Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Teknium
|
b52672c3da |
@@ -1,192 +0,0 @@
|
||||
name: Supply Chain Audit
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
types: [opened, synchronize, reopened]
|
||||
|
||||
permissions:
|
||||
pull-requests: write
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
scan:
|
||||
name: Scan PR for supply chain risks
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Scan diff for suspicious patterns
|
||||
id: scan
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
BASE="${{ github.event.pull_request.base.sha }}"
|
||||
HEAD="${{ github.event.pull_request.head.sha }}"
|
||||
|
||||
# Get the full diff (added lines only)
|
||||
DIFF=$(git diff "$BASE".."$HEAD" -- . ':!uv.lock' ':!*.lock' ':!package-lock.json' ':!yarn.lock' || true)
|
||||
|
||||
FINDINGS=""
|
||||
CRITICAL=false
|
||||
|
||||
# --- .pth files (auto-execute on Python startup) ---
|
||||
PTH_FILES=$(git diff --name-only "$BASE".."$HEAD" | grep '\.pth$' || true)
|
||||
if [ -n "$PTH_FILES" ]; then
|
||||
CRITICAL=true
|
||||
FINDINGS="${FINDINGS}
|
||||
### 🚨 CRITICAL: .pth file added or modified
|
||||
Python \`.pth\` files in \`site-packages/\` execute automatically when the interpreter starts — no import required. This is the exact mechanism used in the [litellm supply chain attack](https://github.com/BerriAI/litellm/issues/24512).
|
||||
|
||||
**Files:**
|
||||
\`\`\`
|
||||
${PTH_FILES}
|
||||
\`\`\`
|
||||
"
|
||||
fi
|
||||
|
||||
# --- base64 + exec/eval combo (the litellm attack pattern) ---
|
||||
B64_EXEC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'base64\.(b64decode|decodebytes|urlsafe_b64decode)' | grep -iE 'exec\(|eval\(' | head -10 || true)
|
||||
if [ -n "$B64_EXEC_HITS" ]; then
|
||||
CRITICAL=true
|
||||
FINDINGS="${FINDINGS}
|
||||
### 🚨 CRITICAL: base64 decode + exec/eval combo
|
||||
This is the exact pattern used in the [litellm supply chain attack](https://github.com/BerriAI/litellm/issues/24512) — base64-decoded strings passed to exec/eval to hide credential-stealing payloads.
|
||||
|
||||
**Matches:**
|
||||
\`\`\`
|
||||
${B64_EXEC_HITS}
|
||||
\`\`\`
|
||||
"
|
||||
fi
|
||||
|
||||
# --- base64 decode/encode (alone — legitimate uses exist) ---
|
||||
B64_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'base64\.(b64decode|b64encode|decodebytes|encodebytes|urlsafe_b64decode)|atob\(|btoa\(|Buffer\.from\(.*base64' | head -20 || true)
|
||||
if [ -n "$B64_HITS" ]; then
|
||||
FINDINGS="${FINDINGS}
|
||||
### ⚠️ WARNING: base64 encoding/decoding detected
|
||||
Base64 has legitimate uses (images, JWT, etc.) but is also commonly used to obfuscate malicious payloads. Verify the usage is appropriate.
|
||||
|
||||
**Matches (first 20):**
|
||||
\`\`\`
|
||||
${B64_HITS}
|
||||
\`\`\`
|
||||
"
|
||||
fi
|
||||
|
||||
# --- exec/eval with string arguments ---
|
||||
EXEC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -E '(exec|eval)\s*\(' | grep -v '^\+\s*#' | grep -v 'test_\|mock\|assert\|# ' | head -20 || true)
|
||||
if [ -n "$EXEC_HITS" ]; then
|
||||
FINDINGS="${FINDINGS}
|
||||
### ⚠️ WARNING: exec() or eval() usage
|
||||
Dynamic code execution can hide malicious behavior, especially when combined with base64 or network fetches.
|
||||
|
||||
**Matches (first 20):**
|
||||
\`\`\`
|
||||
${EXEC_HITS}
|
||||
\`\`\`
|
||||
"
|
||||
fi
|
||||
|
||||
# --- subprocess with encoded/obfuscated commands ---
|
||||
PROC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -E 'subprocess\.(Popen|call|run)\s*\(' | grep -iE 'base64|decode|encode|\\x|chr\(' | head -10 || true)
|
||||
if [ -n "$PROC_HITS" ]; then
|
||||
CRITICAL=true
|
||||
FINDINGS="${FINDINGS}
|
||||
### 🚨 CRITICAL: subprocess with encoded/obfuscated command
|
||||
Subprocess calls with encoded arguments are a strong indicator of payload execution.
|
||||
|
||||
**Matches:**
|
||||
\`\`\`
|
||||
${PROC_HITS}
|
||||
\`\`\`
|
||||
"
|
||||
fi
|
||||
|
||||
# --- Network calls to non-standard domains ---
|
||||
EXFIL_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'requests\.(post|put)\(|httpx\.(post|put)\(|urllib\.request\.urlopen' | grep -v '^\+\s*#' | grep -v 'test_\|mock\|assert' | head -10 || true)
|
||||
if [ -n "$EXFIL_HITS" ]; then
|
||||
FINDINGS="${FINDINGS}
|
||||
### ⚠️ WARNING: Outbound network calls (POST/PUT)
|
||||
Outbound POST/PUT requests in new code could be data exfiltration. Verify the destination URLs are legitimate.
|
||||
|
||||
**Matches (first 10):**
|
||||
\`\`\`
|
||||
${EXFIL_HITS}
|
||||
\`\`\`
|
||||
"
|
||||
fi
|
||||
|
||||
# --- setup.py / setup.cfg install hooks ---
|
||||
SETUP_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -E '(setup\.py|setup\.cfg|__init__\.pth|sitecustomize\.py|usercustomize\.py)$' || true)
|
||||
if [ -n "$SETUP_HITS" ]; then
|
||||
FINDINGS="${FINDINGS}
|
||||
### ⚠️ WARNING: Install hook files modified
|
||||
These files can execute code during package installation or interpreter startup.
|
||||
|
||||
**Files:**
|
||||
\`\`\`
|
||||
${SETUP_HITS}
|
||||
\`\`\`
|
||||
"
|
||||
fi
|
||||
|
||||
# --- Compile/marshal/pickle (code object injection) ---
|
||||
MARSHAL_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'marshal\.loads|pickle\.loads|compile\(' | grep -v '^\+\s*#' | grep -v 'test_\|re\.compile\|ast\.compile' | head -10 || true)
|
||||
if [ -n "$MARSHAL_HITS" ]; then
|
||||
FINDINGS="${FINDINGS}
|
||||
### ⚠️ WARNING: marshal/pickle/compile usage
|
||||
These can deserialize or construct executable code objects.
|
||||
|
||||
**Matches:**
|
||||
\`\`\`
|
||||
${MARSHAL_HITS}
|
||||
\`\`\`
|
||||
"
|
||||
fi
|
||||
|
||||
# --- Output results ---
|
||||
if [ -n "$FINDINGS" ]; then
|
||||
echo "found=true" >> "$GITHUB_OUTPUT"
|
||||
if [ "$CRITICAL" = true ]; then
|
||||
echo "critical=true" >> "$GITHUB_OUTPUT"
|
||||
else
|
||||
echo "critical=false" >> "$GITHUB_OUTPUT"
|
||||
fi
|
||||
# Write findings to a file (multiline env vars are fragile)
|
||||
echo "$FINDINGS" > /tmp/findings.md
|
||||
else
|
||||
echo "found=false" >> "$GITHUB_OUTPUT"
|
||||
echo "critical=false" >> "$GITHUB_OUTPUT"
|
||||
fi
|
||||
|
||||
- name: Post warning comment
|
||||
if: steps.scan.outputs.found == 'true'
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
run: |
|
||||
SEVERITY="⚠️ Supply Chain Risk Detected"
|
||||
if [ "${{ steps.scan.outputs.critical }}" = "true" ]; then
|
||||
SEVERITY="🚨 CRITICAL Supply Chain Risk Detected"
|
||||
fi
|
||||
|
||||
BODY="## ${SEVERITY}
|
||||
|
||||
This PR contains patterns commonly associated with supply chain attacks. This does **not** mean the PR is malicious — but these patterns require careful human review before merging.
|
||||
|
||||
$(cat /tmp/findings.md)
|
||||
|
||||
---
|
||||
*Automated scan triggered by [supply-chain-audit](/.github/workflows/supply-chain-audit.yml). If this is a false positive, a maintainer can approve after manual review.*"
|
||||
|
||||
gh pr comment "${{ github.event.pull_request.number }}" --body "$BODY"
|
||||
|
||||
- name: Fail on critical findings
|
||||
if: steps.scan.outputs.critical == 'true'
|
||||
run: |
|
||||
echo "::error::CRITICAL supply chain risk patterns detected in this PR. See the PR comment for details."
|
||||
exit 1
|
||||
@@ -53,4 +53,3 @@ environments/benchmarks/evals/
|
||||
|
||||
# Release script temp files
|
||||
.release_notes.md
|
||||
mini-swe-agent/
|
||||
|
||||
@@ -1,3 +1,6 @@
|
||||
[submodule "mini-swe-agent"]
|
||||
path = mini-swe-agent
|
||||
url = https://github.com/SWE-agent/mini-swe-agent
|
||||
[submodule "tinker-atropos"]
|
||||
path = tinker-atropos
|
||||
url = https://github.com/nousresearch/tinker-atropos
|
||||
|
||||
@@ -38,7 +38,6 @@ hermes-agent/
|
||||
│ ├── tools_config.py # `hermes tools` — enable/disable tools per platform
|
||||
│ ├── skills_hub.py # `/skills` slash command (search, browse, install)
|
||||
│ ├── models.py # Model catalog, provider model lists
|
||||
│ ├── model_switch.py # Shared /model switch pipeline (CLI + gateway)
|
||||
│ └── auth.py # Provider credential resolution
|
||||
├── tools/ # Tool implementations (one file per tool)
|
||||
│ ├── registry.py # Central tool registry (schemas, handlers, dispatch)
|
||||
|
||||
+2
-3
@@ -72,9 +72,8 @@ export VIRTUAL_ENV="$(pwd)/venv"
|
||||
|
||||
# Install with all extras (messaging, cron, CLI menus, dev tools)
|
||||
uv pip install -e ".[all,dev]"
|
||||
|
||||
# Optional: RL training submodule
|
||||
# git submodule update --init tinker-atropos && uv pip install -e "./tinker-atropos"
|
||||
uv pip install -e "./mini-swe-agent"
|
||||
uv pip install -e "./tinker-atropos"
|
||||
|
||||
# Optional: browser tools
|
||||
npm install
|
||||
|
||||
@@ -144,14 +144,16 @@ Quick start for contributors:
|
||||
```bash
|
||||
git clone https://github.com/NousResearch/hermes-agent.git
|
||||
cd hermes-agent
|
||||
git submodule update --init mini-swe-agent # required terminal backend
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
uv venv venv --python 3.11
|
||||
source venv/bin/activate
|
||||
uv pip install -e ".[all,dev]"
|
||||
uv pip install -e "./mini-swe-agent"
|
||||
python -m pytest tests/ -q
|
||||
```
|
||||
|
||||
> **RL Training (optional):** To work on the RL/Tinker-Atropos integration:
|
||||
> **RL Training (optional):** To work on the RL/Tinker-Atropos integration, also run:
|
||||
> ```bash
|
||||
> git submodule update --init tinker-atropos
|
||||
> uv pip install -e "./tinker-atropos"
|
||||
|
||||
@@ -1,400 +0,0 @@
|
||||
# Hermes Agent v0.4.0 (v2026.3.23)
|
||||
|
||||
**Release Date:** March 23, 2026
|
||||
|
||||
> The platform expansion release — OpenAI-compatible API server, 6 new messaging adapters, 4 new inference providers, MCP server management with OAuth 2.1, @ context references, gateway prompt caching, streaming enabled by default, and a sweeping reliability pass with 200+ bug fixes.
|
||||
|
||||
---
|
||||
|
||||
## ✨ Highlights
|
||||
|
||||
- **OpenAI-compatible API server** — Expose Hermes as an `/v1/chat/completions` endpoint with a new `/api/jobs` REST API for cron job management, hardened with input limits, field whitelists, SQLite-backed response persistence, and CORS origin protection ([#1756](https://github.com/NousResearch/hermes-agent/pull/1756), [#2450](https://github.com/NousResearch/hermes-agent/pull/2450), [#2456](https://github.com/NousResearch/hermes-agent/pull/2456), [#2451](https://github.com/NousResearch/hermes-agent/pull/2451), [#2472](https://github.com/NousResearch/hermes-agent/pull/2472))
|
||||
|
||||
- **6 new messaging platform adapters** — Signal, DingTalk, SMS (Twilio), Mattermost, Matrix, and Webhook adapters join Telegram, Discord, and WhatsApp. Gateway auto-reconnects failed platforms with exponential backoff ([#2206](https://github.com/NousResearch/hermes-agent/pull/2206), [#1685](https://github.com/NousResearch/hermes-agent/pull/1685), [#1688](https://github.com/NousResearch/hermes-agent/pull/1688), [#1683](https://github.com/NousResearch/hermes-agent/pull/1683), [#2166](https://github.com/NousResearch/hermes-agent/pull/2166), [#2584](https://github.com/NousResearch/hermes-agent/pull/2584))
|
||||
|
||||
- **@ context references** — Claude Code-style `@file` and `@url` context injection with tab completions in the CLI ([#2343](https://github.com/NousResearch/hermes-agent/pull/2343), [#2482](https://github.com/NousResearch/hermes-agent/pull/2482))
|
||||
|
||||
- **4 new inference providers** — GitHub Copilot (OAuth + token validation), Alibaba Cloud / DashScope, Kilo Code, and OpenCode Zen/Go ([#1924](https://github.com/NousResearch/hermes-agent/pull/1924), [#1879](https://github.com/NousResearch/hermes-agent/pull/1879) by @mchzimm, [#1673](https://github.com/NousResearch/hermes-agent/pull/1673), [#1666](https://github.com/NousResearch/hermes-agent/pull/1666), [#1650](https://github.com/NousResearch/hermes-agent/pull/1650))
|
||||
|
||||
- **MCP server management CLI** — `hermes mcp` commands for installing, configuring, and authenticating MCP servers with full OAuth 2.1 PKCE flow ([#2465](https://github.com/NousResearch/hermes-agent/pull/2465))
|
||||
|
||||
- **Gateway prompt caching** — Cache AIAgent instances per session, preserving Anthropic prompt cache across turns for dramatic cost reduction on long conversations ([#2282](https://github.com/NousResearch/hermes-agent/pull/2282), [#2284](https://github.com/NousResearch/hermes-agent/pull/2284), [#2361](https://github.com/NousResearch/hermes-agent/pull/2361))
|
||||
|
||||
- **Context compression overhaul** — Structured summaries with iterative updates, token-budget tail protection, configurable summary endpoint, and fallback model support ([#2323](https://github.com/NousResearch/hermes-agent/pull/2323), [#1727](https://github.com/NousResearch/hermes-agent/pull/1727), [#2224](https://github.com/NousResearch/hermes-agent/pull/2224))
|
||||
|
||||
- **Streaming enabled by default** — CLI streaming on by default with proper spinner/tool progress display during streaming mode, plus extensive linebreak and concatenation fixes ([#2340](https://github.com/NousResearch/hermes-agent/pull/2340), [#2161](https://github.com/NousResearch/hermes-agent/pull/2161), [#2258](https://github.com/NousResearch/hermes-agent/pull/2258))
|
||||
|
||||
---
|
||||
|
||||
## 🖥️ CLI & User Experience
|
||||
|
||||
### New Commands & Interactions
|
||||
- **@ context completions** — Tab-completable `@file`/`@url` references that inject file content or web pages into the conversation ([#2482](https://github.com/NousResearch/hermes-agent/pull/2482), [#2343](https://github.com/NousResearch/hermes-agent/pull/2343))
|
||||
- **`/statusbar`** — Toggle a persistent config bar showing model + provider info in the prompt ([#2240](https://github.com/NousResearch/hermes-agent/pull/2240), [#1917](https://github.com/NousResearch/hermes-agent/pull/1917))
|
||||
- **`/queue`** — Queue prompts for the agent without interrupting the current run ([#2191](https://github.com/NousResearch/hermes-agent/pull/2191), [#2469](https://github.com/NousResearch/hermes-agent/pull/2469))
|
||||
- **`/permission`** — Switch approval mode dynamically during a session ([#2207](https://github.com/NousResearch/hermes-agent/pull/2207))
|
||||
- **`/browser`** — Interactive browser sessions from the CLI ([#2273](https://github.com/NousResearch/hermes-agent/pull/2273), [#1814](https://github.com/NousResearch/hermes-agent/pull/1814))
|
||||
- **`/cost`** — Live pricing and usage tracking in gateway mode ([#2180](https://github.com/NousResearch/hermes-agent/pull/2180))
|
||||
- **`/approve` and `/deny`** — Replaced bare text approval in gateway with explicit commands ([#2002](https://github.com/NousResearch/hermes-agent/pull/2002))
|
||||
|
||||
### Streaming & Display
|
||||
- Streaming enabled by default in CLI ([#2340](https://github.com/NousResearch/hermes-agent/pull/2340))
|
||||
- Show spinners and tool progress during streaming mode ([#2161](https://github.com/NousResearch/hermes-agent/pull/2161))
|
||||
- Show reasoning/thinking blocks when `show_reasoning` enabled ([#2118](https://github.com/NousResearch/hermes-agent/pull/2118))
|
||||
- Context pressure warnings for CLI and gateway ([#2159](https://github.com/NousResearch/hermes-agent/pull/2159))
|
||||
- Fix: streaming chunks concatenated without whitespace ([#2258](https://github.com/NousResearch/hermes-agent/pull/2258))
|
||||
- Fix: iteration boundary linebreak prevents stream concatenation ([#2413](https://github.com/NousResearch/hermes-agent/pull/2413))
|
||||
- Fix: defer streaming linebreak to prevent blank line stacking ([#2473](https://github.com/NousResearch/hermes-agent/pull/2473))
|
||||
- Fix: suppress spinner animation in non-TTY environments ([#2216](https://github.com/NousResearch/hermes-agent/pull/2216))
|
||||
- Fix: display provider and endpoint in API error messages ([#2266](https://github.com/NousResearch/hermes-agent/pull/2266))
|
||||
- Fix: resolve garbled ANSI escape codes in status printouts ([#2448](https://github.com/NousResearch/hermes-agent/pull/2448))
|
||||
- Fix: update gold ANSI color to true-color format ([#2246](https://github.com/NousResearch/hermes-agent/pull/2246))
|
||||
- Fix: normalize toolset labels and use skin colors in banner ([#1912](https://github.com/NousResearch/hermes-agent/pull/1912))
|
||||
|
||||
### CLI Polish
|
||||
- Fix: prevent 'Press ENTER to continue...' on exit ([#2555](https://github.com/NousResearch/hermes-agent/pull/2555))
|
||||
- Fix: flush stdout during agent loop to prevent macOS display freeze ([#1654](https://github.com/NousResearch/hermes-agent/pull/1654))
|
||||
- Fix: show human-readable error when `hermes setup` hits permissions error ([#2196](https://github.com/NousResearch/hermes-agent/pull/2196))
|
||||
- Fix: `/stop` command crash + UnboundLocalError in streaming media delivery ([#2463](https://github.com/NousResearch/hermes-agent/pull/2463))
|
||||
- Fix: allow custom/local endpoints without API key ([#2556](https://github.com/NousResearch/hermes-agent/pull/2556))
|
||||
- Fix: Kitty keyboard protocol Shift+Enter for Ghostty/WezTerm (attempted + reverted due to prompt_toolkit crash) ([#2345](https://github.com/NousResearch/hermes-agent/pull/2345), [#2349](https://github.com/NousResearch/hermes-agent/pull/2349))
|
||||
|
||||
### Configuration
|
||||
- **`${ENV_VAR}` substitution** in config.yaml ([#2684](https://github.com/NousResearch/hermes-agent/pull/2684))
|
||||
- **Real-time config reload** — config.yaml changes apply without restart ([#2210](https://github.com/NousResearch/hermes-agent/pull/2210))
|
||||
- **`custom_models.yaml`** for user-managed model additions ([#2214](https://github.com/NousResearch/hermes-agent/pull/2214))
|
||||
- **Priority-based context file selection** + CLAUDE.md support ([#2301](https://github.com/NousResearch/hermes-agent/pull/2301))
|
||||
- **Merge nested YAML sections** instead of replacing on config update ([#2213](https://github.com/NousResearch/hermes-agent/pull/2213))
|
||||
- Fix: config.yaml provider key overrides env var silently ([#2272](https://github.com/NousResearch/hermes-agent/pull/2272))
|
||||
- Fix: log warning instead of silently swallowing config.yaml errors ([#2683](https://github.com/NousResearch/hermes-agent/pull/2683))
|
||||
- Fix: disabled toolsets re-enable themselves after `hermes tools` ([#2268](https://github.com/NousResearch/hermes-agent/pull/2268))
|
||||
- Fix: platform default toolsets silently override tool deselection ([#2624](https://github.com/NousResearch/hermes-agent/pull/2624))
|
||||
- Fix: honor bare YAML `approvals.mode: off` ([#2620](https://github.com/NousResearch/hermes-agent/pull/2620))
|
||||
- Fix: `hermes update` use `.[all]` extras with fallback ([#1728](https://github.com/NousResearch/hermes-agent/pull/1728))
|
||||
- Fix: `hermes update` prompt before resetting working tree on stash conflicts ([#2390](https://github.com/NousResearch/hermes-agent/pull/2390))
|
||||
- Fix: use git pull --rebase in update/install to avoid divergent branch error ([#2274](https://github.com/NousResearch/hermes-agent/pull/2274))
|
||||
- Fix: add zprofile fallback and create zshrc on fresh macOS installs ([#2320](https://github.com/NousResearch/hermes-agent/pull/2320))
|
||||
- Fix: remove `ANTHROPIC_BASE_URL` env var to avoid collisions ([#1675](https://github.com/NousResearch/hermes-agent/pull/1675))
|
||||
- Fix: don't ask IMAP password if already in keyring or env ([#2212](https://github.com/NousResearch/hermes-agent/pull/2212))
|
||||
- Fix: OpenCode Zen/Go show OpenRouter models instead of their own ([#2277](https://github.com/NousResearch/hermes-agent/pull/2277))
|
||||
|
||||
---
|
||||
|
||||
## 🏗️ Core Agent & Architecture
|
||||
|
||||
### New Providers
|
||||
- **GitHub Copilot** — Full OAuth auth, API routing, token validation, and 400k context. ([#1924](https://github.com/NousResearch/hermes-agent/pull/1924), [#1896](https://github.com/NousResearch/hermes-agent/pull/1896), [#1879](https://github.com/NousResearch/hermes-agent/pull/1879) by @mchzimm, [#2507](https://github.com/NousResearch/hermes-agent/pull/2507))
|
||||
- **Alibaba Cloud / DashScope** — Full integration with DashScope v1 runtime, model dot preservation, and 401 auth fixes ([#1673](https://github.com/NousResearch/hermes-agent/pull/1673), [#2332](https://github.com/NousResearch/hermes-agent/pull/2332), [#2459](https://github.com/NousResearch/hermes-agent/pull/2459))
|
||||
- **Kilo Code** — First-class inference provider ([#1666](https://github.com/NousResearch/hermes-agent/pull/1666))
|
||||
- **OpenCode Zen and OpenCode Go** — New provider backends ([#1650](https://github.com/NousResearch/hermes-agent/pull/1650), [#2393](https://github.com/NousResearch/hermes-agent/pull/2393) by @0xbyt4)
|
||||
- **NeuTTS** — Local TTS provider backend with built-in setup flow, replacing the old optional skill ([#1657](https://github.com/NousResearch/hermes-agent/pull/1657), [#1664](https://github.com/NousResearch/hermes-agent/pull/1664))
|
||||
|
||||
### Provider Improvements
|
||||
- **Eager fallback** to backup model on rate-limit errors ([#1730](https://github.com/NousResearch/hermes-agent/pull/1730))
|
||||
- **Endpoint metadata** for custom model context and pricing; query local servers for actual context window size ([#1906](https://github.com/NousResearch/hermes-agent/pull/1906), [#2091](https://github.com/NousResearch/hermes-agent/pull/2091) by @dusterbloom)
|
||||
- **Context length detection overhaul** — models.dev integration, provider-aware resolution, fuzzy matching for custom endpoints, `/v1/props` for llama.cpp ([#2158](https://github.com/NousResearch/hermes-agent/pull/2158), [#2051](https://github.com/NousResearch/hermes-agent/pull/2051), [#2403](https://github.com/NousResearch/hermes-agent/pull/2403))
|
||||
- **Model catalog updates** — gpt-5.4-mini, gpt-5.4-nano, healer-alpha, haiku-4.5, minimax-m2.7, claude 4.6 at 1M context ([#1913](https://github.com/NousResearch/hermes-agent/pull/1913), [#1915](https://github.com/NousResearch/hermes-agent/pull/1915), [#1900](https://github.com/NousResearch/hermes-agent/pull/1900), [#2155](https://github.com/NousResearch/hermes-agent/pull/2155), [#2474](https://github.com/NousResearch/hermes-agent/pull/2474))
|
||||
- **Custom endpoint improvements** — `model.base_url` in config.yaml, `api_mode` override for responses API, allow endpoints without API key, fail fast on missing keys ([#2330](https://github.com/NousResearch/hermes-agent/pull/2330), [#1651](https://github.com/NousResearch/hermes-agent/pull/1651), [#2556](https://github.com/NousResearch/hermes-agent/pull/2556), [#2445](https://github.com/NousResearch/hermes-agent/pull/2445), [#1994](https://github.com/NousResearch/hermes-agent/pull/1994), [#1998](https://github.com/NousResearch/hermes-agent/pull/1998))
|
||||
- Inject model and provider into system prompt ([#1929](https://github.com/NousResearch/hermes-agent/pull/1929))
|
||||
- Tie `api_mode` to provider config instead of env var ([#1656](https://github.com/NousResearch/hermes-agent/pull/1656))
|
||||
- Fix: prevent Anthropic token leaking to third-party `anthropic_messages` providers ([#2389](https://github.com/NousResearch/hermes-agent/pull/2389))
|
||||
- Fix: prevent Anthropic fallback from inheriting non-Anthropic `base_url` ([#2388](https://github.com/NousResearch/hermes-agent/pull/2388))
|
||||
- Fix: `auxiliary_is_nous` flag never resets — leaked Nous tags to other providers ([#1713](https://github.com/NousResearch/hermes-agent/pull/1713))
|
||||
- Fix: Anthropic `tool_choice 'none'` still allowed tool calls ([#1714](https://github.com/NousResearch/hermes-agent/pull/1714))
|
||||
- Fix: Mistral parser nested JSON fallback extraction ([#2335](https://github.com/NousResearch/hermes-agent/pull/2335))
|
||||
- Fix: MiniMax 401 auth resolved by defaulting to `anthropic_messages` ([#2103](https://github.com/NousResearch/hermes-agent/pull/2103))
|
||||
- Fix: case-insensitive model family matching ([#2350](https://github.com/NousResearch/hermes-agent/pull/2350))
|
||||
- Fix: ignore placeholder provider keys in activation checks ([#2358](https://github.com/NousResearch/hermes-agent/pull/2358))
|
||||
- Fix: Preserve Ollama model:tag colons in context length detection ([#2149](https://github.com/NousResearch/hermes-agent/pull/2149))
|
||||
- Fix: recognize Claude Code OAuth credentials in startup gate ([#1663](https://github.com/NousResearch/hermes-agent/pull/1663))
|
||||
- Fix: detect Claude Code version dynamically for OAuth user-agent ([#1670](https://github.com/NousResearch/hermes-agent/pull/1670))
|
||||
- Fix: OAuth flag stale after refresh/fallback ([#1890](https://github.com/NousResearch/hermes-agent/pull/1890))
|
||||
- Fix: auxiliary client skips expired Codex JWT ([#2397](https://github.com/NousResearch/hermes-agent/pull/2397))
|
||||
|
||||
### Agent Loop
|
||||
- **Gateway prompt caching** — Cache AIAgent per session, keep assistant turns, fix session restore ([#2282](https://github.com/NousResearch/hermes-agent/pull/2282), [#2284](https://github.com/NousResearch/hermes-agent/pull/2284), [#2361](https://github.com/NousResearch/hermes-agent/pull/2361))
|
||||
- **Context compression overhaul** — Structured summaries, iterative updates, token-budget tail protection, configurable `summary_base_url` ([#2323](https://github.com/NousResearch/hermes-agent/pull/2323), [#1727](https://github.com/NousResearch/hermes-agent/pull/1727), [#2224](https://github.com/NousResearch/hermes-agent/pull/2224))
|
||||
- **Pre-call sanitization and post-call tool guardrails** ([#1732](https://github.com/NousResearch/hermes-agent/pull/1732))
|
||||
- **Auto-recover** from provider-rejected `tool_choice` by retrying without ([#2174](https://github.com/NousResearch/hermes-agent/pull/2174))
|
||||
- **Background memory/skill review** replaces inline nudges ([#2235](https://github.com/NousResearch/hermes-agent/pull/2235))
|
||||
- **SOUL.md as primary agent identity** instead of hardcoded default ([#1922](https://github.com/NousResearch/hermes-agent/pull/1922))
|
||||
- Fix: prevent silent tool result loss during context compression ([#1993](https://github.com/NousResearch/hermes-agent/pull/1993))
|
||||
- Fix: handle empty/null function arguments in tool call recovery ([#2163](https://github.com/NousResearch/hermes-agent/pull/2163))
|
||||
- Fix: handle API refusal responses gracefully instead of crashing ([#2156](https://github.com/NousResearch/hermes-agent/pull/2156))
|
||||
- Fix: prevent stuck agent loop on malformed tool calls ([#2114](https://github.com/NousResearch/hermes-agent/pull/2114))
|
||||
- Fix: return JSON parse error to model instead of dispatching with empty args ([#2342](https://github.com/NousResearch/hermes-agent/pull/2342))
|
||||
- Fix: consecutive assistant message merge drops content on mixed types ([#1703](https://github.com/NousResearch/hermes-agent/pull/1703))
|
||||
- Fix: message role alternation violations in JSON recovery and error handler ([#1722](https://github.com/NousResearch/hermes-agent/pull/1722))
|
||||
- Fix: `compression_attempts` resets each iteration — allowed unlimited compressions ([#1723](https://github.com/NousResearch/hermes-agent/pull/1723))
|
||||
- Fix: `length_continue_retries` never resets — later truncations got fewer retries ([#1717](https://github.com/NousResearch/hermes-agent/pull/1717))
|
||||
- Fix: compressor summary role violated consecutive-role constraint ([#1720](https://github.com/NousResearch/hermes-agent/pull/1720), [#1743](https://github.com/NousResearch/hermes-agent/pull/1743))
|
||||
- Fix: remove hardcoded `gemini-3-flash-preview` as default summary model ([#2464](https://github.com/NousResearch/hermes-agent/pull/2464))
|
||||
- Fix: correctly handle empty tool results ([#2201](https://github.com/NousResearch/hermes-agent/pull/2201))
|
||||
- Fix: crash on None entry in `tool_calls` list ([#2209](https://github.com/NousResearch/hermes-agent/pull/2209) by @0xbyt4, [#2316](https://github.com/NousResearch/hermes-agent/pull/2316))
|
||||
- Fix: per-thread persistent event loops in worker threads ([#2214](https://github.com/NousResearch/hermes-agent/pull/2214) by @jquesnelle)
|
||||
- Fix: prevent 'event loop already running' when async tools run in parallel ([#2207](https://github.com/NousResearch/hermes-agent/pull/2207))
|
||||
- Fix: strip ANSI at the source — clean terminal output before it reaches the model ([#2115](https://github.com/NousResearch/hermes-agent/pull/2115))
|
||||
- Fix: skip top-level `cache_control` on role:tool for OpenRouter ([#2391](https://github.com/NousResearch/hermes-agent/pull/2391))
|
||||
- Fix: delegate tool — save parent tool names before child construction mutates global ([#2083](https://github.com/NousResearch/hermes-agent/pull/2083) by @ygd58, [#1894](https://github.com/NousResearch/hermes-agent/pull/1894))
|
||||
- Fix: only strip last assistant message if empty string ([#2326](https://github.com/NousResearch/hermes-agent/pull/2326))
|
||||
|
||||
### Session & Memory
|
||||
- **Session search** and management slash commands ([#2198](https://github.com/NousResearch/hermes-agent/pull/2198))
|
||||
- **Auto session titles** and `.hermes.md` project config ([#1712](https://github.com/NousResearch/hermes-agent/pull/1712))
|
||||
- Fix: concurrent memory writes silently drop entries — added file locking ([#1726](https://github.com/NousResearch/hermes-agent/pull/1726))
|
||||
- Fix: search all sources by default in `session_search` ([#1892](https://github.com/NousResearch/hermes-agent/pull/1892))
|
||||
- Fix: handle hyphenated FTS5 queries and preserve quoted literals ([#1776](https://github.com/NousResearch/hermes-agent/pull/1776))
|
||||
- Fix: skip corrupt lines in `load_transcript` instead of crashing ([#1744](https://github.com/NousResearch/hermes-agent/pull/1744))
|
||||
- Fix: normalize session keys to prevent case-sensitive duplicates ([#2157](https://github.com/NousResearch/hermes-agent/pull/2157))
|
||||
- Fix: prevent `session_search` crash when no sessions exist ([#2194](https://github.com/NousResearch/hermes-agent/pull/2194))
|
||||
- Fix: reset token counters on new session for accurate usage display ([#2101](https://github.com/NousResearch/hermes-agent/pull/2101) by @InB4DevOps)
|
||||
- Fix: prevent stale memory overwrites by flush agent ([#2687](https://github.com/NousResearch/hermes-agent/pull/2687))
|
||||
- Fix: remove synthetic error message injection, fix session resume after repeated failures ([#2303](https://github.com/NousResearch/hermes-agent/pull/2303))
|
||||
- Fix: quiet mode with `--resume` now passes conversation_history ([#2357](https://github.com/NousResearch/hermes-agent/pull/2357))
|
||||
- Fix: unify resume logic in batch mode ([#2331](https://github.com/NousResearch/hermes-agent/pull/2331))
|
||||
|
||||
### Honcho Memory
|
||||
- Honcho config fixes and @ context reference integration ([#2343](https://github.com/NousResearch/hermes-agent/pull/2343))
|
||||
- Self-hosted / Docker configuration documentation ([#2475](https://github.com/NousResearch/hermes-agent/pull/2475))
|
||||
|
||||
---
|
||||
|
||||
## 📱 Messaging Platforms (Gateway)
|
||||
|
||||
### New Platform Adapters
|
||||
- **Signal Messenger** — Full adapter with attachment handling, group message filtering, and Note to Self echo-back protection ([#2206](https://github.com/NousResearch/hermes-agent/pull/2206), [#2400](https://github.com/NousResearch/hermes-agent/pull/2400), [#2297](https://github.com/NousResearch/hermes-agent/pull/2297), [#2156](https://github.com/NousResearch/hermes-agent/pull/2156))
|
||||
- **DingTalk** — Adapter with gateway wiring and setup docs ([#1685](https://github.com/NousResearch/hermes-agent/pull/1685), [#1690](https://github.com/NousResearch/hermes-agent/pull/1690), [#1692](https://github.com/NousResearch/hermes-agent/pull/1692))
|
||||
- **SMS (Twilio)** ([#1688](https://github.com/NousResearch/hermes-agent/pull/1688))
|
||||
- **Mattermost** — With @-mention-only channel filter ([#1683](https://github.com/NousResearch/hermes-agent/pull/1683), [#2443](https://github.com/NousResearch/hermes-agent/pull/2443))
|
||||
- **Matrix** — With vision support and image caching ([#1683](https://github.com/NousResearch/hermes-agent/pull/1683), [#2520](https://github.com/NousResearch/hermes-agent/pull/2520))
|
||||
- **Webhook** — Platform adapter for external event triggers ([#2166](https://github.com/NousResearch/hermes-agent/pull/2166))
|
||||
- **OpenAI-compatible API server** — `/v1/chat/completions` endpoint with `/api/jobs` cron management ([#1756](https://github.com/NousResearch/hermes-agent/pull/1756), [#2450](https://github.com/NousResearch/hermes-agent/pull/2450), [#2456](https://github.com/NousResearch/hermes-agent/pull/2456))
|
||||
|
||||
### Telegram Improvements
|
||||
- MarkdownV2 support — strikethrough, spoiler, blockquotes, escape parentheses/braces/backslashes/backticks ([#2199](https://github.com/NousResearch/hermes-agent/pull/2199), [#2200](https://github.com/NousResearch/hermes-agent/pull/2200) by @llbn, [#2386](https://github.com/NousResearch/hermes-agent/pull/2386))
|
||||
- Auto-detect HTML tags and use `parse_mode=HTML` ([#1709](https://github.com/NousResearch/hermes-agent/pull/1709))
|
||||
- Telegram group vision support + thread-based sessions ([#2153](https://github.com/NousResearch/hermes-agent/pull/2153))
|
||||
- Auto-reconnect polling after network interruption ([#2517](https://github.com/NousResearch/hermes-agent/pull/2517))
|
||||
- Aggregate split text messages before dispatching ([#1674](https://github.com/NousResearch/hermes-agent/pull/1674))
|
||||
- Fix: streaming config bridge, not-modified, flood control ([#1782](https://github.com/NousResearch/hermes-agent/pull/1782), [#1783](https://github.com/NousResearch/hermes-agent/pull/1783))
|
||||
- Fix: edited_message event crashes ([#2074](https://github.com/NousResearch/hermes-agent/pull/2074))
|
||||
- Fix: retry 409 polling conflicts before giving up ([#2312](https://github.com/NousResearch/hermes-agent/pull/2312))
|
||||
- Fix: topic delivery via `platform:chat_id:thread_id` format ([#2455](https://github.com/NousResearch/hermes-agent/pull/2455))
|
||||
|
||||
### Discord Improvements
|
||||
- Document caching and text-file injection ([#2503](https://github.com/NousResearch/hermes-agent/pull/2503))
|
||||
- Persistent typing indicator for DMs ([#2468](https://github.com/NousResearch/hermes-agent/pull/2468))
|
||||
- Discord DM vision — inline images + attachment analysis ([#2186](https://github.com/NousResearch/hermes-agent/pull/2186))
|
||||
- Persist thread participation across gateway restarts ([#1661](https://github.com/NousResearch/hermes-agent/pull/1661))
|
||||
- Fix: gateway crash on non-ASCII guild names ([#2302](https://github.com/NousResearch/hermes-agent/pull/2302))
|
||||
- Fix: thread permission errors ([#2073](https://github.com/NousResearch/hermes-agent/pull/2073))
|
||||
- Fix: slash event routing in threads ([#2460](https://github.com/NousResearch/hermes-agent/pull/2460))
|
||||
- Fix: remove bugged followup messages + `/ask` command ([#1836](https://github.com/NousResearch/hermes-agent/pull/1836))
|
||||
- Fix: graceful WebSocket reconnection ([#2127](https://github.com/NousResearch/hermes-agent/pull/2127))
|
||||
- Fix: voice channel TTS when streaming enabled ([#2322](https://github.com/NousResearch/hermes-agent/pull/2322))
|
||||
|
||||
### WhatsApp & Other Adapters
|
||||
- WhatsApp: outbound `send_message` routing ([#1769](https://github.com/NousResearch/hermes-agent/pull/1769) by @sai-samarth), LID format self-chat ([#1667](https://github.com/NousResearch/hermes-agent/pull/1667)), `reply_prefix` config fix ([#1923](https://github.com/NousResearch/hermes-agent/pull/1923)), restart on bridge child exit ([#2334](https://github.com/NousResearch/hermes-agent/pull/2334)), image/bridge improvements ([#2181](https://github.com/NousResearch/hermes-agent/pull/2181))
|
||||
- Matrix: correct `reply_to_message_id` parameter ([#1895](https://github.com/NousResearch/hermes-agent/pull/1895)), bare media types fix ([#1736](https://github.com/NousResearch/hermes-agent/pull/1736))
|
||||
- Mattermost: MIME types for media attachments ([#2329](https://github.com/NousResearch/hermes-agent/pull/2329))
|
||||
|
||||
### Gateway Core
|
||||
- **Auto-reconnect** failed platforms with exponential backoff ([#2584](https://github.com/NousResearch/hermes-agent/pull/2584))
|
||||
- **Notify users when session auto-resets** ([#2519](https://github.com/NousResearch/hermes-agent/pull/2519))
|
||||
- **Reply-to message context** for out-of-session replies ([#1662](https://github.com/NousResearch/hermes-agent/pull/1662))
|
||||
- **Ignore unauthorized DMs** config option ([#1919](https://github.com/NousResearch/hermes-agent/pull/1919))
|
||||
- Fix: `/reset` in thread-mode resets global session instead of thread ([#2254](https://github.com/NousResearch/hermes-agent/pull/2254))
|
||||
- Fix: deliver MEDIA: files after streaming responses ([#2382](https://github.com/NousResearch/hermes-agent/pull/2382))
|
||||
- Fix: cap interrupt recursion depth to prevent resource exhaustion ([#1659](https://github.com/NousResearch/hermes-agent/pull/1659))
|
||||
- Fix: detect stopped processes and release stale locks on `--replace` ([#2406](https://github.com/NousResearch/hermes-agent/pull/2406), [#1908](https://github.com/NousResearch/hermes-agent/pull/1908))
|
||||
- Fix: PID-based wait with force-kill for gateway restart ([#1902](https://github.com/NousResearch/hermes-agent/pull/1902))
|
||||
- Fix: prevent `--replace` mode from killing the caller process ([#2185](https://github.com/NousResearch/hermes-agent/pull/2185))
|
||||
- Fix: `/model` shows active fallback model instead of config default ([#1660](https://github.com/NousResearch/hermes-agent/pull/1660))
|
||||
- Fix: `/title` command fails when session doesn't exist in SQLite yet ([#2379](https://github.com/NousResearch/hermes-agent/pull/2379) by @ten-jampa)
|
||||
- Fix: process `/queue`'d messages after agent completion ([#2469](https://github.com/NousResearch/hermes-agent/pull/2469))
|
||||
- Fix: strip orphaned `tool_results` + let `/reset` bypass running agent ([#2180](https://github.com/NousResearch/hermes-agent/pull/2180))
|
||||
- Fix: prevent agents from starting gateway outside systemd management ([#2617](https://github.com/NousResearch/hermes-agent/pull/2617))
|
||||
- Fix: prevent systemd restart storm on gateway connection failure ([#2327](https://github.com/NousResearch/hermes-agent/pull/2327))
|
||||
- Fix: include resolved node path in systemd unit ([#1767](https://github.com/NousResearch/hermes-agent/pull/1767) by @sai-samarth)
|
||||
- Fix: send error details to user in gateway outer exception handler ([#1966](https://github.com/NousResearch/hermes-agent/pull/1966))
|
||||
- Fix: improve error handling for 429 usage limits and 500 context overflow ([#1839](https://github.com/NousResearch/hermes-agent/pull/1839))
|
||||
- Fix: add all missing platform allowlist env vars to startup warning check ([#2628](https://github.com/NousResearch/hermes-agent/pull/2628))
|
||||
- Fix: media delivery fails for file paths containing spaces ([#2621](https://github.com/NousResearch/hermes-agent/pull/2621))
|
||||
- Fix: duplicate session-key collision in multi-platform gateway ([#2171](https://github.com/NousResearch/hermes-agent/pull/2171))
|
||||
- Fix: Matrix and Mattermost never report as connected ([#1711](https://github.com/NousResearch/hermes-agent/pull/1711))
|
||||
- Fix: PII redaction config never read — missing yaml import ([#1701](https://github.com/NousResearch/hermes-agent/pull/1701))
|
||||
- Fix: NameError on skill slash commands ([#1697](https://github.com/NousResearch/hermes-agent/pull/1697))
|
||||
- Fix: persist watcher metadata in checkpoint for crash recovery ([#1706](https://github.com/NousResearch/hermes-agent/pull/1706))
|
||||
- Fix: pass `message_thread_id` in send_image_file, send_document, send_video ([#2339](https://github.com/NousResearch/hermes-agent/pull/2339))
|
||||
- Fix: media-group aggregation on rapid successive photo messages ([#2160](https://github.com/NousResearch/hermes-agent/pull/2160))
|
||||
|
||||
---
|
||||
|
||||
## 🔧 Tool System
|
||||
|
||||
### MCP Enhancements
|
||||
- **MCP server management CLI** + OAuth 2.1 PKCE auth ([#2465](https://github.com/NousResearch/hermes-agent/pull/2465))
|
||||
- **Expose MCP servers as standalone toolsets** ([#1907](https://github.com/NousResearch/hermes-agent/pull/1907))
|
||||
- **Interactive MCP tool configuration** in `hermes tools` ([#1694](https://github.com/NousResearch/hermes-agent/pull/1694))
|
||||
- Fix: MCP-OAuth port mismatch, path traversal, and shared handler state ([#2552](https://github.com/NousResearch/hermes-agent/pull/2552))
|
||||
- Fix: preserve MCP tool registrations across session resets ([#2124](https://github.com/NousResearch/hermes-agent/pull/2124))
|
||||
- Fix: concurrent file access crash + duplicate MCP registration ([#2154](https://github.com/NousResearch/hermes-agent/pull/2154))
|
||||
- Fix: normalise MCP schemas + expand session list columns ([#2102](https://github.com/NousResearch/hermes-agent/pull/2102))
|
||||
- Fix: `tool_choice` `mcp_` prefix handling ([#1775](https://github.com/NousResearch/hermes-agent/pull/1775))
|
||||
|
||||
### Web Tool Backends
|
||||
- **Tavily** as web search/extract/crawl backend ([#1731](https://github.com/NousResearch/hermes-agent/pull/1731))
|
||||
- **Parallel** as alternative web search/extract backend ([#1696](https://github.com/NousResearch/hermes-agent/pull/1696))
|
||||
- **Configurable web backend** — Firecrawl/BeautifulSoup/Playwright selection ([#2256](https://github.com/NousResearch/hermes-agent/pull/2256))
|
||||
- Fix: whitespace-only env vars bypass web backend detection ([#2341](https://github.com/NousResearch/hermes-agent/pull/2341))
|
||||
|
||||
### New Tools
|
||||
- **IMAP email** reading and sending ([#2173](https://github.com/NousResearch/hermes-agent/pull/2173))
|
||||
- **STT (speech-to-text)** tool using Whisper API ([#2072](https://github.com/NousResearch/hermes-agent/pull/2072))
|
||||
- **Route-aware pricing estimates** ([#1695](https://github.com/NousResearch/hermes-agent/pull/1695))
|
||||
|
||||
### Tool Improvements
|
||||
- TTS: `base_url` support for OpenAI TTS provider ([#2064](https://github.com/NousResearch/hermes-agent/pull/2064) by @hanai)
|
||||
- Vision: configurable timeout, tilde expansion in file paths, DM vision with multi-image and base64 fallback ([#2480](https://github.com/NousResearch/hermes-agent/pull/2480), [#2585](https://github.com/NousResearch/hermes-agent/pull/2585), [#2211](https://github.com/NousResearch/hermes-agent/pull/2211))
|
||||
- Browser: race condition fix in session creation ([#1721](https://github.com/NousResearch/hermes-agent/pull/1721)), TypeError on unexpected LLM params ([#1735](https://github.com/NousResearch/hermes-agent/pull/1735))
|
||||
- File tools: strip ANSI escape codes from write_file and patch content ([#2532](https://github.com/NousResearch/hermes-agent/pull/2532)), include pagination args in repeated search key ([#1824](https://github.com/NousResearch/hermes-agent/pull/1824) by @cutepawss), improve fuzzy matching accuracy + position calculation refactor ([#2096](https://github.com/NousResearch/hermes-agent/pull/2096), [#1681](https://github.com/NousResearch/hermes-agent/pull/1681))
|
||||
- Code execution: resource leak and double socket close fix ([#2381](https://github.com/NousResearch/hermes-agent/pull/2381))
|
||||
- Delegate: thread safety for concurrent subagent delegation ([#1672](https://github.com/NousResearch/hermes-agent/pull/1672)), preserve parent agent's tool list after delegation ([#1778](https://github.com/NousResearch/hermes-agent/pull/1778))
|
||||
- Fix: make concurrent tool batching path-aware for file mutations ([#1914](https://github.com/NousResearch/hermes-agent/pull/1914))
|
||||
- Fix: chunk long messages in `send_message_tool` before platform dispatch ([#1646](https://github.com/NousResearch/hermes-agent/pull/1646))
|
||||
- Fix: add missing 'messaging' toolset ([#1718](https://github.com/NousResearch/hermes-agent/pull/1718))
|
||||
- Fix: prevent unavailable tool names from leaking into model schemas ([#2072](https://github.com/NousResearch/hermes-agent/pull/2072))
|
||||
- Fix: pass visited set by reference to prevent diamond dependency duplication ([#2311](https://github.com/NousResearch/hermes-agent/pull/2311))
|
||||
- Fix: Daytona sandbox lookup migrated from `find_one` to `get/list` ([#2063](https://github.com/NousResearch/hermes-agent/pull/2063) by @rovle)
|
||||
|
||||
---
|
||||
|
||||
## 🧩 Skills Ecosystem
|
||||
|
||||
### Skills System Improvements
|
||||
- **Agent-created skills** — Caution-level findings allowed, dangerous skills ask instead of block ([#1840](https://github.com/NousResearch/hermes-agent/pull/1840), [#2446](https://github.com/NousResearch/hermes-agent/pull/2446))
|
||||
- **`--yes` flag** to bypass confirmation in `/skills install` and uninstall ([#1647](https://github.com/NousResearch/hermes-agent/pull/1647))
|
||||
- **Disabled skills respected** across banner, system prompt, and slash commands ([#1897](https://github.com/NousResearch/hermes-agent/pull/1897))
|
||||
- Fix: skills custom_tools import crash + sandbox file_tools integration ([#2239](https://github.com/NousResearch/hermes-agent/pull/2239))
|
||||
- Fix: agent-created skills with pip requirements crash on install ([#2145](https://github.com/NousResearch/hermes-agent/pull/2145))
|
||||
- Fix: race condition in `Skills.__init__` when `hub.yaml` missing ([#2242](https://github.com/NousResearch/hermes-agent/pull/2242))
|
||||
- Fix: validate skill metadata before install and block duplicates ([#2241](https://github.com/NousResearch/hermes-agent/pull/2241))
|
||||
- Fix: skills hub inspect/resolve — 4 bugs in inspect, redirects, discovery, tap list ([#2447](https://github.com/NousResearch/hermes-agent/pull/2447))
|
||||
- Fix: agent-created skills keep working after session reset ([#2121](https://github.com/NousResearch/hermes-agent/pull/2121))
|
||||
|
||||
### New Skills
|
||||
- **OCR-and-documents** — PDF/DOCX/XLS/PPTX/image OCR with optional GPU ([#2236](https://github.com/NousResearch/hermes-agent/pull/2236), [#2461](https://github.com/NousResearch/hermes-agent/pull/2461))
|
||||
- **Huggingface-hub** bundled skill ([#1921](https://github.com/NousResearch/hermes-agent/pull/1921))
|
||||
- **Sherlock OSINT** username search ([#1671](https://github.com/NousResearch/hermes-agent/pull/1671))
|
||||
- **Meme-generation** — Image generator with Pillow ([#2344](https://github.com/NousResearch/hermes-agent/pull/2344))
|
||||
- **Bioinformatics** gateway skill — index to 400+ bio skills ([#2387](https://github.com/NousResearch/hermes-agent/pull/2387))
|
||||
- **Inference.sh** skill (terminal-based) ([#1686](https://github.com/NousResearch/hermes-agent/pull/1686))
|
||||
- **Base blockchain** optional skill ([#1643](https://github.com/NousResearch/hermes-agent/pull/1643))
|
||||
- **3D-model-viewer** optional skill ([#2226](https://github.com/NousResearch/hermes-agent/pull/2226))
|
||||
- **FastMCP** optional skill ([#2113](https://github.com/NousResearch/hermes-agent/pull/2113))
|
||||
- **Hermes-agent-setup** skill ([#1905](https://github.com/NousResearch/hermes-agent/pull/1905))
|
||||
|
||||
---
|
||||
|
||||
## 🔌 Plugin System Enhancements
|
||||
|
||||
- **TUI extension hooks** — Build custom CLIs on top of Hermes ([#2333](https://github.com/NousResearch/hermes-agent/pull/2333))
|
||||
- **`hermes plugins install/remove/list`** commands ([#2337](https://github.com/NousResearch/hermes-agent/pull/2337))
|
||||
- **Slash command registration** for plugins ([#2359](https://github.com/NousResearch/hermes-agent/pull/2359))
|
||||
- **`session:end` lifecycle event** hook ([#1725](https://github.com/NousResearch/hermes-agent/pull/1725))
|
||||
- Fix: require opt-in for project plugin discovery ([#2215](https://github.com/NousResearch/hermes-agent/pull/2215))
|
||||
|
||||
---
|
||||
|
||||
## 🔒 Security & Reliability
|
||||
|
||||
### Security
|
||||
- **SSRF protection** for vision_tools and web_tools ([#2679](https://github.com/NousResearch/hermes-agent/pull/2679))
|
||||
- **Shell injection prevention** in `_expand_path` via `~user` path suffix ([#2685](https://github.com/NousResearch/hermes-agent/pull/2685))
|
||||
- **Block untrusted browser-origin** API server access ([#2451](https://github.com/NousResearch/hermes-agent/pull/2451))
|
||||
- **Block sandbox backend creds** from subprocess env ([#1658](https://github.com/NousResearch/hermes-agent/pull/1658))
|
||||
- **Block @ references** from reading secrets outside workspace ([#2601](https://github.com/NousResearch/hermes-agent/pull/2601) by @Gutslabs)
|
||||
- **Malicious code pattern pre-exec scanner** for terminal_tool ([#2245](https://github.com/NousResearch/hermes-agent/pull/2245))
|
||||
- **Harden terminal safety** and sandbox file writes ([#1653](https://github.com/NousResearch/hermes-agent/pull/1653))
|
||||
- **PKCE verifier leak** fix + OAuth refresh Content-Type ([#1775](https://github.com/NousResearch/hermes-agent/pull/1775))
|
||||
- **Eliminate SQL string formatting** in `execute()` calls ([#2061](https://github.com/NousResearch/hermes-agent/pull/2061) by @dusterbloom)
|
||||
- **Harden jobs API** — input limits, field whitelist, startup check ([#2456](https://github.com/NousResearch/hermes-agent/pull/2456))
|
||||
|
||||
### Reliability
|
||||
- Thread locks on 4 SessionDB methods ([#1704](https://github.com/NousResearch/hermes-agent/pull/1704))
|
||||
- File locking for concurrent memory writes ([#1726](https://github.com/NousResearch/hermes-agent/pull/1726))
|
||||
- Handle OpenRouter errors gracefully ([#2112](https://github.com/NousResearch/hermes-agent/pull/2112))
|
||||
- Guard print() calls against OSError ([#1668](https://github.com/NousResearch/hermes-agent/pull/1668))
|
||||
- Safely handle non-string inputs in redacting formatter ([#2392](https://github.com/NousResearch/hermes-agent/pull/2392), [#1700](https://github.com/NousResearch/hermes-agent/pull/1700))
|
||||
- ACP: preserve session provider on model switch, persist sessions to disk ([#2380](https://github.com/NousResearch/hermes-agent/pull/2380), [#2071](https://github.com/NousResearch/hermes-agent/pull/2071))
|
||||
- API server: persist ResponseStore to SQLite across restarts ([#2472](https://github.com/NousResearch/hermes-agent/pull/2472))
|
||||
- Fix: `fetch_nous_models` always TypeError from positional args ([#1699](https://github.com/NousResearch/hermes-agent/pull/1699))
|
||||
- Fix: resolve merge conflict markers in cli.py breaking startup ([#2347](https://github.com/NousResearch/hermes-agent/pull/2347))
|
||||
- Fix: `minisweagent_path.py` missing from wheel ([#2098](https://github.com/NousResearch/hermes-agent/pull/2098) by @JiwaniZakir)
|
||||
|
||||
### Cron System
|
||||
- **`[SILENT]` response** — cron agents can suppress delivery ([#1833](https://github.com/NousResearch/hermes-agent/pull/1833))
|
||||
- **Scale missed-job grace window** with schedule frequency ([#2449](https://github.com/NousResearch/hermes-agent/pull/2449))
|
||||
- **Recover recent one-shot jobs** ([#1918](https://github.com/NousResearch/hermes-agent/pull/1918))
|
||||
- Fix: normalize `repeat<=0` to None — jobs deleted after first run when LLM passes -1 ([#2612](https://github.com/NousResearch/hermes-agent/pull/2612) by @Mibayy)
|
||||
- Fix: Matrix added to scheduler delivery platform_map ([#2167](https://github.com/NousResearch/hermes-agent/pull/2167) by @buntingszn)
|
||||
- Fix: naive ISO timestamps without timezone — jobs fire at wrong time ([#1729](https://github.com/NousResearch/hermes-agent/pull/1729))
|
||||
- Fix: `get_due_jobs` reads `jobs.json` twice — race condition ([#1716](https://github.com/NousResearch/hermes-agent/pull/1716))
|
||||
- Fix: silent jobs return empty response for delivery skip ([#2442](https://github.com/NousResearch/hermes-agent/pull/2442))
|
||||
- Fix: stop injecting cron outputs into gateway session history ([#2313](https://github.com/NousResearch/hermes-agent/pull/2313))
|
||||
- Fix: close abandoned coroutine when `asyncio.run()` raises RuntimeError ([#2317](https://github.com/NousResearch/hermes-agent/pull/2317))
|
||||
|
||||
---
|
||||
|
||||
## 🧪 Testing
|
||||
|
||||
- Resolve all consistently failing tests ([#2488](https://github.com/NousResearch/hermes-agent/pull/2488))
|
||||
- Replace `FakePath` with `monkeypatch` for Python 3.12 compat ([#2444](https://github.com/NousResearch/hermes-agent/pull/2444))
|
||||
- Align Hermes setup and full-suite expectations ([#1710](https://github.com/NousResearch/hermes-agent/pull/1710))
|
||||
|
||||
---
|
||||
|
||||
## 📚 Documentation
|
||||
|
||||
- Comprehensive docs update for recent features ([#1693](https://github.com/NousResearch/hermes-agent/pull/1693), [#2183](https://github.com/NousResearch/hermes-agent/pull/2183))
|
||||
- Alibaba Cloud and DingTalk setup guides ([#1687](https://github.com/NousResearch/hermes-agent/pull/1687), [#1692](https://github.com/NousResearch/hermes-agent/pull/1692))
|
||||
- Detailed skills documentation ([#2244](https://github.com/NousResearch/hermes-agent/pull/2244))
|
||||
- Honcho self-hosted / Docker configuration ([#2475](https://github.com/NousResearch/hermes-agent/pull/2475))
|
||||
- Context length detection FAQ and quickstart references ([#2179](https://github.com/NousResearch/hermes-agent/pull/2179))
|
||||
- Fix docs inconsistencies across reference and user guides ([#1995](https://github.com/NousResearch/hermes-agent/pull/1995))
|
||||
- Fix MCP install commands — use uv, not bare pip ([#1909](https://github.com/NousResearch/hermes-agent/pull/1909))
|
||||
- Replace ASCII diagrams with Mermaid/lists ([#2402](https://github.com/NousResearch/hermes-agent/pull/2402))
|
||||
- Gemini OAuth provider implementation plan ([#2467](https://github.com/NousResearch/hermes-agent/pull/2467))
|
||||
- Discord Server Members Intent marked as required ([#2330](https://github.com/NousResearch/hermes-agent/pull/2330))
|
||||
- Fix MDX build error in api-server.md ([#1787](https://github.com/NousResearch/hermes-agent/pull/1787))
|
||||
- Align venv path to match installer ([#2114](https://github.com/NousResearch/hermes-agent/pull/2114))
|
||||
- New skills added to hub index ([#2281](https://github.com/NousResearch/hermes-agent/pull/2281))
|
||||
|
||||
---
|
||||
|
||||
## 👥 Contributors
|
||||
|
||||
### Core
|
||||
- **@teknium1** (Teknium) — 280 PRs
|
||||
|
||||
### Community Contributors
|
||||
- **@mchzimm** (to_the_max) — GitHub Copilot provider integration ([#1879](https://github.com/NousResearch/hermes-agent/pull/1879))
|
||||
- **@jquesnelle** (Jeffrey Quesnelle) — Per-thread persistent event loops fix ([#2214](https://github.com/NousResearch/hermes-agent/pull/2214))
|
||||
- **@llbn** (lbn) — Telegram MarkdownV2 strikethrough, spoiler, blockquotes, and escape fixes ([#2199](https://github.com/NousResearch/hermes-agent/pull/2199), [#2200](https://github.com/NousResearch/hermes-agent/pull/2200))
|
||||
- **@dusterbloom** — SQL injection prevention + local server context window querying ([#2061](https://github.com/NousResearch/hermes-agent/pull/2061), [#2091](https://github.com/NousResearch/hermes-agent/pull/2091))
|
||||
- **@0xbyt4** — Anthropic tool_calls None guard + OpenCode-Go provider config fix ([#2209](https://github.com/NousResearch/hermes-agent/pull/2209), [#2393](https://github.com/NousResearch/hermes-agent/pull/2393))
|
||||
- **@sai-samarth** (Saisamarth) — WhatsApp send_message routing + systemd node path ([#1769](https://github.com/NousResearch/hermes-agent/pull/1769), [#1767](https://github.com/NousResearch/hermes-agent/pull/1767))
|
||||
- **@Gutslabs** (Guts) — Block @ references from reading secrets ([#2601](https://github.com/NousResearch/hermes-agent/pull/2601))
|
||||
- **@Mibayy** (Mibay) — Cron job repeat normalization ([#2612](https://github.com/NousResearch/hermes-agent/pull/2612))
|
||||
- **@ten-jampa** (Tenzin Jampa) — Gateway /title command fix ([#2379](https://github.com/NousResearch/hermes-agent/pull/2379))
|
||||
- **@cutepawss** (lila) — File tools search pagination fix ([#1824](https://github.com/NousResearch/hermes-agent/pull/1824))
|
||||
- **@hanai** (Hanai) — OpenAI TTS base_url support ([#2064](https://github.com/NousResearch/hermes-agent/pull/2064))
|
||||
- **@rovle** (Lovre Pešut) — Daytona sandbox API migration ([#2063](https://github.com/NousResearch/hermes-agent/pull/2063))
|
||||
- **@buntingszn** (bunting szn) — Matrix cron delivery support ([#2167](https://github.com/NousResearch/hermes-agent/pull/2167))
|
||||
- **@InB4DevOps** — Token counter reset on new session ([#2101](https://github.com/NousResearch/hermes-agent/pull/2101))
|
||||
- **@JiwaniZakir** (Zakir Jiwani) — Missing file in wheel fix ([#2098](https://github.com/NousResearch/hermes-agent/pull/2098))
|
||||
- **@ygd58** (buray) — Delegate tool parent tool names fix ([#2083](https://github.com/NousResearch/hermes-agent/pull/2083))
|
||||
|
||||
---
|
||||
|
||||
**Full Changelog**: [v2026.3.17...v2026.3.23](https://github.com/NousResearch/hermes-agent/compare/v2026.3.17...v2026.3.23)
|
||||
+13
-32
@@ -35,12 +35,14 @@ SUMMARY_PREFIX = (
|
||||
)
|
||||
LEGACY_SUMMARY_PREFIX = "[CONTEXT SUMMARY]:"
|
||||
|
||||
# Minimum tokens for the summary output
|
||||
# Minimum / maximum tokens for the summary output
|
||||
_MIN_SUMMARY_TOKENS = 2000
|
||||
_MAX_SUMMARY_TOKENS = 8000
|
||||
# Proportion of compressed content to allocate for summary
|
||||
_SUMMARY_RATIO = 0.20
|
||||
# Absolute ceiling for summary tokens (even on very large context windows)
|
||||
_SUMMARY_TOKENS_CEILING = 12_000
|
||||
|
||||
# Token budget for tail protection (keep most-recent context)
|
||||
_DEFAULT_TAIL_TOKEN_BUDGET = 20_000
|
||||
|
||||
# Placeholder used when pruning old tool results
|
||||
_PRUNED_TOOL_PLACEHOLDER = "[Old tool output cleared to save context space]"
|
||||
@@ -65,8 +67,8 @@ class ContextCompressor:
|
||||
model: str,
|
||||
threshold_percent: float = 0.50,
|
||||
protect_first_n: int = 3,
|
||||
protect_last_n: int = 20,
|
||||
summary_target_ratio: float = 0.20,
|
||||
protect_last_n: int = 4,
|
||||
summary_target_tokens: int = 2500,
|
||||
quiet_mode: bool = False,
|
||||
summary_model_override: str = None,
|
||||
base_url: str = "",
|
||||
@@ -81,7 +83,7 @@ class ContextCompressor:
|
||||
self.threshold_percent = threshold_percent
|
||||
self.protect_first_n = protect_first_n
|
||||
self.protect_last_n = protect_last_n
|
||||
self.summary_target_ratio = max(0.10, min(summary_target_ratio, 0.80))
|
||||
self.summary_target_tokens = summary_target_tokens
|
||||
self.quiet_mode = quiet_mode
|
||||
|
||||
self.context_length = get_model_context_length(
|
||||
@@ -92,22 +94,12 @@ class ContextCompressor:
|
||||
self.threshold_tokens = int(self.context_length * threshold_percent)
|
||||
self.compression_count = 0
|
||||
|
||||
# Derive token budgets: ratio is relative to the threshold, not total context
|
||||
target_tokens = int(self.threshold_tokens * self.summary_target_ratio)
|
||||
self.tail_token_budget = target_tokens
|
||||
self.max_summary_tokens = min(
|
||||
int(self.context_length * 0.05), _SUMMARY_TOKENS_CEILING,
|
||||
)
|
||||
|
||||
if not quiet_mode:
|
||||
logger.info(
|
||||
"Context compressor initialized: model=%s context_length=%d "
|
||||
"threshold=%d (%.0f%%) target_ratio=%.0f%% tail_budget=%d "
|
||||
"provider=%s base_url=%s",
|
||||
"threshold=%d (%.0f%%) provider=%s base_url=%s",
|
||||
model, self.context_length, self.threshold_tokens,
|
||||
threshold_percent * 100, self.summary_target_ratio * 100,
|
||||
self.tail_token_budget,
|
||||
provider or "none", base_url or "none",
|
||||
threshold_percent * 100, provider or "none", base_url or "none",
|
||||
)
|
||||
self._context_probed = False # True after a step-down from context error
|
||||
|
||||
@@ -187,15 +179,10 @@ class ContextCompressor:
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _compute_summary_budget(self, turns_to_summarize: List[Dict[str, Any]]) -> int:
|
||||
"""Scale summary token budget with the amount of content being compressed.
|
||||
|
||||
The maximum scales with the model's context window (5% of context,
|
||||
capped at ``_SUMMARY_TOKENS_CEILING``) so large-context models get
|
||||
richer summaries instead of being hard-capped at 8K tokens.
|
||||
"""
|
||||
"""Scale summary token budget with the amount of content being compressed."""
|
||||
content_tokens = estimate_messages_tokens_rough(turns_to_summarize)
|
||||
budget = int(content_tokens * _SUMMARY_RATIO)
|
||||
return max(_MIN_SUMMARY_TOKENS, min(budget, self.max_summary_tokens))
|
||||
return max(_MIN_SUMMARY_TOKENS, min(budget, _MAX_SUMMARY_TOKENS))
|
||||
|
||||
def _serialize_for_summary(self, turns: List[Dict[str, Any]]) -> str:
|
||||
"""Serialize conversation turns into labeled text for the summarizer.
|
||||
@@ -490,20 +477,14 @@ Write only the summary body. Do not include any preamble or prefix."""
|
||||
|
||||
def _find_tail_cut_by_tokens(
|
||||
self, messages: List[Dict[str, Any]], head_end: int,
|
||||
token_budget: int | None = None,
|
||||
token_budget: int = _DEFAULT_TAIL_TOKEN_BUDGET,
|
||||
) -> int:
|
||||
"""Walk backward from the end of messages, accumulating tokens until
|
||||
the budget is reached. Returns the index where the tail starts.
|
||||
|
||||
``token_budget`` defaults to ``self.tail_token_budget`` which is
|
||||
derived from ``summary_target_ratio * context_length``, so it
|
||||
scales automatically with the model's context window.
|
||||
|
||||
Never cuts inside a tool_call/result group. Falls back to the old
|
||||
``protect_last_n`` if the budget would protect fewer messages.
|
||||
"""
|
||||
if token_budget is None:
|
||||
token_budget = self.tail_token_budget
|
||||
n = len(messages)
|
||||
min_tail = self.protect_last_n
|
||||
accumulated = 0
|
||||
|
||||
+23
-9
@@ -657,6 +657,10 @@ def format_context_pressure(
|
||||
The bar and percentage show progress toward the compaction threshold,
|
||||
NOT the raw context window. 100% = compaction fires.
|
||||
|
||||
Uses ANSI colors:
|
||||
- cyan at ~60% to compaction = informational
|
||||
- bold yellow at ~85% to compaction = warning
|
||||
|
||||
Args:
|
||||
compaction_progress: How close to compaction (0.0–1.0, 1.0 = fires).
|
||||
threshold_tokens: Compaction threshold in tokens.
|
||||
@@ -670,12 +674,18 @@ def format_context_pressure(
|
||||
threshold_k = f"{threshold_tokens // 1000}k" if threshold_tokens >= 1000 else str(threshold_tokens)
|
||||
threshold_pct_int = int(threshold_percent * 100)
|
||||
|
||||
color = f"{_BOLD}{_YELLOW}"
|
||||
icon = "⚠"
|
||||
if compression_enabled:
|
||||
hint = "compaction approaching"
|
||||
# Tier styling
|
||||
if compaction_progress >= 0.85:
|
||||
color = f"{_BOLD}{_YELLOW}"
|
||||
icon = "⚠"
|
||||
if compression_enabled:
|
||||
hint = "compaction imminent"
|
||||
else:
|
||||
hint = "no auto-compaction"
|
||||
else:
|
||||
hint = "no auto-compaction"
|
||||
color = _CYAN
|
||||
icon = "◐"
|
||||
hint = "approaching compaction"
|
||||
|
||||
return (
|
||||
f" {color}{icon} context {bar} {pct_int}% to compaction{_ANSI_RESET}"
|
||||
@@ -699,10 +709,14 @@ def format_context_pressure_gateway(
|
||||
|
||||
threshold_pct_int = int(threshold_percent * 100)
|
||||
|
||||
icon = "⚠️"
|
||||
if compression_enabled:
|
||||
hint = f"Context compaction approaching (threshold: {threshold_pct_int}% of window)."
|
||||
if compaction_progress >= 0.85:
|
||||
icon = "⚠️"
|
||||
if compression_enabled:
|
||||
hint = f"Context compaction is imminent (threshold: {threshold_pct_int}% of window)."
|
||||
else:
|
||||
hint = "Auto-compaction is disabled — context may be truncated."
|
||||
else:
|
||||
hint = "Auto-compaction is disabled — context may be truncated."
|
||||
icon = "ℹ️"
|
||||
hint = f"Compaction threshold is at {threshold_pct_int}% of context window."
|
||||
|
||||
return f"{icon} Context: {bar} {pct_int}% to compaction\n{hint}"
|
||||
|
||||
+3
-18
@@ -232,34 +232,19 @@ browser:
|
||||
# 1. Tracks actual token usage from API responses (not estimates)
|
||||
# 2. When prompt_tokens >= threshold% of model's context_length, triggers compression
|
||||
# 3. Protects first 3 turns (system prompt, initial request, first response)
|
||||
# 4. Protects last N turns (default 20 messages = ~10 full turns of recent context)
|
||||
# 4. Protects last 4 turns (recent context is most relevant)
|
||||
# 5. Summarizes middle turns using a fast/cheap model
|
||||
# 6. Inserts summary as a user message, continues conversation seamlessly
|
||||
#
|
||||
# Post-compression tail budget is target_ratio × threshold × context_length:
|
||||
# 200K context, threshold 0.50, ratio 0.20 → 20K tokens of recent tail preserved
|
||||
# 1M context, threshold 0.50, ratio 0.20 → 100K tokens of recent tail preserved
|
||||
#
|
||||
compression:
|
||||
# Enable automatic context compression (default: true)
|
||||
# Set to false if you prefer to manage context manually or want errors on overflow
|
||||
enabled: true
|
||||
|
||||
# Trigger compression at this % of model's context limit (default: 0.50 = 50%)
|
||||
# Trigger compression at this % of model's context limit (default: 0.85 = 85%)
|
||||
# Lower values = more aggressive compression, higher values = compress later
|
||||
threshold: 0.50
|
||||
threshold: 0.85
|
||||
|
||||
# Fraction of the threshold to preserve as recent tail (default: 0.20 = 20%)
|
||||
# e.g. 20% of 50% threshold = 10% of total context kept as recent messages.
|
||||
# Summary output is separately capped at 12K tokens (Gemini output limit).
|
||||
# Range: 0.10 - 0.80
|
||||
target_ratio: 0.20
|
||||
|
||||
# Number of most-recent messages to always preserve (default: 20 ≈ 10 full turns)
|
||||
# Higher values keep more recent conversation intact at the cost of more aggressive
|
||||
# compression of older turns.
|
||||
protect_last_n: 20
|
||||
|
||||
# Model to use for generating summaries (fast/cheap recommended)
|
||||
# This model compresses the middle turns into a concise summary.
|
||||
# IMPORTANT: it receives the full middle section of the conversation, so it
|
||||
|
||||
@@ -31,6 +31,7 @@ from typing import List, Dict, Any, Optional
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Suppress startup messages for clean CLI experience
|
||||
os.environ["MSWEA_SILENT_STARTUP"] = "1" # mini-swe-agent
|
||||
os.environ["HERMES_QUIET"] = "1" # Our own modules
|
||||
|
||||
import yaml
|
||||
@@ -77,6 +78,8 @@ _hermes_home = Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))
|
||||
_project_env = Path(__file__).parent / '.env'
|
||||
load_hermes_dotenv(hermes_home=_hermes_home, project_env=_project_env)
|
||||
|
||||
# Point mini-swe-agent at ~/.hermes/ so it shares our config
|
||||
os.environ.setdefault("MSWEA_GLOBAL_CONFIG_DIR", str(_hermes_home))
|
||||
|
||||
# =============================================================================
|
||||
# Configuration Loading
|
||||
@@ -298,11 +301,7 @@ def load_cli_config() -> Dict[str, Any]:
|
||||
defaults["agent"]["max_turns"] = file_config["max_turns"]
|
||||
except Exception as e:
|
||||
logger.warning("Failed to load cli-config.yaml: %s", e)
|
||||
|
||||
# Expand ${ENV_VAR} references in config values before bridging to env vars.
|
||||
from hermes_cli.config import _expand_env_vars
|
||||
defaults = _expand_env_vars(defaults)
|
||||
|
||||
|
||||
# Apply terminal config to environment variables (so terminal_tool picks them up)
|
||||
terminal_config = defaults.get("terminal", {})
|
||||
|
||||
@@ -1509,14 +1508,10 @@ class HermesCLI:
|
||||
|
||||
self._reasoning_buf = getattr(self, "_reasoning_buf", "") + text
|
||||
|
||||
# Emit complete lines, and force-flush long partial lines so
|
||||
# reasoning is visible in real-time even without newlines.
|
||||
# Emit complete lines
|
||||
while "\n" in self._reasoning_buf:
|
||||
line, self._reasoning_buf = self._reasoning_buf.split("\n", 1)
|
||||
_cprint(f"{_DIM}{line}{_RST}")
|
||||
if len(self._reasoning_buf) > 80:
|
||||
_cprint(f"{_DIM}{self._reasoning_buf}{_RST}")
|
||||
self._reasoning_buf = ""
|
||||
|
||||
def _close_reasoning_box(self) -> None:
|
||||
"""Close the live reasoning box if it's open."""
|
||||
@@ -1939,7 +1934,6 @@ class HermesCLI:
|
||||
pass_session_id=self.pass_session_id,
|
||||
tool_progress_callback=self._on_tool_progress,
|
||||
stream_delta_callback=self._stream_delta if self.streaming_enabled else None,
|
||||
tool_gen_callback=self._on_tool_gen_start if self.streaming_enabled else None,
|
||||
)
|
||||
# Route agent status output through prompt_toolkit so ANSI escape
|
||||
# sequences aren't garbled by patch_stdout's StdoutProxy (#2262).
|
||||
@@ -3563,85 +3557,103 @@ class HermesCLI:
|
||||
# Use original case so model names like "Anthropic/Claude-Opus-4" are preserved
|
||||
parts = cmd_original.split(maxsplit=1)
|
||||
if len(parts) > 1:
|
||||
from hermes_cli.model_switch import switch_model, switch_to_custom_provider
|
||||
from hermes_cli.auth import resolve_provider
|
||||
from hermes_cli.models import (
|
||||
parse_model_input,
|
||||
validate_requested_model,
|
||||
_PROVIDER_LABELS,
|
||||
)
|
||||
|
||||
raw_input = parts[1].strip()
|
||||
|
||||
# Handle bare "/model custom" — switch to custom provider
|
||||
# and auto-detect the model from the endpoint.
|
||||
if raw_input.strip().lower() == "custom":
|
||||
result = switch_to_custom_provider()
|
||||
if result.success:
|
||||
self.model = result.model
|
||||
self.requested_provider = "custom"
|
||||
self.provider = "custom"
|
||||
self.api_key = result.api_key
|
||||
self.base_url = result.base_url
|
||||
self.agent = None
|
||||
save_config_value("model.default", result.model)
|
||||
save_config_value("model.provider", "custom")
|
||||
save_config_value("model.base_url", result.base_url)
|
||||
print(f"(^_^)b Model changed to: {result.model} [provider: Custom]")
|
||||
print(f" Endpoint: {result.base_url}")
|
||||
print(f" Status: connected (model auto-detected)")
|
||||
else:
|
||||
print(f"(>_<) {result.error_message}")
|
||||
return True
|
||||
|
||||
# Core model-switching pipeline (shared with gateway)
|
||||
# Parse provider:model syntax (e.g. "openrouter:anthropic/claude-sonnet-4.5")
|
||||
current_provider = self.provider or self.requested_provider or "openrouter"
|
||||
result = switch_model(
|
||||
raw_input,
|
||||
current_provider,
|
||||
current_base_url=self.base_url or "",
|
||||
current_api_key=self.api_key or "",
|
||||
target_provider, new_model = parse_model_input(raw_input, current_provider)
|
||||
# Auto-detect provider when no explicit provider:model syntax was used.
|
||||
# Skip auto-detection for custom providers — the model name might
|
||||
# coincidentally match a known provider's catalog, but the user
|
||||
# intends to use it on their custom endpoint. Require explicit
|
||||
# provider:model syntax (e.g. /model openai-codex:gpt-5.2-codex)
|
||||
# to switch away from a custom endpoint.
|
||||
_base = self.base_url or ""
|
||||
is_custom = current_provider == "custom" or (
|
||||
"localhost" in _base or "127.0.0.1" in _base
|
||||
)
|
||||
if target_provider == current_provider and not is_custom:
|
||||
from hermes_cli.models import detect_provider_for_model
|
||||
detected = detect_provider_for_model(new_model, current_provider)
|
||||
if detected:
|
||||
target_provider, new_model = detected
|
||||
provider_changed = target_provider != current_provider
|
||||
|
||||
if not result.success:
|
||||
print(f"(>_<) {result.error_message}")
|
||||
if "Did you mean" not in result.error_message:
|
||||
print(f" Model unchanged: {self.model}")
|
||||
if "credentials" not in result.error_message.lower():
|
||||
print(" Tip: Use /model to see available models, /provider to see providers")
|
||||
# If provider is changing, re-resolve credentials for the new provider
|
||||
api_key_for_probe = self.api_key
|
||||
base_url_for_probe = self.base_url
|
||||
if provider_changed:
|
||||
try:
|
||||
from hermes_cli.runtime_provider import resolve_runtime_provider
|
||||
runtime = resolve_runtime_provider(requested=target_provider)
|
||||
api_key_for_probe = runtime.get("api_key", "")
|
||||
base_url_for_probe = runtime.get("base_url", "")
|
||||
except Exception as e:
|
||||
provider_label = _PROVIDER_LABELS.get(target_provider, target_provider)
|
||||
if target_provider == "custom":
|
||||
print(f"(>_<) Custom endpoint not configured. Set OPENAI_BASE_URL and OPENAI_API_KEY,")
|
||||
print(f" or run: hermes setup → Custom OpenAI-compatible endpoint")
|
||||
else:
|
||||
print(f"(>_<) Could not resolve credentials for provider '{provider_label}': {e}")
|
||||
print(f"(^_^) Current model unchanged: {self.model}")
|
||||
return True
|
||||
|
||||
try:
|
||||
validation = validate_requested_model(
|
||||
new_model,
|
||||
target_provider,
|
||||
api_key=api_key_for_probe,
|
||||
base_url=base_url_for_probe,
|
||||
)
|
||||
except Exception:
|
||||
validation = {"accepted": True, "persist": True, "recognized": False, "message": None}
|
||||
|
||||
if not validation.get("accepted"):
|
||||
print(f"(>_<) {validation.get('message')}")
|
||||
print(f" Model unchanged: {self.model}")
|
||||
if "Did you mean" not in (validation.get("message") or ""):
|
||||
print(" Tip: Use /model to see available models, /provider to see providers")
|
||||
else:
|
||||
self.model = result.new_model
|
||||
self.model = new_model
|
||||
self.agent = None # Force re-init
|
||||
|
||||
if result.provider_changed:
|
||||
self.requested_provider = result.target_provider
|
||||
self.provider = result.target_provider
|
||||
self.api_key = result.api_key
|
||||
self.base_url = result.base_url
|
||||
if provider_changed:
|
||||
self.requested_provider = target_provider
|
||||
self.provider = target_provider
|
||||
self.api_key = api_key_for_probe
|
||||
self.base_url = base_url_for_probe
|
||||
|
||||
provider_note = f" [provider: {result.provider_label}]" if result.provider_changed else ""
|
||||
provider_label = _PROVIDER_LABELS.get(target_provider, target_provider)
|
||||
provider_note = f" [provider: {provider_label}]" if provider_changed else ""
|
||||
|
||||
if result.persist:
|
||||
saved_model = save_config_value("model.default", result.new_model)
|
||||
if result.provider_changed:
|
||||
save_config_value("model.provider", result.target_provider)
|
||||
# Persist base_url for custom endpoints; clear
|
||||
# when switching away from custom (#2562 Phase 2).
|
||||
if result.base_url and "openrouter.ai" not in (result.base_url or ""):
|
||||
save_config_value("model.base_url", result.base_url)
|
||||
else:
|
||||
save_config_value("model.base_url", None)
|
||||
if validation.get("persist"):
|
||||
saved_model = save_config_value("model.default", new_model)
|
||||
if provider_changed:
|
||||
save_config_value("model.provider", target_provider)
|
||||
if saved_model:
|
||||
print(f"(^_^)b Model changed to: {result.new_model}{provider_note} (saved to config)")
|
||||
print(f"(^_^)b Model changed to: {new_model}{provider_note} (saved to config)")
|
||||
else:
|
||||
print(f"(^_^) Model changed to: {result.new_model}{provider_note} (this session only)")
|
||||
print(f"(^_^) Model changed to: {new_model}{provider_note} (this session only)")
|
||||
else:
|
||||
print(f"(^_^) Model changed to: {result.new_model}{provider_note} (this session only)")
|
||||
if result.warning_message:
|
||||
print(f" Reason: {result.warning_message}")
|
||||
message = validation.get("message") or ""
|
||||
print(f"(^_^) Model changed to: {new_model}{provider_note} (this session only)")
|
||||
if message:
|
||||
print(f" Reason: {message}")
|
||||
print(" Note: Model will revert on restart. Use a verified model to save to config.")
|
||||
|
||||
# Show endpoint info for custom providers
|
||||
if result.is_custom_target:
|
||||
endpoint = result.base_url or self.base_url or "custom endpoint"
|
||||
# Helpful hint when staying on a custom endpoint
|
||||
if is_custom and not provider_changed:
|
||||
endpoint = self.base_url or "custom endpoint"
|
||||
print(f" Endpoint: {endpoint}")
|
||||
if not result.provider_changed:
|
||||
print(f" Tip: To switch providers, use /model provider:model")
|
||||
print(f" e.g. /model openai-codex:gpt-5.2-codex")
|
||||
print(f" Tip: To switch providers, use /model provider:model")
|
||||
print(f" e.g. /model openai-codex:gpt-5.2-codex")
|
||||
else:
|
||||
self._show_model_and_providers()
|
||||
elif canonical == "provider":
|
||||
@@ -4445,7 +4457,7 @@ class HermesCLI:
|
||||
logging.getLogger(noisy).setLevel(logging.WARNING)
|
||||
else:
|
||||
logging.getLogger().setLevel(logging.INFO)
|
||||
for quiet_logger in ('tools', 'run_agent', 'trajectory_compressor', 'cron', 'hermes_cli'):
|
||||
for quiet_logger in ('tools', 'minisweagent', 'run_agent', 'trajectory_compressor', 'cron', 'hermes_cli'):
|
||||
logging.getLogger(quiet_logger).setLevel(logging.ERROR)
|
||||
|
||||
def _show_insights(self, command: str = "/insights"):
|
||||
@@ -4617,26 +4629,6 @@ class HermesCLI:
|
||||
except Exception as e:
|
||||
print(f" ❌ MCP reload failed: {e}")
|
||||
|
||||
# ====================================================================
|
||||
# Tool-call generation indicator (shown during streaming)
|
||||
# ====================================================================
|
||||
|
||||
def _on_tool_gen_start(self, tool_name: str) -> None:
|
||||
"""Called when the model begins generating tool-call arguments.
|
||||
|
||||
Closes any open streaming boxes (reasoning / response) exactly once,
|
||||
then prints a short status line so the user sees activity instead of
|
||||
a frozen screen while a large payload (e.g. 45 KB write_file) streams.
|
||||
"""
|
||||
if getattr(self, "_stream_box_opened", False):
|
||||
self._flush_stream()
|
||||
self._stream_box_opened = False
|
||||
self._close_reasoning_box()
|
||||
|
||||
from agent.display import get_tool_emoji
|
||||
emoji = get_tool_emoji(tool_name, default="⚡")
|
||||
_cprint(f" ┊ {emoji} preparing {tool_name}…")
|
||||
|
||||
# ====================================================================
|
||||
# Tool progress callback (audio cues for voice mode)
|
||||
# ====================================================================
|
||||
|
||||
@@ -101,7 +101,7 @@ Available methods:
|
||||
|
||||
### Patches (`patches.py`)
|
||||
|
||||
**Problem**: Some hermes-agent tools use `asyncio.run()` internally (e.g., the Modal backend via SWE-ReX). This crashes when called from inside Atropos's event loop because `asyncio.run()` cannot be nested.
|
||||
**Problem**: Some hermes-agent tools use `asyncio.run()` internally (e.g., mini-swe-agent's Modal backend via SWE-ReX). This crashes when called from inside Atropos's event loop because `asyncio.run()` cannot be nested.
|
||||
|
||||
**Solution**: `patches.py` monkey-patches `SwerexModalEnvironment` to use a dedicated background thread (`_AsyncWorker`) with its own event loop. The calling code sees the same sync interface, but internally the async work happens on a separate thread that doesn't conflict with Atropos's loop.
|
||||
|
||||
|
||||
@@ -23,7 +23,7 @@ from typing import Any, Dict, List, Optional, Set
|
||||
from model_tools import handle_function_call
|
||||
|
||||
# Thread pool for running sync tool calls that internally use asyncio.run()
|
||||
# (e.g., the Modal/Docker/Daytona terminal backends). Running them in a separate
|
||||
# (e.g., mini-swe-agent's modal/docker/daytona backends). Running them in a separate
|
||||
# thread gives them a clean event loop so they don't deadlock inside Atropos's loop.
|
||||
# Size must be large enough for concurrent eval tasks (e.g., 89 TB2 tasks all
|
||||
# making tool calls). Too small = thread pool starvation, tasks queue for minutes.
|
||||
|
||||
+175
-13
@@ -2,41 +2,203 @@
|
||||
Monkey patches for making hermes-agent tools work inside async frameworks (Atropos).
|
||||
|
||||
Problem:
|
||||
Some tools use asyncio.run() internally (e.g., Modal backend via SWE-ReX,
|
||||
Some tools use asyncio.run() internally (e.g., mini-swe-agent's Modal backend,
|
||||
web_extract). This crashes when called from inside Atropos's event loop because
|
||||
asyncio.run() can't be nested.
|
||||
|
||||
Solution:
|
||||
The Modal environment (tools/environments/modal.py) now uses a dedicated
|
||||
_AsyncWorker thread internally, making it safe for both CLI and Atropos use.
|
||||
No monkey-patching is required.
|
||||
Replace the problematic methods with versions that use a dedicated background
|
||||
thread with its own event loop. The calling code sees the same sync interface --
|
||||
call a function, get a result -- but internally the async work happens on a
|
||||
separate thread that doesn't conflict with Atropos's loop.
|
||||
|
||||
This module is kept for backward compatibility — apply_patches() is now a no-op.
|
||||
These patches are safe for normal CLI use too: when there's no running event
|
||||
loop, the behavior is identical (the background thread approach works regardless).
|
||||
|
||||
What gets patched:
|
||||
- SwerexModalEnvironment.__init__ -- creates Modal deployment on a background thread
|
||||
- SwerexModalEnvironment.execute -- runs commands on the same background thread
|
||||
- SwerexModalEnvironment.stop -- stops deployment on the background thread
|
||||
|
||||
Usage:
|
||||
Call apply_patches() once at import time (done automatically by hermes_base_env.py).
|
||||
This is idempotent — calling it multiple times is safe.
|
||||
This is idempotent -- calling it multiple times is safe.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import logging
|
||||
import threading
|
||||
from typing import Any
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_patches_applied = False
|
||||
|
||||
|
||||
def apply_patches():
|
||||
"""Apply all monkey patches needed for Atropos compatibility.
|
||||
class _AsyncWorker:
|
||||
"""
|
||||
A dedicated background thread with its own event loop.
|
||||
|
||||
Now a no-op — Modal async safety is built directly into ModalEnvironment.
|
||||
Safe to call multiple times.
|
||||
Allows sync code to submit async coroutines and block for results,
|
||||
even when called from inside another running event loop. Used to
|
||||
bridge sync tool interfaces with async backends (Modal, SWE-ReX).
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
self._loop: asyncio.AbstractEventLoop = None
|
||||
self._thread: threading.Thread = None
|
||||
self._started = threading.Event()
|
||||
|
||||
def start(self):
|
||||
"""Start the background event loop thread."""
|
||||
self._thread = threading.Thread(target=self._run_loop, daemon=True)
|
||||
self._thread.start()
|
||||
self._started.wait(timeout=30)
|
||||
|
||||
def _run_loop(self):
|
||||
"""Background thread entry point -- runs the event loop forever."""
|
||||
self._loop = asyncio.new_event_loop()
|
||||
asyncio.set_event_loop(self._loop)
|
||||
self._started.set()
|
||||
self._loop.run_forever()
|
||||
|
||||
def run_coroutine(self, coro, timeout=600):
|
||||
"""
|
||||
Submit a coroutine to the background loop and block until it completes.
|
||||
|
||||
Safe to call from any thread, including threads that already have
|
||||
a running event loop.
|
||||
"""
|
||||
if self._loop is None or self._loop.is_closed():
|
||||
raise RuntimeError("AsyncWorker loop is not running")
|
||||
future = asyncio.run_coroutine_threadsafe(coro, self._loop)
|
||||
return future.result(timeout=timeout)
|
||||
|
||||
def stop(self):
|
||||
"""Stop the background event loop and join the thread."""
|
||||
if self._loop and self._loop.is_running():
|
||||
self._loop.call_soon_threadsafe(self._loop.stop)
|
||||
if self._thread:
|
||||
self._thread.join(timeout=10)
|
||||
|
||||
|
||||
def _patch_swerex_modal():
|
||||
"""
|
||||
Monkey patch SwerexModalEnvironment to use a background thread event loop
|
||||
instead of asyncio.run(). This makes it safe to call from inside Atropos's
|
||||
async event loop.
|
||||
|
||||
The patched methods have the exact same interface and behavior -- the only
|
||||
difference is HOW the async work is executed internally.
|
||||
"""
|
||||
try:
|
||||
from minisweagent.environments.extra.swerex_modal import (
|
||||
SwerexModalEnvironment,
|
||||
SwerexModalEnvironmentConfig,
|
||||
)
|
||||
from swerex.deployment.modal import ModalDeployment
|
||||
from swerex.runtime.abstract import Command as RexCommand
|
||||
except ImportError:
|
||||
# mini-swe-agent or swe-rex not installed -- nothing to patch
|
||||
logger.debug("mini-swe-agent Modal backend not available, skipping patch")
|
||||
return
|
||||
|
||||
# Save original methods so we can refer to config handling
|
||||
_original_init = SwerexModalEnvironment.__init__
|
||||
|
||||
def _patched_init(self, **kwargs):
|
||||
"""Patched __init__: creates Modal deployment on a background thread."""
|
||||
self.config = SwerexModalEnvironmentConfig(**kwargs)
|
||||
|
||||
# Start a dedicated event loop thread for all Modal async operations
|
||||
self._worker = _AsyncWorker()
|
||||
self._worker.start()
|
||||
|
||||
# Pre-build a modal.Image with pip fix for Modal's legacy image builder.
|
||||
# Modal requires `python -m pip` to work during image build, but some
|
||||
# task images (e.g., TBLite's broken-python) have intentionally broken pip.
|
||||
# Fix: remove stale pip dist-info and reinstall via ensurepip before Modal
|
||||
# tries to use it. This is a no-op for images where pip already works.
|
||||
import modal as _modal
|
||||
image_spec = self.config.image
|
||||
if isinstance(image_spec, str):
|
||||
image_spec = _modal.Image.from_registry(
|
||||
image_spec,
|
||||
setup_dockerfile_commands=[
|
||||
"RUN rm -rf /usr/local/lib/python*/site-packages/pip* 2>/dev/null; "
|
||||
"python -m ensurepip --upgrade --default-pip 2>/dev/null || true",
|
||||
],
|
||||
)
|
||||
|
||||
# Create AND start the deployment entirely on the worker's loop/thread
|
||||
# so all gRPC channels and async state are bound to that loop
|
||||
async def _create_and_start():
|
||||
deployment = ModalDeployment(
|
||||
image=image_spec,
|
||||
startup_timeout=self.config.startup_timeout,
|
||||
runtime_timeout=self.config.runtime_timeout,
|
||||
deployment_timeout=self.config.deployment_timeout,
|
||||
install_pipx=self.config.install_pipx,
|
||||
modal_sandbox_kwargs=self.config.modal_sandbox_kwargs,
|
||||
)
|
||||
await deployment.start()
|
||||
return deployment
|
||||
|
||||
self.deployment = self._worker.run_coroutine(_create_and_start())
|
||||
|
||||
def _patched_execute(self, command: str, cwd: str = "", *, timeout: int | None = None) -> dict[str, Any]:
|
||||
"""Patched execute: runs commands on the background thread's loop."""
|
||||
async def _do_execute():
|
||||
return await self.deployment.runtime.execute(
|
||||
RexCommand(
|
||||
command=command,
|
||||
shell=True,
|
||||
check=False,
|
||||
cwd=cwd or self.config.cwd,
|
||||
timeout=timeout or self.config.timeout,
|
||||
merge_output_streams=True,
|
||||
env=self.config.env if self.config.env else None,
|
||||
)
|
||||
)
|
||||
|
||||
output = self._worker.run_coroutine(_do_execute())
|
||||
return {
|
||||
"output": output.stdout,
|
||||
"returncode": output.exit_code,
|
||||
}
|
||||
|
||||
def _patched_stop(self):
|
||||
"""Patched stop: stops deployment on the background thread, then stops the thread."""
|
||||
try:
|
||||
self._worker.run_coroutine(
|
||||
asyncio.wait_for(self.deployment.stop(), timeout=10),
|
||||
timeout=15,
|
||||
)
|
||||
except Exception:
|
||||
pass
|
||||
finally:
|
||||
self._worker.stop()
|
||||
|
||||
# Apply the patches
|
||||
SwerexModalEnvironment.__init__ = _patched_init
|
||||
SwerexModalEnvironment.execute = _patched_execute
|
||||
SwerexModalEnvironment.stop = _patched_stop
|
||||
|
||||
logger.debug("Patched SwerexModalEnvironment for async-safe operation")
|
||||
|
||||
|
||||
def apply_patches():
|
||||
"""
|
||||
Apply all monkey patches needed for Atropos compatibility.
|
||||
|
||||
Safe to call multiple times -- patches are only applied once.
|
||||
Safe for normal CLI use -- patched code works identically when
|
||||
there is no running event loop.
|
||||
"""
|
||||
global _patches_applied
|
||||
if _patches_applied:
|
||||
return
|
||||
|
||||
# Modal async-safety is now built into tools/environments/modal.py
|
||||
# via the _AsyncWorker class. No monkey-patching needed.
|
||||
logger.debug("apply_patches() called — no patches needed (async safety is built-in)")
|
||||
_patch_swerex_modal()
|
||||
|
||||
_patches_applied = True
|
||||
|
||||
+2
-7
@@ -523,13 +523,8 @@ def load_gateway_config() -> GatewayConfig:
|
||||
os.environ["DISCORD_FREE_RESPONSE_CHANNELS"] = str(frc)
|
||||
if "auto_thread" in discord_cfg and not os.getenv("DISCORD_AUTO_THREAD"):
|
||||
os.environ["DISCORD_AUTO_THREAD"] = str(discord_cfg["auto_thread"]).lower()
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
"Failed to process config.yaml — falling back to .env / gateway.json values. "
|
||||
"Check %s for syntax errors. Error: %s",
|
||||
_home / "config.yaml",
|
||||
e,
|
||||
)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
config = GatewayConfig.from_dict(gw_data)
|
||||
|
||||
|
||||
+75
-114
@@ -93,9 +93,6 @@ if _config_path.exists():
|
||||
import yaml as _yaml
|
||||
with open(_config_path, encoding="utf-8") as _f:
|
||||
_cfg = _yaml.safe_load(_f) or {}
|
||||
# Expand ${ENV_VAR} references before bridging to env vars.
|
||||
from hermes_cli.config import _expand_env_vars
|
||||
_cfg = _expand_env_vars(_cfg)
|
||||
# Top-level simple values (fallback only — don't override .env)
|
||||
for _key, _val in _cfg.items():
|
||||
if isinstance(_val, (str, int, float, bool)) and _key not in os.environ:
|
||||
@@ -528,12 +525,6 @@ class GatewayRunner:
|
||||
Synchronous worker — meant to be called via run_in_executor from
|
||||
an async context so it doesn't block the event loop.
|
||||
"""
|
||||
# Skip cron sessions — they run headless with no meaningful user
|
||||
# conversation to extract memories from.
|
||||
if old_session_id and old_session_id.startswith("cron_"):
|
||||
logger.debug("Skipping memory flush for cron session: %s", old_session_id)
|
||||
return
|
||||
|
||||
try:
|
||||
history = self.session_store.load_transcript(old_session_id)
|
||||
if not history or len(history) < 4:
|
||||
@@ -566,23 +557,6 @@ class GatewayRunner:
|
||||
if m.get("role") in ("user", "assistant") and m.get("content")
|
||||
]
|
||||
|
||||
# Read live memory state from disk so the flush agent can see
|
||||
# what's already saved and avoid overwriting newer entries.
|
||||
_current_memory = ""
|
||||
try:
|
||||
from tools.memory_tool import MEMORY_DIR
|
||||
for fname, label in [
|
||||
("MEMORY.md", "MEMORY (your personal notes)"),
|
||||
("USER.md", "USER PROFILE (who the user is)"),
|
||||
]:
|
||||
fpath = MEMORY_DIR / fname
|
||||
if fpath.exists():
|
||||
content = fpath.read_text(encoding="utf-8").strip()
|
||||
if content:
|
||||
_current_memory += f"\n\n## Current {label}:\n{content}"
|
||||
except Exception:
|
||||
pass # Non-fatal — flush still works, just without the guard
|
||||
|
||||
# Give the agent a real turn to think about what to save
|
||||
flush_prompt = (
|
||||
"[System: This session is about to be automatically reset due to "
|
||||
@@ -594,20 +568,6 @@ class GatewayRunner:
|
||||
"2. If you discovered a reusable workflow or solved a non-trivial "
|
||||
"problem, consider saving it as a skill.\n"
|
||||
"3. If nothing is worth saving, that's fine — just skip.\n\n"
|
||||
)
|
||||
|
||||
if _current_memory:
|
||||
flush_prompt += (
|
||||
"IMPORTANT — here is the current live state of memory. Other "
|
||||
"sessions, cron jobs, or the user may have updated it since this "
|
||||
"conversation ended. Do NOT overwrite or remove entries unless "
|
||||
"the conversation above reveals something that genuinely "
|
||||
"supersedes them. Only add new information that is not already "
|
||||
"captured below."
|
||||
f"{_current_memory}\n\n"
|
||||
)
|
||||
|
||||
flush_prompt += (
|
||||
"Do NOT respond to the user. Just use the memory and skill_manage "
|
||||
"tools if needed, then stop.]"
|
||||
)
|
||||
@@ -944,9 +904,7 @@ class GatewayRunner:
|
||||
os.getenv(v)
|
||||
for v in ("TELEGRAM_ALLOWED_USERS", "DISCORD_ALLOWED_USERS",
|
||||
"WHATSAPP_ALLOWED_USERS", "SLACK_ALLOWED_USERS",
|
||||
"SIGNAL_ALLOWED_USERS", "EMAIL_ALLOWED_USERS",
|
||||
"SMS_ALLOWED_USERS", "MATTERMOST_ALLOWED_USERS",
|
||||
"MATRIX_ALLOWED_USERS", "DINGTALK_ALLOWED_USERS",
|
||||
"SMS_ALLOWED_USERS",
|
||||
"GATEWAY_ALLOWED_USERS")
|
||||
)
|
||||
_allow_all = os.getenv("GATEWAY_ALLOW_ALL_USERS", "").lower() in ("true", "1", "yes")
|
||||
@@ -2851,63 +2809,70 @@ class GatewayRunner:
|
||||
lines.append("Switch provider: `/model provider-name` or `/model provider:model-name`")
|
||||
return "\n".join(lines)
|
||||
|
||||
# Handle bare "/model custom" — switch to custom provider
|
||||
# and auto-detect the model from the endpoint.
|
||||
if args.strip().lower() == "custom":
|
||||
from hermes_cli.model_switch import switch_to_custom_provider
|
||||
cust_result = switch_to_custom_provider()
|
||||
if not cust_result.success:
|
||||
return f"⚠️ {cust_result.error_message}"
|
||||
try:
|
||||
user_config = {}
|
||||
if config_path.exists():
|
||||
with open(config_path, encoding="utf-8") as f:
|
||||
user_config = yaml.safe_load(f) or {}
|
||||
if "model" not in user_config or not isinstance(user_config["model"], dict):
|
||||
user_config["model"] = {}
|
||||
user_config["model"]["default"] = cust_result.model
|
||||
user_config["model"]["provider"] = "custom"
|
||||
user_config["model"]["base_url"] = cust_result.base_url
|
||||
with open(config_path, 'w', encoding="utf-8") as f:
|
||||
yaml.dump(user_config, f, default_flow_style=False, sort_keys=False)
|
||||
except Exception as e:
|
||||
return f"⚠️ Failed to save model change: {e}"
|
||||
os.environ["HERMES_MODEL"] = cust_result.model
|
||||
os.environ["HERMES_INFERENCE_PROVIDER"] = "custom"
|
||||
self._effective_model = None
|
||||
self._effective_provider = None
|
||||
return (
|
||||
f"🤖 Model changed to `{cust_result.model}` (saved to config)\n"
|
||||
f"**Provider:** Custom\n"
|
||||
f"**Endpoint:** `{cust_result.base_url}`\n"
|
||||
f"_Model auto-detected from endpoint. Takes effect on next message._"
|
||||
)
|
||||
# Parse provider:model syntax
|
||||
target_provider, new_model = parse_model_input(args, current_provider)
|
||||
|
||||
# Core model-switching pipeline (shared with CLI)
|
||||
from hermes_cli.model_switch import switch_model
|
||||
|
||||
# Resolve current base_url for is_custom detection
|
||||
# Detect custom/local provider — skip auto-detection to prevent
|
||||
# silently accepting an OpenRouter model name on a localhost endpoint.
|
||||
# Users must use explicit provider:model syntax to switch away.
|
||||
_resolved_base = ""
|
||||
try:
|
||||
from hermes_cli.runtime_provider import resolve_runtime_provider as _rtp
|
||||
_resolved_base = _rtp(requested=current_provider).get("base_url", "")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
result = switch_model(
|
||||
args,
|
||||
current_provider,
|
||||
current_base_url=_resolved_base,
|
||||
current_api_key=os.getenv("OPENROUTER_API_KEY") or os.getenv("OPENAI_API_KEY") or "",
|
||||
is_custom = current_provider == "custom" or (
|
||||
"localhost" in _resolved_base or "127.0.0.1" in _resolved_base
|
||||
)
|
||||
|
||||
if not result.success:
|
||||
msg = result.error_message
|
||||
# Auto-detect provider when no explicit provider:model syntax was used
|
||||
if target_provider == current_provider and not is_custom:
|
||||
from hermes_cli.models import detect_provider_for_model
|
||||
detected = detect_provider_for_model(new_model, current_provider)
|
||||
if detected:
|
||||
target_provider, new_model = detected
|
||||
provider_changed = target_provider != current_provider
|
||||
|
||||
# Resolve credentials for the target provider (for API probe)
|
||||
api_key = os.getenv("OPENROUTER_API_KEY") or os.getenv("OPENAI_API_KEY") or ""
|
||||
base_url = "https://openrouter.ai/api/v1"
|
||||
if provider_changed:
|
||||
try:
|
||||
from hermes_cli.runtime_provider import resolve_runtime_provider
|
||||
runtime = resolve_runtime_provider(requested=target_provider)
|
||||
api_key = runtime.get("api_key", "")
|
||||
base_url = runtime.get("base_url", "")
|
||||
except Exception as e:
|
||||
provider_label = _PROVIDER_LABELS.get(target_provider, target_provider)
|
||||
return f"⚠️ Could not resolve credentials for provider '{provider_label}': {e}"
|
||||
else:
|
||||
# Use current provider's base_url from config or registry
|
||||
try:
|
||||
from hermes_cli.runtime_provider import resolve_runtime_provider
|
||||
runtime = resolve_runtime_provider(requested=current_provider)
|
||||
api_key = runtime.get("api_key", "")
|
||||
base_url = runtime.get("base_url", "")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Validate the model against the live API
|
||||
try:
|
||||
validation = validate_requested_model(
|
||||
new_model,
|
||||
target_provider,
|
||||
api_key=api_key,
|
||||
base_url=base_url,
|
||||
)
|
||||
except Exception:
|
||||
validation = {"accepted": True, "persist": True, "recognized": False, "message": None}
|
||||
|
||||
if not validation.get("accepted"):
|
||||
msg = validation.get("message", "Invalid model")
|
||||
tip = "\n\nUse `/model` to see available models, `/provider` to see providers" if "Did you mean" not in msg else ""
|
||||
return f"⚠️ {msg}{tip}"
|
||||
|
||||
# Persist to config only if validation approves
|
||||
if result.persist:
|
||||
if validation.get("persist"):
|
||||
try:
|
||||
user_config = {}
|
||||
if config_path.exists():
|
||||
@@ -2915,49 +2880,45 @@ class GatewayRunner:
|
||||
user_config = yaml.safe_load(f) or {}
|
||||
if "model" not in user_config or not isinstance(user_config["model"], dict):
|
||||
user_config["model"] = {}
|
||||
user_config["model"]["default"] = result.new_model
|
||||
if result.provider_changed:
|
||||
user_config["model"]["provider"] = result.target_provider
|
||||
# Persist base_url for custom endpoints; clear when
|
||||
# switching away from custom (#2562 Phase 2).
|
||||
if result.base_url and "openrouter.ai" not in (result.base_url or ""):
|
||||
user_config["model"]["base_url"] = result.base_url
|
||||
else:
|
||||
user_config["model"].pop("base_url", None)
|
||||
user_config["model"]["default"] = new_model
|
||||
if provider_changed:
|
||||
user_config["model"]["provider"] = target_provider
|
||||
with open(config_path, 'w', encoding="utf-8") as f:
|
||||
yaml.dump(user_config, f, default_flow_style=False, sort_keys=False)
|
||||
except Exception as e:
|
||||
return f"⚠️ Failed to save model change: {e}"
|
||||
|
||||
# Set env vars so the next agent run picks up the change
|
||||
os.environ["HERMES_MODEL"] = result.new_model
|
||||
if result.provider_changed:
|
||||
os.environ["HERMES_INFERENCE_PROVIDER"] = result.target_provider
|
||||
os.environ["HERMES_MODEL"] = new_model
|
||||
if provider_changed:
|
||||
os.environ["HERMES_INFERENCE_PROVIDER"] = target_provider
|
||||
|
||||
provider_note = f"\n**Provider:** {result.provider_label}" if result.provider_changed else ""
|
||||
provider_label = _PROVIDER_LABELS.get(target_provider, target_provider)
|
||||
provider_note = f"\n**Provider:** {provider_label}" if provider_changed else ""
|
||||
|
||||
warning = ""
|
||||
if result.warning_message:
|
||||
warning = f"\n⚠️ {result.warning_message}"
|
||||
|
||||
persist_note = "saved to config" if result.persist else "this session only — will revert on restart"
|
||||
if validation.get("message"):
|
||||
warning = f"\n⚠️ {validation['message']}"
|
||||
|
||||
if validation.get("persist"):
|
||||
persist_note = "saved to config"
|
||||
else:
|
||||
persist_note = "this session only — will revert on restart"
|
||||
# Clear fallback state since user explicitly chose a model
|
||||
self._effective_model = None
|
||||
self._effective_provider = None
|
||||
|
||||
# Show endpoint info for custom providers
|
||||
# Helpful hint when staying on a custom/local endpoint
|
||||
custom_hint = ""
|
||||
if result.is_custom_target:
|
||||
endpoint = result.base_url or _resolved_base or "custom endpoint"
|
||||
custom_hint = f"\n**Endpoint:** `{endpoint}`"
|
||||
if not result.provider_changed:
|
||||
custom_hint += (
|
||||
"\n_To switch providers, use_ `/model provider:model`"
|
||||
"\n_e.g._ `/model openrouter:anthropic/claude-sonnet-4`"
|
||||
)
|
||||
if is_custom and not provider_changed:
|
||||
endpoint = _resolved_base or "custom endpoint"
|
||||
custom_hint = (
|
||||
f"\n**Endpoint:** `{endpoint}`"
|
||||
"\n_To switch providers, use_ `/model provider:model`"
|
||||
"\n_e.g._ `/model openrouter:anthropic/claude-sonnet-4`"
|
||||
)
|
||||
|
||||
return f"🤖 Model changed to `{result.new_model}` ({persist_note}){provider_note}{warning}{custom_hint}\n_(takes effect on next message)_"
|
||||
return f"🤖 Model changed to `{new_model}` ({persist_note}){provider_note}{warning}{custom_hint}\n_(takes effect on next message)_"
|
||||
|
||||
async def _handle_provider_command(self, event: MessageEvent) -> str:
|
||||
"""Handle /provider command - show available providers."""
|
||||
|
||||
@@ -12,4 +12,4 @@ Provides subcommands for:
|
||||
"""
|
||||
|
||||
__version__ = "0.4.0"
|
||||
__release_date__ = "2026.3.23"
|
||||
__release_date__ = "2026.3.18"
|
||||
|
||||
+1
-3
@@ -690,10 +690,8 @@ def resolve_provider(
|
||||
}
|
||||
normalized = _PROVIDER_ALIASES.get(normalized, normalized)
|
||||
|
||||
if normalized == "openrouter":
|
||||
if normalized in {"openrouter", "custom"}:
|
||||
return "openrouter"
|
||||
if normalized == "custom":
|
||||
return "custom"
|
||||
if normalized in PROVIDER_REGISTRY:
|
||||
return normalized
|
||||
if normalized != "auto":
|
||||
|
||||
+3
-32
@@ -119,10 +119,6 @@ DEFAULT_CONFIG = {
|
||||
"backend": "local",
|
||||
"cwd": ".", # Use current directory
|
||||
"timeout": 180,
|
||||
# Environment variables to pass through to sandboxed execution
|
||||
# (terminal and execute_code). Skill-declared required_environment_variables
|
||||
# are passed through automatically; this list is for non-skill use cases.
|
||||
"env_passthrough": [],
|
||||
"docker_image": "nikolaik/python-nodejs:python3.11-nodejs20",
|
||||
"docker_forward_env": [],
|
||||
"singularity_image": "docker://nikolaik/python-nodejs:python3.11-nodejs20",
|
||||
@@ -149,7 +145,6 @@ DEFAULT_CONFIG = {
|
||||
|
||||
"browser": {
|
||||
"inactivity_timeout": 120,
|
||||
"command_timeout": 30, # Timeout for browser commands in seconds (screenshot, navigate, etc.)
|
||||
"record_sessions": False, # Auto-record browser sessions as WebM videos
|
||||
},
|
||||
|
||||
@@ -163,10 +158,8 @@ DEFAULT_CONFIG = {
|
||||
|
||||
"compression": {
|
||||
"enabled": True,
|
||||
"threshold": 0.50, # compress when context usage exceeds this ratio
|
||||
"target_ratio": 0.20, # fraction of threshold to preserve as recent tail
|
||||
"protect_last_n": 20, # minimum recent messages to keep uncompressed
|
||||
"summary_model": "", # empty = use main configured model
|
||||
"threshold": 0.50,
|
||||
"summary_model": "", # empty = use main configured model
|
||||
"summary_provider": "auto",
|
||||
"summary_base_url": None,
|
||||
},
|
||||
@@ -1179,26 +1172,6 @@ def _deep_merge(base: dict, override: dict) -> dict:
|
||||
return result
|
||||
|
||||
|
||||
def _expand_env_vars(obj):
|
||||
"""Recursively expand ``${VAR}`` references in config values.
|
||||
|
||||
Only string values are processed; dict keys, numbers, booleans, and
|
||||
None are left untouched. Unresolved references (variable not in
|
||||
``os.environ``) are kept verbatim so callers can detect them.
|
||||
"""
|
||||
if isinstance(obj, str):
|
||||
return re.sub(
|
||||
r"\${([^}]+)}",
|
||||
lambda m: os.environ.get(m.group(1), m.group(0)),
|
||||
obj,
|
||||
)
|
||||
if isinstance(obj, dict):
|
||||
return {k: _expand_env_vars(v) for k, v in obj.items()}
|
||||
if isinstance(obj, list):
|
||||
return [_expand_env_vars(item) for item in obj]
|
||||
return obj
|
||||
|
||||
|
||||
def _normalize_max_turns_config(config: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Normalize legacy root-level max_turns into agent.max_turns."""
|
||||
config = dict(config)
|
||||
@@ -1240,7 +1213,7 @@ def load_config() -> Dict[str, Any]:
|
||||
except Exception as e:
|
||||
print(f"Warning: Failed to load config: {e}")
|
||||
|
||||
return _expand_env_vars(_normalize_max_turns_config(config))
|
||||
return _normalize_max_turns_config(config)
|
||||
|
||||
|
||||
_SECURITY_COMMENT = """
|
||||
@@ -1687,8 +1660,6 @@ def show_config():
|
||||
print(f" Enabled: {'yes' if enabled else 'no'}")
|
||||
if enabled:
|
||||
print(f" Threshold: {compression.get('threshold', 0.50) * 100:.0f}%")
|
||||
print(f" Target ratio: {compression.get('target_ratio', 0.20) * 100:.0f}% of threshold preserved")
|
||||
print(f" Protect last: {compression.get('protect_last_n', 20)} messages")
|
||||
_sm = compression.get('summary_model', '') or '(main model)'
|
||||
print(f" Model: {_sm}")
|
||||
comp_provider = compression.get('summary_provider', 'auto')
|
||||
|
||||
@@ -26,6 +26,10 @@ if _env_path.exists():
|
||||
# Also try project .env as dev fallback
|
||||
load_dotenv(PROJECT_ROOT / ".env", override=False, encoding="utf-8")
|
||||
|
||||
# Point mini-swe-agent at ~/.hermes/ so it shares our config
|
||||
os.environ.setdefault("MSWEA_GLOBAL_CONFIG_DIR", str(HERMES_HOME))
|
||||
os.environ.setdefault("MSWEA_SILENT_STARTUP", "1")
|
||||
|
||||
from hermes_cli.colors import Colors, color
|
||||
from hermes_constants import OPENROUTER_MODELS_URL
|
||||
|
||||
@@ -614,6 +618,18 @@ def run_doctor(args):
|
||||
print()
|
||||
print(color("◆ Submodules", Colors.CYAN, Colors.BOLD))
|
||||
|
||||
# mini-swe-agent (terminal tool backend)
|
||||
mini_swe_dir = PROJECT_ROOT / "mini-swe-agent"
|
||||
if mini_swe_dir.exists() and (mini_swe_dir / "pyproject.toml").exists():
|
||||
try:
|
||||
__import__("minisweagent")
|
||||
check_ok("mini-swe-agent", "(terminal backend)")
|
||||
except ImportError:
|
||||
check_warn("mini-swe-agent found but not installed", "(run: uv pip install -e ./mini-swe-agent)")
|
||||
issues.append("Install mini-swe-agent: uv pip install -e ./mini-swe-agent")
|
||||
else:
|
||||
check_warn("mini-swe-agent not found", "(run: git submodule update --init --recursive)")
|
||||
|
||||
# tinker-atropos (RL training backend)
|
||||
tinker_dir = PROJECT_ROOT / "tinker-atropos"
|
||||
if tinker_dir.exists() and (tinker_dir / "pyproject.toml").exists():
|
||||
|
||||
+8
-33
@@ -371,37 +371,13 @@ def print_systemd_linger_guidance() -> None:
|
||||
def get_launchd_plist_path() -> Path:
|
||||
return Path.home() / "Library" / "LaunchAgents" / "ai.hermes.gateway.plist"
|
||||
|
||||
def _detect_venv_dir() -> Path | None:
|
||||
"""Detect the active virtualenv directory.
|
||||
|
||||
Checks ``sys.prefix`` first (works regardless of the directory name),
|
||||
then falls back to probing common directory names under PROJECT_ROOT.
|
||||
Returns ``None`` when no virtualenv can be found.
|
||||
"""
|
||||
# If we're running inside a virtualenv, sys.prefix points to it.
|
||||
if sys.prefix != sys.base_prefix:
|
||||
venv = Path(sys.prefix)
|
||||
if venv.is_dir():
|
||||
return venv
|
||||
|
||||
# Fallback: check common virtualenv directory names under the project root.
|
||||
for candidate in (".venv", "venv"):
|
||||
venv = PROJECT_ROOT / candidate
|
||||
if venv.is_dir():
|
||||
return venv
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def get_python_path() -> str:
|
||||
venv = _detect_venv_dir()
|
||||
if venv is not None:
|
||||
if is_windows():
|
||||
venv_python = venv / "Scripts" / "python.exe"
|
||||
else:
|
||||
venv_python = venv / "bin" / "python"
|
||||
if venv_python.exists():
|
||||
return str(venv_python)
|
||||
if is_windows():
|
||||
venv_python = PROJECT_ROOT / "venv" / "Scripts" / "python.exe"
|
||||
else:
|
||||
venv_python = PROJECT_ROOT / "venv" / "bin" / "python"
|
||||
if venv_python.exists():
|
||||
return str(venv_python)
|
||||
return sys.executable
|
||||
|
||||
def get_hermes_cli_path() -> str:
|
||||
@@ -423,9 +399,8 @@ def get_hermes_cli_path() -> str:
|
||||
def generate_systemd_unit(system: bool = False, run_as_user: str | None = None) -> str:
|
||||
python_path = get_python_path()
|
||||
working_dir = str(PROJECT_ROOT)
|
||||
detected_venv = _detect_venv_dir()
|
||||
venv_dir = str(detected_venv) if detected_venv else str(PROJECT_ROOT / "venv")
|
||||
venv_bin = str(detected_venv / "bin") if detected_venv else str(PROJECT_ROOT / "venv" / "bin")
|
||||
venv_dir = str(PROJECT_ROOT / "venv")
|
||||
venv_bin = str(PROJECT_ROOT / "venv" / "bin")
|
||||
node_bin = str(PROJECT_ROOT / "node_modules" / ".bin")
|
||||
|
||||
path_entries = [venv_bin, node_bin]
|
||||
|
||||
@@ -60,6 +60,9 @@ from hermes_cli.config import get_hermes_home
|
||||
from hermes_cli.env_loader import load_hermes_dotenv
|
||||
load_hermes_dotenv(project_env=PROJECT_ROOT / '.env')
|
||||
|
||||
# Point mini-swe-agent at ~/.hermes/ so it shares our config
|
||||
os.environ.setdefault("MSWEA_GLOBAL_CONFIG_DIR", str(get_hermes_home()))
|
||||
os.environ.setdefault("MSWEA_SILENT_STARTUP", "1")
|
||||
|
||||
import logging
|
||||
import time as _time
|
||||
|
||||
@@ -1,234 +0,0 @@
|
||||
"""Shared model-switching logic for CLI and gateway /model commands.
|
||||
|
||||
Both the CLI (cli.py) and gateway (gateway/run.py) /model handlers
|
||||
share the same core pipeline:
|
||||
|
||||
parse_model_input → is_custom detection → auto-detect provider
|
||||
→ credential resolution → validate model → return result
|
||||
|
||||
This module extracts that shared pipeline into pure functions that
|
||||
return result objects. The callers handle all platform-specific
|
||||
concerns: state mutation, config persistence, output formatting.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Optional
|
||||
|
||||
|
||||
@dataclass
|
||||
class ModelSwitchResult:
|
||||
"""Result of a model switch attempt."""
|
||||
|
||||
success: bool
|
||||
new_model: str = ""
|
||||
target_provider: str = ""
|
||||
provider_changed: bool = False
|
||||
api_key: str = ""
|
||||
base_url: str = ""
|
||||
persist: bool = False
|
||||
error_message: str = ""
|
||||
warning_message: str = ""
|
||||
is_custom_target: bool = False
|
||||
provider_label: str = ""
|
||||
|
||||
|
||||
@dataclass
|
||||
class CustomAutoResult:
|
||||
"""Result of switching to bare 'custom' provider with auto-detect."""
|
||||
|
||||
success: bool
|
||||
model: str = ""
|
||||
base_url: str = ""
|
||||
api_key: str = ""
|
||||
error_message: str = ""
|
||||
|
||||
|
||||
def switch_model(
|
||||
raw_input: str,
|
||||
current_provider: str,
|
||||
current_base_url: str = "",
|
||||
current_api_key: str = "",
|
||||
) -> ModelSwitchResult:
|
||||
"""Core model-switching pipeline shared between CLI and gateway.
|
||||
|
||||
Handles parsing, provider detection, credential resolution, and
|
||||
model validation. Does NOT handle config persistence, state
|
||||
mutation, or output formatting — those are caller responsibilities.
|
||||
|
||||
Args:
|
||||
raw_input: The user's model input (e.g. "claude-sonnet-4",
|
||||
"zai:glm-5", "custom:local:qwen").
|
||||
current_provider: The currently active provider.
|
||||
current_base_url: The currently active base URL (used for
|
||||
is_custom detection).
|
||||
current_api_key: The currently active API key.
|
||||
|
||||
Returns:
|
||||
ModelSwitchResult with all information the caller needs to
|
||||
apply the switch and format output.
|
||||
"""
|
||||
from hermes_cli.models import (
|
||||
parse_model_input,
|
||||
detect_provider_for_model,
|
||||
validate_requested_model,
|
||||
_PROVIDER_LABELS,
|
||||
)
|
||||
from hermes_cli.runtime_provider import resolve_runtime_provider
|
||||
|
||||
# Step 1: Parse provider:model syntax
|
||||
target_provider, new_model = parse_model_input(raw_input, current_provider)
|
||||
|
||||
# Step 2: Detect if we're currently on a custom endpoint
|
||||
_base = current_base_url or ""
|
||||
is_custom = current_provider == "custom" or (
|
||||
"localhost" in _base or "127.0.0.1" in _base
|
||||
)
|
||||
|
||||
# Step 3: Auto-detect provider when no explicit provider:model syntax
|
||||
# was used. Skip for custom providers — the model name might
|
||||
# coincidentally match a known provider's catalog.
|
||||
if target_provider == current_provider and not is_custom:
|
||||
detected = detect_provider_for_model(new_model, current_provider)
|
||||
if detected:
|
||||
target_provider, new_model = detected
|
||||
|
||||
provider_changed = target_provider != current_provider
|
||||
|
||||
# Step 4: Resolve credentials for target provider
|
||||
api_key = current_api_key
|
||||
base_url = current_base_url
|
||||
if provider_changed:
|
||||
try:
|
||||
runtime = resolve_runtime_provider(requested=target_provider)
|
||||
api_key = runtime.get("api_key", "")
|
||||
base_url = runtime.get("base_url", "")
|
||||
except Exception as e:
|
||||
provider_label = _PROVIDER_LABELS.get(target_provider, target_provider)
|
||||
if target_provider == "custom":
|
||||
return ModelSwitchResult(
|
||||
success=False,
|
||||
target_provider=target_provider,
|
||||
error_message=(
|
||||
"No custom endpoint configured. Set model.base_url "
|
||||
"in config.yaml, or set OPENAI_BASE_URL in .env, "
|
||||
"or run: hermes setup → Custom OpenAI-compatible endpoint"
|
||||
),
|
||||
)
|
||||
return ModelSwitchResult(
|
||||
success=False,
|
||||
target_provider=target_provider,
|
||||
error_message=(
|
||||
f"Could not resolve credentials for provider "
|
||||
f"'{provider_label}': {e}"
|
||||
),
|
||||
)
|
||||
else:
|
||||
# Gateway also resolves for unchanged provider to get accurate
|
||||
# base_url for validation probing.
|
||||
try:
|
||||
runtime = resolve_runtime_provider(requested=current_provider)
|
||||
api_key = runtime.get("api_key", "")
|
||||
base_url = runtime.get("base_url", "")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Step 5: Validate the model
|
||||
try:
|
||||
validation = validate_requested_model(
|
||||
new_model,
|
||||
target_provider,
|
||||
api_key=api_key,
|
||||
base_url=base_url,
|
||||
)
|
||||
except Exception:
|
||||
validation = {
|
||||
"accepted": True,
|
||||
"persist": True,
|
||||
"recognized": False,
|
||||
"message": None,
|
||||
}
|
||||
|
||||
if not validation.get("accepted"):
|
||||
msg = validation.get("message", "Invalid model")
|
||||
return ModelSwitchResult(
|
||||
success=False,
|
||||
new_model=new_model,
|
||||
target_provider=target_provider,
|
||||
error_message=msg,
|
||||
)
|
||||
|
||||
# Step 6: Build result
|
||||
provider_label = _PROVIDER_LABELS.get(target_provider, target_provider)
|
||||
is_custom_target = target_provider == "custom" or (
|
||||
base_url
|
||||
and "openrouter.ai" not in (base_url or "")
|
||||
and ("localhost" in (base_url or "") or "127.0.0.1" in (base_url or ""))
|
||||
)
|
||||
|
||||
return ModelSwitchResult(
|
||||
success=True,
|
||||
new_model=new_model,
|
||||
target_provider=target_provider,
|
||||
provider_changed=provider_changed,
|
||||
api_key=api_key,
|
||||
base_url=base_url,
|
||||
persist=bool(validation.get("persist")),
|
||||
warning_message=validation.get("message") or "",
|
||||
is_custom_target=is_custom_target,
|
||||
provider_label=provider_label,
|
||||
)
|
||||
|
||||
|
||||
def switch_to_custom_provider() -> CustomAutoResult:
|
||||
"""Handle bare '/model custom' — resolve endpoint and auto-detect model.
|
||||
|
||||
Returns a result object; the caller handles persistence and output.
|
||||
"""
|
||||
from hermes_cli.runtime_provider import (
|
||||
resolve_runtime_provider,
|
||||
_auto_detect_local_model,
|
||||
)
|
||||
|
||||
try:
|
||||
runtime = resolve_runtime_provider(requested="custom")
|
||||
except Exception as e:
|
||||
return CustomAutoResult(
|
||||
success=False,
|
||||
error_message=f"Could not resolve custom endpoint: {e}",
|
||||
)
|
||||
|
||||
cust_base = runtime.get("base_url", "")
|
||||
cust_key = runtime.get("api_key", "")
|
||||
|
||||
if not cust_base or "openrouter.ai" in cust_base:
|
||||
return CustomAutoResult(
|
||||
success=False,
|
||||
error_message=(
|
||||
"No custom endpoint configured. "
|
||||
"Set model.base_url in config.yaml, or set OPENAI_BASE_URL "
|
||||
"in .env, or run: hermes setup → Custom OpenAI-compatible endpoint"
|
||||
),
|
||||
)
|
||||
|
||||
detected_model = _auto_detect_local_model(cust_base)
|
||||
if not detected_model:
|
||||
return CustomAutoResult(
|
||||
success=False,
|
||||
base_url=cust_base,
|
||||
api_key=cust_key,
|
||||
error_message=(
|
||||
f"Custom endpoint at {cust_base} is reachable but no single "
|
||||
f"model was auto-detected. Specify the model explicitly: "
|
||||
f"/model custom:<model-name>"
|
||||
),
|
||||
)
|
||||
|
||||
return CustomAutoResult(
|
||||
success=True,
|
||||
model=detected_model,
|
||||
base_url=cust_base,
|
||||
api_key=cust_key,
|
||||
)
|
||||
@@ -345,15 +345,6 @@ def parse_model_input(raw: str, current_provider: str) -> tuple[str, str]:
|
||||
provider_part = stripped[:colon].strip().lower()
|
||||
model_part = stripped[colon + 1:].strip()
|
||||
if provider_part and model_part and provider_part in _KNOWN_PROVIDER_NAMES:
|
||||
# Support custom:name:model triple syntax for named custom
|
||||
# providers. ``custom:local:qwen`` → ("custom:local", "qwen").
|
||||
# Single colon ``custom:qwen`` → ("custom", "qwen") as before.
|
||||
if provider_part == "custom" and ":" in model_part:
|
||||
second_colon = model_part.find(":")
|
||||
custom_name = model_part[:second_colon].strip()
|
||||
actual_model = model_part[second_colon + 1:].strip()
|
||||
if custom_name and actual_model:
|
||||
return (f"custom:{custom_name}", actual_model)
|
||||
return (normalize_provider(provider_part), model_part)
|
||||
return (current_provider, stripped)
|
||||
|
||||
|
||||
@@ -198,7 +198,7 @@ def _resolve_named_custom_runtime(
|
||||
api_key = next((candidate for candidate in api_key_candidates if has_usable_secret(candidate)), "")
|
||||
|
||||
return {
|
||||
"provider": "custom",
|
||||
"provider": "openrouter",
|
||||
"api_mode": custom_provider.get("api_mode")
|
||||
or _detect_api_mode_for_url(base_url)
|
||||
or "chat_completions",
|
||||
@@ -279,16 +279,8 @@ def _resolve_openrouter_runtime(
|
||||
|
||||
source = "explicit" if (explicit_api_key or explicit_base_url) else "env/config"
|
||||
|
||||
# When "custom" was explicitly requested, preserve that as the provider
|
||||
# name instead of silently relabeling to "openrouter" (#2562).
|
||||
# Also provide a placeholder API key for local servers that don't require
|
||||
# authentication — the OpenAI SDK requires a non-empty api_key string.
|
||||
effective_provider = "custom" if requested_norm == "custom" else "openrouter"
|
||||
if effective_provider == "custom" and not api_key and not _is_openrouter_url:
|
||||
api_key = "no-key-required"
|
||||
|
||||
return {
|
||||
"provider": effective_provider,
|
||||
"provider": "openrouter",
|
||||
"api_mode": _parse_api_mode(model_cfg.get("api_mode"))
|
||||
or _detect_api_mode_for_url(base_url)
|
||||
or "chat_completions",
|
||||
|
||||
+77
-77
@@ -873,9 +873,9 @@ def setup_model_provider(config: dict):
|
||||
keep_label = None # No provider configured — don't show "Keep current"
|
||||
|
||||
provider_choices = [
|
||||
"OpenRouter API key (100+ models, pay-per-use)",
|
||||
"Login with Nous Portal (Nous Research subscription — OAuth)",
|
||||
"Login with OpenAI Codex",
|
||||
"OpenRouter API key (100+ models, pay-per-use)",
|
||||
"Custom OpenAI-compatible endpoint (self-hosted / VLLM / etc.)",
|
||||
"Z.AI / GLM (Zhipu AI models)",
|
||||
"Kimi / Moonshot (Kimi coding models)",
|
||||
@@ -894,7 +894,7 @@ def setup_model_provider(config: dict):
|
||||
provider_choices.append(keep_label)
|
||||
|
||||
# Default to "Keep current" if a provider exists, otherwise OpenRouter (most common)
|
||||
default_provider = len(provider_choices) - 1 if has_any_provider else 0
|
||||
default_provider = len(provider_choices) - 1 if has_any_provider else 2
|
||||
|
||||
if not has_any_provider:
|
||||
print_warning("An inference provider is required for Hermes to work.")
|
||||
@@ -911,7 +911,81 @@ def setup_model_provider(config: dict):
|
||||
selected_base_url = None # deferred until after model selection
|
||||
nous_models = [] # populated if Nous login succeeds
|
||||
|
||||
if provider_idx == 0: # OpenRouter
|
||||
if provider_idx == 0: # Nous Portal (OAuth)
|
||||
selected_provider = "nous"
|
||||
print()
|
||||
print_header("Nous Portal Login")
|
||||
print_info("This will open your browser to authenticate with Nous Portal.")
|
||||
print_info("You'll need a Nous Research account with an active subscription.")
|
||||
print()
|
||||
|
||||
try:
|
||||
from hermes_cli.auth import _login_nous, ProviderConfig
|
||||
import argparse
|
||||
|
||||
mock_args = argparse.Namespace(
|
||||
portal_url=None,
|
||||
inference_url=None,
|
||||
client_id=None,
|
||||
scope=None,
|
||||
no_browser=False,
|
||||
timeout=15.0,
|
||||
ca_bundle=None,
|
||||
insecure=False,
|
||||
)
|
||||
pconfig = PROVIDER_REGISTRY["nous"]
|
||||
_login_nous(mock_args, pconfig)
|
||||
_sync_model_from_disk(config)
|
||||
|
||||
# Fetch models for the selection step
|
||||
try:
|
||||
creds = resolve_nous_runtime_credentials(
|
||||
min_key_ttl_seconds=5 * 60,
|
||||
timeout_seconds=15.0,
|
||||
)
|
||||
nous_models = fetch_nous_models(
|
||||
inference_base_url=creds.get("base_url", ""),
|
||||
api_key=creds.get("api_key", ""),
|
||||
)
|
||||
except Exception as e:
|
||||
logger.debug("Could not fetch Nous models after login: %s", e)
|
||||
|
||||
except SystemExit:
|
||||
print_warning("Nous Portal login was cancelled or failed.")
|
||||
print_info("You can try again later with: hermes model")
|
||||
selected_provider = None
|
||||
except Exception as e:
|
||||
print_error(f"Login failed: {e}")
|
||||
print_info("You can try again later with: hermes model")
|
||||
selected_provider = None
|
||||
|
||||
elif provider_idx == 1: # OpenAI Codex
|
||||
selected_provider = "openai-codex"
|
||||
print()
|
||||
print_header("OpenAI Codex Login")
|
||||
print()
|
||||
|
||||
try:
|
||||
import argparse
|
||||
|
||||
mock_args = argparse.Namespace()
|
||||
_login_openai_codex(mock_args, PROVIDER_REGISTRY["openai-codex"])
|
||||
# Clear custom endpoint vars that would override provider routing.
|
||||
if existing_custom:
|
||||
save_env_value("OPENAI_BASE_URL", "")
|
||||
save_env_value("OPENAI_API_KEY", "")
|
||||
_update_config_for_provider("openai-codex", DEFAULT_CODEX_BASE_URL)
|
||||
_set_model_provider(config, "openai-codex", DEFAULT_CODEX_BASE_URL)
|
||||
except SystemExit:
|
||||
print_warning("OpenAI Codex login was cancelled or failed.")
|
||||
print_info("You can try again later with: hermes model")
|
||||
selected_provider = None
|
||||
except Exception as e:
|
||||
print_error(f"Login failed: {e}")
|
||||
print_info("You can try again later with: hermes model")
|
||||
selected_provider = None
|
||||
|
||||
elif provider_idx == 2: # OpenRouter
|
||||
selected_provider = "openrouter"
|
||||
print()
|
||||
print_header("OpenRouter API Key")
|
||||
@@ -966,80 +1040,6 @@ def setup_model_provider(config: dict):
|
||||
except Exception as e:
|
||||
logger.debug("Could not save provider to config.yaml: %s", e)
|
||||
|
||||
elif provider_idx == 1: # Nous Portal (OAuth)
|
||||
selected_provider = "nous"
|
||||
print()
|
||||
print_header("Nous Portal Login")
|
||||
print_info("This will open your browser to authenticate with Nous Portal.")
|
||||
print_info("You'll need a Nous Research account with an active subscription.")
|
||||
print()
|
||||
|
||||
try:
|
||||
from hermes_cli.auth import _login_nous, ProviderConfig
|
||||
import argparse
|
||||
|
||||
mock_args = argparse.Namespace(
|
||||
portal_url=None,
|
||||
inference_url=None,
|
||||
client_id=None,
|
||||
scope=None,
|
||||
no_browser=False,
|
||||
timeout=15.0,
|
||||
ca_bundle=None,
|
||||
insecure=False,
|
||||
)
|
||||
pconfig = PROVIDER_REGISTRY["nous"]
|
||||
_login_nous(mock_args, pconfig)
|
||||
_sync_model_from_disk(config)
|
||||
|
||||
# Fetch models for the selection step
|
||||
try:
|
||||
creds = resolve_nous_runtime_credentials(
|
||||
min_key_ttl_seconds=5 * 60,
|
||||
timeout_seconds=15.0,
|
||||
)
|
||||
nous_models = fetch_nous_models(
|
||||
inference_base_url=creds.get("base_url", ""),
|
||||
api_key=creds.get("api_key", ""),
|
||||
)
|
||||
except Exception as e:
|
||||
logger.debug("Could not fetch Nous models after login: %s", e)
|
||||
|
||||
except SystemExit:
|
||||
print_warning("Nous Portal login was cancelled or failed.")
|
||||
print_info("You can try again later with: hermes model")
|
||||
selected_provider = None
|
||||
except Exception as e:
|
||||
print_error(f"Login failed: {e}")
|
||||
print_info("You can try again later with: hermes model")
|
||||
selected_provider = None
|
||||
|
||||
elif provider_idx == 2: # OpenAI Codex
|
||||
selected_provider = "openai-codex"
|
||||
print()
|
||||
print_header("OpenAI Codex Login")
|
||||
print()
|
||||
|
||||
try:
|
||||
import argparse
|
||||
|
||||
mock_args = argparse.Namespace()
|
||||
_login_openai_codex(mock_args, PROVIDER_REGISTRY["openai-codex"])
|
||||
# Clear custom endpoint vars that would override provider routing.
|
||||
if existing_custom:
|
||||
save_env_value("OPENAI_BASE_URL", "")
|
||||
save_env_value("OPENAI_API_KEY", "")
|
||||
_update_config_for_provider("openai-codex", DEFAULT_CODEX_BASE_URL)
|
||||
_set_model_provider(config, "openai-codex", DEFAULT_CODEX_BASE_URL)
|
||||
except SystemExit:
|
||||
print_warning("OpenAI Codex login was cancelled or failed.")
|
||||
print_info("You can try again later with: hermes model")
|
||||
selected_provider = None
|
||||
except Exception as e:
|
||||
print_error(f"Login failed: {e}")
|
||||
print_info("You can try again later with: hermes model")
|
||||
selected_provider = None
|
||||
|
||||
elif provider_idx == 3: # Custom endpoint
|
||||
selected_provider = "custom"
|
||||
print()
|
||||
|
||||
Submodule
+1
Submodule mini-swe-agent added at 07aa6a7385
+18
-14
@@ -1,13 +1,13 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
SWE Runner with Hermes Trajectory Format
|
||||
Mini-SWE-Agent Runner with Hermes Trajectory Format
|
||||
|
||||
A runner that uses Hermes-Agent's built-in execution environments
|
||||
(local, docker, modal) and outputs trajectories in the Hermes-Agent format
|
||||
This module provides a runner that uses mini-swe-agent's execution environments
|
||||
(local, docker, modal) but outputs trajectories in the Hermes-Agent format
|
||||
compatible with batch_runner.py and trajectory_compressor.py.
|
||||
|
||||
Features:
|
||||
- Uses Hermes-Agent's Docker, Modal, or Local environments for command execution
|
||||
- Uses mini-swe-agent's Docker, Modal, or Local environments for command execution
|
||||
- Outputs trajectories in Hermes format (from/value pairs with <tool_call>/<tool_response> XML)
|
||||
- Compatible with the trajectory compression pipeline
|
||||
- Supports batch processing from JSONL prompt files
|
||||
@@ -42,7 +42,11 @@ from dotenv import load_dotenv
|
||||
# Load environment variables
|
||||
load_dotenv()
|
||||
|
||||
# Add mini-swe-agent to path if not installed. In git worktrees the populated
|
||||
# submodule may live in the main checkout rather than the worktree itself.
|
||||
from minisweagent_path import ensure_minisweagent_on_path
|
||||
|
||||
ensure_minisweagent_on_path(Path(__file__).resolve().parent)
|
||||
|
||||
|
||||
# ============================================================================
|
||||
@@ -106,7 +110,7 @@ def create_environment(
|
||||
**kwargs
|
||||
):
|
||||
"""
|
||||
Create an execution environment using Hermes-Agent's built-in backends.
|
||||
Create an execution environment from mini-swe-agent.
|
||||
|
||||
Args:
|
||||
env_type: One of "local", "docker", "modal"
|
||||
@@ -116,19 +120,19 @@ def create_environment(
|
||||
**kwargs: Additional environment-specific options
|
||||
|
||||
Returns:
|
||||
Environment instance with execute() and cleanup() methods
|
||||
Environment instance with execute() method
|
||||
"""
|
||||
if env_type == "local":
|
||||
from tools.environments.local import LocalEnvironment
|
||||
from minisweagent.environments.local import LocalEnvironment
|
||||
return LocalEnvironment(cwd=cwd, timeout=timeout)
|
||||
|
||||
elif env_type == "docker":
|
||||
from tools.environments.docker import DockerEnvironment
|
||||
from minisweagent.environments.docker import DockerEnvironment
|
||||
return DockerEnvironment(image=image, cwd=cwd, timeout=timeout, **kwargs)
|
||||
|
||||
elif env_type == "modal":
|
||||
from tools.environments.modal import ModalEnvironment
|
||||
return ModalEnvironment(image=image, cwd=cwd, timeout=timeout, **kwargs)
|
||||
from minisweagent.environments.extra.swerex_modal import SwerexModalEnvironment
|
||||
return SwerexModalEnvironment(image=image, cwd=cwd, timeout=timeout, **kwargs)
|
||||
|
||||
else:
|
||||
raise ValueError(f"Unknown environment type: {env_type}. Use 'local', 'docker', or 'modal'")
|
||||
@@ -140,8 +144,8 @@ def create_environment(
|
||||
|
||||
class MiniSWERunner:
|
||||
"""
|
||||
Agent runner that uses Hermes-Agent's built-in execution environments
|
||||
and outputs trajectories in Hermes-Agent format.
|
||||
Agent runner that uses mini-swe-agent environments but outputs
|
||||
trajectories in Hermes-Agent format.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
@@ -614,7 +618,7 @@ Complete the user's task step by step."""
|
||||
def main(
|
||||
task: str = None,
|
||||
prompts_file: str = None,
|
||||
output_file: str = "swe-runner-test1.jsonl",
|
||||
output_file: str = "mini-swe-agent-test1.jsonl",
|
||||
model: str = "claude-sonnet-4-20250514",
|
||||
base_url: str = None,
|
||||
api_key: str = None,
|
||||
@@ -626,7 +630,7 @@ def main(
|
||||
verbose: bool = False,
|
||||
):
|
||||
"""
|
||||
Run SWE tasks with Hermes trajectory format output.
|
||||
Run mini-swe-agent tasks with Hermes trajectory format output.
|
||||
|
||||
Args:
|
||||
task: Single task to run (use this OR prompts_file)
|
||||
|
||||
@@ -0,0 +1,92 @@
|
||||
"""Helpers for locating the mini-swe-agent source tree.
|
||||
|
||||
Hermes often runs from git worktrees. In that layout the worktree root may have
|
||||
an empty ``mini-swe-agent/`` placeholder while the real populated submodule
|
||||
lives under the main checkout that owns the shared ``.git`` directory.
|
||||
|
||||
These helpers locate a usable ``mini-swe-agent/src`` directory and optionally
|
||||
prepend it to ``sys.path`` so imports like ``import minisweagent`` work from
|
||||
both normal checkouts and worktrees.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import importlib.util
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
|
||||
def _read_gitdir(repo_root: Path) -> Optional[Path]:
|
||||
"""Resolve the gitdir referenced by ``repo_root/.git`` when it is a file."""
|
||||
git_marker = repo_root / ".git"
|
||||
if not git_marker.is_file():
|
||||
return None
|
||||
|
||||
try:
|
||||
raw = git_marker.read_text(encoding="utf-8").strip()
|
||||
except OSError:
|
||||
return None
|
||||
|
||||
prefix = "gitdir:"
|
||||
if not raw.lower().startswith(prefix):
|
||||
return None
|
||||
|
||||
target = raw[len(prefix):].strip()
|
||||
gitdir = Path(target)
|
||||
if not gitdir.is_absolute():
|
||||
gitdir = (repo_root / gitdir).resolve()
|
||||
else:
|
||||
gitdir = gitdir.resolve()
|
||||
return gitdir
|
||||
|
||||
|
||||
def discover_minisweagent_src(repo_root: Optional[Path] = None) -> Optional[Path]:
|
||||
"""Return the best available ``mini-swe-agent/src`` path, if any.
|
||||
|
||||
Search order:
|
||||
1. Current checkout/worktree root
|
||||
2. Main checkout that owns the shared ``.git`` directory (for worktrees)
|
||||
"""
|
||||
repo_root = (repo_root or Path(__file__).resolve().parent).resolve()
|
||||
|
||||
candidates: list[Path] = [repo_root / "mini-swe-agent" / "src"]
|
||||
|
||||
gitdir = _read_gitdir(repo_root)
|
||||
if gitdir is not None:
|
||||
# Worktree layout: <main>/.git/worktrees/<name>
|
||||
if len(gitdir.parents) >= 3 and gitdir.parent.name == "worktrees":
|
||||
candidates.append(gitdir.parents[2] / "mini-swe-agent" / "src")
|
||||
# Direct checkout with .git file pointing elsewhere
|
||||
elif gitdir.name == ".git":
|
||||
candidates.append(gitdir.parent / "mini-swe-agent" / "src")
|
||||
|
||||
seen = set()
|
||||
for candidate in candidates:
|
||||
candidate = candidate.resolve()
|
||||
if candidate in seen:
|
||||
continue
|
||||
seen.add(candidate)
|
||||
if candidate.exists() and candidate.is_dir():
|
||||
return candidate
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def ensure_minisweagent_on_path(repo_root: Optional[Path] = None) -> Optional[Path]:
|
||||
"""Ensure ``minisweagent`` is importable by prepending its src dir to sys.path.
|
||||
|
||||
Returns the inserted/discovered path, or ``None`` if the package is already
|
||||
importable or no local source tree could be found.
|
||||
"""
|
||||
if importlib.util.find_spec("minisweagent") is not None:
|
||||
return None
|
||||
|
||||
src = discover_minisweagent_src(repo_root)
|
||||
if src is None:
|
||||
return None
|
||||
|
||||
src_str = str(src)
|
||||
if src_str not in sys.path:
|
||||
sys.path.insert(0, src_str)
|
||||
return src
|
||||
+45
-41
@@ -11,60 +11,64 @@ requires-python = ">=3.11"
|
||||
authors = [{ name = "Nous Research" }]
|
||||
license = { text = "MIT" }
|
||||
dependencies = [
|
||||
# Core — pinned to known-good ranges to limit supply chain attack surface
|
||||
"openai>=2.21.0,<3",
|
||||
"anthropic>=0.39.0,<1",
|
||||
"python-dotenv>=1.2.1,<2",
|
||||
"fire>=0.7.1,<1",
|
||||
"httpx>=0.28.1,<1",
|
||||
"rich>=14.3.3,<15",
|
||||
"tenacity>=9.1.4,<10",
|
||||
"pyyaml>=6.0.2,<7",
|
||||
"requests>=2.32.3,<3",
|
||||
"jinja2>=3.1.5,<4",
|
||||
"pydantic>=2.12.5,<3",
|
||||
# Core
|
||||
"openai",
|
||||
"anthropic>=0.39.0",
|
||||
"python-dotenv",
|
||||
"fire",
|
||||
"httpx",
|
||||
"rich",
|
||||
"tenacity",
|
||||
"pyyaml",
|
||||
"requests",
|
||||
"jinja2",
|
||||
"pydantic>=2.0",
|
||||
# Interactive CLI (prompt_toolkit is used directly by cli.py)
|
||||
"prompt_toolkit>=3.0.52,<4",
|
||||
"prompt_toolkit",
|
||||
# Tools
|
||||
"firecrawl-py>=4.16.0,<5",
|
||||
"parallel-web>=0.4.2,<1",
|
||||
"fal-client>=0.13.1,<1",
|
||||
"firecrawl-py",
|
||||
"parallel-web>=0.4.2",
|
||||
"fal-client",
|
||||
# Text-to-speech (Edge TTS is free, no API key needed)
|
||||
"edge-tts>=7.2.7,<8",
|
||||
"faster-whisper>=1.0.0,<2",
|
||||
"edge-tts",
|
||||
"faster-whisper>=1.0.0",
|
||||
# mini-swe-agent deps (terminal tool)
|
||||
"litellm>=1.75.5",
|
||||
"typer",
|
||||
"platformdirs",
|
||||
# Skills Hub (GitHub App JWT auth — optional, only needed for bot identity)
|
||||
"PyJWT[crypto]>=2.10.1,<3",
|
||||
"PyJWT[crypto]",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
modal = ["swe-rex[modal]>=1.4.0,<2"]
|
||||
daytona = ["daytona>=0.148.0,<1"]
|
||||
dev = ["pytest>=9.0.2,<10", "pytest-asyncio>=1.3.0,<2", "pytest-xdist>=3.0,<4", "mcp>=1.2.0,<2"]
|
||||
messaging = ["python-telegram-bot>=22.6,<23", "discord.py[voice]>=2.7.1,<3", "aiohttp>=3.13.3,<4", "slack-bolt>=1.18.0,<2", "slack-sdk>=3.27.0,<4"]
|
||||
cron = ["croniter>=6.0.0,<7"]
|
||||
slack = ["slack-bolt>=1.18.0,<2", "slack-sdk>=3.27.0,<4"]
|
||||
matrix = ["matrix-nio[e2e]>=0.24.0,<1"]
|
||||
cli = ["simple-term-menu>=1.0,<2"]
|
||||
tts-premium = ["elevenlabs>=1.0,<2"]
|
||||
voice = ["sounddevice>=0.4.6,<1", "numpy>=1.24.0,<3"]
|
||||
modal = ["swe-rex[modal]>=1.4.0"]
|
||||
daytona = ["daytona>=0.148.0"]
|
||||
dev = ["pytest", "pytest-asyncio", "pytest-xdist", "mcp>=1.2.0"]
|
||||
messaging = ["python-telegram-bot>=20.0", "discord.py[voice]>=2.0", "aiohttp>=3.9.0", "slack-bolt>=1.18.0", "slack-sdk>=3.27.0"]
|
||||
cron = ["croniter"]
|
||||
slack = ["slack-bolt>=1.18.0", "slack-sdk>=3.27.0"]
|
||||
matrix = ["matrix-nio[e2e]>=0.24.0"]
|
||||
cli = ["simple-term-menu"]
|
||||
tts-premium = ["elevenlabs"]
|
||||
voice = ["sounddevice>=0.4.6", "numpy>=1.24.0"]
|
||||
pty = [
|
||||
"ptyprocess>=0.7.0,<1; sys_platform != 'win32'",
|
||||
"pywinpty>=2.0.0,<3; sys_platform == 'win32'",
|
||||
"ptyprocess>=0.7.0; sys_platform != 'win32'",
|
||||
"pywinpty>=2.0.0; sys_platform == 'win32'",
|
||||
]
|
||||
honcho = ["honcho-ai>=2.0.1,<3"]
|
||||
mcp = ["mcp>=1.2.0,<2"]
|
||||
homeassistant = ["aiohttp>=3.9.0,<4"]
|
||||
sms = ["aiohttp>=3.9.0,<4"]
|
||||
honcho = ["honcho-ai>=2.0.1"]
|
||||
mcp = ["mcp>=1.2.0"]
|
||||
homeassistant = ["aiohttp>=3.9.0"]
|
||||
sms = ["aiohttp>=3.9.0"]
|
||||
acp = ["agent-client-protocol>=0.8.1,<1.0"]
|
||||
dingtalk = ["dingtalk-stream>=0.1.0,<1"]
|
||||
dingtalk = ["dingtalk-stream>=0.1.0"]
|
||||
rl = [
|
||||
"atroposlib @ git+https://github.com/NousResearch/atropos.git",
|
||||
"tinker @ git+https://github.com/thinking-machines-lab/tinker.git",
|
||||
"fastapi>=0.104.0,<1",
|
||||
"uvicorn[standard]>=0.24.0,<1",
|
||||
"wandb>=0.15.0,<1",
|
||||
"fastapi>=0.104.0",
|
||||
"uvicorn[standard]>=0.24.0",
|
||||
"wandb>=0.15.0",
|
||||
]
|
||||
yc-bench = ["yc-bench @ git+https://github.com/collinear-ai/yc-bench.git ; python_version >= '3.12'"]
|
||||
yc-bench = ["yc-bench @ git+https://github.com/collinear-ai/yc-bench.git"]
|
||||
all = [
|
||||
"hermes-agent[modal]",
|
||||
"hermes-agent[daytona]",
|
||||
@@ -90,7 +94,7 @@ hermes-agent = "run_agent:main"
|
||||
hermes-acp = "acp_adapter.entry:main"
|
||||
|
||||
[tool.setuptools]
|
||||
py-modules = ["run_agent", "model_tools", "toolsets", "batch_runner", "trajectory_compressor", "toolset_distributions", "cli", "hermes_constants", "hermes_state", "hermes_time", "rl_cli", "utils"]
|
||||
py-modules = ["run_agent", "model_tools", "toolsets", "batch_runner", "trajectory_compressor", "toolset_distributions", "cli", "hermes_constants", "hermes_state", "hermes_time", "mini_swe_runner", "minisweagent_path", "rl_cli", "utils"]
|
||||
|
||||
[tool.setuptools.packages.find]
|
||||
include = ["agent", "tools", "tools.*", "hermes_cli", "gateway", "gateway.*", "cron", "honcho_integration", "acp_adapter"]
|
||||
|
||||
@@ -23,6 +23,12 @@ parallel-web>=0.4.2
|
||||
# Image generation
|
||||
fal-client
|
||||
|
||||
# mini-swe-agent dependencies (for terminal tool)
|
||||
# Note: Install mini-swe-agent itself with: pip install -e ./mini-swe-agent
|
||||
litellm>=1.75.5
|
||||
typer
|
||||
platformdirs
|
||||
|
||||
# Text-to-speech (Edge TTS is free, no API key needed)
|
||||
edge-tts
|
||||
|
||||
|
||||
+41
-147
@@ -58,6 +58,9 @@ if _loaded_env_paths:
|
||||
else:
|
||||
logger.info("No .env file found. Using system environment variables.")
|
||||
|
||||
# Point mini-swe-agent at ~/.hermes/ so it shares our config
|
||||
os.environ.setdefault("MSWEA_GLOBAL_CONFIG_DIR", str(_hermes_home))
|
||||
os.environ.setdefault("MSWEA_SILENT_STARTUP", "1")
|
||||
|
||||
# Import our tool system
|
||||
from model_tools import get_tool_definitions, handle_function_call, check_toolset_requirements
|
||||
@@ -402,7 +405,6 @@ class AIAgent:
|
||||
clarify_callback: callable = None,
|
||||
step_callback: callable = None,
|
||||
stream_delta_callback: callable = None,
|
||||
tool_gen_callback: callable = None,
|
||||
status_callback: callable = None,
|
||||
max_tokens: int = None,
|
||||
reasoning_config: Dict[str, Any] = None,
|
||||
@@ -532,7 +534,6 @@ class AIAgent:
|
||||
self.step_callback = step_callback
|
||||
self.stream_delta_callback = stream_delta_callback
|
||||
self.status_callback = status_callback
|
||||
self.tool_gen_callback = tool_gen_callback
|
||||
self._last_reported_tool = None # Track for "new tool" mode
|
||||
|
||||
# Tool execution state — allows _vprint during tool execution
|
||||
@@ -585,7 +586,8 @@ class AIAgent:
|
||||
# Context pressure warnings: notify the USER (not the LLM) as context
|
||||
# fills up. Purely informational — displayed in CLI output and sent via
|
||||
# status_callback for gateway platforms. Does NOT inject into messages.
|
||||
self._context_pressure_warned = False
|
||||
self._context_50_warned = False
|
||||
self._context_70_warned = False
|
||||
|
||||
# Persistent error log -- always writes WARNING+ to ~/.hermes/logs/errors.log
|
||||
# so tool failures, API errors, etc. are inspectable after the fact.
|
||||
@@ -657,7 +659,7 @@ class AIAgent:
|
||||
# INFO/WARNING messages just clutter it.
|
||||
for quiet_logger in [
|
||||
'tools', # all tools.* (terminal, browser, web, file, etc.)
|
||||
|
||||
'minisweagent', # mini-swe-agent execution backend
|
||||
'run_agent', # agent runner internals
|
||||
'trajectory_compressor',
|
||||
'cron', # scheduler (only relevant in daemon mode)
|
||||
@@ -1012,8 +1014,6 @@ class AIAgent:
|
||||
compression_threshold = float(_compression_cfg.get("threshold", 0.50))
|
||||
compression_enabled = str(_compression_cfg.get("enabled", True)).lower() in ("true", "1", "yes")
|
||||
compression_summary_model = _compression_cfg.get("summary_model") or None
|
||||
compression_target_ratio = float(_compression_cfg.get("target_ratio", 0.20))
|
||||
compression_protect_last = int(_compression_cfg.get("protect_last_n", 20))
|
||||
|
||||
# Read explicit context_length override from model config
|
||||
_model_cfg = _agent_cfg.get("model", {})
|
||||
@@ -1052,8 +1052,8 @@ class AIAgent:
|
||||
model=self.model,
|
||||
threshold_percent=compression_threshold,
|
||||
protect_first_n=3,
|
||||
protect_last_n=compression_protect_last,
|
||||
summary_target_ratio=compression_target_ratio,
|
||||
protect_last_n=4,
|
||||
summary_target_tokens=500,
|
||||
summary_model_override=compression_summary_model,
|
||||
quiet_mode=self.quiet_mode,
|
||||
base_url=self.base_url,
|
||||
@@ -2363,13 +2363,7 @@ class AIAgent:
|
||||
prompt_parts.append(skills_prompt)
|
||||
|
||||
if not self.skip_context_files:
|
||||
# Use TERMINAL_CWD for context file discovery when set (gateway
|
||||
# mode). The gateway process runs from the hermes-agent install
|
||||
# dir, so os.getcwd() would pick up the repo's AGENTS.md and
|
||||
# other dev files — inflating token usage by ~10k for no benefit.
|
||||
_context_cwd = os.getenv("TERMINAL_CWD") or None
|
||||
context_files_prompt = build_context_files_prompt(
|
||||
cwd=_context_cwd, skip_soul=_soul_loaded)
|
||||
context_files_prompt = build_context_files_prompt(skip_soul=_soul_loaded)
|
||||
if context_files_prompt:
|
||||
prompt_parts.append(context_files_prompt)
|
||||
|
||||
@@ -3519,21 +3513,6 @@ class AIAgent:
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _fire_tool_gen_started(self, tool_name: str) -> None:
|
||||
"""Notify display layer that the model is generating tool call arguments.
|
||||
|
||||
Fires once per tool name when the streaming response begins producing
|
||||
tool_call / tool_use tokens. Gives the TUI a chance to show a spinner
|
||||
or status line so the user isn't staring at a frozen screen while a
|
||||
large tool payload (e.g. a 45 KB write_file) is being generated.
|
||||
"""
|
||||
cb = self.tool_gen_callback
|
||||
if cb is not None:
|
||||
try:
|
||||
cb(tool_name)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _has_stream_consumers(self) -> bool:
|
||||
"""Return True if any streaming consumer is registered."""
|
||||
return (
|
||||
@@ -3585,20 +3564,7 @@ class AIAgent:
|
||||
|
||||
def _call_chat_completions():
|
||||
"""Stream a chat completions response."""
|
||||
import httpx as _httpx
|
||||
_base_timeout = float(os.getenv("HERMES_API_TIMEOUT", 900.0))
|
||||
_stream_read_timeout = float(os.getenv("HERMES_STREAM_READ_TIMEOUT", 60.0))
|
||||
stream_kwargs = {
|
||||
**api_kwargs,
|
||||
"stream": True,
|
||||
"stream_options": {"include_usage": True},
|
||||
"timeout": _httpx.Timeout(
|
||||
connect=30.0,
|
||||
read=_stream_read_timeout,
|
||||
write=_base_timeout,
|
||||
pool=30.0,
|
||||
),
|
||||
}
|
||||
stream_kwargs = {**api_kwargs, "stream": True, "stream_options": {"include_usage": True}}
|
||||
request_client_holder["client"] = self._create_request_openai_client(
|
||||
reason="chat_completion_stream_request"
|
||||
)
|
||||
@@ -3606,7 +3572,6 @@ class AIAgent:
|
||||
|
||||
content_parts: list = []
|
||||
tool_calls_acc: dict = {}
|
||||
tool_gen_notified: set = set()
|
||||
finish_reason = None
|
||||
model_name = None
|
||||
role = "assistant"
|
||||
@@ -3633,7 +3598,6 @@ class AIAgent:
|
||||
reasoning_text = getattr(delta, "reasoning_content", None) or getattr(delta, "reasoning", None)
|
||||
if reasoning_text:
|
||||
reasoning_parts.append(reasoning_text)
|
||||
_fire_first_delta()
|
||||
self._fire_reasoning_delta(reasoning_text)
|
||||
|
||||
# Accumulate text content — fire callback only when no tool calls
|
||||
@@ -3644,7 +3608,7 @@ class AIAgent:
|
||||
self._fire_stream_delta(delta.content)
|
||||
deltas_were_sent["yes"] = True
|
||||
|
||||
# Accumulate tool call deltas — notify display on first name
|
||||
# Accumulate tool call deltas (silently, no callback)
|
||||
if delta and delta.tool_calls:
|
||||
for tc_delta in delta.tool_calls:
|
||||
idx = tc_delta.index if tc_delta.index is not None else 0
|
||||
@@ -3662,12 +3626,6 @@ class AIAgent:
|
||||
entry["function"]["name"] += tc_delta.function.name
|
||||
if tc_delta.function.arguments:
|
||||
entry["function"]["arguments"] += tc_delta.function.arguments
|
||||
# Fire once per tool when the full name is available
|
||||
name = entry["function"]["name"]
|
||||
if name and idx not in tool_gen_notified:
|
||||
tool_gen_notified.add(idx)
|
||||
_fire_first_delta()
|
||||
self._fire_tool_gen_started(name)
|
||||
|
||||
if chunk.choices[0].finish_reason:
|
||||
finish_reason = chunk.choices[0].finish_reason
|
||||
@@ -3733,10 +3691,6 @@ class AIAgent:
|
||||
block = getattr(event, "content_block", None)
|
||||
if block and getattr(block, "type", None) == "tool_use":
|
||||
has_tool_use = True
|
||||
tool_name = getattr(block, "name", None)
|
||||
if tool_name:
|
||||
_fire_first_delta()
|
||||
self._fire_tool_gen_started(tool_name)
|
||||
|
||||
elif event_type == "content_block_delta":
|
||||
delta = getattr(event, "delta", None)
|
||||
@@ -3750,91 +3704,35 @@ class AIAgent:
|
||||
elif delta_type == "thinking_delta":
|
||||
thinking_text = getattr(delta, "thinking", "")
|
||||
if thinking_text:
|
||||
_fire_first_delta()
|
||||
self._fire_reasoning_delta(thinking_text)
|
||||
|
||||
# Return the native Anthropic Message for downstream processing
|
||||
return stream.get_final_message()
|
||||
|
||||
def _call():
|
||||
import httpx as _httpx
|
||||
|
||||
_max_stream_retries = int(os.getenv("HERMES_STREAM_RETRIES", 2))
|
||||
|
||||
try:
|
||||
for _stream_attempt in range(_max_stream_retries + 1):
|
||||
if self.api_mode == "anthropic_messages":
|
||||
self._try_refresh_anthropic_client_credentials()
|
||||
result["response"] = _call_anthropic()
|
||||
else:
|
||||
result["response"] = _call_chat_completions()
|
||||
except Exception as e:
|
||||
if deltas_were_sent["yes"]:
|
||||
# Streaming failed AFTER some tokens were already delivered
|
||||
# to consumers. Don't fall back — that would cause
|
||||
# double-delivery (partial streamed + full non-streamed).
|
||||
# Let the error propagate; the partial content already
|
||||
# reached the user via the stream.
|
||||
logger.warning("Streaming failed after partial delivery, not falling back: %s", e)
|
||||
result["error"] = e
|
||||
else:
|
||||
# Streaming failed before any tokens reached consumers.
|
||||
# Safe to fall back to the standard non-streaming path.
|
||||
logger.info("Streaming failed before delivery, falling back to non-streaming: %s", e)
|
||||
try:
|
||||
if self.api_mode == "anthropic_messages":
|
||||
self._try_refresh_anthropic_client_credentials()
|
||||
result["response"] = _call_anthropic()
|
||||
else:
|
||||
result["response"] = _call_chat_completions()
|
||||
return # success
|
||||
except Exception as e:
|
||||
if deltas_were_sent["yes"]:
|
||||
# Streaming failed AFTER some tokens were already
|
||||
# delivered. Don't retry or fall back — partial
|
||||
# content already reached the user.
|
||||
logger.warning(
|
||||
"Streaming failed after partial delivery, not retrying: %s", e
|
||||
)
|
||||
result["error"] = e
|
||||
return
|
||||
|
||||
_is_timeout = isinstance(
|
||||
e, (_httpx.ReadTimeout, _httpx.ConnectTimeout, _httpx.PoolTimeout)
|
||||
)
|
||||
_is_conn_err = isinstance(
|
||||
e, (_httpx.ConnectError, _httpx.RemoteProtocolError, ConnectionError)
|
||||
)
|
||||
|
||||
if _is_timeout or _is_conn_err:
|
||||
# Transient network / timeout error. Retry the
|
||||
# streaming request with a fresh connection rather
|
||||
# than falling back to non-streaming (which would
|
||||
# hang for up to 15 min on the same dead server).
|
||||
if _stream_attempt < _max_stream_retries:
|
||||
logger.info(
|
||||
"Streaming attempt %s/%s failed (%s: %s), "
|
||||
"retrying with fresh connection...",
|
||||
_stream_attempt + 1,
|
||||
_max_stream_retries + 1,
|
||||
type(e).__name__,
|
||||
e,
|
||||
)
|
||||
# Close the stale request client before retry
|
||||
stale = request_client_holder.get("client")
|
||||
if stale is not None:
|
||||
self._close_request_openai_client(
|
||||
stale, reason="stream_retry_cleanup"
|
||||
)
|
||||
request_client_holder["client"] = None
|
||||
continue
|
||||
# Exhausted retries — propagate to outer loop
|
||||
logger.warning(
|
||||
"Streaming exhausted %s retries on transient error: %s",
|
||||
_max_stream_retries + 1,
|
||||
e,
|
||||
)
|
||||
result["error"] = e
|
||||
return
|
||||
|
||||
# Non-transient error (e.g. "streaming not supported",
|
||||
# auth error, 4xx). Fall back to non-streaming once.
|
||||
err_msg = str(e).lower()
|
||||
if "stream" in err_msg and "not supported" in err_msg:
|
||||
logger.info(
|
||||
"Streaming not supported, falling back to non-streaming: %s", e
|
||||
)
|
||||
try:
|
||||
result["response"] = self._interruptible_api_call(api_kwargs)
|
||||
except Exception as fallback_err:
|
||||
result["error"] = fallback_err
|
||||
return
|
||||
|
||||
# Unknown error — propagate to outer retry loop
|
||||
result["error"] = e
|
||||
return
|
||||
result["response"] = self._interruptible_api_call(api_kwargs)
|
||||
except Exception as fallback_err:
|
||||
result["error"] = fallback_err
|
||||
finally:
|
||||
request_client = request_client_holder.get("client")
|
||||
if request_client is not None:
|
||||
@@ -4686,17 +4584,9 @@ class AIAgent:
|
||||
except Exception as e:
|
||||
logger.debug("Session DB compression split failed: %s", e)
|
||||
|
||||
# Reset context pressure warning and token estimate — usage drops
|
||||
# after compaction. Without this, the stale last_prompt_tokens from
|
||||
# the previous API call causes the pressure calculation to stay at
|
||||
# >1000% and spam warnings / re-trigger compression in a loop.
|
||||
self._context_pressure_warned = False
|
||||
_compressed_est = (
|
||||
estimate_tokens_rough(new_system_prompt)
|
||||
+ estimate_messages_tokens_rough(compressed)
|
||||
)
|
||||
self.context_compressor.last_prompt_tokens = _compressed_est
|
||||
self.context_compressor.last_completion_tokens = 0
|
||||
# Reset context pressure warnings — usage drops after compaction
|
||||
self._context_50_warned = False
|
||||
self._context_70_warned = False
|
||||
|
||||
return compressed, new_system_prompt
|
||||
|
||||
@@ -6929,8 +6819,12 @@ class AIAgent:
|
||||
# and fires status_callback for gateway platforms.
|
||||
if _compressor.threshold_tokens > 0:
|
||||
_compaction_progress = _estimated_next_prompt / _compressor.threshold_tokens
|
||||
if _compaction_progress >= 0.85 and not self._context_pressure_warned:
|
||||
self._context_pressure_warned = True
|
||||
if _compaction_progress >= 0.85 and not self._context_70_warned:
|
||||
self._context_70_warned = True
|
||||
self._context_50_warned = True # skip first tier if we jumped past it
|
||||
self._emit_context_pressure(_compaction_progress, _compressor)
|
||||
elif _compaction_progress >= 0.60 and not self._context_50_warned:
|
||||
self._context_50_warned = True
|
||||
self._emit_context_pressure(_compaction_progress, _compressor)
|
||||
|
||||
if self.compression_enabled and _compressor.should_compress(_estimated_next_prompt):
|
||||
|
||||
+14
-2
@@ -505,7 +505,7 @@ function Install-Repository {
|
||||
git -c windows.appendAtomically=false config windows.appendAtomically false 2>$null
|
||||
|
||||
# Ensure submodules are initialized and updated
|
||||
Write-Info "Initializing submodules..."
|
||||
Write-Info "Initializing submodules (mini-swe-agent, tinker-atropos)..."
|
||||
git -c windows.appendAtomically=false submodule update --init --recursive 2>$null
|
||||
if ($LASTEXITCODE -ne 0) {
|
||||
Write-Warn "Submodule init failed (terminal/RL tools may need manual setup)"
|
||||
@@ -559,7 +559,19 @@ function Install-Dependencies {
|
||||
|
||||
Write-Success "Main package installed"
|
||||
|
||||
# Install optional submodules
|
||||
# Install submodules
|
||||
Write-Info "Installing mini-swe-agent (terminal tool backend)..."
|
||||
if (Test-Path "mini-swe-agent\pyproject.toml") {
|
||||
try {
|
||||
& $UvCmd pip install -e ".\mini-swe-agent" 2>&1 | Out-Null
|
||||
Write-Success "mini-swe-agent installed"
|
||||
} catch {
|
||||
Write-Warn "mini-swe-agent install failed (terminal tools may not work)"
|
||||
}
|
||||
} else {
|
||||
Write-Warn "mini-swe-agent not found (run: git submodule update --init)"
|
||||
}
|
||||
|
||||
Write-Info "Installing tinker-atropos (RL training backend)..."
|
||||
if (Test-Path "tinker-atropos\pyproject.toml") {
|
||||
try {
|
||||
|
||||
@@ -637,6 +637,13 @@ clone_repo() {
|
||||
|
||||
cd "$INSTALL_DIR"
|
||||
|
||||
# Only init mini-swe-agent (terminal tool backend — required).
|
||||
# tinker-atropos (RL training) is optional and heavy — users can opt in later
|
||||
# with: git submodule update --init tinker-atropos && uv pip install -e ./tinker-atropos
|
||||
log_info "Initializing mini-swe-agent submodule (terminal backend)..."
|
||||
git submodule update --init mini-swe-agent
|
||||
log_success "Submodule ready"
|
||||
|
||||
log_success "Repository ready"
|
||||
}
|
||||
|
||||
@@ -711,6 +718,15 @@ install_deps() {
|
||||
|
||||
log_success "Main package installed"
|
||||
|
||||
# Install submodules
|
||||
log_info "Installing mini-swe-agent (terminal tool backend)..."
|
||||
if [ -d "mini-swe-agent" ] && [ -f "mini-swe-agent/pyproject.toml" ]; then
|
||||
$UV_CMD pip install -e "./mini-swe-agent" || log_warn "mini-swe-agent install failed (terminal tools may not work)"
|
||||
log_success "mini-swe-agent installed"
|
||||
else
|
||||
log_warn "mini-swe-agent not found (run: git submodule update --init)"
|
||||
fi
|
||||
|
||||
# tinker-atropos (RL training) is optional — skip by default.
|
||||
# To enable RL tools: git submodule update --init tinker-atropos && uv pip install -e "./tinker-atropos"
|
||||
if [ -d "tinker-atropos" ] && [ -f "tinker-atropos/pyproject.toml" ]; then
|
||||
|
||||
+13
-15
@@ -116,26 +116,24 @@ export VIRTUAL_ENV="$SCRIPT_DIR/venv"
|
||||
|
||||
echo -e "${CYAN}→${NC} Installing dependencies..."
|
||||
|
||||
# Prefer uv sync with lockfile (hash-verified installs) when available,
|
||||
# fall back to pip install for compatibility or when lockfile is stale.
|
||||
if [ -f "uv.lock" ]; then
|
||||
echo -e "${CYAN}→${NC} Using uv.lock for hash-verified installation..."
|
||||
UV_PROJECT_ENVIRONMENT="$SCRIPT_DIR/venv" $UV_CMD sync --all-extras --locked 2>/dev/null && \
|
||||
echo -e "${GREEN}✓${NC} Dependencies installed (lockfile verified)" || {
|
||||
echo -e "${YELLOW}⚠${NC} Lockfile install failed (may be outdated), falling back to pip install..."
|
||||
$UV_CMD pip install -e ".[all]" || $UV_CMD pip install -e "."
|
||||
echo -e "${GREEN}✓${NC} Dependencies installed"
|
||||
}
|
||||
else
|
||||
$UV_CMD pip install -e ".[all]" || $UV_CMD pip install -e "."
|
||||
echo -e "${GREEN}✓${NC} Dependencies installed"
|
||||
fi
|
||||
$UV_CMD pip install -e ".[all]" || $UV_CMD pip install -e "."
|
||||
|
||||
echo -e "${GREEN}✓${NC} Dependencies installed"
|
||||
|
||||
# ============================================================================
|
||||
# Submodules (terminal backend + RL training)
|
||||
# ============================================================================
|
||||
|
||||
echo -e "${CYAN}→${NC} Installing optional submodules..."
|
||||
echo -e "${CYAN}→${NC} Installing submodules..."
|
||||
|
||||
# mini-swe-agent (terminal tool backend)
|
||||
if [ -d "mini-swe-agent" ] && [ -f "mini-swe-agent/pyproject.toml" ]; then
|
||||
$UV_CMD pip install -e "./mini-swe-agent" && \
|
||||
echo -e "${GREEN}✓${NC} mini-swe-agent installed" || \
|
||||
echo -e "${YELLOW}⚠${NC} mini-swe-agent install failed (terminal tools may not work)"
|
||||
else
|
||||
echo -e "${YELLOW}⚠${NC} mini-swe-agent not found (run: git submodule update --init --recursive)"
|
||||
fi
|
||||
|
||||
# tinker-atropos (RL training backend)
|
||||
if [ -d "tinker-atropos" ] && [ -f "tinker-atropos/pyproject.toml" ]; then
|
||||
|
||||
@@ -217,7 +217,7 @@ class TestCompressWithClient:
|
||||
mock_client.chat.completions.create.return_value = mock_response
|
||||
|
||||
with patch("agent.context_compressor.get_model_context_length", return_value=100000):
|
||||
c = ContextCompressor(model="test", quiet_mode=True, protect_first_n=2, protect_last_n=2)
|
||||
c = ContextCompressor(model="test", quiet_mode=True)
|
||||
|
||||
msgs = [{"role": "user" if i % 2 == 0 else "assistant", "content": f"msg {i}"} for i in range(10)]
|
||||
with patch("agent.context_compressor.call_llm", return_value=mock_response):
|
||||
@@ -513,52 +513,3 @@ class TestCompressWithClient:
|
||||
for msg in result:
|
||||
if msg.get("role") == "tool" and msg.get("tool_call_id"):
|
||||
assert msg["tool_call_id"] in called_ids
|
||||
|
||||
|
||||
class TestSummaryTargetRatio:
|
||||
"""Verify that summary_target_ratio properly scales budgets with context window."""
|
||||
|
||||
def test_tail_budget_scales_with_context(self):
|
||||
"""Tail token budget should be threshold_tokens * summary_target_ratio."""
|
||||
with patch("agent.context_compressor.get_model_context_length", return_value=200_000):
|
||||
c = ContextCompressor(model="test", quiet_mode=True, summary_target_ratio=0.40)
|
||||
# 200K * 0.50 threshold * 0.40 ratio = 40K
|
||||
assert c.tail_token_budget == 40_000
|
||||
|
||||
with patch("agent.context_compressor.get_model_context_length", return_value=1_000_000):
|
||||
c = ContextCompressor(model="test", quiet_mode=True, summary_target_ratio=0.40)
|
||||
# 1M * 0.50 threshold * 0.40 ratio = 200K
|
||||
assert c.tail_token_budget == 200_000
|
||||
|
||||
def test_summary_cap_scales_with_context(self):
|
||||
"""Max summary tokens should be 5% of context, capped at 12K."""
|
||||
with patch("agent.context_compressor.get_model_context_length", return_value=200_000):
|
||||
c = ContextCompressor(model="test", quiet_mode=True)
|
||||
assert c.max_summary_tokens == 10_000 # 200K * 0.05
|
||||
|
||||
with patch("agent.context_compressor.get_model_context_length", return_value=1_000_000):
|
||||
c = ContextCompressor(model="test", quiet_mode=True)
|
||||
assert c.max_summary_tokens == 12_000 # capped at 12K ceiling
|
||||
|
||||
def test_ratio_clamped(self):
|
||||
"""Ratio should be clamped to [0.10, 0.80]."""
|
||||
with patch("agent.context_compressor.get_model_context_length", return_value=100_000):
|
||||
c = ContextCompressor(model="test", quiet_mode=True, summary_target_ratio=0.05)
|
||||
assert c.summary_target_ratio == 0.10
|
||||
|
||||
with patch("agent.context_compressor.get_model_context_length", return_value=100_000):
|
||||
c = ContextCompressor(model="test", quiet_mode=True, summary_target_ratio=0.95)
|
||||
assert c.summary_target_ratio == 0.80
|
||||
|
||||
def test_default_threshold_is_50_percent(self):
|
||||
"""Default compression threshold should be 50%."""
|
||||
with patch("agent.context_compressor.get_model_context_length", return_value=100_000):
|
||||
c = ContextCompressor(model="test", quiet_mode=True)
|
||||
assert c.threshold_percent == 0.50
|
||||
assert c.threshold_tokens == 50_000
|
||||
|
||||
def test_default_protect_last_n_is_20(self):
|
||||
"""Default protect_last_n should be 20."""
|
||||
with patch("agent.context_compressor.get_model_context_length", return_value=100_000):
|
||||
c = ContextCompressor(model="test", quiet_mode=True)
|
||||
assert c.protect_last_n == 20
|
||||
|
||||
@@ -1,167 +0,0 @@
|
||||
"""Tests for memory flush stale-overwrite prevention (#2670).
|
||||
|
||||
Verifies that:
|
||||
1. Cron sessions are skipped (no flush for headless cron runs)
|
||||
2. Current memory state is injected into the flush prompt so the
|
||||
flush agent can see what's already saved and avoid overwrites
|
||||
3. The flush still works normally when memory files don't exist
|
||||
"""
|
||||
|
||||
import pytest
|
||||
from pathlib import Path
|
||||
from unittest.mock import MagicMock, patch, call
|
||||
|
||||
|
||||
def _make_runner():
|
||||
from gateway.run import GatewayRunner
|
||||
|
||||
runner = object.__new__(GatewayRunner)
|
||||
runner._honcho_managers = {}
|
||||
runner._honcho_configs = {}
|
||||
runner._running_agents = {}
|
||||
runner._pending_messages = {}
|
||||
runner._pending_approvals = {}
|
||||
runner.adapters = {}
|
||||
runner.hooks = MagicMock()
|
||||
runner.session_store = MagicMock()
|
||||
return runner
|
||||
|
||||
|
||||
_TRANSCRIPT_4_MSGS = [
|
||||
{"role": "user", "content": "hello"},
|
||||
{"role": "assistant", "content": "hi there"},
|
||||
{"role": "user", "content": "remember my name is Alice"},
|
||||
{"role": "assistant", "content": "Got it, Alice!"},
|
||||
]
|
||||
|
||||
|
||||
class TestCronSessionBypass:
|
||||
"""Cron sessions should never trigger a memory flush."""
|
||||
|
||||
def test_cron_session_skipped(self):
|
||||
runner = _make_runner()
|
||||
runner._flush_memories_for_session("cron_job123_20260323_120000")
|
||||
# session_store.load_transcript should never be called
|
||||
runner.session_store.load_transcript.assert_not_called()
|
||||
|
||||
def test_cron_session_with_honcho_key_skipped(self):
|
||||
runner = _make_runner()
|
||||
runner._flush_memories_for_session("cron_daily_20260323", "some-honcho-key")
|
||||
runner.session_store.load_transcript.assert_not_called()
|
||||
|
||||
def test_non_cron_session_proceeds(self):
|
||||
"""Non-cron sessions should still attempt the flush."""
|
||||
runner = _make_runner()
|
||||
runner.session_store.load_transcript.return_value = []
|
||||
runner._flush_memories_for_session("session_abc123")
|
||||
runner.session_store.load_transcript.assert_called_once_with("session_abc123")
|
||||
|
||||
|
||||
class TestMemoryInjection:
|
||||
"""The flush prompt should include current memory state from disk."""
|
||||
|
||||
def test_memory_content_injected_into_flush_prompt(self, tmp_path):
|
||||
"""When memory files exist, their content appears in the flush prompt."""
|
||||
runner = _make_runner()
|
||||
runner.session_store.load_transcript.return_value = _TRANSCRIPT_4_MSGS
|
||||
|
||||
tmp_agent = MagicMock()
|
||||
memory_dir = tmp_path / "memories"
|
||||
memory_dir.mkdir()
|
||||
(memory_dir / "MEMORY.md").write_text("Agent knows Python\n§\nUser prefers dark mode")
|
||||
(memory_dir / "USER.md").write_text("Name: Alice\n§\nTimezone: PST")
|
||||
|
||||
with (
|
||||
patch("gateway.run._resolve_runtime_agent_kwargs", return_value={"api_key": "k"}),
|
||||
patch("gateway.run._resolve_gateway_model", return_value="test-model"),
|
||||
patch("run_agent.AIAgent", return_value=tmp_agent),
|
||||
# Intercept `from tools.memory_tool import MEMORY_DIR` inside the function
|
||||
patch.dict("sys.modules", {"tools.memory_tool": MagicMock(MEMORY_DIR=memory_dir)}),
|
||||
):
|
||||
runner._flush_memories_for_session("session_123")
|
||||
|
||||
tmp_agent.run_conversation.assert_called_once()
|
||||
call_kwargs = tmp_agent.run_conversation.call_args.kwargs
|
||||
flush_prompt = call_kwargs.get("user_message", "")
|
||||
|
||||
# Verify both memory sections appear in the prompt
|
||||
assert "Agent knows Python" in flush_prompt
|
||||
assert "User prefers dark mode" in flush_prompt
|
||||
assert "Name: Alice" in flush_prompt
|
||||
assert "Timezone: PST" in flush_prompt
|
||||
# Verify the stale-overwrite warning is present
|
||||
assert "Do NOT overwrite or remove entries" in flush_prompt
|
||||
assert "current live state of memory" in flush_prompt
|
||||
|
||||
def test_flush_works_without_memory_files(self, tmp_path):
|
||||
"""When no memory files exist, flush still runs without the guard."""
|
||||
runner = _make_runner()
|
||||
runner.session_store.load_transcript.return_value = _TRANSCRIPT_4_MSGS
|
||||
|
||||
tmp_agent = MagicMock()
|
||||
empty_dir = tmp_path / "no_memories"
|
||||
empty_dir.mkdir()
|
||||
|
||||
with (
|
||||
patch("gateway.run._resolve_runtime_agent_kwargs", return_value={"api_key": "k"}),
|
||||
patch("gateway.run._resolve_gateway_model", return_value="test-model"),
|
||||
patch("run_agent.AIAgent", return_value=tmp_agent),
|
||||
patch.dict("sys.modules", {"tools.memory_tool": MagicMock(MEMORY_DIR=empty_dir)}),
|
||||
):
|
||||
runner._flush_memories_for_session("session_456")
|
||||
|
||||
# Should still run, just without the memory guard section
|
||||
tmp_agent.run_conversation.assert_called_once()
|
||||
flush_prompt = tmp_agent.run_conversation.call_args.kwargs.get("user_message", "")
|
||||
assert "Do NOT overwrite or remove entries" not in flush_prompt
|
||||
assert "Review the conversation above" in flush_prompt
|
||||
|
||||
def test_empty_memory_files_no_injection(self, tmp_path):
|
||||
"""Empty memory files should not trigger the guard section."""
|
||||
runner = _make_runner()
|
||||
runner.session_store.load_transcript.return_value = _TRANSCRIPT_4_MSGS
|
||||
|
||||
tmp_agent = MagicMock()
|
||||
memory_dir = tmp_path / "memories"
|
||||
memory_dir.mkdir()
|
||||
(memory_dir / "MEMORY.md").write_text("")
|
||||
(memory_dir / "USER.md").write_text(" \n ") # whitespace only
|
||||
|
||||
with (
|
||||
patch("gateway.run._resolve_runtime_agent_kwargs", return_value={"api_key": "k"}),
|
||||
patch("gateway.run._resolve_gateway_model", return_value="test-model"),
|
||||
patch("run_agent.AIAgent", return_value=tmp_agent),
|
||||
patch.dict("sys.modules", {"tools.memory_tool": MagicMock(MEMORY_DIR=memory_dir)}),
|
||||
):
|
||||
runner._flush_memories_for_session("session_789")
|
||||
|
||||
tmp_agent.run_conversation.assert_called_once()
|
||||
flush_prompt = tmp_agent.run_conversation.call_args.kwargs.get("user_message", "")
|
||||
# No memory content → no guard section
|
||||
assert "current live state of memory" not in flush_prompt
|
||||
|
||||
|
||||
class TestFlushPromptStructure:
|
||||
"""Verify the flush prompt retains its core instructions."""
|
||||
|
||||
def test_core_instructions_present(self):
|
||||
"""The flush prompt should still contain the original guidance."""
|
||||
runner = _make_runner()
|
||||
runner.session_store.load_transcript.return_value = _TRANSCRIPT_4_MSGS
|
||||
|
||||
tmp_agent = MagicMock()
|
||||
|
||||
with (
|
||||
patch("gateway.run._resolve_runtime_agent_kwargs", return_value={"api_key": "k"}),
|
||||
patch("gateway.run._resolve_gateway_model", return_value="test-model"),
|
||||
patch("run_agent.AIAgent", return_value=tmp_agent),
|
||||
# Make the import fail gracefully so we test without memory files
|
||||
patch.dict("sys.modules", {"tools.memory_tool": MagicMock(MEMORY_DIR=Path("/nonexistent"))}),
|
||||
):
|
||||
runner._flush_memories_for_session("session_struct")
|
||||
|
||||
flush_prompt = tmp_agent.run_conversation.call_args.kwargs.get("user_message", "")
|
||||
assert "automatically reset" in flush_prompt
|
||||
assert "Save any important facts" in flush_prompt
|
||||
assert "consider saving it as a skill" in flush_prompt
|
||||
assert "Do NOT respond to the user" in flush_prompt
|
||||
@@ -282,78 +282,6 @@ class TestGatewaySystemServiceRouting:
|
||||
assert run_calls == []
|
||||
|
||||
|
||||
class TestDetectVenvDir:
|
||||
"""Tests for _detect_venv_dir() virtualenv detection."""
|
||||
|
||||
def test_detects_active_virtualenv_via_sys_prefix(self, tmp_path, monkeypatch):
|
||||
venv_path = tmp_path / "my-custom-venv"
|
||||
venv_path.mkdir()
|
||||
monkeypatch.setattr("sys.prefix", str(venv_path))
|
||||
monkeypatch.setattr("sys.base_prefix", "/usr")
|
||||
|
||||
result = gateway_cli._detect_venv_dir()
|
||||
assert result == venv_path
|
||||
|
||||
def test_falls_back_to_dot_venv_directory(self, tmp_path, monkeypatch):
|
||||
# Not inside a virtualenv
|
||||
monkeypatch.setattr("sys.prefix", "/usr")
|
||||
monkeypatch.setattr("sys.base_prefix", "/usr")
|
||||
monkeypatch.setattr(gateway_cli, "PROJECT_ROOT", tmp_path)
|
||||
|
||||
dot_venv = tmp_path / ".venv"
|
||||
dot_venv.mkdir()
|
||||
|
||||
result = gateway_cli._detect_venv_dir()
|
||||
assert result == dot_venv
|
||||
|
||||
def test_falls_back_to_venv_directory(self, tmp_path, monkeypatch):
|
||||
monkeypatch.setattr("sys.prefix", "/usr")
|
||||
monkeypatch.setattr("sys.base_prefix", "/usr")
|
||||
monkeypatch.setattr(gateway_cli, "PROJECT_ROOT", tmp_path)
|
||||
|
||||
venv = tmp_path / "venv"
|
||||
venv.mkdir()
|
||||
|
||||
result = gateway_cli._detect_venv_dir()
|
||||
assert result == venv
|
||||
|
||||
def test_prefers_dot_venv_over_venv(self, tmp_path, monkeypatch):
|
||||
monkeypatch.setattr("sys.prefix", "/usr")
|
||||
monkeypatch.setattr("sys.base_prefix", "/usr")
|
||||
monkeypatch.setattr(gateway_cli, "PROJECT_ROOT", tmp_path)
|
||||
|
||||
(tmp_path / ".venv").mkdir()
|
||||
(tmp_path / "venv").mkdir()
|
||||
|
||||
result = gateway_cli._detect_venv_dir()
|
||||
assert result == tmp_path / ".venv"
|
||||
|
||||
def test_returns_none_when_no_virtualenv(self, tmp_path, monkeypatch):
|
||||
monkeypatch.setattr("sys.prefix", "/usr")
|
||||
monkeypatch.setattr("sys.base_prefix", "/usr")
|
||||
monkeypatch.setattr(gateway_cli, "PROJECT_ROOT", tmp_path)
|
||||
|
||||
result = gateway_cli._detect_venv_dir()
|
||||
assert result is None
|
||||
|
||||
|
||||
class TestGeneratedUnitUsesDetectedVenv:
|
||||
def test_systemd_unit_uses_dot_venv_when_detected(self, tmp_path, monkeypatch):
|
||||
dot_venv = tmp_path / ".venv"
|
||||
dot_venv.mkdir()
|
||||
(dot_venv / "bin").mkdir()
|
||||
|
||||
monkeypatch.setattr(gateway_cli, "_detect_venv_dir", lambda: dot_venv)
|
||||
monkeypatch.setattr(gateway_cli, "get_python_path", lambda: str(dot_venv / "bin" / "python"))
|
||||
|
||||
unit = gateway_cli.generate_systemd_unit(system=False)
|
||||
|
||||
assert f"VIRTUAL_ENV={dot_venv}" in unit
|
||||
assert f"{dot_venv}/bin" in unit
|
||||
# Must NOT contain a hardcoded /venv/ path
|
||||
assert "/venv/" not in unit or "/.venv/" in unit
|
||||
|
||||
|
||||
class TestEnsureUserSystemdEnv:
|
||||
"""Tests for _ensure_user_systemd_env() D-Bus session bus auto-detection."""
|
||||
|
||||
|
||||
@@ -92,31 +92,6 @@ class TestParseModelInput:
|
||||
assert provider == "openrouter"
|
||||
assert model == "http://localhost:8080/model"
|
||||
|
||||
def test_custom_colon_model_single(self):
|
||||
"""custom:model-name → anonymous custom provider."""
|
||||
provider, model = parse_model_input("custom:qwen-2.5", "openrouter")
|
||||
assert provider == "custom"
|
||||
assert model == "qwen-2.5"
|
||||
|
||||
def test_custom_triple_syntax(self):
|
||||
"""custom:name:model → named custom provider."""
|
||||
provider, model = parse_model_input("custom:local-server:qwen-2.5", "openrouter")
|
||||
assert provider == "custom:local-server"
|
||||
assert model == "qwen-2.5"
|
||||
|
||||
def test_custom_triple_spaces(self):
|
||||
"""Triple syntax should handle whitespace."""
|
||||
provider, model = parse_model_input("custom: my-server : my-model ", "openrouter")
|
||||
assert provider == "custom:my-server"
|
||||
assert model == "my-model"
|
||||
|
||||
def test_custom_triple_empty_model_falls_back(self):
|
||||
"""custom:name: with no model → treated as custom:name (bare)."""
|
||||
provider, model = parse_model_input("custom:name:", "openrouter")
|
||||
# Empty model after second colon → no triple match, falls through
|
||||
assert provider == "custom"
|
||||
assert model == "name:"
|
||||
|
||||
|
||||
# -- curated_models_for_provider ---------------------------------------------
|
||||
|
||||
|
||||
@@ -34,7 +34,7 @@ def test_nous_oauth_setup_keeps_current_model_when_syncing_disk_provider(
|
||||
|
||||
def fake_prompt_choice(question, choices, default=0):
|
||||
if question == "Select your inference provider:":
|
||||
return 1 # Nous Portal
|
||||
return 0
|
||||
if question == "Configure vision:":
|
||||
return len(choices) - 1
|
||||
if question == "Select default model:":
|
||||
@@ -135,7 +135,7 @@ def test_codex_setup_uses_runtime_access_token_for_live_model_list(tmp_path, mon
|
||||
|
||||
def fake_prompt_choice(question, choices, default=0):
|
||||
if question == "Select your inference provider:":
|
||||
return 2 # OpenAI Codex
|
||||
return 1
|
||||
if question == "Select default model:":
|
||||
return 0
|
||||
tts_idx = _maybe_keep_current_tts(question, choices)
|
||||
|
||||
@@ -401,7 +401,7 @@ def test_setup_switch_custom_to_codex_clears_custom_endpoint_and_updates_config(
|
||||
|
||||
def fake_prompt_choice(question, choices, default=0):
|
||||
if question == "Select your inference provider:":
|
||||
return 2 # OpenAI Codex
|
||||
return 1
|
||||
if question == "Select default model:":
|
||||
return 0
|
||||
tts_idx = _maybe_keep_current_tts(question, choices)
|
||||
|
||||
@@ -41,6 +41,7 @@ except ImportError:
|
||||
# Add project root to path for imports
|
||||
parent_dir = Path(__file__).parent.parent.parent
|
||||
sys.path.insert(0, str(parent_dir))
|
||||
sys.path.insert(0, str(parent_dir / "mini-swe-agent" / "src"))
|
||||
|
||||
# Import terminal_tool module directly using importlib to avoid tools/__init__.py
|
||||
import importlib.util
|
||||
|
||||
@@ -111,13 +111,8 @@ class TestModelCommand:
|
||||
assert cli_obj.model == "glm-5"
|
||||
assert cli_obj.provider == "zai"
|
||||
assert cli_obj.base_url == "https://api.z.ai/api/paas/v4"
|
||||
# Model, provider, and base_url should be saved
|
||||
assert save_mock.call_count == 3
|
||||
save_calls = [c.args for c in save_mock.call_args_list]
|
||||
assert ("model.default", "glm-5") in save_calls
|
||||
assert ("model.provider", "zai") in save_calls
|
||||
# base_url is also persisted on provider change (Phase 2 fix)
|
||||
assert any(c[0] == "model.base_url" for c in save_calls)
|
||||
# Both model and provider should be saved
|
||||
assert save_mock.call_count == 2
|
||||
|
||||
def test_provider_switch_fails_on_bad_credentials(self, capsys):
|
||||
cli_obj = self._make_cli()
|
||||
|
||||
@@ -1,132 +0,0 @@
|
||||
"""Tests for ${ENV_VAR} substitution in config.yaml values."""
|
||||
|
||||
import os
|
||||
import pytest
|
||||
from hermes_cli.config import _expand_env_vars, load_config
|
||||
from unittest.mock import patch as mock_patch
|
||||
|
||||
|
||||
class TestExpandEnvVars:
|
||||
def test_simple_substitution(self):
|
||||
with pytest.MonkeyPatch().context() as mp:
|
||||
mp.setenv("MY_KEY", "secret123")
|
||||
assert _expand_env_vars("${MY_KEY}") == "secret123"
|
||||
|
||||
def test_missing_var_kept_verbatim(self):
|
||||
with pytest.MonkeyPatch().context() as mp:
|
||||
mp.delenv("UNDEFINED_VAR_XYZ", raising=False)
|
||||
assert _expand_env_vars("${UNDEFINED_VAR_XYZ}") == "${UNDEFINED_VAR_XYZ}"
|
||||
|
||||
def test_no_placeholder_unchanged(self):
|
||||
assert _expand_env_vars("plain-value") == "plain-value"
|
||||
|
||||
def test_dict_recursive(self):
|
||||
with pytest.MonkeyPatch().context() as mp:
|
||||
mp.setenv("TOKEN", "tok-abc")
|
||||
result = _expand_env_vars({"key": "${TOKEN}", "other": "literal"})
|
||||
assert result == {"key": "tok-abc", "other": "literal"}
|
||||
|
||||
def test_nested_dict(self):
|
||||
with pytest.MonkeyPatch().context() as mp:
|
||||
mp.setenv("API_KEY", "sk-xyz")
|
||||
result = _expand_env_vars({"model": {"api_key": "${API_KEY}"}})
|
||||
assert result["model"]["api_key"] == "sk-xyz"
|
||||
|
||||
def test_list_items(self):
|
||||
with pytest.MonkeyPatch().context() as mp:
|
||||
mp.setenv("VAL", "hello")
|
||||
result = _expand_env_vars(["${VAL}", "literal", 42])
|
||||
assert result == ["hello", "literal", 42]
|
||||
|
||||
def test_non_string_values_untouched(self):
|
||||
assert _expand_env_vars(42) == 42
|
||||
assert _expand_env_vars(3.14) == 3.14
|
||||
assert _expand_env_vars(True) is True
|
||||
assert _expand_env_vars(None) is None
|
||||
|
||||
def test_multiple_placeholders_in_one_string(self):
|
||||
with pytest.MonkeyPatch().context() as mp:
|
||||
mp.setenv("HOST", "localhost")
|
||||
mp.setenv("PORT", "5432")
|
||||
assert _expand_env_vars("${HOST}:${PORT}") == "localhost:5432"
|
||||
|
||||
def test_dict_keys_not_expanded(self):
|
||||
with pytest.MonkeyPatch().context() as mp:
|
||||
mp.setenv("KEY", "value")
|
||||
result = _expand_env_vars({"${KEY}": "no-expand-key"})
|
||||
assert "${KEY}" in result
|
||||
|
||||
|
||||
class TestLoadConfigExpansion:
|
||||
def test_load_config_expands_env_vars(self, tmp_path, monkeypatch):
|
||||
config_yaml = (
|
||||
"model:\n"
|
||||
" api_key: ${GOOGLE_API_KEY}\n"
|
||||
"platforms:\n"
|
||||
" telegram:\n"
|
||||
" token: ${TELEGRAM_BOT_TOKEN}\n"
|
||||
"plain: no-substitution\n"
|
||||
)
|
||||
config_file = tmp_path / "config.yaml"
|
||||
config_file.write_text(config_yaml)
|
||||
|
||||
monkeypatch.setenv("GOOGLE_API_KEY", "gsk-test-key")
|
||||
monkeypatch.setenv("TELEGRAM_BOT_TOKEN", "1234567:ABC-token")
|
||||
monkeypatch.setattr("hermes_cli.config.get_config_path", lambda: config_file)
|
||||
|
||||
config = load_config()
|
||||
|
||||
assert config["model"]["api_key"] == "gsk-test-key"
|
||||
assert config["platforms"]["telegram"]["token"] == "1234567:ABC-token"
|
||||
assert config["plain"] == "no-substitution"
|
||||
|
||||
def test_load_config_unresolved_kept_verbatim(self, tmp_path, monkeypatch):
|
||||
config_yaml = "model:\n api_key: ${NOT_SET_XYZ_123}\n"
|
||||
config_file = tmp_path / "config.yaml"
|
||||
config_file.write_text(config_yaml)
|
||||
|
||||
monkeypatch.delenv("NOT_SET_XYZ_123", raising=False)
|
||||
monkeypatch.setattr("hermes_cli.config.get_config_path", lambda: config_file)
|
||||
|
||||
config = load_config()
|
||||
|
||||
assert config["model"]["api_key"] == "${NOT_SET_XYZ_123}"
|
||||
|
||||
|
||||
class TestLoadCliConfigExpansion:
|
||||
"""Verify that load_cli_config() also expands ${VAR} references."""
|
||||
|
||||
def test_cli_config_expands_auxiliary_api_key(self, tmp_path, monkeypatch):
|
||||
config_yaml = (
|
||||
"auxiliary:\n"
|
||||
" vision:\n"
|
||||
" api_key: ${TEST_VISION_KEY_XYZ}\n"
|
||||
)
|
||||
config_file = tmp_path / "config.yaml"
|
||||
config_file.write_text(config_yaml)
|
||||
|
||||
monkeypatch.setenv("TEST_VISION_KEY_XYZ", "vis-key-123")
|
||||
# Patch the hermes home so load_cli_config finds our test config
|
||||
monkeypatch.setattr("cli._hermes_home", tmp_path)
|
||||
|
||||
from cli import load_cli_config
|
||||
config = load_cli_config()
|
||||
|
||||
assert config["auxiliary"]["vision"]["api_key"] == "vis-key-123"
|
||||
|
||||
def test_cli_config_unresolved_kept_verbatim(self, tmp_path, monkeypatch):
|
||||
config_yaml = (
|
||||
"auxiliary:\n"
|
||||
" vision:\n"
|
||||
" api_key: ${UNSET_CLI_VAR_ABC}\n"
|
||||
)
|
||||
config_file = tmp_path / "config.yaml"
|
||||
config_file.write_text(config_yaml)
|
||||
|
||||
monkeypatch.delenv("UNSET_CLI_VAR_ABC", raising=False)
|
||||
monkeypatch.setattr("cli._hermes_home", tmp_path)
|
||||
|
||||
from cli import load_cli_config
|
||||
config = load_cli_config()
|
||||
|
||||
assert config["auxiliary"]["vision"]["api_key"] == "${UNSET_CLI_VAR_ABC}"
|
||||
@@ -29,36 +29,40 @@ class TestFormatContextPressure:
|
||||
raw context window. 60% = 60% of the way to compaction.
|
||||
"""
|
||||
|
||||
def test_80_percent_uses_warning_icon(self):
|
||||
line = format_context_pressure(0.80, 100_000, 0.50)
|
||||
assert "⚠" in line
|
||||
assert "80% to compaction" in line
|
||||
def test_60_percent_uses_info_icon(self):
|
||||
line = format_context_pressure(0.60, 100_000, 0.50)
|
||||
assert "◐" in line
|
||||
assert "60% to compaction" in line
|
||||
|
||||
def test_90_percent_uses_warning_icon(self):
|
||||
line = format_context_pressure(0.90, 100_000, 0.50)
|
||||
def test_85_percent_uses_warning_icon(self):
|
||||
line = format_context_pressure(0.85, 100_000, 0.50)
|
||||
assert "⚠" in line
|
||||
assert "90% to compaction" in line
|
||||
assert "85% to compaction" in line
|
||||
|
||||
def test_bar_length_scales_with_progress(self):
|
||||
line_80 = format_context_pressure(0.80, 100_000, 0.50)
|
||||
line_95 = format_context_pressure(0.95, 100_000, 0.50)
|
||||
assert line_95.count("▰") > line_80.count("▰")
|
||||
line_60 = format_context_pressure(0.60, 100_000, 0.50)
|
||||
line_85 = format_context_pressure(0.85, 100_000, 0.50)
|
||||
assert line_85.count("▰") > line_60.count("▰")
|
||||
|
||||
def test_shows_threshold_tokens(self):
|
||||
line = format_context_pressure(0.80, 100_000, 0.50)
|
||||
line = format_context_pressure(0.60, 100_000, 0.50)
|
||||
assert "100k" in line
|
||||
|
||||
def test_small_threshold(self):
|
||||
line = format_context_pressure(0.80, 500, 0.50)
|
||||
line = format_context_pressure(0.60, 500, 0.50)
|
||||
assert "500" in line
|
||||
|
||||
def test_shows_threshold_percent(self):
|
||||
line = format_context_pressure(0.80, 100_000, 0.50)
|
||||
assert "50%" in line
|
||||
line = format_context_pressure(0.85, 100_000, 0.50)
|
||||
assert "50%" in line # threshold percent shown
|
||||
|
||||
def test_approaching_hint(self):
|
||||
line = format_context_pressure(0.80, 100_000, 0.50)
|
||||
assert "compaction approaching" in line
|
||||
def test_imminent_hint_at_85(self):
|
||||
line = format_context_pressure(0.85, 100_000, 0.50)
|
||||
assert "compaction imminent" in line
|
||||
|
||||
def test_approaching_hint_below_85(self):
|
||||
line = format_context_pressure(0.60, 100_000, 0.80)
|
||||
assert "approaching compaction" in line
|
||||
|
||||
def test_no_compaction_when_disabled(self):
|
||||
line = format_context_pressure(0.85, 100_000, 0.50, compression_enabled=False)
|
||||
@@ -78,26 +82,26 @@ class TestFormatContextPressure:
|
||||
class TestFormatContextPressureGateway:
|
||||
"""Gateway (plain text) context pressure display."""
|
||||
|
||||
def test_80_percent_warning(self):
|
||||
msg = format_context_pressure_gateway(0.80, 0.50)
|
||||
assert "80% to compaction" in msg
|
||||
assert "50%" in msg
|
||||
def test_60_percent_informational(self):
|
||||
msg = format_context_pressure_gateway(0.60, 0.50)
|
||||
assert "60% to compaction" in msg
|
||||
assert "50%" in msg # threshold shown
|
||||
|
||||
def test_90_percent_warning(self):
|
||||
msg = format_context_pressure_gateway(0.90, 0.50)
|
||||
assert "90% to compaction" in msg
|
||||
assert "approaching" in msg
|
||||
def test_85_percent_warning(self):
|
||||
msg = format_context_pressure_gateway(0.85, 0.50)
|
||||
assert "85% to compaction" in msg
|
||||
assert "imminent" in msg
|
||||
|
||||
def test_no_compaction_warning(self):
|
||||
msg = format_context_pressure_gateway(0.85, 0.50, compression_enabled=False)
|
||||
assert "disabled" in msg
|
||||
|
||||
def test_no_ansi_codes(self):
|
||||
msg = format_context_pressure_gateway(0.80, 0.50)
|
||||
msg = format_context_pressure_gateway(0.85, 0.50)
|
||||
assert "\033[" not in msg
|
||||
|
||||
def test_has_progress_bar(self):
|
||||
msg = format_context_pressure_gateway(0.80, 0.50)
|
||||
msg = format_context_pressure_gateway(0.85, 0.50)
|
||||
assert "▰" in msg
|
||||
|
||||
|
||||
@@ -141,8 +145,9 @@ def agent():
|
||||
class TestContextPressureFlags:
|
||||
"""Context pressure warning flag tracking on AIAgent."""
|
||||
|
||||
def test_flag_initialized_false(self, agent):
|
||||
assert agent._context_pressure_warned is False
|
||||
def test_flags_initialized_false(self, agent):
|
||||
assert agent._context_50_warned is False
|
||||
assert agent._context_70_warned is False
|
||||
|
||||
def test_emit_calls_status_callback(self, agent):
|
||||
"""status_callback should be invoked with event type and message."""
|
||||
@@ -199,11 +204,13 @@ class TestContextPressureFlags:
|
||||
captured = capsys.readouterr()
|
||||
assert "▰" not in captured.out
|
||||
|
||||
def test_flag_reset_on_compression(self, agent):
|
||||
"""After _compress_context, context pressure flag should reset."""
|
||||
agent._context_pressure_warned = True
|
||||
def test_flags_reset_on_compression(self, agent):
|
||||
"""After _compress_context, context pressure flags should reset."""
|
||||
agent._context_50_warned = True
|
||||
agent._context_70_warned = True
|
||||
agent.compression_enabled = True
|
||||
|
||||
# Mock the compressor's compress method to return minimal valid output
|
||||
agent.context_compressor = MagicMock()
|
||||
agent.context_compressor.compress.return_value = [
|
||||
{"role": "user", "content": "Summary of conversation so far."}
|
||||
@@ -211,9 +218,11 @@ class TestContextPressureFlags:
|
||||
agent.context_compressor.context_length = 200_000
|
||||
agent.context_compressor.threshold_tokens = 100_000
|
||||
|
||||
# Mock _todo_store
|
||||
agent._todo_store = MagicMock()
|
||||
agent._todo_store.format_for_injection.return_value = None
|
||||
|
||||
# Mock _build_system_prompt
|
||||
agent._build_system_prompt = MagicMock(return_value="system prompt")
|
||||
agent._cached_system_prompt = "old system prompt"
|
||||
agent._session_db = None
|
||||
@@ -224,7 +233,8 @@ class TestContextPressureFlags:
|
||||
]
|
||||
agent._compress_context(messages, "system prompt")
|
||||
|
||||
assert agent._context_pressure_warned is False
|
||||
assert agent._context_50_warned is False
|
||||
assert agent._context_70_warned is False
|
||||
|
||||
def test_emit_callback_error_handled(self, agent):
|
||||
"""If status_callback raises, it should be caught gracefully."""
|
||||
|
||||
@@ -1,2 +1,34 @@
|
||||
# This file intentionally left empty.
|
||||
# minisweagent_path.py was removed — see PR #2804.
|
||||
"""Tests for minisweagent_path.py."""
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from minisweagent_path import discover_minisweagent_src
|
||||
|
||||
|
||||
def test_discover_minisweagent_src_in_current_checkout(tmp_path):
|
||||
repo = tmp_path / "repo"
|
||||
src = repo / "mini-swe-agent" / "src"
|
||||
src.mkdir(parents=True)
|
||||
|
||||
assert discover_minisweagent_src(repo) == src.resolve()
|
||||
|
||||
|
||||
def test_discover_minisweagent_src_falls_back_from_worktree_to_main_checkout(tmp_path):
|
||||
main_repo = tmp_path / "main-repo"
|
||||
(main_repo / ".git" / "worktrees" / "wt1").mkdir(parents=True)
|
||||
main_src = main_repo / "mini-swe-agent" / "src"
|
||||
main_src.mkdir(parents=True)
|
||||
|
||||
worktree = tmp_path / "worktree"
|
||||
worktree.mkdir()
|
||||
(worktree / ".git").write_text(f"gitdir: {main_repo / '.git' / 'worktrees' / 'wt1'}\n", encoding="utf-8")
|
||||
(worktree / "mini-swe-agent").mkdir() # empty placeholder, no src/
|
||||
|
||||
assert discover_minisweagent_src(worktree) == main_src.resolve()
|
||||
|
||||
|
||||
def test_discover_minisweagent_src_returns_none_when_missing(tmp_path):
|
||||
repo = tmp_path / "repo"
|
||||
repo.mkdir()
|
||||
|
||||
assert discover_minisweagent_src(repo) is None
|
||||
|
||||
@@ -267,7 +267,7 @@ def test_named_custom_provider_uses_saved_credentials(monkeypatch):
|
||||
|
||||
resolved = rp.resolve_runtime_provider(requested="local")
|
||||
|
||||
assert resolved["provider"] == "custom"
|
||||
assert resolved["provider"] == "openrouter"
|
||||
assert resolved["api_mode"] == "chat_completions"
|
||||
assert resolved["base_url"] == "http://1.2.3.4:1234/v1"
|
||||
assert resolved["api_key"] == "local-provider-key"
|
||||
@@ -579,81 +579,3 @@ def test_named_custom_provider_anthropic_api_mode(monkeypatch):
|
||||
|
||||
assert resolved["api_mode"] == "anthropic_messages"
|
||||
assert resolved["base_url"] == "https://proxy.example.com/anthropic"
|
||||
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# fix #2562 — resolve_provider("custom") must not remap to "openrouter"
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
|
||||
def test_resolve_provider_custom_returns_custom():
|
||||
"""resolve_provider('custom') must return 'custom', not 'openrouter'."""
|
||||
from hermes_cli.auth import resolve_provider
|
||||
assert resolve_provider("custom") == "custom"
|
||||
|
||||
|
||||
def test_resolve_provider_openrouter_unchanged():
|
||||
"""resolve_provider('openrouter') must still return 'openrouter'."""
|
||||
from hermes_cli.auth import resolve_provider
|
||||
assert resolve_provider("openrouter") == "openrouter"
|
||||
|
||||
|
||||
def test_custom_provider_runtime_preserves_provider_name(monkeypatch):
|
||||
"""resolve_runtime_provider with provider='custom' must return provider='custom'."""
|
||||
monkeypatch.delenv("OPENAI_API_KEY", raising=False)
|
||||
monkeypatch.delenv("OPENROUTER_API_KEY", raising=False)
|
||||
monkeypatch.delenv("OPENAI_BASE_URL", raising=False)
|
||||
monkeypatch.delenv("OPENROUTER_BASE_URL", raising=False)
|
||||
monkeypatch.setattr(
|
||||
rp,
|
||||
"load_config",
|
||||
lambda: {
|
||||
"model": {
|
||||
"provider": "custom",
|
||||
"base_url": "http://localhost:8080/v1",
|
||||
"api_key": "test-key-123",
|
||||
}
|
||||
},
|
||||
)
|
||||
|
||||
resolved = rp.resolve_runtime_provider(requested="custom")
|
||||
assert resolved["provider"] == "custom", (
|
||||
f"Expected provider='custom', got provider='{resolved['provider']}'"
|
||||
)
|
||||
assert resolved["base_url"] == "http://localhost:8080/v1"
|
||||
assert resolved["api_key"] == "test-key-123"
|
||||
|
||||
|
||||
def test_custom_provider_no_key_gets_placeholder(monkeypatch):
|
||||
"""Local server with no API key should get 'no-key-required' placeholder."""
|
||||
monkeypatch.delenv("OPENAI_API_KEY", raising=False)
|
||||
monkeypatch.delenv("OPENROUTER_API_KEY", raising=False)
|
||||
monkeypatch.delenv("OPENAI_BASE_URL", raising=False)
|
||||
monkeypatch.delenv("OPENROUTER_BASE_URL", raising=False)
|
||||
monkeypatch.setattr(
|
||||
rp,
|
||||
"load_config",
|
||||
lambda: {
|
||||
"model": {
|
||||
"provider": "custom",
|
||||
"base_url": "http://localhost:8080/v1",
|
||||
}
|
||||
},
|
||||
)
|
||||
|
||||
resolved = rp.resolve_runtime_provider(requested="custom")
|
||||
assert resolved["provider"] == "custom"
|
||||
assert resolved["api_key"] == "no-key-required"
|
||||
assert resolved["base_url"] == "http://localhost:8080/v1"
|
||||
|
||||
|
||||
def test_openrouter_provider_not_affected_by_custom_fix(monkeypatch):
|
||||
"""Fixing custom must not change openrouter behavior."""
|
||||
monkeypatch.delenv("OPENAI_API_KEY", raising=False)
|
||||
monkeypatch.delenv("OPENAI_BASE_URL", raising=False)
|
||||
monkeypatch.delenv("OPENROUTER_BASE_URL", raising=False)
|
||||
monkeypatch.setenv("OPENROUTER_API_KEY", "test-or-key")
|
||||
monkeypatch.setattr(rp, "load_config", lambda: {})
|
||||
|
||||
resolved = rp.resolve_runtime_provider(requested="openrouter")
|
||||
assert resolved["provider"] == "openrouter"
|
||||
|
||||
@@ -1,168 +0,0 @@
|
||||
"""Comprehensive tests for ANSI escape sequence stripping (ECMA-48).
|
||||
|
||||
The strip_ansi function in tools/ansi_strip.py is the source-level fix for
|
||||
ANSI codes leaking into the model's context via terminal/execute_code output.
|
||||
It must strip ALL terminal escape sequences while preserving legitimate text.
|
||||
"""
|
||||
|
||||
from tools.ansi_strip import strip_ansi
|
||||
|
||||
|
||||
class TestStripAnsiBasicSGR:
|
||||
"""Select Graphic Rendition — the most common ANSI sequences."""
|
||||
|
||||
def test_reset(self):
|
||||
assert strip_ansi("\x1b[0m") == ""
|
||||
|
||||
def test_color(self):
|
||||
assert strip_ansi("\x1b[31;1m") == ""
|
||||
|
||||
def test_truecolor_semicolon(self):
|
||||
assert strip_ansi("\x1b[38;2;255;0;0m") == ""
|
||||
|
||||
def test_truecolor_colon_separated(self):
|
||||
"""Modern terminals use colon-separated SGR params."""
|
||||
assert strip_ansi("\x1b[38:2:255:0:0m") == ""
|
||||
assert strip_ansi("\x1b[48:2:0:255:0m") == ""
|
||||
|
||||
|
||||
class TestStripAnsiCSIPrivateMode:
|
||||
"""CSI sequences with ? prefix (DEC private modes)."""
|
||||
|
||||
def test_cursor_show_hide(self):
|
||||
assert strip_ansi("\x1b[?25h") == ""
|
||||
assert strip_ansi("\x1b[?25l") == ""
|
||||
|
||||
def test_alt_screen(self):
|
||||
assert strip_ansi("\x1b[?1049h") == ""
|
||||
assert strip_ansi("\x1b[?1049l") == ""
|
||||
|
||||
def test_bracketed_paste(self):
|
||||
assert strip_ansi("\x1b[?2004h") == ""
|
||||
|
||||
|
||||
class TestStripAnsiCSIIntermediate:
|
||||
"""CSI sequences with intermediate bytes (space, etc.)."""
|
||||
|
||||
def test_cursor_shape(self):
|
||||
assert strip_ansi("\x1b[0 q") == ""
|
||||
assert strip_ansi("\x1b[2 q") == ""
|
||||
assert strip_ansi("\x1b[6 q") == ""
|
||||
|
||||
|
||||
class TestStripAnsiOSC:
|
||||
"""Operating System Command sequences."""
|
||||
|
||||
def test_bel_terminator(self):
|
||||
assert strip_ansi("\x1b]0;title\x07") == ""
|
||||
|
||||
def test_st_terminator(self):
|
||||
assert strip_ansi("\x1b]0;title\x1b\\") == ""
|
||||
|
||||
def test_hyperlink_preserves_text(self):
|
||||
assert strip_ansi(
|
||||
"\x1b]8;;https://example.com\x1b\\click\x1b]8;;\x1b\\"
|
||||
) == "click"
|
||||
|
||||
|
||||
class TestStripAnsiDECPrivate:
|
||||
"""DEC private / Fp escape sequences."""
|
||||
|
||||
def test_save_restore_cursor(self):
|
||||
assert strip_ansi("\x1b7") == ""
|
||||
assert strip_ansi("\x1b8") == ""
|
||||
|
||||
def test_keypad_modes(self):
|
||||
assert strip_ansi("\x1b=") == ""
|
||||
assert strip_ansi("\x1b>") == ""
|
||||
|
||||
|
||||
class TestStripAnsiFe:
|
||||
"""Fe (C1 as 7-bit) escape sequences."""
|
||||
|
||||
def test_reverse_index(self):
|
||||
assert strip_ansi("\x1bM") == ""
|
||||
|
||||
def test_reset_terminal(self):
|
||||
assert strip_ansi("\x1bc") == ""
|
||||
|
||||
def test_index_and_newline(self):
|
||||
assert strip_ansi("\x1bD") == ""
|
||||
assert strip_ansi("\x1bE") == ""
|
||||
|
||||
|
||||
class TestStripAnsiNF:
|
||||
"""nF (character set selection) sequences."""
|
||||
|
||||
def test_charset_selection(self):
|
||||
assert strip_ansi("\x1b(A") == ""
|
||||
assert strip_ansi("\x1b(B") == ""
|
||||
assert strip_ansi("\x1b(0") == ""
|
||||
|
||||
|
||||
class TestStripAnsiDCS:
|
||||
"""Device Control String sequences."""
|
||||
|
||||
def test_dcs(self):
|
||||
assert strip_ansi("\x1bP+q\x1b\\") == ""
|
||||
|
||||
|
||||
class TestStripAnsi8BitC1:
|
||||
"""8-bit C1 control characters."""
|
||||
|
||||
def test_8bit_csi(self):
|
||||
assert strip_ansi("\x9b31m") == ""
|
||||
assert strip_ansi("\x9b38;2;255;0;0m") == ""
|
||||
|
||||
def test_8bit_standalone(self):
|
||||
assert strip_ansi("\x9c") == ""
|
||||
assert strip_ansi("\x9d") == ""
|
||||
assert strip_ansi("\x90") == ""
|
||||
|
||||
|
||||
class TestStripAnsiRealWorld:
|
||||
"""Real-world contamination scenarios from bug reports."""
|
||||
|
||||
def test_colored_shebang(self):
|
||||
"""The original reported bug: shebang corrupted by color codes."""
|
||||
assert strip_ansi(
|
||||
"\x1b[32m#!/usr/bin/env python3\x1b[0m\nprint('hello')"
|
||||
) == "#!/usr/bin/env python3\nprint('hello')"
|
||||
|
||||
def test_stacked_sgr(self):
|
||||
assert strip_ansi(
|
||||
"\x1b[1m\x1b[31m\x1b[42mhello\x1b[0m"
|
||||
) == "hello"
|
||||
|
||||
def test_ansi_mid_code(self):
|
||||
assert strip_ansi(
|
||||
"def foo(\x1b[33m):\x1b[0m\n return 42"
|
||||
) == "def foo():\n return 42"
|
||||
|
||||
|
||||
class TestStripAnsiPassthrough:
|
||||
"""Clean content must pass through unmodified."""
|
||||
|
||||
def test_plain_text(self):
|
||||
assert strip_ansi("normal text") == "normal text"
|
||||
|
||||
def test_empty(self):
|
||||
assert strip_ansi("") == ""
|
||||
|
||||
def test_none(self):
|
||||
assert strip_ansi(None) is None
|
||||
|
||||
def test_whitespace_preserved(self):
|
||||
assert strip_ansi("line1\nline2\ttab") == "line1\nline2\ttab"
|
||||
|
||||
def test_unicode_safe(self):
|
||||
assert strip_ansi("emoji 🎉 and ñ café") == "emoji 🎉 and ñ café"
|
||||
|
||||
def test_backslash_in_code(self):
|
||||
code = "path = 'C:\\\\Users\\\\test'"
|
||||
assert strip_ansi(code) == code
|
||||
|
||||
def test_square_brackets_in_code(self):
|
||||
"""Array indexing must not be confused with CSI."""
|
||||
code = "arr[0] = arr[31]"
|
||||
assert strip_ansi(code) == code
|
||||
@@ -1,259 +0,0 @@
|
||||
"""Tests for macOS Homebrew PATH discovery in browser_tool.py."""
|
||||
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch, MagicMock, mock_open
|
||||
|
||||
import pytest
|
||||
|
||||
from tools.browser_tool import (
|
||||
_discover_homebrew_node_dirs,
|
||||
_find_agent_browser,
|
||||
_run_browser_command,
|
||||
_SANE_PATH,
|
||||
)
|
||||
|
||||
|
||||
class TestSanePath:
|
||||
"""Verify _SANE_PATH includes Homebrew directories."""
|
||||
|
||||
def test_includes_homebrew_bin(self):
|
||||
assert "/opt/homebrew/bin" in _SANE_PATH
|
||||
|
||||
def test_includes_homebrew_sbin(self):
|
||||
assert "/opt/homebrew/sbin" in _SANE_PATH
|
||||
|
||||
def test_includes_standard_dirs(self):
|
||||
assert "/usr/local/bin" in _SANE_PATH
|
||||
assert "/usr/bin" in _SANE_PATH
|
||||
assert "/bin" in _SANE_PATH
|
||||
|
||||
|
||||
class TestDiscoverHomebrewNodeDirs:
|
||||
"""Tests for _discover_homebrew_node_dirs()."""
|
||||
|
||||
def test_returns_empty_when_no_homebrew(self):
|
||||
"""Non-macOS systems without /opt/homebrew/opt should return empty."""
|
||||
with patch("os.path.isdir", return_value=False):
|
||||
assert _discover_homebrew_node_dirs() == []
|
||||
|
||||
def test_finds_versioned_node_dirs(self):
|
||||
"""Should discover node@20/bin, node@24/bin etc."""
|
||||
entries = ["node@20", "node@24", "openssl", "node", "python@3.12"]
|
||||
|
||||
def mock_isdir(p):
|
||||
if p == "/opt/homebrew/opt":
|
||||
return True
|
||||
# node@20/bin and node@24/bin exist
|
||||
if p in (
|
||||
"/opt/homebrew/opt/node@20/bin",
|
||||
"/opt/homebrew/opt/node@24/bin",
|
||||
):
|
||||
return True
|
||||
return False
|
||||
|
||||
with patch("os.path.isdir", side_effect=mock_isdir), \
|
||||
patch("os.listdir", return_value=entries):
|
||||
result = _discover_homebrew_node_dirs()
|
||||
|
||||
assert len(result) == 2
|
||||
assert "/opt/homebrew/opt/node@20/bin" in result
|
||||
assert "/opt/homebrew/opt/node@24/bin" in result
|
||||
|
||||
def test_excludes_plain_node(self):
|
||||
"""'node' (unversioned) should be excluded — covered by /opt/homebrew/bin."""
|
||||
with patch("os.path.isdir", return_value=True), \
|
||||
patch("os.listdir", return_value=["node"]):
|
||||
result = _discover_homebrew_node_dirs()
|
||||
assert result == []
|
||||
|
||||
def test_handles_oserror_gracefully(self):
|
||||
"""Should return empty list if listdir raises OSError."""
|
||||
with patch("os.path.isdir", return_value=True), \
|
||||
patch("os.listdir", side_effect=OSError("Permission denied")):
|
||||
assert _discover_homebrew_node_dirs() == []
|
||||
|
||||
|
||||
class TestFindAgentBrowser:
|
||||
"""Tests for _find_agent_browser() Homebrew path search."""
|
||||
|
||||
def test_finds_in_current_path(self):
|
||||
"""Should return result from shutil.which if available on current PATH."""
|
||||
with patch("shutil.which", return_value="/usr/local/bin/agent-browser"):
|
||||
assert _find_agent_browser() == "/usr/local/bin/agent-browser"
|
||||
|
||||
def test_finds_in_homebrew_bin(self):
|
||||
"""Should search Homebrew dirs when not found on current PATH."""
|
||||
def mock_which(cmd, path=None):
|
||||
if path and "/opt/homebrew/bin" in path and cmd == "agent-browser":
|
||||
return "/opt/homebrew/bin/agent-browser"
|
||||
return None
|
||||
|
||||
with patch("shutil.which", side_effect=mock_which), \
|
||||
patch("os.path.isdir", return_value=True), \
|
||||
patch(
|
||||
"tools.browser_tool._discover_homebrew_node_dirs",
|
||||
return_value=[],
|
||||
):
|
||||
result = _find_agent_browser()
|
||||
assert result == "/opt/homebrew/bin/agent-browser"
|
||||
|
||||
def test_finds_npx_in_homebrew(self):
|
||||
"""Should find npx in Homebrew paths as a fallback."""
|
||||
def mock_which(cmd, path=None):
|
||||
if cmd == "agent-browser":
|
||||
return None
|
||||
if cmd == "npx":
|
||||
if path and "/opt/homebrew/bin" in path:
|
||||
return "/opt/homebrew/bin/npx"
|
||||
return None
|
||||
return None
|
||||
|
||||
# Mock Path.exists() to prevent the local node_modules check from matching
|
||||
original_path_exists = Path.exists
|
||||
|
||||
def mock_path_exists(self):
|
||||
if "node_modules" in str(self) and "agent-browser" in str(self):
|
||||
return False
|
||||
return original_path_exists(self)
|
||||
|
||||
with patch("shutil.which", side_effect=mock_which), \
|
||||
patch("os.path.isdir", return_value=True), \
|
||||
patch.object(Path, "exists", mock_path_exists), \
|
||||
patch(
|
||||
"tools.browser_tool._discover_homebrew_node_dirs",
|
||||
return_value=[],
|
||||
):
|
||||
result = _find_agent_browser()
|
||||
assert result == "npx agent-browser"
|
||||
|
||||
def test_raises_when_not_found(self):
|
||||
"""Should raise FileNotFoundError when nothing works."""
|
||||
original_path_exists = Path.exists
|
||||
|
||||
def mock_path_exists(self):
|
||||
if "node_modules" in str(self) and "agent-browser" in str(self):
|
||||
return False
|
||||
return original_path_exists(self)
|
||||
|
||||
with patch("shutil.which", return_value=None), \
|
||||
patch("os.path.isdir", return_value=False), \
|
||||
patch.object(Path, "exists", mock_path_exists), \
|
||||
patch(
|
||||
"tools.browser_tool._discover_homebrew_node_dirs",
|
||||
return_value=[],
|
||||
):
|
||||
with pytest.raises(FileNotFoundError, match="agent-browser CLI not found"):
|
||||
_find_agent_browser()
|
||||
|
||||
|
||||
class TestRunBrowserCommandPathConstruction:
|
||||
"""Verify _run_browser_command() includes Homebrew node dirs in subprocess PATH."""
|
||||
|
||||
def test_subprocess_path_includes_homebrew_node_dirs(self, tmp_path):
|
||||
"""When _discover_homebrew_node_dirs returns dirs, they should appear
|
||||
in the subprocess env PATH passed to Popen."""
|
||||
captured_env = {}
|
||||
|
||||
# Create a mock Popen that captures the env dict
|
||||
mock_proc = MagicMock()
|
||||
mock_proc.returncode = 0
|
||||
mock_proc.wait.return_value = 0
|
||||
|
||||
def capture_popen(cmd, **kwargs):
|
||||
captured_env.update(kwargs.get("env", {}))
|
||||
return mock_proc
|
||||
|
||||
fake_session = {
|
||||
"session_name": "test-session",
|
||||
"session_id": "test-id",
|
||||
"cdp_url": None,
|
||||
}
|
||||
|
||||
# Write fake JSON output to the stdout temp file
|
||||
fake_json = json.dumps({"success": True})
|
||||
stdout_file = tmp_path / "stdout"
|
||||
stdout_file.write_text(fake_json)
|
||||
|
||||
fake_homebrew_dirs = [
|
||||
"/opt/homebrew/opt/node@24/bin",
|
||||
"/opt/homebrew/opt/node@20/bin",
|
||||
]
|
||||
|
||||
# We need os.path.isdir to return True for our fake dirs
|
||||
# but we also need real isdir for tmp_path operations
|
||||
real_isdir = os.path.isdir
|
||||
|
||||
def selective_isdir(p):
|
||||
if p in fake_homebrew_dirs or p.startswith(str(tmp_path)):
|
||||
return True
|
||||
if "/opt/homebrew/" in p:
|
||||
return True # _SANE_PATH dirs
|
||||
return real_isdir(p)
|
||||
|
||||
with patch("tools.browser_tool._find_agent_browser", return_value="/usr/local/bin/agent-browser"), \
|
||||
patch("tools.browser_tool._get_session_info", return_value=fake_session), \
|
||||
patch("tools.browser_tool._socket_safe_tmpdir", return_value=str(tmp_path)), \
|
||||
patch("tools.browser_tool._discover_homebrew_node_dirs", return_value=fake_homebrew_dirs), \
|
||||
patch("os.path.isdir", side_effect=selective_isdir), \
|
||||
patch("subprocess.Popen", side_effect=capture_popen), \
|
||||
patch("os.open", return_value=99), \
|
||||
patch("os.close"), \
|
||||
patch("tools.interrupt.is_interrupted", return_value=False), \
|
||||
patch.dict(os.environ, {"PATH": "/usr/bin:/bin", "HOME": "/home/test"}, clear=True):
|
||||
# The function reads from temp files for stdout/stderr
|
||||
with patch("builtins.open", mock_open(read_data=fake_json)):
|
||||
_run_browser_command("test-task", "navigate", ["https://example.com"])
|
||||
|
||||
# Verify Homebrew node dirs made it into the subprocess PATH
|
||||
result_path = captured_env.get("PATH", "")
|
||||
assert "/opt/homebrew/opt/node@24/bin" in result_path
|
||||
assert "/opt/homebrew/opt/node@20/bin" in result_path
|
||||
assert "/opt/homebrew/bin" in result_path # from _SANE_PATH
|
||||
|
||||
def test_subprocess_path_includes_sane_path_homebrew(self, tmp_path):
|
||||
"""_SANE_PATH Homebrew entries should appear even without versioned node dirs."""
|
||||
captured_env = {}
|
||||
|
||||
mock_proc = MagicMock()
|
||||
mock_proc.returncode = 0
|
||||
mock_proc.wait.return_value = 0
|
||||
|
||||
def capture_popen(cmd, **kwargs):
|
||||
captured_env.update(kwargs.get("env", {}))
|
||||
return mock_proc
|
||||
|
||||
fake_session = {
|
||||
"session_name": "test-session",
|
||||
"session_id": "test-id",
|
||||
"cdp_url": None,
|
||||
}
|
||||
|
||||
fake_json = json.dumps({"success": True})
|
||||
real_isdir = os.path.isdir
|
||||
|
||||
def selective_isdir(p):
|
||||
if "/opt/homebrew/" in p:
|
||||
return True
|
||||
if p.startswith(str(tmp_path)):
|
||||
return True
|
||||
return real_isdir(p)
|
||||
|
||||
with patch("tools.browser_tool._find_agent_browser", return_value="/usr/local/bin/agent-browser"), \
|
||||
patch("tools.browser_tool._get_session_info", return_value=fake_session), \
|
||||
patch("tools.browser_tool._socket_safe_tmpdir", return_value=str(tmp_path)), \
|
||||
patch("tools.browser_tool._discover_homebrew_node_dirs", return_value=[]), \
|
||||
patch("os.path.isdir", side_effect=selective_isdir), \
|
||||
patch("subprocess.Popen", side_effect=capture_popen), \
|
||||
patch("os.open", return_value=99), \
|
||||
patch("os.close"), \
|
||||
patch("tools.interrupt.is_interrupted", return_value=False), \
|
||||
patch.dict(os.environ, {"PATH": "/usr/bin:/bin", "HOME": "/home/test"}, clear=True):
|
||||
with patch("builtins.open", mock_open(read_data=fake_json)):
|
||||
_run_browser_command("test-task", "navigate", ["https://example.com"])
|
||||
|
||||
result_path = captured_env.get("PATH", "")
|
||||
assert "/opt/homebrew/bin" in result_path
|
||||
assert "/opt/homebrew/sbin" in result_path
|
||||
@@ -131,9 +131,9 @@ class TestExecuteCode(unittest.TestCase):
|
||||
|
||||
def test_repo_root_modules_are_importable(self):
|
||||
"""Sandboxed scripts can import modules that live at the repo root."""
|
||||
result = self._run('import hermes_constants; print(hermes_constants.__file__)')
|
||||
result = self._run('import minisweagent_path; print(minisweagent_path.__file__)')
|
||||
self.assertEqual(result["status"], "success")
|
||||
self.assertIn("hermes_constants.py", result["output"])
|
||||
self.assertIn("minisweagent_path.py", result["output"])
|
||||
|
||||
def test_single_tool_call(self):
|
||||
"""Script calls terminal and prints the result."""
|
||||
|
||||
@@ -9,24 +9,25 @@ import pytest
|
||||
from tools.environments import docker as docker_env
|
||||
|
||||
|
||||
def _mock_subprocess_run(monkeypatch):
|
||||
"""Mock subprocess.run to intercept docker run -d and docker version calls.
|
||||
def _install_fake_minisweagent(monkeypatch, captured_run_args):
|
||||
class MockInnerDocker:
|
||||
container_id = "fake-container"
|
||||
config = type("Config", (), {"executable": "/usr/bin/docker", "forward_env": [], "env": {}})()
|
||||
|
||||
Returns a list of captured (cmd, kwargs) tuples for inspection.
|
||||
"""
|
||||
calls = []
|
||||
def __init__(self, **kwargs):
|
||||
captured_run_args.extend(kwargs.get("run_args", []))
|
||||
|
||||
def _run(cmd, **kwargs):
|
||||
calls.append((list(cmd) if isinstance(cmd, list) else cmd, kwargs))
|
||||
if isinstance(cmd, list) and len(cmd) >= 2:
|
||||
if cmd[1] == "version":
|
||||
return subprocess.CompletedProcess(cmd, 0, stdout="Docker version", stderr="")
|
||||
if cmd[1] == "run":
|
||||
return subprocess.CompletedProcess(cmd, 0, stdout="fake-container-id\n", stderr="")
|
||||
return subprocess.CompletedProcess(cmd, 0, stdout="", stderr="")
|
||||
def cleanup(self):
|
||||
pass
|
||||
|
||||
monkeypatch.setattr(docker_env.subprocess, "run", _run)
|
||||
return calls
|
||||
minisweagent_mod = types.ModuleType("minisweagent")
|
||||
environments_mod = types.ModuleType("minisweagent.environments")
|
||||
docker_mod = types.ModuleType("minisweagent.environments.docker")
|
||||
docker_mod.DockerEnvironment = MockInnerDocker
|
||||
|
||||
monkeypatch.setitem(sys.modules, "minisweagent", minisweagent_mod)
|
||||
monkeypatch.setitem(sys.modules, "minisweagent.environments", environments_mod)
|
||||
monkeypatch.setitem(sys.modules, "minisweagent.environments.docker", docker_mod)
|
||||
|
||||
|
||||
def _make_dummy_env(**kwargs):
|
||||
@@ -48,7 +49,7 @@ def _make_dummy_env(**kwargs):
|
||||
|
||||
|
||||
def test_ensure_docker_available_logs_and_raises_when_not_found(monkeypatch, caplog):
|
||||
"""When docker cannot be found, raise a clear error before container setup."""
|
||||
"""When docker cannot be found, raise a clear error before mini-swe setup."""
|
||||
|
||||
monkeypatch.setattr(docker_env, "find_docker", lambda: None)
|
||||
monkeypatch.setattr(
|
||||
@@ -117,8 +118,14 @@ def test_auto_mount_host_cwd_adds_volume(monkeypatch, tmp_path):
|
||||
project_dir = tmp_path / "my-project"
|
||||
project_dir.mkdir()
|
||||
|
||||
def _run_docker_version(*args, **kwargs):
|
||||
return subprocess.CompletedProcess(args[0], 0, stdout="Docker version", stderr="")
|
||||
|
||||
monkeypatch.setattr(docker_env, "find_docker", lambda: "/usr/bin/docker")
|
||||
calls = _mock_subprocess_run(monkeypatch)
|
||||
monkeypatch.setattr(docker_env.subprocess, "run", _run_docker_version)
|
||||
|
||||
captured_run_args = []
|
||||
_install_fake_minisweagent(monkeypatch, captured_run_args)
|
||||
|
||||
_make_dummy_env(
|
||||
cwd="/workspace",
|
||||
@@ -126,10 +133,7 @@ def test_auto_mount_host_cwd_adds_volume(monkeypatch, tmp_path):
|
||||
auto_mount_cwd=True,
|
||||
)
|
||||
|
||||
# Find the docker run call and check its args
|
||||
run_calls = [c for c in calls if isinstance(c[0], list) and len(c[0]) >= 2 and c[0][1] == "run"]
|
||||
assert run_calls, "docker run should have been called"
|
||||
run_args_str = " ".join(run_calls[0][0])
|
||||
run_args_str = " ".join(captured_run_args)
|
||||
assert f"{project_dir}:/workspace" in run_args_str
|
||||
|
||||
|
||||
@@ -138,8 +142,14 @@ def test_auto_mount_disabled_by_default(monkeypatch, tmp_path):
|
||||
project_dir = tmp_path / "my-project"
|
||||
project_dir.mkdir()
|
||||
|
||||
def _run_docker_version(*args, **kwargs):
|
||||
return subprocess.CompletedProcess(args[0], 0, stdout="Docker version", stderr="")
|
||||
|
||||
monkeypatch.setattr(docker_env, "find_docker", lambda: "/usr/bin/docker")
|
||||
calls = _mock_subprocess_run(monkeypatch)
|
||||
monkeypatch.setattr(docker_env.subprocess, "run", _run_docker_version)
|
||||
|
||||
captured_run_args = []
|
||||
_install_fake_minisweagent(monkeypatch, captured_run_args)
|
||||
|
||||
_make_dummy_env(
|
||||
cwd="/root",
|
||||
@@ -147,9 +157,7 @@ def test_auto_mount_disabled_by_default(monkeypatch, tmp_path):
|
||||
auto_mount_cwd=False,
|
||||
)
|
||||
|
||||
run_calls = [c for c in calls if isinstance(c[0], list) and len(c[0]) >= 2 and c[0][1] == "run"]
|
||||
assert run_calls, "docker run should have been called"
|
||||
run_args_str = " ".join(run_calls[0][0])
|
||||
run_args_str = " ".join(captured_run_args)
|
||||
assert f"{project_dir}:/workspace" not in run_args_str
|
||||
|
||||
|
||||
@@ -160,8 +168,14 @@ def test_auto_mount_skipped_when_workspace_already_mounted(monkeypatch, tmp_path
|
||||
other_dir = tmp_path / "other"
|
||||
other_dir.mkdir()
|
||||
|
||||
def _run_docker_version(*args, **kwargs):
|
||||
return subprocess.CompletedProcess(args[0], 0, stdout="Docker version", stderr="")
|
||||
|
||||
monkeypatch.setattr(docker_env, "find_docker", lambda: "/usr/bin/docker")
|
||||
calls = _mock_subprocess_run(monkeypatch)
|
||||
monkeypatch.setattr(docker_env.subprocess, "run", _run_docker_version)
|
||||
|
||||
captured_run_args = []
|
||||
_install_fake_minisweagent(monkeypatch, captured_run_args)
|
||||
|
||||
_make_dummy_env(
|
||||
cwd="/workspace",
|
||||
@@ -170,9 +184,7 @@ def test_auto_mount_skipped_when_workspace_already_mounted(monkeypatch, tmp_path
|
||||
volumes=[f"{other_dir}:/workspace"],
|
||||
)
|
||||
|
||||
run_calls = [c for c in calls if isinstance(c[0], list) and len(c[0]) >= 2 and c[0][1] == "run"]
|
||||
assert run_calls, "docker run should have been called"
|
||||
run_args_str = " ".join(run_calls[0][0])
|
||||
run_args_str = " ".join(captured_run_args)
|
||||
assert f"{other_dir}:/workspace" in run_args_str
|
||||
assert run_args_str.count(":/workspace") == 1
|
||||
|
||||
@@ -182,8 +194,14 @@ def test_auto_mount_replaces_persistent_workspace_bind(monkeypatch, tmp_path):
|
||||
project_dir = tmp_path / "my-project"
|
||||
project_dir.mkdir()
|
||||
|
||||
def _run_docker_version(*args, **kwargs):
|
||||
return subprocess.CompletedProcess(args[0], 0, stdout="Docker version", stderr="")
|
||||
|
||||
monkeypatch.setattr(docker_env, "find_docker", lambda: "/usr/bin/docker")
|
||||
calls = _mock_subprocess_run(monkeypatch)
|
||||
monkeypatch.setattr(docker_env.subprocess, "run", _run_docker_version)
|
||||
|
||||
captured_run_args = []
|
||||
_install_fake_minisweagent(monkeypatch, captured_run_args)
|
||||
|
||||
_make_dummy_env(
|
||||
cwd="/workspace",
|
||||
@@ -193,23 +211,28 @@ def test_auto_mount_replaces_persistent_workspace_bind(monkeypatch, tmp_path):
|
||||
task_id="test-persistent-auto-mount",
|
||||
)
|
||||
|
||||
run_calls = [c for c in calls if isinstance(c[0], list) and len(c[0]) >= 2 and c[0][1] == "run"]
|
||||
assert run_calls, "docker run should have been called"
|
||||
run_args_str = " ".join(run_calls[0][0])
|
||||
run_args_str = " ".join(captured_run_args)
|
||||
assert f"{project_dir}:/workspace" in run_args_str
|
||||
assert "/sandboxes/docker/test-persistent-auto-mount/workspace:/workspace" not in run_args_str
|
||||
|
||||
|
||||
def test_non_persistent_cleanup_removes_container(monkeypatch):
|
||||
"""When persistent=false, cleanup() must schedule docker stop + rm."""
|
||||
monkeypatch.setattr(docker_env, "find_docker", lambda: "/usr/bin/docker")
|
||||
calls = _mock_subprocess_run(monkeypatch)
|
||||
"""When container_persistent=false, cleanup() must run docker rm -f so the container is removed (Fixes #1679)."""
|
||||
run_calls = []
|
||||
|
||||
popen_cmds = []
|
||||
monkeypatch.setattr(
|
||||
docker_env.subprocess, "Popen",
|
||||
lambda cmd, **kw: (popen_cmds.append(cmd), type("P", (), {"poll": lambda s: 0, "wait": lambda s, **k: None, "returncode": 0, "stdout": iter([]), "stdin": None})())[1],
|
||||
)
|
||||
def _run(cmd, **kwargs):
|
||||
run_calls.append((list(cmd) if isinstance(cmd, list) else cmd, kwargs))
|
||||
if cmd and getattr(cmd[0], "__str__", None) and "docker" in str(cmd[0]):
|
||||
if len(cmd) >= 2 and cmd[1] == "run":
|
||||
return subprocess.CompletedProcess(cmd, 0, stdout="abc123container\n", stderr="")
|
||||
return subprocess.CompletedProcess(cmd, 0, stdout="", stderr="")
|
||||
|
||||
monkeypatch.setattr(docker_env, "find_docker", lambda: "/usr/bin/docker")
|
||||
monkeypatch.setattr(docker_env.subprocess, "run", _run)
|
||||
monkeypatch.setattr(docker_env.subprocess, "Popen", lambda *a, **k: type("P", (), {"poll": lambda: None, "wait": lambda **kw: None, "returncode": 0, "stdout": iter([]), "stdin": None})())
|
||||
|
||||
captured_run_args = []
|
||||
_install_fake_minisweagent(monkeypatch, captured_run_args)
|
||||
|
||||
env = _make_dummy_env(persistent_filesystem=False, task_id="ephemeral-task")
|
||||
assert env._container_id
|
||||
@@ -217,9 +240,8 @@ def test_non_persistent_cleanup_removes_container(monkeypatch):
|
||||
|
||||
env.cleanup()
|
||||
|
||||
# Should have stop and rm calls via Popen
|
||||
stop_cmds = [c for c in popen_cmds if container_id in str(c) and "stop" in str(c)]
|
||||
assert len(stop_cmds) >= 1, f"cleanup() should schedule docker stop for {container_id}"
|
||||
rm_calls = [c for c in run_calls if isinstance(c[0], list) and len(c[0]) >= 4 and c[0][1:4] == ["rm", "-f", container_id]]
|
||||
assert len(rm_calls) >= 1, "cleanup() should run docker rm -f <container_id> when container_persistent=false"
|
||||
|
||||
|
||||
class _FakePopen:
|
||||
@@ -241,8 +263,10 @@ def _make_execute_only_env(forward_env=None):
|
||||
env._forward_env = forward_env or []
|
||||
env._prepare_command = lambda command: (command, None)
|
||||
env._timeout_result = lambda timeout: {"output": f"timed out after {timeout}", "returncode": 124}
|
||||
env._container_id = "test-container"
|
||||
env._docker_exe = "/usr/bin/docker"
|
||||
env._inner = type("Inner", (), {
|
||||
"container_id": "test-container",
|
||||
"config": type("Cfg", (), {"executable": "/usr/bin/docker", "env": {}})(),
|
||||
})()
|
||||
return env
|
||||
|
||||
|
||||
@@ -280,3 +304,31 @@ def test_execute_prefers_shell_env_over_hermes_dotenv(monkeypatch):
|
||||
|
||||
assert "GITHUB_TOKEN=value_from_shell" in popen_calls[0]
|
||||
assert "GITHUB_TOKEN=value_from_dotenv" not in popen_calls[0]
|
||||
|
||||
|
||||
def test_non_persistent_cleanup_removes_container(monkeypatch):
|
||||
"""When container_persistent=false, cleanup() must run docker rm -f so the container is removed (Fixes #1679)."""
|
||||
run_calls = []
|
||||
|
||||
def _run(cmd, **kwargs):
|
||||
run_calls.append((list(cmd) if isinstance(cmd, list) else cmd, kwargs))
|
||||
if cmd and getattr(cmd[0], '__str__', None) and 'docker' in str(cmd[0]):
|
||||
if len(cmd) >= 2 and cmd[1] == 'run':
|
||||
return subprocess.CompletedProcess(cmd, 0, stdout="abc123container\n", stderr="")
|
||||
return subprocess.CompletedProcess(cmd, 0, stdout='', stderr='')
|
||||
|
||||
monkeypatch.setattr(docker_env, 'find_docker', lambda: '/usr/bin/docker')
|
||||
monkeypatch.setattr(docker_env.subprocess, 'run', _run)
|
||||
monkeypatch.setattr(docker_env.subprocess, 'Popen', lambda *a, **k: type('P', (), {'poll': lambda: None, 'wait': lambda **kw: None, 'returncode': 0, 'stdout': iter([]), 'stdin': None})())
|
||||
|
||||
captured_run_args = []
|
||||
_install_fake_minisweagent(monkeypatch, captured_run_args)
|
||||
|
||||
env = _make_dummy_env(persistent_filesystem=False, task_id='ephemeral-task')
|
||||
assert env._container_id
|
||||
container_id = env._container_id
|
||||
|
||||
env.cleanup()
|
||||
|
||||
rm_calls = [c for c in run_calls if isinstance(c[0], list) and len(c[0]) >= 4 and c[0][1:4] == ['rm', '-f', container_id]]
|
||||
assert len(rm_calls) >= 1, 'cleanup() should run docker rm -f <container_id> when container_persistent=false'
|
||||
|
||||
@@ -1,199 +0,0 @@
|
||||
"""Tests for tools.env_passthrough — skill and config env var passthrough."""
|
||||
|
||||
import os
|
||||
import pytest
|
||||
import yaml
|
||||
|
||||
from tools.env_passthrough import (
|
||||
clear_env_passthrough,
|
||||
get_all_passthrough,
|
||||
is_env_passthrough,
|
||||
register_env_passthrough,
|
||||
reset_config_cache,
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _clean_passthrough():
|
||||
"""Ensure a clean passthrough state for every test."""
|
||||
clear_env_passthrough()
|
||||
reset_config_cache()
|
||||
yield
|
||||
clear_env_passthrough()
|
||||
reset_config_cache()
|
||||
|
||||
|
||||
class TestSkillScopedPassthrough:
|
||||
def test_register_and_check(self):
|
||||
assert not is_env_passthrough("TENOR_API_KEY")
|
||||
register_env_passthrough(["TENOR_API_KEY"])
|
||||
assert is_env_passthrough("TENOR_API_KEY")
|
||||
|
||||
def test_register_multiple(self):
|
||||
register_env_passthrough(["FOO_TOKEN", "BAR_SECRET"])
|
||||
assert is_env_passthrough("FOO_TOKEN")
|
||||
assert is_env_passthrough("BAR_SECRET")
|
||||
assert not is_env_passthrough("OTHER_KEY")
|
||||
|
||||
def test_clear(self):
|
||||
register_env_passthrough(["TENOR_API_KEY"])
|
||||
assert is_env_passthrough("TENOR_API_KEY")
|
||||
clear_env_passthrough()
|
||||
assert not is_env_passthrough("TENOR_API_KEY")
|
||||
|
||||
def test_get_all(self):
|
||||
register_env_passthrough(["A_KEY", "B_TOKEN"])
|
||||
result = get_all_passthrough()
|
||||
assert "A_KEY" in result
|
||||
assert "B_TOKEN" in result
|
||||
|
||||
def test_strips_whitespace(self):
|
||||
register_env_passthrough([" SPACED_KEY "])
|
||||
assert is_env_passthrough("SPACED_KEY")
|
||||
|
||||
def test_skips_empty(self):
|
||||
register_env_passthrough(["", " ", "VALID_KEY"])
|
||||
assert is_env_passthrough("VALID_KEY")
|
||||
assert not is_env_passthrough("")
|
||||
|
||||
|
||||
class TestConfigPassthrough:
|
||||
def test_reads_from_config(self, tmp_path, monkeypatch):
|
||||
config = {"terminal": {"env_passthrough": ["MY_CUSTOM_KEY", "ANOTHER_TOKEN"]}}
|
||||
config_path = tmp_path / "config.yaml"
|
||||
config_path.write_text(yaml.dump(config))
|
||||
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
||||
reset_config_cache()
|
||||
|
||||
assert is_env_passthrough("MY_CUSTOM_KEY")
|
||||
assert is_env_passthrough("ANOTHER_TOKEN")
|
||||
assert not is_env_passthrough("UNRELATED_VAR")
|
||||
|
||||
def test_empty_config(self, tmp_path, monkeypatch):
|
||||
config = {"terminal": {"env_passthrough": []}}
|
||||
config_path = tmp_path / "config.yaml"
|
||||
config_path.write_text(yaml.dump(config))
|
||||
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
||||
reset_config_cache()
|
||||
|
||||
assert not is_env_passthrough("ANYTHING")
|
||||
|
||||
def test_missing_config_key(self, tmp_path, monkeypatch):
|
||||
config = {"terminal": {"backend": "local"}}
|
||||
config_path = tmp_path / "config.yaml"
|
||||
config_path.write_text(yaml.dump(config))
|
||||
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
||||
reset_config_cache()
|
||||
|
||||
assert not is_env_passthrough("ANYTHING")
|
||||
|
||||
def test_no_config_file(self, tmp_path, monkeypatch):
|
||||
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
||||
reset_config_cache()
|
||||
|
||||
assert not is_env_passthrough("ANYTHING")
|
||||
|
||||
def test_union_of_skill_and_config(self, tmp_path, monkeypatch):
|
||||
config = {"terminal": {"env_passthrough": ["CONFIG_KEY"]}}
|
||||
config_path = tmp_path / "config.yaml"
|
||||
config_path.write_text(yaml.dump(config))
|
||||
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
||||
reset_config_cache()
|
||||
|
||||
register_env_passthrough(["SKILL_KEY"])
|
||||
all_pt = get_all_passthrough()
|
||||
assert "CONFIG_KEY" in all_pt
|
||||
assert "SKILL_KEY" in all_pt
|
||||
|
||||
|
||||
class TestExecuteCodeIntegration:
|
||||
"""Verify that the passthrough is checked in execute_code's env filtering."""
|
||||
|
||||
def test_secret_substring_blocked_by_default(self):
|
||||
"""TENOR_API_KEY should be blocked without passthrough."""
|
||||
_SAFE_ENV_PREFIXES = ("PATH", "HOME", "USER", "LANG", "LC_", "TERM",
|
||||
"TMPDIR", "TMP", "TEMP", "SHELL", "LOGNAME",
|
||||
"XDG_", "PYTHONPATH", "VIRTUAL_ENV", "CONDA")
|
||||
_SECRET_SUBSTRINGS = ("KEY", "TOKEN", "SECRET", "PASSWORD", "CREDENTIAL",
|
||||
"PASSWD", "AUTH")
|
||||
|
||||
test_env = {"PATH": "/usr/bin", "TENOR_API_KEY": "test123", "HOME": "/home/user"}
|
||||
child_env = {}
|
||||
for k, v in test_env.items():
|
||||
if is_env_passthrough(k):
|
||||
child_env[k] = v
|
||||
continue
|
||||
if any(s in k.upper() for s in _SECRET_SUBSTRINGS):
|
||||
continue
|
||||
if any(k.startswith(p) for p in _SAFE_ENV_PREFIXES):
|
||||
child_env[k] = v
|
||||
|
||||
assert "PATH" in child_env
|
||||
assert "HOME" in child_env
|
||||
assert "TENOR_API_KEY" not in child_env
|
||||
|
||||
def test_passthrough_allows_secret_through(self):
|
||||
"""TENOR_API_KEY should pass through when registered."""
|
||||
_SAFE_ENV_PREFIXES = ("PATH", "HOME", "USER", "LANG", "LC_", "TERM",
|
||||
"TMPDIR", "TMP", "TEMP", "SHELL", "LOGNAME",
|
||||
"XDG_", "PYTHONPATH", "VIRTUAL_ENV", "CONDA")
|
||||
_SECRET_SUBSTRINGS = ("KEY", "TOKEN", "SECRET", "PASSWORD", "CREDENTIAL",
|
||||
"PASSWD", "AUTH")
|
||||
|
||||
register_env_passthrough(["TENOR_API_KEY"])
|
||||
|
||||
test_env = {"PATH": "/usr/bin", "TENOR_API_KEY": "test123", "HOME": "/home/user"}
|
||||
child_env = {}
|
||||
for k, v in test_env.items():
|
||||
if is_env_passthrough(k):
|
||||
child_env[k] = v
|
||||
continue
|
||||
if any(s in k.upper() for s in _SECRET_SUBSTRINGS):
|
||||
continue
|
||||
if any(k.startswith(p) for p in _SAFE_ENV_PREFIXES):
|
||||
child_env[k] = v
|
||||
|
||||
assert "PATH" in child_env
|
||||
assert "HOME" in child_env
|
||||
assert "TENOR_API_KEY" in child_env
|
||||
assert child_env["TENOR_API_KEY"] == "test123"
|
||||
|
||||
|
||||
class TestTerminalIntegration:
|
||||
"""Verify that the passthrough is checked in terminal's env sanitizers."""
|
||||
|
||||
def test_blocklisted_var_blocked_by_default(self):
|
||||
from tools.environments.local import _sanitize_subprocess_env, _HERMES_PROVIDER_ENV_BLOCKLIST
|
||||
|
||||
# Pick a var we know is in the blocklist
|
||||
blocked_var = next(iter(_HERMES_PROVIDER_ENV_BLOCKLIST))
|
||||
env = {blocked_var: "secret_value", "PATH": "/usr/bin"}
|
||||
result = _sanitize_subprocess_env(env)
|
||||
assert blocked_var not in result
|
||||
assert "PATH" in result
|
||||
|
||||
def test_passthrough_allows_blocklisted_var(self):
|
||||
from tools.environments.local import _sanitize_subprocess_env, _HERMES_PROVIDER_ENV_BLOCKLIST
|
||||
|
||||
blocked_var = next(iter(_HERMES_PROVIDER_ENV_BLOCKLIST))
|
||||
register_env_passthrough([blocked_var])
|
||||
|
||||
env = {blocked_var: "secret_value", "PATH": "/usr/bin"}
|
||||
result = _sanitize_subprocess_env(env)
|
||||
assert blocked_var in result
|
||||
assert result[blocked_var] == "secret_value"
|
||||
|
||||
def test_make_run_env_passthrough(self, monkeypatch):
|
||||
from tools.environments.local import _make_run_env, _HERMES_PROVIDER_ENV_BLOCKLIST
|
||||
|
||||
blocked_var = next(iter(_HERMES_PROVIDER_ENV_BLOCKLIST))
|
||||
monkeypatch.setenv(blocked_var, "secret_value")
|
||||
|
||||
# Without passthrough — blocked
|
||||
result_before = _make_run_env({})
|
||||
assert blocked_var not in result_before
|
||||
|
||||
# With passthrough — allowed
|
||||
register_env_passthrough([blocked_var])
|
||||
result_after = _make_run_env({})
|
||||
assert blocked_var in result_after
|
||||
@@ -309,6 +309,3 @@ class TestSearchHints:
|
||||
raw = search_tool(pattern="foo", offset=50, limit=50)
|
||||
assert "[Hint:" in raw
|
||||
assert "offset=100" in raw
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -288,34 +288,3 @@ class TestBlocklistCoverage:
|
||||
"DAYTONA_API_KEY",
|
||||
}
|
||||
assert extras.issubset(_HERMES_PROVIDER_ENV_BLOCKLIST)
|
||||
|
||||
|
||||
class TestSanePathIncludesHomebrew:
|
||||
"""Verify _SANE_PATH includes macOS Homebrew directories."""
|
||||
|
||||
def test_sane_path_includes_homebrew_bin(self):
|
||||
from tools.environments.local import _SANE_PATH
|
||||
assert "/opt/homebrew/bin" in _SANE_PATH
|
||||
|
||||
def test_sane_path_includes_homebrew_sbin(self):
|
||||
from tools.environments.local import _SANE_PATH
|
||||
assert "/opt/homebrew/sbin" in _SANE_PATH
|
||||
|
||||
def test_make_run_env_appends_homebrew_on_minimal_path(self):
|
||||
"""When PATH is minimal (no /usr/bin), _make_run_env should append
|
||||
_SANE_PATH which now includes Homebrew dirs."""
|
||||
from tools.environments.local import _make_run_env
|
||||
minimal_env = {"PATH": "/some/custom/bin"}
|
||||
with patch.dict(os.environ, minimal_env, clear=True):
|
||||
result = _make_run_env({})
|
||||
assert "/opt/homebrew/bin" in result["PATH"]
|
||||
assert "/opt/homebrew/sbin" in result["PATH"]
|
||||
|
||||
def test_make_run_env_does_not_duplicate_on_full_path(self):
|
||||
"""When PATH already has /usr/bin, _make_run_env should not append."""
|
||||
from tools.environments.local import _make_run_env
|
||||
full_env = {"PATH": "/usr/bin:/bin"}
|
||||
with patch.dict(os.environ, full_env, clear=True):
|
||||
result = _make_run_env({})
|
||||
# Should keep existing PATH unchanged
|
||||
assert result["PATH"] == "/usr/bin:/bin"
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
"""Tests for Modal sandbox infrastructure fixes (TBLite baseline).
|
||||
|
||||
Covers the bugs discovered while setting up TBLite evaluation:
|
||||
1. Tool resolution — terminal + file tools load correctly
|
||||
Covers the 9 bugs discovered while setting up TBLite evaluation:
|
||||
1. Tool resolution — terminal + file tools load with minisweagent
|
||||
2. CWD fix — host paths get replaced with /root for container backends
|
||||
3. ephemeral_disk version check
|
||||
4. Tilde ~ replaced with /root for container backends
|
||||
5. ensurepip fix in Modal image builder
|
||||
5. ensurepip fix in patches.py for Modal image builder
|
||||
6. install_pipx stays True for swerex-remote
|
||||
7. /home/ added to host prefix check
|
||||
"""
|
||||
@@ -36,8 +36,17 @@ except ImportError:
|
||||
class TestToolResolution:
|
||||
"""Verify get_tool_definitions returns all expected tools for eval."""
|
||||
|
||||
def _has_minisweagent(self):
|
||||
try:
|
||||
import minisweagent # noqa: F401
|
||||
return True
|
||||
except ImportError:
|
||||
return False
|
||||
|
||||
def test_terminal_and_file_toolsets_resolve_all_tools(self):
|
||||
"""enabled_toolsets=['terminal', 'file'] should produce 6 tools."""
|
||||
if not self._has_minisweagent():
|
||||
pytest.skip("minisweagent not installed (git submodule update --init)")
|
||||
from model_tools import get_tool_definitions
|
||||
tools = get_tool_definitions(
|
||||
enabled_toolsets=["terminal", "file"],
|
||||
@@ -49,13 +58,18 @@ class TestToolResolution:
|
||||
|
||||
def test_terminal_tool_present(self):
|
||||
"""The terminal tool must be present (not silently dropped)."""
|
||||
if not self._has_minisweagent():
|
||||
pytest.skip("minisweagent not installed (git submodule update --init)")
|
||||
from model_tools import get_tool_definitions
|
||||
tools = get_tool_definitions(
|
||||
enabled_toolsets=["terminal", "file"],
|
||||
quiet_mode=True,
|
||||
)
|
||||
names = [t["function"]["name"] for t in tools]
|
||||
assert "terminal" in names, f"terminal tool missing! Only got: {names}."
|
||||
assert "terminal" in names, (
|
||||
f"terminal tool missing! Only got: {names}. "
|
||||
"Check that minisweagent is installed (git submodule update --init)."
|
||||
)
|
||||
|
||||
|
||||
# =========================================================================
|
||||
@@ -255,37 +269,38 @@ class TestModalEnvironmentDefaults:
|
||||
# =========================================================================
|
||||
|
||||
class TestEnsurepipFix:
|
||||
"""Verify the pip fix is applied in the ModalEnvironment init."""
|
||||
"""Verify the pip fix is applied in the patched Modal init."""
|
||||
|
||||
def test_modal_environment_creates_image_with_setup_commands(self):
|
||||
"""ModalEnvironment.__init__ should create a modal.Image with pip fix."""
|
||||
def test_patched_init_creates_image_with_setup_commands(self):
|
||||
"""The patched __init__ should create a modal.Image with pip fix."""
|
||||
try:
|
||||
from tools.environments.modal import ModalEnvironment
|
||||
from environments.patches import _patch_swerex_modal
|
||||
except ImportError:
|
||||
pytest.skip("tools.environments.modal not importable")
|
||||
pytest.skip("environments.patches not importable")
|
||||
|
||||
# Check that the patch code references ensurepip
|
||||
import inspect
|
||||
source = inspect.getsource(ModalEnvironment.__init__)
|
||||
source = inspect.getsource(_patch_swerex_modal)
|
||||
assert "ensurepip" in source, (
|
||||
"ModalEnvironment should include ensurepip fix "
|
||||
"patches._patch_swerex_modal should include ensurepip fix "
|
||||
"for Modal's legacy image builder"
|
||||
)
|
||||
assert "setup_dockerfile_commands" in source, (
|
||||
"ModalEnvironment should use setup_dockerfile_commands "
|
||||
"patches._patch_swerex_modal should use setup_dockerfile_commands "
|
||||
"to fix pip before Modal's bootstrap"
|
||||
)
|
||||
|
||||
def test_modal_environment_uses_install_pipx(self):
|
||||
"""ModalEnvironment should pass install_pipx to ModalDeployment."""
|
||||
def test_patched_init_uses_install_pipx_from_config(self):
|
||||
"""The patched init should respect install_pipx from config."""
|
||||
try:
|
||||
from tools.environments.modal import ModalEnvironment
|
||||
from environments.patches import _patch_swerex_modal
|
||||
except ImportError:
|
||||
pytest.skip("tools.environments.modal not importable")
|
||||
pytest.skip("environments.patches not importable")
|
||||
|
||||
import inspect
|
||||
source = inspect.getsource(ModalEnvironment.__init__)
|
||||
source = inspect.getsource(_patch_swerex_modal)
|
||||
assert "install_pipx" in source, (
|
||||
"ModalEnvironment should pass install_pipx to ModalDeployment"
|
||||
"patches._patch_swerex_modal should pass install_pipx to ModalDeployment"
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -1,105 +0,0 @@
|
||||
"""Test that skill_view registers required env vars in the passthrough registry."""
|
||||
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
|
||||
from tools.env_passthrough import clear_env_passthrough, is_env_passthrough, reset_config_cache
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _clean_passthrough():
|
||||
clear_env_passthrough()
|
||||
reset_config_cache()
|
||||
yield
|
||||
clear_env_passthrough()
|
||||
reset_config_cache()
|
||||
|
||||
|
||||
def _create_skill(tmp_path, name, frontmatter_extra=""):
|
||||
"""Create a minimal skill directory with SKILL.md."""
|
||||
skill_dir = tmp_path / name
|
||||
skill_dir.mkdir(parents=True, exist_ok=True)
|
||||
(skill_dir / "SKILL.md").write_text(
|
||||
f"---\n"
|
||||
f"name: {name}\n"
|
||||
f"description: Test skill\n"
|
||||
f"{frontmatter_extra}"
|
||||
f"---\n\n"
|
||||
f"# {name}\n\n"
|
||||
f"Test content.\n"
|
||||
)
|
||||
return skill_dir
|
||||
|
||||
|
||||
class TestSkillViewRegistersPassthrough:
|
||||
def test_available_env_vars_registered(self, tmp_path, monkeypatch):
|
||||
"""When a skill declares required_environment_variables and the var IS set,
|
||||
it should be registered in the passthrough."""
|
||||
_create_skill(
|
||||
tmp_path,
|
||||
"test-skill",
|
||||
frontmatter_extra=(
|
||||
"required_environment_variables:\n"
|
||||
" - name: TENOR_API_KEY\n"
|
||||
" prompt: Enter your Tenor API key\n"
|
||||
),
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
"tools.skills_tool.SKILLS_DIR", tmp_path
|
||||
)
|
||||
# Set the env var so it's "available"
|
||||
monkeypatch.setenv("TENOR_API_KEY", "test-value-123")
|
||||
|
||||
# Patch the secret capture callback to not prompt
|
||||
with patch("tools.skills_tool._secret_capture_callback", None):
|
||||
from tools.skills_tool import skill_view
|
||||
|
||||
result = json.loads(skill_view(name="test-skill"))
|
||||
|
||||
assert result["success"] is True
|
||||
assert is_env_passthrough("TENOR_API_KEY")
|
||||
|
||||
def test_missing_env_vars_not_registered(self, tmp_path, monkeypatch):
|
||||
"""When a skill declares required_environment_variables but the var is NOT set,
|
||||
it should NOT be registered in the passthrough."""
|
||||
_create_skill(
|
||||
tmp_path,
|
||||
"test-skill",
|
||||
frontmatter_extra=(
|
||||
"required_environment_variables:\n"
|
||||
" - name: NONEXISTENT_SKILL_KEY_XYZ\n"
|
||||
" prompt: Enter your key\n"
|
||||
),
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
"tools.skills_tool.SKILLS_DIR", tmp_path
|
||||
)
|
||||
monkeypatch.delenv("NONEXISTENT_SKILL_KEY_XYZ", raising=False)
|
||||
|
||||
with patch("tools.skills_tool._secret_capture_callback", None):
|
||||
from tools.skills_tool import skill_view
|
||||
|
||||
result = json.loads(skill_view(name="test-skill"))
|
||||
|
||||
assert result["success"] is True
|
||||
assert not is_env_passthrough("NONEXISTENT_SKILL_KEY_XYZ")
|
||||
|
||||
def test_no_env_vars_skill_no_registration(self, tmp_path, monkeypatch):
|
||||
"""Skills without required_environment_variables shouldn't register anything."""
|
||||
_create_skill(tmp_path, "simple-skill")
|
||||
monkeypatch.setattr(
|
||||
"tools.skills_tool.SKILLS_DIR", tmp_path
|
||||
)
|
||||
|
||||
with patch("tools.skills_tool._secret_capture_callback", None):
|
||||
from tools.skills_tool import skill_view
|
||||
|
||||
result = json.loads(skill_view(name="simple-skill"))
|
||||
|
||||
assert result["success"] is True
|
||||
from tools.env_passthrough import get_all_passthrough
|
||||
assert len(get_all_passthrough()) == 0
|
||||
@@ -18,8 +18,9 @@ def _clear_terminal_env(monkeypatch):
|
||||
monkeypatch.delenv(key, raising=False)
|
||||
|
||||
|
||||
def test_local_terminal_requirements(monkeypatch, caplog):
|
||||
"""Local backend uses Hermes' own LocalEnvironment wrapper."""
|
||||
def test_local_terminal_requirements_do_not_depend_on_minisweagent(monkeypatch, caplog):
|
||||
"""Local backend uses Hermes' own LocalEnvironment wrapper and should not
|
||||
be marked unavailable just because `minisweagent` isn't importable."""
|
||||
_clear_terminal_env(monkeypatch)
|
||||
monkeypatch.setenv("TERMINAL_ENV", "local")
|
||||
|
||||
@@ -63,7 +64,7 @@ def test_modal_backend_without_token_or_config_logs_specific_error(monkeypatch,
|
||||
monkeypatch.setenv("TERMINAL_ENV", "modal")
|
||||
monkeypatch.setenv("HOME", str(tmp_path))
|
||||
monkeypatch.setenv("USERPROFILE", str(tmp_path))
|
||||
# Pretend swerex is installed
|
||||
monkeypatch.setattr(terminal_tool_module, "ensure_minisweagent_on_path", lambda *_args, **_kwargs: None)
|
||||
monkeypatch.setattr(terminal_tool_module.importlib.util, "find_spec", lambda _name: object())
|
||||
|
||||
with caplog.at_level(logging.ERROR):
|
||||
|
||||
@@ -8,7 +8,7 @@ terminal_tool_module = importlib.import_module("tools.terminal_tool")
|
||||
|
||||
|
||||
class TestTerminalRequirements:
|
||||
def test_local_backend_requirements(self, monkeypatch):
|
||||
def test_local_backend_does_not_require_minisweagent_package(self, monkeypatch):
|
||||
monkeypatch.setattr(
|
||||
terminal_tool_module,
|
||||
"_get_env_config",
|
||||
|
||||
@@ -1,176 +0,0 @@
|
||||
"""Tests for SSRF protection in url_safety module."""
|
||||
|
||||
import socket
|
||||
from unittest.mock import patch
|
||||
|
||||
from tools.url_safety import is_safe_url, _is_blocked_ip
|
||||
|
||||
import ipaddress
|
||||
import pytest
|
||||
|
||||
|
||||
class TestIsSafeUrl:
|
||||
def test_public_url_allowed(self):
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("93.184.216.34", 0)),
|
||||
]):
|
||||
assert is_safe_url("https://example.com/image.png") is True
|
||||
|
||||
def test_localhost_blocked(self):
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("127.0.0.1", 0)),
|
||||
]):
|
||||
assert is_safe_url("http://localhost:8080/secret") is False
|
||||
|
||||
def test_loopback_ip_blocked(self):
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("127.0.0.1", 0)),
|
||||
]):
|
||||
assert is_safe_url("http://127.0.0.1/admin") is False
|
||||
|
||||
def test_private_10_blocked(self):
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("10.0.0.1", 0)),
|
||||
]):
|
||||
assert is_safe_url("http://internal-service.local/api") is False
|
||||
|
||||
def test_private_172_blocked(self):
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("172.16.0.1", 0)),
|
||||
]):
|
||||
assert is_safe_url("http://private.corp/data") is False
|
||||
|
||||
def test_private_192_blocked(self):
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("192.168.1.1", 0)),
|
||||
]):
|
||||
assert is_safe_url("http://router.local") is False
|
||||
|
||||
def test_link_local_169_254_blocked(self):
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("169.254.169.254", 0)),
|
||||
]):
|
||||
assert is_safe_url("http://169.254.169.254/latest/meta-data/") is False
|
||||
|
||||
def test_metadata_google_internal_blocked(self):
|
||||
assert is_safe_url("http://metadata.google.internal/computeMetadata/v1/") is False
|
||||
|
||||
def test_ipv6_loopback_blocked(self):
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(10, 1, 6, "", ("::1", 0, 0, 0)),
|
||||
]):
|
||||
assert is_safe_url("http://[::1]:8080/") is False
|
||||
|
||||
def test_dns_failure_blocked(self):
|
||||
"""DNS failures now fail closed — block the request."""
|
||||
with patch("socket.getaddrinfo", side_effect=socket.gaierror("Name resolution failed")):
|
||||
assert is_safe_url("https://nonexistent.example.com") is False
|
||||
|
||||
def test_empty_url_blocked(self):
|
||||
assert is_safe_url("") is False
|
||||
|
||||
def test_no_hostname_blocked(self):
|
||||
assert is_safe_url("http://") is False
|
||||
|
||||
def test_public_ip_allowed(self):
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("93.184.216.34", 0)),
|
||||
]):
|
||||
assert is_safe_url("https://example.com") is True
|
||||
|
||||
# ── New tests for hardened SSRF protection ──
|
||||
|
||||
def test_cgnat_100_64_blocked(self):
|
||||
"""100.64.0.0/10 (CGNAT/Shared Address Space) is NOT covered by
|
||||
ipaddress.is_private — must be blocked explicitly."""
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("100.64.0.1", 0)),
|
||||
]):
|
||||
assert is_safe_url("http://some-cgnat-host.example/") is False
|
||||
|
||||
def test_cgnat_100_127_blocked(self):
|
||||
"""Upper end of CGNAT range (100.127.255.255)."""
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("100.127.255.254", 0)),
|
||||
]):
|
||||
assert is_safe_url("http://tailscale-peer.example/") is False
|
||||
|
||||
def test_multicast_blocked(self):
|
||||
"""Multicast addresses (224.0.0.0/4) not caught by is_private."""
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("224.0.0.251", 0)),
|
||||
]):
|
||||
assert is_safe_url("http://mdns-host.local/") is False
|
||||
|
||||
def test_multicast_ipv6_blocked(self):
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(10, 1, 6, "", ("ff02::1", 0, 0, 0)),
|
||||
]):
|
||||
assert is_safe_url("http://[ff02::1]/") is False
|
||||
|
||||
def test_ipv4_mapped_ipv6_loopback_blocked(self):
|
||||
"""::ffff:127.0.0.1 — IPv4-mapped IPv6 loopback."""
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(10, 1, 6, "", ("::ffff:127.0.0.1", 0, 0, 0)),
|
||||
]):
|
||||
assert is_safe_url("http://[::ffff:127.0.0.1]/") is False
|
||||
|
||||
def test_ipv4_mapped_ipv6_metadata_blocked(self):
|
||||
"""::ffff:169.254.169.254 — IPv4-mapped IPv6 cloud metadata."""
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(10, 1, 6, "", ("::ffff:169.254.169.254", 0, 0, 0)),
|
||||
]):
|
||||
assert is_safe_url("http://[::ffff:169.254.169.254]/") is False
|
||||
|
||||
def test_unspecified_address_blocked(self):
|
||||
"""0.0.0.0 — unspecified address, can bind to all interfaces."""
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("0.0.0.0", 0)),
|
||||
]):
|
||||
assert is_safe_url("http://0.0.0.0/") is False
|
||||
|
||||
def test_unexpected_error_fails_closed(self):
|
||||
"""Unexpected exceptions should block, not allow."""
|
||||
with patch("tools.url_safety.urlparse", side_effect=ValueError("bad url")):
|
||||
assert is_safe_url("http://evil.com/") is False
|
||||
|
||||
def test_metadata_goog_blocked(self):
|
||||
assert is_safe_url("http://metadata.goog/computeMetadata/v1/") is False
|
||||
|
||||
def test_ipv6_unique_local_blocked(self):
|
||||
"""fc00::/7 — IPv6 unique local addresses."""
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(10, 1, 6, "", ("fd12::1", 0, 0, 0)),
|
||||
]):
|
||||
assert is_safe_url("http://[fd12::1]/internal") is False
|
||||
|
||||
def test_non_cgnat_100_allowed(self):
|
||||
"""100.0.0.1 is NOT in CGNAT range (100.64.0.0/10), should be allowed."""
|
||||
with patch("socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("100.0.0.1", 0)),
|
||||
]):
|
||||
# 100.0.0.1 is a global IP, not in CGNAT range
|
||||
assert is_safe_url("http://legit-host.example/") is True
|
||||
|
||||
|
||||
class TestIsBlockedIp:
|
||||
"""Direct tests for the _is_blocked_ip helper."""
|
||||
|
||||
@pytest.mark.parametrize("ip_str", [
|
||||
"127.0.0.1", "10.0.0.1", "172.16.0.1", "192.168.1.1",
|
||||
"169.254.169.254", "0.0.0.0", "224.0.0.1", "255.255.255.255",
|
||||
"100.64.0.1", "100.100.100.100", "100.127.255.254",
|
||||
"::1", "fe80::1", "fc00::1", "fd12::1", "ff02::1",
|
||||
"::ffff:127.0.0.1", "::ffff:169.254.169.254",
|
||||
])
|
||||
def test_blocked_ips(self, ip_str):
|
||||
ip = ipaddress.ip_address(ip_str)
|
||||
assert _is_blocked_ip(ip) is True, f"{ip_str} should be blocked"
|
||||
|
||||
@pytest.mark.parametrize("ip_str", [
|
||||
"8.8.8.8", "93.184.216.34", "1.1.1.1", "100.0.0.1",
|
||||
"2606:4700::1", "2001:4860:4860::8888",
|
||||
])
|
||||
def test_allowed_ips(self, ip_str):
|
||||
ip = ipaddress.ip_address(ip_str)
|
||||
assert _is_blocked_ip(ip) is False, f"{ip_str} should be allowed"
|
||||
@@ -33,30 +33,17 @@ class TestValidateImageUrl:
|
||||
assert _validate_image_url("https://example.com/image.jpg") is True
|
||||
|
||||
def test_valid_http_url(self):
|
||||
with patch("tools.url_safety.socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("93.184.216.34", 0)),
|
||||
]):
|
||||
assert _validate_image_url("http://cdn.example.org/photo.png") is True
|
||||
assert _validate_image_url("http://cdn.example.org/photo.png") is True
|
||||
|
||||
def test_valid_url_without_extension(self):
|
||||
"""CDN endpoints that redirect to images should still pass."""
|
||||
with patch("tools.url_safety.socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("93.184.216.34", 0)),
|
||||
]):
|
||||
assert _validate_image_url("https://cdn.example.com/abcdef123") is True
|
||||
assert _validate_image_url("https://cdn.example.com/abcdef123") is True
|
||||
|
||||
def test_valid_url_with_query_params(self):
|
||||
with patch("tools.url_safety.socket.getaddrinfo", return_value=[
|
||||
(2, 1, 6, "", ("93.184.216.34", 0)),
|
||||
]):
|
||||
assert _validate_image_url("https://img.example.com/pic?w=200&h=200") is True
|
||||
|
||||
def test_localhost_url_blocked_by_ssrf(self):
|
||||
"""localhost URLs are now blocked by SSRF protection."""
|
||||
assert _validate_image_url("http://localhost:8080/image.png") is False
|
||||
assert _validate_image_url("https://img.example.com/pic?w=200&h=200") is True
|
||||
|
||||
def test_valid_url_with_port(self):
|
||||
assert _validate_image_url("http://example.com:8080/image.png") is True
|
||||
assert _validate_image_url("http://localhost:8080/image.png") is True
|
||||
|
||||
def test_valid_url_with_path_only(self):
|
||||
assert _validate_image_url("https://example.com/") is True
|
||||
|
||||
@@ -343,8 +343,6 @@ def test_browser_navigate_allows_when_shared_file_missing(monkeypatch, tmp_path)
|
||||
async def test_web_extract_short_circuits_blocked_url(monkeypatch):
|
||||
from tools import web_tools
|
||||
|
||||
# Allow test URLs past SSRF check so website policy is what gets tested
|
||||
monkeypatch.setattr(web_tools, "is_safe_url", lambda url: True)
|
||||
monkeypatch.setattr(
|
||||
web_tools,
|
||||
"check_website_access",
|
||||
@@ -391,9 +389,6 @@ def test_check_website_access_fails_open_on_malformed_config(tmp_path, monkeypat
|
||||
async def test_web_extract_blocks_redirected_final_url(monkeypatch):
|
||||
from tools import web_tools
|
||||
|
||||
# Allow test URLs past SSRF check so website policy is what gets tested
|
||||
monkeypatch.setattr(web_tools, "is_safe_url", lambda url: True)
|
||||
|
||||
def fake_check(url):
|
||||
if url == "https://allowed.test":
|
||||
return None
|
||||
@@ -433,8 +428,6 @@ async def test_web_crawl_short_circuits_blocked_url(monkeypatch):
|
||||
|
||||
# web_crawl_tool checks for Firecrawl env before website policy
|
||||
monkeypatch.setenv("FIRECRAWL_API_KEY", "fake-key")
|
||||
# Allow test URLs past SSRF check so website policy is what gets tested
|
||||
monkeypatch.setattr(web_tools, "is_safe_url", lambda url: True)
|
||||
monkeypatch.setattr(
|
||||
web_tools,
|
||||
"check_website_access",
|
||||
@@ -464,8 +457,6 @@ async def test_web_crawl_blocks_redirected_final_url(monkeypatch):
|
||||
|
||||
# web_crawl_tool checks for Firecrawl env before website policy
|
||||
monkeypatch.setenv("FIRECRAWL_API_KEY", "fake-key")
|
||||
# Allow test URLs past SSRF check so website policy is what gets tested
|
||||
monkeypatch.setattr(web_tools, "is_safe_url", lambda url: True)
|
||||
|
||||
def fake_check(url):
|
||||
if url == "https://allowed.test":
|
||||
|
||||
+3
-3
@@ -6,7 +6,7 @@ This package contains all the specific tool implementations for the Hermes Agent
|
||||
Each module provides specialized functionality for different capabilities:
|
||||
|
||||
- web_tools: Web search, content extraction, and crawling
|
||||
- terminal_tool: Command execution (local/docker/modal/daytona/ssh/singularity backends)
|
||||
- terminal_tool: Command execution using mini-swe-agent (local/docker/modal/daytona backends)
|
||||
- vision_tools: Image analysis and understanding
|
||||
- mixture_of_agents_tool: Multi-model collaborative reasoning
|
||||
- image_generation_tool: Text-to-image generation with upscaling
|
||||
@@ -23,7 +23,7 @@ from .web_tools import (
|
||||
check_firecrawl_api_key
|
||||
)
|
||||
|
||||
# Primary terminal tool (local/docker/singularity/modal/daytona/ssh)
|
||||
# Primary terminal tool (mini-swe-agent backend: local/docker/singularity/modal/daytona)
|
||||
from .terminal_tool import (
|
||||
terminal_tool,
|
||||
check_terminal_requirements,
|
||||
@@ -166,7 +166,7 @@ __all__ = [
|
||||
'web_extract_tool',
|
||||
'web_crawl_tool',
|
||||
'check_firecrawl_api_key',
|
||||
# Terminal tools
|
||||
# Terminal tools (mini-swe-agent backend)
|
||||
'terminal_tool',
|
||||
'check_terminal_requirements',
|
||||
'cleanup_vm',
|
||||
|
||||
@@ -1,44 +0,0 @@
|
||||
"""Strip ANSI escape sequences from subprocess output.
|
||||
|
||||
Used by terminal_tool, code_execution_tool, and process_registry to clean
|
||||
command output before returning it to the model. This prevents ANSI codes
|
||||
from entering the model's context — which is the root cause of models
|
||||
copying escape sequences into file writes.
|
||||
|
||||
Covers the full ECMA-48 spec: CSI (including private-mode ``?`` prefix,
|
||||
colon-separated params, intermediate bytes), OSC (BEL and ST terminators),
|
||||
DCS/SOS/PM/APC string sequences, nF multi-byte escapes, Fp/Fe/Fs
|
||||
single-byte escapes, and 8-bit C1 control characters.
|
||||
"""
|
||||
|
||||
import re
|
||||
|
||||
_ANSI_ESCAPE_RE = re.compile(
|
||||
r"\x1b"
|
||||
r"(?:"
|
||||
r"\[[\x30-\x3f]*[\x20-\x2f]*[\x40-\x7e]" # CSI sequence
|
||||
r"|\][\s\S]*?(?:\x07|\x1b\\)" # OSC (BEL or ST terminator)
|
||||
r"|[PX^_][\s\S]*?(?:\x1b\\)" # DCS/SOS/PM/APC strings
|
||||
r"|[\x20-\x2f]+[\x30-\x7e]" # nF escape sequences
|
||||
r"|[\x30-\x7e]" # Fp/Fe/Fs single-byte
|
||||
r")"
|
||||
r"|\x9b[\x30-\x3f]*[\x20-\x2f]*[\x40-\x7e]" # 8-bit CSI
|
||||
r"|\x9d[\s\S]*?(?:\x07|\x9c)" # 8-bit OSC
|
||||
r"|[\x80-\x9f]", # Other 8-bit C1 controls
|
||||
re.DOTALL,
|
||||
)
|
||||
|
||||
# Fast-path check — skip full regex when no escape-like bytes are present.
|
||||
_HAS_ESCAPE = re.compile(r"[\x1b\x80-\x9f]")
|
||||
|
||||
|
||||
def strip_ansi(text: str) -> str:
|
||||
"""Remove ANSI escape sequences from text.
|
||||
|
||||
Returns the input unchanged (fast path) when no ESC or C1 bytes are
|
||||
present. Safe to call on any string — clean text passes through
|
||||
with negligible overhead.
|
||||
"""
|
||||
if not text or not _HAS_ESCAPE.search(text):
|
||||
return text
|
||||
return _ANSI_ESCAPE_RE.sub("", text)
|
||||
+11
-103
@@ -76,35 +76,8 @@ from tools.browser_providers.browser_use import BrowserUseProvider
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Standard PATH entries for environments with minimal PATH (e.g. systemd services).
|
||||
# Includes macOS Homebrew paths (/opt/homebrew/* for Apple Silicon).
|
||||
_SANE_PATH = (
|
||||
"/opt/homebrew/bin:/opt/homebrew/sbin:"
|
||||
"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
|
||||
)
|
||||
|
||||
|
||||
def _discover_homebrew_node_dirs() -> list[str]:
|
||||
"""Find Homebrew versioned Node.js bin directories (e.g. node@20, node@24).
|
||||
|
||||
When Node is installed via ``brew install node@24`` and NOT linked into
|
||||
/opt/homebrew/bin, the binary lives only in /opt/homebrew/opt/node@24/bin/.
|
||||
This function discovers those paths so they can be added to subprocess PATH.
|
||||
"""
|
||||
dirs: list[str] = []
|
||||
homebrew_opt = "/opt/homebrew/opt"
|
||||
if not os.path.isdir(homebrew_opt):
|
||||
return dirs
|
||||
try:
|
||||
for entry in os.listdir(homebrew_opt):
|
||||
if entry.startswith("node") and entry != "node":
|
||||
# e.g. node@20, node@24
|
||||
bin_dir = os.path.join(homebrew_opt, entry, "bin")
|
||||
if os.path.isdir(bin_dir):
|
||||
dirs.append(bin_dir)
|
||||
except OSError:
|
||||
pass
|
||||
return dirs
|
||||
# Standard PATH entries for environments with minimal PATH (e.g. systemd services)
|
||||
_SANE_PATH = "/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
|
||||
|
||||
# Throttle screenshot cleanup to avoid repeated full directory scans.
|
||||
_last_screenshot_cleanup_by_dir: dict[str, float] = {}
|
||||
@@ -123,27 +96,6 @@ DEFAULT_SESSION_TIMEOUT = 300
|
||||
SNAPSHOT_SUMMARIZE_THRESHOLD = 8000
|
||||
|
||||
|
||||
def _get_command_timeout() -> int:
|
||||
"""Return the configured browser command timeout from config.yaml.
|
||||
|
||||
Reads ``config["browser"]["command_timeout"]`` and falls back to
|
||||
``DEFAULT_COMMAND_TIMEOUT`` (30s) if unset or unreadable.
|
||||
"""
|
||||
try:
|
||||
hermes_home = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes"))
|
||||
config_path = hermes_home / "config.yaml"
|
||||
if config_path.exists():
|
||||
import yaml
|
||||
with open(config_path) as f:
|
||||
cfg = yaml.safe_load(f) or {}
|
||||
val = cfg.get("browser", {}).get("command_timeout")
|
||||
if val is not None:
|
||||
return max(int(val), 5) # Floor at 5s to avoid instant kills
|
||||
except Exception as e:
|
||||
logger.debug("Could not read command_timeout from config: %s", e)
|
||||
return DEFAULT_COMMAND_TIMEOUT
|
||||
|
||||
|
||||
def _get_vision_model() -> Optional[str]:
|
||||
"""Model for browser_vision (screenshot analysis — multimodal)."""
|
||||
return os.getenv("AUXILIARY_VISION_MODEL", "").strip() or None
|
||||
@@ -667,8 +619,7 @@ def _find_agent_browser() -> str:
|
||||
"""
|
||||
Find the agent-browser CLI executable.
|
||||
|
||||
Checks in order: current PATH, Homebrew/common bin dirs, Hermes-managed
|
||||
node, local node_modules/.bin/, npx fallback.
|
||||
Checks in order: PATH, local node_modules/.bin/, npx fallback.
|
||||
|
||||
Returns:
|
||||
Path to agent-browser executable
|
||||
@@ -681,36 +632,15 @@ def _find_agent_browser() -> str:
|
||||
which_result = shutil.which("agent-browser")
|
||||
if which_result:
|
||||
return which_result
|
||||
|
||||
# Build an extended search PATH including Homebrew and Hermes-managed dirs.
|
||||
# This covers macOS where the process PATH may not include Homebrew paths.
|
||||
extra_dirs: list[str] = []
|
||||
for d in ["/opt/homebrew/bin", "/usr/local/bin"]:
|
||||
if os.path.isdir(d):
|
||||
extra_dirs.append(d)
|
||||
extra_dirs.extend(_discover_homebrew_node_dirs())
|
||||
|
||||
hermes_home = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes"))
|
||||
hermes_node_bin = str(hermes_home / "node" / "bin")
|
||||
if os.path.isdir(hermes_node_bin):
|
||||
extra_dirs.append(hermes_node_bin)
|
||||
|
||||
if extra_dirs:
|
||||
extended_path = os.pathsep.join(extra_dirs)
|
||||
which_result = shutil.which("agent-browser", path=extended_path)
|
||||
if which_result:
|
||||
return which_result
|
||||
|
||||
|
||||
# Check local node_modules/.bin/ (npm install in repo root)
|
||||
repo_root = Path(__file__).parent.parent
|
||||
local_bin = repo_root / "node_modules" / ".bin" / "agent-browser"
|
||||
if local_bin.exists():
|
||||
return str(local_bin)
|
||||
|
||||
# Check common npx locations (also search extended dirs)
|
||||
# Check common npx locations
|
||||
npx_path = shutil.which("npx")
|
||||
if not npx_path and extra_dirs:
|
||||
npx_path = shutil.which("npx", path=os.pathsep.join(extra_dirs))
|
||||
if npx_path:
|
||||
return "npx agent-browser"
|
||||
|
||||
@@ -746,7 +676,7 @@ def _run_browser_command(
|
||||
task_id: str,
|
||||
command: str,
|
||||
args: List[str] = None,
|
||||
timeout: Optional[int] = None,
|
||||
timeout: int = DEFAULT_COMMAND_TIMEOUT
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Run an agent-browser CLI command using our pre-created Browserbase session.
|
||||
@@ -755,14 +685,11 @@ def _run_browser_command(
|
||||
task_id: Task identifier to get the right session
|
||||
command: The command to run (e.g., "open", "click")
|
||||
args: Additional arguments for the command
|
||||
timeout: Command timeout in seconds. ``None`` reads
|
||||
``browser.command_timeout`` from config (default 30s).
|
||||
timeout: Command timeout in seconds
|
||||
|
||||
Returns:
|
||||
Parsed JSON response from agent-browser
|
||||
"""
|
||||
if timeout is None:
|
||||
timeout = _get_command_timeout()
|
||||
args = args or []
|
||||
|
||||
# Build the command
|
||||
@@ -815,18 +742,13 @@ def _run_browser_command(
|
||||
|
||||
browser_env = {**os.environ}
|
||||
|
||||
# Ensure PATH includes Hermes-managed Node first, Homebrew versioned
|
||||
# node dirs (for macOS ``brew install node@24``), then standard system dirs.
|
||||
# Ensure PATH includes Hermes-managed Node first, then standard system dirs.
|
||||
hermes_home = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes"))
|
||||
hermes_node_bin = str(hermes_home / "node" / "bin")
|
||||
|
||||
existing_path = browser_env.get("PATH", "")
|
||||
path_parts = [p for p in existing_path.split(":") if p]
|
||||
candidate_dirs = (
|
||||
[hermes_node_bin]
|
||||
+ _discover_homebrew_node_dirs()
|
||||
+ [p for p in _SANE_PATH.split(":") if p]
|
||||
)
|
||||
candidate_dirs = [hermes_node_bin] + [p for p in _SANE_PATH.split(":") if p]
|
||||
|
||||
for part in reversed(candidate_dirs):
|
||||
if os.path.isdir(part) and part not in path_parts:
|
||||
@@ -1046,7 +968,7 @@ def browser_navigate(url: str, task_id: Optional[str] = None) -> str:
|
||||
session_info["_first_nav"] = False
|
||||
_maybe_start_recording(effective_task_id)
|
||||
|
||||
result = _run_browser_command(effective_task_id, "open", [url], timeout=max(_get_command_timeout(), 60))
|
||||
result = _run_browser_command(effective_task_id, "open", [url], timeout=60)
|
||||
|
||||
if result.get("success"):
|
||||
data = result.get("data", {})
|
||||
@@ -1520,6 +1442,7 @@ def browser_vision(question: str, annotate: bool = False, task_id: Optional[str]
|
||||
effective_task_id,
|
||||
"screenshot",
|
||||
screenshot_args,
|
||||
timeout=30
|
||||
)
|
||||
|
||||
if not result.get("success"):
|
||||
@@ -1567,20 +1490,6 @@ def browser_vision(question: str, annotate: bool = False, task_id: Optional[str]
|
||||
vision_model = _get_vision_model()
|
||||
logger.debug("browser_vision: analysing screenshot (%d bytes)",
|
||||
len(image_data))
|
||||
|
||||
# Read vision timeout from config (auxiliary.vision.timeout), default 120s.
|
||||
# Local vision models (llama.cpp, ollama) can take well over 30s for
|
||||
# screenshot analysis, so the default must be generous.
|
||||
vision_timeout = 120.0
|
||||
try:
|
||||
from hermes_cli.config import load_config
|
||||
_cfg = load_config()
|
||||
_vt = _cfg.get("auxiliary", {}).get("vision", {}).get("timeout")
|
||||
if _vt is not None:
|
||||
vision_timeout = float(_vt)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
call_kwargs = {
|
||||
"task": "vision",
|
||||
"messages": [
|
||||
@@ -1594,7 +1503,6 @@ def browser_vision(question: str, annotate: bool = False, task_id: Optional[str]
|
||||
],
|
||||
"max_tokens": 2000,
|
||||
"temperature": 0.1,
|
||||
"timeout": vision_timeout,
|
||||
}
|
||||
if vision_model:
|
||||
call_kwargs["model"] = vision_model
|
||||
|
||||
@@ -428,34 +428,21 @@ def execute_code(
|
||||
# Build a minimal environment for the child. We intentionally exclude
|
||||
# API keys and tokens to prevent credential exfiltration from LLM-
|
||||
# generated scripts. The child accesses tools via RPC, not direct API.
|
||||
# Exception: env vars declared by loaded skills (via env_passthrough
|
||||
# registry) or explicitly allowed by the user in config.yaml
|
||||
# (terminal.env_passthrough) are passed through.
|
||||
_SAFE_ENV_PREFIXES = ("PATH", "HOME", "USER", "LANG", "LC_", "TERM",
|
||||
"TMPDIR", "TMP", "TEMP", "SHELL", "LOGNAME",
|
||||
"XDG_", "PYTHONPATH", "VIRTUAL_ENV", "CONDA")
|
||||
_SECRET_SUBSTRINGS = ("KEY", "TOKEN", "SECRET", "PASSWORD", "CREDENTIAL",
|
||||
"PASSWD", "AUTH")
|
||||
try:
|
||||
from tools.env_passthrough import is_env_passthrough as _is_passthrough
|
||||
except Exception:
|
||||
_is_passthrough = lambda _: False # noqa: E731
|
||||
child_env = {}
|
||||
for k, v in os.environ.items():
|
||||
# Passthrough vars (skill-declared or user-configured) always pass.
|
||||
if _is_passthrough(k):
|
||||
child_env[k] = v
|
||||
continue
|
||||
# Block vars with secret-like names.
|
||||
if any(s in k.upper() for s in _SECRET_SUBSTRINGS):
|
||||
continue
|
||||
# Allow vars with known safe prefixes.
|
||||
if any(k.startswith(p) for p in _SAFE_ENV_PREFIXES):
|
||||
child_env[k] = v
|
||||
child_env["HERMES_RPC_SOCKET"] = sock_path
|
||||
child_env["PYTHONDONTWRITEBYTECODE"] = "1"
|
||||
# Ensure the hermes-agent root is importable in the sandbox so
|
||||
# repo-root modules are available to child scripts.
|
||||
# modules like minisweagent_path are available to child scripts.
|
||||
_hermes_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||||
_existing_pp = child_env.get("PYTHONPATH", "")
|
||||
child_env["PYTHONPATH"] = _hermes_root + (os.pathsep + _existing_pp if _existing_pp else "")
|
||||
@@ -590,12 +577,6 @@ def execute_code(
|
||||
server_sock = None # prevent double close in finally
|
||||
rpc_thread.join(timeout=3)
|
||||
|
||||
# Strip ANSI escape sequences so the model never sees terminal
|
||||
# formatting — prevents it from copying escapes into file writes.
|
||||
from tools.ansi_strip import strip_ansi
|
||||
stdout_text = strip_ansi(stdout_text)
|
||||
stderr_text = strip_ansi(stderr_text)
|
||||
|
||||
# Build response
|
||||
result: Dict[str, Any] = {
|
||||
"status": status,
|
||||
|
||||
@@ -1,99 +0,0 @@
|
||||
"""Environment variable passthrough registry.
|
||||
|
||||
Skills that declare ``required_environment_variables`` in their frontmatter
|
||||
need those vars available in sandboxed execution environments (execute_code,
|
||||
terminal). By default both sandboxes strip secrets from the child process
|
||||
environment for security. This module provides a session-scoped allowlist
|
||||
so skill-declared vars (and user-configured overrides) pass through.
|
||||
|
||||
Two sources feed the allowlist:
|
||||
|
||||
1. **Skill declarations** — when a skill is loaded via ``skill_view``, its
|
||||
``required_environment_variables`` are registered here automatically.
|
||||
2. **User config** — ``terminal.env_passthrough`` in config.yaml lets users
|
||||
explicitly allowlist vars for non-skill use cases.
|
||||
|
||||
Both ``code_execution_tool.py`` and ``tools/environments/local.py`` consult
|
||||
:func:`is_env_passthrough` before stripping a variable.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
from pathlib import Path
|
||||
from typing import Iterable
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Session-scoped set of env var names that should pass through to sandboxes.
|
||||
_allowed_env_vars: set[str] = set()
|
||||
|
||||
# Cache for the config-based allowlist (loaded once per process).
|
||||
_config_passthrough: frozenset[str] | None = None
|
||||
|
||||
|
||||
def register_env_passthrough(var_names: Iterable[str]) -> None:
|
||||
"""Register environment variable names as allowed in sandboxed environments.
|
||||
|
||||
Typically called when a skill declares ``required_environment_variables``.
|
||||
"""
|
||||
for name in var_names:
|
||||
name = name.strip()
|
||||
if name:
|
||||
_allowed_env_vars.add(name)
|
||||
logger.debug("env passthrough: registered %s", name)
|
||||
|
||||
|
||||
def _load_config_passthrough() -> frozenset[str]:
|
||||
"""Load ``tools.env_passthrough`` from config.yaml (cached)."""
|
||||
global _config_passthrough
|
||||
if _config_passthrough is not None:
|
||||
return _config_passthrough
|
||||
|
||||
result: set[str] = set()
|
||||
try:
|
||||
hermes_home = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes"))
|
||||
config_path = hermes_home / "config.yaml"
|
||||
if config_path.exists():
|
||||
import yaml
|
||||
|
||||
with open(config_path) as f:
|
||||
cfg = yaml.safe_load(f) or {}
|
||||
passthrough = cfg.get("terminal", {}).get("env_passthrough")
|
||||
if isinstance(passthrough, list):
|
||||
for item in passthrough:
|
||||
if isinstance(item, str) and item.strip():
|
||||
result.add(item.strip())
|
||||
except Exception as e:
|
||||
logger.debug("Could not read tools.env_passthrough from config: %s", e)
|
||||
|
||||
_config_passthrough = frozenset(result)
|
||||
return _config_passthrough
|
||||
|
||||
|
||||
def is_env_passthrough(var_name: str) -> bool:
|
||||
"""Check whether *var_name* is allowed to pass through to sandboxes.
|
||||
|
||||
Returns ``True`` if the variable was registered by a skill or listed in
|
||||
the user's ``tools.env_passthrough`` config.
|
||||
"""
|
||||
if var_name in _allowed_env_vars:
|
||||
return True
|
||||
return var_name in _load_config_passthrough()
|
||||
|
||||
|
||||
def get_all_passthrough() -> frozenset[str]:
|
||||
"""Return the union of skill-registered and config-based passthrough vars."""
|
||||
return frozenset(_allowed_env_vars) | _load_config_passthrough()
|
||||
|
||||
|
||||
def clear_env_passthrough() -> None:
|
||||
"""Reset the skill-scoped allowlist (e.g. on session reset)."""
|
||||
_allowed_env_vars.clear()
|
||||
|
||||
|
||||
def reset_config_cache() -> None:
|
||||
"""Force re-read of config on next access (for testing)."""
|
||||
global _config_passthrough
|
||||
_config_passthrough = None
|
||||
@@ -1,6 +1,6 @@
|
||||
"""Docker execution environment for sandboxed command execution.
|
||||
"""Docker execution environment wrapping mini-swe-agent's DockerEnvironment.
|
||||
|
||||
Security hardened (cap-drop ALL, no-new-privileges, PID limits),
|
||||
Adds security hardening (cap-drop ALL, no-new-privileges, PID limits),
|
||||
configurable resource limits (CPU, memory, disk), and optional filesystem
|
||||
persistence via bind mounts.
|
||||
"""
|
||||
@@ -13,7 +13,6 @@ import subprocess
|
||||
import sys
|
||||
import threading
|
||||
import time
|
||||
import uuid
|
||||
from typing import Optional
|
||||
|
||||
from tools.environments.base import BaseEnvironment
|
||||
@@ -228,9 +227,12 @@ class DockerEnvironment(BaseEnvironment):
|
||||
logger.warning(f"docker_volumes config is not a list: {volumes!r}")
|
||||
volumes = []
|
||||
|
||||
# Fail fast if Docker is not available.
|
||||
# Fail fast if Docker is not available rather than surfacing a cryptic
|
||||
# FileNotFoundError deep inside the mini-swe-agent stack.
|
||||
_ensure_docker_available()
|
||||
|
||||
from minisweagent.environments.docker import DockerEnvironment as _Docker
|
||||
|
||||
# Build resource limit args
|
||||
resource_args = []
|
||||
if cpu > 0:
|
||||
@@ -318,28 +320,14 @@ class DockerEnvironment(BaseEnvironment):
|
||||
|
||||
# Resolve the docker executable once so it works even when
|
||||
# /usr/local/bin is not in PATH (common on macOS gateway/service).
|
||||
self._docker_exe = find_docker() or "docker"
|
||||
docker_exe = find_docker() or "docker"
|
||||
|
||||
# Start the container directly via `docker run -d`.
|
||||
container_name = f"hermes-{uuid.uuid4().hex[:8]}"
|
||||
run_cmd = [
|
||||
self._docker_exe, "run", "-d",
|
||||
"--name", container_name,
|
||||
"-w", cwd,
|
||||
*all_run_args,
|
||||
image,
|
||||
"sleep", "2h",
|
||||
]
|
||||
logger.debug(f"Starting container: {' '.join(run_cmd)}")
|
||||
result = subprocess.run(
|
||||
run_cmd,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=120, # image pull may take a while
|
||||
check=True,
|
||||
self._inner = _Docker(
|
||||
image=image, cwd=cwd, timeout=timeout,
|
||||
run_args=all_run_args,
|
||||
executable=docker_exe,
|
||||
)
|
||||
self._container_id = result.stdout.strip()
|
||||
logger.info(f"Started container {container_name} ({self._container_id[:12]})")
|
||||
self._container_id = self._inner.container_id
|
||||
|
||||
@staticmethod
|
||||
def _storage_opt_supported() -> bool:
|
||||
@@ -401,8 +389,8 @@ class DockerEnvironment(BaseEnvironment):
|
||||
exec_command = f"cd {work_dir} && {exec_command}"
|
||||
work_dir = "/"
|
||||
|
||||
assert self._container_id, "Container not started"
|
||||
cmd = [self._docker_exe, "exec"]
|
||||
assert self._inner.container_id, "Container not started"
|
||||
cmd = [self._inner.config.executable, "exec"]
|
||||
if effective_stdin is not None:
|
||||
cmd.append("-i")
|
||||
cmd.extend(["-w", work_dir])
|
||||
@@ -413,7 +401,9 @@ class DockerEnvironment(BaseEnvironment):
|
||||
value = hermes_env.get(key)
|
||||
if value is not None:
|
||||
cmd.extend(["-e", f"{key}={value}"])
|
||||
cmd.extend([self._container_id, "bash", "-lc", exec_command])
|
||||
for key, value in self._inner.config.env.items():
|
||||
cmd.extend(["-e", f"{key}={value}"])
|
||||
cmd.extend([self._inner.container_id, "bash", "-lc", exec_command])
|
||||
|
||||
try:
|
||||
_output_chunks = []
|
||||
@@ -466,29 +456,24 @@ class DockerEnvironment(BaseEnvironment):
|
||||
|
||||
def cleanup(self):
|
||||
"""Stop and remove the container. Bind-mount dirs persist if persistent=True."""
|
||||
if self._container_id:
|
||||
try:
|
||||
# Stop in background so cleanup doesn't block
|
||||
stop_cmd = (
|
||||
f"(timeout 60 {self._docker_exe} stop {self._container_id} || "
|
||||
f"{self._docker_exe} rm -f {self._container_id}) >/dev/null 2>&1 &"
|
||||
)
|
||||
subprocess.Popen(stop_cmd, shell=True)
|
||||
except Exception as e:
|
||||
logger.warning("Failed to stop container %s: %s", self._container_id, e)
|
||||
self._inner.cleanup()
|
||||
|
||||
if not self._persistent:
|
||||
# Also schedule removal (stop only leaves it as stopped)
|
||||
try:
|
||||
subprocess.Popen(
|
||||
f"sleep 3 && {self._docker_exe} rm -f {self._container_id} >/dev/null 2>&1 &",
|
||||
shell=True,
|
||||
)
|
||||
except Exception:
|
||||
pass
|
||||
if not self._persistent and self._container_id:
|
||||
# Inner cleanup only runs `docker stop` in background; container is left
|
||||
# as stopped. When container_persistent=false we must remove it.
|
||||
docker_exe = find_docker() or self._inner.config.executable
|
||||
try:
|
||||
subprocess.run(
|
||||
[docker_exe, "rm", "-f", self._container_id],
|
||||
capture_output=True,
|
||||
timeout=30,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning("Failed to remove non-persistent container %s: %s", self._container_id, e)
|
||||
self._container_id = None
|
||||
|
||||
if not self._persistent:
|
||||
import shutil
|
||||
for d in (self._workspace_dir, self._home_dir):
|
||||
if d:
|
||||
shutil.rmtree(d, ignore_errors=True)
|
||||
|
||||
@@ -135,28 +135,21 @@ def _sanitize_subprocess_env(base_env: dict | None, extra_env: dict | None = Non
|
||||
"""Filter Hermes-managed secrets from a subprocess environment.
|
||||
|
||||
`_HERMES_FORCE_<VAR>` entries in ``extra_env`` opt a blocked variable back in
|
||||
intentionally for callers that truly need it. Vars registered via
|
||||
:mod:`tools.env_passthrough` (skill-declared or user-configured) also
|
||||
bypass the blocklist.
|
||||
intentionally for callers that truly need it.
|
||||
"""
|
||||
try:
|
||||
from tools.env_passthrough import is_env_passthrough as _is_passthrough
|
||||
except Exception:
|
||||
_is_passthrough = lambda _: False # noqa: E731
|
||||
|
||||
sanitized: dict[str, str] = {}
|
||||
|
||||
for key, value in (base_env or {}).items():
|
||||
if key.startswith(_HERMES_PROVIDER_ENV_FORCE_PREFIX):
|
||||
continue
|
||||
if key not in _HERMES_PROVIDER_ENV_BLOCKLIST or _is_passthrough(key):
|
||||
if key not in _HERMES_PROVIDER_ENV_BLOCKLIST:
|
||||
sanitized[key] = value
|
||||
|
||||
for key, value in (extra_env or {}).items():
|
||||
if key.startswith(_HERMES_PROVIDER_ENV_FORCE_PREFIX):
|
||||
real_key = key[len(_HERMES_PROVIDER_ENV_FORCE_PREFIX):]
|
||||
sanitized[real_key] = value
|
||||
elif key not in _HERMES_PROVIDER_ENV_BLOCKLIST or _is_passthrough(key):
|
||||
elif key not in _HERMES_PROVIDER_ENV_BLOCKLIST:
|
||||
sanitized[key] = value
|
||||
|
||||
return sanitized
|
||||
@@ -261,28 +254,18 @@ def _clean_shell_noise(output: str) -> str:
|
||||
return result
|
||||
|
||||
|
||||
# Standard PATH entries for environments with minimal PATH (e.g. systemd services).
|
||||
# Includes macOS Homebrew paths (/opt/homebrew/* for Apple Silicon).
|
||||
_SANE_PATH = (
|
||||
"/opt/homebrew/bin:/opt/homebrew/sbin:"
|
||||
"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
|
||||
)
|
||||
_SANE_PATH = "/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
|
||||
|
||||
|
||||
def _make_run_env(env: dict) -> dict:
|
||||
"""Build a run environment with a sane PATH and provider-var stripping."""
|
||||
try:
|
||||
from tools.env_passthrough import is_env_passthrough as _is_passthrough
|
||||
except Exception:
|
||||
_is_passthrough = lambda _: False # noqa: E731
|
||||
|
||||
merged = dict(os.environ | env)
|
||||
run_env = {}
|
||||
for k, v in merged.items():
|
||||
if k.startswith(_HERMES_PROVIDER_ENV_FORCE_PREFIX):
|
||||
real_key = k[len(_HERMES_PROVIDER_ENV_FORCE_PREFIX):]
|
||||
run_env[real_key] = v
|
||||
elif k not in _HERMES_PROVIDER_ENV_BLOCKLIST or _is_passthrough(k):
|
||||
elif k not in _HERMES_PROVIDER_ENV_BLOCKLIST:
|
||||
run_env[k] = v
|
||||
existing_path = run_env.get("PATH", "")
|
||||
if "/usr/bin" not in existing_path.split(":"):
|
||||
|
||||
+50
-123
@@ -1,14 +1,14 @@
|
||||
"""Modal cloud execution environment using SWE-ReX directly.
|
||||
"""Modal cloud execution environment wrapping mini-swe-agent's SwerexModalEnvironment.
|
||||
|
||||
Supports persistent filesystem snapshots: when enabled, the sandbox's filesystem
|
||||
is snapshotted on cleanup and restored on next creation, so installed packages,
|
||||
project files, and config changes survive across sessions.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import logging
|
||||
import threading
|
||||
import time
|
||||
import uuid
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, Optional
|
||||
@@ -38,50 +38,16 @@ def _save_snapshots(data: Dict[str, str]) -> None:
|
||||
_SNAPSHOT_STORE.write_text(json.dumps(data, indent=2))
|
||||
|
||||
|
||||
class _AsyncWorker:
|
||||
"""Background thread with its own event loop for async-safe swe-rex calls.
|
||||
|
||||
Allows sync code to submit async coroutines and block for results,
|
||||
even when called from inside another running event loop (e.g. Atropos).
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
self._loop: Optional[asyncio.AbstractEventLoop] = None
|
||||
self._thread: Optional[threading.Thread] = None
|
||||
self._started = threading.Event()
|
||||
|
||||
def start(self):
|
||||
self._thread = threading.Thread(target=self._run_loop, daemon=True)
|
||||
self._thread.start()
|
||||
self._started.wait(timeout=30)
|
||||
|
||||
def _run_loop(self):
|
||||
self._loop = asyncio.new_event_loop()
|
||||
asyncio.set_event_loop(self._loop)
|
||||
self._started.set()
|
||||
self._loop.run_forever()
|
||||
|
||||
def run_coroutine(self, coro, timeout=600):
|
||||
if self._loop is None or self._loop.is_closed():
|
||||
raise RuntimeError("AsyncWorker loop is not running")
|
||||
future = asyncio.run_coroutine_threadsafe(coro, self._loop)
|
||||
return future.result(timeout=timeout)
|
||||
|
||||
def stop(self):
|
||||
if self._loop and self._loop.is_running():
|
||||
self._loop.call_soon_threadsafe(self._loop.stop)
|
||||
if self._thread:
|
||||
self._thread.join(timeout=10)
|
||||
|
||||
|
||||
class ModalEnvironment(BaseEnvironment):
|
||||
"""Modal cloud execution via SWE-ReX.
|
||||
"""Modal cloud execution via mini-swe-agent.
|
||||
|
||||
Uses swe-rex's ModalDeployment directly for sandbox management.
|
||||
Adds sudo -S support, configurable resources (CPU, memory, disk),
|
||||
and optional filesystem persistence via Modal's snapshot API.
|
||||
Wraps SwerexModalEnvironment and adds sudo -S support, configurable
|
||||
resources (CPU, memory, disk), and optional filesystem persistence
|
||||
via Modal's snapshot_filesystem() API.
|
||||
"""
|
||||
|
||||
_patches_applied = False
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
image: str,
|
||||
@@ -93,11 +59,17 @@ class ModalEnvironment(BaseEnvironment):
|
||||
):
|
||||
super().__init__(cwd=cwd, timeout=timeout)
|
||||
|
||||
if not ModalEnvironment._patches_applied:
|
||||
try:
|
||||
from environments.patches import apply_patches
|
||||
apply_patches()
|
||||
except ImportError:
|
||||
pass
|
||||
ModalEnvironment._patches_applied = True
|
||||
|
||||
self._persistent = persistent_filesystem
|
||||
self._task_id = task_id
|
||||
self._base_image = image
|
||||
self._deployment = None
|
||||
self._worker = _AsyncWorker()
|
||||
|
||||
sandbox_kwargs = dict(modal_sandbox_kwargs or {})
|
||||
|
||||
@@ -116,37 +88,16 @@ class ModalEnvironment(BaseEnvironment):
|
||||
|
||||
effective_image = restored_image if restored_image else image
|
||||
|
||||
# Pre-build a modal.Image with pip fix for Modal's legacy image builder.
|
||||
# Some task images have broken pip; fix via ensurepip before Modal uses it.
|
||||
import modal as _modal
|
||||
if isinstance(effective_image, str):
|
||||
effective_image = _modal.Image.from_registry(
|
||||
effective_image,
|
||||
setup_dockerfile_commands=[
|
||||
"RUN rm -rf /usr/local/lib/python*/site-packages/pip* 2>/dev/null; "
|
||||
"python -m ensurepip --upgrade --default-pip 2>/dev/null || true",
|
||||
],
|
||||
)
|
||||
|
||||
# Start the async worker thread and create the deployment on it
|
||||
# so all gRPC channels are bound to the worker's event loop.
|
||||
self._worker.start()
|
||||
|
||||
from swerex.deployment.modal import ModalDeployment
|
||||
|
||||
async def _create_and_start():
|
||||
deployment = ModalDeployment(
|
||||
image=effective_image,
|
||||
startup_timeout=180.0,
|
||||
runtime_timeout=3600.0,
|
||||
deployment_timeout=3600.0,
|
||||
install_pipx=True,
|
||||
modal_sandbox_kwargs=sandbox_kwargs,
|
||||
)
|
||||
await deployment.start()
|
||||
return deployment
|
||||
|
||||
self._deployment = self._worker.run_coroutine(_create_and_start())
|
||||
from minisweagent.environments.extra.swerex_modal import SwerexModalEnvironment
|
||||
self._inner = SwerexModalEnvironment(
|
||||
image=effective_image,
|
||||
cwd=cwd,
|
||||
timeout=timeout,
|
||||
startup_timeout=180.0,
|
||||
runtime_timeout=3600.0,
|
||||
modal_sandbox_kwargs=sandbox_kwargs,
|
||||
install_pipx=True, # Required: installs pipx + swe-rex runtime (swerex-remote)
|
||||
)
|
||||
|
||||
def execute(self, command: str, cwd: str = "", *,
|
||||
timeout: int | None = None,
|
||||
@@ -163,39 +114,21 @@ class ModalEnvironment(BaseEnvironment):
|
||||
# subprocess stdin directly the way a local Popen can. When a sudo
|
||||
# password is present, use a shell-level pipe from printf so that the
|
||||
# password feeds sudo -S without appearing as an echo argument embedded
|
||||
# in the shell string.
|
||||
# in the shell string. The password is still visible in the remote
|
||||
# sandbox's command line, but it is not exposed on the user's local
|
||||
# machine — which is the primary threat being mitigated.
|
||||
if sudo_stdin is not None:
|
||||
import shlex
|
||||
exec_command = (
|
||||
f"printf '%s\\n' {shlex.quote(sudo_stdin.rstrip())} | {exec_command}"
|
||||
)
|
||||
|
||||
from swerex.runtime.abstract import Command as RexCommand
|
||||
|
||||
effective_cwd = cwd or self.cwd
|
||||
effective_timeout = timeout or self.timeout
|
||||
|
||||
# Run in a background thread so we can poll for interrupts
|
||||
result_holder = {"value": None, "error": None}
|
||||
|
||||
def _run():
|
||||
try:
|
||||
async def _do_execute():
|
||||
return await self._deployment.runtime.execute(
|
||||
RexCommand(
|
||||
command=exec_command,
|
||||
shell=True,
|
||||
check=False,
|
||||
cwd=effective_cwd,
|
||||
timeout=effective_timeout,
|
||||
merge_output_streams=True,
|
||||
)
|
||||
)
|
||||
output = self._worker.run_coroutine(_do_execute())
|
||||
result_holder["value"] = {
|
||||
"output": output.stdout,
|
||||
"returncode": output.exit_code,
|
||||
}
|
||||
result_holder["value"] = self._inner.execute(exec_command, cwd=cwd, timeout=timeout)
|
||||
except Exception as e:
|
||||
result_holder["error"] = e
|
||||
|
||||
@@ -205,10 +138,7 @@ class ModalEnvironment(BaseEnvironment):
|
||||
t.join(timeout=0.2)
|
||||
if is_interrupted():
|
||||
try:
|
||||
self._worker.run_coroutine(
|
||||
asyncio.wait_for(self._deployment.stop(), timeout=10),
|
||||
timeout=15,
|
||||
)
|
||||
self._inner.stop()
|
||||
except Exception:
|
||||
pass
|
||||
return {
|
||||
@@ -222,38 +152,35 @@ class ModalEnvironment(BaseEnvironment):
|
||||
|
||||
def cleanup(self):
|
||||
"""Snapshot the filesystem (if persistent) then stop the sandbox."""
|
||||
if self._deployment is None:
|
||||
# Check if _inner was ever set (init may have failed)
|
||||
if not hasattr(self, '_inner') or self._inner is None:
|
||||
return
|
||||
|
||||
if self._persistent:
|
||||
try:
|
||||
sandbox = getattr(self._deployment, '_sandbox', None)
|
||||
sandbox = getattr(self._inner, 'deployment', None)
|
||||
sandbox = getattr(sandbox, '_sandbox', None) if sandbox else None
|
||||
if sandbox:
|
||||
import asyncio
|
||||
async def _snapshot():
|
||||
img = await sandbox.snapshot_filesystem.aio()
|
||||
return img.object_id
|
||||
|
||||
try:
|
||||
snapshot_id = self._worker.run_coroutine(_snapshot(), timeout=60)
|
||||
except Exception:
|
||||
snapshot_id = None
|
||||
snapshot_id = asyncio.run(_snapshot())
|
||||
except RuntimeError:
|
||||
import concurrent.futures
|
||||
with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
|
||||
snapshot_id = pool.submit(
|
||||
asyncio.run, _snapshot()
|
||||
).result(timeout=60)
|
||||
|
||||
if snapshot_id:
|
||||
snapshots = _load_snapshots()
|
||||
snapshots[self._task_id] = snapshot_id
|
||||
_save_snapshots(snapshots)
|
||||
logger.info("Modal: saved filesystem snapshot %s for task %s",
|
||||
snapshot_id[:20], self._task_id)
|
||||
snapshots = _load_snapshots()
|
||||
snapshots[self._task_id] = snapshot_id
|
||||
_save_snapshots(snapshots)
|
||||
logger.info("Modal: saved filesystem snapshot %s for task %s",
|
||||
snapshot_id[:20], self._task_id)
|
||||
except Exception as e:
|
||||
logger.warning("Modal: filesystem snapshot failed: %s", e)
|
||||
|
||||
try:
|
||||
self._worker.run_coroutine(
|
||||
asyncio.wait_for(self._deployment.stop(), timeout=10),
|
||||
timeout=15,
|
||||
)
|
||||
except Exception:
|
||||
pass
|
||||
finally:
|
||||
self._worker.stop()
|
||||
self._deployment = None
|
||||
if hasattr(self._inner, 'stop'):
|
||||
self._inner.stop()
|
||||
|
||||
@@ -433,13 +433,9 @@ class ShellFileOperations(FileOperations):
|
||||
slash_idx = rest.find('/')
|
||||
username = rest[:slash_idx] if slash_idx >= 0 else rest
|
||||
if username and re.fullmatch(r'[a-zA-Z0-9._-]+', username):
|
||||
# Only expand ~username (not the full path) to avoid shell
|
||||
# injection via path suffixes like "~user/$(malicious)".
|
||||
expand_result = self._exec(f"echo ~{username}")
|
||||
expand_result = self._exec(f"echo {path}")
|
||||
if expand_result.exit_code == 0 and expand_result.stdout.strip():
|
||||
user_home = expand_result.stdout.strip()
|
||||
suffix = path[1 + len(username):] # e.g. "/rest/of/path"
|
||||
return user_home + suffix
|
||||
return expand_result.stdout.strip()
|
||||
|
||||
return path
|
||||
|
||||
|
||||
@@ -5,6 +5,7 @@ import errno
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import threading
|
||||
from typing import Optional
|
||||
from tools.file_operations import ShellFileOperations
|
||||
@@ -12,6 +13,17 @@ from agent.redact import redact_sensitive_text
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Regex to match ANSI escape sequences (CSI codes, OSC codes, simple escapes).
|
||||
# Models occasionally copy these from terminal output into file content.
|
||||
_ANSI_ESCAPE_RE = re.compile(r"\x1b\[[0-9;]*[A-Za-z]|\x1b\][^\x07]*\x07|\x1b[()][A-B012]|\x1b[=>]")
|
||||
|
||||
|
||||
def _strip_ansi(text: str) -> str:
|
||||
"""Remove ANSI escape sequences from text destined for file writes."""
|
||||
if not text or "\x1b" not in text:
|
||||
return text
|
||||
return _ANSI_ESCAPE_RE.sub("", text)
|
||||
|
||||
|
||||
_EXPECTED_WRITE_ERRNOS = {errno.EACCES, errno.EPERM, errno.EROFS}
|
||||
|
||||
@@ -289,6 +301,7 @@ def notify_other_tool_call(task_id: str = "default"):
|
||||
def write_file_tool(path: str, content: str, task_id: str = "default") -> str:
|
||||
"""Write content to a file."""
|
||||
try:
|
||||
content = _strip_ansi(content)
|
||||
file_ops = _get_file_ops(task_id)
|
||||
result = file_ops.write_file(path, content)
|
||||
return json.dumps(result.to_dict(), ensure_ascii=False)
|
||||
@@ -312,10 +325,13 @@ def patch_tool(mode: str = "replace", path: str = None, old_string: str = None,
|
||||
return json.dumps({"error": "path required"})
|
||||
if old_string is None or new_string is None:
|
||||
return json.dumps({"error": "old_string and new_string required"})
|
||||
old_string = _strip_ansi(old_string)
|
||||
new_string = _strip_ansi(new_string)
|
||||
result = file_ops.patch_replace(path, old_string, new_string, replace_all)
|
||||
elif mode == "patch":
|
||||
if not patch:
|
||||
return json.dumps({"error": "patch content required"})
|
||||
patch = _strip_ansi(patch)
|
||||
result = file_ops.patch_v4a(patch)
|
||||
else:
|
||||
return json.dumps({"error": f"Unknown mode: {mode}"})
|
||||
|
||||
@@ -426,14 +426,12 @@ class ProcessRegistry:
|
||||
|
||||
def poll(self, session_id: str) -> dict:
|
||||
"""Check status and get new output for a background process."""
|
||||
from tools.ansi_strip import strip_ansi
|
||||
|
||||
session = self.get(session_id)
|
||||
if session is None:
|
||||
return {"status": "not_found", "error": f"No process with ID {session_id}"}
|
||||
|
||||
with session._lock:
|
||||
output_preview = strip_ansi(session.output_buffer[-1000:]) if session.output_buffer else ""
|
||||
output_preview = session.output_buffer[-1000:] if session.output_buffer else ""
|
||||
|
||||
result = {
|
||||
"session_id": session.id,
|
||||
@@ -452,14 +450,12 @@ class ProcessRegistry:
|
||||
|
||||
def read_log(self, session_id: str, offset: int = 0, limit: int = 200) -> dict:
|
||||
"""Read the full output log with optional pagination by lines."""
|
||||
from tools.ansi_strip import strip_ansi
|
||||
|
||||
session = self.get(session_id)
|
||||
if session is None:
|
||||
return {"status": "not_found", "error": f"No process with ID {session_id}"}
|
||||
|
||||
with session._lock:
|
||||
full_output = strip_ansi(session.output_buffer)
|
||||
full_output = session.output_buffer
|
||||
|
||||
lines = full_output.splitlines()
|
||||
total_lines = len(lines)
|
||||
@@ -490,7 +486,6 @@ class ProcessRegistry:
|
||||
dict with status ("exited", "timeout", "interrupted", "not_found")
|
||||
and output snapshot.
|
||||
"""
|
||||
from tools.ansi_strip import strip_ansi
|
||||
from tools.terminal_tool import _interrupt_event
|
||||
|
||||
default_timeout = int(os.getenv("TERMINAL_TIMEOUT", "180"))
|
||||
@@ -518,7 +513,7 @@ class ProcessRegistry:
|
||||
result = {
|
||||
"status": "exited",
|
||||
"exit_code": session.exit_code,
|
||||
"output": strip_ansi(session.output_buffer[-2000:]),
|
||||
"output": session.output_buffer[-2000:],
|
||||
}
|
||||
if timeout_note:
|
||||
result["timeout_note"] = timeout_note
|
||||
@@ -527,7 +522,7 @@ class ProcessRegistry:
|
||||
if _interrupt_event.is_set():
|
||||
result = {
|
||||
"status": "interrupted",
|
||||
"output": strip_ansi(session.output_buffer[-1000:]),
|
||||
"output": session.output_buffer[-1000:],
|
||||
"note": "User sent a new message -- wait interrupted",
|
||||
}
|
||||
if timeout_note:
|
||||
@@ -538,7 +533,7 @@ class ProcessRegistry:
|
||||
|
||||
result = {
|
||||
"status": "timeout",
|
||||
"output": strip_ansi(session.output_buffer[-1000:]),
|
||||
"output": session.output_buffer[-1000:],
|
||||
}
|
||||
if timeout_note:
|
||||
result["timeout_note"] = timeout_note
|
||||
|
||||
@@ -179,58 +179,6 @@ async def _summarize_session(
|
||||
return None
|
||||
|
||||
|
||||
def _list_recent_sessions(db, limit: int, current_session_id: str = None) -> str:
|
||||
"""Return metadata for the most recent sessions (no LLM calls)."""
|
||||
try:
|
||||
sessions = db.list_sessions_rich(limit=limit + 5) # fetch extra to skip current
|
||||
|
||||
# Resolve current session lineage to exclude it
|
||||
current_root = None
|
||||
if current_session_id:
|
||||
try:
|
||||
sid = current_session_id
|
||||
visited = set()
|
||||
while sid and sid not in visited:
|
||||
visited.add(sid)
|
||||
s = db.get_session(sid)
|
||||
parent = s.get("parent_session_id") if s else None
|
||||
sid = parent if parent else None
|
||||
current_root = max(visited, key=len) if visited else current_session_id
|
||||
except Exception:
|
||||
current_root = current_session_id
|
||||
|
||||
results = []
|
||||
for s in sessions:
|
||||
sid = s.get("id", "")
|
||||
if current_root and (sid == current_root or sid == current_session_id):
|
||||
continue
|
||||
# Skip child/delegation sessions (they have parent_session_id)
|
||||
if s.get("parent_session_id"):
|
||||
continue
|
||||
results.append({
|
||||
"session_id": sid,
|
||||
"title": s.get("title") or None,
|
||||
"source": s.get("source", ""),
|
||||
"started_at": s.get("started_at", ""),
|
||||
"last_active": s.get("last_active", ""),
|
||||
"message_count": s.get("message_count", 0),
|
||||
"preview": s.get("preview", ""),
|
||||
})
|
||||
if len(results) >= limit:
|
||||
break
|
||||
|
||||
return json.dumps({
|
||||
"success": True,
|
||||
"mode": "recent",
|
||||
"results": results,
|
||||
"count": len(results),
|
||||
"message": f"Showing {len(results)} most recent sessions. Use a keyword query to search specific topics.",
|
||||
}, ensure_ascii=False)
|
||||
except Exception as e:
|
||||
logging.error("Error listing recent sessions: %s", e, exc_info=True)
|
||||
return json.dumps({"success": False, "error": f"Failed to list recent sessions: {e}"}, ensure_ascii=False)
|
||||
|
||||
|
||||
def session_search(
|
||||
query: str,
|
||||
role_filter: str = None,
|
||||
@@ -247,14 +195,11 @@ def session_search(
|
||||
if db is None:
|
||||
return json.dumps({"success": False, "error": "Session database not available."}, ensure_ascii=False)
|
||||
|
||||
limit = min(limit, 5) # Cap at 5 sessions to avoid excessive LLM calls
|
||||
|
||||
# Recent sessions mode: when query is empty, return metadata for recent sessions.
|
||||
# No LLM calls — just DB queries for titles, previews, timestamps.
|
||||
if not query or not query.strip():
|
||||
return _list_recent_sessions(db, limit, current_session_id)
|
||||
return json.dumps({"success": False, "error": "Query cannot be empty."}, ensure_ascii=False)
|
||||
|
||||
query = query.strip()
|
||||
limit = min(limit, 5) # Cap at 5 sessions to avoid excessive LLM calls
|
||||
|
||||
try:
|
||||
# Parse role filter
|
||||
@@ -419,14 +364,8 @@ def check_session_search_requirements() -> bool:
|
||||
SESSION_SEARCH_SCHEMA = {
|
||||
"name": "session_search",
|
||||
"description": (
|
||||
"Search your long-term memory of past conversations, or browse recent sessions. This is your recall -- "
|
||||
"Search your long-term memory of past conversations. This is your recall -- "
|
||||
"every past session is searchable, and this tool summarizes what happened.\n\n"
|
||||
"TWO MODES:\n"
|
||||
"1. Recent sessions (no query): Call with no arguments to see what was worked on recently. "
|
||||
"Returns titles, previews, and timestamps. Zero LLM cost, instant. "
|
||||
"Start here when the user asks what were we working on or what did we do recently.\n"
|
||||
"2. Keyword search (with query): Search for specific topics across all past sessions. "
|
||||
"Returns LLM-generated summaries of matching sessions.\n\n"
|
||||
"USE THIS PROACTIVELY when:\n"
|
||||
"- The user says 'we did this before', 'remember when', 'last time', 'as I mentioned'\n"
|
||||
"- The user asks about a topic you worked on before but don't have in current context\n"
|
||||
@@ -446,7 +385,7 @@ SESSION_SEARCH_SCHEMA = {
|
||||
"properties": {
|
||||
"query": {
|
||||
"type": "string",
|
||||
"description": "Search query — keywords, phrases, or boolean expressions to find in past sessions. Omit this parameter entirely to browse recent sessions instead (returns titles, previews, timestamps with no LLM cost).",
|
||||
"description": "Search query — keywords, phrases, or boolean expressions to find in past sessions.",
|
||||
},
|
||||
"role_filter": {
|
||||
"type": "string",
|
||||
@@ -458,7 +397,7 @@ SESSION_SEARCH_SCHEMA = {
|
||||
"default": 3,
|
||||
},
|
||||
},
|
||||
"required": [],
|
||||
"required": ["query"],
|
||||
},
|
||||
}
|
||||
|
||||
@@ -471,7 +410,7 @@ registry.register(
|
||||
toolset="session_search",
|
||||
schema=SESSION_SEARCH_SCHEMA,
|
||||
handler=lambda args, **kw: session_search(
|
||||
query=args.get("query") or "",
|
||||
query=args.get("query", ""),
|
||||
role_filter=args.get("role_filter"),
|
||||
limit=args.get("limit", 3),
|
||||
db=kw.get("db"),
|
||||
|
||||
@@ -1050,9 +1050,6 @@ def _get_configured_model() -> str:
|
||||
|
||||
def _resolve_trust_level(source: str) -> str:
|
||||
"""Map a source identifier to a trust level."""
|
||||
# Agent-created skills get their own permissive trust level
|
||||
if source == "agent-created":
|
||||
return "agent-created"
|
||||
# Official optional skills shipped with the repo
|
||||
if source.startswith("official/") or source == "official":
|
||||
return "builtin"
|
||||
|
||||
@@ -1146,26 +1146,6 @@ def skill_view(name: str, file_path: str = None, task_id: str = None) -> str:
|
||||
)
|
||||
setup_needed = bool(remaining_missing_required_envs)
|
||||
|
||||
# Register available skill env vars so they pass through to sandboxed
|
||||
# execution environments (execute_code, terminal). Only vars that are
|
||||
# actually set get registered — missing ones are reported as setup_needed.
|
||||
available_env_names = [
|
||||
e["name"]
|
||||
for e in required_env_vars
|
||||
if e["name"] not in remaining_missing_required_envs
|
||||
]
|
||||
if available_env_names:
|
||||
try:
|
||||
from tools.env_passthrough import register_env_passthrough
|
||||
|
||||
register_env_passthrough(available_env_names)
|
||||
except Exception:
|
||||
logger.debug(
|
||||
"Could not register env passthrough for skill %s",
|
||||
skill_name,
|
||||
exc_info=True,
|
||||
)
|
||||
|
||||
result = {
|
||||
"success": True,
|
||||
"name": skill_name,
|
||||
|
||||
+35
-20
@@ -1,8 +1,8 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Terminal Tool Module
|
||||
Terminal Tool Module (mini-swe-agent backend)
|
||||
|
||||
A terminal tool that executes commands in local, Docker, Modal, SSH, Singularity, and Daytona environments.
|
||||
A terminal tool that executes commands using mini-swe-agent's execution environments.
|
||||
Supports local execution, Docker containers, and Modal cloud sandboxes.
|
||||
|
||||
Environment Selection (via TERMINAL_ENV environment variable):
|
||||
@@ -51,6 +51,13 @@ logger = logging.getLogger(__name__)
|
||||
from tools.interrupt import is_interrupted, _interrupt_event
|
||||
|
||||
|
||||
# Add mini-swe-agent to path if not installed. In git worktrees the populated
|
||||
# submodule may live in the main checkout rather than the worktree itself.
|
||||
from minisweagent_path import ensure_minisweagent_on_path
|
||||
|
||||
ensure_minisweagent_on_path(Path(__file__).resolve().parent.parent)
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# Custom Singularity Environment with more space
|
||||
# =============================================================================
|
||||
@@ -483,12 +490,10 @@ def _get_env_config() -> Dict[str, Any]:
|
||||
host_cwd = candidate
|
||||
cwd = "/workspace"
|
||||
elif env_type in ("modal", "docker", "singularity", "daytona") and cwd:
|
||||
# Host paths and relative paths that won't work inside containers
|
||||
is_host_path = any(cwd.startswith(p) for p in host_prefixes)
|
||||
is_relative = not os.path.isabs(cwd) # e.g. "." or "src/"
|
||||
if (is_host_path or is_relative) and cwd != default_cwd:
|
||||
# Host paths that won't exist inside containers
|
||||
if any(cwd.startswith(p) for p in host_prefixes) and cwd != default_cwd:
|
||||
logger.info("Ignoring TERMINAL_CWD=%r for %s backend "
|
||||
"(host/relative path won't work in sandbox). Using %r instead.",
|
||||
"(host path won't exist in sandbox). Using %r instead.",
|
||||
cwd, env_type, default_cwd)
|
||||
cwd = default_cwd
|
||||
|
||||
@@ -532,7 +537,7 @@ def _create_environment(env_type: str, image: str, cwd: str, timeout: int,
|
||||
task_id: str = "default",
|
||||
host_cwd: str = None):
|
||||
"""
|
||||
Create an execution environment for sandboxed command execution.
|
||||
Create an execution environment from mini-swe-agent.
|
||||
|
||||
Args:
|
||||
env_type: One of "local", "docker", "singularity", "modal", "daytona", "ssh"
|
||||
@@ -847,7 +852,7 @@ def terminal_tool(
|
||||
pty: bool = False,
|
||||
) -> str:
|
||||
"""
|
||||
Execute a command in the configured terminal environment.
|
||||
Execute a command using mini-swe-agent's execution environments.
|
||||
|
||||
Args:
|
||||
command: The command to execute
|
||||
@@ -982,7 +987,7 @@ def terminal_tool(
|
||||
return json.dumps({
|
||||
"output": "",
|
||||
"exit_code": -1,
|
||||
"error": f"Terminal tool disabled: environment creation failed ({e})",
|
||||
"error": f"Terminal tool disabled: mini-swe-agent not available ({e})",
|
||||
"status": "disabled"
|
||||
}, ensure_ascii=False)
|
||||
|
||||
@@ -1158,11 +1163,6 @@ def terminal_tool(
|
||||
)
|
||||
output = output[:head_chars] + truncated_notice + output[-tail_chars:]
|
||||
|
||||
# Strip ANSI escape sequences so the model never sees terminal
|
||||
# formatting — prevents it from copying escapes into file writes.
|
||||
from tools.ansi_strip import strip_ansi
|
||||
output = strip_ansi(output)
|
||||
|
||||
# Redact secrets from command output (catches env/printenv leaking keys)
|
||||
from agent.redact import redact_sensitive_text
|
||||
output = redact_sensitive_text(output.strip()) if output else ""
|
||||
@@ -1183,15 +1183,27 @@ def terminal_tool(
|
||||
|
||||
|
||||
def check_terminal_requirements() -> bool:
|
||||
"""Check if all requirements for the terminal tool are met."""
|
||||
"""Check if all requirements for the terminal tool are met.
|
||||
|
||||
Important: local and singularity backends now use Hermes' own environment
|
||||
wrappers directly and do not require the ``minisweagent`` Python package to
|
||||
be installed. Docker and Modal still rely on mini-swe-agent internals.
|
||||
"""
|
||||
config = _get_env_config()
|
||||
env_type = config["env_type"]
|
||||
|
||||
try:
|
||||
if env_type == "local":
|
||||
# Local execution uses Hermes' own LocalEnvironment wrapper and does
|
||||
# not depend on minisweagent being importable.
|
||||
return True
|
||||
|
||||
elif env_type == "docker":
|
||||
ensure_minisweagent_on_path(Path(__file__).resolve().parent.parent)
|
||||
if importlib.util.find_spec("minisweagent") is None:
|
||||
logger.error("mini-swe-agent is required for docker terminal backend but is not importable")
|
||||
return False
|
||||
# Check if docker is available (use find_docker for macOS PATH issues)
|
||||
from tools.environments.docker import find_docker
|
||||
docker = find_docker()
|
||||
if not docker:
|
||||
@@ -1208,6 +1220,7 @@ def check_terminal_requirements() -> bool:
|
||||
return False
|
||||
|
||||
elif env_type == "ssh":
|
||||
# Check that host and user are configured
|
||||
if not config.get("ssh_host") or not config.get("ssh_user"):
|
||||
logger.error(
|
||||
"SSH backend selected but TERMINAL_SSH_HOST and TERMINAL_SSH_USER "
|
||||
@@ -1217,9 +1230,11 @@ def check_terminal_requirements() -> bool:
|
||||
return True
|
||||
|
||||
elif env_type == "modal":
|
||||
if importlib.util.find_spec("swerex") is None:
|
||||
logger.error("swe-rex is required for modal terminal backend: pip install 'swe-rex[modal]'")
|
||||
ensure_minisweagent_on_path(Path(__file__).resolve().parent.parent)
|
||||
if importlib.util.find_spec("minisweagent") is None:
|
||||
logger.error("mini-swe-agent is required for modal terminal backend but is not importable")
|
||||
return False
|
||||
# Check for modal token
|
||||
has_token = os.getenv("MODAL_TOKEN_ID") is not None
|
||||
has_config = Path.home().joinpath(".modal.toml").exists()
|
||||
if not (has_token or has_config):
|
||||
@@ -1249,7 +1264,7 @@ def check_terminal_requirements() -> bool:
|
||||
|
||||
if __name__ == "__main__":
|
||||
# Simple test when run directly
|
||||
print("Terminal Tool Module")
|
||||
print("Terminal Tool Module (mini-swe-agent backend)")
|
||||
print("=" * 50)
|
||||
|
||||
config = _get_env_config()
|
||||
@@ -1267,7 +1282,7 @@ if __name__ == "__main__":
|
||||
|
||||
print("\n✅ All requirements met!")
|
||||
print("\nAvailable Tool:")
|
||||
print(" - terminal_tool: Execute commands in sandboxed environments")
|
||||
print(" - terminal_tool: Execute commands using mini-swe-agent environments")
|
||||
|
||||
print("\nUsage Examples:")
|
||||
print(" # Execute a command")
|
||||
|
||||
@@ -1,96 +0,0 @@
|
||||
"""URL safety checks — blocks requests to private/internal network addresses.
|
||||
|
||||
Prevents SSRF (Server-Side Request Forgery) where a malicious prompt or
|
||||
skill could trick the agent into fetching internal resources like cloud
|
||||
metadata endpoints (169.254.169.254), localhost services, or private
|
||||
network hosts.
|
||||
|
||||
Limitations (documented, not fixable at pre-flight level):
|
||||
- DNS rebinding (TOCTOU): an attacker-controlled DNS server with TTL=0
|
||||
can return a public IP for the check, then a private IP for the actual
|
||||
connection. Fixing this requires connection-level validation (e.g.
|
||||
Python's Champion library or an egress proxy like Stripe's Smokescreen).
|
||||
- Redirect-based bypass in vision_tools is mitigated by an httpx event
|
||||
hook that re-validates each redirect target. Web tools use third-party
|
||||
SDKs (Firecrawl/Tavily) where redirect handling is on their servers.
|
||||
"""
|
||||
|
||||
import ipaddress
|
||||
import logging
|
||||
import socket
|
||||
from urllib.parse import urlparse
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Hostnames that should always be blocked regardless of IP resolution
|
||||
_BLOCKED_HOSTNAMES = frozenset({
|
||||
"metadata.google.internal",
|
||||
"metadata.goog",
|
||||
})
|
||||
|
||||
# 100.64.0.0/10 (CGNAT / Shared Address Space, RFC 6598) is NOT covered by
|
||||
# ipaddress.is_private — it returns False for both is_private and is_global.
|
||||
# Must be blocked explicitly. Used by carrier-grade NAT, Tailscale/WireGuard
|
||||
# VPNs, and some cloud internal networks.
|
||||
_CGNAT_NETWORK = ipaddress.ip_network("100.64.0.0/10")
|
||||
|
||||
|
||||
def _is_blocked_ip(ip: ipaddress.IPv4Address | ipaddress.IPv6Address) -> bool:
|
||||
"""Return True if the IP should be blocked for SSRF protection."""
|
||||
if ip.is_private or ip.is_loopback or ip.is_link_local or ip.is_reserved:
|
||||
return True
|
||||
if ip.is_multicast or ip.is_unspecified:
|
||||
return True
|
||||
# CGNAT range not covered by is_private
|
||||
if ip in _CGNAT_NETWORK:
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def is_safe_url(url: str) -> bool:
|
||||
"""Return True if the URL target is not a private/internal address.
|
||||
|
||||
Resolves the hostname to an IP and checks against private ranges.
|
||||
Fails closed: DNS errors and unexpected exceptions block the request.
|
||||
"""
|
||||
try:
|
||||
parsed = urlparse(url)
|
||||
hostname = (parsed.hostname or "").strip().lower()
|
||||
if not hostname:
|
||||
return False
|
||||
|
||||
# Block known internal hostnames
|
||||
if hostname in _BLOCKED_HOSTNAMES:
|
||||
logger.warning("Blocked request to internal hostname: %s", hostname)
|
||||
return False
|
||||
|
||||
# Try to resolve and check IP
|
||||
try:
|
||||
addr_info = socket.getaddrinfo(hostname, None, socket.AF_UNSPEC, socket.SOCK_STREAM)
|
||||
except socket.gaierror:
|
||||
# DNS resolution failed — fail closed. If DNS can't resolve it,
|
||||
# the HTTP client will also fail, so blocking loses nothing.
|
||||
logger.warning("Blocked request — DNS resolution failed for: %s", hostname)
|
||||
return False
|
||||
|
||||
for family, _, _, _, sockaddr in addr_info:
|
||||
ip_str = sockaddr[0]
|
||||
try:
|
||||
ip = ipaddress.ip_address(ip_str)
|
||||
except ValueError:
|
||||
continue
|
||||
|
||||
if _is_blocked_ip(ip):
|
||||
logger.warning(
|
||||
"Blocked request to private/internal address: %s -> %s",
|
||||
hostname, ip_str,
|
||||
)
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
except Exception as exc:
|
||||
# Fail closed on unexpected errors — don't let parsing edge cases
|
||||
# become SSRF bypass vectors
|
||||
logger.warning("Blocked request — URL safety check error for %s: %s", url, exc)
|
||||
return False
|
||||
+4
-38
@@ -69,12 +69,7 @@ def _validate_image_url(url: str) -> bool:
|
||||
if not parsed.netloc:
|
||||
return False
|
||||
|
||||
# Block private/internal addresses to prevent SSRF
|
||||
from tools.url_safety import is_safe_url
|
||||
if not is_safe_url(url):
|
||||
return False
|
||||
|
||||
return True
|
||||
return True # Allow all well-formed HTTP/HTTPS URLs for flexibility
|
||||
|
||||
|
||||
async def _download_image(image_url: str, destination: Path, max_retries: int = 3) -> Path:
|
||||
@@ -97,33 +92,12 @@ async def _download_image(image_url: str, destination: Path, max_retries: int =
|
||||
# Create parent directories if they don't exist
|
||||
destination.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
async def _ssrf_redirect_guard(response):
|
||||
"""Re-validate each redirect target to prevent redirect-based SSRF.
|
||||
|
||||
Without this, an attacker can host a public URL that 302-redirects
|
||||
to http://169.254.169.254/ and bypass the pre-flight is_safe_url check.
|
||||
|
||||
Must be async because httpx.AsyncClient awaits event hooks.
|
||||
"""
|
||||
if response.is_redirect and response.next_request:
|
||||
redirect_url = str(response.next_request.url)
|
||||
from tools.url_safety import is_safe_url
|
||||
if not is_safe_url(redirect_url):
|
||||
raise ValueError(
|
||||
f"Blocked redirect to private/internal address: {redirect_url}"
|
||||
)
|
||||
|
||||
last_error = None
|
||||
for attempt in range(max_retries):
|
||||
try:
|
||||
# Download the image with appropriate headers using async httpx
|
||||
# Enable follow_redirects to handle image CDNs that redirect (e.g., Imgur, Picsum)
|
||||
# SSRF: event_hooks validates each redirect target against private IP ranges
|
||||
async with httpx.AsyncClient(
|
||||
timeout=30.0,
|
||||
follow_redirects=True,
|
||||
event_hooks={"response": [_ssrf_redirect_guard]},
|
||||
) as client:
|
||||
async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
|
||||
response = await client.get(
|
||||
image_url,
|
||||
headers={
|
||||
@@ -325,9 +299,8 @@ async def vision_analyze_tool(
|
||||
logger.info("Processing image with vision model...")
|
||||
|
||||
# Call the vision API via centralized router.
|
||||
# Read timeout from config.yaml (auxiliary.vision.timeout), default 120s.
|
||||
# Local vision models (llama.cpp, ollama) can take well over 30s.
|
||||
vision_timeout = 120.0
|
||||
# Read timeout from config.yaml (auxiliary.vision.timeout), default 30s.
|
||||
vision_timeout = 30.0
|
||||
try:
|
||||
from hermes_cli.config import load_config
|
||||
_cfg = load_config()
|
||||
@@ -376,13 +349,6 @@ async def vision_analyze_tool(
|
||||
# so it can inform the user instead of a cryptic API error.
|
||||
err_str = str(e).lower()
|
||||
if any(hint in err_str for hint in (
|
||||
"402", "insufficient", "payment required", "credits", "billing",
|
||||
)):
|
||||
analysis = (
|
||||
"Insufficient credits or payment required. Please top up your "
|
||||
f"API provider account and try again. Error: {e}"
|
||||
)
|
||||
elif any(hint in err_str for hint in (
|
||||
"does not support", "not support image", "invalid_request",
|
||||
"content_policy", "image_url", "multimodal",
|
||||
"unrecognized request argument", "image input",
|
||||
|
||||
+118
-148
@@ -46,7 +46,6 @@ import httpx
|
||||
from firecrawl import Firecrawl
|
||||
from agent.auxiliary_client import async_call_llm
|
||||
from tools.debug_helpers import DebugSession
|
||||
from tools.url_safety import is_safe_url
|
||||
from tools.website_policy import check_website_access
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -862,155 +861,136 @@ async def web_extract_tool(
|
||||
try:
|
||||
logger.info("Extracting content from %d URL(s)", len(urls))
|
||||
|
||||
# ── SSRF protection — filter out private/internal URLs before any backend ──
|
||||
safe_urls = []
|
||||
ssrf_blocked: List[Dict[str, Any]] = []
|
||||
for url in urls:
|
||||
if not is_safe_url(url):
|
||||
ssrf_blocked.append({
|
||||
"url": url, "title": "", "content": "",
|
||||
"error": "Blocked: URL targets a private or internal network address",
|
||||
})
|
||||
else:
|
||||
safe_urls.append(url)
|
||||
# Dispatch to the configured backend
|
||||
backend = _get_backend()
|
||||
|
||||
# Dispatch only safe URLs to the configured backend
|
||||
if not safe_urls:
|
||||
results = []
|
||||
if backend == "parallel":
|
||||
results = await _parallel_extract(urls)
|
||||
elif backend == "tavily":
|
||||
logger.info("Tavily extract: %d URL(s)", len(urls))
|
||||
raw = _tavily_request("extract", {
|
||||
"urls": urls,
|
||||
"include_images": False,
|
||||
})
|
||||
results = _normalize_tavily_documents(raw, fallback_url=urls[0] if urls else "")
|
||||
else:
|
||||
backend = _get_backend()
|
||||
|
||||
if backend == "parallel":
|
||||
results = await _parallel_extract(safe_urls)
|
||||
elif backend == "tavily":
|
||||
logger.info("Tavily extract: %d URL(s)", len(safe_urls))
|
||||
raw = _tavily_request("extract", {
|
||||
"urls": safe_urls,
|
||||
"include_images": False,
|
||||
})
|
||||
results = _normalize_tavily_documents(raw, fallback_url=safe_urls[0] if safe_urls else "")
|
||||
# ── Firecrawl extraction ──
|
||||
# Determine requested formats for Firecrawl v2
|
||||
formats: List[str] = []
|
||||
if format == "markdown":
|
||||
formats = ["markdown"]
|
||||
elif format == "html":
|
||||
formats = ["html"]
|
||||
else:
|
||||
# ── Firecrawl extraction ──
|
||||
# Determine requested formats for Firecrawl v2
|
||||
formats: List[str] = []
|
||||
if format == "markdown":
|
||||
formats = ["markdown"]
|
||||
elif format == "html":
|
||||
formats = ["html"]
|
||||
else:
|
||||
# Default: request markdown for LLM-readiness and include html as backup
|
||||
formats = ["markdown", "html"]
|
||||
# Default: request markdown for LLM-readiness and include html as backup
|
||||
formats = ["markdown", "html"]
|
||||
|
||||
# Always use individual scraping for simplicity and reliability
|
||||
# Batch scraping adds complexity without much benefit for small numbers of URLs
|
||||
results: List[Dict[str, Any]] = []
|
||||
# Always use individual scraping for simplicity and reliability
|
||||
# Batch scraping adds complexity without much benefit for small numbers of URLs
|
||||
results: List[Dict[str, Any]] = []
|
||||
|
||||
from tools.interrupt import is_interrupted as _is_interrupted
|
||||
for url in safe_urls:
|
||||
if _is_interrupted():
|
||||
results.append({"url": url, "error": "Interrupted", "title": ""})
|
||||
continue
|
||||
from tools.interrupt import is_interrupted as _is_interrupted
|
||||
for url in urls:
|
||||
if _is_interrupted():
|
||||
results.append({"url": url, "error": "Interrupted", "title": ""})
|
||||
continue
|
||||
|
||||
# Website policy check — block before fetching
|
||||
blocked = check_website_access(url)
|
||||
if blocked:
|
||||
logger.info("Blocked web_extract for %s by rule %s", blocked["host"], blocked["rule"])
|
||||
# Website policy check — block before fetching
|
||||
blocked = check_website_access(url)
|
||||
if blocked:
|
||||
logger.info("Blocked web_extract for %s by rule %s", blocked["host"], blocked["rule"])
|
||||
results.append({
|
||||
"url": url, "title": "", "content": "",
|
||||
"error": blocked["message"],
|
||||
"blocked_by_policy": {"host": blocked["host"], "rule": blocked["rule"], "source": blocked["source"]},
|
||||
})
|
||||
continue
|
||||
|
||||
try:
|
||||
logger.info("Scraping: %s", url)
|
||||
scrape_result = _get_firecrawl_client().scrape(
|
||||
url=url,
|
||||
formats=formats
|
||||
)
|
||||
|
||||
# Process the result - properly handle object serialization
|
||||
metadata = {}
|
||||
title = ""
|
||||
content_markdown = None
|
||||
content_html = None
|
||||
|
||||
# Extract data from the scrape result
|
||||
if hasattr(scrape_result, 'model_dump'):
|
||||
# Pydantic model - use model_dump to get dict
|
||||
result_dict = scrape_result.model_dump()
|
||||
content_markdown = result_dict.get('markdown')
|
||||
content_html = result_dict.get('html')
|
||||
metadata = result_dict.get('metadata', {})
|
||||
elif hasattr(scrape_result, '__dict__'):
|
||||
# Regular object with attributes
|
||||
content_markdown = getattr(scrape_result, 'markdown', None)
|
||||
content_html = getattr(scrape_result, 'html', None)
|
||||
|
||||
# Handle metadata - convert to dict if it's an object
|
||||
metadata_obj = getattr(scrape_result, 'metadata', {})
|
||||
if hasattr(metadata_obj, 'model_dump'):
|
||||
metadata = metadata_obj.model_dump()
|
||||
elif hasattr(metadata_obj, '__dict__'):
|
||||
metadata = metadata_obj.__dict__
|
||||
elif isinstance(metadata_obj, dict):
|
||||
metadata = metadata_obj
|
||||
else:
|
||||
metadata = {}
|
||||
elif isinstance(scrape_result, dict):
|
||||
# Already a dictionary
|
||||
content_markdown = scrape_result.get('markdown')
|
||||
content_html = scrape_result.get('html')
|
||||
metadata = scrape_result.get('metadata', {})
|
||||
|
||||
# Ensure metadata is a dict (not an object)
|
||||
if not isinstance(metadata, dict):
|
||||
if hasattr(metadata, 'model_dump'):
|
||||
metadata = metadata.model_dump()
|
||||
elif hasattr(metadata, '__dict__'):
|
||||
metadata = metadata.__dict__
|
||||
else:
|
||||
metadata = {}
|
||||
|
||||
# Get title from metadata
|
||||
title = metadata.get("title", "")
|
||||
|
||||
# Re-check final URL after redirect
|
||||
final_url = metadata.get("sourceURL", url)
|
||||
final_blocked = check_website_access(final_url)
|
||||
if final_blocked:
|
||||
logger.info("Blocked redirected web_extract for %s by rule %s", final_blocked["host"], final_blocked["rule"])
|
||||
results.append({
|
||||
"url": url, "title": "", "content": "",
|
||||
"error": blocked["message"],
|
||||
"blocked_by_policy": {"host": blocked["host"], "rule": blocked["rule"], "source": blocked["source"]},
|
||||
"url": final_url, "title": title, "content": "", "raw_content": "",
|
||||
"error": final_blocked["message"],
|
||||
"blocked_by_policy": {"host": final_blocked["host"], "rule": final_blocked["rule"], "source": final_blocked["source"]},
|
||||
})
|
||||
continue
|
||||
|
||||
try:
|
||||
logger.info("Scraping: %s", url)
|
||||
scrape_result = _get_firecrawl_client().scrape(
|
||||
url=url,
|
||||
formats=formats
|
||||
)
|
||||
# Choose content based on requested format
|
||||
chosen_content = content_markdown if (format == "markdown" or (format is None and content_markdown)) else content_html or content_markdown or ""
|
||||
|
||||
# Process the result - properly handle object serialization
|
||||
metadata = {}
|
||||
title = ""
|
||||
content_markdown = None
|
||||
content_html = None
|
||||
results.append({
|
||||
"url": final_url,
|
||||
"title": title,
|
||||
"content": chosen_content,
|
||||
"raw_content": chosen_content,
|
||||
"metadata": metadata # Now guaranteed to be a dict
|
||||
})
|
||||
|
||||
# Extract data from the scrape result
|
||||
if hasattr(scrape_result, 'model_dump'):
|
||||
# Pydantic model - use model_dump to get dict
|
||||
result_dict = scrape_result.model_dump()
|
||||
content_markdown = result_dict.get('markdown')
|
||||
content_html = result_dict.get('html')
|
||||
metadata = result_dict.get('metadata', {})
|
||||
elif hasattr(scrape_result, '__dict__'):
|
||||
# Regular object with attributes
|
||||
content_markdown = getattr(scrape_result, 'markdown', None)
|
||||
content_html = getattr(scrape_result, 'html', None)
|
||||
|
||||
# Handle metadata - convert to dict if it's an object
|
||||
metadata_obj = getattr(scrape_result, 'metadata', {})
|
||||
if hasattr(metadata_obj, 'model_dump'):
|
||||
metadata = metadata_obj.model_dump()
|
||||
elif hasattr(metadata_obj, '__dict__'):
|
||||
metadata = metadata_obj.__dict__
|
||||
elif isinstance(metadata_obj, dict):
|
||||
metadata = metadata_obj
|
||||
else:
|
||||
metadata = {}
|
||||
elif isinstance(scrape_result, dict):
|
||||
# Already a dictionary
|
||||
content_markdown = scrape_result.get('markdown')
|
||||
content_html = scrape_result.get('html')
|
||||
metadata = scrape_result.get('metadata', {})
|
||||
|
||||
# Ensure metadata is a dict (not an object)
|
||||
if not isinstance(metadata, dict):
|
||||
if hasattr(metadata, 'model_dump'):
|
||||
metadata = metadata.model_dump()
|
||||
elif hasattr(metadata, '__dict__'):
|
||||
metadata = metadata.__dict__
|
||||
else:
|
||||
metadata = {}
|
||||
|
||||
# Get title from metadata
|
||||
title = metadata.get("title", "")
|
||||
|
||||
# Re-check final URL after redirect
|
||||
final_url = metadata.get("sourceURL", url)
|
||||
final_blocked = check_website_access(final_url)
|
||||
if final_blocked:
|
||||
logger.info("Blocked redirected web_extract for %s by rule %s", final_blocked["host"], final_blocked["rule"])
|
||||
results.append({
|
||||
"url": final_url, "title": title, "content": "", "raw_content": "",
|
||||
"error": final_blocked["message"],
|
||||
"blocked_by_policy": {"host": final_blocked["host"], "rule": final_blocked["rule"], "source": final_blocked["source"]},
|
||||
})
|
||||
continue
|
||||
|
||||
# Choose content based on requested format
|
||||
chosen_content = content_markdown if (format == "markdown" or (format is None and content_markdown)) else content_html or content_markdown or ""
|
||||
|
||||
results.append({
|
||||
"url": final_url,
|
||||
"title": title,
|
||||
"content": chosen_content,
|
||||
"raw_content": chosen_content,
|
||||
"metadata": metadata # Now guaranteed to be a dict
|
||||
})
|
||||
|
||||
except Exception as scrape_err:
|
||||
logger.debug("Scrape failed for %s: %s", url, scrape_err)
|
||||
results.append({
|
||||
"url": url,
|
||||
"title": "",
|
||||
"content": "",
|
||||
"raw_content": "",
|
||||
"error": str(scrape_err)
|
||||
})
|
||||
|
||||
# Merge any SSRF-blocked results back in
|
||||
if ssrf_blocked:
|
||||
results = ssrf_blocked + results
|
||||
except Exception as scrape_err:
|
||||
logger.debug("Scrape failed for %s: %s", url, scrape_err)
|
||||
results.append({
|
||||
"url": url,
|
||||
"title": "",
|
||||
"content": "",
|
||||
"raw_content": "",
|
||||
"error": str(scrape_err)
|
||||
})
|
||||
|
||||
response = {"results": results}
|
||||
|
||||
@@ -1193,11 +1173,6 @@ async def web_crawl_tool(
|
||||
if not url.startswith(('http://', 'https://')):
|
||||
url = f'https://{url}'
|
||||
|
||||
# SSRF protection — block private/internal addresses
|
||||
if not is_safe_url(url):
|
||||
return json.dumps({"results": [{"url": url, "title": "", "content": "",
|
||||
"error": "Blocked: URL targets a private or internal network address"}]}, ensure_ascii=False)
|
||||
|
||||
# Website policy check
|
||||
blocked = check_website_access(url)
|
||||
if blocked:
|
||||
@@ -1283,11 +1258,6 @@ async def web_crawl_tool(
|
||||
instructions_text = f" with instructions: '{instructions}'" if instructions else ""
|
||||
logger.info("Crawling %s%s", url, instructions_text)
|
||||
|
||||
# SSRF protection — block private/internal addresses
|
||||
if not is_safe_url(url):
|
||||
return json.dumps({"results": [{"url": url, "title": "", "content": "",
|
||||
"error": "Blocked: URL targets a private or internal network address"}]}, ensure_ascii=False)
|
||||
|
||||
# Website policy check — block before crawling
|
||||
blocked = check_website_access(url)
|
||||
if blocked:
|
||||
|
||||
@@ -75,9 +75,7 @@ Concurrent tool execution preserves message/result ordering when reinserting too
|
||||
- `reasoning_callback`
|
||||
- `clarify_callback`
|
||||
- `step_callback`
|
||||
- `stream_delta_callback`
|
||||
- `tool_gen_callback`
|
||||
- `status_callback`
|
||||
- `message_callback`
|
||||
|
||||
These are how the CLI, gateway, and ACP integrations stream intermediate progress and interactive approval/clarification flows.
|
||||
|
||||
|
||||
@@ -49,6 +49,7 @@ export VIRTUAL_ENV="$(pwd)/venv"
|
||||
|
||||
# Install with all extras (messaging, cron, CLI menus, dev tools)
|
||||
uv pip install -e ".[all,dev]"
|
||||
uv pip install -e "./mini-swe-agent"
|
||||
uv pip install -e "./tinker-atropos"
|
||||
|
||||
# Optional: browser tools
|
||||
|
||||
@@ -57,15 +57,6 @@ metadata:
|
||||
hermes:
|
||||
tags: [Category, Subcategory, Keywords]
|
||||
related_skills: [other-skill-name]
|
||||
requires_toolsets: [web] # Optional — only show when these toolsets are active
|
||||
requires_tools: [web_search] # Optional — only show when these tools are available
|
||||
fallback_for_toolsets: [browser] # Optional — hide when these toolsets are active
|
||||
fallback_for_tools: [browser_navigate] # Optional — hide when these tools exist
|
||||
required_environment_variables: # Optional — env vars the skill needs
|
||||
- name: MY_API_KEY
|
||||
prompt: "Enter your API key"
|
||||
help: "Get one at https://example.com"
|
||||
required_for: "API access"
|
||||
---
|
||||
|
||||
# Skill Title
|
||||
@@ -100,57 +91,6 @@ platforms: [windows] # Windows only
|
||||
|
||||
When set, the skill is automatically hidden from the system prompt, `skills_list()`, and slash commands on incompatible platforms. If omitted or empty, the skill loads on all platforms (backward compatible).
|
||||
|
||||
### Conditional Skill Activation
|
||||
|
||||
Skills can declare dependencies on specific tools or toolsets. This controls whether the skill appears in the system prompt for a given session.
|
||||
|
||||
```yaml
|
||||
metadata:
|
||||
hermes:
|
||||
requires_toolsets: [web] # Hide if the web toolset is NOT active
|
||||
requires_tools: [web_search] # Hide if web_search tool is NOT available
|
||||
fallback_for_toolsets: [browser] # Hide if the browser toolset IS active
|
||||
fallback_for_tools: [browser_navigate] # Hide if browser_navigate IS available
|
||||
```
|
||||
|
||||
| Field | Behavior |
|
||||
|-------|----------|
|
||||
| `requires_toolsets` | Skill is **hidden** when ANY listed toolset is **not** available |
|
||||
| `requires_tools` | Skill is **hidden** when ANY listed tool is **not** available |
|
||||
| `fallback_for_toolsets` | Skill is **hidden** when ANY listed toolset **is** available |
|
||||
| `fallback_for_tools` | Skill is **hidden** when ANY listed tool **is** available |
|
||||
|
||||
**Use case for `fallback_for_*`:** Create a skill that serves as a workaround when a primary tool isn't available. For example, a `duckduckgo-search` skill with `fallback_for_tools: [web_search]` only shows when the web search tool (which requires an API key) is not configured.
|
||||
|
||||
**Use case for `requires_*`:** Create a skill that only makes sense when certain tools are present. For example, a web scraping workflow skill with `requires_toolsets: [web]` won't clutter the prompt when web tools are disabled.
|
||||
|
||||
### Environment Variable Requirements
|
||||
|
||||
Skills can declare environment variables they need. When a skill is loaded via `skill_view`, its required vars are automatically registered for passthrough into sandboxed execution environments (terminal, execute_code).
|
||||
|
||||
```yaml
|
||||
required_environment_variables:
|
||||
- name: TENOR_API_KEY
|
||||
prompt: "Tenor API key" # Shown when prompting user
|
||||
help: "Get your key at https://tenor.com" # Help text or URL
|
||||
required_for: "GIF search functionality" # What needs this var
|
||||
```
|
||||
|
||||
Each entry supports:
|
||||
- `name` (required) — the environment variable name
|
||||
- `prompt` (optional) — prompt text when asking the user for the value
|
||||
- `help` (optional) — help text or URL for obtaining the value
|
||||
- `required_for` (optional) — describes which feature needs this variable
|
||||
|
||||
Users can also manually configure passthrough variables in `config.yaml`:
|
||||
|
||||
```yaml
|
||||
terminal:
|
||||
env_passthrough:
|
||||
- MY_CUSTOM_VAR
|
||||
- ANOTHER_VAR
|
||||
```
|
||||
|
||||
See `skills/apple/` for examples of macOS-only skills.
|
||||
|
||||
## Secure Setup on Load
|
||||
@@ -167,10 +107,6 @@ required_environment_variables:
|
||||
|
||||
The user can skip setup and keep loading the skill. Hermes never exposes the raw secret value to the model. Gateway and messaging sessions show local setup guidance instead of collecting secrets in-band.
|
||||
|
||||
:::tip Sandbox Passthrough
|
||||
When your skill is loaded, any declared `required_environment_variables` that are set are **automatically passed through** to `execute_code` and `terminal` sandboxes. Your skill's scripts can access `$TENOR_API_KEY` (or `os.environ["TENOR_API_KEY"]` in Python) without the user needing to configure anything extra. See [Environment Variable Passthrough](/docs/user-guide/security#environment-variable-passthrough) for details.
|
||||
:::
|
||||
|
||||
Legacy `prerequisites.env_vars` remains supported as a backward-compatible alias.
|
||||
|
||||
## Skill Guidelines
|
||||
|
||||
@@ -58,12 +58,11 @@ Local memory and user profile data are injected as frozen snapshots at session s
|
||||
|
||||
## Context files
|
||||
|
||||
`agent/prompt_builder.py` scans and sanitizes project context files using a **priority system** — only one type is loaded (first match wins):
|
||||
`agent/prompt_builder.py` scans and sanitizes:
|
||||
|
||||
1. `.hermes.md` / `HERMES.md` (walks to git root)
|
||||
2. `AGENTS.md` (recursive directory walk)
|
||||
3. `CLAUDE.md` (CWD only)
|
||||
4. `.cursorrules` / `.cursor/rules/*.mdc` (CWD only)
|
||||
- `AGENTS.md`
|
||||
- `.cursorrules`
|
||||
- `.cursor/rules/*.mdc`
|
||||
|
||||
`SOUL.md` is loaded separately via `load_soul_md()` for the identity slot. When it loads successfully, `build_context_files_prompt(skip_soul=True)` prevents it from appearing twice.
|
||||
|
||||
|
||||
@@ -16,10 +16,9 @@ Hermes has a shared provider runtime resolver used across:
|
||||
|
||||
Primary implementation:
|
||||
|
||||
- `hermes_cli/runtime_provider.py` — credential resolution, `_resolve_custom_runtime()`
|
||||
- `hermes_cli/auth.py` — provider registry, `resolve_provider()`
|
||||
- `hermes_cli/model_switch.py` — shared `/model` switch pipeline (CLI + gateway)
|
||||
- `agent/auxiliary_client.py` — auxiliary model routing
|
||||
- `hermes_cli/runtime_provider.py`
|
||||
- `hermes_cli/auth.py`
|
||||
- `agent/auxiliary_client.py`
|
||||
|
||||
If you are trying to add a new first-class inference provider, read [Adding Providers](./adding-providers.md) alongside this page.
|
||||
|
||||
@@ -47,8 +46,7 @@ Current provider families include:
|
||||
- Kimi / Moonshot
|
||||
- MiniMax
|
||||
- MiniMax China
|
||||
- Custom (`provider: custom`) — first-class provider for any OpenAI-compatible endpoint
|
||||
- Named custom providers (`custom_providers` list in config.yaml)
|
||||
- custom OpenAI-compatible endpoints
|
||||
|
||||
## Output of runtime resolution
|
||||
|
||||
|
||||
@@ -132,10 +132,13 @@ You can combine extras: `uv pip install -e ".[messaging,cron]"`
|
||||
|
||||
</details>
|
||||
|
||||
### Step 4: Install Optional Submodules (if needed)
|
||||
### Step 4: Install Submodule Packages
|
||||
|
||||
```bash
|
||||
# RL training backend (optional)
|
||||
# Terminal tool backend (required for terminal/command-execution)
|
||||
uv pip install -e "./mini-swe-agent"
|
||||
|
||||
# RL training backend
|
||||
uv pip install -e "./tinker-atropos"
|
||||
```
|
||||
|
||||
@@ -235,6 +238,7 @@ export VIRTUAL_ENV="$(pwd)/venv"
|
||||
|
||||
# Install everything
|
||||
uv pip install -e ".[all]"
|
||||
uv pip install -e "./mini-swe-agent"
|
||||
uv pip install -e "./tinker-atropos"
|
||||
npm install # optional, for browser tools and WhatsApp
|
||||
|
||||
|
||||
@@ -139,7 +139,7 @@ hermes gateway setup # Interactive platform configuration
|
||||
Want microphone input in the CLI or spoken replies in messaging?
|
||||
|
||||
```bash
|
||||
pip install "hermes-agent[voice]"
|
||||
pip install hermes-agent[voice]
|
||||
|
||||
# Optional but recommended for free local speech-to-text
|
||||
pip install faster-whisper
|
||||
|
||||
@@ -44,6 +44,7 @@ git submodule update --init --recursive
|
||||
|
||||
# Reinstall (picks up new dependencies)
|
||||
uv pip install -e ".[all]"
|
||||
uv pip install -e "./mini-swe-agent"
|
||||
uv pip install -e "./tinker-atropos"
|
||||
|
||||
# Check for new config options
|
||||
|
||||
@@ -29,14 +29,12 @@ Create `plugin.yaml`:
|
||||
name: calculator
|
||||
version: 1.0.0
|
||||
description: Math calculator — evaluate expressions and convert units
|
||||
provides_tools:
|
||||
- calculate
|
||||
- unit_convert
|
||||
provides_hooks:
|
||||
- post_tool_call
|
||||
provides:
|
||||
tools: true
|
||||
hooks: true
|
||||
```
|
||||
|
||||
This tells Hermes: "I'm a plugin called calculator, I provide tools and hooks." The `provides_tools` and `provides_hooks` fields are lists of what the plugin registers.
|
||||
This tells Hermes: "I'm a plugin called calculator, I provide tools and hooks." That's all the manifest needs.
|
||||
|
||||
Optional fields you could add:
|
||||
```yaml
|
||||
@@ -234,7 +232,7 @@ def register(ctx):
|
||||
- Called exactly once at startup
|
||||
- `ctx.register_tool()` puts your tool in the registry — the model sees it immediately
|
||||
- `ctx.register_hook()` subscribes to lifecycle events
|
||||
- `ctx.register_command()` — _planned but not yet implemented_
|
||||
- `ctx.register_command()` adds a slash command to `/help`, autocomplete, and gateway dispatch
|
||||
- If this function crashes, the plugin is disabled but Hermes continues fine
|
||||
|
||||
## Step 6: Test it
|
||||
|
||||
@@ -170,7 +170,7 @@ Instead of manually collecting user IDs for allowlists, enable DM pairing. When
|
||||
Use `/verbose` to control how much tool activity you see. In messaging platforms, less is usually more — keep it on "new" to see just new tool calls. In the CLI, "all" gives you a satisfying live view of everything the agent does.
|
||||
|
||||
:::tip
|
||||
On messaging platforms, sessions auto-reset after idle time (default: 24 hours) or daily at 4 AM. Adjust per-platform in `~/.hermes/config.yaml` if you need longer sessions.
|
||||
On messaging platforms, sessions auto-reset after idle time (default: 120 min) or daily at 4 AM. Adjust per-platform in `~/.hermes/gateway.json` if you need longer sessions.
|
||||
:::
|
||||
|
||||
## Security
|
||||
|
||||
@@ -57,19 +57,19 @@ If that is not solid yet, fix text mode first.
|
||||
### CLI microphone + playback
|
||||
|
||||
```bash
|
||||
pip install "hermes-agent[voice]"
|
||||
pip install hermes-agent[voice]
|
||||
```
|
||||
|
||||
### Messaging platforms
|
||||
|
||||
```bash
|
||||
pip install "hermes-agent[messaging]"
|
||||
pip install hermes-agent[messaging]
|
||||
```
|
||||
|
||||
### Premium ElevenLabs TTS
|
||||
|
||||
```bash
|
||||
pip install "hermes-agent[tts-premium]"
|
||||
pip install hermes-agent[tts-premium]
|
||||
```
|
||||
|
||||
### Local NeuTTS (optional)
|
||||
@@ -81,7 +81,7 @@ python -m pip install -U neutts[all]
|
||||
### Everything
|
||||
|
||||
```bash
|
||||
pip install "hermes-agent[all]"
|
||||
pip install hermes-agent[all]
|
||||
```
|
||||
|
||||
## Step 3: install system dependencies
|
||||
|
||||
@@ -66,8 +66,7 @@ Common options:
|
||||
| `-q`, `--query "..."` | One-shot, non-interactive prompt. |
|
||||
| `-m`, `--model <model>` | Override the model for this run. |
|
||||
| `-t`, `--toolsets <csv>` | Enable a comma-separated set of toolsets. |
|
||||
| `--provider <provider>` | Force a provider: `auto`, `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `kilocode`. |
|
||||
| `-s`, `--skills <name>` | Preload one or more skills for the session (can be repeated or comma-separated). |
|
||||
| `--provider <provider>` | Force a provider: `auto`, `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `opencode-zen`, `opencode-go`, `ai-gateway`, `kilocode`, `alibaba`. |
|
||||
| `-v`, `--verbose` | Verbose output. |
|
||||
| `-Q`, `--quiet` | Programmatic mode: suppress banner/spinner/tool previews. |
|
||||
| `--resume <session>` / `--continue [name]` | Resume a session directly from `chat`. |
|
||||
@@ -99,25 +98,8 @@ Use this when you want to:
|
||||
- switch default providers
|
||||
- log into OAuth-backed providers during model selection
|
||||
- pick from provider-specific model lists
|
||||
- configure a custom/self-hosted endpoint
|
||||
- save the new default into config
|
||||
|
||||
### `/model` slash command (mid-session)
|
||||
|
||||
Switch models without leaving a session:
|
||||
|
||||
```
|
||||
/model # Show current model and available options
|
||||
/model claude-sonnet-4 # Switch model (auto-detects provider)
|
||||
/model zai:glm-5 # Switch provider and model
|
||||
/model custom:qwen-2.5 # Use model on your custom endpoint
|
||||
/model custom # Auto-detect model from custom endpoint
|
||||
/model custom:local:qwen-2.5 # Use a named custom provider
|
||||
/model openrouter:anthropic/claude-sonnet-4 # Switch back to cloud
|
||||
```
|
||||
|
||||
Provider and base URL changes are persisted to `config.yaml` automatically. When switching away from a custom endpoint, the stale base URL is cleared to prevent it leaking into other providers.
|
||||
|
||||
## `hermes gateway`
|
||||
|
||||
```bash
|
||||
@@ -344,41 +326,6 @@ pip install -e '.[acp]'
|
||||
|
||||
See [ACP Editor Integration](../user-guide/features/acp.md) and [ACP Internals](../developer-guide/acp-internals.md).
|
||||
|
||||
## `hermes mcp`
|
||||
|
||||
```bash
|
||||
hermes mcp <subcommand>
|
||||
```
|
||||
|
||||
Manage MCP (Model Context Protocol) server configurations.
|
||||
|
||||
| Subcommand | Description |
|
||||
|------------|-------------|
|
||||
| `add <name> [--url URL] [--command CMD] [--args ...] [--auth oauth\|header]` | Add an MCP server with automatic tool discovery. |
|
||||
| `remove <name>` (alias: `rm`) | Remove an MCP server from config. |
|
||||
| `list` (alias: `ls`) | List configured MCP servers. |
|
||||
| `test <name>` | Test connection to an MCP server. |
|
||||
| `configure <name>` (alias: `config`) | Toggle tool selection for a server. |
|
||||
|
||||
See [MCP Config Reference](./mcp-config-reference.md) and [Use MCP with Hermes](../guides/use-mcp-with-hermes.md).
|
||||
|
||||
## `hermes plugins`
|
||||
|
||||
```bash
|
||||
hermes plugins <subcommand>
|
||||
```
|
||||
|
||||
Manage Hermes Agent plugins.
|
||||
|
||||
| Subcommand | Description |
|
||||
|------------|-------------|
|
||||
| `install <identifier> [--force]` | Install a plugin from a Git URL or `owner/repo`. |
|
||||
| `update <name>` | Pull latest changes for an installed plugin. |
|
||||
| `remove <name>` (aliases: `rm`, `uninstall`) | Remove an installed plugin. |
|
||||
| `list` (alias: `ls`) | List installed plugins. |
|
||||
|
||||
See [Plugins](../user-guide/features/plugins.md) and [Build a Hermes Plugin](../guides/build-a-hermes-plugin.md).
|
||||
|
||||
## `hermes tools`
|
||||
|
||||
```bash
|
||||
|
||||
@@ -61,7 +61,7 @@ For native Anthropic auth, Hermes prefers Claude Code's own credential files whe
|
||||
|
||||
| Variable | Description |
|
||||
|----------|-------------|
|
||||
| `HERMES_INFERENCE_PROVIDER` | Override provider selection: `auto`, `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `kilocode` (default: `auto`) |
|
||||
| `HERMES_INFERENCE_PROVIDER` | Override provider selection: `auto`, `openrouter`, `nous`, `openai-codex`, `copilot`, `anthropic`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `kilocode`, `alibaba` (default: `auto`) |
|
||||
| `HERMES_PORTAL_BASE_URL` | Override Nous Portal URL (for development/testing) |
|
||||
| `NOUS_INFERENCE_BASE_URL` | Override Nous inference API URL |
|
||||
| `HERMES_NOUS_MIN_KEY_TTL_SECONDS` | Min agent key TTL before re-mint (default: 1800 = 30min) |
|
||||
|
||||
@@ -53,16 +53,7 @@ hermes model
|
||||
# Context length: 32768 ← set this to match your server's actual context window
|
||||
```
|
||||
|
||||
Or configure it directly in `config.yaml`:
|
||||
|
||||
```yaml
|
||||
model:
|
||||
default: qwen3.5:27b
|
||||
provider: custom
|
||||
base_url: http://localhost:11434/v1
|
||||
```
|
||||
|
||||
Hermes persists the endpoint, provider, and base URL in `config.yaml` so it survives restarts. If your local server has exactly one model loaded, `/model custom` auto-detects it. You can also set `provider: custom` in config.yaml — it's a first-class provider, not an alias for anything else.
|
||||
Hermes persists the endpoint in `config.yaml` and prompts for the context window size so compression triggers at the right time. If you leave context length blank, Hermes auto-detects it from the server's `/models` endpoint or [models.dev](https://models.dev).
|
||||
|
||||
This works with Ollama, vLLM, llama.cpp server, SGLang, LocalAI, and others. See the [Configuration guide](../user-guide/configuration.md) for details.
|
||||
|
||||
@@ -93,7 +84,7 @@ Yes. Import the `AIAgent` class and use Hermes programmatically:
|
||||
from hermes.agent import AIAgent
|
||||
|
||||
agent = AIAgent(model="openrouter/nous/hermes-3-llama-3.1-70b")
|
||||
response = agent.chat("Explain quantum computing briefly")
|
||||
response = await agent.chat("Explain quantum computing briefly")
|
||||
```
|
||||
|
||||
See the [Python Library guide](../user-guide/features/code-execution.md) for full API usage.
|
||||
@@ -175,8 +166,8 @@ curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scri
|
||||
|
||||
**Solution:**
|
||||
```bash
|
||||
# Check your configuration
|
||||
hermes config show
|
||||
# Check which keys are set
|
||||
hermes config get OPENROUTER_API_KEY
|
||||
|
||||
# Re-configure your provider
|
||||
hermes model
|
||||
@@ -196,7 +187,7 @@ Make sure the key matches the provider. An OpenAI key won't work with OpenRouter
|
||||
**Solution:**
|
||||
```bash
|
||||
# List available models for your provider
|
||||
hermes model
|
||||
hermes models
|
||||
|
||||
# Set a valid model
|
||||
hermes config set HERMES_MODEL openrouter/nous/hermes-3-llama-3.1-70b
|
||||
@@ -232,7 +223,10 @@ hermes chat --model openrouter/google/gemini-2.0-flash-001
|
||||
|
||||
If this happens on the first long conversation, Hermes may have the wrong context length for your model. Check what it detected:
|
||||
|
||||
Look at the CLI startup line — it shows the detected context length (e.g., `📊 Context limit: 128000 tokens`). You can also check with `/usage` during a session.
|
||||
```bash
|
||||
# Look at the status bar — it shows the detected context length
|
||||
/context
|
||||
```
|
||||
|
||||
To fix context detection, set it explicitly:
|
||||
|
||||
@@ -315,7 +309,7 @@ hermes gateway status
|
||||
hermes gateway start
|
||||
|
||||
# Check logs for errors
|
||||
cat ~/.hermes/logs/gateway.log | tail -50
|
||||
hermes gateway logs
|
||||
```
|
||||
|
||||
#### Messages not delivering
|
||||
@@ -324,7 +318,7 @@ cat ~/.hermes/logs/gateway.log | tail -50
|
||||
|
||||
**Solution:**
|
||||
- Verify your bot token is valid with `hermes gateway setup`
|
||||
- Check gateway logs: `cat ~/.hermes/logs/gateway.log | tail -50`
|
||||
- Check gateway logs: `hermes gateway logs`
|
||||
- For webhook-based platforms (Slack, WhatsApp), ensure your server is publicly accessible
|
||||
|
||||
#### Allowlist confusion — who can talk to the bot?
|
||||
@@ -348,7 +342,7 @@ Configure in `~/.hermes/config.yaml` under your gateway's settings. See the [Mes
|
||||
**Solution:**
|
||||
```bash
|
||||
# Install messaging dependencies
|
||||
pip install "hermes-agent[telegram]" # or [discord], [slack], [whatsapp]
|
||||
pip install hermes-agent[telegram] # or [discord], [slack], [whatsapp]
|
||||
|
||||
# Check for port conflicts
|
||||
lsof -i :8080
|
||||
@@ -380,8 +374,8 @@ hermes config show
|
||||
# Compress the conversation to reduce tokens
|
||||
/compress
|
||||
|
||||
# Check session token usage
|
||||
/usage
|
||||
# Check session token count
|
||||
/stats
|
||||
```
|
||||
|
||||
:::tip
|
||||
|
||||
@@ -18,16 +18,8 @@ Official optional skills live in the repository under `optional-skills/`. Instal
|
||||
|
||||
| Skill | Description | Path |
|
||||
|-------|-------------|------|
|
||||
| `base` | Query Base (Ethereum L2) blockchain data with USD pricing — wallet balances, token info, transaction details, gas analysis, contract inspection. | `blockchain/base` |
|
||||
| `solana` | Query Solana blockchain data with USD pricing — wallet balances, token portfolios with values, transaction details, NFTs, whale detection, and live network stats. Uses Solana RPC + CoinGecko. No API key required. | `blockchain/solana` |
|
||||
|
||||
## creative
|
||||
|
||||
| Skill | Description | Path |
|
||||
|-------|-------------|------|
|
||||
| `blender-mcp` | Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python. | `creative/blender-mcp` |
|
||||
| `meme-generation` | Generate real meme images by picking a template and overlaying text with Pillow. Produces actual .png meme files. | `creative/meme-generation` |
|
||||
|
||||
## email
|
||||
|
||||
| Skill | Description | Path |
|
||||
@@ -40,29 +32,16 @@ Official optional skills live in the repository under `optional-skills/`. Instal
|
||||
|-------|-------------|------|
|
||||
| `neuroskill-bci` | Connect to a running NeuroSkill instance and incorporate the user's real-time cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness, heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses. Requires a BCI wearable (Muse 2/S or Open… | `health/neuroskill-bci` |
|
||||
|
||||
## mcp
|
||||
|
||||
| Skill | Description | Path |
|
||||
|-------|-------------|------|
|
||||
| `fastmcp` | Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. | `mcp/fastmcp` |
|
||||
|
||||
## migration
|
||||
|
||||
| Skill | Description | Path |
|
||||
|-------|-------------|------|
|
||||
| `openclaw-migration` | Migrate a user's OpenClaw customization footprint into Hermes Agent. Imports Hermes-compatible memories, SOUL.md, command allowlists, user skills, and selected workspace assets from ~/.openclaw, then reports exactly what could not be migrated and why. | `migration/openclaw-migration` |
|
||||
|
||||
## productivity
|
||||
|
||||
| Skill | Description | Path |
|
||||
|-------|-------------|------|
|
||||
| `telephony` | Give Hermes phone capabilities — provision a Twilio number, send/receive SMS/MMS, make direct calls, and place AI-driven outbound calls through Bland.ai or Vapi. | `productivity/telephony` |
|
||||
|
||||
## research
|
||||
|
||||
| Skill | Description | Path |
|
||||
|-------|-------------|------|
|
||||
| `bioinformatics` | Gateway to 400+ bioinformatics skills from bioSkills and ClawBio. Covers genomics, transcriptomics, single-cell, variant calling, pharmacogenomics, metagenomics, structural biology. | `research/bioinformatics` |
|
||||
| `qmd` | Search personal knowledge bases, notes, docs, and meeting transcripts locally using qmd — a hybrid retrieval engine with BM25, vector search, and LLM reranking. Supports CLI and MCP integration. | `research/qmd` |
|
||||
|
||||
## security
|
||||
@@ -70,5 +49,3 @@ Official optional skills live in the repository under `optional-skills/`. Instal
|
||||
| Skill | Description | Path |
|
||||
|-------|-------------|------|
|
||||
| `1password` | Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in, and reading/injecting secrets for commands. | `security/1password` |
|
||||
| `oss-forensics` | Supply chain investigation, evidence recovery, and forensic analysis for GitHub repositories. Covers deleted commit recovery, force-push detection, IOC extraction. | `security/oss-forensics` |
|
||||
| `sherlock` | OSINT username search across 400+ social networks. Hunt down social media accounts by username. | `security/sherlock` |
|
||||
|
||||
@@ -30,14 +30,6 @@ Skills for spawning and orchestrating autonomous AI coding agents and multi-agen
|
||||
| `hermes-agent-spawning` | Spawn additional Hermes Agent instances as autonomous subprocesses for independent long-running tasks. Supports non-interactive one-shot mode (-q) and interactive PTY mode for multi-turn collaboration. Different from delegate_task — this runs a full separate hermes process. | `autonomous-ai-agents/hermes-agent` |
|
||||
| `opencode` | Delegate coding tasks to OpenCode CLI agent for feature implementation, refactoring, PR review, and long-running autonomous sessions. Requires the opencode CLI installed and authenticated. | `autonomous-ai-agents/opencode` |
|
||||
|
||||
## data-science
|
||||
|
||||
Skills for data science workflows — interactive exploration, Jupyter notebooks, data analysis, and visualization.
|
||||
|
||||
| Skill | Description | Path |
|
||||
|-------|-------------|------|
|
||||
| `jupyter-live-kernel` | Use a live Jupyter kernel for stateful, iterative Python execution via hamelnb. Load this skill when the task involves exploration, iteration, or inspecting intermediate results. | `data-science/jupyter-live-kernel` |
|
||||
|
||||
## creative
|
||||
|
||||
Creative content generation — ASCII art, hand-drawn style diagrams, and visual design tools.
|
||||
@@ -52,8 +44,7 @@ Creative content generation — ASCII art, hand-drawn style diagrams, and visual
|
||||
|
||||
| Skill | Description | Path |
|
||||
|-------|-------------|------|
|
||||
| `dogfood` | Systematic exploratory QA testing of web applications — find bugs, capture evidence, and generate structured reports. | `dogfood/dogfood` |
|
||||
| `hermes-agent-setup` | Help users configure Hermes Agent — CLI usage, setup wizard, model/provider selection, tools, skills, voice/STT/TTS, gateway, and troubleshooting. | `dogfood/hermes-agent-setup` |
|
||||
| `dogfood` | Systematic exploratory QA testing of web applications — find bugs, capture evidence, and generate structured reports | `dogfood` |
|
||||
|
||||
## email
|
||||
|
||||
@@ -85,14 +76,6 @@ GitHub workflow skills for managing repositories, pull requests, code reviews, i
|
||||
| `github-pr-workflow` | Full pull request lifecycle — create branches, commit changes, open PRs, monitor CI status, auto-fix failures, and merge. Works with gh CLI or falls back to git + GitHub REST API via curl. | `github/github-pr-workflow` |
|
||||
| `github-repo-management` | Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl. | `github/github-repo-management` |
|
||||
|
||||
## inference-sh
|
||||
|
||||
Skills for AI app execution via inference.sh cloud platform.
|
||||
|
||||
| Skill | Description | Path |
|
||||
|-------|-------------|------|
|
||||
| `inference-sh-cli` | Run 150+ AI apps via inference.sh CLI (infsh) — image generation, video creation, LLMs, search, 3D, social automation. | `inference-sh/cli` |
|
||||
|
||||
## leisure
|
||||
|
||||
| Skill | Description | Path |
|
||||
@@ -119,14 +102,6 @@ Skills for working with media content — YouTube transcripts, GIF search, music
|
||||
| `songsee` | Generate spectrograms and audio feature visualizations (mel, chroma, MFCC, tempogram, etc.) from audio files via CLI. Useful for audio analysis, music production debugging, and visual documentation. | `media/songsee` |
|
||||
| `youtube-content` | Fetch YouTube video transcripts and transform them into structured content (chapters, summaries, threads, blog posts). | `media/youtube-content` |
|
||||
|
||||
## mlops
|
||||
|
||||
General-purpose ML operations tools — model hub management, dataset operations, and workflow orchestration.
|
||||
|
||||
| Skill | Description | Path |
|
||||
|-------|-------------|------|
|
||||
| `huggingface-hub` | Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, deploy inference endpoints. | `mlops/huggingface-hub` |
|
||||
|
||||
## mlops/cloud
|
||||
|
||||
GPU cloud providers and serverless compute platforms for ML workloads.
|
||||
@@ -230,7 +205,6 @@ Skills for document creation, presentations, spreadsheets, and other productivit
|
||||
| Skill | Description | Path |
|
||||
|-------|-------------|------|
|
||||
| `google-workspace` | Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration via Python. Uses OAuth2 with automatic token refresh. No external binaries needed — runs entirely with Google's Python client libraries in the Hermes venv. | `productivity/google-workspace` |
|
||||
| `linear` | Manage Linear issues, projects, and teams via the GraphQL API. Create, update, search, and organize issues. | `productivity/linear` |
|
||||
| `nano-pdf` | Edit PDFs with natural-language instructions using the nano-pdf CLI. Modify text, fix typos, update titles, and make content changes to specific pages without manual editing. | `productivity/nano-pdf` |
|
||||
| `notion` | Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal. | `productivity/notion` |
|
||||
| `ocr-and-documents` | Extract text from PDFs and scanned documents. Use web_extract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill. | `productivity/ocr-and-documents` |
|
||||
@@ -246,7 +220,6 @@ Skills for academic research, paper discovery, literature review, domain reconna
|
||||
| `blogwatcher` | Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI. Add blogs, scan for new articles, and track what you've read. | `research/blogwatcher` |
|
||||
| `domain-intel` | Passive domain reconnaissance using Python stdlib. Subdomain discovery, SSL certificate inspection, WHOIS lookups, DNS records, domain availability checks, and bulk multi-domain analysis. No API keys required. | `research/domain-intel` |
|
||||
| `duckduckgo-search` | Free web search via DuckDuckGo — text, news, images, videos. No API key needed. Use the Python DDGS library or CLI to search, then web_extract for full content. | `research/duckduckgo-search` |
|
||||
| `parallel-cli` | Optional vendor skill for Parallel CLI — agent-native web search, extraction, deep research, enrichment, FindAll, and monitoring. | `research/parallel-cli` |
|
||||
| `ml-paper-writing` | Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verificatio… | `research/ml-paper-writing` |
|
||||
| `polymarket` | Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed. | `research/polymarket` |
|
||||
|
||||
@@ -258,14 +231,6 @@ Skills for controlling smart home devices — lights, switches, sensors, and hom
|
||||
|-------|-------------|------|
|
||||
| `openhue` | Control Philips Hue lights, rooms, and scenes via the OpenHue CLI. Turn lights on/off, adjust brightness, color, color temperature, and activate scenes. | `smart-home/openhue` |
|
||||
|
||||
## social-media
|
||||
|
||||
Skills for interacting with social platforms — posting, reading, monitoring, and account operations.
|
||||
|
||||
| Skill | Description | Path |
|
||||
|-------|-------------|------|
|
||||
| `xitter` | Interact with X/Twitter via the x-cli terminal client using official X API credentials. | `social-media/xitter` |
|
||||
|
||||
## software-development
|
||||
|
||||
| Skill | Description | Path |
|
||||
|
||||
@@ -31,8 +31,6 @@ Type `/` in the CLI to open the autocomplete menu. Built-in commands are case-in
|
||||
| `/compress` | Manually compress conversation context (flush memories + summarize) |
|
||||
| `/rollback` | List or restore filesystem checkpoints (usage: /rollback [number]) |
|
||||
| `/stop` | Kill all running background processes |
|
||||
| `/queue <prompt>` (alias: `/q`) | Queue a prompt for the next turn (doesn't interrupt the current agent response) |
|
||||
| `/resume [name]` | Resume a previously-named session |
|
||||
| `/statusbar` (alias: `/sb`) | Toggle the context/model status bar on or off |
|
||||
| `/background <prompt>` | Run a prompt in a separate background session. The agent processes your prompt independently — your current session stays free for other work. Results appear as a panel when the task finishes. See [CLI Background Sessions](/docs/user-guide/cli#background-sessions). |
|
||||
| `/plan [request]` | Load the bundled `plan` skill to write a markdown plan instead of executing the work. Plans are saved under `.hermes/plans/` relative to the active workspace/backend working directory. |
|
||||
@@ -42,7 +40,7 @@ Type `/` in the CLI to open the autocomplete menu. Built-in commands are case-in
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `/config` | Show current configuration |
|
||||
| `/model [model-name]` | Show or change the current model. Supports: `/model claude-sonnet-4`, `/model provider:model` (switch providers), `/model custom:model` (custom endpoint), `/model custom:name:model` (named custom provider), `/model custom` (auto-detect from endpoint) |
|
||||
| `/model` | Show or change the current model |
|
||||
| `/provider` | Show available providers and current provider |
|
||||
| `/prompt` | View/set custom system prompt |
|
||||
| `/personality` | Set a predefined personality |
|
||||
@@ -100,7 +98,7 @@ The messaging gateway supports the following built-in commands inside Telegram,
|
||||
| `/reset` | Reset conversation history. |
|
||||
| `/status` | Show session info. |
|
||||
| `/stop` | Kill all running background processes and interrupt the running agent. |
|
||||
| `/model [provider:model]` | Show or change the model. Supports provider switches (`/model zai:glm-5`), custom endpoints (`/model custom:model`), named custom providers (`/model custom:local:qwen`), and auto-detect (`/model custom`). |
|
||||
| `/model [provider:model]` | Show or change the model, including provider switches. |
|
||||
| `/provider` | Show provider availability and auth status. |
|
||||
| `/personality [name]` | Set a personality overlay for the session. |
|
||||
| `/retry` | Retry the last message. |
|
||||
@@ -117,7 +115,7 @@ The messaging gateway supports the following built-in commands inside Telegram,
|
||||
| `/background <prompt>` | Run a prompt in a separate background session. Results are delivered back to the same chat when the task finishes. See [Messaging Background Sessions](/docs/user-guide/messaging/#background-sessions). |
|
||||
| `/plan [request]` | Load the bundled `plan` skill to write a markdown plan instead of executing the work. Plans are saved under `.hermes/plans/` relative to the active workspace/backend working directory. |
|
||||
| `/reload-mcp` | Reload MCP servers from config. |
|
||||
| `/approve [session\|always]` | Approve and execute a pending dangerous command. `session` approves for this session only; `always` adds to permanent allowlist. |
|
||||
| `/approve` | Approve and execute a pending dangerous command (terminal commands flagged for review). |
|
||||
| `/deny` | Reject a pending dangerous command. |
|
||||
| `/update` | Update Hermes Agent to the latest version. |
|
||||
| `/help` | Show messaging help. |
|
||||
|
||||
@@ -160,4 +160,15 @@ This page documents the built-in Hermes tool registry as it exists in code. Avai
|
||||
|------|-------------|----------------------|
|
||||
| `text_to_speech` | Convert text to speech audio. Returns a MEDIA: path that the platform delivers as a voice message. On Telegram it plays as a voice bubble, on Discord/WhatsApp as an audio attachment. In CLI mode, saves to ~/voice-memos/. Voice and provider… | — |
|
||||
|
||||
## `vision` toolset
|
||||
|
||||
| Tool | Description | Requires environment |
|
||||
|------|-------------|----------------------|
|
||||
| `vision_analyze` | Analyze images using AI vision. Provides a comprehensive description and answers a specific question about the image content. | — |
|
||||
|
||||
## `web` toolset
|
||||
|
||||
| Tool | Description | Requires environment |
|
||||
|------|-------------|----------------------|
|
||||
| `web_extract` | Extract content from web page URLs. Returns page content in markdown format. Also works with PDF URLs (arxiv papers, documents, etc.) — pass the PDF link directly and it converts to markdown text. Pages under 5000 chars return full markdow… | FIRECRAWL_API_KEY |
|
||||
| `web_search` | Search the web for information on any topic. Returns up to 5 relevant results with titles, URLs, and descriptions. | FIRECRAWL_API_KEY |
|
||||
|
||||
@@ -179,11 +179,12 @@ Built-in personalities include: `helpful`, `concise`, `technical`, `creative`, `
|
||||
You can also define custom personalities in `~/.hermes/config.yaml`:
|
||||
|
||||
```yaml
|
||||
personalities:
|
||||
helpful: "You are a helpful, friendly AI assistant."
|
||||
kawaii: "You are a kawaii assistant! Use cute expressions..."
|
||||
pirate: "Arrr! Ye be talkin' to Captain Hermes..."
|
||||
# Add your own!
|
||||
agent:
|
||||
personalities:
|
||||
helpful: "You are a helpful, friendly AI assistant."
|
||||
kawaii: "You are a kawaii assistant! Use cute expressions..."
|
||||
pirate: "Arrr! Ye be talkin' to Captain Hermes..."
|
||||
# Add your own!
|
||||
```
|
||||
|
||||
## Multi-line Input
|
||||
|
||||
@@ -55,22 +55,6 @@ Settings are resolved in this order (highest priority first):
|
||||
Secrets (API keys, bot tokens, passwords) go in `.env`. Everything else (model, terminal backend, compression settings, memory limits, toolsets) goes in `config.yaml`. When both are set, `config.yaml` wins for non-secret settings.
|
||||
:::
|
||||
|
||||
## Environment Variable Substitution
|
||||
|
||||
You can reference environment variables in `config.yaml` using `${VAR_NAME}` syntax:
|
||||
|
||||
```yaml
|
||||
auxiliary:
|
||||
vision:
|
||||
api_key: ${GOOGLE_API_KEY}
|
||||
base_url: ${CUSTOM_VISION_URL}
|
||||
|
||||
delegation:
|
||||
api_key: ${DELEGATION_KEY}
|
||||
```
|
||||
|
||||
Multiple references in a single value work: `url: "${HOST}:${PORT}"`. If a referenced variable is not set, the placeholder is kept verbatim (`${UNDEFINED_VAR}` stays as-is). Only the `${VAR}` syntax is supported — bare `$VAR` is not expanded.
|
||||
|
||||
## Inference Providers
|
||||
|
||||
You need at least one way to connect to an LLM. Use `hermes model` to switch providers and models interactively, or configure directly:
|
||||
@@ -230,57 +214,24 @@ Hermes Agent works with **any OpenAI-compatible API endpoint**. If a server impl
|
||||
|
||||
### General Setup
|
||||
|
||||
Three ways to configure a custom endpoint:
|
||||
Two ways to configure a custom endpoint:
|
||||
|
||||
**Interactive setup (recommended):**
|
||||
**Interactive (recommended):**
|
||||
```bash
|
||||
hermes model
|
||||
# Select "Custom endpoint (self-hosted / VLLM / etc.)"
|
||||
# Enter: API base URL, API key, Model name
|
||||
```
|
||||
|
||||
**Manual config (`config.yaml`):**
|
||||
```yaml
|
||||
# In ~/.hermes/config.yaml
|
||||
model:
|
||||
default: your-model-name
|
||||
provider: custom
|
||||
base_url: http://localhost:8000/v1
|
||||
api_key: your-key-or-leave-empty-for-local
|
||||
```
|
||||
|
||||
**Environment variables (`.env` file):**
|
||||
**Manual (`.env` file):**
|
||||
```bash
|
||||
# Add to ~/.hermes/.env
|
||||
OPENAI_BASE_URL=http://localhost:8000/v1
|
||||
OPENAI_API_KEY=your-key # Any non-empty string for local servers
|
||||
OPENAI_API_KEY=***
|
||||
LLM_MODEL=your-model-name
|
||||
```
|
||||
|
||||
All three approaches end up in the same runtime path. `hermes model` persists provider, model, and base URL to `config.yaml` so later sessions keep using that endpoint even if env vars are not set.
|
||||
|
||||
### Switching Models with `/model`
|
||||
|
||||
Once a custom endpoint is configured, you can switch models mid-session:
|
||||
|
||||
```
|
||||
/model custom:qwen-2.5 # Switch to a model on your custom endpoint
|
||||
/model custom # Auto-detect the model from the endpoint
|
||||
/model openrouter:claude-sonnet-4 # Switch back to a cloud provider
|
||||
```
|
||||
|
||||
If you have **named custom providers** configured (see below), use the triple syntax:
|
||||
|
||||
```
|
||||
/model custom:local:qwen-2.5 # Use the "local" custom provider with model qwen-2.5
|
||||
/model custom:work:llama3 # Use the "work" custom provider with llama3
|
||||
```
|
||||
|
||||
When switching providers, Hermes persists the base URL and provider to config so the change survives restarts. When switching away from a custom endpoint to a built-in provider, the stale base URL is automatically cleared.
|
||||
|
||||
:::tip
|
||||
`/model custom` (bare, no model name) queries your endpoint's `/models` API and auto-selects the model if exactly one is loaded. Useful for local servers running a single model.
|
||||
:::
|
||||
`hermes model` and the manual `.env` approach end up in the same runtime path. If you save a custom endpoint through `hermes model`, Hermes persists the provider + base URL in `config.yaml` so later sessions keep using that endpoint even if `OPENAI_BASE_URL` is not exported in your current shell.
|
||||
|
||||
Everything below follows this same pattern — just change the URL, key, and model name.
|
||||
|
||||
@@ -336,7 +287,7 @@ vLLM supports tool calling, structured output, and multi-modal models. Use `--en
|
||||
|
||||
```bash
|
||||
# Start SGLang server
|
||||
pip install "sglang[all]"
|
||||
pip install sglang[all]
|
||||
python -m sglang.launch_server \
|
||||
--model meta-llama/Llama-3.1-70B-Instruct \
|
||||
--port 8000 \
|
||||
@@ -379,7 +330,7 @@ Download GGUF models from [Hugging Face](https://huggingface.co/models?library=g
|
||||
|
||||
```bash
|
||||
# Install and start
|
||||
pip install "litellm[proxy]"
|
||||
pip install litellm[proxy]
|
||||
litellm --model anthropic/claude-sonnet-4 --port 4000
|
||||
|
||||
# Or with a config file for multiple models:
|
||||
@@ -511,37 +462,6 @@ custom_providers:
|
||||
|
||||
---
|
||||
|
||||
### Named Custom Providers
|
||||
|
||||
If you work with multiple custom endpoints (e.g., a local dev server and a remote GPU server), you can define them as named custom providers in `config.yaml`:
|
||||
|
||||
```yaml
|
||||
custom_providers:
|
||||
- name: local
|
||||
base_url: http://localhost:8080/v1
|
||||
# api_key omitted — Hermes uses "no-key-required" for keyless local servers
|
||||
- name: work
|
||||
base_url: https://gpu-server.internal.corp/v1
|
||||
api_key: corp-api-key
|
||||
api_mode: chat_completions # optional, auto-detected from URL
|
||||
- name: anthropic-proxy
|
||||
base_url: https://proxy.example.com/anthropic
|
||||
api_key: proxy-key
|
||||
api_mode: anthropic_messages # for Anthropic-compatible proxies
|
||||
```
|
||||
|
||||
Switch between them mid-session with the triple syntax:
|
||||
|
||||
```
|
||||
/model custom:local:qwen-2.5 # Use the "local" endpoint with qwen-2.5
|
||||
/model custom:work:llama3-70b # Use the "work" endpoint with llama3-70b
|
||||
/model custom:anthropic-proxy:claude-sonnet-4 # Use the proxy
|
||||
```
|
||||
|
||||
You can also select named custom providers from the interactive `hermes model` menu.
|
||||
|
||||
---
|
||||
|
||||
### Choosing the Right Setup
|
||||
|
||||
| Use Case | Recommended |
|
||||
@@ -1345,23 +1265,6 @@ Usage: type `/status`, `/disk`, `/update`, or `/gpu` in the CLI or any messaging
|
||||
- **Type** — only `exec` is supported (runs a shell command); other types show an error
|
||||
- **Works everywhere** — CLI, Telegram, Discord, Slack, WhatsApp, Signal, Email, Home Assistant
|
||||
|
||||
## Gateway Streaming
|
||||
|
||||
Enable progressive token delivery on messaging platforms. When streaming is enabled, responses appear character-by-character in Telegram, Discord, and Slack via message editing, rather than waiting for the full response.
|
||||
|
||||
```yaml
|
||||
streaming:
|
||||
enabled: false # Enable streaming token delivery (default: off)
|
||||
transport: edit # "edit" (progressive message editing) or "off"
|
||||
edit_interval: 0.3 # Min seconds between message edits
|
||||
buffer_threshold: 40 # Characters accumulated before forcing an edit
|
||||
cursor: " ▉" # Cursor character shown during streaming
|
||||
```
|
||||
|
||||
**Platform support:** Telegram, Discord, and Slack support edit-based streaming. Platforms that don't support message editing (Signal, Email, Home Assistant) are auto-detected on the first attempt — streaming is gracefully disabled for that session with no flood of messages.
|
||||
|
||||
**Overflow handling:** If the streamed text exceeds the platform's message length limit (~4096 chars), the current message is finalized and a new one starts automatically.
|
||||
|
||||
## Human Delay
|
||||
|
||||
Simulate human-like response pacing in messaging platforms:
|
||||
@@ -1369,8 +1272,8 @@ Simulate human-like response pacing in messaging platforms:
|
||||
```yaml
|
||||
human_delay:
|
||||
mode: "off" # off | natural | custom
|
||||
min_ms: 800 # Minimum delay (custom mode)
|
||||
max_ms: 2500 # Maximum delay (custom mode)
|
||||
min_ms: 500 # Minimum delay (custom mode)
|
||||
max_ms: 2000 # Maximum delay (custom mode)
|
||||
```
|
||||
|
||||
## Code Execution
|
||||
@@ -1383,27 +1286,6 @@ code_execution:
|
||||
max_tool_calls: 50 # Max tool calls within code execution
|
||||
```
|
||||
|
||||
## Web Search Backends
|
||||
|
||||
The `web_search`, `web_extract`, and `web_crawl` tools support three backend providers. Configure the backend in `config.yaml` or via `hermes tools`:
|
||||
|
||||
```yaml
|
||||
web:
|
||||
backend: firecrawl # firecrawl | parallel | tavily
|
||||
```
|
||||
|
||||
| Backend | Env Var | Search | Extract | Crawl |
|
||||
|---------|---------|--------|---------|-------|
|
||||
| **Firecrawl** (default) | `FIRECRAWL_API_KEY` | ✔ | ✔ | ✔ |
|
||||
| **Parallel** | `PARALLEL_API_KEY` | ✔ | ✔ | — |
|
||||
| **Tavily** | `TAVILY_API_KEY` | ✔ | ✔ | ✔ |
|
||||
|
||||
**Backend selection:** If `web.backend` is not set, the backend is auto-detected from available API keys. If only `TAVILY_API_KEY` is set, Tavily is used. If only `PARALLEL_API_KEY` is set, Parallel is used. Otherwise Firecrawl is the default.
|
||||
|
||||
**Self-hosted Firecrawl:** Set `FIRECRAWL_API_URL` to point at your own instance. When a custom URL is set, the API key becomes optional (set `USE_DB_AUTHENTICATION=false` on the server to disable auth).
|
||||
|
||||
**Parallel search modes:** Set `PARALLEL_SEARCH_MODE` to control search behavior — `fast`, `one-shot`, or `agentic` (default: `agentic`).
|
||||
|
||||
## Browser
|
||||
|
||||
Configure browser automation behavior:
|
||||
@@ -1421,15 +1303,14 @@ The browser toolset supports multiple providers. See the [Browser feature page](
|
||||
Block specific domains from being accessed by the agent's web and browser tools:
|
||||
|
||||
```yaml
|
||||
security:
|
||||
website_blocklist:
|
||||
enabled: false # Enable URL blocking (default: false)
|
||||
domains: # List of blocked domain patterns
|
||||
- "*.internal.company.com"
|
||||
- "admin.example.com"
|
||||
- "*.local"
|
||||
shared_files: # Load additional rules from external files
|
||||
- "/etc/hermes/blocked-sites.txt"
|
||||
website_blocklist:
|
||||
enabled: false # Enable URL blocking (default: false)
|
||||
domains: # List of blocked domain patterns
|
||||
- "*.internal.company.com"
|
||||
- "admin.example.com"
|
||||
- "*.local"
|
||||
shared_files: # Load additional rules from external files
|
||||
- "/etc/hermes/blocked-sites.txt"
|
||||
```
|
||||
|
||||
When enabled, any URL matching a blocked domain pattern is rejected before the web or browser tool executes. This applies to `web_search`, `web_extract`, `browser_navigate`, and any tool that accesses URLs.
|
||||
@@ -1448,20 +1329,19 @@ The policy is cached for 30 seconds, so config changes take effect quickly witho
|
||||
Control how Hermes handles potentially dangerous commands:
|
||||
|
||||
```yaml
|
||||
approvals:
|
||||
mode: manual # manual | smart | off
|
||||
approval_mode: ask # ask | smart | off
|
||||
```
|
||||
|
||||
| Mode | Behavior |
|
||||
|------|----------|
|
||||
| `manual` (default) | Prompt the user before executing any flagged command. In the CLI, shows an interactive approval dialog. In messaging, queues a pending approval request. |
|
||||
| `ask` (default) | Prompt the user before executing any flagged command. In the CLI, shows an interactive approval dialog. In messaging, queues a pending approval request. |
|
||||
| `smart` | Use an auxiliary LLM to assess whether a flagged command is actually dangerous. Low-risk commands are auto-approved with session-level persistence. Genuinely risky commands are escalated to the user. |
|
||||
| `off` | Skip all approval checks. Equivalent to `HERMES_YOLO_MODE=true`. **Use with caution.** |
|
||||
|
||||
Smart mode is particularly useful for reducing approval fatigue — it lets the agent work more autonomously on safe operations while still catching genuinely destructive commands.
|
||||
|
||||
:::warning
|
||||
Setting `approvals.mode: off` disables all safety checks for terminal commands. Only use this in trusted, sandboxed environments.
|
||||
Setting `approval_mode: off` disables all safety checks for terminal commands. Only use this in trusted, sandboxed environments.
|
||||
:::
|
||||
|
||||
## Checkpoints
|
||||
@@ -1470,7 +1350,7 @@ Automatic filesystem snapshots before destructive file operations. See the [Chec
|
||||
|
||||
```yaml
|
||||
checkpoints:
|
||||
enabled: true # Enable automatic checkpoints (also: hermes --checkpoints)
|
||||
enabled: false # Enable automatic checkpoints (also: hermes --checkpoints)
|
||||
max_snapshots: 50 # Max checkpoints to keep per directory
|
||||
```
|
||||
|
||||
@@ -1481,6 +1361,11 @@ Configure subagent behavior for the delegate tool:
|
||||
|
||||
```yaml
|
||||
delegation:
|
||||
max_iterations: 50 # Max iterations per subagent
|
||||
default_toolsets: # Toolsets available to subagents
|
||||
- terminal
|
||||
- file
|
||||
- web
|
||||
# model: "google/gemini-3-flash-preview" # Override model (empty = inherit parent)
|
||||
# provider: "openrouter" # Override provider (empty = inherit parent)
|
||||
# base_url: "http://localhost:1234/v1" # Direct OpenAI-compatible endpoint (takes precedence over provider)
|
||||
@@ -1511,15 +1396,12 @@ Hermes uses two different context scopes:
|
||||
| File | Purpose | Scope |
|
||||
|------|---------|-------|
|
||||
| `SOUL.md` | **Primary agent identity** — defines who the agent is (slot #1 in the system prompt) | `~/.hermes/SOUL.md` or `$HERMES_HOME/SOUL.md` |
|
||||
| `.hermes.md` / `HERMES.md` | Project-specific instructions (highest priority) | Walks to git root |
|
||||
| `AGENTS.md` | Project-specific instructions, coding conventions | Recursive directory walk |
|
||||
| `CLAUDE.md` | Claude Code context files (also detected) | Working directory only |
|
||||
| `.cursorrules` | Cursor IDE rules (also detected) | Working directory only |
|
||||
| `.cursor/rules/*.mdc` | Cursor rule files (also detected) | Working directory only |
|
||||
| `AGENTS.md` | Project-specific instructions, coding conventions | Working directory / project tree |
|
||||
| `.cursorrules` | Cursor IDE rules (also detected) | Working directory |
|
||||
| `.cursor/rules/*.mdc` | Cursor rule files (also detected) | Working directory |
|
||||
|
||||
- **SOUL.md** is the agent's primary identity. It occupies slot #1 in the system prompt, completely replacing the built-in default identity. Edit it to fully customize who the agent is.
|
||||
- If SOUL.md is missing, empty, or cannot be loaded, Hermes falls back to a built-in default identity.
|
||||
- **Project context files use a priority system** — only ONE type is loaded (first match wins): `.hermes.md` → `AGENTS.md` → `CLAUDE.md` → `.cursorrules`. SOUL.md is always loaded independently.
|
||||
- **AGENTS.md** is hierarchical: if subdirectories also have AGENTS.md, all are combined.
|
||||
- Hermes automatically seeds a default `SOUL.md` if one does not already exist.
|
||||
- All loaded context files are capped at 20,000 characters with smart truncation.
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user