
||||
``boards/<slug>/`` itself. Allowed roots:
|
||||
|
||||
* ``HERMES_KANBAN_WORKSPACES_ROOT`` when set (worker-side override
|
||||
injected by the dispatcher).
|
||||
* ``<kanban_home>/kanban/workspaces`` — legacy default-board scratch root.
|
||||
* ``<kanban_home>/kanban/boards/<slug>/workspaces`` for each board slug
|
||||
that currently exists on disk.
|
||||
|
||||
The check requires strict descendancy: a path equal to one of these
|
||||
roots is NOT managed (deleting the workspaces root would wipe every
|
||||
task's scratch dir at once), and a path that resolves to ``<kanban_home>
|
||||
/kanban`` itself, ``<kanban_home>/kanban/logs``, or
|
||||
``<kanban_home>/kanban/boards/<slug>`` is rejected because those
|
||||
subtrees hold Hermes' own DB, metadata, and logs, not task workspaces.
|
||||
|
||||
Used by :func:`_cleanup_workspace` to refuse to ``shutil.rmtree`` paths
|
||||
outside Hermes-managed storage. A board ``default_workdir`` pointing at a
|
||||
real source tree can otherwise pair with ``workspace_kind='scratch'`` and
|
||||
cause task completion to delete user data (#28818).
|
||||
"""
|
||||
try:
|
||||
p_abs = p.resolve(strict=False)
|
||||
except OSError:
|
||||
return False
|
||||
roots: list[Path] = []
|
||||
override = os.environ.get("HERMES_KANBAN_WORKSPACES_ROOT", "").strip()
|
||||
if override:
|
||||
try:
|
||||
roots.append(Path(override).expanduser().resolve(strict=False))
|
||||
except OSError:
|
||||
pass
|
||||
try:
|
||||
home = kanban_home()
|
||||
except OSError:
|
||||
home = None
|
||||
if home is not None:
|
||||
try:
|
||||
roots.append((home / "kanban" / "workspaces").resolve(strict=False))
|
||||
except OSError:
|
||||
pass
|
||||
try:
|
||||
boards_parent = (home / "kanban" / "boards").resolve(strict=False)
|
||||
except OSError:
|
||||
boards_parent = None
|
||||
if boards_parent is not None:
|
||||
try:
|
||||
entries = list(boards_parent.iterdir())
|
||||
except OSError:
|
||||
entries = []
|
||||
for entry in entries:
|
||||
try:
|
||||
if not entry.is_dir():
|
||||
continue
|
||||
except OSError:
|
||||
continue
|
||||
try:
|
||||
roots.append((entry / "workspaces").resolve(strict=False))
|
||||
except OSError:
|
||||
continue
|
||||
for root in roots:
|
||||
if p_abs == root:
|
||||
continue
|
||||
try:
|
||||
if p_abs.is_relative_to(root):
|
||||
return True
|
||||
except ValueError:
|
||||
continue
|
||||
return False
|
||||
|
||||
|
||||
def _cleanup_workspace(conn: sqlite3.Connection, task_id: str) -> None:
|
||||
"""Remove a task's scratch workspace dir and kill its stale tmux session.
|
||||
|
||||
@@ -3141,21 +2926,8 @@ def _cleanup_workspace(conn: sqlite3.Connection, task_id: str) -> None:
|
||||
import shutil
|
||||
wp = Path(path)
|
||||
if wp.is_dir():
|
||||
# Containment guard (#28818): a board's ``default_workdir`` can
|
||||
# pair ``workspace_kind='scratch'`` with a user-supplied path
|
||||
# pointing at a real source tree. Without this check, task
|
||||
# completion would unconditionally ``shutil.rmtree`` that path
|
||||
# and silently delete the user's source data.
|
||||
if _is_managed_scratch_path(wp):
|
||||
shutil.rmtree(wp, ignore_errors=True)
|
||||
_log.debug("Removed scratch workspace: %s", wp)
|
||||
else:
|
||||
_log.warning(
|
||||
"Refusing to remove out-of-scratch workspace for task %s: %s "
|
||||
"(workspace_kind='scratch' but path is outside any "
|
||||
"kanban-managed workspaces root)",
|
||||
task_id, wp,
|
||||
)
|
||||
shutil.rmtree(wp, ignore_errors=True)
|
||||
_log.debug("Removed scratch workspace: %s", wp)
|
||||
# Also kill the tmux session for the worker that owned this task,
|
||||
# if the tmux session is now dead (worker process exited).
|
||||
_cleanup_worker_tmux(conn, task_id)
|
||||
@@ -3189,93 +2961,6 @@ def _cleanup_worker_tmux(conn: sqlite3.Connection, task_id: str) -> None:
|
||||
pass # best-effort — never block completion
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# First-use tip for scratch workspaces
|
||||
# ---------------------------------------------------------------------------
|
||||
#
|
||||
# Scratch workspaces are intentionally ephemeral — ``_cleanup_workspace``
|
||||
# removes them as soon as ``complete_task`` runs. New users often don't
|
||||
# realize that and lose worker output (community report, May 2026). The
|
||||
# behavior is right; the lack of warning is the bug.
|
||||
#
|
||||
# On the FIRST scratch workspace materialization across the whole install
|
||||
# we:
|
||||
# 1. Log a warning line on the dispatcher logger.
|
||||
# 2. Append a ``tip_scratch_workspace`` event on the task so it's visible
|
||||
# via ``hermes kanban show <id>`` and the dashboard.
|
||||
# 3. Touch a sentinel file under ``kanban_home() / '.scratch_tip_shown'``
|
||||
# so we don't repeat the tip — once you know, you know.
|
||||
#
|
||||
# Scope is per-install, not per-board: a user creating a second board
|
||||
# already learned the lesson on board #1.
|
||||
|
||||
_SCRATCH_TIP_SENTINEL_NAME = ".scratch_tip_shown"
|
||||
|
||||
_SCRATCH_TIP_MESSAGE = (
|
||||
"scratch workspaces are ephemeral — they're deleted when the task "
|
||||
"completes. Use --workspace worktree: (git worktree) or "
|
||||
"--workspace dir:/abs/path (existing dir) to preserve worker output."
|
||||
)
|
||||
|
||||
|
||||
def _scratch_tip_sentinel_path() -> Path:
|
||||
"""Path to the per-install scratch-workspace-tip sentinel file."""
|
||||
return kanban_home() / _SCRATCH_TIP_SENTINEL_NAME
|
||||
|
||||
|
||||
def _scratch_tip_shown() -> bool:
|
||||
"""True iff the scratch-workspace tip has already been emitted on this
|
||||
install. Best-effort — any error means we re-emit, which is the safer
|
||||
failure mode for a help message."""
|
||||
try:
|
||||
return _scratch_tip_sentinel_path().exists()
|
||||
except OSError:
|
||||
return False
|
||||
|
||||
|
||||
def _mark_scratch_tip_shown() -> None:
|
||||
"""Touch the sentinel so future scratch workspaces stay silent.
|
||||
|
||||
Best-effort: a failure here just means the tip might appear once more,
|
||||
which is preferable to crashing dispatch over a help message.
|
||||
"""
|
||||
try:
|
||||
path = _scratch_tip_sentinel_path()
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
path.touch(exist_ok=True)
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
|
||||
def _maybe_emit_scratch_tip(
|
||||
conn: sqlite3.Connection,
|
||||
task_id: str,
|
||||
workspace_kind: Optional[str],
|
||||
) -> None:
|
||||
"""Emit the first-use scratch-workspace tip exactly once per install.
|
||||
|
||||
Called from the dispatcher right after a scratch workspace is
|
||||
materialized. No-op for ``worktree`` / ``dir`` workspaces (they're
|
||||
preserved by design) and no-op after the sentinel exists.
|
||||
"""
|
||||
if (workspace_kind or "scratch") != "scratch":
|
||||
return
|
||||
if _scratch_tip_shown():
|
||||
return
|
||||
try:
|
||||
_log.warning("kanban: %s (task %s)", _SCRATCH_TIP_MESSAGE, task_id)
|
||||
with write_txn(conn):
|
||||
_append_event(
|
||||
conn, task_id, "tip_scratch_workspace",
|
||||
{"message": _SCRATCH_TIP_MESSAGE},
|
||||
)
|
||||
except Exception:
|
||||
# Best-effort — never block the spawn loop over a help message.
|
||||
pass
|
||||
finally:
|
||||
_mark_scratch_tip_shown()
|
||||
|
||||
|
||||
def edit_completed_task_result(
|
||||
conn: sqlite3.Connection,
|
||||
task_id: str,
|
||||
@@ -3398,77 +3083,6 @@ def block_task(
|
||||
return True
|
||||
|
||||
|
||||
|
||||
def promote_task(
|
||||
conn: sqlite3.Connection,
|
||||
task_id: str,
|
||||
*,
|
||||
actor: str,
|
||||
reason: Optional[str] = None,
|
||||
force: bool = False,
|
||||
dry_run: bool = False,
|
||||
) -> tuple[bool, Optional[str]]:
|
||||
"""Manually promote a `todo` or `blocked` task to `ready`.
|
||||
|
||||
Mirrors the automatic promotion done by ``recompute_ready`` but
|
||||
drives it from a deliberate operator action with an audit-trail
|
||||
entry. Refuses to promote if any parent dep is not in a terminal
|
||||
state (`done`/`archived`) unless ``force=True``. Does NOT change
|
||||
assignee or claim state. Returns ``(True, None)`` on success and
|
||||
``(False, reason)`` if refused. ``dry_run=True`` validates the
|
||||
promotion would succeed without mutating state.
|
||||
"""
|
||||
row = conn.execute(
|
||||
"SELECT status FROM tasks WHERE id = ?", (task_id,)
|
||||
).fetchone()
|
||||
if row is None:
|
||||
return False, f"task {task_id} not found"
|
||||
|
||||
cur_status = row["status"]
|
||||
if cur_status not in ("todo", "blocked"):
|
||||
return False, (
|
||||
f"task {task_id} is {cur_status!r}; promote only applies to "
|
||||
f"'todo' or 'blocked'"
|
||||
)
|
||||
|
||||
if not force:
|
||||
parents = conn.execute(
|
||||
"SELECT t.id, t.status FROM tasks t "
|
||||
"JOIN task_links l ON l.parent_id = t.id "
|
||||
"WHERE l.child_id = ?",
|
||||
(task_id,),
|
||||
).fetchall()
|
||||
unsatisfied = [
|
||||
p["id"] for p in parents
|
||||
if p["status"] not in ("done", "archived")
|
||||
]
|
||||
if unsatisfied:
|
||||
return False, (
|
||||
f"unsatisfied parent dependencies: "
|
||||
f"{', '.join(unsatisfied)} (use --force to override)"
|
||||
)
|
||||
|
||||
if dry_run:
|
||||
return True, None
|
||||
|
||||
with write_txn(conn):
|
||||
upd = conn.execute(
|
||||
"UPDATE tasks SET status = 'ready' "
|
||||
"WHERE id = ? AND status IN ('todo', 'blocked')",
|
||||
(task_id,),
|
||||
)
|
||||
if upd.rowcount != 1:
|
||||
return False, f"task {task_id} status changed during promotion"
|
||||
_append_event(
|
||||
conn,
|
||||
task_id,
|
||||
"promoted_manual",
|
||||
{"actor": actor, "reason": reason, "forced": force},
|
||||
)
|
||||
|
||||
return True, None
|
||||
|
||||
|
||||
def unblock_task(conn: sqlite3.Connection, task_id: str) -> bool:
|
||||
"""Transition ``blocked``/``scheduled`` -> ready or todo.
|
||||
|
||||
@@ -5278,7 +4892,6 @@ def dispatch_once(
|
||||
continue
|
||||
# Persist the resolved workspace path so the worker can cd there.
|
||||
set_workspace_path(conn, claimed.id, str(workspace))
|
||||
_maybe_emit_scratch_tip(conn, claimed.id, claimed.workspace_kind)
|
||||
_spawn = spawn_fn if spawn_fn is not None else _default_spawn
|
||||
try:
|
||||
# Back-compat: older spawn_fn signatures accept only
|
||||
@@ -5357,7 +4970,6 @@ def dispatch_once(
|
||||
continue
|
||||
# Persist the resolved workspace path so the worker can cd there.
|
||||
set_workspace_path(conn, claimed.id, str(workspace))
|
||||
_maybe_emit_scratch_tip(conn, claimed.id, claimed.workspace_kind)
|
||||
# Force-load sdlc-review skill for review agents. The
|
||||
# _default_spawn function already auto-loads kanban-worker, and
|
||||
# appends task.skills via --skills. Setting task.skills here
|
||||
|
||||
+19
-135
@@ -1454,7 +1454,7 @@ def _launch_tui(
|
||||
provider: Optional[str] = None,
|
||||
toolsets: object = None,
|
||||
skills: object = None,
|
||||
verbose: Optional[bool] = None,
|
||||
verbose: bool = False,
|
||||
quiet: bool = False,
|
||||
query: Optional[str] = None,
|
||||
image: Optional[str] = None,
|
||||
@@ -1763,7 +1763,7 @@ def cmd_chat(args):
|
||||
provider=getattr(args, "provider", None),
|
||||
toolsets=getattr(args, "toolsets", None),
|
||||
skills=getattr(args, "skills", None),
|
||||
verbose=getattr(args, "verbose", None),
|
||||
verbose=getattr(args, "verbose", False),
|
||||
quiet=getattr(args, "quiet", False),
|
||||
query=getattr(args, "query", None),
|
||||
image=getattr(args, "image", None),
|
||||
@@ -1783,7 +1783,7 @@ def cmd_chat(args):
|
||||
"provider": getattr(args, "provider", None),
|
||||
"toolsets": args.toolsets,
|
||||
"skills": getattr(args, "skills", None),
|
||||
"verbose": getattr(args, "verbose", None),
|
||||
"verbose": args.verbose,
|
||||
"quiet": getattr(args, "quiet", False),
|
||||
"query": args.query,
|
||||
"image": getattr(args, "image", None),
|
||||
@@ -2505,27 +2505,6 @@ _AUX_TASKS: list[tuple[str, str, str]] = [
|
||||
]
|
||||
|
||||
|
||||
def _all_aux_tasks() -> list[tuple[str, str, str]]:
|
||||
"""Return built-in + plugin-registered auxiliary tasks for picker/menu use.
|
||||
|
||||
Built-in tasks come first (preserving order), followed by plugin tasks
|
||||
sorted by key. Used by ``_aux_config_menu``, ``_reset_aux_to_auto``, and
|
||||
display-name lookups so plugin-registered tasks (registered via
|
||||
:meth:`hermes_cli.plugins.PluginContext.register_auxiliary_task`) appear
|
||||
in the same surfaces as built-in ones without core knowing about them.
|
||||
"""
|
||||
tasks = list(_AUX_TASKS)
|
||||
try:
|
||||
from hermes_cli.plugins import get_plugin_auxiliary_tasks
|
||||
for entry in get_plugin_auxiliary_tasks():
|
||||
tasks.append((entry["key"], entry["display_name"], entry["description"]))
|
||||
except Exception:
|
||||
# Plugin discovery failure must not break the aux config UI.
|
||||
# Built-in tasks remain available.
|
||||
pass
|
||||
return tasks
|
||||
|
||||
|
||||
def _format_aux_current(task_cfg: dict) -> str:
|
||||
"""Render the current aux config for display in the task menu."""
|
||||
if not isinstance(task_cfg, dict):
|
||||
@@ -2576,11 +2555,7 @@ def _save_aux_choice(
|
||||
|
||||
|
||||
def _reset_aux_to_auto() -> int:
|
||||
"""Reset every known aux task back to auto/empty. Returns number reset.
|
||||
|
||||
Includes plugin-registered tasks (via ``_all_aux_tasks``) so a plugin
|
||||
that contributed an auxiliary task gets reset alongside built-ins.
|
||||
"""
|
||||
"""Reset every known aux task back to auto/empty. Returns number reset."""
|
||||
from hermes_cli.config import load_config, save_config
|
||||
|
||||
cfg = load_config()
|
||||
@@ -2589,7 +2564,7 @@ def _reset_aux_to_auto() -> int:
|
||||
aux = {}
|
||||
cfg["auxiliary"] = aux
|
||||
count = 0
|
||||
for task, _name, _desc in _all_aux_tasks():
|
||||
for task, _name, _desc in _AUX_TASKS:
|
||||
entry = aux.setdefault(task, {})
|
||||
if not isinstance(entry, dict):
|
||||
entry = {}
|
||||
@@ -2632,11 +2607,10 @@ def _aux_config_menu() -> None:
|
||||
print()
|
||||
|
||||
# Build the task menu with current settings inline
|
||||
all_tasks = _all_aux_tasks()
|
||||
name_col = max(len(name) for _, name, _ in all_tasks) + 2
|
||||
desc_col = max(len(desc) for _, _, desc in all_tasks) + 4
|
||||
name_col = max(len(name) for _, name, _ in _AUX_TASKS) + 2
|
||||
desc_col = max(len(desc) for _, _, desc in _AUX_TASKS) + 4
|
||||
entries: list[tuple[str, str]] = []
|
||||
for task_key, name, desc in all_tasks:
|
||||
for task_key, name, desc in _AUX_TASKS:
|
||||
task_cfg = (
|
||||
aux.get(task_key, {}) if isinstance(aux.get(task_key), dict) else {}
|
||||
)
|
||||
@@ -2687,7 +2661,7 @@ def _aux_select_for_task(task: str) -> None:
|
||||
current_model = str(task_cfg.get("model") or "").strip()
|
||||
current_base_url = str(task_cfg.get("base_url") or "").strip()
|
||||
|
||||
display_name = next((name for key, name, _ in _all_aux_tasks() if key == task), task)
|
||||
display_name = next((name for key, name, _ in _AUX_TASKS if key == task), task)
|
||||
|
||||
# Gather authenticated providers (has credentials + curated model list)
|
||||
try:
|
||||
@@ -2758,7 +2732,7 @@ def _aux_flow_provider_model(
|
||||
from hermes_cli.auth import _prompt_model_selection
|
||||
from hermes_cli.models import get_pricing_for_provider
|
||||
|
||||
display_name = next((name for key, name, _ in _all_aux_tasks() if key == task), task)
|
||||
display_name = next((name for key, name, _ in _AUX_TASKS if key == task), task)
|
||||
|
||||
# Fetch live pricing for this provider (non-blocking)
|
||||
pricing: dict = {}
|
||||
@@ -2804,7 +2778,7 @@ def _aux_flow_custom_endpoint(task: str, task_cfg: dict) -> None:
|
||||
"""Prompt for a direct OpenAI-compatible base_url + optional api_key/model."""
|
||||
import getpass
|
||||
|
||||
display_name = next((name for key, name, _ in _all_aux_tasks() if key == task), task)
|
||||
display_name = next((name for key, name, _ in _AUX_TASKS if key == task), task)
|
||||
current_base_url = str(task_cfg.get("base_url") or "").strip()
|
||||
current_model = str(task_cfg.get("model") or "").strip()
|
||||
|
||||
@@ -6123,13 +6097,6 @@ def cmd_webhook(args):
|
||||
webhook_command(args)
|
||||
|
||||
|
||||
def cmd_portal(args):
|
||||
"""Nous Portal status and Tool Gateway routing surface."""
|
||||
from hermes_cli.portal_cli import portal_command
|
||||
|
||||
return portal_command(args)
|
||||
|
||||
|
||||
def cmd_slack(args):
|
||||
"""Slack integration helpers.
|
||||
|
||||
@@ -6182,19 +6149,6 @@ def cmd_doctor(args):
|
||||
run_doctor(args)
|
||||
|
||||
|
||||
def cmd_security(args):
|
||||
"""Dispatch `hermes security <subcmd>`."""
|
||||
sub = getattr(args, "security_command", None)
|
||||
if sub in ("audit", None):
|
||||
from hermes_cli.security_audit import cmd_security_audit
|
||||
|
||||
# Default subcommand is `audit` when no subcmd is given.
|
||||
code = cmd_security_audit(args)
|
||||
sys.exit(int(code or 0))
|
||||
print(f"unknown security subcommand: {sub}", file=sys.stderr)
|
||||
sys.exit(2)
|
||||
|
||||
|
||||
def cmd_dump(args):
|
||||
"""Dump setup summary for support/debugging."""
|
||||
from hermes_cli.dump import run_dump
|
||||
@@ -6971,8 +6925,8 @@ def _update_via_zip(args):
|
||||
)
|
||||
|
||||
print("→ Downloading latest version...")
|
||||
tmp_dir = tempfile.mkdtemp(prefix="hermes-update-")
|
||||
try:
|
||||
tmp_dir = tempfile.mkdtemp(prefix="hermes-update-")
|
||||
zip_path = os.path.join(tmp_dir, f"hermes-agent-{branch}.zip")
|
||||
urlretrieve(zip_url, zip_path)
|
||||
|
||||
@@ -7019,11 +6973,12 @@ def _update_via_zip(args):
|
||||
|
||||
print(f"✓ Updated {update_count} items from ZIP")
|
||||
|
||||
# Cleanup
|
||||
shutil.rmtree(tmp_dir, ignore_errors=True)
|
||||
|
||||
except Exception as e:
|
||||
print(f"✗ ZIP update failed: {e}")
|
||||
sys.exit(1)
|
||||
finally:
|
||||
shutil.rmtree(tmp_dir, ignore_errors=True)
|
||||
|
||||
# Clear stale bytecode after ZIP extraction
|
||||
removed = _clear_bytecode_cache(PROJECT_ROOT)
|
||||
@@ -9855,7 +9810,6 @@ def _coalesce_session_name_args(argv: list) -> list:
|
||||
"honcho",
|
||||
"claw",
|
||||
"plugins",
|
||||
"security",
|
||||
"acp",
|
||||
"webhook",
|
||||
"memory",
|
||||
@@ -10693,10 +10647,10 @@ _BUILTIN_SUBCOMMANDS = frozenset(
|
||||
"config", "cron", "curator", "dashboard", "debug", "doctor",
|
||||
"dump", "fallback", "gateway", "hooks", "import", "insights",
|
||||
"kanban", "login", "logout", "logs", "lsp", "mcp", "memory", "migrate",
|
||||
"model", "pairing", "plugins", "portal", "postinstall", "profile", "proxy",
|
||||
"model", "pairing", "plugins", "postinstall", "profile", "proxy",
|
||||
"send", "sessions", "setup",
|
||||
"skills", "slack", "status", "tools", "uninstall", "update",
|
||||
"version", "webhook", "whatsapp", "chat", "secrets", "security",
|
||||
"version", "webhook", "whatsapp", "chat", "secrets",
|
||||
# Help-ish invocations — plugin commands not being listed in
|
||||
# top-level --help is an acceptable trade-off for skipping an
|
||||
# expensive eager import of every bundled plugin module.
|
||||
@@ -11430,13 +11384,6 @@ def main():
|
||||
help="On existing installs: only prompt for items that are missing "
|
||||
"or unset, instead of running the full reconfigure wizard.",
|
||||
)
|
||||
setup_parser.add_argument(
|
||||
"--portal",
|
||||
action="store_true",
|
||||
help="One-shot Nous Portal setup: log in via OAuth, set Nous as the "
|
||||
"inference provider, and opt into the Tool Gateway. Skips the "
|
||||
"rest of the wizard.",
|
||||
)
|
||||
setup_parser.set_defaults(func=cmd_setup)
|
||||
|
||||
# =========================================================================
|
||||
@@ -11912,12 +11859,6 @@ def main():
|
||||
|
||||
webhook_parser.set_defaults(func=cmd_webhook)
|
||||
|
||||
# =========================================================================
|
||||
# portal command — Nous Portal status + Tool Gateway routing
|
||||
# =========================================================================
|
||||
from hermes_cli.portal_cli import add_parser as _add_portal_parser
|
||||
_add_portal_parser(subparsers)
|
||||
|
||||
# =========================================================================
|
||||
# kanban command — multi-profile collaboration board
|
||||
# =========================================================================
|
||||
@@ -12016,58 +11957,6 @@ def main():
|
||||
)
|
||||
doctor_parser.set_defaults(func=cmd_doctor)
|
||||
|
||||
# =========================================================================
|
||||
# security command — on-demand supply-chain audit
|
||||
# =========================================================================
|
||||
security_parser = subparsers.add_parser(
|
||||
"security",
|
||||
help="Supply-chain audit (OSV.dev) for venv, plugins, and MCP servers",
|
||||
description=(
|
||||
"On-demand vulnerability scan against OSV.dev. Covers the Hermes "
|
||||
"venv (installed PyPI dists), Python deps declared by plugins under "
|
||||
"~/.hermes/plugins/, and pinned npx/uvx MCP servers in config.yaml. "
|
||||
"Does NOT scan globally-installed packages or editor/browser extensions."
|
||||
),
|
||||
)
|
||||
security_subparsers = security_parser.add_subparsers(
|
||||
dest="security_command",
|
||||
metavar="<subcommand>",
|
||||
)
|
||||
|
||||
audit_parser = security_subparsers.add_parser(
|
||||
"audit",
|
||||
help="Run a one-shot supply-chain audit",
|
||||
description="Query OSV.dev for known vulnerabilities in installed components.",
|
||||
)
|
||||
audit_parser.add_argument(
|
||||
"--json",
|
||||
action="store_true",
|
||||
help="Emit machine-readable JSON instead of human-readable text",
|
||||
)
|
||||
audit_parser.add_argument(
|
||||
"--fail-on",
|
||||
default="critical",
|
||||
choices=["low", "moderate", "high", "critical"],
|
||||
help="Exit non-zero when any finding meets this severity (default: critical)",
|
||||
)
|
||||
audit_parser.add_argument(
|
||||
"--skip-venv",
|
||||
action="store_true",
|
||||
help="Skip scanning the Hermes Python venv",
|
||||
)
|
||||
audit_parser.add_argument(
|
||||
"--skip-plugins",
|
||||
action="store_true",
|
||||
help="Skip scanning plugin requirements files",
|
||||
)
|
||||
audit_parser.add_argument(
|
||||
"--skip-mcp",
|
||||
action="store_true",
|
||||
help="Skip scanning pinned MCP servers in config.yaml",
|
||||
)
|
||||
audit_parser.set_defaults(func=cmd_security)
|
||||
security_parser.set_defaults(func=cmd_security)
|
||||
|
||||
# =========================================================================
|
||||
# dump command
|
||||
# =========================================================================
|
||||
@@ -12393,11 +12282,6 @@ Examples:
|
||||
skills_audit.add_argument(
|
||||
"name", nargs="?", help="Specific skill to audit (default: all)"
|
||||
)
|
||||
skills_audit.add_argument(
|
||||
"--deep",
|
||||
action="store_true",
|
||||
help="Run AST-level analysis on Python files (opt-in diagnostic)",
|
||||
)
|
||||
|
||||
skills_uninstall = skills_subparsers.add_parser(
|
||||
"uninstall", help="Remove a hub-installed skill"
|
||||
@@ -13877,7 +13761,7 @@ Examples:
|
||||
("model", None),
|
||||
("provider", None),
|
||||
("toolsets", None),
|
||||
("verbose", None),
|
||||
("verbose", False),
|
||||
("worktree", False),
|
||||
]:
|
||||
if not hasattr(args, attr):
|
||||
@@ -13892,7 +13776,7 @@ Examples:
|
||||
("model", None),
|
||||
("provider", None),
|
||||
("toolsets", None),
|
||||
("verbose", None),
|
||||
("verbose", False),
|
||||
("resume", None),
|
||||
("continue_last", None),
|
||||
("worktree", False),
|
||||
|
||||
+12
-7
@@ -17,6 +17,7 @@ Model / provider selection mirrors `hermes chat`:
|
||||
|
||||
Env var fallbacks (used when the corresponding arg is not passed):
|
||||
- HERMES_INFERENCE_MODEL
|
||||
- HERMES_INFERENCE_PROVIDER (already read by resolve_runtime_provider)
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -27,8 +28,6 @@ import sys
|
||||
from contextlib import redirect_stderr, redirect_stdout
|
||||
from typing import Optional
|
||||
|
||||
from hermes_cli.fallback_config import get_fallback_chain
|
||||
|
||||
|
||||
def _normalize_toolsets(toolsets: object = None) -> list[str] | None:
|
||||
if not toolsets:
|
||||
@@ -134,8 +133,9 @@ def run_oneshot(
|
||||
prompt: The user message to send.
|
||||
model: Optional model override. Falls back to HERMES_INFERENCE_MODEL
|
||||
env var, then config.yaml's model.default / model.model.
|
||||
provider: Optional provider override. Falls back to config.yaml's
|
||||
model.provider, then "auto".
|
||||
provider: Optional provider override. Falls back to
|
||||
HERMES_INFERENCE_PROVIDER env var, then config.yaml's model.provider,
|
||||
then "auto".
|
||||
toolsets: Optional comma-separated string or iterable of toolsets.
|
||||
|
||||
Returns the exit code. Caller should sys.exit() with the return.
|
||||
@@ -301,9 +301,14 @@ def _run_agent(
|
||||
toolsets_list = sorted(_get_platform_tools(cfg, "cli"))
|
||||
|
||||
session_db = _create_session_db_for_oneshot()
|
||||
# Read the effective fallback chain from profile config so oneshot workers
|
||||
# honour the same merge semantics as interactive CLI and gateway sessions.
|
||||
_fb = get_fallback_chain(cfg)
|
||||
# Read fallback chain from profile config — supports both the new list
|
||||
# format (fallback_providers) and the legacy single-dict (fallback_model).
|
||||
# Mirrors the same normalization in cli.py so oneshot workers (e.g. kanban
|
||||
# workers spawned via `hermes -p <profile> chat -q ...`) honour the
|
||||
# profile's fallback chain just like interactive sessions do.
|
||||
_fb = cfg.get("fallback_providers") or cfg.get("fallback_model") or []
|
||||
if isinstance(_fb, dict):
|
||||
_fb = [_fb] if _fb.get("provider") and _fb.get("model") else []
|
||||
|
||||
agent = AIAgent(
|
||||
api_key=runtime.get("api_key"),
|
||||
|
||||
@@ -698,119 +698,6 @@ class PluginContext:
|
||||
|
||||
# -- hook registration --------------------------------------------------
|
||||
|
||||
# -- auxiliary task registration ---------------------------------------
|
||||
|
||||
def register_auxiliary_task(
|
||||
self,
|
||||
key: str,
|
||||
*,
|
||||
display_name: str,
|
||||
description: str,
|
||||
defaults: Optional[Dict[str, Any]] = None,
|
||||
) -> None:
|
||||
"""Register a plugin-defined auxiliary LLM task.
|
||||
|
||||
Auxiliary tasks are LLM-backed side jobs (vision analysis, web extraction,
|
||||
compression, smart-approval, etc.) that route through ``auxiliary_client.py``.
|
||||
Each task has its own ``auxiliary.<key>`` config block where users can
|
||||
pin a provider/model independent of the main chat model.
|
||||
|
||||
Plugins use this to declare their own auxiliary tasks without touching
|
||||
core files. After registration, the task:
|
||||
|
||||
- Appears in the ``hermes model → Configure auxiliary models`` picker
|
||||
- Has its provider/model/base_url/api_key bridged from config.yaml to
|
||||
``AUXILIARY_<KEY_UPPER>_*`` env vars at gateway startup
|
||||
- Gets default routing fields (provider="auto", model="", etc.) merged
|
||||
into loaded configs so ``cfg.get("auxiliary", {}).get(key)`` works
|
||||
|
||||
Args:
|
||||
key: stable task key (snake_case). Used in config ``auxiliary.<key>``
|
||||
and env vars ``AUXILIARY_<KEY_UPPER>_*``. Must not shadow a
|
||||
built-in task key (vision, compression, web_extract, approval,
|
||||
mcp, title_generation, skills_hub, curator).
|
||||
display_name: human-readable name shown in the picker.
|
||||
description: short one-line description shown next to the name.
|
||||
defaults: optional dict of default routing fields. Recognized keys:
|
||||
``provider`` (default "auto"), ``model`` (default ""),
|
||||
``base_url`` (default ""), ``api_key`` (default ""),
|
||||
``timeout`` (default 60), ``extra_body`` (default {}),
|
||||
plus any task-specific extras (e.g. ``download_timeout``).
|
||||
Unknown keys are preserved verbatim — the plugin owns the
|
||||
schema for its own task.
|
||||
|
||||
Raises:
|
||||
ValueError: if *key* is empty, contains invalid characters, or
|
||||
shadows a built-in auxiliary task key.
|
||||
|
||||
Example:
|
||||
ctx.register_auxiliary_task(
|
||||
key="memory_retain_filter",
|
||||
display_name="Memory retain filter",
|
||||
description="hindsight pre-retain dedup/extract",
|
||||
defaults={"provider": "auto", "timeout": 30},
|
||||
)
|
||||
"""
|
||||
# Validate key shape
|
||||
if not key or not isinstance(key, str):
|
||||
raise ValueError(
|
||||
f"Plugin '{self.manifest.name}' tried to register auxiliary task "
|
||||
f"with invalid key {key!r}"
|
||||
)
|
||||
if not all(c.isalnum() or c == "_" for c in key):
|
||||
raise ValueError(
|
||||
f"Plugin '{self.manifest.name}' auxiliary task key {key!r} "
|
||||
f"must contain only alphanumeric characters and underscores"
|
||||
)
|
||||
|
||||
# Lazy import to avoid circular: hermes_cli.main imports plugins indirectly
|
||||
from hermes_cli.main import _AUX_TASKS as _BUILTIN_AUX_TASKS
|
||||
|
||||
builtin_keys = {k for k, _name, _desc in _BUILTIN_AUX_TASKS}
|
||||
if key in builtin_keys:
|
||||
raise ValueError(
|
||||
f"Plugin '{self.manifest.name}' cannot register auxiliary task "
|
||||
f"{key!r} — that key is reserved for a built-in task. "
|
||||
f"Pick a plugin-namespaced key (e.g. '{self.manifest.name}_{key}')."
|
||||
)
|
||||
|
||||
# Reject duplicate registrations across plugins
|
||||
existing = self._manager._aux_tasks.get(key)
|
||||
if existing is not None and existing.get("plugin") != self.manifest.name:
|
||||
raise ValueError(
|
||||
f"Plugin '{self.manifest.name}' cannot register auxiliary task "
|
||||
f"{key!r} — already registered by plugin "
|
||||
f"'{existing.get('plugin')}'"
|
||||
)
|
||||
|
||||
# Normalize defaults — plugin owns the schema, but we ensure routing
|
||||
# fields exist with sensible types so consumers don't crash.
|
||||
merged_defaults: Dict[str, Any] = {
|
||||
"provider": "auto",
|
||||
"model": "",
|
||||
"base_url": "",
|
||||
"api_key": "",
|
||||
"timeout": 60,
|
||||
"extra_body": {},
|
||||
}
|
||||
if defaults:
|
||||
for k, v in defaults.items():
|
||||
merged_defaults[k] = v
|
||||
|
||||
self._manager._aux_tasks[key] = {
|
||||
"key": key,
|
||||
"display_name": display_name,
|
||||
"description": description,
|
||||
"defaults": merged_defaults,
|
||||
"plugin": self.manifest.name,
|
||||
}
|
||||
logger.debug(
|
||||
"Plugin %s registered auxiliary task: %s (%s)",
|
||||
self.manifest.name,
|
||||
key,
|
||||
display_name,
|
||||
)
|
||||
|
||||
def register_hook(self, hook_name: str, callback: Callable) -> None:
|
||||
"""Register a lifecycle hook callback.
|
||||
|
||||
@@ -895,9 +782,6 @@ class PluginManager:
|
||||
self._cli_ref = None # Set by CLI after plugin discovery
|
||||
# Plugin skill registry: qualified name → metadata dict.
|
||||
self._plugin_skills: Dict[str, Dict[str, Any]] = {}
|
||||
# Plugin-registered auxiliary tasks: key → {key, display_name,
|
||||
# description, defaults, plugin}. See PluginContext.register_auxiliary_task.
|
||||
self._aux_tasks: Dict[str, Dict[str, Any]] = {}
|
||||
|
||||
# -----------------------------------------------------------------------
|
||||
# Public
|
||||
@@ -919,7 +803,6 @@ class PluginManager:
|
||||
self._cli_commands.clear()
|
||||
self._plugin_commands.clear()
|
||||
self._plugin_skills.clear()
|
||||
self._aux_tasks.clear()
|
||||
self._context_engine = None
|
||||
self._discovered = True
|
||||
|
||||
@@ -1665,21 +1548,6 @@ def get_plugin_commands() -> Dict[str, dict]:
|
||||
return _ensure_plugins_discovered()._plugin_commands
|
||||
|
||||
|
||||
def get_plugin_auxiliary_tasks() -> List[Dict[str, Any]]:
|
||||
"""Return all plugin-registered auxiliary tasks as a stable-ordered list.
|
||||
|
||||
Each entry is the registration dict from
|
||||
:meth:`PluginContext.register_auxiliary_task`:
|
||||
``{key, display_name, description, defaults, plugin}``.
|
||||
|
||||
Triggers idempotent plugin discovery so callers can read the registry
|
||||
before any explicit ``discover_plugins()`` call. Sorted by ``key`` for
|
||||
deterministic ordering in pickers and tests.
|
||||
"""
|
||||
manager = _ensure_plugins_discovered()
|
||||
return [manager._aux_tasks[k] for k in sorted(manager._aux_tasks)]
|
||||
|
||||
|
||||
def get_plugin_toolsets() -> List[tuple]:
|
||||
"""Return plugin toolsets as ``(key, label, description)`` tuples.
|
||||
|
||||
|
||||
@@ -1,219 +0,0 @@
|
||||
"""``hermes portal`` — small CLI surface for Nous Portal users.
|
||||
|
||||
Subcommands:
|
||||
status Show Portal auth state + which Tool Gateway tools are routed.
|
||||
open Open the Portal subscription page in the user's default browser.
|
||||
tools List Tool Gateway tools and which are active in the current config.
|
||||
|
||||
This command is intentionally minimal — it does not duplicate functionality
|
||||
already in ``hermes auth`` or ``hermes tools``. It's a discovery + status
|
||||
surface for the Portal subscription itself.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import sys
|
||||
import webbrowser
|
||||
from typing import Optional
|
||||
|
||||
from hermes_cli.colors import Colors, color
|
||||
from hermes_cli.config import load_config
|
||||
|
||||
DEFAULT_PORTAL_URL = "https://portal.nousresearch.com"
|
||||
SUBSCRIPTION_URL = "https://portal.nousresearch.com/manage-subscription"
|
||||
DOCS_URL = "https://hermes-agent.nousresearch.com/docs/user-guide/features/tool-gateway"
|
||||
|
||||
|
||||
def _nous_portal_base_url() -> str:
|
||||
"""Resolve the Portal base URL from auth state or default."""
|
||||
try:
|
||||
from hermes_cli.auth import get_nous_auth_status
|
||||
status = get_nous_auth_status() or {}
|
||||
url = status.get("portal_base_url")
|
||||
if isinstance(url, str) and url.strip():
|
||||
return url.rstrip("/")
|
||||
except Exception:
|
||||
pass
|
||||
return DEFAULT_PORTAL_URL
|
||||
|
||||
|
||||
def _cmd_status(args) -> int:
|
||||
"""Show Portal auth + Tool Gateway routing summary."""
|
||||
from hermes_cli.auth import get_nous_auth_status
|
||||
from hermes_cli.nous_subscription import get_nous_subscription_features
|
||||
|
||||
config = load_config() or {}
|
||||
|
||||
try:
|
||||
auth = get_nous_auth_status() or {}
|
||||
except Exception:
|
||||
auth = {}
|
||||
|
||||
logged_in = bool(auth.get("logged_in"))
|
||||
|
||||
print()
|
||||
print(color(" Nous Portal", Colors.MAGENTA))
|
||||
print(color(" ───────────", Colors.MAGENTA))
|
||||
if logged_in:
|
||||
portal = auth.get("portal_base_url") or DEFAULT_PORTAL_URL
|
||||
print(f" Auth: {color('✓ logged in', Colors.GREEN)}")
|
||||
print(f" Portal: {portal}")
|
||||
inference = auth.get("inference_base_url")
|
||||
if inference:
|
||||
print(f" API: {inference}")
|
||||
else:
|
||||
print(f" Auth: {color('not logged in', Colors.YELLOW)}")
|
||||
print(f" Sign up: {SUBSCRIPTION_URL}")
|
||||
print(f" Login: hermes auth add nous --type oauth")
|
||||
|
||||
# Provider selection (independent of auth)
|
||||
model_cfg = config.get("model") if isinstance(config.get("model"), dict) else {}
|
||||
provider = str(model_cfg.get("provider") or "").strip().lower()
|
||||
if provider == "nous":
|
||||
print(f" Model: {color('✓ using Nous as inference provider', Colors.GREEN)}")
|
||||
elif provider:
|
||||
print(f" Model: currently {provider} (switch with `hermes model`)")
|
||||
|
||||
# Tool Gateway routing
|
||||
print()
|
||||
print(color(" Tool Gateway", Colors.MAGENTA))
|
||||
print(color(" ────────────", Colors.MAGENTA))
|
||||
try:
|
||||
features = get_nous_subscription_features(config)
|
||||
except Exception:
|
||||
features = None
|
||||
|
||||
if features is None:
|
||||
print(" (could not resolve subscription state)")
|
||||
return 0
|
||||
|
||||
rows = []
|
||||
for feat in features.items():
|
||||
if feat.managed_by_nous:
|
||||
state = color("via Nous Portal", Colors.GREEN)
|
||||
elif feat.active and feat.current_provider:
|
||||
state = feat.current_provider
|
||||
elif feat.active:
|
||||
state = "active"
|
||||
else:
|
||||
state = color("not configured", Colors.DIM)
|
||||
rows.append((feat.label, state))
|
||||
|
||||
width = max((len(r[0]) for r in rows), default=0)
|
||||
for label, state in rows:
|
||||
print(f" {label:<{width}} {state}")
|
||||
|
||||
if not logged_in:
|
||||
print()
|
||||
print(color(f" Docs: {DOCS_URL}", Colors.DIM))
|
||||
return 0
|
||||
|
||||
|
||||
def _cmd_open(args) -> int:
|
||||
"""Open the Portal subscription page in the default browser."""
|
||||
target = SUBSCRIPTION_URL
|
||||
print(f"Opening {target}")
|
||||
try:
|
||||
opened = webbrowser.open(target)
|
||||
except Exception:
|
||||
opened = False
|
||||
if not opened:
|
||||
print()
|
||||
print("Could not launch a browser. Visit the URL above manually.")
|
||||
return 1
|
||||
return 0
|
||||
|
||||
|
||||
def _cmd_tools(args) -> int:
|
||||
"""List the Tool Gateway catalog + current routing."""
|
||||
from hermes_cli.nous_subscription import get_nous_subscription_features
|
||||
|
||||
config = load_config() or {}
|
||||
try:
|
||||
features = get_nous_subscription_features(config)
|
||||
except Exception:
|
||||
print("Could not resolve Tool Gateway state.", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
# Static catalog — the partners Tool Gateway routes to today.
|
||||
catalog = [
|
||||
("web", "Web search & extract", "Firecrawl"),
|
||||
("image_gen", "Image generation", "FAL"),
|
||||
("tts", "Text-to-speech", "OpenAI TTS"),
|
||||
("browser", "Browser automation", "Browser Use"),
|
||||
("modal", "Cloud terminal", "Modal"),
|
||||
]
|
||||
|
||||
print()
|
||||
print(color(" Tool Gateway catalog", Colors.MAGENTA))
|
||||
print(color(" ────────────────────", Colors.MAGENTA))
|
||||
|
||||
if not features.nous_auth_present:
|
||||
print(color(" Not logged into Nous Portal — sign in with `hermes auth add nous --type oauth`.", Colors.YELLOW))
|
||||
print()
|
||||
|
||||
label_width = max(len(label) for _, label, _ in catalog)
|
||||
for key, label, partner in catalog:
|
||||
feat = features.features.get(key)
|
||||
if feat is None:
|
||||
state = color("unknown", Colors.DIM)
|
||||
elif feat.managed_by_nous:
|
||||
state = color("✓ via Nous Portal", Colors.GREEN)
|
||||
elif feat.active and feat.current_provider:
|
||||
state = feat.current_provider
|
||||
elif feat.active:
|
||||
state = "active"
|
||||
else:
|
||||
state = color("not configured", Colors.DIM)
|
||||
print(f" {label:<{label_width}} partner: {partner:<14} {state}")
|
||||
|
||||
print()
|
||||
print(color(f" Manage your subscription: {SUBSCRIPTION_URL}", Colors.DIM))
|
||||
print(color(f" Docs: {DOCS_URL}", Colors.DIM))
|
||||
return 0
|
||||
|
||||
|
||||
def portal_command(args) -> int:
|
||||
"""Top-level dispatch for `hermes portal <subcommand>`."""
|
||||
sub = getattr(args, "portal_command", None)
|
||||
if sub in {None, ""}:
|
||||
# Default to status — matches gh / kubectl conventions where the
|
||||
# subcommand-less form gives a useful overview.
|
||||
return _cmd_status(args)
|
||||
if sub == "status":
|
||||
return _cmd_status(args)
|
||||
if sub == "open":
|
||||
return _cmd_open(args)
|
||||
if sub == "tools":
|
||||
return _cmd_tools(args)
|
||||
print(f"Unknown portal subcommand: {sub}", file=sys.stderr)
|
||||
print("Run `hermes portal -h` for usage.", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
|
||||
def add_parser(subparsers) -> None:
|
||||
"""Register `hermes portal` on the given argparse subparsers object."""
|
||||
portal_parser = subparsers.add_parser(
|
||||
"portal",
|
||||
help="Nous Portal status, subscription, and Tool Gateway routing",
|
||||
description=(
|
||||
"Inspect Nous Portal auth, Tool Gateway routing, and open the "
|
||||
"Portal subscription page. Subcommands: status (default), "
|
||||
"open, tools."
|
||||
),
|
||||
)
|
||||
portal_sub = portal_parser.add_subparsers(dest="portal_command")
|
||||
|
||||
portal_sub.add_parser(
|
||||
"status",
|
||||
help="Show Portal auth + Tool Gateway routing summary (default)",
|
||||
)
|
||||
portal_sub.add_parser(
|
||||
"open",
|
||||
help="Open the Portal subscription page in your default browser",
|
||||
)
|
||||
portal_sub.add_parser(
|
||||
"tools",
|
||||
help="List Tool Gateway tools and which are routed via Nous",
|
||||
)
|
||||
|
||||
portal_parser.set_defaults(func=portal_command)
|
||||
@@ -777,14 +777,6 @@ def create_profile(
|
||||
except Exception:
|
||||
pass # non-fatal — user can describe later with `hermes profile describe`
|
||||
|
||||
# Phase 4: when running inside a container under s6, register the
|
||||
# new profile's gateway as a runtime s6 service so
|
||||
# `hermes -p <profile> gateway start` can supervise it via
|
||||
# `s6-svc -u` instead of spawning a bare process. On host (systemd
|
||||
# / launchd / windows) this is a no-op — the existing per-profile
|
||||
# unit-generation paths handle gateway lifecycle.
|
||||
_maybe_register_gateway_service(canon)
|
||||
|
||||
return profile_dir
|
||||
|
||||
|
||||
@@ -901,10 +893,6 @@ def delete_profile(name: str, yes: bool = False) -> Path:
|
||||
|
||||
# 1. Disable service (prevents auto-restart)
|
||||
_cleanup_gateway_service(canon, profile_dir)
|
||||
# 1b. Phase 4: unregister the s6 service slot (container path).
|
||||
# On host this is a no-op; on container it removes
|
||||
# /run/service/gateway-<profile>/ so s6-supervise drops it.
|
||||
_maybe_unregister_gateway_service(canon)
|
||||
|
||||
# 2. Stop running gateway
|
||||
if gw_running:
|
||||
@@ -977,61 +965,6 @@ def delete_profile(name: str, yes: bool = False) -> Path:
|
||||
return profile_dir
|
||||
|
||||
|
||||
def _maybe_register_gateway_service(profile_name: str) -> None:
|
||||
"""Register a profile's gateway with s6 inside the container.
|
||||
|
||||
No-op on host (systemd/launchd/windows) — those backends raise
|
||||
``NotImplementedError`` on ``register_profile_gateway`` and the
|
||||
existing per-profile unit-generation paths handle lifecycle.
|
||||
|
||||
Best-effort: any error (no backend detected, s6 not yet ready,
|
||||
etc.) is logged and swallowed so profile creation doesn't fail
|
||||
because the s6 supervision tree is in a weird state. The user
|
||||
can re-register manually later via the gateway start command,
|
||||
which goes through the same dispatch path.
|
||||
|
||||
Port selection is governed by the profile's ``config.yaml``
|
||||
(``[gateway] port = …``) — there is no Python-side allocator
|
||||
(PR #30136 review item I5 retired the SHA-256-derived range
|
||||
[9200, 9800) because it was dead code through the entire stack).
|
||||
"""
|
||||
try:
|
||||
from hermes_cli.service_manager import get_service_manager
|
||||
mgr = get_service_manager()
|
||||
except RuntimeError:
|
||||
return # no backend on this host — nothing to do
|
||||
if not mgr.supports_runtime_registration():
|
||||
return # host backend; no-op
|
||||
try:
|
||||
mgr.register_profile_gateway(profile_name)
|
||||
except ValueError:
|
||||
# Already registered (e.g. the container-boot reconciler ran
|
||||
# first and brought up a stale slot). That's fine.
|
||||
pass
|
||||
except Exception as exc:
|
||||
# Don't fail profile create over a supervision-tree hiccup.
|
||||
print(f"⚠ Could not register s6 gateway service: {exc}")
|
||||
|
||||
|
||||
def _maybe_unregister_gateway_service(profile_name: str) -> None:
|
||||
"""Tear down a profile's s6 gateway service inside the container.
|
||||
|
||||
No-op on host. Idempotent: absent services are silently skipped
|
||||
by ``unregister_profile_gateway``.
|
||||
"""
|
||||
try:
|
||||
from hermes_cli.service_manager import get_service_manager
|
||||
mgr = get_service_manager()
|
||||
except RuntimeError:
|
||||
return
|
||||
if not mgr.supports_runtime_registration():
|
||||
return
|
||||
try:
|
||||
mgr.unregister_profile_gateway(profile_name)
|
||||
except Exception as exc:
|
||||
print(f"⚠ Could not unregister s6 gateway service: {exc}")
|
||||
|
||||
|
||||
def _cleanup_gateway_service(name: str, profile_dir: Path) -> None:
|
||||
"""Disable and remove systemd/launchd service for a profile."""
|
||||
import platform as _platform
|
||||
|
||||
+5
-137
@@ -57,15 +57,6 @@ def register_cli(parent_parser: argparse.ArgumentParser) -> None:
|
||||
"--access-token",
|
||||
help="Provide the access token non-interactively (will be stored in .env)",
|
||||
)
|
||||
setup.add_argument(
|
||||
"--server-url",
|
||||
help=(
|
||||
"Bitwarden region / self-hosted endpoint. Examples: "
|
||||
"https://vault.bitwarden.com (US, default), "
|
||||
"https://vault.bitwarden.eu (EU), or your self-hosted URL. "
|
||||
"Skips the interactive region prompt."
|
||||
),
|
||||
)
|
||||
setup.set_defaults(func=cmd_setup)
|
||||
|
||||
status = sub.add_parser("status", help="Show config + binary + last fetch")
|
||||
@@ -154,28 +145,14 @@ def cmd_setup(args: argparse.Namespace) -> int:
|
||||
os.environ[token_env] = token # so the test fetch below sees it
|
||||
console.print(f" [green]✓[/green] stored in {get_env_path()} as {token_env}")
|
||||
|
||||
# ------------------------------------------------------------------ region
|
||||
console.print()
|
||||
console.print("[bold]Step 3[/bold] Pick a Bitwarden region")
|
||||
server_url = _resolve_server_url(args, secrets_cfg, console)
|
||||
if server_url is None:
|
||||
return 1
|
||||
if server_url:
|
||||
console.print(f" [green]✓[/green] using {server_url}")
|
||||
else:
|
||||
console.print(
|
||||
" [green]✓[/green] using bws default "
|
||||
"(US Cloud, https://vault.bitwarden.com)"
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------- project
|
||||
if args.project_id and args.project_id.strip():
|
||||
project_id = args.project_id.strip()
|
||||
else:
|
||||
console.print()
|
||||
console.print("[bold]Step 4[/bold] Pick a project")
|
||||
console.print("[bold]Step 3[/bold] Pick a project")
|
||||
project_id = ""
|
||||
projects = _list_projects(binary, token, console, server_url=server_url)
|
||||
projects = _list_projects(binary, token, console)
|
||||
if projects is None:
|
||||
return 1
|
||||
if not projects:
|
||||
@@ -210,7 +187,7 @@ def cmd_setup(args: argparse.Namespace) -> int:
|
||||
|
||||
# ------------------------------------------------------------------- test
|
||||
console.print()
|
||||
step_num = 5 if not (args.project_id and args.project_id.strip()) else 4
|
||||
step_num = 4 if not (args.project_id and args.project_id.strip()) else 3
|
||||
console.print(f"[bold]Step {step_num}[/bold] Test fetch")
|
||||
try:
|
||||
secrets, warnings = bw.fetch_bitwarden_secrets(
|
||||
@@ -218,7 +195,6 @@ def cmd_setup(args: argparse.Namespace) -> int:
|
||||
project_id=project_id,
|
||||
binary=binary,
|
||||
use_cache=False,
|
||||
server_url=server_url,
|
||||
)
|
||||
except Exception as exc: # noqa: BLE001
|
||||
console.print(f" [red]✗ Fetch failed: {exc}[/red]")
|
||||
@@ -245,7 +221,6 @@ def cmd_setup(args: argparse.Namespace) -> int:
|
||||
# ------------------------------------------------------------------- save
|
||||
secrets_cfg["enabled"] = True
|
||||
secrets_cfg["project_id"] = project_id
|
||||
secrets_cfg["server_url"] = server_url
|
||||
secrets_cfg.setdefault("access_token_env", token_env)
|
||||
secrets_cfg.setdefault("cache_ttl_seconds", 300)
|
||||
secrets_cfg.setdefault("override_existing", True)
|
||||
@@ -273,7 +248,6 @@ def cmd_status(args: argparse.Namespace) -> int:
|
||||
enabled = bool(bw_cfg.get("enabled"))
|
||||
token_env = bw_cfg.get("access_token_env", "BWS_ACCESS_TOKEN")
|
||||
project_id = bw_cfg.get("project_id", "")
|
||||
server_url = str(bw_cfg.get("server_url", "") or "").strip()
|
||||
token_set = bool(os.environ.get(token_env))
|
||||
|
||||
table = Table(show_header=False, box=None, padding=(0, 2))
|
||||
@@ -283,10 +257,6 @@ def cmd_status(args: argparse.Namespace) -> int:
|
||||
table.add_row("Token env var", token_env)
|
||||
table.add_row("Token in env", _yn(token_set))
|
||||
table.add_row("Project ID", project_id or "[dim](unset)[/dim]")
|
||||
table.add_row(
|
||||
"Server URL",
|
||||
server_url or "[dim]default (US Cloud, https://vault.bitwarden.com)[/dim]",
|
||||
)
|
||||
table.add_row("Override existing", _yn(bool(bw_cfg.get("override_existing", False))))
|
||||
table.add_row("Cache TTL (s)", str(bw_cfg.get("cache_ttl_seconds", 300)))
|
||||
table.add_row("Auto-install", _yn(bool(bw_cfg.get("auto_install", True))))
|
||||
@@ -336,14 +306,11 @@ def cmd_sync(args: argparse.Namespace) -> int:
|
||||
console.print("[red]No project_id configured.[/red]")
|
||||
return 1
|
||||
|
||||
server_url = str(bw_cfg.get("server_url", "") or "").strip()
|
||||
|
||||
try:
|
||||
secrets, warnings = bw.fetch_bitwarden_secrets(
|
||||
access_token=token,
|
||||
project_id=project_id,
|
||||
use_cache=False,
|
||||
server_url=server_url,
|
||||
)
|
||||
except Exception as exc: # noqa: BLE001
|
||||
console.print(f"[red]Fetch failed: {exc}[/red]")
|
||||
@@ -440,14 +407,12 @@ def _bws_version(binary: Path) -> str:
|
||||
|
||||
|
||||
def _list_projects(
|
||||
binary: Path, token: str, console: Console, *, server_url: str = ""
|
||||
binary: Path, token: str, console: Console
|
||||
) -> Optional[List[dict]]:
|
||||
"""Call ``bws project list`` and return the parsed list, or None on failure."""
|
||||
env = os.environ.copy()
|
||||
env["BWS_ACCESS_TOKEN"] = token
|
||||
env.setdefault("NO_COLOR", "1")
|
||||
if server_url:
|
||||
env["BWS_SERVER_URL"] = server_url
|
||||
try:
|
||||
res = subprocess.run(
|
||||
[str(binary), "project", "list", "--output", "json"],
|
||||
@@ -463,16 +428,7 @@ def _list_projects(
|
||||
if res.returncode != 0:
|
||||
err = (res.stderr or res.stdout).strip()[:300]
|
||||
console.print(f" [red]bws project list failed: {err}[/red]")
|
||||
lowered = err.lower()
|
||||
if "invalid_client" in lowered or "400 bad request" in lowered:
|
||||
console.print(
|
||||
" [yellow]'invalid_client' from the US identity endpoint usually "
|
||||
"means the token is for a different Bitwarden region. Re-run "
|
||||
"[cyan]hermes secrets bitwarden setup[/cyan] and pick EU or "
|
||||
"self-hosted at the region prompt, or set [cyan]secrets.bitwarden."
|
||||
"server_url[/cyan] in config.yaml.[/yellow]"
|
||||
)
|
||||
elif "authorization" in lowered or "invalid" in lowered:
|
||||
if "authorization" in err.lower() or "invalid" in err.lower():
|
||||
console.print(
|
||||
" [yellow]This usually means the access token is wrong or revoked. "
|
||||
"Double-check it in the Bitwarden web app.[/yellow]"
|
||||
@@ -487,91 +443,3 @@ def _list_projects(
|
||||
if not isinstance(data, list):
|
||||
return []
|
||||
return [p for p in data if isinstance(p, dict) and p.get("id")]
|
||||
|
||||
|
||||
# Canonical Bitwarden region endpoints. Keep in sync with what Bitwarden
|
||||
# publishes — these are stable but if a third region appears, add it here
|
||||
# and to the prompt below.
|
||||
_REGION_PRESETS = [
|
||||
("US Cloud (https://vault.bitwarden.com — bws default)", ""),
|
||||
("EU Cloud (https://vault.bitwarden.eu)", "https://vault.bitwarden.eu"),
|
||||
]
|
||||
|
||||
|
||||
def _resolve_server_url(
|
||||
args: argparse.Namespace,
|
||||
secrets_cfg: dict,
|
||||
console: Console,
|
||||
) -> Optional[str]:
|
||||
"""Pick a Bitwarden server URL for setup.
|
||||
|
||||
Resolution order:
|
||||
1. ``--server-url`` CLI flag (non-interactive)
|
||||
2. ``BWS_SERVER_URL`` env var (so users running with that already set
|
||||
in their shell don't have to re-enter it)
|
||||
3. Existing ``secrets.bitwarden.server_url`` value (for re-runs)
|
||||
4. Interactive menu: US / EU / self-hosted
|
||||
|
||||
Returns the chosen URL as a string (empty string = bws default,
|
||||
i.e. US Cloud). Returns None if the user aborted with an empty
|
||||
custom URL.
|
||||
"""
|
||||
if args.server_url and args.server_url.strip():
|
||||
return args.server_url.strip()
|
||||
|
||||
env_url = os.environ.get("BWS_SERVER_URL", "").strip()
|
||||
if env_url:
|
||||
console.print(
|
||||
f" Detected [cyan]BWS_SERVER_URL[/cyan]={env_url} in your shell — using it."
|
||||
)
|
||||
return env_url
|
||||
|
||||
existing = str(secrets_cfg.get("server_url", "") or "").strip()
|
||||
if existing:
|
||||
console.print(
|
||||
f" Existing config: [cyan]{existing}[/cyan]. "
|
||||
"Press Enter to keep, or pick a different option below."
|
||||
)
|
||||
|
||||
table = Table(show_header=True, header_style="bold", box=None, padding=(0, 2))
|
||||
table.add_column("#", style="cyan", width=4)
|
||||
table.add_column("Region / endpoint")
|
||||
for i, (label, _url) in enumerate(_REGION_PRESETS, 1):
|
||||
table.add_row(str(i), label)
|
||||
table.add_row(str(len(_REGION_PRESETS) + 1), "Self-hosted / custom URL")
|
||||
console.print(table)
|
||||
|
||||
custom_idx = len(_REGION_PRESETS) + 1
|
||||
while True:
|
||||
prompt = f" Select region [1-{custom_idx}]"
|
||||
if existing:
|
||||
prompt += " (Enter to keep current)"
|
||||
prompt += ": "
|
||||
choice = console.input(prompt).strip()
|
||||
if not choice:
|
||||
if existing:
|
||||
return existing
|
||||
console.print(" [red]Enter a number.[/red]")
|
||||
continue
|
||||
try:
|
||||
idx = int(choice)
|
||||
except ValueError:
|
||||
console.print(" [red]Enter a number.[/red]")
|
||||
continue
|
||||
if 1 <= idx <= len(_REGION_PRESETS):
|
||||
return _REGION_PRESETS[idx - 1][1]
|
||||
if idx == custom_idx:
|
||||
custom = console.input(
|
||||
" Enter your Bitwarden server URL "
|
||||
"(e.g. https://vault.example.com): "
|
||||
).strip()
|
||||
if not custom:
|
||||
console.print(" [red]Empty URL, aborting.[/red]")
|
||||
return None
|
||||
if not custom.startswith(("http://", "https://")):
|
||||
console.print(
|
||||
" [yellow]Warning: URL doesn't start with http:// or "
|
||||
"https:// — bws may reject it.[/yellow]"
|
||||
)
|
||||
return custom
|
||||
console.print(f" [red]Out of range — pick 1-{custom_idx}.[/red]")
|
||||
|
||||
@@ -1,576 +0,0 @@
|
||||
"""On-demand supply-chain audit for Hermes Agent installs.
|
||||
|
||||
Scans three surfaces a Hermes user actually controls and we can map to
|
||||
upstream advisories without auth or extra binaries:
|
||||
|
||||
1. The Hermes venv (every PyPI dist via ``importlib.metadata``).
|
||||
2. Python deps declared by user-installed plugins under ``~/.hermes/plugins``
|
||||
(``requirements.txt`` + ``pyproject.toml`` best-effort pin extraction).
|
||||
3. MCP servers wired in ``config.yaml`` whose ``command/args`` look like
|
||||
``npx -y <pkg>@<ver>`` or ``uvx <pkg>==<ver>``.
|
||||
|
||||
Vulnerabilities are looked up against OSV.dev (``api.osv.dev/v1/querybatch``
|
||||
+ ``/v1/vulns/{id}``). Single-shot, on-demand, never daily — see the design
|
||||
notes in ``references/security-disclosure-triage.md``.
|
||||
|
||||
Out of scope on purpose: global pip/npm, editor/browser extensions,
|
||||
daily background scans, auto-blocking installs.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import concurrent.futures
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
from typing import Any, Iterable, Optional
|
||||
|
||||
from hermes_constants import get_hermes_home
|
||||
|
||||
OSV_BATCH_URL = "https://api.osv.dev/v1/querybatch"
|
||||
OSV_VULN_URL = "https://api.osv.dev/v1/vulns/{vid}"
|
||||
OSV_BATCH_MAX = 1000 # OSV documented hard cap per request
|
||||
HTTP_TIMEOUT = 20
|
||||
DETAIL_PARALLELISM = 8
|
||||
|
||||
# Severity ordering for --fail-on gating. UNKNOWN sits below LOW so it
|
||||
# never blocks unless --fail-on is passed something even lower (we don't
|
||||
# expose that).
|
||||
SEVERITY_ORDER = {
|
||||
"UNKNOWN": 0,
|
||||
"LOW": 1,
|
||||
"MODERATE": 2,
|
||||
"MEDIUM": 2,
|
||||
"HIGH": 3,
|
||||
"CRITICAL": 4,
|
||||
}
|
||||
|
||||
|
||||
# ─── Data shapes ──────────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class Component:
|
||||
"""A single (name, version, ecosystem) tuple discovered on disk."""
|
||||
|
||||
name: str
|
||||
version: str
|
||||
ecosystem: str # "PyPI" | "npm" — exactly as OSV expects
|
||||
source: str # human-readable origin, e.g. "venv", "plugin:foo", "mcp:bar"
|
||||
|
||||
|
||||
@dataclass
|
||||
class Vulnerability:
|
||||
osv_id: str
|
||||
severity: str = "UNKNOWN"
|
||||
summary: str = ""
|
||||
fixed_versions: list[str] = field(default_factory=list)
|
||||
|
||||
|
||||
@dataclass
|
||||
class Finding:
|
||||
component: Component
|
||||
vuln: Vulnerability
|
||||
|
||||
|
||||
# ─── Component discovery ──────────────────────────────────────────────────────
|
||||
|
||||
|
||||
def _discover_venv() -> list[Component]:
|
||||
"""Every dist installed in the running Python's import path."""
|
||||
from importlib.metadata import distributions
|
||||
|
||||
out: list[Component] = []
|
||||
seen: set[tuple[str, str]] = set()
|
||||
for dist in distributions():
|
||||
try:
|
||||
name = (dist.metadata["Name"] or "").strip()
|
||||
except Exception:
|
||||
continue
|
||||
version = (dist.version or "").strip()
|
||||
if not name or not version:
|
||||
continue
|
||||
key = (name.lower(), version)
|
||||
if key in seen:
|
||||
continue
|
||||
seen.add(key)
|
||||
out.append(Component(name=name, version=version, ecosystem="PyPI", source="venv"))
|
||||
return out
|
||||
|
||||
|
||||
# requirements.txt line: drop comments, environment markers, options, extras
|
||||
_REQ_LINE = re.compile(
|
||||
r"""^\s*
|
||||
(?P<name>[A-Za-z0-9][A-Za-z0-9._-]*)
|
||||
(?:\[[^\]]+\])? # extras
|
||||
\s*==\s*
|
||||
(?P<version>[A-Za-z0-9._+!-]+)
|
||||
\s*(?:;.*)?$
|
||||
""",
|
||||
re.VERBOSE,
|
||||
)
|
||||
|
||||
|
||||
def _parse_requirements(text: str) -> list[tuple[str, str]]:
|
||||
"""Extract ``name==version`` pins. Everything else (>=, ~=, no pin) is skipped.
|
||||
|
||||
A loose pin can't be mapped to a single OSV query, and getting it wrong
|
||||
is worse than missing a finding for an audit tool — false positives
|
||||
train users to ignore output.
|
||||
"""
|
||||
pins: list[tuple[str, str]] = []
|
||||
for raw in text.splitlines():
|
||||
line = raw.strip()
|
||||
if not line or line.startswith("#") or line.startswith("-"):
|
||||
continue
|
||||
m = _REQ_LINE.match(line)
|
||||
if m:
|
||||
pins.append((m.group("name"), m.group("version")))
|
||||
return pins
|
||||
|
||||
|
||||
def _parse_pyproject_pins(text: str) -> list[tuple[str, str]]:
|
||||
"""Pull ``name==version`` pins from a ``pyproject.toml`` ``dependencies`` list.
|
||||
|
||||
Uses stdlib ``tomllib`` (3.11+). Same exact-pin policy as requirements.
|
||||
"""
|
||||
try:
|
||||
import tomllib
|
||||
except ImportError: # pragma: no cover - 3.10 only
|
||||
return []
|
||||
try:
|
||||
data = tomllib.loads(text)
|
||||
except Exception:
|
||||
return []
|
||||
deps: list[str] = []
|
||||
project = data.get("project") or {}
|
||||
if isinstance(project.get("dependencies"), list):
|
||||
deps.extend(str(x) for x in project["dependencies"])
|
||||
optional = project.get("optional-dependencies") or {}
|
||||
if isinstance(optional, dict):
|
||||
for group in optional.values():
|
||||
if isinstance(group, list):
|
||||
deps.extend(str(x) for x in group)
|
||||
pins: list[tuple[str, str]] = []
|
||||
for dep in deps:
|
||||
m = _REQ_LINE.match(dep)
|
||||
if m:
|
||||
pins.append((m.group("name"), m.group("version")))
|
||||
return pins
|
||||
|
||||
|
||||
def _discover_plugins(hermes_home: Path) -> list[Component]:
|
||||
"""Python deps declared by plugins under ``~/.hermes/plugins``.
|
||||
|
||||
Plugins typically don't install into the venv (they're directory-based
|
||||
with relative imports), so their stated requirements are useful audit
|
||||
surface even when the venv scan misses them.
|
||||
"""
|
||||
plugins_dir = hermes_home / "plugins"
|
||||
if not plugins_dir.is_dir():
|
||||
return []
|
||||
|
||||
out: list[Component] = []
|
||||
for plugin_dir in sorted(plugins_dir.iterdir()):
|
||||
if not plugin_dir.is_dir() or plugin_dir.name.startswith("."):
|
||||
continue
|
||||
source = f"plugin:{plugin_dir.name}"
|
||||
for req_file in ("requirements.txt", "requirements-dev.txt"):
|
||||
path = plugin_dir / req_file
|
||||
if path.is_file():
|
||||
try:
|
||||
pins = _parse_requirements(path.read_text(encoding="utf-8", errors="replace"))
|
||||
except OSError:
|
||||
continue
|
||||
for name, version in pins:
|
||||
out.append(Component(name=name, version=version, ecosystem="PyPI", source=source))
|
||||
pyproject = plugin_dir / "pyproject.toml"
|
||||
if pyproject.is_file():
|
||||
try:
|
||||
pins = _parse_pyproject_pins(pyproject.read_text(encoding="utf-8", errors="replace"))
|
||||
except OSError:
|
||||
continue
|
||||
for name, version in pins:
|
||||
out.append(Component(name=name, version=version, ecosystem="PyPI", source=source))
|
||||
return out
|
||||
|
||||
|
||||
# npx forms we recognise:
|
||||
# npx -y @scope/pkg@1.2.3
|
||||
# npx --yes pkg@1.2.3
|
||||
# npx pkg@1.2.3 [...args]
|
||||
# We deliberately don't try to resolve unversioned names — that maps to
|
||||
# "latest" at runtime and isn't a stable audit subject.
|
||||
_NPX_PKG = re.compile(r"^(@[A-Za-z0-9._-]+/[A-Za-z0-9._-]+|[A-Za-z0-9._-]+)@([A-Za-z0-9._+-]+)$")
|
||||
# uvx forms:
|
||||
# uvx pkg==1.2.3
|
||||
# uvx --with pkg==1.2.3 entrypoint
|
||||
_UVX_PKG = re.compile(r"^([A-Za-z0-9][A-Za-z0-9._-]*)==([A-Za-z0-9._+!-]+)$")
|
||||
|
||||
|
||||
def _extract_mcp_component(server_name: str, command: str, args: list[str]) -> Optional[Component]:
|
||||
"""Best-effort: parse `command/args` into a (name, version, ecosystem).
|
||||
|
||||
Returns None when the entry doesn't pin a version we can audit (local
|
||||
paths, Docker images, unversioned npx, etc.). Audit output stays silent
|
||||
rather than guess.
|
||||
"""
|
||||
cmd = (command or "").strip().lower()
|
||||
if not args:
|
||||
return None
|
||||
# npx (any prefix path)
|
||||
if cmd.endswith("npx") or cmd == "npx":
|
||||
# Skip flag tokens until we see the first thing that looks like a pkg ref
|
||||
for token in args:
|
||||
if token.startswith("-"):
|
||||
continue
|
||||
m = _NPX_PKG.match(token)
|
||||
if m:
|
||||
return Component(
|
||||
name=m.group(1),
|
||||
version=m.group(2),
|
||||
ecosystem="npm",
|
||||
source=f"mcp:{server_name}",
|
||||
)
|
||||
return None # First non-flag token isn't a pinned ref
|
||||
# uvx (any prefix path)
|
||||
if cmd.endswith("uvx") or cmd == "uvx":
|
||||
for token in args:
|
||||
if token.startswith("-"):
|
||||
continue
|
||||
m = _UVX_PKG.match(token)
|
||||
if m:
|
||||
return Component(
|
||||
name=m.group(1),
|
||||
version=m.group(2),
|
||||
ecosystem="PyPI",
|
||||
source=f"mcp:{server_name}",
|
||||
)
|
||||
return None
|
||||
return None
|
||||
|
||||
|
||||
def _discover_mcp() -> list[Component]:
|
||||
"""Pinned MCP server packages from ``config.yaml``."""
|
||||
try:
|
||||
from hermes_cli.mcp_config import _get_mcp_servers
|
||||
except Exception:
|
||||
return []
|
||||
|
||||
out: list[Component] = []
|
||||
servers = _get_mcp_servers()
|
||||
if not isinstance(servers, dict):
|
||||
return []
|
||||
for name, cfg in servers.items():
|
||||
if not isinstance(cfg, dict):
|
||||
continue
|
||||
command = cfg.get("command", "") or ""
|
||||
args = cfg.get("args") or []
|
||||
if not isinstance(args, list):
|
||||
continue
|
||||
comp = _extract_mcp_component(name, command, [str(a) for a in args])
|
||||
if comp is not None:
|
||||
out.append(comp)
|
||||
return out
|
||||
|
||||
|
||||
# ─── OSV client ───────────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
def _http_post_json(url: str, payload: dict) -> dict:
|
||||
data = json.dumps(payload).encode("utf-8")
|
||||
req = urllib.request.Request(
|
||||
url, data=data, headers={"Content-Type": "application/json"}, method="POST"
|
||||
)
|
||||
with urllib.request.urlopen(req, timeout=HTTP_TIMEOUT) as resp:
|
||||
return json.loads(resp.read().decode("utf-8"))
|
||||
|
||||
|
||||
def _http_get_json(url: str) -> dict:
|
||||
req = urllib.request.Request(url, method="GET")
|
||||
with urllib.request.urlopen(req, timeout=HTTP_TIMEOUT) as resp:
|
||||
return json.loads(resp.read().decode("utf-8"))
|
||||
|
||||
|
||||
def _osv_query_batch(components: list[Component]) -> dict[Component, list[str]]:
|
||||
"""Return {component -> [osv_id, ...]} for components with any vulns.
|
||||
|
||||
Components without findings are omitted from the result dict.
|
||||
"""
|
||||
if not components:
|
||||
return {}
|
||||
findings: dict[Component, list[str]] = {}
|
||||
for chunk_start in range(0, len(components), OSV_BATCH_MAX):
|
||||
chunk = components[chunk_start:chunk_start + OSV_BATCH_MAX]
|
||||
payload = {
|
||||
"queries": [
|
||||
{
|
||||
"package": {"name": c.name, "ecosystem": c.ecosystem},
|
||||
"version": c.version,
|
||||
}
|
||||
for c in chunk
|
||||
]
|
||||
}
|
||||
try:
|
||||
resp = _http_post_json(OSV_BATCH_URL, payload)
|
||||
except (urllib.error.URLError, TimeoutError, ConnectionError) as exc:
|
||||
raise RuntimeError(f"OSV batch query failed: {exc}") from exc
|
||||
results = resp.get("results") or []
|
||||
for comp, result in zip(chunk, results):
|
||||
vulns = (result or {}).get("vulns") or []
|
||||
ids = [v.get("id") for v in vulns if v.get("id")]
|
||||
if ids:
|
||||
findings[comp] = ids
|
||||
return findings
|
||||
|
||||
|
||||
def _osv_severity_from_record(record: dict) -> str:
|
||||
"""Extract CVSS-derived severity tier from an OSV vuln record."""
|
||||
# OSV puts CVSS in `severity` (top-level or per-affected) and a
|
||||
# human-readable bucket in `database_specific.severity` for GHSAs.
|
||||
db_specific = record.get("database_specific") or {}
|
||||
raw = db_specific.get("severity")
|
||||
if isinstance(raw, str) and raw.strip():
|
||||
upper = raw.strip().upper()
|
||||
if upper in SEVERITY_ORDER:
|
||||
return upper
|
||||
# Fall back to CVSS score → tier
|
||||
score: Optional[float] = None
|
||||
for sev_entry in record.get("severity") or []:
|
||||
s = sev_entry.get("score")
|
||||
if isinstance(s, str):
|
||||
# CVSS vector strings look like "CVSS:3.1/AV:N/..." — we can't
|
||||
# parse without a lib. Look for an explicit numeric in
|
||||
# affected[].ecosystem_specific later if present.
|
||||
continue
|
||||
affected = record.get("affected") or []
|
||||
for entry in affected:
|
||||
eco_spec = entry.get("ecosystem_specific") or {}
|
||||
sev = eco_spec.get("severity")
|
||||
if isinstance(sev, str) and sev.strip().upper() in SEVERITY_ORDER:
|
||||
return sev.strip().upper()
|
||||
if score is not None:
|
||||
if score >= 9.0:
|
||||
return "CRITICAL"
|
||||
if score >= 7.0:
|
||||
return "HIGH"
|
||||
if score >= 4.0:
|
||||
return "MODERATE"
|
||||
if score > 0:
|
||||
return "LOW"
|
||||
return "UNKNOWN"
|
||||
|
||||
|
||||
def _osv_fixed_versions(record: dict) -> list[str]:
|
||||
fixes: list[str] = []
|
||||
for entry in record.get("affected") or []:
|
||||
for rng in entry.get("ranges") or []:
|
||||
for event in rng.get("events") or []:
|
||||
if "fixed" in event:
|
||||
fixes.append(str(event["fixed"]))
|
||||
# Dedupe, preserve order
|
||||
seen: set[str] = set()
|
||||
out: list[str] = []
|
||||
for f in fixes:
|
||||
if f not in seen:
|
||||
seen.add(f)
|
||||
out.append(f)
|
||||
return out
|
||||
|
||||
|
||||
def _osv_fetch_details(vuln_ids: Iterable[str]) -> dict[str, Vulnerability]:
|
||||
"""Fetch summary/severity for each unique vuln id, in parallel."""
|
||||
unique = sorted({vid for vid in vuln_ids if vid})
|
||||
if not unique:
|
||||
return {}
|
||||
out: dict[str, Vulnerability] = {}
|
||||
|
||||
def _fetch_one(vid: str) -> Vulnerability:
|
||||
try:
|
||||
rec = _http_get_json(OSV_VULN_URL.format(vid=vid))
|
||||
except (urllib.error.URLError, TimeoutError, ConnectionError):
|
||||
return Vulnerability(osv_id=vid)
|
||||
return Vulnerability(
|
||||
osv_id=vid,
|
||||
severity=_osv_severity_from_record(rec),
|
||||
summary=(rec.get("summary") or "").strip(),
|
||||
fixed_versions=_osv_fixed_versions(rec),
|
||||
)
|
||||
|
||||
with concurrent.futures.ThreadPoolExecutor(max_workers=DETAIL_PARALLELISM) as pool:
|
||||
for vuln in pool.map(_fetch_one, unique):
|
||||
out[vuln.osv_id] = vuln
|
||||
return out
|
||||
|
||||
|
||||
# ─── Orchestration ────────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
def run_audit(
|
||||
*,
|
||||
skip_venv: bool = False,
|
||||
skip_plugins: bool = False,
|
||||
skip_mcp: bool = False,
|
||||
hermes_home: Optional[Path] = None,
|
||||
) -> list[Finding]:
|
||||
"""Discover components, query OSV, return findings sorted by severity desc."""
|
||||
home = hermes_home or Path(get_hermes_home())
|
||||
components: list[Component] = []
|
||||
if not skip_venv:
|
||||
components.extend(_discover_venv())
|
||||
if not skip_plugins:
|
||||
components.extend(_discover_plugins(home))
|
||||
if not skip_mcp:
|
||||
components.extend(_discover_mcp())
|
||||
|
||||
if not components:
|
||||
return []
|
||||
|
||||
raw = _osv_query_batch(components)
|
||||
if not raw:
|
||||
return []
|
||||
|
||||
all_ids: list[str] = []
|
||||
for ids in raw.values():
|
||||
all_ids.extend(ids)
|
||||
details = _osv_fetch_details(all_ids)
|
||||
|
||||
findings: list[Finding] = []
|
||||
for comp, ids in raw.items():
|
||||
for vid in ids:
|
||||
vuln = details.get(vid) or Vulnerability(osv_id=vid)
|
||||
findings.append(Finding(component=comp, vuln=vuln))
|
||||
|
||||
findings.sort(
|
||||
key=lambda f: (
|
||||
-SEVERITY_ORDER.get(f.vuln.severity, 0),
|
||||
f.component.source,
|
||||
f.component.name.lower(),
|
||||
f.vuln.osv_id,
|
||||
)
|
||||
)
|
||||
return findings
|
||||
|
||||
|
||||
# ─── Rendering ────────────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
def _render_human(findings: list[Finding], total_components: int) -> str:
|
||||
if not findings:
|
||||
return f"No known vulnerabilities found across {total_components} component(s)."
|
||||
|
||||
lines: list[str] = []
|
||||
lines.append(
|
||||
f"Found {len(findings)} known vulnerability finding(s) "
|
||||
f"across {total_components} component(s):"
|
||||
)
|
||||
lines.append("")
|
||||
last_source = None
|
||||
for f in findings:
|
||||
if f.component.source != last_source:
|
||||
lines.append(f"[{f.component.source}]")
|
||||
last_source = f.component.source
|
||||
sev = f.vuln.severity.ljust(8)
|
||||
head = f" {sev} {f.component.name}=={f.component.version} {f.vuln.osv_id}"
|
||||
lines.append(head)
|
||||
if f.vuln.summary:
|
||||
summary = f.vuln.summary
|
||||
if len(summary) > 100:
|
||||
summary = summary[:97] + "..."
|
||||
lines.append(f" {summary}")
|
||||
if f.vuln.fixed_versions:
|
||||
lines.append(f" fixed in: {', '.join(f.vuln.fixed_versions[:3])}")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def _render_json(findings: list[Finding], total_components: int) -> str:
|
||||
payload = {
|
||||
"total_components_scanned": total_components,
|
||||
"finding_count": len(findings),
|
||||
"findings": [
|
||||
{
|
||||
"package": f.component.name,
|
||||
"version": f.component.version,
|
||||
"ecosystem": f.component.ecosystem,
|
||||
"source": f.component.source,
|
||||
"vuln_id": f.vuln.osv_id,
|
||||
"severity": f.vuln.severity,
|
||||
"summary": f.vuln.summary,
|
||||
"fixed_versions": f.vuln.fixed_versions,
|
||||
}
|
||||
for f in findings
|
||||
],
|
||||
}
|
||||
return json.dumps(payload, indent=2)
|
||||
|
||||
|
||||
def _count_components(
|
||||
*, skip_venv: bool, skip_plugins: bool, skip_mcp: bool, hermes_home: Path
|
||||
) -> int:
|
||||
total = 0
|
||||
if not skip_venv:
|
||||
total += len(_discover_venv())
|
||||
if not skip_plugins:
|
||||
total += len(_discover_plugins(hermes_home))
|
||||
if not skip_mcp:
|
||||
total += len(_discover_mcp())
|
||||
return total
|
||||
|
||||
|
||||
# ─── CLI entrypoint ───────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
def cmd_security_audit(args: argparse.Namespace) -> int:
|
||||
"""Implementation of `hermes security audit`."""
|
||||
home = Path(get_hermes_home())
|
||||
skip_venv = bool(getattr(args, "skip_venv", False))
|
||||
skip_plugins = bool(getattr(args, "skip_plugins", False))
|
||||
skip_mcp = bool(getattr(args, "skip_mcp", False))
|
||||
output_json = bool(getattr(args, "json", False))
|
||||
fail_on = (getattr(args, "fail_on", None) or "critical").upper()
|
||||
if fail_on not in SEVERITY_ORDER:
|
||||
print(
|
||||
f"unknown --fail-on value: {fail_on.lower()} "
|
||||
f"(choose from: low, moderate, high, critical)",
|
||||
file=sys.stderr,
|
||||
)
|
||||
return 2
|
||||
|
||||
total = _count_components(
|
||||
skip_venv=skip_venv, skip_plugins=skip_plugins, skip_mcp=skip_mcp, hermes_home=home
|
||||
)
|
||||
if total == 0:
|
||||
msg = "No components discovered (everything skipped, or empty environment)."
|
||||
if output_json:
|
||||
print(json.dumps({"total_components_scanned": 0, "finding_count": 0, "findings": []}))
|
||||
else:
|
||||
print(msg)
|
||||
return 0
|
||||
|
||||
try:
|
||||
findings = run_audit(
|
||||
skip_venv=skip_venv,
|
||||
skip_plugins=skip_plugins,
|
||||
skip_mcp=skip_mcp,
|
||||
hermes_home=home,
|
||||
)
|
||||
except RuntimeError as exc:
|
||||
print(f"audit failed: {exc}", file=sys.stderr)
|
||||
return 2
|
||||
|
||||
if output_json:
|
||||
print(_render_json(findings, total))
|
||||
else:
|
||||
print(_render_human(findings, total))
|
||||
|
||||
# Exit code: 1 iff any finding meets or exceeds the --fail-on threshold.
|
||||
threshold = SEVERITY_ORDER[fail_on]
|
||||
for f in findings:
|
||||
if SEVERITY_ORDER.get(f.vuln.severity, 0) >= threshold:
|
||||
return 1
|
||||
return 0
|
||||
@@ -1,886 +0,0 @@
|
||||
"""Abstract service manager interface.
|
||||
|
||||
Wraps the existing systemd (Linux host), launchd (macOS host), Windows
|
||||
Scheduled Task (native Windows host), and s6 (container) backends behind
|
||||
a common Protocol. Only the s6 backend supports runtime registration
|
||||
(for per-profile gateways) — host backends raise NotImplementedError
|
||||
from those methods, and callers MUST check supports_runtime_registration()
|
||||
before invoking them.
|
||||
|
||||
Host-side call sites (setup wizard, uninstall, status) continue to use
|
||||
the existing module-level functions in hermes_cli.gateway and
|
||||
hermes_cli.gateway_windows directly. This protocol is a thin facade
|
||||
used by new code that needs to be backend-agnostic — specifically the
|
||||
profile create/delete hooks (Phase 4) and the s6 dispatch path in
|
||||
``hermes gateway start/stop/restart`` when running inside a container.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from pathlib import Path
|
||||
from typing import Literal, Protocol, runtime_checkable
|
||||
|
||||
ServiceManagerKind = Literal["systemd", "launchd", "windows", "s6", "none"]
|
||||
|
||||
# Profile name → service directory mapping. Profile names must be safe
|
||||
# as filesystem directory names because the s6 backend creates a service
|
||||
# directory at ``<scandir>/gateway-<profile>/``. We reject anything that
|
||||
# could traverse paths, span filesystems, or break s6's own naming rules.
|
||||
_VALID_PROFILE_RE = re.compile(r"^[a-z0-9][a-z0-9_-]*$")
|
||||
_MAX_PROFILE_LEN = 251 # s6-svscan default name_max
|
||||
|
||||
|
||||
def validate_profile_name(name: str) -> None:
|
||||
"""Raise ValueError if ``name`` is not usable as a profile name.
|
||||
|
||||
Profile names are used as s6 service directory names, so they must
|
||||
match a conservative subset of filesystem-safe characters. Reject
|
||||
empty strings, uppercase, paths-traversal sequences, and anything
|
||||
longer than s6's default ``name_max``.
|
||||
"""
|
||||
if not name:
|
||||
raise ValueError("profile name must not be empty")
|
||||
if len(name) > _MAX_PROFILE_LEN:
|
||||
raise ValueError(
|
||||
f"profile name too long ({len(name)} > {_MAX_PROFILE_LEN})"
|
||||
)
|
||||
if not _VALID_PROFILE_RE.match(name):
|
||||
raise ValueError(
|
||||
f"profile name must match [a-z0-9][a-z0-9_-]*, got {name!r}"
|
||||
)
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
class ServiceManager(Protocol):
|
||||
"""Abstract interface for init-system-specific service operations.
|
||||
|
||||
Lifecycle methods (start / stop / restart / is_running) are
|
||||
implemented by every backend. Runtime registration
|
||||
(register_profile_gateway / unregister_profile_gateway /
|
||||
list_profile_gateways) is implemented only by the s6 backend —
|
||||
callers MUST check ``supports_runtime_registration()`` before
|
||||
invoking the registration methods.
|
||||
"""
|
||||
|
||||
kind: ServiceManagerKind
|
||||
|
||||
# Lifecycle of a pre-declared service.
|
||||
def start(self, name: str) -> None: ...
|
||||
def stop(self, name: str) -> None: ...
|
||||
def restart(self, name: str) -> None: ...
|
||||
def is_running(self, name: str) -> bool: ...
|
||||
|
||||
# Runtime registration (s6 only).
|
||||
def supports_runtime_registration(self) -> bool: ...
|
||||
def register_profile_gateway(
|
||||
self,
|
||||
profile: str,
|
||||
*,
|
||||
extra_env: dict[str, str] | None = None,
|
||||
) -> None: ...
|
||||
def unregister_profile_gateway(self, profile: str) -> None: ...
|
||||
def list_profile_gateways(self) -> list[str]: ...
|
||||
|
||||
|
||||
def detect_service_manager() -> ServiceManagerKind:
|
||||
"""Detect which service manager is available in this environment.
|
||||
|
||||
Returns:
|
||||
"s6" — inside a container when /init is s6-svscan (Phase 2+)
|
||||
"windows" — native Windows host
|
||||
"launchd" — macOS host
|
||||
"systemd" — Linux host with a working user/system bus
|
||||
"none" — anything else (Termux, sandbox shells, etc.)
|
||||
|
||||
This function does NOT replace ``supports_systemd_services()`` —
|
||||
host call sites continue to use that. It exists for new backend-
|
||||
agnostic code (profile create/delete hooks, the s6 dispatch path
|
||||
in ``hermes gateway start/stop/restart``).
|
||||
"""
|
||||
# Imports deferred so importing this module doesn't drag in the
|
||||
# whole gateway dependency graph for callers that only need the
|
||||
# Protocol type or validate_profile_name().
|
||||
from hermes_constants import is_container
|
||||
from hermes_cli.gateway import (
|
||||
is_macos,
|
||||
is_windows,
|
||||
supports_systemd_services,
|
||||
)
|
||||
|
||||
if is_container() and _s6_running():
|
||||
return "s6"
|
||||
if is_windows():
|
||||
return "windows"
|
||||
if is_macos():
|
||||
return "launchd"
|
||||
if supports_systemd_services():
|
||||
return "systemd"
|
||||
return "none"
|
||||
|
||||
|
||||
def _s6_running() -> bool:
|
||||
"""True when s6-svscan is running as PID 1 in this container.
|
||||
|
||||
Detection has to work for **both** root and the unprivileged hermes
|
||||
user (UID 10000). The obvious probe — ``Path('/proc/1/exe').resolve()``
|
||||
— only works as root: for any other UID, the symlink at
|
||||
``/proc/1/exe`` is unreadable and ``resolve()`` silently returns the
|
||||
path unchanged, so the resolved name is the literal ``"exe"`` and
|
||||
detection always fails. Since every Hermes runtime call inside the
|
||||
container drops to hermes via ``s6-setuidgid``, that silent failure
|
||||
made the entire service-manager runtime-registration path inert in
|
||||
production (PR #30136 review).
|
||||
|
||||
Probe instead via:
|
||||
* ``/proc/1/comm`` — world-readable, contains the process comm
|
||||
(``s6-svscan`` when s6-overlay is PID 1).
|
||||
* ``/run/s6/basedir`` — s6-overlay-specific directory created by
|
||||
stage1. World-readable. More specific than ``/run/s6`` (which
|
||||
other tools occasionally create).
|
||||
|
||||
Both signals are required; either alone could false-positive
|
||||
(e.g. a container with the s6 binaries installed but a different
|
||||
init, or an unrelated process named ``s6-svscan``).
|
||||
"""
|
||||
try:
|
||||
comm = Path("/proc/1/comm").read_text(encoding="utf-8").strip()
|
||||
except OSError:
|
||||
return False
|
||||
if comm != "s6-svscan":
|
||||
return False
|
||||
return Path("/run/s6/basedir").is_dir()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Backend wrappers
|
||||
#
|
||||
# These adapters are thin facades over the existing module-level functions
|
||||
# in ``hermes_cli.gateway`` (systemd/launchd) and ``hermes_cli.gateway_windows``
|
||||
# (Windows Scheduled Tasks). The protocol's ``name`` parameter is currently
|
||||
# unused for host backends — they operate on whichever profile is currently
|
||||
# active (set via the ``hermes -p <profile>`` flag before the call). This
|
||||
# matches existing host-side semantics; the parameter shape is designed
|
||||
# for s6 where each profile maps to a distinct service directory.
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class _RegistrationUnsupportedMixin:
|
||||
"""Mixin for host backends that don't support runtime registration."""
|
||||
|
||||
def supports_runtime_registration(self) -> bool:
|
||||
return False
|
||||
|
||||
def register_profile_gateway(
|
||||
self,
|
||||
profile: str,
|
||||
*,
|
||||
extra_env: dict[str, str] | None = None,
|
||||
) -> None:
|
||||
raise NotImplementedError(
|
||||
f"{type(self).__name__} does not support runtime profile "
|
||||
"gateway registration (container-only feature)"
|
||||
)
|
||||
|
||||
def unregister_profile_gateway(self, profile: str) -> None:
|
||||
raise NotImplementedError(
|
||||
f"{type(self).__name__} does not support runtime profile "
|
||||
"gateway unregistration (container-only feature)"
|
||||
)
|
||||
|
||||
def list_profile_gateways(self) -> list[str]:
|
||||
return []
|
||||
|
||||
|
||||
class SystemdServiceManager(_RegistrationUnsupportedMixin):
|
||||
"""Thin wrapper around the ``systemd_*`` functions in hermes_cli.gateway.
|
||||
|
||||
Existing host call sites continue to use those functions directly;
|
||||
this wrapper exists for new code that needs to be backend-agnostic
|
||||
(the Phase 4 profile create/delete hooks).
|
||||
"""
|
||||
|
||||
kind: ServiceManagerKind = "systemd"
|
||||
|
||||
def start(self, name: str) -> None:
|
||||
from hermes_cli.gateway import systemd_start
|
||||
systemd_start()
|
||||
|
||||
def stop(self, name: str) -> None:
|
||||
from hermes_cli.gateway import systemd_stop
|
||||
systemd_stop()
|
||||
|
||||
def restart(self, name: str) -> None:
|
||||
from hermes_cli.gateway import systemd_restart
|
||||
systemd_restart()
|
||||
|
||||
def is_running(self, name: str) -> bool:
|
||||
from hermes_cli.gateway import _probe_systemd_service_running
|
||||
_, running = _probe_systemd_service_running()
|
||||
return running
|
||||
|
||||
|
||||
class LaunchdServiceManager(_RegistrationUnsupportedMixin):
|
||||
"""Thin wrapper around the ``launchd_*`` functions in hermes_cli.gateway."""
|
||||
|
||||
kind: ServiceManagerKind = "launchd"
|
||||
|
||||
def start(self, name: str) -> None:
|
||||
from hermes_cli.gateway import launchd_start
|
||||
launchd_start()
|
||||
|
||||
def stop(self, name: str) -> None:
|
||||
from hermes_cli.gateway import launchd_stop
|
||||
launchd_stop()
|
||||
|
||||
def restart(self, name: str) -> None:
|
||||
from hermes_cli.gateway import launchd_restart
|
||||
launchd_restart()
|
||||
|
||||
def is_running(self, name: str) -> bool:
|
||||
from hermes_cli.gateway import _probe_launchd_service_running
|
||||
return _probe_launchd_service_running()
|
||||
|
||||
|
||||
class WindowsServiceManager(_RegistrationUnsupportedMixin):
|
||||
"""Thin wrapper around ``hermes_cli.gateway_windows`` (Scheduled Task /
|
||||
Startup-folder fallback).
|
||||
|
||||
The native Windows backend uses a Scheduled Task rather than a true
|
||||
init-system service, but for protocol purposes the lifecycle is the
|
||||
same: start / stop / restart / is_running. ``install`` accepts a
|
||||
handful of Windows-specific kwargs (start_now, start_on_login,
|
||||
elevated_handoff) that are passed straight through — non-Windows
|
||||
callers should never invoke ``install`` on this wrapper.
|
||||
"""
|
||||
|
||||
kind: ServiceManagerKind = "windows"
|
||||
|
||||
def install(
|
||||
self,
|
||||
*,
|
||||
force: bool = False,
|
||||
start_now: bool | None = None,
|
||||
start_on_login: bool | None = None,
|
||||
elevated_handoff: bool = False,
|
||||
) -> None:
|
||||
from hermes_cli import gateway_windows
|
||||
gateway_windows.install(
|
||||
force=force,
|
||||
start_now=start_now,
|
||||
start_on_login=start_on_login,
|
||||
elevated_handoff=elevated_handoff,
|
||||
)
|
||||
|
||||
def start(self, name: str) -> None:
|
||||
from hermes_cli import gateway_windows
|
||||
gateway_windows.start()
|
||||
|
||||
def stop(self, name: str) -> None:
|
||||
from hermes_cli import gateway_windows
|
||||
gateway_windows.stop()
|
||||
|
||||
def restart(self, name: str) -> None:
|
||||
from hermes_cli import gateway_windows
|
||||
gateway_windows.restart()
|
||||
|
||||
def is_running(self, name: str) -> bool:
|
||||
from hermes_cli import gateway_windows
|
||||
from hermes_cli.gateway import find_gateway_pids
|
||||
if not gateway_windows.is_installed():
|
||||
return False
|
||||
return bool(find_gateway_pids())
|
||||
|
||||
|
||||
def get_service_manager() -> ServiceManager:
|
||||
"""Return the ServiceManager instance for the current environment.
|
||||
|
||||
Raises:
|
||||
RuntimeError: when no supported backend is available.
|
||||
"""
|
||||
kind = detect_service_manager()
|
||||
if kind == "systemd":
|
||||
return SystemdServiceManager()
|
||||
if kind == "launchd":
|
||||
return LaunchdServiceManager()
|
||||
if kind == "windows":
|
||||
return WindowsServiceManager()
|
||||
if kind == "s6":
|
||||
return S6ServiceManager()
|
||||
raise RuntimeError("no supported service manager detected")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# S6ServiceManager (container-only)
|
||||
#
|
||||
# Per-profile gateways are registered dynamically when `hermes profile create`
|
||||
# runs inside the container (Phase 4). Static services (main-hermes, dashboard)
|
||||
# live in /etc/s6-overlay/s6-rc.d/ and are NOT managed by this class — they're
|
||||
# part of the image, not runtime-created.
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
# s6-overlay's dynamic scandir for runtime-registered services. Lives on
|
||||
# tmpfs and is the directory s6-svscan watches. Writes here trigger
|
||||
# automatic supervision on the next rescan.
|
||||
S6_DYNAMIC_SCANDIR = Path("/run/service")
|
||||
S6_SERVICE_PREFIX = "gateway-"
|
||||
|
||||
# s6-overlay installs its binaries under /command/ and only adds that
|
||||
# directory to PATH for processes started under the supervision tree
|
||||
# (services started by s6-svscan, cont-init.d scripts, etc.). Code
|
||||
# that runs via `docker exec` or any other out-of-tree entry point —
|
||||
# notably our Phase 4 profile create/delete hooks — inherits the
|
||||
# container's base PATH which does NOT include /command/.
|
||||
#
|
||||
# Rather than asking every caller to fix up its environment, the
|
||||
# S6ServiceManager calls s6-* binaries by absolute path via this
|
||||
# constant. We don't use `/usr/bin/s6-…` symlinks because the
|
||||
# s6-overlay-symlinks-noarch tarball only links a subset, and we
|
||||
# want every s6 invocation to be guaranteed-findable.
|
||||
_S6_BIN_DIR = "/command"
|
||||
|
||||
|
||||
# UID/GID of the in-image ``hermes`` user. Hardcoded to match what
|
||||
# ``stage2-hook.sh`` enforces (the runtime invariant — see also
|
||||
# tests/docker/test_uid_remap.py). The container starts s6-supervise
|
||||
# under root and immediately drops to this UID via ``s6-setuidgid``.
|
||||
_HERMES_UID = 10000
|
||||
_HERMES_GID = 10000
|
||||
|
||||
|
||||
def _seed_supervise_skeleton(svc_dir: Path) -> None:
|
||||
"""Pre-create the ``supervise/`` and top-level ``event/`` skeleton
|
||||
inside a service directory, owned by the hermes user.
|
||||
|
||||
Why this exists
|
||||
---------------
|
||||
When s6-supervise spawns a service it tries to ``mkdir`` two
|
||||
directories: ``<svc>/event`` and ``<svc>/supervise``, both with mode
|
||||
``0700``. It also ``mkfifo``s ``<svc>/supervise/control`` with mode
|
||||
``0600``. Because s6-supervise runs as PID 1's effective UID (root)
|
||||
these dirs end up root-owned mode 0700, and an unprivileged client
|
||||
(the ``hermes`` user — UID 10000 — running every Hermes runtime
|
||||
operation via ``s6-setuidgid``) gets ``EACCES`` on any ``s6-svc``,
|
||||
``s6-svstat``, or ``s6-svwait`` invocation against the slot.
|
||||
|
||||
The PR #30136 review surfaced this as a real product gap: the
|
||||
entire S6ServiceManager lifecycle (``register/start/stop/unregister
|
||||
_profile_gateway``) was inert in production because every operation
|
||||
is dispatched as the hermes user.
|
||||
|
||||
Why this works
|
||||
--------------
|
||||
Reading s6's source (src/supervision/s6-supervise.c::trymkdir +
|
||||
control_init): the ``mkdir`` and ``mkfifo`` calls both treat
|
||||
``EEXIST`` as success. If the directory is already present, the
|
||||
chown/chmod fix-up that would normally make event/ ``03730
|
||||
root:root`` is **skipped** entirely — s6-supervise just opens the
|
||||
pre-existing FIFOs and proceeds. So if we lay the skeleton down
|
||||
with hermes ownership before triggering ``s6-svscanctl -a``,
|
||||
s6-supervise inherits our layout and never touches it.
|
||||
|
||||
Layout produced
|
||||
---------------
|
||||
``svc_dir/`` hermes:hermes, 0755 (parent must already exist)
|
||||
``svc_dir/event/`` hermes:hermes, 03730 (setgid + g+rwx + sticky)
|
||||
``svc_dir/supervise/`` hermes:hermes, 0755
|
||||
``svc_dir/supervise/event/`` hermes:hermes, 03730
|
||||
``svc_dir/supervise/control`` hermes:hermes, 0660 (FIFO)
|
||||
|
||||
The ``death_tally``, ``lock``, and ``status`` regular files end up
|
||||
written by s6-supervise itself (as root), but those land mode 0644 —
|
||||
world-readable — and ``s6-svstat`` only needs read access, so the
|
||||
hermes user reads them fine.
|
||||
|
||||
If ``svc_dir/log/`` is present (the canonical s6 logger pattern —
|
||||
one s6-supervise instance per service, plus a second for its
|
||||
logger), the same skeleton is seeded under ``log/`` as well:
|
||||
``log/event/``, ``log/supervise/``, ``log/supervise/event/``,
|
||||
``log/supervise/control``. Without this, unregister teardown
|
||||
would EACCES on the logger's supervise dir even after the parent
|
||||
slot's supervise/ was hermes-owned.
|
||||
|
||||
Idempotency
|
||||
-----------
|
||||
Safe to call against a directory where the skeleton already exists.
|
||||
Existing entries are left untouched (the helper doesn't try to
|
||||
re-chown / re-chmod live FIFOs that s6-supervise may have already
|
||||
opened).
|
||||
|
||||
Reference
|
||||
---------
|
||||
Discussed at length on the skarnet `skaware` mailing list in 2020
|
||||
(`<http://skarnet.org/lists/skaware/1424.html>`_); see also
|
||||
just-containers/s6-overlay#130. The pre-creation pattern was
|
||||
historically called out as forward-compatibility-fragile, but the
|
||||
EEXIST handling in s6-supervise has been stable since 2015 — it's
|
||||
the same pattern ``s6-svperms`` and ``fix-attrs.d`` rely on.
|
||||
"""
|
||||
import os
|
||||
|
||||
def _mkdir_owned(path: Path, mode: int) -> None:
|
||||
if path.exists():
|
||||
return
|
||||
path.mkdir(parents=False, exist_ok=False)
|
||||
path.chmod(mode)
|
||||
try:
|
||||
os.chown(path, _HERMES_UID, _HERMES_GID)
|
||||
except PermissionError:
|
||||
# Running as the hermes user already — directory is hermes-
|
||||
# owned by default. The chown is a no-op in that case, so
|
||||
# swallowing this keeps both root and unprivileged callers
|
||||
# on one code path.
|
||||
pass
|
||||
|
||||
# Top-level event/ dir (this is the s6-svlisten1 event-subscription
|
||||
# dir at the service root, distinct from supervise/event/).
|
||||
_mkdir_owned(svc_dir / "event", 0o3730)
|
||||
|
||||
# supervise/ dir + its inner event/ dir.
|
||||
supervise = svc_dir / "supervise"
|
||||
_mkdir_owned(supervise, 0o755)
|
||||
_mkdir_owned(supervise / "event", 0o3730)
|
||||
|
||||
# supervise/control FIFO. Same EEXIST-safe pattern: if it's already
|
||||
# there (s6-supervise has already started against this slot), leave
|
||||
# it alone. The explicit chmod after mkfifo is required because
|
||||
# mkfifo honors the process umask, which can strip group-write
|
||||
# (e.g. the default 0022 on most dev hosts → 0o660 becomes 0o640).
|
||||
# The container runs with umask 0 inside s6-overlay's stage2, but
|
||||
# being defensive here keeps the helper consistent under any
|
||||
# invocation context.
|
||||
control = supervise / "control"
|
||||
if not control.exists():
|
||||
os.mkfifo(control, 0o660)
|
||||
control.chmod(0o660)
|
||||
try:
|
||||
os.chown(control, _HERMES_UID, _HERMES_GID)
|
||||
except PermissionError:
|
||||
pass
|
||||
|
||||
# If a log/ subdir is present (the canonical s6 logger pattern —
|
||||
# see servicedir(7)), it gets its own s6-supervise instance and
|
||||
# needs the same skeleton. Without this, unregister teardown
|
||||
# would EACCES on the logger's root-owned supervise/ dir even
|
||||
# when the parent slot's supervise/ is hermes-owned.
|
||||
log_dir = svc_dir / "log"
|
||||
if log_dir.is_dir():
|
||||
_mkdir_owned(log_dir / "event", 0o3730)
|
||||
log_supervise = log_dir / "supervise"
|
||||
_mkdir_owned(log_supervise, 0o755)
|
||||
_mkdir_owned(log_supervise / "event", 0o3730)
|
||||
log_control = log_supervise / "control"
|
||||
if not log_control.exists():
|
||||
os.mkfifo(log_control, 0o660)
|
||||
log_control.chmod(0o660)
|
||||
try:
|
||||
os.chown(log_control, _HERMES_UID, _HERMES_GID)
|
||||
except PermissionError:
|
||||
pass
|
||||
|
||||
|
||||
class S6Error(RuntimeError):
|
||||
"""Base error for S6ServiceManager lifecycle failures.
|
||||
|
||||
Concrete subclasses carry the slot name (and, where useful, the
|
||||
underlying subprocess output) so the CLI can render an actionable
|
||||
message instead of leaking a raw ``CalledProcessError`` traceback.
|
||||
"""
|
||||
|
||||
def __init__(self, message: str, *, service: str | None = None) -> None:
|
||||
super().__init__(message)
|
||||
self.service = service
|
||||
|
||||
|
||||
class GatewayNotRegisteredError(S6Error):
|
||||
"""Raised when a lifecycle method targets a slot that doesn't exist.
|
||||
|
||||
Most commonly: ``hermes -p typo gateway start`` when no profile
|
||||
``typo`` exists. Carries the unprefixed profile name (not the
|
||||
full ``gateway-<profile>`` service-dir name) so callers can phrase
|
||||
a user-facing message like "no such gateway 'typo'".
|
||||
"""
|
||||
|
||||
def __init__(self, profile: str) -> None:
|
||||
self.profile = profile
|
||||
super().__init__(
|
||||
f"no such gateway {profile!r}: register it with "
|
||||
f"`hermes profile create {profile}` first, or pass "
|
||||
"an existing profile name via `-p <name>`",
|
||||
service=f"gateway-{profile}",
|
||||
)
|
||||
|
||||
|
||||
class S6CommandError(S6Error):
|
||||
"""Raised when an s6 command fails for a reason other than a
|
||||
missing slot — e.g. permission denied on the supervise control
|
||||
FIFO, or s6-svc returning a non-zero exit for an unexpected
|
||||
reason. Carries the stderr from the failing command so callers
|
||||
can surface it.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self, *, service: str, action: str, returncode: int, stderr: str,
|
||||
) -> None:
|
||||
self.action = action
|
||||
self.returncode = returncode
|
||||
self.stderr = stderr
|
||||
message = (
|
||||
f"s6-svc {action} on {service!r} failed (rc={returncode})"
|
||||
)
|
||||
if stderr.strip():
|
||||
message += f": {stderr.strip()}"
|
||||
super().__init__(message, service=service)
|
||||
|
||||
|
||||
class S6ServiceManager:
|
||||
"""Per-profile gateway supervision via s6-overlay.
|
||||
|
||||
Only handles runtime-registered services under
|
||||
``S6_DYNAMIC_SCANDIR``. Static services (main-hermes, dashboard)
|
||||
are managed by s6-rc at image-build time and are out of scope.
|
||||
"""
|
||||
|
||||
kind: ServiceManagerKind = "s6"
|
||||
|
||||
def __init__(self, scandir: Path = S6_DYNAMIC_SCANDIR) -> None:
|
||||
self.scandir = scandir
|
||||
|
||||
# -- internal helpers --------------------------------------------------
|
||||
|
||||
def _service_dir(self, profile: str) -> Path:
|
||||
validate_profile_name(profile)
|
||||
return self.scandir / f"{S6_SERVICE_PREFIX}{profile}"
|
||||
|
||||
def _service_name(self, profile: str) -> str:
|
||||
return f"{S6_SERVICE_PREFIX}{profile}"
|
||||
|
||||
@staticmethod
|
||||
def _render_run_script(
|
||||
profile: str,
|
||||
extra_env: dict[str, str],
|
||||
) -> str:
|
||||
"""Generate the run script for a profile-gateway s6 service.
|
||||
|
||||
The script:
|
||||
1. Sources HERMES_HOME (and any extra env) via with-contenv —
|
||||
so e.g. ``-e HERMES_HOME=/data/hermes`` is honored at run
|
||||
time, not Python-substituted at registration time (OQ8-C).
|
||||
2. Activates the bundled venv.
|
||||
3. Drops to the hermes user and exec's
|
||||
``hermes -p <profile> gateway run`` (or just ``hermes
|
||||
gateway run`` for the default profile — see below).
|
||||
|
||||
Special case: ``profile == "default"`` emits ``hermes gateway
|
||||
run`` with **no** ``-p`` flag. This is the sentinel for "the
|
||||
root HERMES_HOME profile" (the implicit profile that exists at
|
||||
the top of $HERMES_HOME, not under profiles/). It must be
|
||||
spelled this way because ``_profile_suffix()`` returns the
|
||||
empty string for the root profile, and the dispatcher in
|
||||
``hermes_cli.gateway`` maps that empty string to the
|
||||
``gateway-default`` service slot. Passing ``-p default`` here
|
||||
would instead look up ``$HERMES_HOME/profiles/default/`` — a
|
||||
completely different (and almost always nonexistent) profile.
|
||||
|
||||
Port selection: the gateway picks its bind port from the
|
||||
profile's ``config.yaml`` (``[gateway] port = ...``) — that
|
||||
is the single source of truth. Previously this method took a
|
||||
``port`` parameter that was passed in but never substituted
|
||||
into the rendered script (it was carried in for "API parity"
|
||||
with a deterministic SHA-256 allocator in
|
||||
``hermes_cli.profiles._allocate_gateway_port``). PR #30136
|
||||
review item I5 retired both the allocator and the parameter
|
||||
because they were dead code through the entire stack.
|
||||
"""
|
||||
import shlex
|
||||
lines = [
|
||||
"#!/command/with-contenv sh",
|
||||
"# shellcheck shell=sh",
|
||||
"set -e",
|
||||
"cd /opt/data",
|
||||
". /opt/hermes/.venv/bin/activate",
|
||||
]
|
||||
for k, v in sorted(extra_env.items()):
|
||||
lines.append(f"export {k}={shlex.quote(v)}")
|
||||
if profile == "default":
|
||||
lines.append("exec s6-setuidgid hermes hermes gateway run")
|
||||
else:
|
||||
lines.append(
|
||||
f"exec s6-setuidgid hermes hermes -p {shlex.quote(profile)} gateway run"
|
||||
)
|
||||
return "\n".join(lines) + "\n"
|
||||
|
||||
@staticmethod
|
||||
def _render_log_run(profile: str) -> str:
|
||||
"""Generate the log/run script for a profile-gateway service.
|
||||
|
||||
OQ8-C: persist to ``${HERMES_HOME}/logs/gateways/<profile>/``.
|
||||
CRITICAL: the HERMES_HOME path is sourced from the runtime env
|
||||
via with-contenv — NOT Python-substituted at registration time
|
||||
— so a container started with ``-e HERMES_HOME=/data/hermes``
|
||||
gets its logs under /data/hermes/logs/..., not the build-time
|
||||
default.
|
||||
"""
|
||||
import shlex
|
||||
prof = shlex.quote(profile)
|
||||
return (
|
||||
f"#!/command/with-contenv sh\n"
|
||||
f"# shellcheck shell=sh\n"
|
||||
f': "${{HERMES_HOME:=/opt/data}}"\n'
|
||||
f'log_dir="$HERMES_HOME/logs/gateways/{prof}"\n'
|
||||
f'mkdir -p "$log_dir"\n'
|
||||
f'chown -R hermes:hermes "$log_dir" 2>/dev/null || true\n'
|
||||
f'exec s6-setuidgid hermes s6-log n10 s1000000 T "$log_dir"\n'
|
||||
)
|
||||
|
||||
# -- lifecycle ---------------------------------------------------------
|
||||
|
||||
def _run_svc(self, action_flag: str, action_label: str, name: str) -> None:
|
||||
"""Shared lifecycle dispatch for start / stop / restart.
|
||||
|
||||
Translates the two failure modes operators care about into
|
||||
named errors:
|
||||
|
||||
* ``GatewayNotRegisteredError`` — the service directory at
|
||||
``<scandir>/<name>/`` doesn't exist. ``s6-svc`` would
|
||||
exit non-zero with a fairly opaque message; we pre-empt
|
||||
it with a clear "no such gateway 'X'" tied to the profile
|
||||
name (without the ``gateway-`` prefix).
|
||||
* ``S6CommandError`` — anything else (EACCES on the
|
||||
supervise control FIFO, timeout, etc.). Carries the
|
||||
subprocess return code and stderr so callers can render
|
||||
them inline.
|
||||
|
||||
``action_flag`` is the ``s6-svc`` flag (``-u`` / ``-d`` /
|
||||
``-t``); ``action_label`` is the human verb (``start`` /
|
||||
``stop`` / ``restart``) used in error messages.
|
||||
"""
|
||||
import subprocess
|
||||
|
||||
service_dir = self.scandir / name
|
||||
if not service_dir.is_dir():
|
||||
# Strip the gateway- prefix back off so the message
|
||||
# matches what the user typed on the CLI (``-p <profile>``).
|
||||
profile = (
|
||||
name[len(S6_SERVICE_PREFIX):]
|
||||
if name.startswith(S6_SERVICE_PREFIX)
|
||||
else name
|
||||
)
|
||||
raise GatewayNotRegisteredError(profile)
|
||||
|
||||
try:
|
||||
subprocess.run(
|
||||
[f"{_S6_BIN_DIR}/s6-svc", action_flag, str(service_dir)],
|
||||
check=True, capture_output=True, text=True, timeout=5,
|
||||
)
|
||||
except subprocess.CalledProcessError as exc:
|
||||
raise S6CommandError(
|
||||
service=name,
|
||||
action=action_label,
|
||||
returncode=exc.returncode,
|
||||
stderr=exc.stderr or "",
|
||||
) from exc
|
||||
|
||||
def start(self, name: str) -> None:
|
||||
"""Bring up a registered service (``s6-svc -u``).
|
||||
|
||||
Raises:
|
||||
GatewayNotRegisteredError: no service directory for ``name``.
|
||||
S6CommandError: s6-svc exited non-zero for any other reason
|
||||
(permission denied on the supervise FIFO, timeout, etc.).
|
||||
"""
|
||||
self._run_svc("-u", "start", name)
|
||||
|
||||
def stop(self, name: str) -> None:
|
||||
"""Bring down a registered service (``s6-svc -d``).
|
||||
|
||||
Raises:
|
||||
GatewayNotRegisteredError: no service directory for ``name``.
|
||||
S6CommandError: s6-svc exited non-zero for any other reason.
|
||||
"""
|
||||
self._run_svc("-d", "stop", name)
|
||||
|
||||
def restart(self, name: str) -> None:
|
||||
"""Restart a registered service (``s6-svc -t`` = SIGTERM).
|
||||
|
||||
Raises:
|
||||
GatewayNotRegisteredError: no service directory for ``name``.
|
||||
S6CommandError: s6-svc exited non-zero for any other reason.
|
||||
"""
|
||||
self._run_svc("-t", "restart", name)
|
||||
|
||||
def is_running(self, name: str) -> bool:
|
||||
"""True iff ``s6-svstat`` reports the service as up."""
|
||||
import subprocess
|
||||
result = subprocess.run(
|
||||
[f"{_S6_BIN_DIR}/s6-svstat", str(self.scandir / name)],
|
||||
capture_output=True, text=True, timeout=5,
|
||||
)
|
||||
return result.returncode == 0 and "up " in result.stdout
|
||||
|
||||
# -- runtime registration ---------------------------------------------
|
||||
|
||||
def supports_runtime_registration(self) -> bool:
|
||||
return True
|
||||
|
||||
def register_profile_gateway(
|
||||
self,
|
||||
profile: str,
|
||||
*,
|
||||
extra_env: dict[str, str] | None = None,
|
||||
) -> None:
|
||||
"""Create the s6 service directory for a profile gateway.
|
||||
|
||||
Triggers ``s6-svscanctl -a`` so s6-svscan picks the new directory
|
||||
up immediately. The service is created in the *up* state — to
|
||||
register without auto-starting, follow up with ``stop(profile)``
|
||||
(or pass the start flag via the future ``start_now=False`` arg,
|
||||
which the Phase 4 reconciliation path uses via a ``down``
|
||||
marker file written directly).
|
||||
|
||||
Raises:
|
||||
ValueError: if the profile name is invalid or the service
|
||||
directory already exists.
|
||||
RuntimeError: if ``s6-svscanctl`` fails.
|
||||
"""
|
||||
import shutil
|
||||
import subprocess
|
||||
|
||||
svc_dir = self._service_dir(profile)
|
||||
if svc_dir.exists():
|
||||
raise ValueError(
|
||||
f"profile gateway {profile!r} already registered at {svc_dir}"
|
||||
)
|
||||
|
||||
# Build the service directory atomically: write to a sibling
|
||||
# temp dir, then rename. Avoids s6-svscan observing a half-
|
||||
# populated directory on a fast rescan.
|
||||
tmp_dir = svc_dir.with_name(svc_dir.name + ".tmp")
|
||||
if tmp_dir.exists():
|
||||
shutil.rmtree(tmp_dir, ignore_errors=True)
|
||||
tmp_dir.mkdir(parents=True)
|
||||
|
||||
try:
|
||||
(tmp_dir / "type").write_text("longrun\n")
|
||||
|
||||
run_script = self._render_run_script(profile, extra_env or {})
|
||||
run_path = tmp_dir / "run"
|
||||
run_path.write_text(run_script)
|
||||
run_path.chmod(0o755)
|
||||
|
||||
# Persistent log rotation (OQ8-C).
|
||||
log_subdir = tmp_dir / "log"
|
||||
log_subdir.mkdir()
|
||||
log_run = log_subdir / "run"
|
||||
log_run.write_text(self._render_log_run(profile))
|
||||
log_run.chmod(0o755)
|
||||
|
||||
# Pre-create the supervise/ skeleton with hermes ownership
|
||||
# BEFORE we publish the slot. s6-supervise will EEXIST our
|
||||
# dirs/FIFOs and inherit the ownership, so the runtime
|
||||
# s6-svc / s6-svstat / s6-svwait calls (all dispatched as
|
||||
# the hermes user) won't hit EACCES on root-owned 0700
|
||||
# dirs. See ``_seed_supervise_skeleton`` for the full
|
||||
# rationale.
|
||||
_seed_supervise_skeleton(tmp_dir)
|
||||
|
||||
tmp_dir.rename(svc_dir)
|
||||
except Exception:
|
||||
shutil.rmtree(tmp_dir, ignore_errors=True)
|
||||
raise
|
||||
|
||||
# Trigger rescan so s6-svscan picks up the new service.
|
||||
result = subprocess.run(
|
||||
[f"{_S6_BIN_DIR}/s6-svscanctl", "-a", str(self.scandir)],
|
||||
capture_output=True, text=True, timeout=5,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
# Clean up: rescan failed, leave the directory in place would
|
||||
# be confusing (no supervisor watching it).
|
||||
shutil.rmtree(svc_dir, ignore_errors=True)
|
||||
raise RuntimeError(
|
||||
f"s6-svscanctl failed: {result.stderr or result.stdout}"
|
||||
)
|
||||
|
||||
def unregister_profile_gateway(self, profile: str) -> None:
|
||||
"""Stop the profile gateway service and remove its directory.
|
||||
|
||||
Idempotent: absent services are a no-op. Best-effort stop +
|
||||
wait-for-down before removal so the running gateway process
|
||||
gets a chance to shut down cleanly before its service dir
|
||||
disappears.
|
||||
|
||||
Teardown ordering matters: ``s6-svscanctl -an`` is fired
|
||||
**before** ``rmtree`` so s6-svscan reaps the supervise child
|
||||
process (releasing its handle on ``supervise/lock`` and the
|
||||
regular files inside the supervise dir), giving us a clean
|
||||
directory to remove. Without the reap-first ordering, the
|
||||
rmtree races s6-supervise on a set of root-owned files inside
|
||||
the supervise dir and the dir is left half-removed.
|
||||
"""
|
||||
import shutil
|
||||
import subprocess
|
||||
import time
|
||||
|
||||
svc_dir = self._service_dir(profile)
|
||||
if not svc_dir.exists():
|
||||
return
|
||||
|
||||
# Stop the service (best effort — service may already be down).
|
||||
subprocess.run(
|
||||
[f"{_S6_BIN_DIR}/s6-svc", "-d", str(svc_dir)],
|
||||
capture_output=True, text=True, timeout=5,
|
||||
check=False,
|
||||
)
|
||||
# Wait for it to actually go down (up to 10s).
|
||||
subprocess.run(
|
||||
[f"{_S6_BIN_DIR}/s6-svwait", "-D", "-t", "10000", str(svc_dir)],
|
||||
capture_output=True, text=True, timeout=15,
|
||||
check=False,
|
||||
)
|
||||
|
||||
# Reap the supervise child FIRST: -n tells s6-svscan to drop
|
||||
# any supervise processes whose service dir is gone (which
|
||||
# includes any service dir we're about to remove). This
|
||||
# releases the file handles s6-supervise holds against the
|
||||
# supervise/lock + supervise/status + supervise/death_tally
|
||||
# files inside the slot, so the upcoming rmtree doesn't race.
|
||||
subprocess.run(
|
||||
[f"{_S6_BIN_DIR}/s6-svscanctl", "-an", str(self.scandir)],
|
||||
capture_output=True, text=True, timeout=5,
|
||||
check=False,
|
||||
)
|
||||
# Give s6-svscan a moment to reap. There's no synchronous
|
||||
# "scan completed" handshake — the -a/-n trigger just sets a
|
||||
# flag s6-svscan reads on its next loop iteration. 200ms is
|
||||
# comfortably above the loop's resolution but well under any
|
||||
# user-perceived latency.
|
||||
time.sleep(0.2)
|
||||
|
||||
# Now the supervise dir's files are no longer held open by a
|
||||
# live s6-supervise, so rmtree can remove them. Files inside
|
||||
# supervise/ are root-owned (death_tally, lock, status, written
|
||||
# by s6-supervise itself) — but the parent supervise/ directory
|
||||
# is hermes-owned (see ``_seed_supervise_skeleton``), and on
|
||||
# POSIX you only need write+execute on the parent to remove
|
||||
# contained files regardless of file ownership.
|
||||
shutil.rmtree(svc_dir, ignore_errors=True)
|
||||
|
||||
def list_profile_gateways(self) -> list[str]:
|
||||
"""Return the profile names of all currently-registered gateway services.
|
||||
|
||||
Filters the scandir to entries that match the ``gateway-`` prefix.
|
||||
Other services (e.g. ``s6-linux-init-shutdownd``) are ignored.
|
||||
"""
|
||||
if not self.scandir.exists():
|
||||
return []
|
||||
profiles: list[str] = []
|
||||
for entry in self.scandir.iterdir():
|
||||
if entry.name.startswith("."):
|
||||
continue
|
||||
if not entry.is_dir():
|
||||
continue
|
||||
if not entry.name.startswith(S6_SERVICE_PREFIX):
|
||||
continue
|
||||
profiles.append(entry.name[len(S6_SERVICE_PREFIX):])
|
||||
return profiles
|
||||
+20
-168
@@ -2188,58 +2188,28 @@ def _setup_matrix():
|
||||
print_success("E2EE enabled")
|
||||
|
||||
matrix_pkg = "mautrix[encryption]" if want_e2ee else "mautrix"
|
||||
# Use the central lazy-deps feature group so we install ALL of
|
||||
# platform.matrix's dependencies (mautrix, Markdown, aiosqlite,
|
||||
# asyncpg, aiohttp-socks) — not just mautrix itself. The previous
|
||||
# hand-rolled ``pip install mautrix[encryption]`` left asyncpg /
|
||||
# aiosqlite uninstalled and broke E2EE connect with
|
||||
# ``No module named 'asyncpg'`` on every fresh install (#31116).
|
||||
try:
|
||||
from tools.lazy_deps import ensure as _lazy_ensure, feature_missing
|
||||
_missing_before = feature_missing("platform.matrix")
|
||||
if _missing_before:
|
||||
print_info(
|
||||
f"Installing {matrix_pkg} (+ {len(_missing_before)} runtime deps)..."
|
||||
)
|
||||
try:
|
||||
_lazy_ensure("platform.matrix", prompt=False)
|
||||
print_success(f"{matrix_pkg} installed")
|
||||
except Exception as exc:
|
||||
print_warning(
|
||||
f"Install failed — run manually: pip install "
|
||||
f"'mautrix[encryption]' asyncpg aiosqlite Markdown "
|
||||
f"aiohttp-socks"
|
||||
)
|
||||
print_info(f" Error: {exc}")
|
||||
__import__("mautrix")
|
||||
except ImportError:
|
||||
# tools.lazy_deps unavailable (extreme edge case — partial
|
||||
# install). Fall back to the legacy single-package install
|
||||
# path so the wizard still does *something*.
|
||||
try:
|
||||
__import__("mautrix")
|
||||
except ImportError:
|
||||
print_info(f"Installing {matrix_pkg}...")
|
||||
import subprocess
|
||||
uv_bin = shutil.which("uv")
|
||||
if uv_bin:
|
||||
result = subprocess.run(
|
||||
[uv_bin, "pip", "install", "--python", sys.executable, matrix_pkg],
|
||||
capture_output=True, text=True,
|
||||
)
|
||||
else:
|
||||
result = subprocess.run(
|
||||
[sys.executable, "-m", "pip", "install", matrix_pkg],
|
||||
capture_output=True, text=True,
|
||||
)
|
||||
if result.returncode == 0:
|
||||
print_success(f"{matrix_pkg} installed")
|
||||
else:
|
||||
print_warning(
|
||||
f"Install failed — run manually: pip install "
|
||||
f"'{matrix_pkg}' asyncpg aiosqlite Markdown aiohttp-socks"
|
||||
)
|
||||
if result.stderr:
|
||||
print_info(f" Error: {result.stderr.strip().splitlines()[-1]}")
|
||||
print_info(f"Installing {matrix_pkg}...")
|
||||
import subprocess
|
||||
uv_bin = shutil.which("uv")
|
||||
if uv_bin:
|
||||
result = subprocess.run(
|
||||
[uv_bin, "pip", "install", "--python", sys.executable, matrix_pkg],
|
||||
capture_output=True, text=True,
|
||||
)
|
||||
else:
|
||||
result = subprocess.run(
|
||||
[sys.executable, "-m", "pip", "install", matrix_pkg],
|
||||
capture_output=True, text=True,
|
||||
)
|
||||
if result.returncode == 0:
|
||||
print_success(f"{matrix_pkg} installed")
|
||||
else:
|
||||
print_warning(f"Install failed — run manually: pip install '{matrix_pkg}'")
|
||||
if result.stderr:
|
||||
print_info(f" Error: {result.stderr.strip().splitlines()[-1]}")
|
||||
|
||||
print()
|
||||
print_info("🔒 Security: Restrict who can use your bot")
|
||||
@@ -3090,119 +3060,6 @@ SETUP_SECTIONS = [
|
||||
]
|
||||
|
||||
|
||||
def _run_portal_one_shot(config: dict) -> None:
|
||||
"""One-shot Nous Portal setup — OAuth + provider switch + Tool Gateway.
|
||||
|
||||
Wired into ``hermes setup --portal``. Does NOT prompt for anything
|
||||
besides what the underlying OAuth + Tool Gateway prompts already need.
|
||||
Designed to be shareable as a single command (``hermes setup --portal``)
|
||||
that gets a brand-new user from zero to a fully working Hermes session
|
||||
with web/image/tts/browser tools all routed via their Portal sub.
|
||||
"""
|
||||
from types import SimpleNamespace
|
||||
|
||||
from hermes_cli.auth_commands import auth_add_command
|
||||
from hermes_cli.config import save_config
|
||||
from hermes_cli.auth import get_nous_auth_status
|
||||
from hermes_cli.nous_subscription import prompt_enable_tool_gateway
|
||||
|
||||
print()
|
||||
print(
|
||||
color(
|
||||
"┌─────────────────────────────────────────────────────────┐",
|
||||
Colors.MAGENTA,
|
||||
)
|
||||
)
|
||||
print(color("│ ⚕ Hermes Setup — Nous Portal (one-shot) │", Colors.MAGENTA))
|
||||
print(
|
||||
color(
|
||||
"└─────────────────────────────────────────────────────────┘",
|
||||
Colors.MAGENTA,
|
||||
)
|
||||
)
|
||||
print()
|
||||
print_info(" One subscription, 300+ models, plus the Tool Gateway:")
|
||||
print_info(" web search, image generation, TTS, browser automation")
|
||||
print_info(" — all routed through your Nous Portal sub.")
|
||||
print()
|
||||
print_info(" Sign up: https://portal.nousresearch.com/manage-subscription")
|
||||
print()
|
||||
|
||||
# Skip OAuth if already logged in (don't re-prompt every time the user
|
||||
# runs `hermes setup --portal` after a successful first run).
|
||||
already_logged_in = False
|
||||
try:
|
||||
already_logged_in = bool((get_nous_auth_status() or {}).get("logged_in"))
|
||||
except Exception:
|
||||
already_logged_in = False
|
||||
|
||||
if already_logged_in:
|
||||
print_success(" Already logged into Nous Portal.")
|
||||
else:
|
||||
# Hand off to the shared auth wiring so the device-code flow is
|
||||
# identical to `hermes auth add nous --type oauth`. SimpleNamespace
|
||||
# mirrors the argparse Namespace contract that auth_add_command expects.
|
||||
ns = SimpleNamespace(
|
||||
provider="nous",
|
||||
auth_type="oauth",
|
||||
label=None,
|
||||
api_key=None,
|
||||
portal_url=None,
|
||||
inference_url=None,
|
||||
client_id=None,
|
||||
scope=None,
|
||||
no_browser=False,
|
||||
timeout=None,
|
||||
insecure=False,
|
||||
ca_bundle=None,
|
||||
min_key_ttl_seconds=5 * 60,
|
||||
)
|
||||
try:
|
||||
auth_add_command(ns)
|
||||
except SystemExit as e:
|
||||
print()
|
||||
print_error(f" Nous Portal login failed (exit {e.code}).")
|
||||
print_info(" You can retry later with `hermes auth add nous --type oauth`.")
|
||||
return
|
||||
except (KeyboardInterrupt, EOFError):
|
||||
print()
|
||||
print_info(" Setup cancelled.")
|
||||
return
|
||||
except Exception as exc:
|
||||
print()
|
||||
print_error(f" Nous Portal login failed: {exc}")
|
||||
print_info(" You can retry later with `hermes auth add nous --type oauth`.")
|
||||
return
|
||||
|
||||
# Set provider → nous so the model picker, status surfaces, and
|
||||
# managed-tool gating all light up. Leave model.model empty so the
|
||||
# runtime picks Nous's default model; the user can change it later
|
||||
# with `hermes model`.
|
||||
model_cfg = config.get("model")
|
||||
if not isinstance(model_cfg, dict):
|
||||
model_cfg = {}
|
||||
config["model"] = model_cfg
|
||||
model_cfg["provider"] = "nous"
|
||||
save_config(config)
|
||||
print()
|
||||
print_success(" Nous set as your inference provider.")
|
||||
|
||||
# Offer the Tool Gateway opt-in (single Y/n) — same flow that fires
|
||||
# from `hermes model` after picking Nous.
|
||||
print()
|
||||
try:
|
||||
prompt_enable_tool_gateway(config)
|
||||
except (KeyboardInterrupt, EOFError):
|
||||
pass
|
||||
except Exception as exc:
|
||||
print_warning(f" Tool Gateway prompt skipped: {exc}")
|
||||
|
||||
print()
|
||||
print_success("Portal setup complete.")
|
||||
print_info(" Run `hermes portal status` to inspect routing.")
|
||||
print_info(" Run `hermes` to start chatting.")
|
||||
|
||||
|
||||
def run_setup_wizard(args):
|
||||
"""Run the interactive setup wizard.
|
||||
|
||||
@@ -3258,11 +3115,6 @@ def run_setup_wizard(args):
|
||||
)
|
||||
return
|
||||
|
||||
# --portal: one-shot Nous Portal setup. Skips the rest of the wizard.
|
||||
if bool(getattr(args, "portal", False)):
|
||||
_run_portal_one_shot(config)
|
||||
return
|
||||
|
||||
# Check if a specific section was requested
|
||||
section = getattr(args, "section", None)
|
||||
if section:
|
||||
|
||||
@@ -906,14 +906,8 @@ def do_update(name: Optional[str] = None, console: Optional[Console] = None) ->
|
||||
c.print(f"[bold green]Updated {len(updates)} skill(s).[/]\n")
|
||||
|
||||
|
||||
def do_audit(name: Optional[str] = None, console: Optional[Console] = None,
|
||||
deep: bool = False) -> None:
|
||||
"""Re-run security scan on installed hub skills.
|
||||
|
||||
When ``deep=True``, also runs an opt-in AST-level diagnostic on Python
|
||||
files (review aid only — not a security gate; skills_guard.py verdicts
|
||||
are unchanged).
|
||||
"""
|
||||
def do_audit(name: Optional[str] = None, console: Optional[Console] = None) -> None:
|
||||
"""Re-run security scan on installed hub skills."""
|
||||
from tools.skills_hub import HubLockFile, SKILLS_DIR
|
||||
from tools.skills_guard import scan_skill, format_scan_report
|
||||
|
||||
@@ -934,9 +928,6 @@ def do_audit(name: Optional[str] = None, console: Optional[Console] = None,
|
||||
|
||||
c.print(f"\n[bold]Auditing {len(targets)} skill(s)...[/]\n")
|
||||
|
||||
if deep:
|
||||
from tools.skills_ast_audit import ast_scan_path, format_ast_report
|
||||
|
||||
for entry in targets:
|
||||
skill_path = SKILLS_DIR / entry["install_path"]
|
||||
if not skill_path.exists():
|
||||
@@ -945,10 +936,6 @@ def do_audit(name: Optional[str] = None, console: Optional[Console] = None,
|
||||
|
||||
result = scan_skill(skill_path, source=entry.get("identifier", entry["source"]))
|
||||
c.print(format_scan_report(result))
|
||||
|
||||
if deep:
|
||||
c.print(format_ast_report(ast_scan_path(skill_path), skill_name=entry["name"]))
|
||||
|
||||
c.print()
|
||||
|
||||
|
||||
@@ -1356,8 +1343,7 @@ def skills_command(args) -> None:
|
||||
elif action == "update":
|
||||
do_update(name=getattr(args, "name", None))
|
||||
elif action == "audit":
|
||||
do_audit(name=getattr(args, "name", None),
|
||||
deep=getattr(args, "deep", False))
|
||||
do_audit(name=getattr(args, "name", None))
|
||||
elif action == "uninstall":
|
||||
do_uninstall(args.name)
|
||||
elif action == "reset":
|
||||
@@ -1409,8 +1395,6 @@ def handle_skills_slash(cmd: str, console: Optional[Console] = None) -> None:
|
||||
/skills update
|
||||
/skills audit
|
||||
/skills audit my-skill
|
||||
/skills audit --deep
|
||||
/skills audit my-skill --deep
|
||||
/skills uninstall my-skill
|
||||
/skills tap list
|
||||
/skills tap add owner/repo
|
||||
@@ -1525,9 +1509,8 @@ def handle_skills_slash(cmd: str, console: Optional[Console] = None) -> None:
|
||||
do_update(name=name, console=c)
|
||||
|
||||
elif action == "audit":
|
||||
name = args[0] if args and not args[0].startswith("--") else None
|
||||
deep = "--deep" in args
|
||||
do_audit(name=name, console=c, deep=deep)
|
||||
name = args[0] if args else None
|
||||
do_audit(name=name, console=c)
|
||||
|
||||
elif action == "uninstall":
|
||||
if not args:
|
||||
|
||||
@@ -1925,16 +1925,6 @@ def _configure_tool_category(ts_key: str, cat: dict, config: dict):
|
||||
print()
|
||||
|
||||
# Plain text labels only (no ANSI codes in menu items)
|
||||
# When the user is logged into Nous, surface a marker on providers
|
||||
# whose access is included in their subscription so it's visually
|
||||
# obvious which options cost extra vs. cost nothing on top of Nous.
|
||||
try:
|
||||
_nous_logged_in = bool(
|
||||
get_nous_subscription_features(config).nous_auth_present
|
||||
)
|
||||
except Exception:
|
||||
_nous_logged_in = False
|
||||
|
||||
provider_choices = []
|
||||
for p in providers:
|
||||
badge = f" [{p['badge']}]" if p.get("badge") else ""
|
||||
@@ -1948,15 +1938,7 @@ def _configure_tool_category(ts_key: str, cat: dict, config: dict):
|
||||
configured = ""
|
||||
else:
|
||||
configured = " [configured]"
|
||||
# Highlight Nous-managed entries when the user has Portal auth.
|
||||
# curses_radiolist can't render ANSI inside item strings, so we
|
||||
# use a plain unicode star + parenthetical phrase. Suppressed
|
||||
# when no Portal auth is present so non-subscribers see the
|
||||
# picker unchanged.
|
||||
sub_marker = ""
|
||||
if _nous_logged_in and p.get("managed_nous_feature"):
|
||||
sub_marker = " ★ Included with your Nous subscription"
|
||||
provider_choices.append(f"{p['name']}{badge}{tag}{configured}{sub_marker}")
|
||||
provider_choices.append(f"{p['name']}{badge}{tag}{configured}")
|
||||
|
||||
# Add skip option
|
||||
provider_choices.append("Skip — keep defaults / configure later")
|
||||
@@ -2423,30 +2405,6 @@ def _configure_provider(provider: dict, config: dict):
|
||||
|
||||
# Prompt for each required env var
|
||||
all_configured = True
|
||||
# If this BYOK provider lives in a category that ALSO has a
|
||||
# Nous-managed sibling, show a single dim hint so users know
|
||||
# they can avoid the key entirely via a Portal subscription.
|
||||
# Suppressed when the user is already authed to Nous.
|
||||
_show_portal_hint = False
|
||||
if env_vars and not managed_feature and not provider.get("requires_nous_auth"):
|
||||
try:
|
||||
_has_managed_sibling = False
|
||||
for _cat_key, _cat in TOOL_CATEGORIES.items():
|
||||
_providers = _cat.get("providers", [])
|
||||
if provider in _providers and any(
|
||||
sib.get("managed_nous_feature") for sib in _providers
|
||||
):
|
||||
_has_managed_sibling = True
|
||||
break
|
||||
if _has_managed_sibling:
|
||||
_features = get_nous_subscription_features(config)
|
||||
_show_portal_hint = not _features.nous_auth_present
|
||||
except Exception:
|
||||
_show_portal_hint = False
|
||||
|
||||
if _show_portal_hint:
|
||||
_print_info(" Available through Nous Portal subscription.")
|
||||
|
||||
for var in env_vars:
|
||||
existing = get_env_value(var["key"])
|
||||
if existing:
|
||||
|
||||
+14
-38
@@ -119,6 +119,7 @@ _PUBLIC_API_PATHS: frozenset = frozenset({
|
||||
"/api/model/info",
|
||||
"/api/dashboard/themes",
|
||||
"/api/dashboard/plugins",
|
||||
"/api/dashboard/plugins/rescan",
|
||||
})
|
||||
|
||||
|
||||
@@ -3295,49 +3296,24 @@ _VALID_CHANNEL_RE = re.compile(r"^[A-Za-z0-9._-]{1,128}$")
|
||||
_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 clients only.
|
||||
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
|
||||
|
||||
|
||||
def _ws_host_origin_is_allowed(ws: "WebSocket") -> bool:
|
||||
"""Apply the dashboard Host/Origin guard to WebSocket upgrades.
|
||||
|
||||
FastAPI HTTP middleware does not run for WebSocket routes, so the
|
||||
DNS-rebinding Host check used for normal dashboard HTTP requests must be
|
||||
repeated here before accepting the upgrade. Browsers also send an Origin
|
||||
header on WebSocket handshakes; when present, require it to target the
|
||||
same bound dashboard host.
|
||||
"""
|
||||
bound_host = getattr(app.state, "bound_host", None)
|
||||
if not bound_host:
|
||||
return True
|
||||
|
||||
host_header = ws.headers.get("host", "")
|
||||
if not _is_accepted_host(host_header, bound_host):
|
||||
return False
|
||||
|
||||
origin = ws.headers.get("origin", "")
|
||||
if not origin:
|
||||
return True
|
||||
|
||||
parsed = urllib.parse.urlparse(origin)
|
||||
if parsed.scheme not in {"http", "https"} or not parsed.netloc:
|
||||
return False
|
||||
|
||||
return _is_accepted_host(parsed.netloc, bound_host)
|
||||
|
||||
|
||||
def _ws_request_is_allowed(ws: "WebSocket") -> bool:
|
||||
"""Return True when the WebSocket upgrade matches dashboard boundaries."""
|
||||
return _ws_host_origin_is_allowed(ws) and _ws_client_is_allowed(ws)
|
||||
|
||||
# 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
|
||||
@@ -3439,7 +3415,7 @@ async def pty_ws(ws: WebSocket) -> None:
|
||||
await ws.close(code=4401)
|
||||
return
|
||||
|
||||
if not _ws_request_is_allowed(ws):
|
||||
if not _ws_client_is_allowed(ws):
|
||||
await ws.close(code=4403)
|
||||
return
|
||||
|
||||
@@ -3558,7 +3534,7 @@ async def gateway_ws(ws: WebSocket) -> None:
|
||||
await ws.close(code=4401)
|
||||
return
|
||||
|
||||
if not _ws_request_is_allowed(ws):
|
||||
if not _ws_client_is_allowed(ws):
|
||||
await ws.close(code=4403)
|
||||
return
|
||||
|
||||
@@ -3590,7 +3566,7 @@ async def pub_ws(ws: WebSocket) -> None:
|
||||
await ws.close(code=4401)
|
||||
return
|
||||
|
||||
if not _ws_request_is_allowed(ws):
|
||||
if not _ws_client_is_allowed(ws):
|
||||
await ws.close(code=4403)
|
||||
return
|
||||
|
||||
@@ -3619,7 +3595,7 @@ async def events_ws(ws: WebSocket) -> None:
|
||||
await ws.close(code=4401)
|
||||
return
|
||||
|
||||
if not _ws_request_is_allowed(ws):
|
||||
if not _ws_client_is_allowed(ws):
|
||||
await ws.close(code=4403)
|
||||
return
|
||||
|
||||
|
||||
+5
-29
@@ -11,10 +11,8 @@ hot-reloaded by the webhook adapter without a gateway restart.
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import secrets
|
||||
import tempfile
|
||||
import time
|
||||
from pathlib import Path
|
||||
from typing import Dict
|
||||
@@ -25,7 +23,6 @@ from hermes_cli.config import cfg_get
|
||||
|
||||
|
||||
_SUBSCRIPTIONS_FILENAME = "webhook_subscriptions.json"
|
||||
_SUBSCRIPTIONS_FILE_MODE = 0o600
|
||||
|
||||
|
||||
def _hermes_home() -> Path:
|
||||
@@ -51,33 +48,12 @@ def _load_subscriptions() -> Dict[str, dict]:
|
||||
def _save_subscriptions(subs: Dict[str, dict]) -> None:
|
||||
path = _subscriptions_path()
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
# webhook_subscriptions.json contains per-route HMAC secrets — write
|
||||
# via tempfile + chmod 0o600 before the atomic rename so a permissive
|
||||
# umask cannot leave the secrets readable to other local users in the
|
||||
# window between create and rename.
|
||||
fd, tmp_name = tempfile.mkstemp(
|
||||
prefix=f".{path.name}.",
|
||||
suffix=".tmp",
|
||||
dir=path.parent,
|
||||
text=True,
|
||||
tmp_path = path.with_suffix(".tmp")
|
||||
tmp_path.write_text(
|
||||
json.dumps(subs, indent=2, ensure_ascii=False),
|
||||
encoding="utf-8",
|
||||
)
|
||||
tmp_path = Path(tmp_name)
|
||||
try:
|
||||
with os.fdopen(fd, "w", encoding="utf-8") as fh:
|
||||
json.dump(subs, fh, indent=2, ensure_ascii=False)
|
||||
fh.flush()
|
||||
os.fsync(fh.fileno())
|
||||
os.chmod(tmp_path, _SUBSCRIPTIONS_FILE_MODE)
|
||||
atomic_replace(tmp_path, path)
|
||||
# Re-assert after rename in case the destination existed with a
|
||||
# broader mode and atomic_replace preserved it.
|
||||
os.chmod(path, _SUBSCRIPTIONS_FILE_MODE)
|
||||
except Exception:
|
||||
try:
|
||||
tmp_path.unlink(missing_ok=True)
|
||||
except OSError:
|
||||
pass
|
||||
raise
|
||||
atomic_replace(tmp_path, path)
|
||||
|
||||
|
||||
def _get_webhook_config() -> dict:
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 1.1 MiB |
@@ -222,12 +222,9 @@ gateway:
|
||||
no_named_sessions: "Geen benoemde sessies gevind nie.\nGebruik `/title My Sessie` om jou huidige sessie 'n naam te gee, en dan `/resume My Sessie` om later daarheen terug te keer."
|
||||
list_header: "📋 **Benoemde Sessies**\n"
|
||||
list_item: "• **{title}**{preview_part}"
|
||||
list_item_numbered: "{index}. **{title}**{preview_part}"
|
||||
list_preview_suffix: " — _{preview}_"
|
||||
list_footer: "\nGebruik: `/resume <session name>`"
|
||||
list_footer_numbered: "\nGebruik: `/resume <sessienaam>` of `/resume <nommer>` (bv. `/resume 1` vir die mees onlangse)"
|
||||
list_failed: "Kon nie sessies lys nie: {error}"
|
||||
out_of_range: "Hervat-indeks {index} is buite bereik.\nGebruik `/resume` sonder argumente om beskikbare sessies te sien."
|
||||
not_found: "Geen sessie gevind wat by '**{name}**' pas nie.\nGebruik `/resume` sonder argumente om beskikbare sessies te sien."
|
||||
already_on: "📌 Reeds op sessie **{name}**."
|
||||
switch_failed: "Kon nie sessie verander nie."
|
||||
|
||||
@@ -222,12 +222,9 @@ gateway:
|
||||
no_named_sessions: "Keine benannten Sitzungen gefunden.\nVerwenden Sie `/title Meine Sitzung`, um die aktuelle Sitzung zu benennen, dann `/resume Meine Sitzung`, um später dorthin zurückzukehren."
|
||||
list_header: "📋 **Benannte Sitzungen**\n"
|
||||
list_item: "• **{title}**{preview_part}"
|
||||
list_item_numbered: "{index}. **{title}**{preview_part}"
|
||||
list_preview_suffix: " — _{preview}_"
|
||||
list_footer: "\nVerwendung: `/resume <Sitzungsname>`"
|
||||
list_footer_numbered: "\nVerwendung: `/resume <Sitzungsname>` oder `/resume <Nummer>` (z. B. `/resume 1` für die zuletzt verwendete)"
|
||||
list_failed: "Sitzungen konnten nicht aufgelistet werden: {error}"
|
||||
out_of_range: "Wiederaufnahme-Index {index} liegt außerhalb des gültigen Bereichs.\nVerwenden Sie `/resume` ohne Argumente, um verfügbare Sitzungen anzuzeigen."
|
||||
not_found: "Keine Sitzung passend zu '**{name}**' gefunden.\nVerwenden Sie `/resume` ohne Argumente, um verfügbare Sitzungen zu sehen."
|
||||
already_on: "📌 Bereits in Sitzung **{name}**."
|
||||
switch_failed: "Sitzungswechsel fehlgeschlagen."
|
||||
|
||||
@@ -237,12 +237,9 @@ gateway:
|
||||
no_named_sessions: "No named sessions found.\nUse `/title My Session` to name your current session, then `/resume My Session` to return to it later."
|
||||
list_header: "📋 **Named Sessions**\n"
|
||||
list_item: "• **{title}**{preview_part}"
|
||||
list_item_numbered: "{index}. **{title}**{preview_part}"
|
||||
list_preview_suffix: " — _{preview}_"
|
||||
list_footer: "\nUsage: `/resume <session name>`"
|
||||
list_footer_numbered: "\nUsage: `/resume <session name>` or `/resume <number>` (e.g. `/resume 1` for the most recent)"
|
||||
list_failed: "Could not list sessions: {error}"
|
||||
out_of_range: "Resume index {index} is out of range.\nUse `/resume` with no arguments to see available sessions."
|
||||
not_found: "No session found matching '**{name}**'.\nUse `/resume` with no arguments to see available sessions."
|
||||
already_on: "📌 Already on session **{name}**."
|
||||
switch_failed: "Failed to switch session."
|
||||
|
||||
@@ -222,12 +222,9 @@ gateway:
|
||||
no_named_sessions: "No se encontraron sesiones con nombre.\nUsa `/title Mi sesión` para nombrar la sesión actual y luego `/resume Mi sesión` para volver a ella."
|
||||
list_header: "📋 **Sesiones con nombre**\n"
|
||||
list_item: "• **{title}**{preview_part}"
|
||||
list_item_numbered: "{index}. **{title}**{preview_part}"
|
||||
list_preview_suffix: " — _{preview}_"
|
||||
list_footer: "\nUso: `/resume <nombre de sesión>`"
|
||||
list_footer_numbered: "\nUso: `/resume <nombre de sesión>` o `/resume <número>` (p. ej. `/resume 1` para la más reciente)"
|
||||
list_failed: "No se pudieron listar las sesiones: {error}"
|
||||
out_of_range: "El índice de reanudación {index} está fuera de rango.\nUsa `/resume` sin argumentos para ver las sesiones disponibles."
|
||||
not_found: "No se encontró ninguna sesión que coincida con '**{name}**'.\nUsa `/resume` sin argumentos para ver las sesiones disponibles."
|
||||
already_on: "📌 Ya estás en la sesión **{name}**."
|
||||
switch_failed: "No se pudo cambiar de sesión."
|
||||
|
||||
@@ -222,12 +222,9 @@ gateway:
|
||||
no_named_sessions: "Aucune session nommée trouvée.\nUtilisez `/title Ma session` pour nommer la session actuelle, puis `/resume Ma session` pour y revenir plus tard."
|
||||
list_header: "📋 **Sessions nommées**\n"
|
||||
list_item: "• **{title}**{preview_part}"
|
||||
list_item_numbered: "{index}. **{title}**{preview_part}"
|
||||
list_preview_suffix: " — _{preview}_"
|
||||
list_footer: "\nUsage : `/resume <nom de session>`"
|
||||
list_footer_numbered: "\nUtilisation : `/resume <nom de session>` ou `/resume <numéro>` (par exemple `/resume 1` pour la plus récente)"
|
||||
list_failed: "Impossible de lister les sessions : {error}"
|
||||
out_of_range: "L'index de reprise {index} est hors limites.\nUtilisez `/resume` sans arguments pour voir les sessions disponibles."
|
||||
not_found: "Aucune session correspondant à '**{name}**' trouvée.\nUtilisez `/resume` sans argument pour voir les sessions disponibles."
|
||||
already_on: "📌 Déjà sur la session **{name}**."
|
||||
switch_failed: "Échec du changement de session."
|
||||
|
||||
@@ -226,12 +226,9 @@ gateway:
|
||||
no_named_sessions: "Níor aimsíodh aon seisiún ainmnithe.\nÚsáid `/title M'Ainm Seisiúin` chun do sheisiún reatha a ainmniú, ansin `/resume M'Ainm Seisiúin` chun filleadh air níos déanaí."
|
||||
list_header: "📋 **Seisiúin Ainmnithe**\n"
|
||||
list_item: "• **{title}**{preview_part}"
|
||||
list_item_numbered: "{index}. **{title}**{preview_part}"
|
||||
list_preview_suffix: " — _{preview}_"
|
||||
list_footer: "\nÚsáid: `/resume <session name>`"
|
||||
list_footer_numbered: "\nÚsáid: `/resume <ainm seisiúin>` nó `/resume <uimhir>` (m.sh. `/resume 1` don cheann is déanaí)"
|
||||
list_failed: "Níorbh fhéidir seisiúin a liostáil: {error}"
|
||||
out_of_range: "Tá an t-innéacs atosaithe {index} as raon.\nÚsáid `/resume` gan argóintí chun na seisiúin atá ar fáil a fheiceáil."
|
||||
not_found: "Níor aimsíodh aon seisiún ag teacht le '**{name}**'.\nÚsáid `/resume` gan argóintí chun seisiúin atá ar fáil a fheiceáil."
|
||||
already_on: "📌 Cheana ar an seisiún **{name}**."
|
||||
switch_failed: "Theip ar athrú seisiúin."
|
||||
|
||||
@@ -222,12 +222,9 @@ gateway:
|
||||
no_named_sessions: "Nem található elnevezett munkamenet.\nHasználd a `/title Saját munkamenet` parancsot a jelenlegi munkamenet elnevezéséhez, majd a `/resume Saját munkamenet` paranccsal térhetsz vissza hozzá."
|
||||
list_header: "📋 **Elnevezett munkamenetek**\n"
|
||||
list_item: "• **{title}**{preview_part}"
|
||||
list_item_numbered: "{index}. **{title}**{preview_part}"
|
||||
list_preview_suffix: " — _{preview}_"
|
||||
list_footer: "\nHasználat: `/resume <munkamenet neve>`"
|
||||
list_footer_numbered: "\nHasználat: `/resume <munkamenet neve>` vagy `/resume <szám>` (pl. `/resume 1` a legutóbbihoz)"
|
||||
list_failed: "Nem sikerült listázni a munkameneteket: {error}"
|
||||
out_of_range: "A folytatási index ({index}) tartományon kívül esik.\nA `/resume` argumentumok nélküli használata megjeleníti az elérhető munkameneteket."
|
||||
not_found: "Nem található '**{name}**' nevű munkamenet.\nArgumentumok nélkül használd a `/resume` parancsot az elérhető munkamenetek megtekintéséhez."
|
||||
already_on: "📌 Már a **{name}** munkamenetben vagy."
|
||||
switch_failed: "Nem sikerült munkamenetet váltani."
|
||||
|
||||
@@ -222,12 +222,9 @@ gateway:
|
||||
no_named_sessions: "Nessuna sessione con nome trovata.\nUsa `/title My Session` per dare un nome alla sessione attuale, poi `/resume My Session` per tornare a essa in seguito."
|
||||
list_header: "📋 **Sessioni con nome**\n"
|
||||
list_item: "• **{title}**{preview_part}"
|
||||
list_item_numbered: "{index}. **{title}**{preview_part}"
|
||||
list_preview_suffix: " — _{preview}_"
|
||||
list_footer: "\nUso: `/resume <session name>`"
|
||||
list_footer_numbered: "\nUso: `/resume <nome sessione>` o `/resume <numero>` (es. `/resume 1` per la più recente)"
|
||||
list_failed: "Impossibile elencare le sessioni: {error}"
|
||||
out_of_range: "L'indice di ripresa {index} è fuori intervallo.\nUsa `/resume` senza argomenti per vedere le sessioni disponibili."
|
||||
not_found: "Nessuna sessione trovata corrispondente a '**{name}**'.\nUsa `/resume` senza argomenti per vedere le sessioni disponibili."
|
||||
already_on: "📌 Già nella sessione **{name}**."
|
||||
switch_failed: "Cambio di sessione non riuscito."
|
||||
|
||||
@@ -222,12 +222,9 @@ gateway:
|
||||
no_named_sessions: "名前付きセッションが見つかりません。\n`/title セッション名` で現在のセッションに名前を付けると、後で `/resume セッション名` で戻れます。"
|
||||
list_header: "📋 **名前付きセッション**\n"
|
||||
list_item: "• **{title}**{preview_part}"
|
||||
list_item_numbered: "{index}. **{title}**{preview_part}"
|
||||
list_preview_suffix: " — _{preview}_"
|
||||
list_footer: "\n使い方: `/resume <セッション名>`"
|
||||
list_footer_numbered: "\n使い方: `/resume <セッション名>` または `/resume <番号>`（例: 最新のセッションには `/resume 1`）"
|
||||
list_failed: "セッションを一覧表示できませんでした: {error}"
|
||||
out_of_range: "再開インデックス {index} は範囲外です。\n引数なしで `/resume` を実行すると、利用可能なセッションが表示されます。"
|
||||
not_found: "'**{name}**' に一致するセッションが見つかりません。\n引数なしで `/resume` を実行すると利用可能なセッションを表示します。"
|
||||
already_on: "📌 既にセッション **{name}** にいます。"
|
||||
switch_failed: "セッションの切り替えに失敗しました。"
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user