The agent that grows with you

TTekniumtest(telegram): add brand-new-topic regression for #31086

文件	最后提交记录	最后更新时间
.github	feat(ci): use 6-way slicing based on benchmark results Benchmarked 4/5/6/7/8 slices with LPT duration-balanced distribution: - 4 slices: 4.8m wall, 135s spread - 5 slices: 3.4m wall, 46s spread - 6 slices: 3.3m wall, 26s spread ← optimal - 7 slices: 3.9m wall, 109s spread - 8 slices: 3.7m wall, 96s spread 6 slices is the sweet spot: lowest wall time, tightest spread. 7+ gets slower due to per-slice startup overhead dominating. Also removes benchmark branch markers from save-durations condition.	13 天前
.plans	Merge PR #724: feat: --yolo flag to bypass all approval prompts Authored by dmahan93. Adds HERMES_YOLO_MODE env var and --yolo CLI flag to auto-approve all dangerous command prompts. Post-merge: renamed --fuck-it-ship-it to --yolo for brevity, resolved conflict with --checkpoints flag.	2 个月前
acp_adapter	fix(acp): only deliver final_response after streaming when transformed PR #29119 dropped the 'not streamed_message' guard unconditionally so that plugin-transformed responses (transform_llm_output hook) would reach ACP clients. That regressed test_prompt_does_not_duplicate_streamed_final_message: when no transform happened, the streamed text was re-sent as a duplicate final delivery. Tighten the condition to mirror the gateway side: deliver after streaming only when response_transformed=True. Otherwise keep the old guard. Adds test_prompt_delivers_transformed_response_after_streaming so the transformed path stays covered.	12 天前
acp_registry	chore(acp): bump registry manifest to 0.14.0 matching pyproject	18 天前
agent	fix(anthropic): skip mcp_ prefix on outgoing tool schemas when already prefixed Companion to the GH-25255 incoming-strip fix from @hayka-pacha. Without this, build_anthropic_kwargs unconditionally added 'mcp_' to every tool name in step 3, so a native MCP server tool registered as 'mcp_composio_X' was sent as 'mcp_mcp_composio_X' on the wire. The incoming strip only removes ONE prefix, which still worked on first call, but on subsequent calls the model pattern-matched the single-prefixed form from message history and produced names that stripped to 'composio_X' — registry miss, dispatch fail. The history-rewrite block (#4) already has this guard. Apply the same guard to the schema-rewrite block (#3) so round-trip is symmetric. Added 4 outgoing-side tests. Existing 7 incoming-side tests still pass. Author map: hayka-pacha added for PR #25270 salvage attribution. Refs GH-25255.	11 天前
assets	Update banner image to new version	3 个月前
cron	refactor(ntfy): convert built-in adapter to platform plugin ntfy now ships as a self-contained plugin under plugins/platforms/ntfy/ instead of editing 8 core files (gateway/config.py Platform enum, gateway/run.py factory + auth maps, cron/scheduler.py, toolsets.py, hermes_cli/status.py, agent/prompt_builder.py, gateway/channel_directory.py, tools/send_message_tool.py). All routing goes through gateway/platform_registry via register_platform(): - adapter_factory, check_fn, validate_config, is_connected - env_enablement_fn seeds PlatformConfig.extra from NTFY_* env vars so gateway status reflects env-only setups without instantiating httpx - standalone_sender_fn handles deliver=ntfy cron jobs when cron runs out-of-process from the gateway - allowed_users_env / allow_all_env hook into _is_user_authorized - cron_deliver_env_var=NTFY_HOME_CHANNEL for cron home routing - platform_hint surfaces in the system prompt - pii_safe=True (topic names are the only identifier; no PII to redact) Tests moved to tests/gateway/test_ntfy_plugin.py using _plugin_adapter_loader so the module lives under plugin_adapter_ntfy in sys.modules and cannot collide with sibling plugin-adapter tests on the same xdist worker. The core-file grep tests (Platform.NTFY in source, hermes-ntfy in toolsets, etc.) are replaced with plugin-shape tests covering register() metadata, env_enablement_fn output, and standalone_sender_fn behavior. 68 tests pass under scripts/run_tests.sh.	12 天前
datagen-config-examples	feat: add WebResearchEnv RL environment for multi-step web research	2 个月前
docker	fix(docker): keep dashboard side-process loopback by default (#30740)	12 天前
docs	docs: add ACP Zed edit approval diffs plan	18 天前
gateway	fix(telegram): preserve new DM topic lanes	11 天前
hermes_cli	fix(matrix,gateway): Matrix E2EE installs full dep set; plugins respect is_connected Fixes #31116 — two distinct bugs in fresh-install Matrix gateway: 1. Matrix E2EE setup installed only mautrix[encryption], leaving asyncpg / aiosqlite / Markdown / aiohttp-socks uninstalled. The first encrypted connect failed with 'No module named asyncpg' deep inside MatrixAdapter.connect(). Root cause: the setup wizard hand-rolled a pip install of one package instead of using lazy_deps.ensure( 'platform.matrix'), and check_matrix_requirements() short-circuited the runtime installer on 'import mautrix' alone — so the other 4 packages were never pulled in. 2. Discord auto-enabled itself on every gateway start, even when the user never selected Discord and had no DISCORD_BOT_TOKEN. Root cause: gateway/config.py plugin-enablement loop gated enablement on entry.check_fn() (just 'is the SDK importable?') and ignored entry.is_connected (the 'did the user configure credentials?' probe). Same bug class as commit 7849a3d73 fixed for _platform_status in the setup wizard; this is the runtime counterpart. Affects Discord, Teams, and Google Chat. Changes: - hermes_cli/setup.py::_setup_matrix — install via lazy_deps.ensure('platform.matrix') to pull the full feature group. - gateway/platforms/matrix.py::_check_e2ee_deps — verify asyncpg + aiosqlite + PgCryptoStore in addition to OlmMachine, so E2EE failures surface at startup instead of at first encrypted-room connect. - gateway/platforms/matrix.py::check_matrix_requirements — use feature_missing('platform.matrix') as the install gate instead of a single 'import mautrix' check, so partial installs trigger the lazy installer correctly. - gateway/config.py plugin-enablement loop — consult entry.is_connected before flipping enabled=True. Explicit YAML enabled=true still wins. Tests: 3 new in tests/gateway/test_matrix.py (asyncpg-required, aiosqlite-required, partial-install lazy-runs), 5 new in tests/gateway/test_platform_registry.py (is_connected=False blocks, is_connected=True enables, is_connected=None falls back to check_fn, raising probe doesn't enable, explicit YAML wins). Validation: 310 tests across affected test modules pass.	11 天前
infographic	infographic: kanban.db corruption defense (#30858 + #30862) (#30952)	13 天前
locales	fix(compress): abort instead of dropping messages when summary LLM fails (#28102) When auxiliary compression's summary generation returns None (aux model errored, returned non-JSON, timed out, etc.) the compressor previously still dropped every middle message between compress_start..compress_end and replaced them with a static 'Summary generation was unavailable' placeholder. The session kept going but the user silently lost N turns of context for nothing. New behavior: on summary failure, compress() aborts entirely — returns the input messages unchanged and sets _last_compress_aborted=True. The existing _summary_failure_cooldown_until gate (30-60s) keeps the aux model from being burned on every turn. Auto-compress callers detect the no-op (len(after) == len(before)) and stop looping. The chat is 'frozen' at its current size until the next /compress or /new. Manual /compress (CLI + gateway) now passes force=True which clears the cooldown so users can retry immediately after an auto-abort. If the manual retry also fails, the user gets a visible warning telling them nothing was dropped and how to retry. - agent/context_compressor.py: compress() gains force= kwarg; failure branch sets _last_compress_aborted and returns messages unchanged instead of inserting placeholder. - run_agent.py: _compress_context() detects abort, surfaces warning, skips session-rotation entirely, returns messages unchanged. - cli.py + gateway/run.py: manual /compress paths pass force=True. - gateway/run.py: hygiene + /compress handlers detect _last_compress_aborted and emit the new 'Compression aborted' warning (gateway.compress.aborted) instead of the old 'N historical messages were removed' message. - locales/*.yaml: new gateway.compress.aborted key in all 16 locales. - tests: updated to assert the abort contract (messages preserved, compression_count not incremented, abort flag set, no placeholder leaked). New test_force_true_bypasses_failure_cooldown covers the manual-retry path.	17 天前
nix	refactor(web): dashboard typography & contrast pass Removes the global `uppercase` + `font-mondwest` from the App.tsx root that forced every page to opt-out, replaces stacked-alpha text colors with semantic tokens for WCAG-AA contrast across all 7 themes, and applies the new `text-display` utility from @nous-research/ui@0.16.0 on intentional brand chrome (page titles, sidebar headings, segmented filters) only. Bumps every sub-12px arbitrary text size to text-xs. Also widens the dashboard plugin routes (/api/dashboard/agent-plugins/ {name:path}/...) so category-namespaced plugins like observability/ langfuse and image_gen/openai can be enable/disabled from the dashboard — previously the FE encodeURIComponent-ed the slash and the backend {name} route rejected it. _validate_plugin_name still blocks .. and backslash, and strips leading/trailing slash. Touches sessions/env/keys page chrome and adds two new i18n keys (`overview`, `showMore`/`showLess`) across all 18 locales. Squashes 19 commits from PR #28832. Co-authored-by: Hermes <noreply@nousresearch.com>	13 天前
optional-skills	chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) Six days after #23937 (608 fixes) the codebase had accumulated 241 new PLR6201 violations. Same mechanical `x in (...)` → `x in {...}` fix, same zero-risk profile: set lookup is O(1) vs O(n) for tuple and the two are semantically equivalent for hashable scalar membership tests. All 241 instances fixed via `ruff check --select PLR6201 --fix --unsafe-fixes`, zero remaining. Every changed value is a hashable scalar (str/int/None/enum/signal); no risk of unhashable runtime errors. No behavior change. Test plan: - 119 files changed, +244/-244 (net zero) — exactly one-line edits - `ruff check` clean afterward - Compile checks pass on the largest touched files (cli.py, run_agent.py, gateway/run.py, gateway/platforms/discord.py, model_tools.py) - Subset broad test run on tests/gateway/ tests/hermes_cli/ tests/agent/ tests/tools/: 18187 passed, 59 pre-existing failures (verified against origin/main with the same shape — identical failure count, identical category — all xdist test-order flakes unrelated to this change) Follows the same template as PR #23937 ([tracker: #23972](https://github.com/NousResearch/hermes-agent/issues/23972)).	19 天前
packaging	chore: prepare Hermes for Homebrew packaging (#4099) Co-authored-by: Yabuku-xD <78594762+Yabuku-xD@users.noreply.github.com>	2 个月前
plans	fix(gemini): tighten native routing and streaming replay - only use the native adapter for the canonical Gemini native endpoint - keep custom and /openai base URLs on the OpenAI-compatible path - preserve Hermes keepalive transport injection for native Gemini clients - stabilize streaming tool-call replay across repeated SSE events - add follow-up tests for base_url precedence, async streaming, and duplicate tool-call chunks	1 个月前
plugins	ntfy: tighten robustness, dedupe auth/truncation, add docs Robustness: - Surface 401/404 stream failures via _set_fatal_error() so the gateway's runtime status reflects 'fatal: ntfy_unauthorized' / 'ntfy_topic_not_found' instead of staying 'connected' when the reconnect loop halts. Matches the pattern in whatsapp / telegram / sms adapters. - Strip whitespace from auth tokens so pasted tokens with trailing newlines don't produce malformed Authorization headers. Simplicity: - Extract _build_auth_header() and _truncate_body() to module-level helpers, used by both NtfyAdapter and _standalone_send. Removes the duplicated auth/truncation logic between the two paths. Docs: - website/docs/user-guide/messaging/ntfy.md — full setup guide, identity-model warning, self-hosting, cron usage, troubleshooting. - website/docs/reference/environment-variables.md — all 9 NTFY_* vars. - website/docs/user-guide/messaging/index.md — platform comparison row. - website/sidebars.ts — sidebar entry between simplex and open-webui. Tests: 78/78 (+ 10 new robustness tests covering token hygiene, fatal error propagation for 401/404, and the _truncate_body helper).	12 天前
providers	fix(providers): set User-Agent on ProviderProfile.fetch_models Some catalog endpoints (OpenCode Zen, etc.) sit behind a WAF that returns 403 for the default Python-urllib/<ver> User-Agent. The generic profile-based live fetch in providers/base.py was silently failing for any such provider — falling through to the static catalog and missing newly-launched models. Set a generic 'hermes-cli/<version>' UA on the catalog probe so every api_key provider profile benefits. Verified live against opencode-zen: before this change, profile.fetch_models() raised HTTP 403; after, it returns 42 models including gpt-5.5, gpt-5.5-pro, kimi-k2.6, glm-5.1 and the *-free variants the static catalog doesn't list. Also strip the now-stale comment in validate_requested_model() claiming opencode-zen's /models returns 404 against the HTML marketing site — the API endpoint at /zen/v1/models returns 200 with valid JSON. Surfaced by #2651 (@aashizpoudel) — fixes the same user-facing gap their PR targeted, applied at the right layer so all api_key provider profiles get live catalogs through the same code path. Co-authored-by: Aashish Poudel <mr.aashiz@gmail.com>	21 天前
scripts	fix(anthropic): skip mcp_ prefix on outgoing tool schemas when already prefixed Companion to the GH-25255 incoming-strip fix from @hayka-pacha. Without this, build_anthropic_kwargs unconditionally added 'mcp_' to every tool name in step 3, so a native MCP server tool registered as 'mcp_composio_X' was sent as 'mcp_mcp_composio_X' on the wire. The incoming strip only removes ONE prefix, which still worked on first call, but on subsequent calls the model pattern-matched the single-prefixed form from message history and produced names that stripped to 'composio_X' — registry miss, dispatch fail. The history-rewrite block (#4) already has this guard. Apply the same guard to the schema-rewrite block (#3) so round-trip is symmetric. Added 4 outgoing-side tests. Existing 7 incoming-side tests still pass. Author map: hayka-pacha added for PR #25270 salvage attribution. Refs GH-25255.	11 天前
skills	feat(sessions): opt-in per-session JSON snapshot writer PR #29182 deleted the per-session JSON snapshot writer outright because state.db is canonical and the snapshots had no in-tree consumer. Some users have external tooling that reads `~/.hermes/sessions/session_{sid}.json` directly, so reintroduce the writer behind a config flag that defaults to off. - Add `sessions.write_json_snapshots` (default False) to DEFAULT_CONFIG - Restore `AIAgent._save_session_log` + `_clean_session_content` as gated methods. When the flag is off the call is a fast no-op; when on, the writer behaves as before (atomic write, truncation guard preserved, REASONING_SCRATCHPAD → think tag normalization) - Re-derive the target path from `agent.session_id` on each call so `/branch` and `/compress` re-points happen automatically — no need to restore the explicit re-point bookkeeping at call sites - Wire the single call site in `_persist_session` (the cleanup-on-exit hook). Did NOT restore the 7 intra-turn calls the original PR deleted — those were redundant writes within the same turn that doubled disk I/O without adding any persistence guarantee `_persist_session` does not already provide - Read the flag once at agent init via `load_config()`, cache as `agent._session_json_enabled` - Update `TestNoSessionJsonSnapshot` → `TestSessionJsonSnapshotOptIn` to pin behavior: default off (no file), opt-in true (file written), no-op method on default agents, logs_dir retained unconditionally - Update CONTRIBUTING.md and the bundled `hermes-agent` skill to document the flag and its default	15 天前
tests	test(telegram): add brand-new-topic regression for #31086 The cherry-picked fix from #28605 inverts an existing test (an unknown non-lobby thread_id no longer rewrites to the most-recent binding), but that test only seeds two bindings and queries a third thread_id. Add a second regression test that more closely mirrors the live failure mode: seed exactly one prior binding, then query a brand-new thread_id and assert recovery returns None — so the new topic is allowed to get its own session row instead of being silently merged into the previous topic's session. Co-authored-by: Fábio Siqueira <fabioxxx@gmail.com> Co-authored-by: dillweed <dillweed@users.noreply.github.com>	11 天前
tools	fix(vision): route auxiliary.vision.provider=openai to api.openai.com, skip text-only main (#31452) * fix(vision): route auxiliary.vision.provider=openai to api.openai.com, skip text-only main for vision Fixes #31179. Three coupled fixes so a configured aux vision backend actually serves vision tasks instead of silently routing images to the user's main provider: 1. agent/auxiliary_client.py: `auxiliary.<task>.provider: openai` resolves to `custom` + `https://api.openai.com/v1`. "openai" was not in PROVIDER_REGISTRY (we have `openai-codex` for OAuth and `custom` for manual base_url), so the obvious config name silently failed to build a client. User-supplied base_url is still preserved; only the provider name normalises to `custom` so resolution doesn't hit the PROVIDER_REGISTRY-only path. 2. agent/auxiliary_client.py: the vision auto-detect chain now skips the user's main provider when models.dev reports `supports_vision=False`. Without this guard, a misconfigured aux provider would fall back to `auto`, which happily returned the main-provider client. The caller would then send image content to e.g. api.deepseek.com with model `gpt-4o-mini` and get a cryptic `unknown variant 'image_url', expected 'text'` from the provider's parser. 3. tools/vision_tools.py + tools/browser_tool.py: `check_vision_requirements` now mirrors the runtime fallback chain (explicit provider, then auto), so `vision_analyze` shows up whenever vision is actually serviceable. `browser_vision` gets a new `check_browser_vision_requirements` check_fn that AND-gates browser + vision availability, so it doesn't get advertised to the model when the call would fail at runtime. Reproduction (config from the bug report): model.provider: deepseek model.default: deepseek-v4-pro auxiliary.vision.provider: openai auxiliary.vision.model: gpt-4o-mini Before: resolve_vision_provider_client() returns None for the explicit provider, fallback auto returns the deepseek client with model='gpt-4o-mini', image hits api.deepseek.com → 'unknown variant image_url'. vision_analyze hidden from tool list; browser_vision exposed but fails at call time. After: resolves to custom + api.openai.com/v1 with model gpt-4o-mini. vision_analyze and browser_vision both gate correctly on capability. Tests: tests/agent/test_vision_routing_31179.py covers all three fixes (12 cases including the user's exact scenario, base_url preservation, text-only-main skip, capability-unknown permissive fallback, and tool gating parity). Existing 382 tests across auxiliary/vision/image_routing suites still pass. * test(vision): use exact hostname check to silence CodeQL substring-sanitization alert * fix(auxiliary): drop model name from vision-skip debug log to silence CodeQL The new `logger.debug(...)` added in the previous commit interpolated both `main_provider` and `vision_model` (a public model slug \u2014 not sensitive). CodeQL's `py/clear-text-logging-sensitive-data` heuristic re-flagged it twice because the rule mis-detects multi-value interpolations near tainted-via-config provider strings. Drop the model from the log args (provider alone is enough to diagnose the skip; the same sibling branch a few lines up already logs provider only). Behavior unchanged; CodeQL false positive cleared.	11 天前
tui_gateway	fix(cli): decouple tool_progress=verbose from global DEBUG logging (#31379) PR #6a1aa420e coupled `display.tool_progress: verbose` (a per-tool display toggle for full args / results / think blocks) to `self.verbose` — which controls root-logger DEBUG level. Result: setting tool_progress: verbose in config silently flipped every module in the process to DEBUG and flooded the terminal with internal logging, far beyond just full tool calls. The two concepts are separate: - `tool_progress_mode == 'verbose'` → display behavior (tool rendering) - `self.verbose` → logging behavior (root logger → DEBUG, line 9795) This change keeps PR #6a1aa420e's argparse.SUPPRESS / config-fallback plumbing but severs the verbose-display → debug-logging link. Changes: - cli.py:2868 — `self.verbose` only follows explicit `verbose=` arg; no longer auto-True when tool_progress_mode == 'verbose'. - cli.py:_toggle_verbose — slash-cycle through tool progress modes no longer flips `self.verbose` / `agent.verbose_logging` / `agent.quiet_mode`. - cli.py:9355 — fix misleading label (drop 'and debug logs'). - tui_gateway/server.py:_make_agent — same decoupling on the TUI side (verbose_logging no longer derived from tool_progress_mode). - tests/cli/test_tool_progress_scrollback.py — invert the test that asserted the broken coupling; add coverage for explicit `--verbose` still enabling DEBUG independent of tool_progress. Live verified: - tool_progress: verbose, no --verbose flag → 0 DEBUG/INFO log lines - --verbose flag explicit → 32 DEBUG/INFO log lines (as expected)	12 天前
ui-tui	fix(tui): stop slash dropdown from chopping last char of /goal (#31311) Two independent bugs caused the slash-command autocomplete to render `/goal` as `/goa` (and `/gquota` as `/gquot` for that matter) in the TUI: 1. `tui_gateway/server.py` was forwarding `c.display` from prompt_toolkit's `Completion` straight into the JSON-RPC payload. prompt_toolkit normalizes `display=` into `FormattedText` (a `list` subclass), so the wire format became `[["", "/goal"]]` instead of the `string` that `CompletionItem.display` in the TUI declares. `meta` already went through `to_plain_text` — `display` did not. 2. The dropdown row in `appOverlays.tsx` used `flexDirection="row"` with the display `<Text>` and the (very long) meta `<Text>` as siblings. When the meta overflows the row width, Ink/Yoga shrinks the first column by one cell, lopping the trailing character off the command name. `/goal` triggers it reliably because its meta string is the longest of any built-in command (description + embedded `[text \| pause \| resume \| clear \| status]` usage hint). Wrapping the display column in `<Box flexShrink={0}>` keeps it at its natural width and lets the meta wrap or truncate instead.	12 天前
web	refactor(web): dashboard typography & contrast pass Removes the global `uppercase` + `font-mondwest` from the App.tsx root that forced every page to opt-out, replaces stacked-alpha text colors with semantic tokens for WCAG-AA contrast across all 7 themes, and applies the new `text-display` utility from @nous-research/ui@0.16.0 on intentional brand chrome (page titles, sidebar headings, segmented filters) only. Bumps every sub-12px arbitrary text size to text-xs. Also widens the dashboard plugin routes (/api/dashboard/agent-plugins/ {name:path}/...) so category-namespaced plugins like observability/ langfuse and image_gen/openai can be enable/disabled from the dashboard — previously the FE encodeURIComponent-ed the slash and the backend {name} route rejected it. _validate_plugin_name still blocks .. and backslash, and strips leading/trailing slash. Touches sessions/env/keys page chrome and adds two new i18n keys (`overview`, `showMore`/`showLess`) across all 18 locales. Squashes 19 commits from PR #28832. Co-authored-by: Hermes <noreply@nousresearch.com>	13 天前
website	feat(security): on-demand supply-chain audit via OSV.dev (#31460) Adds 'hermes security audit' — a one-shot vulnerability scan against OSV.dev covering three surfaces a Hermes user actually controls: 1. The running Python's installed PyPI dists (importlib.metadata) 2. Plugin requirements.txt / pyproject.toml pins under ~/.hermes/plugins/ 3. Pinned npx/uvx MCP servers in config.yaml Zero new dependencies (stdlib urllib + importlib.metadata + tomllib + concurrent.futures). No auth required for OSV's public batch API. Flags: --json, --fail-on {low,moderate,high,critical} (default: critical), --skip-venv, --skip-plugins, --skip-mcp Output groups findings by source, sorts by severity descending, surfaces fixed-versions inline. Exit 1 when any finding meets the --fail-on tier. Deliberately out of scope: globally-installed pip/npm, editor/browser extensions, daily background scans, auto-blocking of installs. The audit is on-demand by design — daily scans become noise the user trains themselves to ignore.	11 天前
.dockerignore	fix(docker): exclude compose/profile runtime state from build context	1 个月前
.env.example	fix(cron): route Telegram cron deliveries to a dedicated topic via TELEGRAM_CRON_THREAD_ID When Telegram topic mode is enabled, cron messages delivered to the bot's root DM (TELEGRAM_HOME_CHANNEL without a thread id) land in the system lobby — replies there are rebuffed with the lobby reminder and reply_to_message_id is dropped, so users cannot interact with the cron output (#24409). Add an optional TELEGRAM_CRON_THREAD_ID env var that overrides TELEGRAM_HOME_CHANNEL_THREAD_ID for cron deliveries only. Operators can create a "Cron" forum topic in the DM, point this var at its thread id, and replies to cron messages will land in that topic's existing session instead of the lobby. The home-channel thread id (used elsewhere, e.g. restart notifications) is unchanged, and explicit deliver="telegram:chat:thread" targets continue to win over the env var. Per the reporter's clarification on 2026-05-13, option (a) (cron-side route to a dedicated topic + config knob) was chosen. Fixes #24409	17 天前
.envrc	nix: add tui lockfile update script	1 个月前
.gitattributes	feat: web UI dashboard for managing Hermes Agent (#8756) * feat: web UI dashboard for managing Hermes Agent (salvage of #8204/#7621) Adds an embedded web UI dashboard accessible via `hermes web`: - Status page: agent version, active sessions, gateway status, connected platforms - Config editor: schema-driven form with tabbed categories, import/export, reset - API Keys page: set, clear, and view redacted values with category grouping - Sessions, Skills, Cron, Logs, and Analytics pages Backend: - hermes_cli/web_server.py: FastAPI server with REST endpoints - hermes_cli/config.py: reload_env() utility for hot-reloading .env - hermes_cli/main.py: `hermes web` subcommand (--port, --host, --no-open) - cli.py / commands.py: /reload slash command for .env hot-reload - pyproject.toml: [web] optional dependency extra (fastapi + uvicorn) - Both update paths (git + zip) auto-build web frontend when npm available Frontend: - Vite + React + TypeScript + Tailwind v4 SPA in web/ - shadcn/ui-style components, Nous design language - Auto-refresh status page, toast notifications, masked password inputs Security: - Path traversal guard (resolve().is_relative_to()) on SPA file serving - CORS localhost-only via allow_origin_regex - Generic error messages (no internal leak), SessionDB handles closed properly Tests: 47 tests covering reload_env, redact_key, API endpoints, schema generation, path traversal, category merging, internal key stripping, and full config round-trip. Original work by @austinpickett (PR #1813), salvaged by @kshitijk4poor (PR #7621 → #8204), re-salvaged onto current main with stale-branch regressions removed. * fix(web): clean up status page cards, always rebuild on `hermes web` - Remove config version migration alert banner from status page - Remove config version card (internal noise, not surfaced in TUI) - Reorder status cards: Agent → Gateway → Active Sessions (3-col grid) - `hermes web` now always rebuilds from source before serving, preventing stale web_dist when editing frontend files * feat(web): full-text search across session messages - Add GET /api/sessions/search endpoint backed by FTS5 - Auto-append prefix wildcards so partial words match (e.g. 'nimb' → 'nimby') - Debounced search (300ms) with spinner in the search icon slot - Search results show FTS5 snippets with highlighted match delimiters - Expanding a search hit auto-scrolls to the first matching message - Matching messages get a warning ring + 'match' badge - Inline term highlighting within Markdown (text, bold, italic, headings, lists) - Clear button (x) on search input for quick reset --------- Co-authored-by: emozilla <emozilla@nousresearch.com>	1 个月前
.gitignore	feat(ci): 4-way matrix slicing with LPT duration-balanced distribution run_tests_parallel.py: - --slice I/N flag (also HERMES_TEST_SLICE env var) runs only the I-th slice of N, distributing files across slices by cached duration using LPT (Longest Processing Time first) greedy algorithm so each slice gets roughly equal wall time - Duration cache (test_durations.json): maps relative file paths to last-observed subprocess wall time. _save_durations merges with existing cache so entries from other slices are preserved. - Per-file subprocess timing in progress output + end-of-run distribution summary (percentiles, top-10 slowest, <1s/<2s counts) - Unknown files default to 2.0s estimate (~P50), spread evenly by LPT .github/workflows/tests.yml: - Matrix strategy: slice [1, 2, 3, 4] with fail-fast: false - Each slice restores duration cache from main (stable key, no SHA), runs its portion, uploads per-slice durations as artifacts - save-durations job (main only, if: always()) downloads all 4 artifacts, merges into single cache entry for future PRs - Timeout reduced from 60min to 30min per slice (~1/4 the work) Cache design: - Stable key (test-durations) not keyed by commit SHA — durations are about files, not commits, and SHA-keyed caches miss on every new commit and on PR merge commits - actions/cache scoping: main's cache is visible to all PRs targeting main; feature branches without a cache still work (default 2.0s) - No dotfile prefix (upload-artifact v7 skips hidden files)	13 天前
.mailmap	chore: add MestreY0d4-Uninter to AUTHOR_MAP and .mailmap	1 个月前
AGENTS.md	test: use subprocesses for each test file (#29016) * ci(tests): install ripgrep from prebuilt tarball instead of apt apt-get update + install of ripgrep takes ~4 min on the GHA Ubuntu runners (the apt-get update against archive.ubuntu.com is the slow part; ripgrep itself is small). Switching to the upstream musl binary tarball cuts the step to a few seconds. - Pinned to ripgrep 15.1.0 with sha256 verification (same hash as published in the releases sha256 sidecar file). - Drops the `rg` binary into /usr/local/bin so it is on PATH for every subsequent step without GITHUB_PATH manipulation. - Applied to both the test and e2e jobs in tests.yml. * fix(cli): compile syntax check to tempdir, not source __pycache__ `_validate_critical_files_syntax` runs `py_compile.compile()` on each critical bootstrap file after a successful `git pull`. The default `py_compile` writes the resulting `.pyc` next to the source under `__pycache__/`, which causes two real problems: 1. Parallel test workers walking the same source tree (e.g. running the suite under per-file process isolation) can race against each other on the `__pycache__` write — manifests as flaky 'directory not empty' errors during teardown. 2. In production, the post-pull syntax check leaves a `.pyc` behind that the next interpreter run might pick up — fine when the interpreter version matches, sketchy if it doesn't. Fix: write the compiled output to a `tempfile.TemporaryDirectory()` that's discarded on function exit. We only care about the compile-or-not signal, not the artifact. * test(runner): per-file process isolation, drop manual state reset + xdist Replace fragile manual _reset_module_state test fixtures with robust per-file subprocess isolation. Each test file runs in a fresh `python -m pytest <file>` subprocess via ThreadPoolExecutor. No xdist, no custom pytest plugin, no shared worker state. Key changes: * scripts/run_tests_parallel.py — new runner: discovers test files, runs N in parallel via ThreadPoolExecutor, captures stdout per file, treats exit code 5 (no tests collected) as pass, kills all children on exit. Change from cpu_count to cpu_count2. The runner is I/O-bound (waiting on subprocess.communicate() from pytest children) The parent process does almost no CPU work, so 2x oversubscription keeps more pipes full. When a file fails, immediately show the last 30 lines of pytest output (stack traces + FAILED summary) plus a ready-to-copy repro command: python -m pytest tests/agent/test_auxiliary_client.py scripts/run_tests.sh — delegates to run_tests_parallel.py * .github/workflows/tests.yml — test step: python scripts/run_tests_parallel.py * pyproject.toml — drop pytest-xdist, pytest-split; simplify addopts * tests/conftest.py — remove ~200 lines of manual state-reset fixtures * AGENTS.md — update Testing section for per-file design * test(runner): speed gateway test antipattern scan up * fix(test): web search provider plugin test missing xai * fix(tests): make 14 test files pass under per-file subprocess isolation Tests that relied on cross-file state pollution from xdist workers fail when run in isolation (per-file subprocess model). Root causes and fixes: Tool registry not populated: - test_video_generation_tool_surface_matrix: add discover_builtin_tools() - test_web_providers_brave_free/ddgs/searxng/general: autouse fixtures registering all 8 bundled web providers, reset after each test - test_website_policy: same provider registration pattern - test_web_tools_tavily: same pattern across 3 dispatch test classes - Also add is_safe_url/check_website_access mocks where SSRF check blocks example.com (DNS resolution fails in isolated envs) Stale check_fn cache: - test_kanban_tools: invalidate_check_fn_cache() + _clear_tool_defs_cache() in both kanban guidance tests (prior test cached False for kanban_show) - test_discord_tool: cache invalidation in setup/teardown - test_homeassistant_tool: invalidate_check_fn_cache() before registry queries Module-level state pollution: - test_auxiliary_client: autouse fixture clearing _aux_unhealthy_until cache - test_skill_commands: set_session_vars() instead of patch.dict(os.environ) (ContextVar takes precedence over os.environ) - test_dm_topics: overwrite sys.modules + separate telegram.constants mock + force-reimport of gateway.platforms.telegram - test_terminal_tool_requirements: removed duplicate class declaration, autouse _clear_caches fixture * change(tests): run_tests.sh explicitly includes env vars instead of manually dropping some vars, now we just only include some * fix(tests): 5 more isolation/NixOS fixes - test_approval_plugin_hooks: isolate HERMES_HOME so real user's command_allowlist doesn't short-circuit the approval path - test_google_chat: skipif when Platform.GOOGLE_CHAT not in enum (feature not merged on this branch) - test_write_deny: test systemd prefix against tmp_path instead of /etc/systemd which resolves to /nix/store on NixOS - test_pty_bridge: use shutil.which('cat') instead of /bin/cat (doesn't exist on NixOS) - profiles.py: rmtree onexc handler chmod's parent dirs too, fixing profile deletion when copytree preserved read-only modes from nix store * fix(tests): clear unhealthy cache in autouse fixture for auxiliary_client * fix(tests): skip send_message when telegram not installed; handle missing worker_id in browser_supervisor * fix: py3.11 rmtree onexc compat + belt-and-suspenders unhealthy cache clear for expired codex test * fix: address PR #29016 review feedback - Remove tracked .pytest-cache/ artifact and add to .gitignore - Fix stale 'xdist worker' comment in conftest.py - Deduplicate web provider registration into tests/tools/conftest.py shared helper (register_all_web_providers), replacing 8 copy-pasted blocks across 6 test files - Update PR description: remove stale recovered-test-files claim, fix worker count to match code (cpu_count2) fix: eliminate race in stale-cache achievements test The background scan thread could complete and overwrite _SNAPSHOT_CACHE before evaluate_all() returned the stale data — only 10 fake sessions made the scan finish instantly. Added scan_delay param to _FakeSessionDB and set it to 2s in the stale-cache test so the background thread can't win the race.	15 天前
CONTRIBUTING.md	feat(sessions): opt-in per-session JSON snapshot writer PR #29182 deleted the per-session JSON snapshot writer outright because state.db is canonical and the snapshots had no in-tree consumer. Some users have external tooling that reads `~/.hermes/sessions/session_{sid}.json` directly, so reintroduce the writer behind a config flag that defaults to off. - Add `sessions.write_json_snapshots` (default False) to DEFAULT_CONFIG - Restore `AIAgent._save_session_log` + `_clean_session_content` as gated methods. When the flag is off the call is a fast no-op; when on, the writer behaves as before (atomic write, truncation guard preserved, REASONING_SCRATCHPAD → think tag normalization) - Re-derive the target path from `agent.session_id` on each call so `/branch` and `/compress` re-points happen automatically — no need to restore the explicit re-point bookkeeping at call sites - Wire the single call site in `_persist_session` (the cleanup-on-exit hook). Did NOT restore the 7 intra-turn calls the original PR deleted — those were redundant writes within the same turn that doubled disk I/O without adding any persistence guarantee `_persist_session` does not already provide - Read the flag once at agent init via `load_config()`, cache as `agent._session_json_enabled` - Update `TestNoSessionJsonSnapshot` → `TestSessionJsonSnapshotOptIn` to pin behavior: default off (no file), opt-in true (file written), no-op method on default agents, logs_dir retained unconditionally - Update CONTRIBUTING.md and the bundled `hermes-agent` skill to document the flag and its default	15 天前
Dockerfile	feat(config): add install-method stamping + Docker detection (#27843) * feat(config): add install-method stamping + Docker detection Dockerfile stamps "docker", install.sh stamps "git", and cmd_postinstall stamps "pip" into ~/.hermes/.install_method. detect_install_method() reads the stamp first, then falls back to managed-system / container / .git heuristics. Adds Docker upgrade guidance. Tracking: #27826 * fix(stamp): move Docker stamp to entrypoint, install.sh stamp after print_success The Dockerfile stamp was overwritten by the VOLUME overlay at container start. Moving it to entrypoint.sh ensures it persists. The install.sh stamp now writes after print_success so it only lands on full success.	18 天前
LICENSE	fix: restore missing MIT license file	2 个月前
MANIFEST.in	chore: prepare Hermes for Homebrew packaging (#4099) Co-authored-by: Yabuku-xD <78594762+Yabuku-xD@users.noreply.github.com>	2 个月前
README.md	docs(readme): add Nous Portal section between Getting Started and CLI/Messaging reference (#30941) A small, self-contained section under 'Skip the API-key collection — Nous Portal' explaining what Portal gives you (300+ models + Tool Gateway), the one-shot install command, and how to inspect routing. No buzzwords, no comparison tables, no overselling. Positioned right after 'Getting Started' so it lands where someone scanning the README has just seen the install steps and is deciding their next move. Skippable by anyone who already knows their provider. The line 'You can still bring your own keys per-tool whenever you want' is the deliberate honesty rail — Portal is an option, not a funnel. Existing per-provider language elsewhere in the README is unchanged. Mirrored to README.zh-CN.md to keep the two READMEs in sync.	13 天前
README.zh-CN.md	docs(readme): add Nous Portal section between Getting Started and CLI/Messaging reference (#30941) A small, self-contained section under 'Skip the API-key collection — Nous Portal' explaining what Portal gives you (300+ models + Tool Gateway), the one-shot install command, and how to inspect routing. No buzzwords, no comparison tables, no overselling. Positioned right after 'Getting Started' so it lands where someone scanning the README has just seen the install steps and is deciding their next move. Skippable by anyone who already knows their provider. The line 'You can still bring your own keys per-tool whenever you want' is the deliberate honesty rail — Portal is an option, not a funnel. Existing per-provider language elsewhere in the README is unchanged. Mirrored to README.zh-CN.md to keep the two READMEs in sync.	13 天前
RELEASE_v0.10.0.md	chore: release v0.10.0 (2026.4.16) (#11209) Tool Gateway release — paid Nous Portal subscribers get web search, image gen, TTS, and browser automation through their existing subscription.	1 个月前
RELEASE_v0.11.0.md	chore: release v0.11.0 (2026.4.23) (#14791) The Interface release — new Ink-based TUI, pluggable transport architecture, native AWS Bedrock, five new inference paths (NVIDIA NIM, Arcee, Step Plan, Gemini CLI OAuth, ai-gateway), GPT-5.5 via Codex OAuth, QQBot (17th platform), expanded plugin surface, dashboard plugin system + live theme switching, /steer mid-run nudges, shell hooks, webhook direct-delivery, smarter delegation, and auxiliary models config UI. Also folds in the v0.10.0 deferred batch (v0.10.0 shipped only the Nous Tool Gateway). 1,556 commits · 761 PRs · 290 contributors since v0.9.0.	1 个月前
RELEASE_v0.12.0.md	chore: release v0.12.0 (2026.4.30) (#18057) The Curator release — Hermes Agent now maintains itself. Autonomous background Curator grades, prunes, and consolidates the skill library; self-improvement loop substantially upgraded; four new inference providers; Microsoft Teams (via pluggable platforms) + Yuanbao as 18th and 19th messaging platforms; Spotify + Google Meet native integrations; ComfyUI + TouchDesigner-MCP bundled by default; Humanizer skill ported; ~57% cut to visible TUI cold start. Stats since v0.11.0: 1,096 commits, 550 merged PRs, 1,270 files changed, 217,776 insertions, 213 community contributors.	1 个月前
RELEASE_v0.13.0.md	chore: release v0.13.0 (2026.5.7) (#21406) The Tenacity Release — Hermes Agent now finishes what it starts. - Durable multi-agent Kanban with heartbeat, reclaim, zombie detection, retry budgets, hallucination gate - /goal persistent cross-turn goals (Ralph loop) - Checkpoints v2 single-store rewrite with real pruning - Gateway auto-resume interrupted sessions after restart - no_agent cron watchdog mode - Post-write delta lint on write_file + patch - 8 P0 security closures — redaction ON by default, CVSS 8.1 Discord fix, WhatsApp stranger rejection, MCP/auth TOCTOU, SSRF floor, cron prompt-injection skill scanning - Google Chat (20th platform) + generic platform-plugin hooks - ProviderProfile ABC + plugins/model-providers/ - 7 i18n locales (zh/ja/de/es/fr/uk/tr) + display.language - video_analyze tool, xAI Custom Voices, SearXNG, OpenRouter caching - MCP SSE transport + OAuth + image MEDIA surfacing - 864 commits, 588 merged PRs, 295 contributors	28 天前
RELEASE_v0.14.0.md	docs(release): expand v0.14.0 highlights with newcomer-friendly context (#27053) Each highlight now gets 2-3 sentences explaining the user-facing value, not just the technical change. Targeted at someone discovering Hermes for the first time who isn't deep in the codebase.	19 天前
RELEASE_v0.2.0.md	chore: rebuild changelog with correct time window (Feb 25 12PM PST onwards) Changelog now covers only v0.1.0 → v0.2.0 changes: - 216 merged PRs (not all 231) - 119 resolved issues - 63 contributors (not 74+) - Window: Feb 25 2026 12PM PST to present	2 个月前
RELEASE_v0.3.0.md	chore: release v0.3.0 (v2026.3.17) - Bump version 0.2.0 → 0.3.0 - Add comprehensive changelog (248 merged PRs, 15 contributors) - CalVer tag: v2026.3.17	2 个月前
RELEASE_v0.4.0.md	docs: revise v0.4.0 changelog — fix feature attribution, reorder sections	2 个月前
RELEASE_v0.5.0.md	chore: release v0.5.0 (v2026.3.28) (#3568) The hardening release — Nous Portal 400+ models, Hugging Face provider, Telegram Private Chat Topics, native Modal SDK, plugin lifecycle hooks, improved OpenAI model reliability, Nix flake, supply chain hardening, Anthropic output limits fix, and 50+ security/reliability fixes. 165 merged PRs, 65 closed issues across a 5-day window.	2 个月前
RELEASE_v0.6.0.md	chore: release v0.6.0 (2026.3.30) (#3985)	2 个月前
RELEASE_v0.7.0.md	chore: release v0.7.0 (2026.4.3) (#4812) 168 merged PRs, 223 commits, 46 resolved issues, 40+ contributors. Highlights: pluggable memory providers, credential pools, Camofox browser, inline diff previews, API server session continuity, ACP MCP registration, gateway hardening, secret exfiltration blocking.	2 个月前
RELEASE_v0.8.0.md	docs: update v0.8.0 highlights — notify_on_complete, MiMo v2 Pro, reorder	1 个月前
RELEASE_v0.9.0.md	fix: add contributor audit script + fix missed contributors (#9264) Three problems fixed: 1. bobashopcashier missing from v0.9.0 contributor list despite authoring the gateway drain PR (#7290, salvaged into #7503). Their email (kennyx102@gmail.com) was missing from AUTHOR_MAP. 2. release.py only scanned git commit authors, missing Co-authored-by trailers. Now parse_coauthors() extracts trailers from commit bodies. 3. No mechanism to detect contributors from salvaged PRs (where original author only appears in PR description, not git log). Changes: - scripts/release.py: add kennyx102@gmail.com to AUTHOR_MAP, enhance get_commits() to parse Co-authored-by trailers, filter AI assistants (Claude, Copilot, Cursor Agent) from co-author lists - scripts/contributor_audit.py: new script that cross-references git authors, co-author trailers, and salvaged PR descriptions. Reports unknown emails and contributors missing from release notes. - RELEASE_v0.9.0.md: add bobashopcashier to community contributors Usage: python scripts/contributor_audit.py --since-tag v2026.4.8 python scripts/contributor_audit.py --since-tag v2026.4.8 --release-file RELEASE_v0.9.0.md	1 个月前
SECURITY.md	changes from feedback	30 天前
batch_runner.py	feat(azure-foundry): add Microsoft Entra ID auth Use azure-identity DefaultAzureCredential for keyless Foundry auth. Preserve refreshable callable credentials through OpenAI and Anthropic client paths. Add setup, doctor, auth status, docs, and tests for Entra auth. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>	17 天前
cli-config.yaml.example	fix(provider): make config.yaml model.provider the single source of truth (#31222) Policy: if it ain't a secret it goes in config.yaml. HERMES_INFERENCE_PROVIDER was leaking behavioral config into the .env surface, including from the gateway, which bypassed config.yaml entirely. Behavior: - gateway/run.py: drop HERMES_INFERENCE_PROVIDER read in _resolve_runtime_agent_kwargs. Gateway now flows through resolve_runtime_provider() with no `requested` override, which reads model.provider from config.yaml first. Docs/UX (strip env var from user-facing surface): - --provider help text no longer mentions the env var - cli-config.yaml.example same - reference/environment-variables.md: remove HERMES_INFERENCE_PROVIDER row and the cross-reference from HERMES_INFERENCE_MODEL - reference/cli-commands.md: blank the env-var column for --provider - guides/xai-grok-oauth.md, guides/minimax-oauth.md: replace HERMES_INFERENCE_PROVIDER=x hermes invocations with config.yaml / --provider - developer-guide/adding-providers.md, model-provider-plugin.md: reframe Internal mechanism (kept as-is): - hermes_cli/main.py writes HERMES_INFERENCE_PROVIDER into the TUI subprocess env - tui_gateway/server.py reads it on TUI startup - resolve_requested_provider() / oneshot.py / cli.py still fall through to the env var as a last-resort behind config.yaml, which is what makes the TUI parent->child handoff work This stays. We just stop documenting it as a user knob. Tests: tests/gateway/test_auth_fallback.py — simplify mock to fail on first call, succeed on second; drop monkeypatch.setenv lines that no longer matter. Supersedes #31064 (closed with credit to @novax635 who surfaced the underlying issue but proposed aligning gateway to the env var rather than removing it).	12 天前
cli.py	fix(cli): decouple tool_progress=verbose from global DEBUG logging (#31379) PR #6a1aa420e coupled `display.tool_progress: verbose` (a per-tool display toggle for full args / results / think blocks) to `self.verbose` — which controls root-logger DEBUG level. Result: setting tool_progress: verbose in config silently flipped every module in the process to DEBUG and flooded the terminal with internal logging, far beyond just full tool calls. The two concepts are separate: - `tool_progress_mode == 'verbose'` → display behavior (tool rendering) - `self.verbose` → logging behavior (root logger → DEBUG, line 9795) This change keeps PR #6a1aa420e's argparse.SUPPRESS / config-fallback plumbing but severs the verbose-display → debug-logging link. Changes: - cli.py:2868 — `self.verbose` only follows explicit `verbose=` arg; no longer auto-True when tool_progress_mode == 'verbose'. - cli.py:_toggle_verbose — slash-cycle through tool progress modes no longer flips `self.verbose` / `agent.verbose_logging` / `agent.quiet_mode`. - cli.py:9355 — fix misleading label (drop 'and debug logs'). - tui_gateway/server.py:_make_agent — same decoupling on the TUI side (verbose_logging no longer derived from tool_progress_mode). - tests/cli/test_tool_progress_scrollback.py — invert the test that asserted the broken coupling; add coverage for explicit `--verbose` still enabling DEBUG independent of tool_progress. Live verified: - tool_progress: verbose, no --verbose flag → 0 DEBUG/INFO log lines - --verbose flag explicit → 32 DEBUG/INFO log lines (as expected)	12 天前
constraints-termux.txt	feat: add tested Termux install path and EOF-aware gh auth	1 个月前
docker-compose.yml	feat(plugins/google_chat): Google Chat platform adapter as a bundled plugin Adds Google Chat as a new gateway platform, shipped under plugins/platforms/google_chat/ following the canonical bundled-plugin pattern (Teams, IRC). Rewired from the original PR #18425 to use the new env_enablement_fn + cron_deliver_env_var plugin interfaces landed in the preceding commit, so the adapter touches ZERO core files. What it does: - Inbound DM + group messages via Cloud Pub/Sub pull subscription (no public URL needed), with attachments (PDFs, images, audio, video) downloaded through an SSRF-guarded Google-host allowlist. - Outbound text replies with the 'Hermes is thinking…' patch-in-place pattern — no tombstones. - Native file attachment delivery via per-user OAuth. Google Chat's media.upload endpoint rejects service-account auth, so each user runs /setup-files once in their own DM to grant chat.messages.create for themselves; the adapter then uploads as them. Tokens stored per email at ~/.hermes/google_chat_user_tokens/<email>.json. - Thread isolation: side-threads get isolated sessions, top-level DM messages share one continuous session. Persistent thread-count store survives gateway restart. - Supervisor reconnect with exponential backoff. - Multi-user out of the box. How it plugs in (no core edits): - env_enablement_fn seeds PlatformConfig.extra with project_id, subscription_name, service_account_json, and the home_channel dict (which the core hook turns into a HomeChannel dataclass). Reads GOOGLE_CHAT_PROJECT_ID (falls back to GOOGLE_CLOUD_PROJECT), GOOGLE_CHAT_SUBSCRIPTION_NAME (falls back to GOOGLE_CHAT_SUBSCRIPTION), GOOGLE_CHAT_SERVICE_ACCOUNT_JSON (falls back to GOOGLE_APPLICATION_CREDENTIALS), GOOGLE_CHAT_HOME_CHANNEL. - cron_deliver_env_var='GOOGLE_CHAT_HOME_CHANNEL' gets cron delivery for free — cron/scheduler.py consults the platform registry for any name not in its hardcoded built-in sets. - plugin.yaml's rich requires_env / optional_env blocks auto-populate OPTIONAL_ENV_VARS via the new hermes_cli/config.py injector, so 'hermes config' UI surfaces them with description / url / prompt / password metadata. - Module-level Platform('google_chat') call in adapter.py triggers the Platform._missing_() registration so Platform.GOOGLE_CHAT attribute access works without an enum entry. Distribution: ships inside the existing hermes-agent package. Users opt in via 'pip install hermes-agent[google_chat]' and follow the 8-step GCP walkthrough at website/docs/user-guide/messaging/google_chat.md. Test coverage: 153 tests in tests/gateway/test_google_chat.py, all passing. Spans platform registration, env config loading, Pub/Sub envelope routing, outbound send + chunking + typing patch-in-place, attachment send paths, SSRF guard, thread/session model, supervisor reconnect, authorization, per-user OAuth, and the new plugin-registry cron delivery wiring. Credit: adapter + OAuth + tests + docs authored by @donramon77 (PR #18425). Rewire onto the new plugin hooks + salvage commit by Teknium. Co-Authored-By: Ramón Fernández <112875006+donramon77@users.noreply.github.com>	28 天前
flake.lock	fix nix build	1 个月前
flake.nix	feat(nix): declarative plugin installation for NixOS module (#15953) * feat(nix): parameterize dependency-groups in python.nix * refactor(nix): extract package to callPackage-able hermes-agent.nix Makes the package overridable via .override{} and adds extraPythonPackages parameter for PYTHONPATH injection. Includes build-time collision check using PEP 503 name canonicalization. * feat(nix): add overlay for external NixOS consumption External flakes can now add overlays = [ inputs.hermes-agent.overlays.default ] to get pkgs.hermes-agent with full .override support. * test(nix): add check for extraPythonPackages PYTHONPATH injection Verifies wrapper has PYTHONPATH when extras provided, and base package has no PYTHONPATH without extras. * feat(nix): add extraPlugins option for directory-based plugins Symlinks plugin packages into HERMES_HOME/plugins/ at activation time. Validates plugin.yaml presence. Asserts unique plugin names at eval time. Hermes discovers them automatically via its directory scan. * feat(nix): add extraPythonPackages option for entry-point plugins Overrides the hermes package with PYTHONPATH injection when extraPythonPackages is non-empty. Plugin .dist-info directories become visible to importlib.metadata for entry-point discovery. Works in both native systemd and container modes. * docs: add NixOS declarative plugin installation to nix-setup, plugins, and build-a-plugin guides - nix-setup.md: new Plugins section with extraPlugins/extraPythonPackages examples, overlay usage, collision checking note, options reference rows - plugins.md: Nix row in discovery table, NixOS declarative plugins section - build-a-hermes-plugin.md: Distribute for NixOS section after pip section * fix: address review feedback — remove unrelated umask, fix fetchFromGitHub naming, simplify checks - Remove accidentally introduced umask/migration changes (unrelated to plugins) - Add pluginName helper, fix fetchFromGitHub producing name='source' - Show name= in extraPlugins example docs - Simplify checks.nix: use hermes-agent.override instead of re-callPackage - Fix fragile grep shell logic in checks * refactor: address simplify feedback — lib.getName, drop unused inputs', Python list for extras - Use lib.getName instead of custom pluginName helper - Drop unused inputs' from checks.nix perSystem args - Pass extraPythonPackages as Python list literal instead of colon-split string * fix: walk propagatedBuildInputs for plugin PYTHONPATH and collision check Uses python312.pkgs.requiredPythonModules to resolve the full transitive closure of extraPythonPackages. Without this, a plugin with third-party deps (e.g. requests) would fail at runtime if those deps weren't already in the sealed uv2nix venv. The collision check now also scans the full closure, catching transitive conflicts. * cleanup: fold plugins into subdir loop, use find for symlink cleanup, inline lib.getName - Add 'plugins' to the existing cron/sessions/logs/memories subdir loop instead of a separate mkdir/chown/chmod block - Replace fragile for-glob with find -delete for stale symlink cleanup - Inline lib.getName at both call sites, remove pluginName wrapper	1 个月前
hermes	fix: use argparse entrypoint in top-level launcher (#3874) The ./hermes convenience script still used the legacy Fire-based cli.main wrapper, which doesn't support subcommands (gateway, cron, doctor, etc.). The installed 'hermes' command already uses hermes_cli.main:main (argparse) — this aligns the launcher. Salvaged from PR #2009 by gito369.	2 个月前
hermes-already-has-routines.md	docs: automation templates gallery + comparison post (#9821) * feat(skills): add fitness-nutrition skill to optional-skills Cherry-picked from PR #9177 by @haileymarshall. Adds a fitness and nutrition skill for gym-goers and health-conscious users: - Exercise search via wger API (690+ exercises, free, no auth) - Nutrition lookup via USDA FoodData Central (380K+ foods, DEMO_KEY fallback) - Offline body composition calculators (BMI, TDEE, 1RM, macros, body fat %) - Pure stdlib Python, no pip dependencies Changes from original PR: - Moved from skills/ to optional-skills/health/ (correct location) - Fixed BMR formula in FORMULAS.md (removed confusing -5+10, now just +5) - Fixed author attribution to match PR submitter - Marked USDA_API_KEY as optional (DEMO_KEY works without signup) Also adds optional env var support to the skill readiness checker: - New 'optional: true' field in required_environment_variables entries - Optional vars are preserved in metadata but don't block skill readiness - Optional vars skip the CLI capture prompt flow - Skills with only optional missing vars show as 'available' not 'setup_needed' * docs: add automation templates gallery and comparison post - New docs page: guides/automation-templates.md with 15+ ready-to-use automation recipes covering development workflow, devops, research, GitHub events, and business operations - Comparison post (hermes-already-has-routines.md) showing Hermes has had schedule/webhook/API triggers since March 2026 - Added automation-templates to sidebar navigation --------- Co-authored-by: haileymarshall <haileymarshall@users.noreply.github.com>	1 个月前
hermes_bootstrap.py	hermes_bootstrap: Windows-only UTF-8 stdio shim for all entry points Codebase-wide fix for Python-on-Windows UTF-8 footguns, complementing the earlier execute_code sandbox fixes (which remain load-bearing for when the sandbox explicitly scrubs child env). Problem: Python on Windows has two long-standing text-encoding pitfalls: 1. sys.stdout/stderr are bound to the console code page (cp1252 on US-locale installs) — print('café') crashes with UnicodeEncodeError. 2. Subprocess children don't know to use UTF-8 unless PYTHONUTF8 and/or PYTHONIOENCODING are set in their env — so any Python we spawn (linters, sandbox children, delegation workers) hits the same bug. Solution: A tiny bootstrap module (hermes_bootstrap.py) imported as the first statement of every Hermes entry point: - hermes_cli/main.py (hermes / hermes-agent console_script) - run_agent.py (hermes-agent direct) - acp_adapter/entry.py (hermes-acp) - gateway/run.py (messaging gateway) - batch_runner.py (parallel batch mode) - cli.py (legacy direct-launch CLI) On Windows, the bootstrap: - os.environ.setdefault('PYTHONUTF8', '1') (PEP 540 UTF-8 mode) - os.environ.setdefault('PYTHONIOENCODING', 'utf-8') - sys.stdout/stderr/stdin.reconfigure(encoding='utf-8', errors='replace') Children inherit the env vars → they run in UTF-8 mode. Current process's stdio is reconfigured → print('café') works now. On POSIX (Linux/macOS), the bootstrap is a complete no-op. We don't touch LANG, LC_, or anything else — users who have intentionally configured a non-UTF-8 locale aren't affected. POSIX systems are already UTF-8 by default in 99% of modern setups, so there's nothing to fix. setdefault() (not overwrite) means users who explicitly set PYTHONUTF8=0 or PYTHONIOENCODING=cp1252 in their environment are respected. What this does NOT fix: bare open(path, 'w') calls in the parent* process still default to locale encoding because PYTHONUTF8 is only read at interpreter init. A ruff PLW1514 sweep (separate follow-up) will add explicit encoding='utf-8' at those ~219 call sites for belt-and-suspenders. Tests (17): 16 passed, 1 skipped on Windows. - Windows: env vars set, stdio reconfigured, child inherits UTF-8 mode - POSIX: complete no-op (verified on fake POSIX + skipped on real POSIX since we don't have a Linux box in this session) - Idempotence: multiple calls safe - Graceful degradation: non-reconfigurable streams don't crash - User opt-out: explicit PYTHONUTF8=0 is respected - Load order: every entry point's FIRST top-level import is hermes_bootstrap, enforced by an AST-level parametrized test pyproject.toml: added hermes_bootstrap to py-modules so it ships with pip installs.	27 天前
hermes_constants.py	style: docstring + whitespace cleanup on secure_parent_dir - Drop two extra blank lines between display_hermes_home and secure_parent_dir - Fix docstring saying 'depth < 2' (actual guard is parts < 3)	15 天前
hermes_logging.py	fix: include hermes_plugins in gateway.log component filter gateway.log uses a _ComponentFilter that only passes records from loggers starting with ('gateway',). Plugin modules are loaded under the hermes_plugins.* namespace, so all plugin log output is silently dropped from gateway.log. This makes plugin registration — which directly affects gateway hooks (pre_gateway_dispatch, transform_llm_output, etc.) — invisible in the gateway-specific log. Operators debugging gateway behavior check gateway.log and see no plugin activity, even when plugins are working correctly. Add 'hermes_plugins' to the gateway component prefixes tuple so plugin log messages appear in gateway.log. Closes #28138	17 天前
hermes_state.py	fix(gateway): separate observed Telegram group context	13 天前
hermes_time.py	codebase: add encoding='utf-8' to all bare open() calls (PLW1514) Closes the last Python-on-Windows UTF-8 exposure by making every text-mode open() call explicit about its encoding. Before: on Windows, bare open(path, 'r') defaults to the system locale encoding (cp1252 on US-locale installs). That means reading any config/yaml/markdown/json file with non-ASCII content either crashes with UnicodeDecodeError or silently mis-decodes bytes. After: all 89 affected call sites in production code now pass encoding='utf-8' explicitly. Works identically on every platform and every locale, no surprise behavior. Mechanical sweep via: ruff check --preview --extend-select PLW1514 --unsafe-fixes --fix --exclude 'tests,venv,.venv,node_modules,website,optional-skills, skills,tinker-atropos,plugins' . All 89 fixes have the same shape: open(x) or open(x, mode) became open(x, encoding='utf-8') or open(x, mode, encoding='utf-8'). Nothing else changed. Every modified file still parses and the Windows/sandbox test suite is still green (85 passed, 14 skipped, 0 failed across tests/tools/test_code_execution_windows_env.py + tests/tools/test_code_execution_modes.py + tests/tools/test_env_passthrough.py + tests/test_hermes_bootstrap.py). Scope notes: - tests/ excluded: test fixtures can use locale encoding intentionally (exercising edge cases). If we want to tighten tests later that's a separate PR. - plugins/ excluded: plugin-specific conventions may differ; plugin authors own their code. - optional-skills/ and skills/ excluded: skill scripts are user-authored and we don't want to mass-edit them. - website/ and tinker-atropos/ excluded: vendored / generated content. 46 files touched, 89 +/- lines (symmetric replacement). No behavior change on POSIX or on Windows when the file is ASCII; bug fix on Windows when the file contains non-ASCII.	27 天前
mcp_serve.py	chore: ruff auto-fix PLR6201 — tuple → set in membership tests (#23937) Replace with for all literal-tuple membership tests. Set lookup is O(1) vs O(n) for tuple — consistent micro-optimization across the codebase. 608 instances fixed via `ruff --fix --unsafe-fixes`, 0 remaining. 133 files, +626/-626 (net zero).	24 天前
mini_swe_runner.py	fix(agent): set tool_name on tool-result messages at construction time Introduces make_tool_result_message() in tool_dispatch_helpers.py as the single place where tool-result message dicts are built. All six construction sites in tool_executor.py, agent_runtime_helpers.py, and mini_swe_runner.py now use it, so tool_name is set in memory from the moment a message is created rather than relying on fallback logic in the flush paths. Fixes blank tool_name in both state.db and JSON session logs. Adds tests.	16 天前
model_tools.py	fix(kanban): preserve worker tools with restricted toolsets	17 天前
package-lock.json	fix(update): make Camofox lazy-installed instead of eager (#27055) The `@askjo/camofox-browser` npm package was a top-level entry in the root `package.json` `dependencies` block, so `hermes update` ran its postinstall on every user, every update. That postinstall calls `npx camoufox-js fetch`, which silently downloads a ~300MB Firefox-fork browser binary from GitHub Releases — multi-minute on fast connections, and a hard block for users on slow / restricted networks (notably users in China running through a VPN). Camofox is an explicit opt-in browser backend. The runtime check in `tools/browser_tool.py` only routes through Camofox when the user has set `CAMOFOX_URL` (selected via `hermes tools` → Browser Automation → Camofox). Users who never opted in never touched the package at runtime, yet every `hermes update` paid for the binary fetch anyway. This change: * Removes `@askjo/camofox-browser` from root `package.json` dependencies (and the regenerated `package-lock.json` drops Camofox's entire transitive tree, ~2.6k lines). * Updates the Camofox `post_setup` handler in `hermes_cli/tools_config.py` to install `@askjo/camofox-browser@^1.5.2` explicitly when the user selects Camofox, and streams npm output (no `--silent`, no `capture_output`) so the ~300MB download is visible rather than appearing frozen. * Adds `tests/test_package_json_lazy_deps.py` as a regression guard so future PRs can't silently re-add Camofox (or any binary-postinstall package) to eager root dependencies. `agent-browser` stays eager — it is the default Chromium-driving backend used by every session that does not have a cloud browser provider configured, and its postinstall is small. Validation: \| \| Before \| After \| \|---\|---\|---\| \| `hermes update` time on slow network \| multi-minute hang at `→ Updating Node.js dependencies...` \| seconds (no binary fetch) \| \| Camofox opt-in install visibility \| silent, looked frozen \| streamed npm output \| \| Regression guard against re-adding \| none \| `test_package_json_lazy_deps.py` \| Tests: - `tests/test_package_json_lazy_deps.py`: 3/3 pass - `tests/tools/test_browser_camofox*`: 92/92 pass - `tests/hermes_cli/test_tools_config.py`: 66/66 pass - `tests/hermes_cli/test_cmd_update.py` + adjacent: green Reported by lulu (Discord, May 2026) — `hermes update` hangs at `→ Updating Node.js dependencies...` in China. Related: #18840, #18869.	19 天前
package.json	fix(update): make Camofox lazy-installed instead of eager (#27055) The `@askjo/camofox-browser` npm package was a top-level entry in the root `package.json` `dependencies` block, so `hermes update` ran its postinstall on every user, every update. That postinstall calls `npx camoufox-js fetch`, which silently downloads a ~300MB Firefox-fork browser binary from GitHub Releases — multi-minute on fast connections, and a hard block for users on slow / restricted networks (notably users in China running through a VPN). Camofox is an explicit opt-in browser backend. The runtime check in `tools/browser_tool.py` only routes through Camofox when the user has set `CAMOFOX_URL` (selected via `hermes tools` → Browser Automation → Camofox). Users who never opted in never touched the package at runtime, yet every `hermes update` paid for the binary fetch anyway. This change: * Removes `@askjo/camofox-browser` from root `package.json` dependencies (and the regenerated `package-lock.json` drops Camofox's entire transitive tree, ~2.6k lines). * Updates the Camofox `post_setup` handler in `hermes_cli/tools_config.py` to install `@askjo/camofox-browser@^1.5.2` explicitly when the user selects Camofox, and streams npm output (no `--silent`, no `capture_output`) so the ~300MB download is visible rather than appearing frozen. * Adds `tests/test_package_json_lazy_deps.py` as a regression guard so future PRs can't silently re-add Camofox (or any binary-postinstall package) to eager root dependencies. `agent-browser` stays eager — it is the default Chromium-driving backend used by every session that does not have a cloud browser provider configured, and its postinstall is small. Validation: \| \| Before \| After \| \|---\|---\|---\| \| `hermes update` time on slow network \| multi-minute hang at `→ Updating Node.js dependencies...` \| seconds (no binary fetch) \| \| Camofox opt-in install visibility \| silent, looked frozen \| streamed npm output \| \| Regression guard against re-adding \| none \| `test_package_json_lazy_deps.py` \| Tests: - `tests/test_package_json_lazy_deps.py`: 3/3 pass - `tests/tools/test_browser_camofox*`: 92/92 pass - `tests/hermes_cli/test_tools_config.py`: 66/66 pass - `tests/hermes_cli/test_cmd_update.py` + adjacent: green Reported by lulu (Discord, May 2026) — `hermes update` hangs at `→ Updating Node.js dependencies...` in China. Related: #18840, #18869.	19 天前
pyproject.toml	test: use subprocesses for each test file (#29016) * ci(tests): install ripgrep from prebuilt tarball instead of apt apt-get update + install of ripgrep takes ~4 min on the GHA Ubuntu runners (the apt-get update against archive.ubuntu.com is the slow part; ripgrep itself is small). Switching to the upstream musl binary tarball cuts the step to a few seconds. - Pinned to ripgrep 15.1.0 with sha256 verification (same hash as published in the releases sha256 sidecar file). - Drops the `rg` binary into /usr/local/bin so it is on PATH for every subsequent step without GITHUB_PATH manipulation. - Applied to both the test and e2e jobs in tests.yml. * fix(cli): compile syntax check to tempdir, not source __pycache__ `_validate_critical_files_syntax` runs `py_compile.compile()` on each critical bootstrap file after a successful `git pull`. The default `py_compile` writes the resulting `.pyc` next to the source under `__pycache__/`, which causes two real problems: 1. Parallel test workers walking the same source tree (e.g. running the suite under per-file process isolation) can race against each other on the `__pycache__` write — manifests as flaky 'directory not empty' errors during teardown. 2. In production, the post-pull syntax check leaves a `.pyc` behind that the next interpreter run might pick up — fine when the interpreter version matches, sketchy if it doesn't. Fix: write the compiled output to a `tempfile.TemporaryDirectory()` that's discarded on function exit. We only care about the compile-or-not signal, not the artifact. * test(runner): per-file process isolation, drop manual state reset + xdist Replace fragile manual _reset_module_state test fixtures with robust per-file subprocess isolation. Each test file runs in a fresh `python -m pytest <file>` subprocess via ThreadPoolExecutor. No xdist, no custom pytest plugin, no shared worker state. Key changes: * scripts/run_tests_parallel.py — new runner: discovers test files, runs N in parallel via ThreadPoolExecutor, captures stdout per file, treats exit code 5 (no tests collected) as pass, kills all children on exit. Change from cpu_count to cpu_count2. The runner is I/O-bound (waiting on subprocess.communicate() from pytest children) The parent process does almost no CPU work, so 2x oversubscription keeps more pipes full. When a file fails, immediately show the last 30 lines of pytest output (stack traces + FAILED summary) plus a ready-to-copy repro command: python -m pytest tests/agent/test_auxiliary_client.py scripts/run_tests.sh — delegates to run_tests_parallel.py * .github/workflows/tests.yml — test step: python scripts/run_tests_parallel.py * pyproject.toml — drop pytest-xdist, pytest-split; simplify addopts * tests/conftest.py — remove ~200 lines of manual state-reset fixtures * AGENTS.md — update Testing section for per-file design * test(runner): speed gateway test antipattern scan up * fix(test): web search provider plugin test missing xai * fix(tests): make 14 test files pass under per-file subprocess isolation Tests that relied on cross-file state pollution from xdist workers fail when run in isolation (per-file subprocess model). Root causes and fixes: Tool registry not populated: - test_video_generation_tool_surface_matrix: add discover_builtin_tools() - test_web_providers_brave_free/ddgs/searxng/general: autouse fixtures registering all 8 bundled web providers, reset after each test - test_website_policy: same provider registration pattern - test_web_tools_tavily: same pattern across 3 dispatch test classes - Also add is_safe_url/check_website_access mocks where SSRF check blocks example.com (DNS resolution fails in isolated envs) Stale check_fn cache: - test_kanban_tools: invalidate_check_fn_cache() + _clear_tool_defs_cache() in both kanban guidance tests (prior test cached False for kanban_show) - test_discord_tool: cache invalidation in setup/teardown - test_homeassistant_tool: invalidate_check_fn_cache() before registry queries Module-level state pollution: - test_auxiliary_client: autouse fixture clearing _aux_unhealthy_until cache - test_skill_commands: set_session_vars() instead of patch.dict(os.environ) (ContextVar takes precedence over os.environ) - test_dm_topics: overwrite sys.modules + separate telegram.constants mock + force-reimport of gateway.platforms.telegram - test_terminal_tool_requirements: removed duplicate class declaration, autouse _clear_caches fixture * change(tests): run_tests.sh explicitly includes env vars instead of manually dropping some vars, now we just only include some * fix(tests): 5 more isolation/NixOS fixes - test_approval_plugin_hooks: isolate HERMES_HOME so real user's command_allowlist doesn't short-circuit the approval path - test_google_chat: skipif when Platform.GOOGLE_CHAT not in enum (feature not merged on this branch) - test_write_deny: test systemd prefix against tmp_path instead of /etc/systemd which resolves to /nix/store on NixOS - test_pty_bridge: use shutil.which('cat') instead of /bin/cat (doesn't exist on NixOS) - profiles.py: rmtree onexc handler chmod's parent dirs too, fixing profile deletion when copytree preserved read-only modes from nix store * fix(tests): clear unhealthy cache in autouse fixture for auxiliary_client * fix(tests): skip send_message when telegram not installed; handle missing worker_id in browser_supervisor * fix: py3.11 rmtree onexc compat + belt-and-suspenders unhealthy cache clear for expired codex test * fix: address PR #29016 review feedback - Remove tracked .pytest-cache/ artifact and add to .gitignore - Fix stale 'xdist worker' comment in conftest.py - Deduplicate web provider registration into tests/tools/conftest.py shared helper (register_all_web_providers), replacing 8 copy-pasted blocks across 6 test files - Update PR description: remove stale recovered-test-files claim, fix worker count to match code (cpu_count2) fix: eliminate race in stale-cache achievements test The background scan thread could complete and overwrite _SNAPSHOT_CACHE before evaluate_all() returned the stale data — only 10 fake sessions made the scan finish instantly. Added scan_delay param to _FakeSessionDB and set it to 2s in the stale-cache test so the background thread can't win the race.	15 天前
run_agent.py	fix(xai-oauth): honor [WKE=unauthenticated:...] disambiguator in entitlement classifier (#29344) `_is_entitlement_failure` over-matched on xAI 403s. xAI returns the same permission-denied `code` text for two distinct conditions: 1. Unsubscribed account ("active Grok subscription. Manage at https://grok.com" in the `error` field). 2. Stale OAuth access token ("OAuth2 access token could not be validated. [WKE=unauthenticated:bad-credentials]" in the `error` field). The classifier's "does not have permission + grok" substring heuristic treated both identically, so the credential-pool refresh path was short-circuited for case (2) — long-running TUI sessions stuck on a stale OAuth token surfaced a non-retryable client error and the user had to exit + reopen the TUI to recover (the startup-resolve path bypasses the classifier entirely, which is why bridge adapters with proactive refresh cadences didn't see this in practice). This patch adopts the reporter's recommended fix (option 1, tightest): honor xAI's explicit `[WKE=unauthenticated:...]` suffix and the `OAuth2 access token could not be validated` phrasing as authoritative "this is auth, not entitlement" signals. When either appears anywhere in the body's text fields, the classifier returns False eagerly — before the entitlement keyword checks run — so the refresh-on-401 path takes over and the existing loop-protection still guards against runaway refresh storms if the refresh itself fails. Two small adjustments fall out of this: * The haystack now also covers `code` and `error` keys directly, not just the `message`/`reason` shape `_extract_api_error_context` produces. Real runtime paths use the normalised shape, but the test suite and any future call sites that pass raw bodies get the same treatment. Backwards compatible: missing keys default to empty strings, the haystack still skips when everything is blank. * Both disambiguator checks fire BEFORE the entitlement keyword checks. If a future xAI body somehow lands with both an entitlement message AND the WKE suffix, the WKE suffix wins (correct — auth is recoverable; entitlement is not, and a refreshed token will surface the entitlement message on the next request anyway). Existing tests (`test_is_entitlement_failure_matches_real_xai_bodies`, `test_is_entitlement_failure_false_for_unrelated_auth_errors`, `test_recover_with_credential_pool_skips_refresh_on_entitlement_403`, `test_recover_with_credential_pool_still_refreshes_genuine_auth_failure`) continue to pass unchanged — the unsubscribed-account path, the generic auth-error path, and the refresh-on-401 path are all left intact.	13 天前
setup-hermes.sh	chore: remove Atropos RL environments and tinker-atropos integration (#26106) * chore: remove Atropos RL environments, tools, tests, skill, and tinker-atropos submodule Delete: - environments/ (43 files — base env, agent loop, tool call parsers, benchmarks) - rl_cli.py (standalone RL training CLI) - tools/rl_training_tool.py (all 10 rl_* tools) - tests: test_rl_training_tool, test_tool_call_parsers, test_managed_server_tool_support, test_agent_loop, test_agent_loop_vllm, test_agent_loop_tool_calling, test_terminalbench2_env_security - optional-skills/mlops/hermes-atropos-environments/ - tinker-atropos git submodule + .gitmodules * chore: remove RL/Atropos references from Python source - toolsets.py: remove rl toolset block + update comment - model_tools.py: remove rl_tools group + update async bridging comment - hermes_cli/tools_config.py: remove RL display entry, _DEFAULT_OFF_TOOLSETS, setup block, and rl_training post-setup handler - tools/budget_config.py: remove RL environment reference in docstring - tests/test_model_tools.py: remove rl_tools from expected groups - tests/run_agent/test_streaming_tool_call_repair.py: fix stale cross-reference * chore: remove rl/yc-bench extras and tinker-atropos refs from pyproject.toml - Remove rl extra (atroposlib, tinker, fastapi, uvicorn, wandb) - Remove yc-bench extra - Remove rl_cli from py-modules - Remove [tool.ty.src] exclude for tinker-atropos - Remove [tool.ruff] exclude for tinker-atropos - Regenerate uv.lock * chore: remove tinker-atropos from install/setup scripts - setup-hermes.sh: remove entire tinker-atropos submodule install block - scripts/install.sh: remove both tinker-atropos blocks (Termux + standard) - scripts/install.ps1: remove tinker-atropos block - nix/hermes-agent.nix: remove tinker-atropos pip install line * chore: remove RL references from cli-config.yaml.example * docs: remove Atropos/RL references from README, CONTRIBUTING, AGENTS.md * docs: remove RL/Atropos references from website - Delete: environments.md, rl-training.md, mlops-hermes-atropos-environments.md - sidebars.ts: remove rl-training and environments sidebar entries - optional-skills-catalog.md: remove hermes-atropos-environments row - tools-reference.md: remove entire rl toolset section - toolsets-reference.md: remove rl row + update example - integrations/index.md: remove RL Training bullet - architecture.md: remove environments/ from tree + RL section - contributing.md: remove tinker-atropos setup - updating.md: remove tinker-atropos install + stale submodule update * chore: remove remaining RL/Atropos stragglers - hermes_cli/config.py: remove TINKER_API_KEY + WANDB_API_KEY env var defs - hermes_cli/doctor.py: remove Submodules check section (tinker-atropos) - hermes_cli/setup.py: remove RL Training status check - hermes_cli/status.py: remove Tinker + WandB from API key status display - agent/display.py: remove both rl_* tool preview/activity blocks - website/docs: remove RL references from providers.md + env-variables.md - tests: remove TINKER_API_KEY from conftest, set_config_value, setup_script * chore: remove RL training section from .env.example	21 天前
setup.py	fix(packaging): ship bundled skills in wheel Salvages #23738 by @LeonSGP43. Wheel installs were missing skills/ and optional-skills/ because pyproject's [tool.setuptools.packages.find] only includes Python packages — the skills directories don't have __init__.py so they were silently dropped from the wheel. Adds setup.py with data_files spec emitting skills/* and optional-skills/* under hermes_agent-<v>.data/data/, and a get_bundled_skills_dir() helper in hermes_constants that discovers the wheel-installed location via sysconfig before falling back to a source-checkout path. tools/skills_sync uses the helper so 'hermes update' works for pip-installed users.	17 天前
toolset_distributions.py	chore: fix 154 f-strings, simplify getattr/URL patterns, remove dead code (#3119) Three categories of cleanup, all zero-behavioral-change: 1. F-strings without placeholders (154 fixes across 29 files) - Converted f'...' to '...' where no {expression} was present - Heaviest files: run_agent.py (24), cli.py (20), honcho_integration/cli.py (34) 2. Simplify defensive patterns in run_agent.py - Added explicit self._is_anthropic_oauth = False in __init__ (before the api_mode branch that conditionally sets it) - Replaced 7x getattr(self, '_is_anthropic_oauth', False) with direct self._is_anthropic_oauth (attribute always initialized now) - Added _is_openrouter_url() and _is_anthropic_url() helper methods - Replaced 3 inline 'openrouter' in self._base_url_lower checks 3. Remove dead code in small files - hermes_cli/claw.py: removed unused 'total' computation - tools/fuzzy_match.py: removed unused strip_indent() function and pattern_stripped variable Full test suite: 6184 passed, 0 failures E2E PTY: banner clean, tool calls work, zero garbled ANSI	2 个月前
toolsets.py	security: restrict default webhook toolset capabilities (#30745)	12 天前
trajectory_compressor.py	fix: guard yaml.safe_load, flock unlock, TOCTOU races, and atomic writes 1. trajectory_compressor.py: yaml.safe_load() returns None on empty files, crashing with TypeError on `if 'tokenizer' in data`. Fix by adding `or {}` fallback. (HIGH — blocks startup with empty config) 2. 6 files with fcntl.flock(LOCK_UN) in finally blocks without try/except: cron/scheduler.py, hermes_cli/auth.py, agent/shell_hooks.py, tools/skill_usage.py, tools/environments/file_sync.py, tools/memory_tool.py. If unlock raises OSError, fd.close() is skipped and the lock is held forever. The msvcrt branches already had try/except; the fcntl branches did not. Fix by wrapping in try/except (OSError, IOError): pass. 3. agent/copilot_acp_client.py line 639: TOCTOU race — path.exists() followed by path.read_text() with no try/except. If file is deleted between the check and the read, FileNotFoundError propagates. Fix by using try/except FileNotFoundError. 4. gateway/sticker_cache.py: non-atomic write via Path.write_text() can leave truncated JSON on crash, causing JSONDecodeError on next load. Fix by writing to tempfile + fsync + os.replace (atomic).	17 天前
utils.py	fix(cli): preserve config comments on setting writes	26 天前
uv.lock	test: use subprocesses for each test file (#29016) * ci(tests): install ripgrep from prebuilt tarball instead of apt apt-get update + install of ripgrep takes ~4 min on the GHA Ubuntu runners (the apt-get update against archive.ubuntu.com is the slow part; ripgrep itself is small). Switching to the upstream musl binary tarball cuts the step to a few seconds. - Pinned to ripgrep 15.1.0 with sha256 verification (same hash as published in the releases sha256 sidecar file). - Drops the `rg` binary into /usr/local/bin so it is on PATH for every subsequent step without GITHUB_PATH manipulation. - Applied to both the test and e2e jobs in tests.yml. * fix(cli): compile syntax check to tempdir, not source __pycache__ `_validate_critical_files_syntax` runs `py_compile.compile()` on each critical bootstrap file after a successful `git pull`. The default `py_compile` writes the resulting `.pyc` next to the source under `__pycache__/`, which causes two real problems: 1. Parallel test workers walking the same source tree (e.g. running the suite under per-file process isolation) can race against each other on the `__pycache__` write — manifests as flaky 'directory not empty' errors during teardown. 2. In production, the post-pull syntax check leaves a `.pyc` behind that the next interpreter run might pick up — fine when the interpreter version matches, sketchy if it doesn't. Fix: write the compiled output to a `tempfile.TemporaryDirectory()` that's discarded on function exit. We only care about the compile-or-not signal, not the artifact. * test(runner): per-file process isolation, drop manual state reset + xdist Replace fragile manual _reset_module_state test fixtures with robust per-file subprocess isolation. Each test file runs in a fresh `python -m pytest <file>` subprocess via ThreadPoolExecutor. No xdist, no custom pytest plugin, no shared worker state. Key changes: * scripts/run_tests_parallel.py — new runner: discovers test files, runs N in parallel via ThreadPoolExecutor, captures stdout per file, treats exit code 5 (no tests collected) as pass, kills all children on exit. Change from cpu_count to cpu_count2. The runner is I/O-bound (waiting on subprocess.communicate() from pytest children) The parent process does almost no CPU work, so 2x oversubscription keeps more pipes full. When a file fails, immediately show the last 30 lines of pytest output (stack traces + FAILED summary) plus a ready-to-copy repro command: python -m pytest tests/agent/test_auxiliary_client.py scripts/run_tests.sh — delegates to run_tests_parallel.py * .github/workflows/tests.yml — test step: python scripts/run_tests_parallel.py * pyproject.toml — drop pytest-xdist, pytest-split; simplify addopts * tests/conftest.py — remove ~200 lines of manual state-reset fixtures * AGENTS.md — update Testing section for per-file design * test(runner): speed gateway test antipattern scan up * fix(test): web search provider plugin test missing xai * fix(tests): make 14 test files pass under per-file subprocess isolation Tests that relied on cross-file state pollution from xdist workers fail when run in isolation (per-file subprocess model). Root causes and fixes: Tool registry not populated: - test_video_generation_tool_surface_matrix: add discover_builtin_tools() - test_web_providers_brave_free/ddgs/searxng/general: autouse fixtures registering all 8 bundled web providers, reset after each test - test_website_policy: same provider registration pattern - test_web_tools_tavily: same pattern across 3 dispatch test classes - Also add is_safe_url/check_website_access mocks where SSRF check blocks example.com (DNS resolution fails in isolated envs) Stale check_fn cache: - test_kanban_tools: invalidate_check_fn_cache() + _clear_tool_defs_cache() in both kanban guidance tests (prior test cached False for kanban_show) - test_discord_tool: cache invalidation in setup/teardown - test_homeassistant_tool: invalidate_check_fn_cache() before registry queries Module-level state pollution: - test_auxiliary_client: autouse fixture clearing _aux_unhealthy_until cache - test_skill_commands: set_session_vars() instead of patch.dict(os.environ) (ContextVar takes precedence over os.environ) - test_dm_topics: overwrite sys.modules + separate telegram.constants mock + force-reimport of gateway.platforms.telegram - test_terminal_tool_requirements: removed duplicate class declaration, autouse _clear_caches fixture * change(tests): run_tests.sh explicitly includes env vars instead of manually dropping some vars, now we just only include some * fix(tests): 5 more isolation/NixOS fixes - test_approval_plugin_hooks: isolate HERMES_HOME so real user's command_allowlist doesn't short-circuit the approval path - test_google_chat: skipif when Platform.GOOGLE_CHAT not in enum (feature not merged on this branch) - test_write_deny: test systemd prefix against tmp_path instead of /etc/systemd which resolves to /nix/store on NixOS - test_pty_bridge: use shutil.which('cat') instead of /bin/cat (doesn't exist on NixOS) - profiles.py: rmtree onexc handler chmod's parent dirs too, fixing profile deletion when copytree preserved read-only modes from nix store * fix(tests): clear unhealthy cache in autouse fixture for auxiliary_client * fix(tests): skip send_message when telegram not installed; handle missing worker_id in browser_supervisor * fix: py3.11 rmtree onexc compat + belt-and-suspenders unhealthy cache clear for expired codex test * fix: address PR #29016 review feedback - Remove tracked .pytest-cache/ artifact and add to .gitignore - Fix stale 'xdist worker' comment in conftest.py - Deduplicate web provider registration into tests/tools/conftest.py shared helper (register_all_web_providers), replacing 8 copy-pasted blocks across 6 test files - Update PR description: remove stale recovered-test-files claim, fix worker count to match code (cpu_count2) fix: eliminate race in stale-cache achievements test The background scan thread could complete and overwrite _SNAPSHOT_CACHE before evaluate_all() returned the stale data — only 10 fake sessions made the scan finish instantly. Added scan_delay param to _FakeSessionDB and set it to 2s in the stale-cache test so the background thread can't win the race.	15 天前

Hermes Agent ☤

由 Nous Research 构建的自进化 AI 代理。 它是唯一内置学习闭环的智能代理——从经验中创建技能，在使用中改进技能，主动持久化知识，搜索过往对话，并在跨会话中逐步构建对你的深度理解。可以在 $5 的 VPS 上运行，也可以在 GPU 集群上运行，或者使用几乎零成本的 Serverless 基础设施。它不绑定你的笔记本——你可以在 Telegram 上与它对话，而它在云端 VM 上工作。

支持任意模型——Nous Portal、OpenRouter（200+ 模型）、NVIDIA NIM（Nemotron）、小米 MiMo、z.ai/GLM、Kimi/Moonshot、MiniMax、Hugging Face、OpenAI，或自定义端点。使用 hermes model 即可切换——无需改代码，无锁定。

真正的终端界面	完整的 TUI，支持多行编辑、斜杠命令自动补全、对话历史、中断重定向和流式工具输出。
随你所在	Telegram、Discord、Slack、WhatsApp、Signal 和 CLI——全部从单个网关进程运行。语音备忘录转写、跨平台对话连续性。
闭环学习	代理管理记忆并定期自我提醒。复杂任务后自动创建技能。技能在使用中自我改进。FTS5 会话搜索配合 LLM 摘要实现跨会话回溯。Honcho 辩证式用户建模。兼容 agentskills.io 开放标准。
定时自动化	内置 cron 调度器，支持向任何平台投递。日报、夜间备份、周审计——全部用自然语言描述，无人值守运行。
委派与并行	生成隔离子代理处理并行工作流。编写 Python 脚本通过 RPC 调用工具，将多步管道压缩为零上下文开销的轮次。
随处运行	六种终端后端——本地、Docker、SSH、Daytona、Singularity 和 Modal。Daytona 和 Modal 提供 Serverless 持久化——代理环境空闲时休眠、按需唤醒，空闲期间几乎零成本。$5 VPS 或 GPU 集群都能跑。
研究就绪	批量轨迹生成、轨迹压缩——用于训练下一代工具调用模型。

快速安装

curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

支持 Linux、macOS、WSL2 和 Android (Termux)。安装程序会自动处理平台特定的配置。

Android / Termux： 已测试的手动安装路径请参考 Termux 指南。在 Termux 上，Hermes 会安装精选的 .[termux] 扩展，因为完整的 .[all] 扩展会拉取 Android 不兼容的语音依赖。

Windows： 原生 Windows 不受支持。请安装 WSL2 并运行上述命令。

安装后：

source ~/.bashrc    # 重新加载 shell（或: source ~/.zshrc）
hermes              # 开始对话！

快速入门

hermes              # 交互式 CLI — 开始对话
hermes model        # 选择 LLM 提供商和模型
hermes tools        # 配置启用的工具
hermes config set   # 设置单个配置项
hermes gateway      # 启动消息网关（Telegram、Discord 等）
hermes setup        # 运行完整设置向导（一次性配置所有内容）
hermes claw migrate # 从 OpenClaw 迁移（如果来自 OpenClaw）
hermes update       # 更新到最新版本
hermes doctor       # 诊断问题

📖 完整文档 →

省去到处收集 API Key — Nous Portal

Hermes 始终允许你使用任意服务商，这点不会改变。但如果你不想为模型、网页搜索、图像生成、TTS、云浏览器分别去申请五个不同的 API Key，Nous Portal 用一个订阅就能覆盖全部：

300+ 模型 — 用 /model <name> 随时切换
Tool Gateway — 网页搜索（Firecrawl）、图像生成（FAL）、文本转语音（OpenAI）、云浏览器（Browser Use），全部通过订阅托管。无需额外注册任何账户。

全新安装时一条命令即可：

hermes setup --portal

它会通过 OAuth 登录、把 Nous 设为推理服务商，并启用 Tool Gateway。随时用 hermes portal status 查看路由状态。完整说明见 Tool Gateway 文档。

你随时可以按工具单独切回自己的 API Key — Gateway 是按工具粒度生效的，不是一刀切。

CLI 与消息平台快速对照

Hermes 有两种入口：用 hermes 启动终端 UI，或运行网关从 Telegram、Discord、Slack、WhatsApp、Signal 或 Email 与之对话。进入对话后，许多斜杠命令在两种界面中通用。

操作	CLI	消息平台
开始对话	`hermes`	运行 `hermes gateway setup` + `hermes gateway start`，然后给机器人发消息
开始新对话	`/new` 或 `/reset`	`/new` 或 `/reset`
更换模型	`/model [provider:model]`	`/model [provider:model]`
设置人格	`/personality [name]`	`/personality [name]`
重试或撤销上一轮	`/retry`、`/undo`	`/retry`、`/undo`
压缩上下文 / 查看用量	`/compress`、`/usage`、`/insights [--days N]`	`/compress`、`/usage`、`/insights [days]`
浏览技能	`/skills` 或 `/<skill-name>`	`/skills` 或 `/<skill-name>`
中断当前工作	`Ctrl+C` 或发送新消息	`/stop` 或发送新消息
平台特定状态	`/platforms`	`/status`、`/sethome`

完整命令列表请参阅 CLI 指南和消息网关指南。

文档

所有文档位于 hermes-agent.nousresearch.com/docs：

章节	内容
快速开始	安装 → 设置 → 2 分钟内开始首次对话
CLI 使用	命令、快捷键、人格、会话
配置	配置文件、提供商、模型、所有选项
消息网关	Telegram、Discord、Slack、WhatsApp、Signal、Home Assistant
安全	命令审批、DM 配对、容器隔离
工具与工具集	40+ 工具、工具集系统、终端后端
技能系统	过程记忆、技能中心、创建技能
记忆	持久记忆、用户画像、最佳实践
MCP 集成	连接任意 MCP 服务器扩展能力
定时调度	定时任务与平台投递
上下文文件	影响每次对话的项目上下文
架构	项目结构、代理循环、关键类
贡献	开发设置、PR 流程、代码风格
CLI 参考	所有命令和标志
环境变量	完整环境变量参考

从 OpenClaw 迁移

如果你来自 OpenClaw，Hermes 可以自动导入你的设置、记忆、技能和 API 密钥。

首次安装时： 安装向导（hermes setup）会自动检测 ~/.openclaw 并在配置开始前提供迁移选项。

安装后任意时间：

hermes claw migrate              # 交互式迁移（完整预设）
hermes claw migrate --dry-run    # 预览将要迁移的内容
hermes claw migrate --preset user-data   # 仅迁移用户数据，不含密钥
hermes claw migrate --overwrite  # 覆盖已有冲突

导入内容：

SOUL.md — 人格文件
记忆 — MEMORY.md 和 USER.md 条目
技能 — 用户创建的技能 → ~/.hermes/skills/openclaw-imports/
命令白名单 — 审批模式
消息设置 — 平台配置、允许用户、工作目录
API 密钥 — 白名单中的密钥（Telegram、OpenRouter、OpenAI、Anthropic、ElevenLabs）
TTS 资产 — 工作区音频文件
工作区指令 — AGENTS.md（使用 --workspace-target）

使用 hermes claw migrate --help 查看所有选项，或使用 openclaw-migration 技能进行交互式代理引导迁移（含干运行预览）。

贡献

欢迎贡献！请参阅贡献指南了解开发设置、代码风格和 PR 流程。

贡献者快速开始——克隆并使用 setup-hermes.sh：

git clone https://github.com/NousResearch/hermes-agent.git
cd hermes-agent
./setup-hermes.sh     # 安装 uv、创建 venv、安装 .[all]、创建符号链接 ~/.local/bin/hermes
./hermes              # 自动检测 venv，无需先 source

手动安装（等效于上述命令）：

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]"
python -m pytest tests/ -q

社区

💬 Discord
📚 技能中心
🐛 问题反馈
💡 讨论区
🔌 HermesClaw — 社区微信桥接：在同一微信账号上运行 Hermes Agent 和 OpenClaw。

许可证

MIT — 详见 LICENSE。

由 Nous Research 构建。

项目介绍

The agent that grows with you

MIT_License Python 9.38 K提交数

定制我的领域

README

规则集

下载使用量

项目总下载次数（含Clone、Pull、 zip 包及 release 下载），每日凌晨更新

语言类型

Python88.92%

TypeScript5.27%

TSX3.21%

TeX1.06%

Shell0.51%

hermes-agent:基于多模型生态的自改进AI代理项目