Compare commits

...

112 Commits

Author SHA1 Message Date
Teknium 67cd15800d feat: add MiniMax M2.7 to hermes model picker and opencode-go
Add MiniMax-M2.7 and M2.7-highspeed to _PROVIDER_MODELS for minimax
and minimax-cn providers in main.py so hermes model shows them.
Update opencode-go bare ID from m2.5 to m2.7 in models.py.

Salvaged from PR #4197 by octo-patch.
2026-03-31 01:53:44 -07:00
Teknium 1bca6f3930 fix: save API key to model config for custom endpoints (#4182)
Custom cloud endpoints (Together.ai, RunPod, Groq, etc.) lost their
API key after #4165 removed OPENAI_API_KEY .env saves.  The key was
only saved to the custom_providers list which is unreachable at
runtime for plain 'custom' provider resolution.

Save model.api_key to config.yaml alongside model.provider and
model.base_url in all three custom endpoint code paths:
- _model_flow_custom (new endpoint with model name)
- _model_flow_custom (new endpoint without model name)
- _model_flow_named_custom (switching to a saved endpoint)

The runtime resolver already reads model.api_key (runtime_provider.py
line 224-228), so the key is picked up automatically.  Each custom
endpoint carries its own key in config — no shared OPENAI_API_KEY
env var needed.
2026-03-31 01:36:15 -07:00
Teknium a994cf5e5a docs: update adding-providers guide for unified setup flow
setup_model_provider() now delegates to select_provider_and_model()
from main.py, so new providers only need to be wired in main.py.
Removed setup.py from file checklists, replaced the setup.py section
with a tip explaining the automatic inheritance.
2026-03-31 01:29:43 -07:00
Teknium ff78ad4c81 feat: add discord.reactions config option to disable message reactions (#4199)
Adds a 'reactions' key under the discord config section (default: true).
When set to false, the bot no longer adds 👀// reactions to messages
during processing. The config maps to DISCORD_REACTIONS env var following
the same pattern as require_mention and auto_thread.

Files changed:
- hermes_cli/config.py: Add reactions default to DEFAULT_CONFIG
- gateway/config.py: Map discord.reactions to DISCORD_REACTIONS env var
- gateway/platforms/discord.py: Gate on_processing_start/complete hooks
- tests/gateway/test_discord_reactions.py: 3 new tests for config gate
2026-03-31 01:24:48 -07:00
Teknium 491e79bca9 refactor: unify setup wizard provider selection with hermes model
setup_model_provider() had 800+ lines of duplicated provider handling
that reimplemented the same credential prompting, OAuth flows, and model
selection that hermes model already provides via the _model_flow_*
functions.  Every new provider had to be added in both places, and the
two implementations diverged in config persistence (setup.py did raw
YAML writes, _set_model_provider, and _update_config_for_provider
depending on the provider — main.py used its own load/save cycle).

This caused the #4172 bug: _model_flow_custom saved config to disk but
the wizard's final save_config(config) overwrote it with stale values.

Fix: extract the core of cmd_model() into select_provider_and_model()
and have setup_model_provider() call it.  After the call, re-sync the
wizard's config dict from disk.  Deletes ~800 lines of duplicated
provider handling from setup.py.

Also fixes cmd_model() double-AuthError crash on fresh installs with
no API keys configured.
2026-03-31 01:04:07 -07:00
Teknium 89d8127772 fix: setup wizard overwrites custom endpoint config (#4172)
_model_flow_custom() saved model.provider and model.base_url to disk
via its own load_config/save_config cycle, but never updated the
setup wizard's in-memory config dict.  The wizard's final
save_config(config) then overwrote the custom settings with the
stale default string model value.

Fix: after saving to disk, also mutate the caller's config dict so
the wizard's final save preserves model.provider='custom' and the
base_url.  Both the model_name and no-model_name branches are
covered.

Added regression tests that simulate the full wizard flow including
the final save_config(config) call — the step that was previously
untested.
2026-03-30 23:17:26 -07:00
Teknium f890a94c12 refactor: make config.yaml the single source of truth for endpoint URLs (#4165)
OPENAI_BASE_URL was written to .env AND config.yaml, creating a dual-source
confusion. Users (especially Docker) would see the URL in .env and assume
that's where all config lives, then wonder why LLM_MODEL in .env didn't work.

Changes:
- Remove all 27 save_env_value("OPENAI_BASE_URL", ...) calls across main.py,
  setup.py, and tools_config.py
- Remove OPENAI_BASE_URL env var reading from runtime_provider.py, cli.py,
  models.py, and gateway/run.py
- Remove LLM_MODEL/HERMES_MODEL env var reading from gateway/run.py and
  auxiliary_client.py — config.yaml model.default is authoritative
- Vision base URL now saved to config.yaml auxiliary.vision.base_url
  (both setup wizard and tools_config paths)
- Tests updated to set config values instead of env vars

Convention enforced: .env is for SECRETS only (API keys). All other
configuration (model names, base URLs, provider selection) lives
exclusively in config.yaml.
2026-03-30 22:02:53 -07:00
Teknium 4d7e3c7157 fix(tests): provide model name in Codex 401 refresh tests for CI (#4166)
CI has no config.yaml, so cron/gateway resolve an empty model name.
The Codex Responses validator rejects empty models before the mock
API call is reached. Provide explicit model in job dict and env var.
2026-03-30 21:17:09 -07:00
Teknium 1bd206ea5d feat: add /btw command for ephemeral side questions (#4161)
Adds /btw <question> — ask a quick follow-up using the current
session context without interrupting the main conversation.

- Snapshots conversation history, answers with a no-tools agent
- Response is not persisted to session history or DB
- Runs in a background thread (CLI) / async task (gateway)
- Per-session guard prevents concurrent /btw in gateway

Implementation:
- model_tools.py: enabled_toolsets=[] now correctly means "no tools"
  (was falsy, fell through to default "all tools")
- run_agent.py: persist_session=False gates _persist_session()
- cli.py: _handle_btw_command (background thread, Rich panel output)
- gateway/run.py: _handle_btw_command + _run_btw_task (async task)
- hermes_cli/commands.py: CommandDef for "btw"

Inspired by PR #3504 by areu01or00, reimplemented cleanly on current
main with the enabled_toolsets=[] fix and without the __btw_no_tools__
hack.
2026-03-30 21:10:05 -07:00
Teknium f8e1ee10aa Fix profile list model display (#4160)
Co-authored-by: txhno <roshwarrier@gmail.com>
2026-03-30 20:40:13 -07:00
Teknium c1ef9b2250 fix(cli): ensure on_session_end hook fires on interrupted exits (#4159)
- Add SIGTERM/SIGHUP signal handlers for graceful shutdown
- Add BrokenPipeError to exit exception handling (SSH disconnects)
- Fire on_session_end plugin hook in finally block, guarded by
  _agent_running to avoid double-firing on normal exits (the hook
  already fires per-turn from run_conversation)

Co-authored-by: kelsia14 <kelsia14@users.noreply.github.com>
2026-03-30 20:37:17 -07:00
Teknium 3a68ec3172 feat: add Fireworks context length detection support (#4158)
- Add api.fireworks.ai to _URL_TO_PROVIDER for automatic provider detection
- Add fireworks to PROVIDER_TO_MODELS_DEV mapped to 'fireworks-ai' (the
  correct models.dev provider key — original PR used 'fireworks' which
  would silently fail the lookup)


Cherry-picked from PR #3989 with models.dev key fix.

Co-authored-by: sroecker <sroecker@users.noreply.github.com>
2026-03-30 20:37:08 -07:00
Teknium d30ea65c9b fix: URL-based auth for third-party Anthropic endpoints + CI test fixes (#4148)
* fix(tests): mock sys.stdin.isatty for cmd_model TTY guard

* fix(tests): update camofox snapshot format + trajectory compressor mock path

- test_browser_camofox: mock response now uses snapshot format (accessibility tree)
- test_trajectory_compressor: mock _get_async_client instead of setting async_client directly

* fix: URL-based auth detection for third-party Anthropic endpoints + test fixes

Reverts the key-prefix approach from #4093 which broke JWT and managed
key OAuth detection. Instead, detects third-party endpoints by URL:
if base_url is set and isn't anthropic.com, it's a proxy (Azure AI
Foundry, AWS Bedrock, etc.) that uses x-api-key regardless of key format.

Auth decision chain is now:
1. _requires_bearer_auth(url) → MiniMax → Bearer
2. _is_third_party_anthropic_endpoint(url) → Azure/Bedrock → x-api-key
3. _is_oauth_token(key) → OAuth on direct Anthropic → Bearer
4. else → x-api-key

Also includes test fixes from PR #4051 by @erosika:
- Mock sys.stdin.isatty for cmd_model TTY guard
- Update camofox snapshot format mock
- Fix trajectory compressor async client mock path

---------

Co-authored-by: Erosika <eri@plasticlabs.ai>
2026-03-30 20:36:56 -07:00
Teknium fb4b87f4af chore: add claude-sonnet-4.6 to OpenRouter and Nous model lists (#4157) 2026-03-30 20:33:21 -07:00
Teknium 5b0243e6ad docs: deep quality pass — expand 10 thin pages, fix specific issues (#4134)
Developer guide stubs expanded to full documentation:
- trajectory-format.md: 56→233 lines (JSONL format, ShareGPT example,
  normalization rules, reasoning markup, replay code)
- session-storage.md: 66→388 lines (SQLite schema, migration table,
  FTS5 search syntax, lineage queries, Python API examples)
- context-compression-and-caching.md: 72→321 lines (dual compression
  system, config defaults, 4-phase algorithm, before/after example,
  prompt caching mechanics, cache-aware patterns)
- tools-runtime.md: 65→246 lines (registry API, dispatch flow,
  availability checking, error wrapping, approval flow)
- prompt-assembly.md: 89→246 lines (concrete assembled prompt example,
  SOUL.md injection, context file discovery table)

User-facing pages expanded:
- docker.md: 62→224 lines (volumes, env forwarding, docker-compose,
  resource limits, troubleshooting)
- updating.md: 79→167 lines (update behavior, version checking,
  rollback instructions, Nix users)
- skins.md: 80→206 lines (all color/spinner/branding keys, built-in
  skin descriptions, full custom skin YAML template)

Hub pages improved:
- integrations/index.md: 25→82 lines (web search backends table,
  TTS/browser providers, quick config example)
- features/overview.md: added Integrations section with 6 missing links

Specific fixes:
- configuration.md: removed duplicate Gateway Streaming section
- mcp.md: removed internal "PR work" language
- plugins.md: added inline minimal plugin example (self-contained)

13 files changed, ~1700 lines added. Docusaurus build verified clean.
2026-03-30 20:30:11 -07:00
Teknium 54b876a5c9 fix: add actionable guidance to context-exceeded error messages (#4155)
When context compression fails, users now see hints suggesting /new
or /compress instead of a dead-end error. Covers all 4 error paths:
payload-too-large, max compression attempts (2 paths), and context
length exceeded.

Closes #4061
Salvaged from PR #4076 by SHL0MS.

Co-authored-by: SHL0MS <SHL0MS@users.noreply.github.com>
2026-03-30 20:23:28 -07:00
Teknium 83e5249be6 fix(gateway): use setsid instead of systemd-run --user for /update (salvage #4024) (#4104)
Salvaged from PR #4024 by @Sertug17. Fixes #4017.

- Replace systemd-run --user --scope with setsid for portable session detach
- Add system-level service detection to cmd_update gateway restart
- Falls back to start_new_session=True on systems without setsid (macOS, minimal containers)
2026-03-30 20:22:09 -07:00
Teknium fb2af3bd1d docs: document tool progress streaming in API server and Open WebUI (#4138)
Update docs to reflect that tool progress now streams inline during
SSE responses. Previously docs said tool calls were invisible.

- api-server.md: add 'Tool progress in streams' note to streaming docs
- open-webui.md: update 'How It Works' steps, add Tool Progress tip
2026-03-30 19:40:39 -07:00
Teknium cc63b2d1cd fix(gateway): remove user-facing compression warnings (#4139)
Auto-compression still runs silently in the background with server-side
logging, but no longer sends messages to the user's chat about it.

Removed:
- 'Session is large... Auto-compressing' pre-compression notification
- 'Compressed: N → M messages' post-compression notification
- 'Session is still very large after compression' warning
- 'Auto-compression failed' warning
- Rate-limit tracking (only existed for these warnings)
2026-03-30 19:17:07 -07:00
Teknium 45396aaa92 fix(alibaba): use standard DashScope international endpoint (#4133)
* fix(alibaba): use standard DashScope international endpoint

The Alibaba Cloud provider was hardcoded to the coding-intl endpoint
(https://coding-intl.dashscope.aliyuncs.com/v1) which only accepts
Alibaba Coding Plan API keys.

Standard DashScope API keys fail with invalid_api_key error against
this endpoint. Changed to the international compatible-mode endpoint
(https://dashscope-intl.aliyuncs.com/compatible-mode/v1) which works
with standard DashScope keys.

Users with Coding Plan keys or China-region keys can still override
via DASHSCOPE_BASE_URL or config.yaml base_url.

Fixes #3912

* fix: update test to match new DashScope default endpoint

---------

Co-authored-by: kagura-agent <kagura.chen28@gmail.com>
2026-03-30 19:06:30 -07:00
Teknium 04367e2fac fix(cron): stop truncating job IDs in list view (#4132)
Remove [:8] truncation from hermes cron list output. Job IDs are 12
hex chars — truncating to 8 makes them unusable for cron run/pause/remove
which require the full ID.

Co-authored-by: vitobotta <vitobotta@users.noreply.github.com>
2026-03-30 19:05:34 -07:00
Teknium cdb64a869a fix(security): reject private and loopback IPs in Telegram DoH fallback (#4129)
Co-authored-by: Maymun <139681654+maymuneth@users.noreply.github.com>
2026-03-30 18:53:24 -07:00
Teknium 1e59d4813c feat(api_server): stream tool progress to Open WebUI (#4092)
Wire the existing tool_progress_callback through the API server's
streaming handler so Open WebUI users see what tool is running.

Uses the existing 3-arg callback signature (name, preview, args)
that fires at tool start — no changes to run_agent.py needed.
Progress appears as inline markdown in the SSE content stream.

Inspired by PR #4032 by sroecker, reimplemented to avoid breaking
the callback signature used by CLI and gateway consumers.
2026-03-30 18:50:27 -07:00
Teknium f776191650 fix: persist compressed context to gateway session after mid-run compression
When context compression fires during run_conversation() in the gateway,
the compressed messages were silently lost on the next turn. Two bugs:

1. Agent-side: _flush_messages_to_session_db() calculated
   flush_from = max(len(conversation_history), _last_flushed_db_idx).
   After compression, _last_flushed_db_idx was correctly reset to 0,
   but conversation_history still had its original pre-compression
   length (e.g. 200). Since compressed messages are shorter (~30),
   messages[200:] was empty — nothing written to the new session's
   SQLite.

   Fix: Set conversation_history = None after each _compress_context()
   call so start_idx = 0 and all compressed messages are flushed.

2. Gateway-side: history_offset was always len(agent_history) — the
   original pre-compression length. After compression shortened the
   message list, agent_messages[200:] was empty, causing the gateway
   to fall back to writing only a user/assistant pair, losing the
   compressed summary and tail context.

   Fix: Detect session splits (agent.session_id != original) and set
   history_offset = 0 so all compressed messages are written to JSONL.
2026-03-30 18:49:14 -07:00
Teknium 44d02f35d2 docs: restructure site navigation — promote features and platforms to top-level (#4116)
Major reorganization of the documentation site for better discoverability
and navigation. 94 pages across 8 top-level sections (was 5).

Structural changes:
- Promote Features from 3-level-deep subcategory to top-level section
  with new Overview hub page categorizing all 26 feature pages
- Promote Messaging Platforms from User Guide subcategory to top-level
  section, add platform comparison matrix (13 platforms x 7 features)
- Create new Integrations section with hub page, grouping MCP, ACP,
  API Server, Honcho, Provider Routing, Fallback Providers
- Extract AI provider content (626 lines) from configuration.md into
  dedicated integrations/providers.md — configuration.md drops from
  1803 to 1178 lines
- Subcategorize Developer Guide into Architecture, Extending, Internals
- Rename "User Guide" to "Using Hermes" for top-level items

Orphan fixes (7 pages now reachable via sidebar):
- build-a-hermes-plugin.md added to Guides
- sms.md added to Messaging Platforms
- context-references.md added to Features > Core
- plugins.md added to Features > Core
- git-worktrees.md added to Using Hermes
- checkpoints-and-rollback.md added to Using Hermes
- checkpoints.md (30-line stub) deleted, superseded by
  checkpoints-and-rollback.md (203 lines)

New files:
- integrations/index.md — Integrations hub page
- integrations/providers.md — AI provider setup (extracted)
- user-guide/features/overview.md — Features hub page

Broken link fixes:
- quickstart.md, faq.md: update context-length-detection anchors
- configuration.md: update checkpoints link
- overview.md: fix checkpoint link path

Docusaurus build verified clean (zero broken links/anchors).
2026-03-30 18:39:51 -07:00
Teknium b2e1a095f8 fix(anthropic): write scopes field to Claude Code credentials on token refresh (#4126)
Claude Code >=2.1.81 checks for a 'scopes' array containing 'user:inference'
in ~/.claude/.credentials.json before accepting stored OAuth tokens as valid.

When Hermes refreshes the token, it writes only accessToken, refreshToken, and
expiresAt — omitting the scopes field. This causes Claude Code to report
'loggedIn: false' and refuse to start, even though the token is valid.

This commit:
- Parses the 'scope' field from the OAuth refresh response
- Passes it to _write_claude_code_credentials() as a keyword argument
- Persists the scopes array in the claudeAiOauth credential store
- Preserves existing scopes when the refresh response omits the field

Tested against Claude Code v2.1.87 on Linux — auth status correctly reports
loggedIn: true and claude --print works after this fix.

Co-authored-by: Nick <git@flybynight.io>
2026-03-30 18:35:16 -07:00
Teknium ffd5d37f9b fix: treat non-sk-ant- keys as regular API keys, not OAuth tokens (#4093)
* fix: treat non-sk-ant- prefixed keys (Azure AI Foundry) as regular API keys, not OAuth tokens

* fix: treat non-sk-ant- keys as regular API keys, not OAuth tokens

_is_oauth_token() returned True for any key not starting with
sk-ant-api, misclassifying Azure AI Foundry keys as OAuth tokens
and sending Bearer auth instead of x-api-key → 401 rejection.

Real Anthropic OAuth tokens all start with sk-ant-oat (confirmed
from live .credentials.json). Non-sk-ant- keys are third-party
provider keys that should use x-api-key.

Test fixtures updated to use realistic sk-ant-oat01- prefixed
tokens instead of fake strings.

Salvaged from PR #4075 by @HangGlidersRule.

---------

Co-authored-by: Clawdbot <clawdbot@openclaw.ai>
2026-03-30 17:41:13 -07:00
Teknium 720507efac feat: add post-migration cleanup for OpenClaw directories (#4100)
After migrating from OpenClaw, leftover workspace directories contain
state files (todo.json, sessions, logs) that confuse the agent — it
discovers them and reads/writes to stale locations instead of the
Hermes state directory, causing issues like cron jobs reading a
different todo list than interactive sessions.

Changes:
- hermes claw migrate now offers to archive the source directory after
  successful migration (rename to .pre-migration, not delete)
- New `hermes claw cleanup` subcommand for users who already migrated
  and need to archive leftover OpenClaw directories
- Migration notes updated with explicit cleanup guidance
- 42 tests covering all new functionality

Reported by SteveSkedasticity — multiple todo.json files across
~/.hermes/, ~/.openclaw/workspace/, and ~/.openclaw/workspace-assistant/
caused cron jobs to read from wrong locations.
2026-03-30 17:39:08 -07:00
Teknium 8a794d029d fix(ci): add repo conditionals to prevent fork workflow failures (#4107)
Add github.repository checks to docker-publish and deploy-site
workflows so they skip on forks where upstream-specific resources
(Docker Hub org, custom domain) are unavailable.

Co-authored-by: StreamOfRon <StreamOfRon@users.noreply.github.com>
2026-03-30 17:38:32 -07:00
Teknium e64b047663 chore: prepare Hermes for Homebrew packaging (#4099)
Co-authored-by: Yabuku-xD <78594762+Yabuku-xD@users.noreply.github.com>
2026-03-30 17:34:43 -07:00
Teknium 11aa44d34d docs(telegram): add webhook mode documentation (#4089)
Documents the Telegram webhook mode from #3880:
- New 'Webhook Mode' section in telegram.md with polling vs webhook
  comparison, config table, Fly.io deployment example, troubleshooting
- Add TELEGRAM_WEBHOOK_URL/PORT/SECRET to environment-variables.md
- Add Telegram section to .env.example (existing + webhook vars)

Co-authored-by: raulbcs <raulbcs@users.noreply.github.com>
2026-03-30 17:21:59 -07:00
Teknium 07746dca0c fix(matrix): E2EE decryption — request keys, auto-trust devices, retry buffered events (#4083)
When the Matrix adapter receives encrypted events it can't decrypt
(MegolmEvent), it now:

1. Requests the missing room key from other devices via
   client.request_room_key(event) instead of silently dropping the message

2. Buffers undecrypted events (bounded to 100, 5 min TTL) and retries
   decryption after each E2EE maintenance cycle when new keys arrive

3. Auto-trusts/verifies all devices after key queries so other clients
   share session keys with the bot proactively

4. Exports Megolm keys on disconnect and imports them on connect, so
   session keys survive gateway restarts

This addresses the 'could not decrypt event' warnings that caused the
bot to miss messages in encrypted rooms.
2026-03-30 17:16:09 -07:00
Teknium 7e0c2c3ce3 docs: comprehensive documentation audit — fix 9 HIGH, 20+ MEDIUM gaps (#4087)
Reference docs fixes:
- cli-commands.md: remove non-existent --provider alibaba, add hermes
  profile/completion/plugins/mcp to top-level table, add --profile/-p
  global flag, add --source chat option
- slash-commands.md: add /yolo and /commands, fix /q alias conflict
  (resolves to /queue not /quit), add missing aliases (/bg, /set-home,
  /reload_mcp, /gateway)
- toolsets-reference.md: fix hermes-api-server (not same as hermes-cli,
  omits clarify/send_message/text_to_speech)
- profile-commands.md: fix show name required not optional, --clone-from
  not --from, add --remove/--name to alias, fix alias path, fix export/
  import arg types, remove non-existent fish completion
- tools-reference.md: add EXA_API_KEY to web tools requires_env
- mcp-config-reference.md: add auth key for OAuth, tool name sanitization
- environment-variables.md: add EXA_API_KEY, update provider values
- plugins.md: remove non-existent ctx.register_command(), add
  ctx.inject_message()

Feature docs additions:
- security.md: add /yolo mode, approval modes (manual/smart/off),
  configurable timeout, expanded dangerous patterns table
- cron.md: add wrap_response config, [SILENT] suppression
- mcp.md: add dynamic tool discovery, MCP sampling support
- cli.md: add Ctrl+Z suspend, busy_input_mode, tool_preview_length
- docker.md: add skills/credential file mounting

Messaging platform docs:
- telegram.md: add webhook mode, DoH fallback IPs
- slack.md: add multi-workspace OAuth support
- discord.md: add DISCORD_IGNORE_NO_MENTION
- matrix.md: add MSC3245 native voice messages
- feishu.md: expand from 129 to 365 lines (encrypt key, verification
  token, group policy, card actions, media, rate limiting, markdown,
  troubleshooting)
- wecom.md: expand from 86 to 264 lines (per-group allowlists, media,
  AES decryption, stream replies, reconnection, troubleshooting)

Configuration docs:
- quickstart.md: add DeepSeek, Copilot, Copilot ACP providers
- configuration.md: add DeepSeek provider, Exa web backend, terminal
  env_passthrough/images, browser.command_timeout, compression params,
  discord config, security/tirith config, timezone, auxiliary models

21 files changed, ~1000 lines added
2026-03-30 17:15:21 -07:00
SHL0MS 3c8f910973 feat: respect NO_COLOR env var and TERM=dumb (#4079)
Add should_use_color() function to hermes_cli/colors.py that checks
NO_COLOR (https://no-color.org/) and TERM=dumb before emitting ANSI
escapes. The existing color() helper now uses this function instead
of a bare isatty() check.

This is the foundation — cli.py and banner.py still have inline ANSI
constants that bypass this module (tracked in #4071).

Closes #4066

Co-authored-by: SHL0MS <SHL0MS@users.noreply.github.com>
2026-03-30 17:07:21 -07:00
Teknium 13f3e67165 ux: show 'Initializing agent...' on first message (#4086)
Display a brief status message before the heavy agent initialization
(OpenAI client setup, tool loading, memory init, etc.) so users
aren't staring at a blank screen for several seconds.

Only prints when self.agent is None (first use or after model switch).

Closes #4060

Co-authored-by: SHL0MS <SHL0MS@users.noreply.github.com>
2026-03-30 17:05:40 -07:00
Teknium 4a7c17fca5 fix(gateway): read custom_providers context_length in hygiene compression (#4085)
Gateway hygiene pre-compression only checked model.context_length from
the top-level config, missing per-model context_length defined in
custom_providers entries. This caused premature compression for custom
provider users (e.g. 128K default instead of 200K configured).

The AIAgent's own compressor already reads custom_providers correctly
(run_agent.py lines 1171-1189). This adds the same fallback to the
gateway hygiene path, running after runtime provider resolution so
the base_url is available for matching.
2026-03-30 17:04:31 -07:00
Teknium f007284d05 fix: rate-limit pairing rejection messages to prevent spam (#4081)
* fix: rate-limit pairing rejection messages to prevent spam

When generate_code() returns None (rate limited or max pending), the
"Too many pairing requests" message was sent on every subsequent DM
with no cooldown. A user sending 30 messages would get 30 rejection
replies — reported as potential hack on WhatsApp.

Now check _is_rate_limited() before any pairing response, and record
rate limit after sending a rejection. Subsequent messages from the
same user are silently ignored until the rate limit window expires.

* test: add coverage for pairing response rate limiting

Follow-up to cherry-picked PR #4042 — adds tests verifying:
- Rate-limited users get silently ignored (no response sent)
- Rejection messages record rate limit for subsequent suppression

---------

Co-authored-by: 0xbyt4 <35742124+0xbyt4@users.noreply.github.com>
2026-03-30 16:48:00 -07:00
Teknium 3d47af01c3 fix(honcho): write config to instance-local path for profile isolation (#4037)
Multiple agents/profiles running 'hermes honcho setup' all wrote to
the shared global ~/.honcho/config.json, overwriting each other's
configuration.

Root cause: _write_config() defaulted to resolve_config_path() which
returns the global path when no instance-local file exists yet (i.e.
on first setup).

Fix: _write_config() now defaults to _local_config_path() which always
returns $HERMES_HOME/honcho.json. Each profile gets its own config file.
Reading still falls back to global for cross-app interop and seeding.

Also updates cmd_setup and cmd_status messaging to show the actual
write path.

Includes 10 new tests verifying profile isolation, global fallback
reads, and multi-profile independence.
2026-03-30 16:41:19 -07:00
SHL0MS 275fcc6673 Merge pull request #4054 from NousResearch/ascii-video/text-readability-and-layout-oracle
ascii-video skill: text readability techniques and external layout oracle
2026-03-30 15:52:14 -07:00
SHL0MS ab62614a89 ascii-video: add text readability techniques and external layout oracle pattern
- composition.md: add text backdrop (gaussian dark mask behind glyphs) and
  external layout oracle pattern (browser-based text layout → JSON → Python
  renderer pipeline for obstacle-aware text reflow)
- shaders.md: add reverse vignette shader (center-darkening for text readability)
- troubleshooting.md: add diagnostic entries for text-over-busy-background
  readability and kaleidoscope-destroys-text pitfall
2026-03-30 18:48:22 -04:00
Teknium de368cac54 fix(tools): show browser and TTS in reconfigure menu (#4041)
* fix(gateway): honor default for invalid bool-like config values

* refactor: simplify web backend priority detection

Replace cascading boolean conditions with a priority-ordered loop.
Same behavior (verified against all 16 env var combinations),
half the lines, trivially extensible for new backends.

* fix(tools): show browser and TTS in reconfigure menu

_toolset_has_keys() returned False for toolsets with no-key providers
(Local Browser, Edge TTS) because it only checked providers with
env_vars. Users couldn't find these tools in the reconfigure list
and had no obvious way to switch browser/TTS backends.

Now treats providers with empty env_vars as always-configured, so
toolsets with free/local options always appear in the reconfigure menu.

---------

Co-authored-by: aydnOktay <xaydinoktay@gmail.com>
2026-03-30 14:11:39 -07:00
Teknium 0d1003559d refactor: simplify web backend priority detection (#4036)
* fix(gateway): honor default for invalid bool-like config values

* refactor: simplify web backend priority detection

Replace cascading boolean conditions with a priority-ordered loop.
Same behavior (verified against all 16 env var combinations),
half the lines, trivially extensible for new backends.

---------

Co-authored-by: aydnOktay <xaydinoktay@gmail.com>
2026-03-30 13:37:25 -07:00
Teknium eba8d52d54 fix: show correct shell config path for macOS/zsh in install script (#4025)
- print_success() hardcoded 'source ~/.bashrc' regardless of user's shell
- On macOS (default zsh), ~/.bashrc doesn't exist, leaving users unable to
  find the hermes command after install
- Now detects $SHELL and shows the correct file (zshrc/bashrc)
- Also captures .[all] install failure output instead of silencing with
  2>/dev/null, so users can diagnose why full extras failed
2026-03-30 13:25:11 -07:00
Teknium 72104eb06f fix(gateway): honor default for invalid bool-like config values (#4029)
Co-authored-by: aydnOktay <xaydinoktay@gmail.com>
2026-03-30 13:24:48 -07:00
Teknium 4b35836ba4 fix(auth): use bearer auth for MiniMax Anthropic endpoints (#4028)
MiniMax's /anthropic endpoints implement Anthropic's Messages API but
require Authorization: Bearer instead of x-api-key. Without this fix,
MiniMax users get 401 errors in gateway sessions.

Adds _requires_bearer_auth() to detect MiniMax endpoints and route
through auth_token in the Anthropic SDK. Check runs before OAuth
token detection so MiniMax keys aren't misclassified as setup tokens.

Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>
2026-03-30 13:21:39 -07:00
Teknium bd376fe976 fix(docs): improve mobile sidebar navigation
The sidebar had all categories expanded by default (collapsed: false),
which on mobile created a 60+ item flat list when opening the sidebar.
Reported by danny on Discord.

Changes:
- Set all top-level categories to collapsed: true (tap to expand)
- Enable autoCollapseCategories: true (accordion — opening one section
  closes others, prevents the overwhelming flat list)
- Enable hideable sidebar (swipe-to-dismiss on mobile)
- Add mobile CSS: larger touch targets (0.75rem padding), bolder
  category headers, visible subcategory indentation with left border,
  wider sidebar (85vw / 360px max), darker backdrop overlay
2026-03-30 13:20:55 -07:00
Teknium f93637b3a1 feat: add /profile slash command to show active profile (#4027)
Adds /profile to COMMAND_REGISTRY (Info category) with handlers in
both CLI and gateway. Shows the active profile name and home directory.

Works on all platforms — CLI, Telegram, Discord, Slack, etc.
Detects profile by checking if HERMES_HOME is under ~/.hermes/profiles/.
Shows 'default' when running without a profile.
2026-03-30 13:20:06 -07:00
Teknium 7b4fe0528f fix(auth): use bearer auth for MiniMax Anthropic endpoints (#4028)
MiniMax's /anthropic endpoints implement Anthropic's Messages API but
require Authorization: Bearer instead of x-api-key. Without this fix,
MiniMax users get 401 errors in gateway sessions.

Adds _requires_bearer_auth() to detect MiniMax endpoints and route
through auth_token in the Anthropic SDK. Check runs before OAuth
token detection so MiniMax keys aren't misclassified as setup tokens.

Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>
2026-03-30 13:19:44 -07:00
Teknium 950f69475f feat(browser): add Camofox local anti-detection browser backend (#4008)
Camofox-browser is a self-hosted Node.js server wrapping Camoufox
(Firefox fork with C++ fingerprint spoofing). When CAMOFOX_URL is set,
all 11 browser tools route through the Camofox REST API instead of
the agent-browser CLI.

Maps 1:1 to the existing browser tool interface:
- Navigate, snapshot, click, type, scroll, back, press, close
- Get images, vision (screenshot + LLM analysis)
- Console (returns empty with note — camofox limitation)

Setup: npm start in camofox-browser dir, or docker run -p 9377:9377
Then: CAMOFOX_URL=http://localhost:9377 in ~/.hermes/.env

Advantages over Browserbase (cloud):
- Free (no per-session API costs)
- Local (zero network latency for browser ops)
- Anti-detection at C++ level (bypasses Cloudflare/Google bot detection)
- Works offline, Docker-ready

Files:
- tools/browser_camofox.py: Full REST backend (~400 lines)
- tools/browser_tool.py: Routing at each tool function
- hermes_cli/config.py: CAMOFOX_URL env var entry
- tests/tools/test_browser_camofox.py: 20 tests
2026-03-30 13:18:42 -07:00
Teknium 7dac75f2ae fix: prevent context pressure warning spam after compression (#4012)
* feat: add /yolo slash command to toggle dangerous command approvals

Adds a /yolo command that toggles HERMES_YOLO_MODE at runtime, skipping
all dangerous command approval prompts for the current session. Works in
both CLI and gateway (Telegram, Discord, etc.).

- /yolo -> ON: all commands auto-approved, no confirmation prompts
- /yolo -> OFF: normal approval flow restored

The --yolo CLI flag already existed for launch-time opt-in. This adds
the ability to toggle mid-session without restarting.

Session-scoped — resets when the process ends. Uses the existing
HERMES_YOLO_MODE env var that check_all_command_guards() already
respects.

* fix: prevent context pressure warning spam (agent loop + gateway rate-limit)

Two complementary fixes for repeated context pressure warnings spamming
gateway users (Telegram, Discord, etc.):

1. Agent-level loop fix (run_agent.py):
   After compression, only reset _context_pressure_warned if the
   post-compression estimate is actually below the 85% warning level.
   Previously the flag was unconditionally reset, causing the warning
   to re-fire every loop iteration when compression couldn't reduce
   below 85% of the threshold (e.g. very low threshold like 15%,
   or system prompt alone exceeds the warning level).

2. Gateway-level rate-limit (gateway/run.py, salvaged from PR #3786):
   Per-chat_id cooldown of 1 hour on compression warning messages.
   Both warning paths ('still large after compression' and 'compression
   failed') are gated. Defense-in-depth — even if the agent-level fix
   has edge cases, users won't see more than one warning per hour.

Co-authored-by: dlkakbs <dlkakbs@users.noreply.github.com>

---------

Co-authored-by: dlkakbs <dlkakbs@users.noreply.github.com>
2026-03-30 13:18:21 -07:00
Teknium ed9af6e589 fix: create AsyncOpenAI lazily in trajectory_compressor to avoid closed event loop (#4013)
The AsyncOpenAI client was created once at __init__ and stored as an
instance attribute. process_directory() calls asyncio.run() which creates
and closes a fresh event loop. On a second call, the client's httpx
transport is still bound to the closed loop, raising RuntimeError:
"Event loop is closed" — the same pattern fixed by PR #3398 for the
main agent loop.

Create the client lazily in _get_async_client() so each asyncio.run()
gets a client bound to the current loop.

Co-authored-by: binhnt92 <binhnt.ht.92@gmail.com>
2026-03-30 13:16:16 -07:00
Teknium 158f49f19a fix: enforce priority order in Telegram menu — core > plugins > skills (#4023)
The menu now has explicit priority tiers:
1. Core CommandDef commands (always included, never bumped)
2. Plugin slash commands (take precedence over skills)
3. Built-in skill commands (fill remaining slots alphabetically)

Only skills get trimmed when the 100-command cap is hit. Adding new
core commands or plugin commands automatically pushes skills out,
not the other way around.
2026-03-30 13:04:06 -07:00
Teknium 86250a3e45 docs: expand terminal backends section + fix docs build (#4016)
* feat(telegram): add webhook mode as alternative to polling

When TELEGRAM_WEBHOOK_URL is set, the adapter starts an HTTP webhook
server (via python-telegram-bot's start_webhook()) instead of long
polling. This enables cloud platforms like Fly.io and Railway to
auto-wake suspended machines on inbound HTTP traffic.

Polling remains the default — no behavior change unless the env var
is set.

Env vars:
  TELEGRAM_WEBHOOK_URL    Public HTTPS URL for Telegram to push to
  TELEGRAM_WEBHOOK_PORT   Local listen port (default 8443)
  TELEGRAM_WEBHOOK_SECRET Secret token for update verification

Cherry-picked and adapted from PR #2022 by SHL0MS. Preserved all
current main enhancements (network error recovery, polling conflict
detection, DM topics setup).

Co-authored-by: SHL0MS <SHL0MS@users.noreply.github.com>

* fix: send_document call in background task delivery + vision download timeout

Two fixes salvaged from PR #2269 by amethystani:

1. gateway/run.py: adapter.send_file() → adapter.send_document()
   send_file() doesn't exist on BasePlatformAdapter. Background task
   media files were silently never delivered (AttributeError swallowed
   by except Exception: pass).

2. tools/vision_tools.py: configurable image download timeout via
   HERMES_VISION_DOWNLOAD_TIMEOUT env var (default 30s), plus guard
   against raise None when max_retries=0.

The third fix in #2269 (opencode-go auth config) was already resolved
on main.

Co-authored-by: amethystani <amethystani@users.noreply.github.com>

* docs: expand terminal backends section + fix feishu MDX build error

---------

Co-authored-by: SHL0MS <SHL0MS@users.noreply.github.com>
Co-authored-by: amethystani <amethystani@users.noreply.github.com>
2026-03-30 12:59:58 -07:00
Teknium ea342f2382 Fix banner alignment in installer script (#4011)
Co-authored-by: Ahmed Khaled <wakeupwithme000@gmail.com>
2026-03-30 11:24:10 -07:00
Teknium 60ecde8ac7 fix: fit all 100 commands in Telegram menu with 40-char descriptions (#4010)
* fix: truncate skill descriptions to 100 chars in Telegram menu

* fix: 40-char desc cap + 100 command limit for Telegram menu

setMyCommands has an undocumented total payload size limit.
50 commands with 256-char descriptions failed, 50 with 100-char
worked, and 100 with 40-char descriptions also works (~5300 total
chars). Truncate skill descriptions to 40 chars in the menu picker
and set cap back to 100. Full descriptions available via /commands.
2026-03-30 11:21:13 -07:00
Teknium f3069c649c fix(cli): add missing subprocess.run() timeouts in doctor and status (#4009)
Add timeout parameters to 4 subprocess.run() calls that could hang
indefinitely if the child process blocks (e.g., unresponsive docker
daemon, systemctl waiting for D-Bus):

- doctor.py: docker info (timeout=10), ssh check (timeout=15)
- status.py: systemctl is-active (timeout=5), launchctl list (timeout=5)

Each call site now catches subprocess.TimeoutExpired and treats it as
a failure, consistent with how non-zero return codes are already handled.

Add AST-based regression test that verifies every subprocess.run() call
in CLI modules specifies a timeout keyword argument.

Co-authored-by: dieutx <dangtc94@gmail.com>
2026-03-30 11:17:15 -07:00
Teknium 0976bf6cd0 feat: add /yolo slash command to toggle dangerous command approvals (#3990)
Adds a /yolo command that toggles HERMES_YOLO_MODE at runtime, skipping
all dangerous command approval prompts for the current session. Works in
both CLI and gateway (Telegram, Discord, etc.).

- /yolo -> ON: all commands auto-approved, no confirmation prompts
- /yolo -> OFF: normal approval flow restored

The --yolo CLI flag already existed for launch-time opt-in. This adds
the ability to toggle mid-session without restarting.

Session-scoped — resets when the process ends. Uses the existing
HERMES_YOLO_MODE env var that check_all_command_guards() already
respects.
2026-03-30 11:17:09 -07:00
Teknium da3e22bcfa fix: cap Telegram menu at 50 commands — API rejects above ~60 (#4006)
* fix: use SKILLS_DIR not repo path for Telegram menu skill filter

Skills are synced to ~/.hermes/skills/ (SKILLS_DIR), not the repo's
skills/ directory. The previous filter compared against the repo path
so no skills matched. Now checks SKILLS_DIR and excludes .hub/
subdirectory (user-installed hub skills).

* fix: cap Telegram menu at 50 commands — API rejects above ~60

Telegram's setMyCommands returns BOT_COMMANDS_TOO_MUCH when
registering close to 100 commands despite docs claiming 100 is the
limit. Metadata overhead causes rejection above ~60. Cap at 50 for
reliability — remaining commands accessible via /commands.
2026-03-30 11:05:20 -07:00
Teknium 9fd78c7a8e fix: use SKILLS_DIR not repo path for Telegram menu skill filter (#4005)
Skills are synced to ~/.hermes/skills/ (SKILLS_DIR), not the repo's
skills/ directory. The previous filter compared against the repo path
so no skills matched. Now checks SKILLS_DIR and excludes .hub/
subdirectory (user-installed hub skills).
2026-03-30 11:01:13 -07:00
Teknium 5ceed021dc feat(gateway): skill-aware slash commands, paginated /commands, Telegram 100-cap (#3934)
* feat(gateway): skill-aware slash commands, paginated /commands, Telegram 100-cap

Map active skills to Telegram's slash command menu so users can
discover and invoke skills directly. Three changes:

1. Telegram menu now includes active skill commands alongside built-in
   commands, capped at 100 entries (Telegram Bot API limit). Overflow
   commands remain callable but hidden from the picker. Logged at
   startup when cap is hit.

2. New /commands [page] gateway command for paginated browsing of all
   commands + skills. /help now shows first 10 skill commands and
   points to /commands for the full list.

3. When a user types a slash command that matches a disabled or
   uninstalled skill, they get actionable guidance:
   - Disabled: 'Enable it with: hermes skills config'
   - Optional (not installed): 'Install with: hermes skills install official/<path>'

Built on ideas from PR #3921 by @kshitijk4poor.

* chore: move 21 niche skills to optional-skills

Move specialized/niche skills from built-in (skills/) to optional
(optional-skills/) to reduce the default skill count. Users can
install them with: hermes skills install official/<category>/<name>

Moved skills (21):
- mlops: accelerate, chroma, faiss, flash-attention,
  hermes-atropos-environments, huggingface-tokenizers, instructor,
  lambda-labs, llava, nemo-curator, pinecone, pytorch-lightning,
  qdrant, saelens, simpo, slime, tensorrt-llm, torchtitan
- research: domain-intel, duckduckgo-search
- devops: inference-sh cli

Built-in skills: 96 → 75
Optional skills: 22 → 43

* fix: only include repo built-in skills in Telegram menu, not user-installed

User-installed skills (from hub or manually added) stay accessible via
/skills and by typing the command directly, but don't get registered
in the Telegram slash command picker. Only skills whose SKILL.md is
under the repo's skills/ directory are included in the menu.

This keeps the Telegram menu focused on the curated built-in set while
user-installed skills remain discoverable through /skills and /commands.
2026-03-30 10:57:30 -07:00
Teknium 97d6813f51 fix(cache): use deterministic call_id fallbacks instead of random UUIDs (#3991)
When the API doesn't provide a call_id for tool calls, the fallback
generated a random uuid4 hex. This made every API call's input unique
when replayed, preventing OpenAI's prompt cache from matching the
prefix across turns.

Replaced all four uuid4 fallback sites with a deterministic hash of
(function_name, arguments, position_index). The same tool call now
always produces the same fallback call_id, preserving cache-friendly
input stability.

Affected code paths:
- _chat_messages_to_responses_input() — Codex input reconstruction
- _normalize_codex_response() — function_call and custom_tool_call
- _build_assistant_message() — assistant message construction
2026-03-30 09:43:56 -07:00
Teknium 37825189dd fix(skills): validate hub bundle paths before install (#3986)
Co-authored-by: Gutslabs <gutslabsxyz@gmail.com>
2026-03-30 08:37:19 -07:00
Teknium e08778fa1e chore: release v0.6.0 (2026.3.30) (#3985) 2026-03-30 08:29:38 -07:00
Teknium fb634068df fix(security): extend secret redaction to ElevenLabs, Tavily and Exa API keys (#3920)
ElevenLabs (sk_), Tavily (tvly-), and Exa (exa_) keys were not covered
by _PREFIX_PATTERNS, leaking in plain text via printenv or log output.

Salvaged from PR #3790 by @memosr. Tests rewritten with correct
assertions (original tests had vacuously true checks).

Co-authored-by: memosr <memosr@users.noreply.github.com>
2026-03-30 08:13:01 -07:00
Teknium 74181fe726 fix: add TTY guard to interactive CLI commands to prevent CPU spin (#3933)
When interactive TUI commands are invoked non-interactively (e.g. via
the agent's terminal() tool through a subprocess pipe), curses loops
spin at 100% CPU and input() calls hang indefinitely.

Defense in depth — two layers:

1. Source-level guard in curses_checklist() (curses_ui.py + checklist.py):
   Returns cancel_returns immediately when stdin is not a TTY. This
   catches ALL callers automatically, including future code.

2. Command-level guards with clear error messages:
   - hermes tools (interactive checklist, not list/disable/enable)
   - hermes setup (interactive wizard)
   - hermes model (provider/model picker)
   - hermes whatsapp (pairing setup)
   - hermes skills config (skill toggle)
   - hermes mcp configure (tool selection)
   - hermes uninstall (confirmation prompt)

Non-interactive subcommands (hermes tools list, hermes tools enable,
hermes mcp add/remove/list/test, hermes skills search/install/browse)
remain unaffected.
2026-03-30 08:10:23 -07:00
Teknium 1e896b0251 fix: resolve 7 failing CI tests (#3936)
1. matrix voice: _on_room_message_media unconditionally overwrote
   media_urls with the image cache path (always None for non-images),
   wiping the locally-cached voice path. Now only overrides when
   cached_path is truthy.

2. cli_tools_command: /tools disable no longer prompts for confirmation
   (input() removed in earlier commit to fix TUI hang), but tests still
   expected the old Y/N prompt flow. Updated tests to match current
   behavior (direct apply + session reset).

3. slack app_mention: connect() was refactored for multi-workspace
   (creates AsyncWebClient per token), but test only mocked the old
   self._app.client path. Added AsyncWebClient and acquire_scoped_lock
   mocks.

4. website_policy: module-level _cached_policy from earlier tests caused
   fast-path return of None. Added invalidate_cache() before assertion.

5. codex 401 refresh: already passing on current main (fixed by
   intervening commit).
2026-03-30 08:10:14 -07:00
0xbyt4 0b0c1b326c fix: openclaw migration overwrites model config dict with string (#3924)
migrate_model_config() was writing `config["model"] = model_str` which
replaces the entire model dict (default, provider, base_url) with a
bare string. This causes 'str' object has no attribute 'get' errors
throughout Hermes when any code does model_cfg.get("default").

Now preserves the existing model dict and only updates the "default"
key, keeping provider/base_url intact.
2026-03-30 03:02:28 -07:00
Teknium b4496b33b5 fix: background task media delivery + vision download timeout (#3919)
* feat(telegram): add webhook mode as alternative to polling

When TELEGRAM_WEBHOOK_URL is set, the adapter starts an HTTP webhook
server (via python-telegram-bot's start_webhook()) instead of long
polling. This enables cloud platforms like Fly.io and Railway to
auto-wake suspended machines on inbound HTTP traffic.

Polling remains the default — no behavior change unless the env var
is set.

Env vars:
  TELEGRAM_WEBHOOK_URL    Public HTTPS URL for Telegram to push to
  TELEGRAM_WEBHOOK_PORT   Local listen port (default 8443)
  TELEGRAM_WEBHOOK_SECRET Secret token for update verification

Cherry-picked and adapted from PR #2022 by SHL0MS. Preserved all
current main enhancements (network error recovery, polling conflict
detection, DM topics setup).

Co-authored-by: SHL0MS <SHL0MS@users.noreply.github.com>

* fix: send_document call in background task delivery + vision download timeout

Two fixes salvaged from PR #2269 by amethystani:

1. gateway/run.py: adapter.send_file() → adapter.send_document()
   send_file() doesn't exist on BasePlatformAdapter. Background task
   media files were silently never delivered (AttributeError swallowed
   by except Exception: pass).

2. tools/vision_tools.py: configurable image download timeout via
   HERMES_VISION_DOWNLOAD_TIMEOUT env var (default 30s), plus guard
   against raise None when max_retries=0.

The third fix in #2269 (opencode-go auth config) was already resolved
on main.

Co-authored-by: amethystani <amethystani@users.noreply.github.com>

---------

Co-authored-by: SHL0MS <SHL0MS@users.noreply.github.com>
Co-authored-by: amethystani <amethystani@users.noreply.github.com>
2026-03-30 02:59:39 -07:00
Teknium d028a94b83 fix(whatsapp): skip reply prefix in bot mode — only needed for self-chat (#3931)
The WhatsApp bridge prepends '⚕ *Hermes Agent*\n────────────\n' to
every outgoing message. In self-chat mode this is necessary to
distinguish the bot's responses from the user's own messages. In bot
mode the messages already come from a different number, making the
prefix redundant and cluttered.

Now only prepends the prefix when WHATSAPP_MODE is 'self-chat' (the
default). Bot mode messages are sent clean.
2026-03-30 02:55:33 -07:00
Teknium 0e592aa5b4 fix(cli): remove input() from /tools disable that freezes the terminal (#3918)
input() hangs inside prompt_toolkit's TUI event loop — this is a known
pitfall (AGENTS.md). The /tools disable and /tools enable commands used
input() for a Y/N confirmation prompt, causing the terminal to freeze
with no way to type a response.

Fix: remove the confirmation prompt. The user typing '/tools disable web'
is implicit consent. The change is applied directly with a status message.
2026-03-30 02:53:21 -07:00
Wing Lian efae525dc5 feat(plugins): add inject_message interface for remote message injection (#3778) 2026-03-30 02:48:06 -07:00
Teknium 5148682b43 feat: mount skills directory into all remote backends with live sync (#3890)
Skills with scripts/, templates/, and references/ subdirectories need
those files available inside sandboxed execution environments. Previously
the skills directory was missing entirely from remote backends.

Live sync — files stay current as credentials refresh and skills update:
- Docker/Singularity: bind mounts are inherently live (host changes
  visible immediately)
- Modal: _sync_files() runs before each command with mtime+size caching,
  pushing only changed credential and skill files (~13μs no-op overhead)
- SSH: rsync --safe-links before each command (naturally incremental)
- Daytona: _upload_if_changed() with mtime+size caching before each command

Security — symlink filtering:
- Docker/Singularity: sanitized temp copy when symlinks detected
- Modal/Daytona: iter_skills_files() skips symlinks
- SSH: rsync --safe-links skips symlinks pointing outside source tree
- Temp dir cleanup via atexit + reuse across calls

Non-root user support:
- SSH: detects remote home via echo $HOME, syncs to $HOME/.hermes/
- Daytona: detects sandbox home before sync, uploads to $HOME/.hermes/
- Docker/Modal/Singularity: run as root, /root/.hermes/ is correct

Also:
- credential_files.py: fix name/path key fallback in required_credential_files
- Singularity, SSH, Daytona: gained credential file support
- 14 tests covering symlink filtering, name/path fallback, iter_skills_files
2026-03-30 02:45:41 -07:00
Teknium 791f4e94b2 feat(slack): multi-workspace support via OAuth token file (#3903)
Salvaged from PR #2033 by yoannes. Adds multi-workspace Slack support
so a single Hermes instance can serve multiple Slack workspaces after
OAuth installs.

Changes:
- Support comma-separated bot tokens in SLACK_BOT_TOKEN env var
- Load additional OAuth-persisted tokens from HERMES_HOME/slack_tokens.json
- Route all Slack API calls through workspace-aware _get_client(chat_id)
  instead of always using the primary app client
- Track channel → workspace mapping from incoming events
- Per-workspace bot_user_id for correct mention detection
- Workspace-aware file downloads (correct auth token per workspace)

Backward compatible: single-token setups work identically.

Token file format (slack_tokens.json):
  {"T12345": {"token": "xoxb-...", "team_name": "My Workspace"}}

Fixed from original PR:
- Uses get_hermes_home() instead of hardcoded ~/.hermes/ path

Co-authored-by: yoannes <yoannes@users.noreply.github.com>
2026-03-30 01:51:48 -07:00
Teknium a4b064763d fix(cron): tighten [SILENT] instruction to prevent report-with-silent-prefix (#3901)
The model was interpreting [SILENT] as a metadata prefix and writing
full reports with [SILENT] slapped at the front. The old instruction
said 'optionally followed by a brief internal note' which gave too
much room. New instruction explicitly says: [SILENT] means nothing
else, do NOT combine it with a report.
2026-03-30 00:11:00 -07:00
Teknium 138ea3fbe8 fix(docs): escape angle-bracket URLs in feishu.md breaking MDX build (#3902) 2026-03-30 00:09:30 -07:00
Teknium ee61485cac feat(matrix): support native voice messages via MSC3245 (#3877)
* feat(matrix): support native voice messages

* fix: skip matrix voice tests when matrix-nio not installed

---------

Co-authored-by: Carlos Alberto Pereira Gomes <carlosapgomes@users.noreply.github.com>
2026-03-30 00:02:51 -07:00
Teknium 947faed3bc feat(approvals): make dangerous command approval timeout configurable (#3886)
* feat(approvals): make dangerous command approval timeout configurable

Read `approvals.timeout` from config.yaml (default 60s) instead of
hardcoding 60 seconds in both the fallback CLI prompt and the TUI
prompt_toolkit callback.

Follows the same pattern as `clarify.timeout` which is already
configurable via CLI_CONFIG.

Closes #3765

* fix: add timeout default to approvals section in DEFAULT_CONFIG

---------

Co-authored-by: acsezen <asezen@icloud.com>
2026-03-30 00:02:02 -07:00
kshitij c288bbfb57 fix(cli): prevent status bar wrapping into duplicate rows (#3883)
- measure status bar display width using prompt_toolkit cell widths
- trim rendered status text when fragments would overflow
- add a final single-fragment fallback to prevent wrapping
- update width assertions to validate display cells instead of len()
2026-03-29 23:59:07 -07:00
Teknium a347921314 docs: comprehensive OpenClaw migration guide (#3900)
New standalone guide at guides/migrate-from-openclaw.md with:
- Complete config key mapping tables for every category
- Agent behavior mappings (thinkingDefault → reasoning_effort, etc.)
- Session reset policy mapping (session.reset vs resetTriggers)
- TTS dual-source explanation (messages.tts.providers + talk config)
- MCP server field-by-field mapping
- Messaging platform table with exact config paths and env vars
- API key resolution: 3 sources, priority order, supported targets
- SecretRef handling: plain strings, env templates, SecretRef objects
- Post-migration checklist (6 steps)
- Troubleshooting section
- Complete archived items table with recreation guidance

CLI commands reference condensed to summary + link to full guide.
Added to sidebar under Guides & Tutorials.
2026-03-29 23:58:12 -07:00
Teknium 09def65eff fix(migration): expand OpenClaw migration to cover full data footprint (#3869)
Cross-referenced the OpenClaw Zod schema and TypeScript source against
our migration script. Found and fixed:

Expanded data sources:
- Legacy config fallback: clawdbot.json, moldbot.json
- Legacy dir fallback: ~/.clawdbot/, ~/.moldbot/
- API keys from ~/.openclaw/.env and auth-profiles.json
- Personal skills from ~/.agents/skills/
- Project skills from workspace/.agents/skills/
- BOOTSTRAP.md archived (was silently skipped)
- Expanded env key allowlist: DEEPSEEK, GEMINI, ZAI, MINIMAX

Fixed wrong config paths (verified against Zod schema):
- humanDelay.enabled → humanDelay.mode (field doesn't exist as .enabled)
- agents.defaults.exec.timeout → tools.exec.timeoutSec (wrong path + name)
- messages.tts.elevenlabs.voiceId → messages.tts.providers.elevenlabs.voiceId
- session.resetTriggers (string[]) → session.reset (structured object)
- approvals.mode → approvals.exec.mode (no top-level mode)
- browser.inactivityTimeoutMs → doesn't exist; map cdpUrl+headless instead
- tools.webSearch.braveApiKey → tools.web.search.brave.apiKey
- tools.exec.timeout → tools.exec.timeoutSec

Added SecretRef resolution:
- All token/apiKey fields in OpenClaw can be strings, env templates
  (${VAR}), or SecretRef objects ({source:'env',id:'VAR'}). Added
  resolve_secret_input() to handle all three forms.

Fixed auth-profiles.json:
- Canonical field is 'key' not 'apiKey' (though alias accepted)
- File wraps entries in a 'profiles' key — now handled

Fixed TTS config:
- Provider settings at messages.tts.providers.{name} (not flat)
- Also checks top-level 'talk' config as fallback source

Docs updated with new sources and key list.
2026-03-29 22:49:34 -07:00
Teknium 649d149438 feat(telegram): add webhook mode as alternative to polling (#3880)
When TELEGRAM_WEBHOOK_URL is set, the adapter starts an HTTP webhook
server (via python-telegram-bot's start_webhook()) instead of long
polling. This enables cloud platforms like Fly.io and Railway to
auto-wake suspended machines on inbound HTTP traffic.

Polling remains the default — no behavior change unless the env var
is set.

Env vars:
  TELEGRAM_WEBHOOK_URL    Public HTTPS URL for Telegram to push to
  TELEGRAM_WEBHOOK_PORT   Local listen port (default 8443)
  TELEGRAM_WEBHOOK_SECRET Secret token for update verification

Cherry-picked and adapted from PR #2022 by SHL0MS. Preserved all
current main enhancements (network error recovery, polling conflict
detection, DM topics setup).

Co-authored-by: SHL0MS <SHL0MS@users.noreply.github.com>
2026-03-29 22:36:07 -07:00
Teknium 5602458794 security: harden dangerous command detection and add file tool path guards (#3872)
Closes gaps that allowed an agent to expose Docker's Remote API to the
internet by writing to /etc/docker/daemon.json.

Terminal tool (approval.py):
- chmod: now catches 666 and symbolic modes (o+w, a+w), not just 777
- cp/mv/install: detected when targeting /etc/
- sed -i/--in-place: detected when targeting /etc/

File tools (file_tools.py):
- write_file and patch now refuse to write to sensitive system paths
  (/etc/, /boot/, /usr/lib/systemd/, docker.sock)
- Directs users to the terminal tool (which has approval prompts) for
  system file modifications
2026-03-29 22:33:47 -07:00
Teknium 1c900c45e3 fix(agent): support full context length resolution for direct Gemini API endpoints (#3876)
* add .aac audio file format support to transcription tool

* fix(agent): support full context length resolution for direct Gemini API endpoints

Add generativelanguage.googleapis.com to _URL_TO_PROVIDER so direct
Gemini API users get correct 1M+ context length instead of the 128K
unknown-proxy fallback.

Co-authored-by: bb873 <bb873@users.noreply.github.com>

---------

Co-authored-by: Adrian Scott <adrian@adrianscott.com>
Co-authored-by: bb873 <bb873@users.noreply.github.com>
2026-03-29 21:56:07 -07:00
Teknium 227601c200 feat(discord): add message processing reactions (salvage #1980) (#3871)
Adds lifecycle hooks to the base platform adapter so Discord (and future
platforms) can react to message processing events:

  👀  when processing starts
    on successful completion (delivery confirmed)
    on failure, error, or cancellation

Implementation:
- base.py: on_processing_start/on_processing_complete hooks with
  _run_processing_hook error isolation wrapper; delivery tracking
  via _record_delivery closure for accurate success detection
- discord.py: _add_reaction/_remove_reaction helpers + hook overrides
- Tests for base hook lifecycle and Discord-specific reactions

Co-authored-by: alanwilhelm <alanwilhelm@users.noreply.github.com>
2026-03-29 21:55:23 -07:00
Teknium fd29933a6d 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.
2026-03-29 21:54:36 -07:00
Teknium 839f798b74 feat(telegram): add group mention gating and regex triggers (#3870)
Adds Discord-style mention gating for Telegram groups:
- telegram.require_mention: gate group messages (default: false)
- telegram.mention_patterns: regex wake-word triggers
- telegram.free_response_chats: bypass gating for specific chats

When require_mention is enabled, group messages are accepted only for:
- slash commands
- replies to the bot
- @botusername mentions
- regex wake-word pattern matches

DMs remain unrestricted. @mention text is stripped before passing to
the agent. Invalid regex patterns are ignored with a warning.

Config bridges follow the existing Discord pattern (yaml → env vars).

Cherry-picked and adapted from PR #1977 by mcleay. Fixed ChatType
comparison to work without python-telegram-bot installed (uses string
matching instead of enum, consistent with other entity_type checks).

Co-authored-by: mcleay <mcleay@users.noreply.github.com>
2026-03-29 21:53:59 -07:00
Teknium 366bfc3c76 fix(setup): auto-install matrix-nio during hermes setup (#3873)
Setup previously only printed a manual install hint for matrix-nio,
causing the gateway to crash with 'matrix-nio not installed' after
configuring Matrix. Now auto-installs matrix-nio (or matrix-nio[e2e]
when E2EE is enabled) using the same uv-first/pip-fallback pattern
as Daytona and Modal backends.

Also adds hermes-agent[matrix] to the [all] extra in pyproject.toml
and a regression test to keep it there.

Co-authored-by: Gutslabs <Gutslabs@users.noreply.github.com>
Co-authored-by: cutepawss <cutepawss@users.noreply.github.com>
2026-03-29 21:53:28 -07:00
Teknium b4ceb541a7 fix(terminal): preserve partial output when command times out (#3868)
When a command timed out, all captured output was discarded — the agent
only saw 'Command timed out after Xs' with zero context. Now returns
the buffered output followed by a timeout marker, matching the existing
interrupt path behavior.

Salvaged from PR #3286 by @binhnt92.

Co-authored-by: nguyen binh <binhnt92@users.noreply.github.com>
2026-03-29 21:51:44 -07:00
Teknium ccf7bb1102 fix(nous): use curated model list instead of full API dump for Nous Portal (#3867)
All three Nous Portal model selection paths (hermes model, first-time
login, setup wizard) were hitting the live /models endpoint and showing
every model available — potentially hundreds. Now uses the curated
_PROVIDER_MODELS['nous'] list (25 agentic models matching OpenRouter
defaults) with 'Enter custom model name' for anything else.

Fixed in:
- hermes_cli/main.py: _model_flow_nous()
- hermes_cli/auth.py: _login_nous() model selection
- hermes_cli/setup.py: post-login model selection
2026-03-29 21:38:10 -07:00
Teknium ce2841f3c9 feat(gateway): add WeCom (Enterprise WeChat) platform support (#3847)
Adds WeCom as a gateway platform adapter using the AI Bot WebSocket
gateway for real-time bidirectional communication. No public endpoint
or new pip dependencies needed (uses existing aiohttp + httpx).

Features:
- WebSocket persistent connection with auto-reconnect (exponential backoff)
- DM and group messaging with configurable access policies
- Media upload/download with AES decryption for encrypted attachments
- Markdown rendering, quote context preservation
- Proactive + passive reply message modes
- Chunked media upload pipeline (512KB chunks)

Cherry-picked from PR #1898 by EvilRan with:
- Moved to current main (PR was 300 commits behind)
- Skipped base.py regressions (reply_to additions are good but belong
  in a separate PR since they affect all platforms)
- Fixed test assertions to match current base class send() signature
  (reply_to=None kwarg now explicit)
- All 16 integration points added surgically to current main
- No new pip dependencies (aiohttp + httpx already installed)

Fixes #1898

Co-authored-by: EvilRan <EvilRan@users.noreply.github.com>
2026-03-29 21:29:13 -07:00
Teknium e296efbf24 fix: add INFO-level logging for auxiliary provider resolution (#3866)
The auxiliary client's auto-detection chain was a black box — when
compression, summarization, or memory flush failed, the only clue was
a generic 'Request timed out' with no indication of which provider was
tried or why it was skipped.

Now logs at INFO level:
- 'Auxiliary auto-detect: using local/custom (qwen3.5-9b) — skipped:
  openrouter, nous' when auto-detection picks a provider
- 'Auxiliary compression: using auto (qwen3.5-9b) at http://localhost:11434/v1'
  before each auxiliary call
- 'Auxiliary compression: provider custom unavailable, falling back to
  openrouter' on fallback
- Clear warning with actionable guidance when NO provider is available:
  'Set OPENROUTER_API_KEY or configure a local model in config.yaml'
2026-03-29 21:29:00 -07:00
Teknium 2ff2cd3a59 add .aac audio file format support to transcription tool (#3865)
Co-authored-by: Adrian Scott <adrian@adrianscott.com>
2026-03-29 21:27:03 -07:00
Teknium f39ca81bab docs: comprehensive hermes claw migrate reference (#3864)
The existing docs were two lines. The migration script handles 35
categories of data across persona, memory, skills, messaging platforms,
model providers, MCP servers, agent config, and more.

New docs cover:
- All CLI options (--dry-run, --preset, --overwrite, --migrate-secrets,
  --source, --workspace-target, --skill-conflict, --yes)
- 27 directly-imported categories with source → destination mapping
- 7 archived categories with manual recreation guidance
- Security notes on API key allowlisting
- Usage examples for common migration scenarios
2026-03-29 21:25:13 -07:00
Teknium 3fad1e7cc1 fix(cron): resolve human-friendly delivery labels via channel directory (#3860)
Cron jobs configured with deliver labels from send_message(action='list')
like 'whatsapp:Alice (dm)' passed the label as a literal chat_id.
WhatsApp bridge failed with jidDecode error since 'Alice (dm)' isn't
a valid JID.

Now _resolve_delivery_target() strips display suffixes like ' (dm)' and
resolves human-friendly names via the channel directory before using
them. Raw IDs pass through unchanged when the directory has no match.

Fixes #1945.
2026-03-29 21:24:17 -07:00
Teknium 86ac23c8da fix(auth): stop silently falling back to OpenRouter when no provider is configured (#3862)
Previously, when no API keys or provider credentials were found, Hermes
silently defaulted to OpenRouter + Claude Opus. This caused confusion
when users configured local servers (LM Studio, Ollama, etc.) with a
typo or unrecognized provider name — the system would silently route to
OpenRouter instead of telling them something was wrong.

Changes:
- resolve_provider() now raises AuthError when no credentials are found
  instead of returning 'openrouter' as a silent fallback
- Added local server aliases: lmstudio, ollama, vllm, llamacpp → custom
- Removed hardcoded 'anthropic/claude-opus-4.6' fallback from gateway
  and cron scheduler (they read from config.yaml instead)
- Updated cli-config.yaml.example with complete provider documentation
  including all supported providers, aliases, and local server setup
2026-03-29 21:06:35 -07:00
Teknium 3cc50532d1 fix: auxiliary client uses placeholder key for local servers without auth (#3842)
Local inference servers (Ollama, llama.cpp, vLLM, LM Studio) don't
require API keys, but the auxiliary client's _resolve_custom_runtime()
rejected endpoints with empty keys — causing the auto-detection chain
to skip the user's local server entirely.  This broke compression,
summarization, and memory flush for users running local models without
an OpenRouter/cloud API key.

The main CLI already had this fix (PR #2556, 'no-key-required'
placeholder), but the auxiliary client's resolution path was missed.

Two fixes:
- _resolve_custom_runtime(): use 'no-key-required' placeholder instead
  of returning None when base_url is present but key is empty
- resolve_provider_client() custom branch: same placeholder fallback
  for explicit_base_url without explicit_api_key

Updates 2 tests that expected the old (broken) behavior.
2026-03-29 21:05:36 -07:00
Teknium 2d607d36f6 fix(security): catch sensitive path writes in approval checks (#3859)
Co-authored-by: Gutslabs <gutslabsxyz@gmail.com>
2026-03-29 20:57:57 -07:00
Teknium aa389924ad fix: prefer curated model list when live probe returns fewer models (#3856)
The model picker for API-key providers (MiniMax, z.ai, etc.) probes
the live /models endpoint when the curated list has fewer than 8
models. When the live endpoint returns fewer models than the curated
list (e.g. MiniMax's Anthropic-compatible endpoint doesn't list M2.7),
the incomplete live list was used instead.

Now falls back to the curated list when live returns fewer models,
ensuring new models like MiniMax-M2.7 always appear in the picker.
2026-03-29 20:55:15 -07:00
Teknium 5e67fc8c40 fix(vision): reject non-image files and enforce website policy (salvage #1940) (#3845)
Three safety gaps in vision_analyze_tool:

1. Local files accepted without checking if they're actually images —
   a renamed text file would get base64-encoded and sent to the model.
   Now validates magic bytes (PNG, JPEG, GIF, BMP, WebP, SVG).

2. No website policy enforcement on image URLs — blocked domains could
   be fetched via the vision tool. Now checks before download.

3. No redirect check — if an allowed URL redirected to a blocked domain,
   the download would proceed. Now re-checks the final URL.

Fixed one test that needed _validate_image_url mocked to bypass DNS
resolution on the fake blocked.test domain (is_safe_url does DNS
checks that were added after the original PR).

Co-authored-by: GutSlabs <GutSlabs@users.noreply.github.com>
2026-03-29 20:55:04 -07:00
Teknium b60cfd6ce6 fix(telegram): gracefully handle deleted reply targets (#3858)
* fix: add gpt-5.4-mini to Codex fallback catalog

* fix(telegram): gracefully handle deleted reply targets

When a user deletes their message while Hermes is processing, Telegram
returns BadRequest 'Message to be replied not found'. Previously this
was an unhandled permanent error causing silent delivery failure.

Now clears reply_to_id and retries so the response is still delivered,
matching the existing 'thread not found' recovery pattern.

Inspired by PR #3231 by @heathley. Fixes #3229.

---------

Co-authored-by: Clippy <clippy@grads.flow>
Co-authored-by: Nigel Gibbs <heathley@users.noreply.github.com>
2026-03-29 20:47:07 -07:00
Teknium 981e14001c fix: clear api_mode on provider switch instead of hardcoding chat_completions (#3857)
PR #3726 fixed stale codex_responses persisting when switching providers
by hardcoding api_mode=chat_completions in 5 model flows. This broke
MiniMax, MiniMax-CN, and Alibaba which use /anthropic endpoints that
need anthropic_messages — the hardcoded value overrides the URL-based
auto-detection in runtime_provider.py.

Fix: pop api_mode from config in the 3 URL-dependent flows (custom
endpoint, Kimi, api_key_provider) instead of hardcoding. The runtime
resolver already correctly auto-detects api_mode from the base_url
suffix (/anthropic -> anthropic_messages, else chat_completions).

OpenRouter and Copilot ACP flows keep the explicit value since their
api_mode is always known.

Reported by stefan171.
2026-03-29 20:44:39 -07:00
Teknium 9d28f4aba3 fix: add gpt-5.4-mini to Codex fallback catalog (#3855)
Co-authored-by: Clippy <clippy@grads.flow>
2026-03-29 20:10:00 -07:00
Teknium 3e203de125 fix(skills): block category path traversal in skill manager (#3844)
Validate category names in _create_skill() before using them as
filesystem path segments. Previously, categories like '../escape' or
'/tmp/pwned' could write skill files outside ~/.hermes/skills/.

Adds _validate_category() that rejects slashes, backslashes, absolute
paths, and non-alphanumeric characters (reuses existing VALID_NAME_RE).

Tests: 5 new tests for traversal, absolute paths, and valid categories.

Salvaged from PR #1939 by Gutslabs.
2026-03-29 20:08:22 -07:00
Teknium 2d264a4562 fix(tests): resolve 10 CI failures across hooks, tiktoken, plugins (#3848)
test_hooks.py (7 failures): Built-in boot-md hook was always loaded
by _register_builtin_hooks(), adding +1 to every expected hook count.
Mock out built-in registration in TestDiscoverAndLoad so tests isolate
user-hook discovery logic.

test_tool_token_estimation.py (2 failures): tiktoken is not in
core/[all] dependencies. The estimation function gracefully returns {}
when tiktoken is missing, but tests expected non-empty results. Added
skipif markers for tests that need tiktoken.

test_plugins_cmd.py (1 failure): bare 'hermes plugins' now dispatches
to cmd_toggle() (interactive curses UI) instead of cmd_list(). Updated
test to match the new behavior.
2026-03-29 20:05:59 -07:00
Teknium 3e2c8c529b fix(whatsapp): resolve LID↔phone aliases in allowlist matching (#3830)
WhatsApp DMs can arrive with LID sender IDs even when
WHATSAPP_ALLOWED_USERS is configured with phone numbers. The allowlist
check now reads bridge session mapping files (lid-mapping-*.json) to
resolve phone↔LID aliases, matching users regardless of which
identifier format the message uses.

Both the Python gateway (_is_user_authorized) and the Node bridge
(allowlist.js) now share the same mapping-file-based resolution logic.

Co-authored-by: Frederico Ribeiro <fr@tecompanytea.com>
2026-03-29 18:21:50 -07:00
Teknium e4d575e563 fix: report subagent status as completed when summary exists (#3829)
When a subagent hit max_iterations, status was always 'failed' even
if it produced a usable summary via _handle_max_iterations(). This
happened because the status check required both completed=True AND
a summary, but completed is False whenever max_iterations is reached
(run_agent.py line 7969).

Now gates status on whether a summary was produced — if the subagent
returned a final_response, the parent has usable output regardless of
iteration budget. The exit_reason field already distinguishes
'completed' vs 'max_iterations' for anything that needs to know how
the task ended.

Closes #1899.
2026-03-29 18:21:36 -07:00
Teknium 2a0e8b001f fix(cli): handle closed stdout ValueError in safe print paths (#3843)
When stdout is closed (piped to a dead process, broken terminal),
Python raises ValueError('I/O operation on closed file'), not OSError.
_safe_print and the API error printer only caught OSError, letting the
ValueError propagate and crash the agent.

Salvaged from PR #3760 by @apexscaleai. Fixes #3534.

Co-authored-by: apexscaleai <apexscaleai@users.noreply.github.com>
2026-03-29 18:21:27 -07:00
Teknium ca4907dfbc feat(gateway): add Feishu/Lark platform support (#3817)
Adds Feishu (ByteDance's enterprise messaging platform) as a gateway
platform adapter with full feature parity: WebSocket + webhook transports,
message batching, dedup, rate limiting, rich post/card content parsing,
media handling (images/audio/files/video), group @mention gating,
reaction routing, and interactive card button support.

Cherry-picked from PR #1793 by penwyp with:
- Moved to current main (PR was 458 commits behind)
- Fixed _send_with_retry shadowing BasePlatformAdapter method (renamed to
  _feishu_send_with_retry to avoid signature mismatch crash)
- Fixed import structure: aiohttp/websockets imported independently of
  lark_oapi so they remain available when SDK is missing
- Fixed get_hermes_home import (hermes_constants, not hermes_cli.config)
- Added skip decorators for tests requiring lark_oapi SDK
- All 16 integration points added surgically to current main

New dependency: lark-oapi>=1.5.3,<2 (optional, pip install hermes-agent[feishu])

Fixes #1788

Co-authored-by: penwyp <penwyp@users.noreply.github.com>
2026-03-29 18:17:42 -07:00
Teknium e314833c9d feat(display): configurable tool preview length -- show full paths by default (#3841)
Tool call previews (paths, commands, queries) were hardcoded to truncate
at 35-40 chars across CLI spinners, completion lines, and gateway progress
messages. Users could not see full file paths in tool output.

New config option: display.tool_preview_length (default 0 = no limit).
Set a positive number to truncate at that length.

Changes:
- display.py: module-level _tool_preview_max_len with getter/setter;
  build_tool_preview() and get_cute_tool_message() _trunc/_path respect it
- cli.py: reads config at startup, spinner widget respects config
- gateway/run.py: reads config per-message, progress callback respects config
- run_agent.py: removed redundant 30-char quiet-mode spinner truncation
- config.py: added display.tool_preview_length to DEFAULT_CONFIG

Reported by kriskaminski
2026-03-29 18:02:42 -07:00
Teknium 59f2b228f7 fix(paths): respect HERMES_HOME for protected .env write-deny path (#3840)
The write-deny list in file_operations.py hardcoded ~/.hermes/.env,
which misses the actual .env in custom HERMES_HOME or profile setups.
Use get_hermes_home() for profile-safe path resolution.

Salvaged from PR #3232 by @erhnysr.

Co-authored-by: Erhnysr <erhnysr@users.noreply.github.com>
2026-03-29 18:02:11 -07:00
Teknium d6b7836210 fix: update session_log_file during context compression (#3835)
When compression creates a child session with a new session_id,
session_log_file was still pointing to the old session's JSON file.
This caused _save_session_log() to write new data to the wrong file.

Closes #3731.

Co-authored-by: kelsia14 <kelsia14@users.noreply.github.com>
2026-03-29 17:49:58 -07:00
Teknium 17b6000e90 feat(skills): add songwriting-and-ai-music creative skill (salvage #1901) (#3834)
Adds a songwriting craft and AI music prompt engineering skill covering
song structure, rhyme/meter, emotional arcs, Suno metatag reference,
phonetic tricks for AI singers, parody adaptation, and production workflow.

Complements existing music skills (heartmula, audiocraft, songsee) which
cover model setup/usage — this one covers the creative process itself.

Also removes the empty skills/music-creation/ category (only had a
DESCRIPTION.md, no actual skills).

Co-authored-by: 123mikeyd <123mikeyd@users.noreply.github.com>
2026-03-29 17:49:19 -07:00
260 changed files with 21246 additions and 3312 deletions
+15
View File
@@ -231,6 +231,21 @@ VOICE_TOOLS_OPENAI_KEY=
# Slack allowed users (comma-separated Slack user IDs)
# SLACK_ALLOWED_USERS=
# =============================================================================
# TELEGRAM INTEGRATION
# =============================================================================
# Telegram Bot Token - From @BotFather (https://t.me/BotFather)
# TELEGRAM_BOT_TOKEN=
# TELEGRAM_ALLOWED_USERS= # Comma-separated user IDs
# TELEGRAM_HOME_CHANNEL= # Default chat for cron delivery
# TELEGRAM_HOME_CHANNEL_NAME= # Display name for home channel
# Webhook mode (optional — for cloud deployments like Fly.io/Railway)
# Default is long polling. Setting TELEGRAM_WEBHOOK_URL switches to webhook mode.
# TELEGRAM_WEBHOOK_URL=https://my-app.fly.dev/telegram
# TELEGRAM_WEBHOOK_PORT=8443
# TELEGRAM_WEBHOOK_SECRET= # Recommended for production
# WhatsApp (built-in Baileys bridge — run `hermes whatsapp` to pair)
# WHATSAPP_ENABLED=false
# WHATSAPP_ALLOWED_USERS=15551234567
+2
View File
@@ -19,6 +19,8 @@ concurrency:
jobs:
build-and-deploy:
# Only run on the upstream repository, not on forks
if: github.repository == 'NousResearch/hermes-agent'
runs-on: ubuntu-latest
environment:
name: github-pages
+2
View File
@@ -12,6 +12,8 @@ concurrency:
jobs:
build-and-push:
# Only run on the upstream repository, not on forks
if: github.repository == 'NousResearch/hermes-agent'
runs-on: ubuntu-latest
timeout-minutes: 30
steps:
+4
View File
@@ -0,0 +1,4 @@
graft skills
graft optional-skills
global-exclude __pycache__
global-exclude *.py[cod]
+249
View File
@@ -0,0 +1,249 @@
# Hermes Agent v0.6.0 (v2026.3.30)
**Release Date:** March 30, 2026
> The multi-instance release — Profiles for running isolated agent instances, MCP server mode, Docker container, fallback provider chains, two new messaging platforms (Feishu/Lark and WeCom), Telegram webhook mode, Slack multi-workspace OAuth, 95 PRs and 16 resolved issues in 2 days.
---
## ✨ Highlights
- **Profiles — Multi-Instance Hermes** — Run multiple isolated Hermes instances from the same installation. Each profile gets its own config, memory, sessions, skills, and gateway service. Create with `hermes profile create`, switch with `hermes -p <name>`, export/import for sharing. Full token-lock isolation prevents two profiles from using the same bot credential. ([#3681](https://github.com/NousResearch/hermes-agent/pull/3681))
- **MCP Server Mode** — Expose Hermes conversations and sessions to any MCP-compatible client (Claude Desktop, Cursor, VS Code, etc.) via `hermes mcp serve`. Browse conversations, read messages, search across sessions, and manage attachments — all through the Model Context Protocol. Supports both stdio and Streamable HTTP transports. ([#3795](https://github.com/NousResearch/hermes-agent/pull/3795))
- **Docker Container** — Official Dockerfile for running Hermes Agent in a container. Supports both CLI and gateway modes with volume-mounted config. ([#3668](https://github.com/NousResearch/hermes-agent/pull/3668), closes [#850](https://github.com/NousResearch/hermes-agent/issues/850))
- **Ordered Fallback Provider Chain** — Configure multiple inference providers with automatic failover. When your primary provider returns errors or is unreachable, Hermes automatically tries the next provider in the chain. Configure via `fallback_providers` in config.yaml. ([#3813](https://github.com/NousResearch/hermes-agent/pull/3813), closes [#1734](https://github.com/NousResearch/hermes-agent/issues/1734))
- **Feishu/Lark Platform Support** — Full gateway adapter for Feishu (飞书) and Lark with event subscriptions, message cards, group chat, image/file attachments, and interactive card callbacks. ([#3799](https://github.com/NousResearch/hermes-agent/pull/3799), [#3817](https://github.com/NousResearch/hermes-agent/pull/3817), closes [#1788](https://github.com/NousResearch/hermes-agent/issues/1788))
- **WeCom (Enterprise WeChat) Platform Support** — New gateway adapter for WeCom (企业微信) with text/image/voice messages, group chats, and callback verification. ([#3847](https://github.com/NousResearch/hermes-agent/pull/3847))
- **Slack Multi-Workspace OAuth** — Connect a single Hermes gateway to multiple Slack workspaces via OAuth token file. Each workspace gets its own bot token, resolved dynamically per incoming event. ([#3903](https://github.com/NousResearch/hermes-agent/pull/3903))
- **Telegram Webhook Mode & Group Controls** — Run the Telegram adapter in webhook mode as an alternative to polling — faster response times and better for production deployments behind a reverse proxy. New group mention gating controls when the bot responds: always, only when @mentioned, or via regex triggers. ([#3880](https://github.com/NousResearch/hermes-agent/pull/3880), [#3870](https://github.com/NousResearch/hermes-agent/pull/3870))
- **Exa Search Backend** — Add Exa as an alternative web search and content extraction backend alongside Firecrawl and DuckDuckGo. Set `EXA_API_KEY` and configure as preferred backend. ([#3648](https://github.com/NousResearch/hermes-agent/pull/3648))
- **Skills & Credentials on Remote Backends** — Mount skill directories and credential files into Modal and Docker containers, so remote terminal sessions have access to the same skills and secrets as local execution. ([#3890](https://github.com/NousResearch/hermes-agent/pull/3890), [#3671](https://github.com/NousResearch/hermes-agent/pull/3671), closes [#3665](https://github.com/NousResearch/hermes-agent/issues/3665), [#3433](https://github.com/NousResearch/hermes-agent/issues/3433))
---
## 🏗️ Core Agent & Architecture
### Provider & Model Support
- **Ordered fallback provider chain** — automatic failover across multiple configured providers ([#3813](https://github.com/NousResearch/hermes-agent/pull/3813))
- **Fix api_mode on provider switch** — switching providers via `hermes model` now correctly clears stale `api_mode` instead of hardcoding `chat_completions`, fixing 404s for providers with Anthropic-compatible endpoints ([#3726](https://github.com/NousResearch/hermes-agent/pull/3726), [#3857](https://github.com/NousResearch/hermes-agent/pull/3857), closes [#3685](https://github.com/NousResearch/hermes-agent/issues/3685))
- **Stop silent OpenRouter fallback** — when no provider is configured, Hermes now raises a clear error instead of silently routing to OpenRouter ([#3807](https://github.com/NousResearch/hermes-agent/pull/3807), [#3862](https://github.com/NousResearch/hermes-agent/pull/3862))
- **Gemini 3.1 preview models** — added to OpenRouter and Nous Portal catalogs ([#3803](https://github.com/NousResearch/hermes-agent/pull/3803), closes [#3753](https://github.com/NousResearch/hermes-agent/issues/3753))
- **Gemini direct API context length** — full context length resolution for direct Google AI endpoints ([#3876](https://github.com/NousResearch/hermes-agent/pull/3876))
- **gpt-5.4-mini** added to Codex fallback catalog ([#3855](https://github.com/NousResearch/hermes-agent/pull/3855))
- **Curated model lists preferred** over live API probe when the probe returns fewer models ([#3856](https://github.com/NousResearch/hermes-agent/pull/3856), [#3867](https://github.com/NousResearch/hermes-agent/pull/3867))
- **User-friendly 429 rate limit messages** with Retry-After countdown ([#3809](https://github.com/NousResearch/hermes-agent/pull/3809))
- **Auxiliary client placeholder key** for local servers without auth requirements ([#3842](https://github.com/NousResearch/hermes-agent/pull/3842))
- **INFO-level logging** for auxiliary provider resolution ([#3866](https://github.com/NousResearch/hermes-agent/pull/3866))
### Agent Loop & Conversation
- **Subagent status reporting** — reports `completed` status when summary exists instead of generic failure ([#3829](https://github.com/NousResearch/hermes-agent/pull/3829))
- **Session log file updated during compression** — prevents stale file references after context compression ([#3835](https://github.com/NousResearch/hermes-agent/pull/3835))
- **Omit empty tools param** — sends no `tools` parameter when empty instead of `None`, fixing compatibility with strict providers ([#3820](https://github.com/NousResearch/hermes-agent/pull/3820))
### Profiles & Multi-Instance
- **Profiles system** — `hermes profile create/list/switch/delete/export/import/rename`. Each profile gets isolated HERMES_HOME, gateway service, CLI wrapper. Token locks prevent credential collisions. Tab completion for profile names. ([#3681](https://github.com/NousResearch/hermes-agent/pull/3681))
- **Profile-aware display paths** — all user-facing `~/.hermes` paths replaced with `display_hermes_home()` to show the correct profile directory ([#3623](https://github.com/NousResearch/hermes-agent/pull/3623))
- **Lazy display_hermes_home imports** — prevents `ImportError` during `hermes update` when modules cache stale bytecode ([#3776](https://github.com/NousResearch/hermes-agent/pull/3776))
- **HERMES_HOME for protected paths** — `.env` write-deny path now respects HERMES_HOME instead of hardcoded `~/.hermes` ([#3840](https://github.com/NousResearch/hermes-agent/pull/3840))
---
## 📱 Messaging Platforms (Gateway)
### New Platforms
- **Feishu/Lark** — Full adapter with event subscriptions, message cards, group chat, image/file attachments, interactive card callbacks ([#3799](https://github.com/NousResearch/hermes-agent/pull/3799), [#3817](https://github.com/NousResearch/hermes-agent/pull/3817))
- **WeCom (Enterprise WeChat)** — Text/image/voice messages, group chats, callback verification ([#3847](https://github.com/NousResearch/hermes-agent/pull/3847))
### Telegram
- **Webhook mode** — run as webhook endpoint instead of polling for production deployments ([#3880](https://github.com/NousResearch/hermes-agent/pull/3880))
- **Group mention gating & regex triggers** — configurable bot response behavior in groups: always, @mention-only, or regex-matched ([#3870](https://github.com/NousResearch/hermes-agent/pull/3870))
- **Gracefully handle deleted reply targets** — no more crashes when the message being replied to was deleted ([#3858](https://github.com/NousResearch/hermes-agent/pull/3858), closes [#3229](https://github.com/NousResearch/hermes-agent/issues/3229))
### Discord
- **Message processing reactions** — adds a reaction emoji while processing and removes it when done, giving visual feedback in channels ([#3871](https://github.com/NousResearch/hermes-agent/pull/3871))
- **DISCORD_IGNORE_NO_MENTION** — skip messages that @mention other users/bots but not Hermes ([#3640](https://github.com/NousResearch/hermes-agent/pull/3640))
- **Clean up deferred "thinking..."** — properly removes the "thinking..." indicator after slash commands complete ([#3674](https://github.com/NousResearch/hermes-agent/pull/3674), closes [#3595](https://github.com/NousResearch/hermes-agent/issues/3595))
### Slack
- **Multi-workspace OAuth** — connect to multiple Slack workspaces from a single gateway via OAuth token file ([#3903](https://github.com/NousResearch/hermes-agent/pull/3903))
### WhatsApp
- **Persistent aiohttp session** — reuse HTTP sessions across requests instead of creating new ones per message ([#3818](https://github.com/NousResearch/hermes-agent/pull/3818))
- **LID↔phone alias resolution** — correctly match Linked ID and phone number formats in allowlists ([#3830](https://github.com/NousResearch/hermes-agent/pull/3830))
- **Skip reply prefix in bot mode** — cleaner message formatting when running as a WhatsApp bot ([#3931](https://github.com/NousResearch/hermes-agent/pull/3931))
### Matrix
- **Native voice messages via MSC3245** — send voice messages as proper Matrix voice events instead of file attachments ([#3877](https://github.com/NousResearch/hermes-agent/pull/3877))
### Mattermost
- **Configurable mention behavior** — respond to messages without requiring @mention ([#3664](https://github.com/NousResearch/hermes-agent/pull/3664))
### Signal
- **URL-encode phone numbers** and correct attachment RPC parameter — fixes delivery failures with certain phone number formats ([#3670](https://github.com/NousResearch/hermes-agent/pull/3670)) — @kshitijk4poor
### Email
- **Close SMTP/IMAP connections on failure** — prevents connection leaks during error scenarios ([#3804](https://github.com/NousResearch/hermes-agent/pull/3804))
### Gateway Core
- **Atomic config writes** — use atomic file writes for config.yaml to prevent data loss during crashes ([#3800](https://github.com/NousResearch/hermes-agent/pull/3800))
- **Home channel env overrides** — apply environment variable overrides for home channels consistently ([#3796](https://github.com/NousResearch/hermes-agent/pull/3796), [#3808](https://github.com/NousResearch/hermes-agent/pull/3808))
- **Replace print() with logger** — BasePlatformAdapter now uses proper logging instead of print statements ([#3669](https://github.com/NousResearch/hermes-agent/pull/3669))
- **Cron delivery labels** — resolve human-friendly delivery labels via channel directory ([#3860](https://github.com/NousResearch/hermes-agent/pull/3860), closes [#1945](https://github.com/NousResearch/hermes-agent/issues/1945))
- **Cron [SILENT] tightening** — prevent agents from prefixing reports with [SILENT] to suppress delivery ([#3901](https://github.com/NousResearch/hermes-agent/pull/3901))
- **Background task media delivery** and vision download timeout fixes ([#3919](https://github.com/NousResearch/hermes-agent/pull/3919))
- **Boot-md hook** — example built-in hook to run a BOOT.md file on gateway startup ([#3733](https://github.com/NousResearch/hermes-agent/pull/3733))
---
## 🖥️ CLI & User Experience
### Interactive CLI
- **Configurable tool preview length** — show full file paths by default instead of truncating at 40 chars ([#3841](https://github.com/NousResearch/hermes-agent/pull/3841))
- **Tool token context display** — `hermes tools` checklist now shows estimated token cost per toolset ([#3805](https://github.com/NousResearch/hermes-agent/pull/3805))
- **/bg spinner TUI fix** — route background task spinner through the TUI widget to prevent status bar collision ([#3643](https://github.com/NousResearch/hermes-agent/pull/3643))
- **Prevent status bar wrapping** into duplicate rows ([#3883](https://github.com/NousResearch/hermes-agent/pull/3883)) — @kshitijk4poor
- **Handle closed stdout ValueError** in safe print paths — fixes crashes when stdout is closed during gateway thread shutdown ([#3843](https://github.com/NousResearch/hermes-agent/pull/3843), closes [#3534](https://github.com/NousResearch/hermes-agent/issues/3534))
- **Remove input() from /tools disable** — eliminates freeze in terminal when disabling tools ([#3918](https://github.com/NousResearch/hermes-agent/pull/3918))
- **TTY guard for interactive CLI commands** — prevent CPU spin when launched without a terminal ([#3933](https://github.com/NousResearch/hermes-agent/pull/3933))
- **Argparse entrypoint** — use argparse in the top-level launcher for cleaner error handling ([#3874](https://github.com/NousResearch/hermes-agent/pull/3874))
- **Lazy-initialized tools show yellow** in banner instead of red, reducing false alarm about "missing" tools ([#3822](https://github.com/NousResearch/hermes-agent/pull/3822))
- **Honcho tools shown in banner** when configured ([#3810](https://github.com/NousResearch/hermes-agent/pull/3810))
### Setup & Configuration
- **Auto-install matrix-nio** during `hermes setup` when Matrix is selected ([#3802](https://github.com/NousResearch/hermes-agent/pull/3802), [#3873](https://github.com/NousResearch/hermes-agent/pull/3873))
- **Session export stdout support** — export sessions to stdout with `-` for piping ([#3641](https://github.com/NousResearch/hermes-agent/pull/3641), closes [#3609](https://github.com/NousResearch/hermes-agent/issues/3609))
- **Configurable approval timeouts** — set how long dangerous command approval prompts wait before auto-denying ([#3886](https://github.com/NousResearch/hermes-agent/pull/3886), closes [#3765](https://github.com/NousResearch/hermes-agent/issues/3765))
- **Clear __pycache__ during update** — prevents stale bytecode ImportError after `hermes update` ([#3819](https://github.com/NousResearch/hermes-agent/pull/3819))
---
## 🔧 Tool System
### MCP
- **MCP Server Mode** — `hermes mcp serve` exposes conversations, sessions, and attachments to MCP clients via stdio or Streamable HTTP ([#3795](https://github.com/NousResearch/hermes-agent/pull/3795))
- **Dynamic tool discovery** — respond to `notifications/tools/list_changed` events to pick up new tools from MCP servers without reconnecting ([#3812](https://github.com/NousResearch/hermes-agent/pull/3812))
- **Non-deprecated HTTP transport** — switched from `sse_client` to `streamable_http_client` ([#3646](https://github.com/NousResearch/hermes-agent/pull/3646))
### Web Tools
- **Exa search backend** — alternative to Firecrawl and DuckDuckGo for web search and extraction ([#3648](https://github.com/NousResearch/hermes-agent/pull/3648))
### Browser
- **Guard against None LLM responses** in browser snapshot and vision tools ([#3642](https://github.com/NousResearch/hermes-agent/pull/3642))
### Terminal & Remote Backends
- **Mount skill directories** into Modal and Docker containers ([#3890](https://github.com/NousResearch/hermes-agent/pull/3890))
- **Mount credential files** into remote backends with mtime+size caching ([#3671](https://github.com/NousResearch/hermes-agent/pull/3671))
- **Preserve partial output** when commands time out instead of losing everything ([#3868](https://github.com/NousResearch/hermes-agent/pull/3868))
- **Stop marking persisted env vars as missing** on remote backends ([#3650](https://github.com/NousResearch/hermes-agent/pull/3650))
### Audio
- **.aac format support** in transcription tool ([#3865](https://github.com/NousResearch/hermes-agent/pull/3865), closes [#1963](https://github.com/NousResearch/hermes-agent/issues/1963))
- **Audio download retry** — retry logic for `cache_audio_from_url` matching the existing image download pattern ([#3401](https://github.com/NousResearch/hermes-agent/pull/3401)) — @binhnt92
### Vision
- **Reject non-image files** and enforce website-only policy for vision analysis ([#3845](https://github.com/NousResearch/hermes-agent/pull/3845))
### Tool Schema
- **Ensure name field** always present in tool definitions, fixing `KeyError: 'name'` crashes ([#3811](https://github.com/NousResearch/hermes-agent/pull/3811), closes [#3729](https://github.com/NousResearch/hermes-agent/issues/3729))
### ACP (Editor Integration)
- **Complete session management surface** for VS Code/Zed/JetBrains clients — proper task lifecycle, cancel support, session persistence ([#3675](https://github.com/NousResearch/hermes-agent/pull/3675))
---
## 🧩 Skills & Plugins
### Skills System
- **External skill directories** — configure additional skill directories via `skills.external_dirs` in config.yaml ([#3678](https://github.com/NousResearch/hermes-agent/pull/3678))
- **Category path traversal blocked** — prevents `../` attacks in skill category names ([#3844](https://github.com/NousResearch/hermes-agent/pull/3844))
- **parallel-cli moved to optional-skills** — reduces default skill footprint ([#3673](https://github.com/NousResearch/hermes-agent/pull/3673)) — @kshitijk4poor
### New Skills
- **memento-flashcards** — spaced repetition flashcard system ([#3827](https://github.com/NousResearch/hermes-agent/pull/3827))
- **songwriting-and-ai-music** — songwriting craft and AI music generation prompts ([#3834](https://github.com/NousResearch/hermes-agent/pull/3834))
- **SiYuan Note** — integration with SiYuan note-taking app ([#3742](https://github.com/NousResearch/hermes-agent/pull/3742))
- **Scrapling** — web scraping skill using Scrapling library ([#3742](https://github.com/NousResearch/hermes-agent/pull/3742))
- **one-three-one-rule** — communication framework skill ([#3797](https://github.com/NousResearch/hermes-agent/pull/3797))
### Plugin System
- **Plugin enable/disable commands** — `hermes plugins enable/disable <name>` for managing plugin state without removing them ([#3747](https://github.com/NousResearch/hermes-agent/pull/3747))
- **Plugin message injection** — plugins can now inject messages into the conversation stream on behalf of the user via `ctx.inject_message()` ([#3778](https://github.com/NousResearch/hermes-agent/pull/3778)) — @winglian
- **Honcho self-hosted support** — allow local Honcho instances without requiring an API key ([#3644](https://github.com/NousResearch/hermes-agent/pull/3644))
---
## 🔒 Security & Reliability
### Security Hardening
- **Hardened dangerous command detection** — expanded pattern matching for risky shell commands and added file tool path guards for sensitive locations (`/etc/`, `/boot/`, docker.sock) ([#3872](https://github.com/NousResearch/hermes-agent/pull/3872))
- **Sensitive path write checks** in approval system — catch writes to system config files through file tools, not just terminal ([#3859](https://github.com/NousResearch/hermes-agent/pull/3859))
- **Secret redaction expansion** — now covers ElevenLabs, Tavily, and Exa API keys ([#3920](https://github.com/NousResearch/hermes-agent/pull/3920))
- **Vision file rejection** — reject non-image files passed to vision analysis to prevent information disclosure ([#3845](https://github.com/NousResearch/hermes-agent/pull/3845))
- **Category path traversal blocking** — prevent directory traversal in skill category names ([#3844](https://github.com/NousResearch/hermes-agent/pull/3844))
### Reliability
- **Atomic config.yaml writes** — prevent data loss during gateway crashes ([#3800](https://github.com/NousResearch/hermes-agent/pull/3800))
- **Clear __pycache__ on update** — prevent stale bytecode from causing ImportError after updates ([#3819](https://github.com/NousResearch/hermes-agent/pull/3819))
- **Lazy imports for update safety** — prevent ImportError chains during `hermes update` when modules reference new functions ([#3776](https://github.com/NousResearch/hermes-agent/pull/3776))
- **Restore terminalbench2 from patch corruption** — recovered file damaged by patch tool's secret redaction ([#3801](https://github.com/NousResearch/hermes-agent/pull/3801))
- **Terminal timeout preserves partial output** — no more lost command output on timeout ([#3868](https://github.com/NousResearch/hermes-agent/pull/3868))
---
## 🐛 Notable Bug Fixes
- **OpenClaw migration model config overwrite** — migration no longer overwrites model config dict with a string ([#3924](https://github.com/NousResearch/hermes-agent/pull/3924)) — @0xbyt4
- **OpenClaw migration expanded** — covers full data footprint including sessions, cron, memory ([#3869](https://github.com/NousResearch/hermes-agent/pull/3869))
- **Telegram deleted reply targets** — gracefully handle replies to deleted messages instead of crashing ([#3858](https://github.com/NousResearch/hermes-agent/pull/3858))
- **Discord "thinking..." persistence** — properly cleans up deferred response indicators ([#3674](https://github.com/NousResearch/hermes-agent/pull/3674))
- **WhatsApp LID↔phone aliases** — fixes allowlist matching failures with Linked ID format ([#3830](https://github.com/NousResearch/hermes-agent/pull/3830))
- **Signal URL-encoded phone numbers** — fixes delivery failures with certain formats ([#3670](https://github.com/NousResearch/hermes-agent/pull/3670))
- **Email connection leaks** — properly close SMTP/IMAP connections on error ([#3804](https://github.com/NousResearch/hermes-agent/pull/3804))
- **_safe_print ValueError** — no more gateway thread crashes on closed stdout ([#3843](https://github.com/NousResearch/hermes-agent/pull/3843))
- **Tool schema KeyError 'name'** — ensure name field always present in tool definitions ([#3811](https://github.com/NousResearch/hermes-agent/pull/3811))
- **api_mode stale on provider switch** — correctly clear when switching providers via `hermes model` ([#3857](https://github.com/NousResearch/hermes-agent/pull/3857))
---
## 🧪 Testing
- Resolved 10+ CI failures across hooks, tiktoken, plugins, and skill tests ([#3848](https://github.com/NousResearch/hermes-agent/pull/3848), [#3721](https://github.com/NousResearch/hermes-agent/pull/3721), [#3936](https://github.com/NousResearch/hermes-agent/pull/3936))
---
## 📚 Documentation
- **Comprehensive OpenClaw migration guide** — step-by-step guide for migrating from OpenClaw/Claw3D to Hermes Agent ([#3864](https://github.com/NousResearch/hermes-agent/pull/3864), [#3900](https://github.com/NousResearch/hermes-agent/pull/3900))
- **Credential file passthrough docs** — document how to forward credential files and env vars to remote backends ([#3677](https://github.com/NousResearch/hermes-agent/pull/3677))
- **DuckDuckGo requirements clarified** — note runtime dependency on duckduckgo-search package ([#3680](https://github.com/NousResearch/hermes-agent/pull/3680))
- **Skills catalog updated** — added red-teaming category and optional skills listing ([#3745](https://github.com/NousResearch/hermes-agent/pull/3745))
- **Feishu docs MDX fix** — escape angle-bracket URLs that break Docusaurus build ([#3902](https://github.com/NousResearch/hermes-agent/pull/3902))
---
## 👥 Contributors
### Core
- **@teknium1** — 90 PRs across all subsystems
### Community Contributors
- **@kshitijk4poor** — 3 PRs: Signal phone number fix ([#3670](https://github.com/NousResearch/hermes-agent/pull/3670)), parallel-cli to optional-skills ([#3673](https://github.com/NousResearch/hermes-agent/pull/3673)), status bar wrapping fix ([#3883](https://github.com/NousResearch/hermes-agent/pull/3883))
- **@winglian** — 1 PR: Plugin message injection interface ([#3778](https://github.com/NousResearch/hermes-agent/pull/3778))
- **@binhnt92** — 1 PR: Audio download retry logic ([#3401](https://github.com/NousResearch/hermes-agent/pull/3401))
- **@0xbyt4** — 1 PR: OpenClaw migration model config fix ([#3924](https://github.com/NousResearch/hermes-agent/pull/3924))
### Issues Resolved from Community
@Material-Scientist ([#850](https://github.com/NousResearch/hermes-agent/issues/850)), @hanxu98121 ([#1734](https://github.com/NousResearch/hermes-agent/issues/1734)), @penwyp ([#1788](https://github.com/NousResearch/hermes-agent/issues/1788)), @dan-and ([#1945](https://github.com/NousResearch/hermes-agent/issues/1945)), @AdrianScott ([#1963](https://github.com/NousResearch/hermes-agent/issues/1963)), @clawdbot47 ([#3229](https://github.com/NousResearch/hermes-agent/issues/3229)), @alanfwilliams ([#3404](https://github.com/NousResearch/hermes-agent/issues/3404)), @kentimsit ([#3433](https://github.com/NousResearch/hermes-agent/issues/3433)), @hayka-pacha ([#3534](https://github.com/NousResearch/hermes-agent/issues/3534)), @primmer ([#3595](https://github.com/NousResearch/hermes-agent/issues/3595)), @dagelf ([#3609](https://github.com/NousResearch/hermes-agent/issues/3609)), @HenkDz ([#3685](https://github.com/NousResearch/hermes-agent/issues/3685)), @tmdgusya ([#3729](https://github.com/NousResearch/hermes-agent/issues/3729)), @TypQxQ ([#3753](https://github.com/NousResearch/hermes-agent/issues/3753)), @acsezen ([#3765](https://github.com/NousResearch/hermes-agent/issues/3765))
---
**Full Changelog**: [v2026.3.28...v2026.3.30](https://github.com/NousResearch/hermes-agent/compare/v2026.3.28...v2026.3.30)
+80 -5
View File
@@ -162,6 +162,36 @@ def _is_oauth_token(key: str) -> bool:
return True
def _is_third_party_anthropic_endpoint(base_url: str | None) -> bool:
"""Return True for non-Anthropic endpoints using the Anthropic Messages API.
Third-party proxies (Azure AI Foundry, AWS Bedrock, self-hosted) authenticate
with their own API keys via x-api-key, not Anthropic OAuth tokens. OAuth
detection should be skipped for these endpoints.
"""
if not base_url:
return False # No base_url = direct Anthropic API
normalized = base_url.rstrip("/").lower()
if "anthropic.com" in normalized:
return False # Direct Anthropic API — OAuth applies
return True # Any other endpoint is a third-party proxy
def _requires_bearer_auth(base_url: str | None) -> bool:
"""Return True for Anthropic-compatible providers that require Bearer auth.
Some third-party /anthropic endpoints implement Anthropic's Messages API but
require Authorization: Bearer instead of Anthropic's native x-api-key header.
MiniMax's global and China Anthropic-compatible endpoints follow this pattern.
"""
if not base_url:
return False
normalized = base_url.rstrip("/").lower()
return normalized.startswith("https://api.minimax.io/anthropic") or normalized.startswith(
"https://api.minimaxi.com/anthropic"
)
def build_anthropic_client(api_key: str, base_url: str = None):
"""Create an Anthropic client, auto-detecting setup-tokens vs API keys.
@@ -180,7 +210,25 @@ def build_anthropic_client(api_key: str, base_url: str = None):
if base_url:
kwargs["base_url"] = base_url
if _is_oauth_token(api_key):
if _requires_bearer_auth(base_url):
# Some Anthropic-compatible providers (e.g. MiniMax) expect the API key in
# Authorization: Bearer even for regular API keys. Route those endpoints
# through auth_token so the SDK sends Bearer auth instead of x-api-key.
# Check this before OAuth token shape detection because MiniMax secrets do
# not use Anthropic's sk-ant-api prefix and would otherwise be misread as
# Anthropic OAuth/setup tokens.
kwargs["auth_token"] = api_key
if _COMMON_BETAS:
kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
elif _is_third_party_anthropic_endpoint(base_url):
# Third-party proxies (Azure AI Foundry, AWS Bedrock, etc.) use their
# own API keys with x-api-key auth. Skip OAuth detection — their keys
# don't follow Anthropic's sk-ant-* prefix convention and would be
# misclassified as OAuth tokens.
kwargs["api_key"] = api_key
if _COMMON_BETAS:
kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
elif _is_oauth_token(api_key):
# OAuth access token / setup-token → Bearer auth + Claude Code identity.
# Anthropic routes OAuth requests based on user-agent and headers;
# without Claude Code's fingerprint, requests get intermittent 500s.
@@ -313,7 +361,14 @@ def _refresh_oauth_token(creds: Dict[str, Any]) -> Optional[str]:
if new_access:
new_expires_ms = int(time.time() * 1000) + (expires_in * 1000)
_write_claude_code_credentials(new_access, new_refresh, new_expires_ms)
# Parse scopes from refresh response — Claude Code >=2.1.81
# requires a "scopes" field in the credential store and checks
# for "user:inference" before accepting the token as valid.
scope_str = result.get("scope", "")
scopes = scope_str.split() if scope_str else None
_write_claude_code_credentials(
new_access, new_refresh, new_expires_ms, scopes=scopes,
)
logger.debug("Refreshed Claude Code OAuth token via %s", endpoint)
return new_access
except Exception as e:
@@ -322,8 +377,20 @@ def _refresh_oauth_token(creds: Dict[str, Any]) -> Optional[str]:
return None
def _write_claude_code_credentials(access_token: str, refresh_token: str, expires_at_ms: int) -> None:
"""Write refreshed credentials back to ~/.claude/.credentials.json."""
def _write_claude_code_credentials(
access_token: str,
refresh_token: str,
expires_at_ms: int,
*,
scopes: Optional[list] = None,
) -> None:
"""Write refreshed credentials back to ~/.claude/.credentials.json.
The optional *scopes* list (e.g. ``["user:inference", "user:profile", ...]``)
is persisted so that Claude Code's own auth check recognises the credential
as valid. Claude Code >=2.1.81 gates on the presence of ``"user:inference"``
in the stored scopes before it will use the token.
"""
cred_path = Path.home() / ".claude" / ".credentials.json"
try:
# Read existing file to preserve other fields
@@ -331,11 +398,19 @@ def _write_claude_code_credentials(access_token: str, refresh_token: str, expire
if cred_path.exists():
existing = json.loads(cred_path.read_text(encoding="utf-8"))
existing["claudeAiOauth"] = {
oauth_data: Dict[str, Any] = {
"accessToken": access_token,
"refreshToken": refresh_token,
"expiresAt": expires_at_ms,
}
if scopes is not None:
oauth_data["scopes"] = scopes
elif "claudeAiOauth" in existing and "scopes" in existing["claudeAiOauth"]:
# Preserve previously-stored scopes when the refresh response
# does not include a scope field.
oauth_data["scopes"] = existing["claudeAiOauth"]["scopes"]
existing["claudeAiOauth"] = oauth_data
cred_path.parent.mkdir(parents=True, exist_ok=True)
cred_path.write_text(json.dumps(existing, indent=2), encoding="utf-8")
+45 -15
View File
@@ -7,7 +7,7 @@ the best available backend without duplicating fallback logic.
Resolution order for text tasks (auto mode):
1. OpenRouter (OPENROUTER_API_KEY)
2. Nous Portal (~/.hermes/auth.json active provider)
3. Custom endpoint (OPENAI_BASE_URL + OPENAI_API_KEY)
3. Custom endpoint (config.yaml model.base_url + OPENAI_API_KEY)
4. Codex OAuth (Responses API via chatgpt.com with gpt-5.3-codex,
wrapped to look like a chat.completions client)
5. Native Anthropic
@@ -584,15 +584,11 @@ def _try_nous() -> Tuple[Optional[OpenAI], Optional[str]]:
def _read_main_model() -> str:
"""Read the user's configured main model from config/env.
"""Read the user's configured main model from config.yaml.
Falls back through HERMES_MODEL → LLM_MODEL → config.yaml model.default
so the auxiliary client can use the same model as the main agent when no
dedicated auxiliary model is available.
config.yaml model.default is the single source of truth for the active
model. Environment variables are no longer consulted.
"""
from_env = os.getenv("OPENAI_MODEL") or os.getenv("HERMES_MODEL") or os.getenv("LLM_MODEL")
if from_env:
return from_env.strip()
try:
from hermes_cli.config import load_config
cfg = load_config()
@@ -627,8 +623,6 @@ def _resolve_custom_runtime() -> Tuple[Optional[str], Optional[str]]:
custom_key = runtime.get("api_key")
if not isinstance(custom_base, str) or not custom_base.strip():
return None, None
if not isinstance(custom_key, str) or not custom_key.strip():
return None, None
custom_base = custom_base.strip().rstrip("/")
if "openrouter.ai" in custom_base.lower():
@@ -636,6 +630,13 @@ def _resolve_custom_runtime() -> Tuple[Optional[str], Optional[str]]:
# configured. Treat that as "no custom endpoint" for auxiliary routing.
return None, None
# Local servers (Ollama, llama.cpp, vLLM, LM Studio) don't require auth.
# Use a placeholder key — the OpenAI SDK requires a non-empty string but
# local servers ignore the Authorization header. Same fix as cli.py
# _ensure_runtime_credentials() (PR #2556).
if not isinstance(custom_key, str) or not custom_key.strip():
custom_key = "no-key-required"
return custom_base, custom_key.strip()
@@ -737,16 +738,37 @@ def _resolve_forced_provider(forced: str) -> Tuple[Optional[OpenAI], Optional[st
return None, None
_AUTO_PROVIDER_LABELS = {
"_try_openrouter": "openrouter",
"_try_nous": "nous",
"_try_custom_endpoint": "local/custom",
"_try_codex": "openai-codex",
"_resolve_api_key_provider": "api-key",
}
def _resolve_auto() -> Tuple[Optional[OpenAI], Optional[str]]:
"""Full auto-detection chain: OpenRouter → Nous → custom → Codex → API-key → None."""
global auxiliary_is_nous
auxiliary_is_nous = False # Reset — _try_nous() will set True if it wins
tried = []
for try_fn in (_try_openrouter, _try_nous, _try_custom_endpoint,
_try_codex, _resolve_api_key_provider):
fn_name = getattr(try_fn, "__name__", "unknown")
label = _AUTO_PROVIDER_LABELS.get(fn_name, fn_name)
client, model = try_fn()
if client is not None:
if tried:
logger.info("Auxiliary auto-detect: using %s (%s) — skipped: %s",
label, model or "default", ", ".join(tried))
else:
logger.info("Auxiliary auto-detect: using %s (%s)", label, model or "default")
return client, model
logger.debug("Auxiliary client: none available")
tried.append(label)
logger.warning("Auxiliary auto-detect: no provider available (tried: %s). "
"Compression, summarization, and memory flush will not work. "
"Set OPENROUTER_API_KEY or configure a local model in config.yaml.",
", ".join(tried))
return None, None
@@ -897,11 +919,12 @@ def resolve_provider_client(
custom_key = (
(explicit_api_key or "").strip()
or os.getenv("OPENAI_API_KEY", "").strip()
or "no-key-required" # local servers don't need auth
)
if not custom_base or not custom_key:
if not custom_base:
logger.warning(
"resolve_provider_client: explicit custom endpoint requested "
"but no API key was found (set explicit_api_key or OPENAI_API_KEY)"
"but base_url is empty"
)
return None, None
final_model = model or _read_main_model() or "gpt-4o-mini"
@@ -1612,8 +1635,8 @@ def call_llm(
)
# For auto/custom, fall back to OpenRouter
if not resolved_base_url:
logger.warning("Provider %s unavailable, falling back to openrouter",
resolved_provider)
logger.info("Auxiliary %s: provider %s unavailable, falling back to openrouter",
task or "call", resolved_provider)
client, final_model = _get_cached_client(
"openrouter", resolved_model or _OPENROUTER_MODEL)
if client is None:
@@ -1623,6 +1646,13 @@ def call_llm(
effective_timeout = timeout if timeout is not None else _get_task_timeout(task)
# Log what we're about to do — makes auxiliary operations visible
_base_info = str(getattr(client, "base_url", resolved_base_url) or "")
if task:
logger.info("Auxiliary %s: using %s (%s)%s",
task, resolved_provider or "auto", final_model or "default",
f" at {_base_info}" if _base_info and "openrouter" not in _base_info else "")
kwargs = _build_call_kwargs(
resolved_provider, final_model, messages,
temperature=temperature, max_tokens=max_tokens,
+30 -3
View File
@@ -17,6 +17,23 @@ _RESET = "\033[0m"
logger = logging.getLogger(__name__)
# =========================================================================
# Configurable tool preview length (0 = no limit)
# Set once at startup by CLI or gateway from display.tool_preview_length config.
# =========================================================================
_tool_preview_max_len: int = 0 # 0 = unlimited
def set_tool_preview_max_len(n: int) -> None:
"""Set the global max length for tool call previews. 0 = no limit."""
global _tool_preview_max_len
_tool_preview_max_len = max(int(n), 0) if n else 0
def get_tool_preview_max_len() -> int:
"""Return the configured max preview length (0 = unlimited)."""
return _tool_preview_max_len
# =========================================================================
# Skin-aware helpers (lazy import to avoid circular deps)
@@ -94,8 +111,14 @@ def _oneline(text: str) -> str:
return " ".join(text.split())
def build_tool_preview(tool_name: str, args: dict, max_len: int = 40) -> str | None:
"""Build a short preview of a tool call's primary argument for display."""
def build_tool_preview(tool_name: str, args: dict, max_len: int | None = None) -> str | None:
"""Build a short preview of a tool call's primary argument for display.
*max_len* controls truncation. ``None`` (default) defers to the global
``_tool_preview_max_len`` set via config; ``0`` means unlimited.
"""
if max_len is None:
max_len = _tool_preview_max_len
if not args:
return None
primary_args = {
@@ -190,7 +213,7 @@ def build_tool_preview(tool_name: str, args: dict, max_len: int = 40) -> str | N
preview = _oneline(str(value))
if not preview:
return None
if len(preview) > max_len:
if max_len > 0 and len(preview) > max_len:
preview = preview[:max_len - 3] + "..."
return preview
@@ -484,10 +507,14 @@ def get_cute_tool_message(
def _trunc(s, n=40):
s = str(s)
if _tool_preview_max_len == 0:
return s # no limit
return (s[:n-3] + "...") if len(s) > n else s
def _path(p, n=35):
p = str(p)
if _tool_preview_max_len == 0:
return p # no limit
return ("..." + p[-(n-3):]) if len(p) > n else p
def _wrap(line: str) -> str:
+2
View File
@@ -171,10 +171,12 @@ _URL_TO_PROVIDER: Dict[str, str] = {
"dashscope.aliyuncs.com": "alibaba",
"dashscope-intl.aliyuncs.com": "alibaba",
"openrouter.ai": "openrouter",
"generativelanguage.googleapis.com": "google",
"inference-api.nousresearch.com": "nous",
"api.deepseek.com": "deepseek",
"api.githubcopilot.com": "copilot",
"models.github.ai": "copilot",
"api.fireworks.ai": "fireworks",
}
+1
View File
@@ -43,6 +43,7 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
"opencode-zen": "opencode",
"opencode-go": "opencode-go",
"kilocode": "kilo",
"fireworks": "fireworks-ai",
}
+3
View File
@@ -37,6 +37,9 @@ _PREFIX_PATTERNS = [
r"dop_v1_[A-Za-z0-9]{10,}", # DigitalOcean PAT
r"doo_v1_[A-Za-z0-9]{10,}", # DigitalOcean OAuth
r"am_[A-Za-z0-9_-]{10,}", # AgentMail API key
r"sk_[A-Za-z0-9_]{10,}", # ElevenLabs TTS key (sk_ underscore, not sk- dash)
r"tvly-[A-Za-z0-9]{10,}", # Tavily search API key
r"exa_[A-Za-z0-9]{10,}", # Exa search API key
]
# ENV assignment patterns: KEY=value where KEY contains a secret-like name
+26 -8
View File
@@ -11,14 +11,29 @@ model:
default: "anthropic/claude-opus-4.6"
# Inference provider selection:
# "auto" - Use Nous Portal if logged in, otherwise OpenRouter/env vars (default)
# "nous-api" - Use Nous Portal via API key (requires: NOUS_API_KEY)
# "openrouter" - Always use OpenRouter API key from OPENROUTER_API_KEY
# "nous" - Always use Nous Portal (requires: hermes login)
# "zai" - Use z.ai / ZhipuAI GLM models (requires: GLM_API_KEY)
# "kimi-coding"- Use Kimi / Moonshot AI models (requires: KIMI_API_KEY)
# "minimax" - Use MiniMax global endpoint (requires: MINIMAX_API_KEY)
# "minimax-cn" - Use MiniMax China endpoint (requires: MINIMAX_CN_API_KEY)
# "auto" - Auto-detect from credentials (default)
# "openrouter" - OpenRouter (requires: OPENROUTER_API_KEY or OPENAI_API_KEY)
# "nous" - Nous Portal OAuth (requires: hermes login)
# "nous-api" - Nous Portal API key (requires: NOUS_API_KEY)
# "anthropic" - Direct Anthropic API (requires: ANTHROPIC_API_KEY)
# "openai-codex" - OpenAI Codex (requires: hermes login --provider openai-codex)
# "copilot" - GitHub Copilot / GitHub Models (requires: GITHUB_TOKEN)
# "zai" - z.ai / ZhipuAI GLM (requires: GLM_API_KEY)
# "kimi-coding" - Kimi / Moonshot AI (requires: KIMI_API_KEY)
# "minimax" - MiniMax global (requires: MINIMAX_API_KEY)
# "minimax-cn" - MiniMax China (requires: MINIMAX_CN_API_KEY)
# "huggingface" - Hugging Face Inference (requires: HF_TOKEN)
# "kilocode" - KiloCode gateway (requires: KILOCODE_API_KEY)
# "ai-gateway" - Vercel AI Gateway (requires: AI_GATEWAY_API_KEY)
#
# Local servers (LM Studio, Ollama, vLLM, llama.cpp):
# "custom" - Any OpenAI-compatible endpoint. Set base_url below.
# Aliases: "lmstudio", "ollama", "vllm", "llamacpp" all map to "custom".
# Example for LM Studio:
# provider: "lmstudio"
# base_url: "http://localhost:1234/v1"
# No API key needed — local servers typically ignore auth.
#
# Can also be overridden with --provider flag or HERMES_INFERENCE_PROVIDER env var.
provider: "auto"
@@ -309,6 +324,9 @@ compression:
# vision:
# provider: "auto"
# model: "" # e.g. "google/gemini-2.5-flash", "openai/gpt-4o"
# timeout: 30 # LLM API call timeout (seconds)
# download_timeout: 30 # Image HTTP download timeout (seconds)
# # Increase for slow connections or self-hosted image servers
#
# # Web page scraping / summarization + browser page text extraction
# web_extract:
+306 -69
View File
@@ -449,6 +449,14 @@ try:
except Exception:
pass # Skin engine is optional — default skin used if unavailable
# Initialize tool preview length from config
try:
from agent.display import set_tool_preview_max_len
_tpl = CLI_CONFIG.get("display", {}).get("tool_preview_length", 0)
set_tool_preview_max_len(int(_tpl) if _tpl else 0)
except Exception:
pass
# Neuter AsyncHttpxClientWrapper.__del__ before any AsyncOpenAI clients are
# created. The SDK's __del__ schedules aclose() on asyncio.get_running_loop()
# which, during CLI idle time, finds prompt_toolkit's event loop and tries to
@@ -1079,10 +1087,10 @@ class HermesCLI:
# env vars would stomp each other.
_model_config = CLI_CONFIG.get("model", {})
_config_model = (_model_config.get("default") or _model_config.get("model") or "") if isinstance(_model_config, dict) else (_model_config or "")
_FALLBACK_MODEL = "anthropic/claude-opus-4.6"
self.model = model or _config_model or _FALLBACK_MODEL
# Auto-detect model from local server if still on fallback
if self.model == _FALLBACK_MODEL:
_DEFAULT_CONFIG_MODEL = "anthropic/claude-opus-4.6"
self.model = model or _config_model or _DEFAULT_CONFIG_MODEL
# Auto-detect model from local server if still on default
if self.model == _DEFAULT_CONFIG_MODEL:
_base_url = (_model_config.get("base_url") or "") if isinstance(_model_config, dict) else ""
if "localhost" in _base_url or "127.0.0.1" in _base_url:
from hermes_cli.runtime_provider import _auto_detect_local_model
@@ -1096,7 +1104,7 @@ class HermesCLI:
# explicit choice — the user just never changed it. But a config model
# like "gpt-5.3-codex" IS explicit and must be preserved.
self._model_is_default = not model and (
not _config_model or _config_model == _FALLBACK_MODEL
not _config_model or _config_model == _DEFAULT_CONFIG_MODEL
)
self._explicit_api_key = api_key
@@ -1116,9 +1124,9 @@ class HermesCLI:
self.acp_args: list[str] = []
self.base_url = (
base_url
or os.getenv("OPENAI_BASE_URL")
or os.getenv("OPENROUTER_BASE_URL", CLI_CONFIG["model"]["base_url"])
)
or CLI_CONFIG["model"].get("base_url", "")
or os.getenv("OPENROUTER_BASE_URL", "")
) or None
# Match key to resolved base_url: OpenRouter URL → prefer OPENROUTER_API_KEY,
# custom endpoint → prefer OPENAI_API_KEY (issue #560).
# Note: _ensure_runtime_credentials() re-resolves this before first use.
@@ -1347,6 +1355,49 @@ class HermesCLI:
return snapshot
@staticmethod
def _status_bar_display_width(text: str) -> int:
"""Return terminal cell width for status-bar text.
len() is not enough for prompt_toolkit layout decisions because some
glyphs can render wider than one Python codepoint. Keeping the status
bar within the real display width prevents it from wrapping onto a
second line and leaving behind duplicate rows.
"""
try:
from prompt_toolkit.utils import get_cwidth
return get_cwidth(text or "")
except Exception:
return len(text or "")
@classmethod
def _trim_status_bar_text(cls, text: str, max_width: int) -> str:
"""Trim status-bar text to a single terminal row."""
if max_width <= 0:
return ""
try:
from prompt_toolkit.utils import get_cwidth
except Exception:
get_cwidth = None
if cls._status_bar_display_width(text) <= max_width:
return text
ellipsis = "..."
ellipsis_width = cls._status_bar_display_width(ellipsis)
if max_width <= ellipsis_width:
return ellipsis[:max_width]
out = []
width = 0
for ch in text:
ch_width = get_cwidth(ch) if get_cwidth else len(ch)
if width + ch_width + ellipsis_width > max_width:
break
out.append(ch)
width += ch_width
return "".join(out).rstrip() + ellipsis
def _build_status_bar_text(self, width: Optional[int] = None) -> str:
try:
snapshot = self._get_status_bar_snapshot()
@@ -1361,11 +1412,12 @@ class HermesCLI:
duration_label = snapshot["duration"]
if width < 52:
return f"{snapshot['model_short']} · {duration_label}"
text = f"{snapshot['model_short']} · {duration_label}"
return self._trim_status_bar_text(text, width)
if width < 76:
parts = [f"{snapshot['model_short']}", percent_label]
parts.append(duration_label)
return " · ".join(parts)
return self._trim_status_bar_text(" · ".join(parts), width)
if snapshot["context_length"]:
ctx_total = _format_context_length(snapshot["context_length"])
@@ -1376,7 +1428,7 @@ class HermesCLI:
parts = [f"{snapshot['model_short']}", context_label, percent_label]
parts.append(duration_label)
return "".join(parts)
return self._trim_status_bar_text("".join(parts), width)
except Exception:
return f"{self.model if getattr(self, 'model', None) else 'Hermes'}"
@@ -1398,53 +1450,54 @@ class HermesCLI:
duration_label = snapshot["duration"]
if width < 52:
return [
("class:status-bar", ""),
("class:status-bar-strong", snapshot["model_short"]),
("class:status-bar-dim", " · "),
("class:status-bar-dim", duration_label),
("class:status-bar", " "),
]
percent = snapshot["context_percent"]
percent_label = f"{percent}%" if percent is not None else "--"
if width < 76:
frags = [
("class:status-bar", ""),
("class:status-bar-strong", snapshot["model_short"]),
("class:status-bar-dim", " · "),
(self._status_bar_context_style(percent), percent_label),
]
frags.extend([
("class:status-bar-dim", " · "),
("class:status-bar-dim", duration_label),
("class:status-bar", " "),
])
return frags
if snapshot["context_length"]:
ctx_total = _format_context_length(snapshot["context_length"])
ctx_used = format_token_count_compact(snapshot["context_tokens"])
context_label = f"{ctx_used}/{ctx_total}"
]
else:
context_label = "ctx --"
percent = snapshot["context_percent"]
percent_label = f"{percent}%" if percent is not None else "--"
if width < 76:
frags = [
("class:status-bar", ""),
("class:status-bar-strong", snapshot["model_short"]),
("class:status-bar-dim", " · "),
(self._status_bar_context_style(percent), percent_label),
("class:status-bar-dim", " · "),
("class:status-bar-dim", duration_label),
("class:status-bar", " "),
]
else:
if snapshot["context_length"]:
ctx_total = _format_context_length(snapshot["context_length"])
ctx_used = format_token_count_compact(snapshot["context_tokens"])
context_label = f"{ctx_used}/{ctx_total}"
else:
context_label = "ctx --"
bar_style = self._status_bar_context_style(percent)
frags = [
("class:status-bar", ""),
("class:status-bar-strong", snapshot["model_short"]),
("class:status-bar-dim", ""),
("class:status-bar-dim", context_label),
("class:status-bar-dim", ""),
(bar_style, self._build_context_bar(percent)),
("class:status-bar-dim", " "),
(bar_style, percent_label),
]
frags.extend([
("class:status-bar-dim", " "),
("class:status-bar-dim", duration_label),
("class:status-bar", " "),
])
bar_style = self._status_bar_context_style(percent)
frags = [
("class:status-bar", ""),
("class:status-bar-strong", snapshot["model_short"]),
("class:status-bar-dim", ""),
("class:status-bar-dim", context_label),
("class:status-bar-dim", ""),
(bar_style, self._build_context_bar(percent)),
("class:status-bar-dim", " "),
(bar_style, percent_label),
("class:status-bar-dim", ""),
("class:status-bar-dim", duration_label),
("class:status-bar", " "),
]
total_width = sum(self._status_bar_display_width(text) for _, text in frags)
if total_width > width:
plain_text = "".join(text for _, text in frags)
trimmed = self._trim_status_bar_text(plain_text, width)
return [("class:status-bar", trimmed)]
return frags
except Exception:
return [("class:status-bar", f" {self._build_status_bar_text()} ")]
@@ -2736,22 +2789,12 @@ class HermesCLI:
print(f" MCP tool: /tools {subcommand} github:create_issue")
return
# Confirm session reset before applying
verb = "Disable" if subcommand == "disable" else "Enable"
# Apply the change directly — the user typing the command is implicit
# consent. Do NOT use input() here; it hangs inside prompt_toolkit's
# TUI event loop (known pitfall).
verb = "Disabling" if subcommand == "disable" else "Enabling"
label = ", ".join(names)
_cprint(f"{_GOLD}{verb} {label}?{_RST}")
_cprint(f"{_DIM}This will save to config and reset your session so the "
f"change takes effect cleanly.{_RST}")
try:
answer = input(" Continue? [y/N] ").strip().lower()
except (EOFError, KeyboardInterrupt):
print()
_cprint(f"{_DIM}Cancelled.{_RST}")
return
if answer not in ("y", "yes"):
_cprint(f"{_DIM}Cancelled.{_RST}")
return
_cprint(f"{_GOLD}{verb} {label}...{_RST}")
tools_disable_enable_command(
Namespace(tools_action=subcommand, names=names, platform="cli"))
@@ -2794,6 +2837,28 @@ class HermesCLI:
print(" Example: python cli.py --toolsets web,terminal")
print()
def _handle_profile_command(self):
"""Display active profile name and home directory."""
from hermes_constants import get_hermes_home, display_hermes_home
home = get_hermes_home()
display = display_hermes_home()
profiles_parent = Path.home() / ".hermes" / "profiles"
try:
rel = home.relative_to(profiles_parent)
profile_name = str(rel).split("/")[0]
except ValueError:
profile_name = None
print()
if profile_name:
print(f" Profile: {profile_name}")
else:
print(" Profile: default")
print(f" Home: {display}")
print()
def show_config(self):
"""Display current configuration with kawaii ASCII art."""
# Get terminal config from environment (which was set from cli-config.yaml)
@@ -3174,7 +3239,7 @@ class HermesCLI:
print(f" {mid}{current_marker}")
elif p["id"] == "custom":
from hermes_cli.models import _get_custom_base_url
custom_url = _get_custom_base_url() or os.getenv("OPENAI_BASE_URL", "")
custom_url = _get_custom_base_url()
if custom_url:
print(f" endpoint: {custom_url}")
if is_active:
@@ -3636,6 +3701,8 @@ class HermesCLI:
return False
elif canonical == "help":
self.show_help()
elif canonical == "profile":
self._handle_profile_command()
elif canonical == "tools":
self._handle_tools_command(cmd_original)
elif canonical == "toolsets":
@@ -3793,6 +3860,8 @@ class HermesCLI:
self.console.print(f" Status bar {state}")
elif canonical == "verbose":
self._toggle_verbose()
elif canonical == "yolo":
self._toggle_yolo()
elif canonical == "reasoning":
self._handle_reasoning_command(cmd_original)
elif canonical == "compress":
@@ -3835,6 +3904,8 @@ class HermesCLI:
self._handle_stop_command()
elif canonical == "background":
self._handle_background_command(cmd_original)
elif canonical == "btw":
self._handle_btw_command(cmd_original)
elif canonical == "queue":
# Extract prompt after "/queue " or "/q "
parts = cmd_original.split(None, 1)
@@ -4121,6 +4192,121 @@ class HermesCLI:
self._background_tasks[task_id] = thread
thread.start()
def _handle_btw_command(self, cmd: str):
"""Handle /btw <question> — ephemeral side question using session context.
Snapshots the current conversation history, spawns a no-tools agent in
a background thread, and prints the answer without persisting anything
to the main session.
"""
parts = cmd.strip().split(maxsplit=1)
if len(parts) < 2 or not parts[1].strip():
_cprint(" Usage: /btw <question>")
_cprint(" Example: /btw what module owns session title sanitization?")
_cprint(" Answers using session context. No tools, not persisted.")
return
question = parts[1].strip()
task_id = f"btw_{datetime.now().strftime('%H%M%S')}_{uuid.uuid4().hex[:6]}"
if not self._ensure_runtime_credentials():
_cprint(" (>_<) Cannot start /btw: no valid credentials.")
return
turn_route = self._resolve_turn_agent_config(question)
history_snapshot = list(self.conversation_history)
preview = question[:60] + ("..." if len(question) > 60 else "")
_cprint(f' 💬 /btw: "{preview}"')
def run_btw():
try:
btw_agent = AIAgent(
model=turn_route["model"],
api_key=turn_route["runtime"].get("api_key"),
base_url=turn_route["runtime"].get("base_url"),
provider=turn_route["runtime"].get("provider"),
api_mode=turn_route["runtime"].get("api_mode"),
acp_command=turn_route["runtime"].get("command"),
acp_args=turn_route["runtime"].get("args"),
max_iterations=8,
enabled_toolsets=[],
quiet_mode=True,
verbose_logging=False,
session_id=task_id,
platform="cli",
reasoning_config=self.reasoning_config,
providers_allowed=self._providers_only,
providers_ignored=self._providers_ignore,
providers_order=self._providers_order,
provider_sort=self._provider_sort,
provider_require_parameters=self._provider_require_params,
provider_data_collection=self._provider_data_collection,
fallback_model=self._fallback_model,
session_db=None,
skip_memory=True,
skip_context_files=True,
persist_session=False,
)
btw_prompt = (
"[Ephemeral /btw side question. Answer using the conversation "
"context. No tools available. Be direct and concise.]\n\n"
+ question
)
result = btw_agent.run_conversation(
user_message=btw_prompt,
conversation_history=history_snapshot,
task_id=task_id,
sync_honcho=False,
)
response = (result.get("final_response") or "") if result else ""
if not response and result and result.get("error"):
response = f"Error: {result['error']}"
# TUI refresh before printing
if self._app:
self._app.invalidate()
time.sleep(0.05)
print()
if response:
try:
from hermes_cli.skin_engine import get_active_skin
_skin = get_active_skin()
_resp_color = _skin.get_color("response_border", "#4F6D4A")
except Exception:
_resp_color = "#4F6D4A"
ChatConsole().print(Panel(
_rich_text_from_ansi(response),
title=f"[{_resp_color} bold]⚕ /btw[/]",
title_align="left",
border_style=_resp_color,
box=rich_box.HORIZONTALS,
padding=(1, 2),
))
else:
_cprint(" 💬 /btw: (no response)")
if self.bell_on_complete:
sys.stdout.write("\a")
sys.stdout.flush()
except Exception as e:
if self._app:
self._app.invalidate()
time.sleep(0.05)
print()
_cprint(f" ❌ /btw failed: {e}")
finally:
if self._app:
self._invalidate(min_interval=0)
thread = threading.Thread(target=run_btw, daemon=True, name=f"btw-{task_id}")
thread.start()
@staticmethod
def _try_launch_chrome_debug(port: int, system: str) -> bool:
"""Try to launch Chrome/Chromium with remote debugging enabled.
@@ -4391,6 +4577,17 @@ class HermesCLI:
}
_cprint(labels.get(self.tool_progress_mode, ""))
def _toggle_yolo(self):
"""Toggle YOLO mode — skip all dangerous command approval prompts."""
import os
current = bool(os.environ.get("HERMES_YOLO_MODE"))
if current:
os.environ.pop("HERMES_YOLO_MODE", None)
self.console.print(" ⚠ YOLO mode [bold red]OFF[/] — dangerous commands will require approval.")
else:
os.environ["HERMES_YOLO_MODE"] = "1"
self.console.print(" ⚡ YOLO mode [bold green]ON[/] — all commands auto-approved. Use with caution.")
def _handle_reasoning_command(self, cmd: str):
"""Handle /reasoning — manage effort level and display toggle.
@@ -4782,8 +4979,10 @@ class HermesCLI:
from agent.display import get_tool_emoji
emoji = get_tool_emoji(function_name)
label = preview or function_name
if len(label) > 50:
label = label[:47] + "..."
from agent.display import get_tool_preview_max_len
_pl = get_tool_preview_max_len()
if _pl > 0 and len(label) > _pl:
label = label[:_pl - 3] + "..."
self._spinner_text = f"{emoji} {label}"
self._invalidate()
@@ -5515,6 +5714,8 @@ class HermesCLI:
self.agent = None
# Initialize agent if needed
if self.agent is None:
_cprint(f"{_DIM}Initializing agent...{_RST}")
if not self._init_agent(
model_override=turn_route["model"],
runtime_override=turn_route["runtime"],
@@ -6155,6 +6356,11 @@ class HermesCLI:
self._interrupt_queue = queue.Queue() # For messages typed while agent is running
self._should_exit = False
self._last_ctrl_c_time = 0 # Track double Ctrl+C for force exit
# Give plugin manager a CLI reference so plugins can inject messages
from hermes_cli.plugins import get_plugin_manager
get_plugin_manager()._cli_ref = self
# Config file watcher — detect mcp_servers changes and auto-reload
from hermes_cli.config import get_config_path as _get_config_path
_cfg_path = _get_config_path()
@@ -7358,6 +7564,20 @@ class HermesCLI:
# Register atexit cleanup so resources are freed even on unexpected exit
atexit.register(_run_cleanup)
# Register signal handlers for graceful shutdown on SSH disconnect / SIGTERM
def _signal_handler(signum, frame):
"""Handle SIGHUP/SIGTERM by triggering graceful cleanup."""
logger.debug("Received signal %s, triggering graceful shutdown", signum)
raise KeyboardInterrupt()
try:
import signal as _signal
_signal.signal(_signal.SIGTERM, _signal_handler)
if hasattr(_signal, 'SIGHUP'):
_signal.signal(_signal.SIGHUP, _signal_handler)
except Exception:
pass # Signal handlers may fail in restricted environments
# Install a custom asyncio exception handler that suppresses the
# "Event loop is closed" RuntimeError from httpx transport cleanup.
# This is defense-in-depth — the primary fix is neuter_async_httpx_del
@@ -7381,7 +7601,7 @@ class HermesCLI:
except Exception:
pass
app.run()
except (EOFError, KeyboardInterrupt):
except (EOFError, KeyboardInterrupt, BrokenPipeError):
pass
finally:
self._should_exit = True
@@ -7420,6 +7640,23 @@ class HermesCLI:
self._session_db.end_session(self.agent.session_id, "cli_close")
except (Exception, KeyboardInterrupt) as e:
logger.debug("Could not close session in DB: %s", e)
# Plugin hook: on_session_end — safety net for interrupted exits.
# run_conversation() already fires this per-turn on normal completion,
# so only fire here if the agent was mid-turn (_agent_running) when
# the exit occurred, meaning run_conversation's hook didn't fire.
if self.agent and getattr(self, '_agent_running', False):
try:
from hermes_cli.plugins import invoke_hook as _invoke_hook
_invoke_hook(
"on_session_end",
session_id=self.agent.session_id,
completed=False,
interrupted=True,
model=getattr(self.agent, 'model', None),
platform=getattr(self.agent, 'platform', None) or "cli",
)
except Exception:
pass
_run_cleanup()
self._print_exit_summary()
+25 -6
View File
@@ -87,6 +87,22 @@ def _resolve_delivery_target(job: dict) -> Optional[dict]:
chat_id, thread_id = rest.split(":", 1)
else:
chat_id, thread_id = rest, None
# Resolve human-friendly labels like "Alice (dm)" to real IDs.
# send_message(action="list") shows labels with display suffixes
# that aren't valid platform IDs (e.g. WhatsApp JIDs).
try:
from gateway.channel_directory import resolve_channel_name
target = chat_id
# Strip display suffix like " (dm)" or " (group)"
if target.endswith(")") and " (" in target:
target = target.rsplit(" (", 1)[0].strip()
resolved = resolve_channel_name(platform_name.lower(), target)
if resolved:
chat_id = resolved
except Exception:
pass
return {
"platform": platform_name,
"chat_id": chat_id,
@@ -146,6 +162,8 @@ def _deliver_result(job: dict, content: str) -> None:
"mattermost": Platform.MATTERMOST,
"homeassistant": Platform.HOMEASSISTANT,
"dingtalk": Platform.DINGTALK,
"feishu": Platform.FEISHU,
"wecom": Platform.WECOM,
"email": Platform.EMAIL,
"sms": Platform.SMS,
}
@@ -218,11 +236,12 @@ def _build_job_prompt(job: dict) -> str:
# Always prepend [SILENT] guidance so the cron agent can suppress
# delivery when it has nothing new or noteworthy to report.
silent_hint = (
"[SYSTEM: If you have nothing new or noteworthy to report, respond "
"with exactly \"[SILENT]\" (optionally followed by a brief internal "
"note). This suppresses delivery to the user while still saving "
"output locally. Only use [SILENT] when there are genuinely no "
"changes worth reporting.]\n\n"
"[SYSTEM: If you have a meaningful status report or findings, "
"send them — that is the whole point of this job. Only respond "
"with exactly \"[SILENT]\" (nothing else) when there is genuinely "
"nothing new to report. [SILENT] suppresses delivery to the user. "
"Never combine [SILENT] with content — either report your "
"findings normally, or say [SILENT] and nothing more.]\n\n"
)
prompt = silent_hint + prompt
if skills is None:
@@ -320,7 +339,7 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
if delivery_target.get("thread_id") is not None:
os.environ["HERMES_CRON_AUTO_DELIVER_THREAD_ID"] = str(delivery_target["thread_id"])
model = job.get("model") or os.getenv("HERMES_MODEL") or "anthropic/claude-opus-4.6"
model = job.get("model") or os.getenv("HERMES_MODEL") or ""
# Load config.yaml for model, reasoning, prefill, toolsets, provider routing
_cfg = {}
+86 -2
View File
@@ -27,9 +27,16 @@ def _coerce_bool(value: Any, default: bool = True) -> bool:
return default
if isinstance(value, bool):
return value
if isinstance(value, int):
return value != 0
if isinstance(value, str):
return value.strip().lower() in ("true", "1", "yes", "on")
return bool(value)
lowered = value.strip().lower()
if lowered in ("true", "1", "yes", "on"):
return True
if lowered in ("false", "0", "no", "off"):
return False
return default
return default
def _normalize_unauthorized_dm_behavior(value: Any, default: str = "pair") -> str:
@@ -57,6 +64,8 @@ class Platform(Enum):
DINGTALK = "dingtalk"
API_SERVER = "api_server"
WEBHOOK = "webhook"
FEISHU = "feishu"
WECOM = "wecom"
@dataclass
@@ -274,6 +283,12 @@ class GatewayConfig:
# Webhook uses enabled flag only (secrets are per-route)
elif platform == Platform.WEBHOOK:
connected.append(platform)
# Feishu uses extra dict for app credentials
elif platform == Platform.FEISHU and config.extra.get("app_id"):
connected.append(platform)
# WeCom uses extra dict for bot credentials
elif platform == Platform.WECOM and config.extra.get("bot_id"):
connected.append(platform)
return connected
def get_home_channel(self, platform: Platform) -> Optional[HomeChannel]:
@@ -507,6 +522,10 @@ def load_gateway_config() -> GatewayConfig:
)
if "reply_prefix" in platform_cfg:
bridged["reply_prefix"] = platform_cfg["reply_prefix"]
if "require_mention" in platform_cfg:
bridged["require_mention"] = platform_cfg["require_mention"]
if "mention_patterns" in platform_cfg:
bridged["mention_patterns"] = platform_cfg["mention_patterns"]
if not bridged:
continue
plat_data = platforms_data.setdefault(plat.value, {})
@@ -531,6 +550,22 @@ def load_gateway_config() -> GatewayConfig:
os.environ["DISCORD_FREE_RESPONSE_CHANNELS"] = str(frc)
if "auto_thread" in discord_cfg and not os.getenv("DISCORD_AUTO_THREAD"):
os.environ["DISCORD_AUTO_THREAD"] = str(discord_cfg["auto_thread"]).lower()
if "reactions" in discord_cfg and not os.getenv("DISCORD_REACTIONS"):
os.environ["DISCORD_REACTIONS"] = str(discord_cfg["reactions"]).lower()
# Telegram settings → env vars (env vars take precedence)
telegram_cfg = yaml_cfg.get("telegram", {})
if isinstance(telegram_cfg, dict):
if "require_mention" in telegram_cfg and not os.getenv("TELEGRAM_REQUIRE_MENTION"):
os.environ["TELEGRAM_REQUIRE_MENTION"] = str(telegram_cfg["require_mention"]).lower()
if "mention_patterns" in telegram_cfg and not os.getenv("TELEGRAM_MENTION_PATTERNS"):
import json as _json
os.environ["TELEGRAM_MENTION_PATTERNS"] = _json.dumps(telegram_cfg["mention_patterns"])
frc = telegram_cfg.get("free_response_chats")
if frc is not None and not os.getenv("TELEGRAM_FREE_RESPONSE_CHATS"):
if isinstance(frc, list):
frc = ",".join(str(v) for v in frc)
os.environ["TELEGRAM_FREE_RESPONSE_CHATS"] = str(frc)
except Exception as e:
logger.warning(
"Failed to process config.yaml — falling back to .env / gateway.json values. "
@@ -810,6 +845,55 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
if webhook_secret:
config.platforms[Platform.WEBHOOK].extra["secret"] = webhook_secret
# Feishu / Lark
feishu_app_id = os.getenv("FEISHU_APP_ID")
feishu_app_secret = os.getenv("FEISHU_APP_SECRET")
if feishu_app_id and feishu_app_secret:
if Platform.FEISHU not in config.platforms:
config.platforms[Platform.FEISHU] = PlatformConfig()
config.platforms[Platform.FEISHU].enabled = True
config.platforms[Platform.FEISHU].extra.update({
"app_id": feishu_app_id,
"app_secret": feishu_app_secret,
"domain": os.getenv("FEISHU_DOMAIN", "feishu"),
"connection_mode": os.getenv("FEISHU_CONNECTION_MODE", "websocket"),
})
feishu_encrypt_key = os.getenv("FEISHU_ENCRYPT_KEY", "")
if feishu_encrypt_key:
config.platforms[Platform.FEISHU].extra["encrypt_key"] = feishu_encrypt_key
feishu_verification_token = os.getenv("FEISHU_VERIFICATION_TOKEN", "")
if feishu_verification_token:
config.platforms[Platform.FEISHU].extra["verification_token"] = feishu_verification_token
feishu_home = os.getenv("FEISHU_HOME_CHANNEL")
if feishu_home:
config.platforms[Platform.FEISHU].home_channel = HomeChannel(
platform=Platform.FEISHU,
chat_id=feishu_home,
name=os.getenv("FEISHU_HOME_CHANNEL_NAME", "Home"),
)
# WeCom (Enterprise WeChat)
wecom_bot_id = os.getenv("WECOM_BOT_ID")
wecom_secret = os.getenv("WECOM_SECRET")
if wecom_bot_id and wecom_secret:
if Platform.WECOM not in config.platforms:
config.platforms[Platform.WECOM] = PlatformConfig()
config.platforms[Platform.WECOM].enabled = True
config.platforms[Platform.WECOM].extra.update({
"bot_id": wecom_bot_id,
"secret": wecom_secret,
})
wecom_ws_url = os.getenv("WECOM_WEBSOCKET_URL", "")
if wecom_ws_url:
config.platforms[Platform.WECOM].extra["websocket_url"] = wecom_ws_url
wecom_home = os.getenv("WECOM_HOME_CHANNEL")
if wecom_home:
config.platforms[Platform.WECOM].home_channel = HomeChannel(
platform=Platform.WECOM,
chat_id=wecom_home,
name=os.getenv("WECOM_HOME_CHANNEL_NAME", "Home"),
)
# Session settings
idle_minutes = os.getenv("SESSION_IDLE_MINUTES")
if idle_minutes:
+14
View File
@@ -380,6 +380,7 @@ class APIServerAdapter(BasePlatformAdapter):
ephemeral_system_prompt: Optional[str] = None,
session_id: Optional[str] = None,
stream_delta_callback=None,
tool_progress_callback=None,
) -> Any:
"""
Create an AIAgent instance using the gateway's runtime config.
@@ -412,6 +413,7 @@ class APIServerAdapter(BasePlatformAdapter):
session_id=session_id,
platform="api_server",
stream_delta_callback=stream_delta_callback,
tool_progress_callback=tool_progress_callback,
)
return agent
@@ -514,6 +516,15 @@ class APIServerAdapter(BasePlatformAdapter):
if delta is not None:
_stream_q.put(delta)
def _on_tool_progress(name, preview, args):
"""Inject tool progress into the SSE stream for Open WebUI."""
if name.startswith("_"):
return # Skip internal events (_thinking)
from agent.display import get_tool_emoji
emoji = get_tool_emoji(name)
label = preview or name
_stream_q.put(f"\n`{emoji} {label}`\n")
# Start agent in background. agent_ref is a mutable container
# so the SSE writer can interrupt the agent on client disconnect.
agent_ref = [None]
@@ -523,6 +534,7 @@ class APIServerAdapter(BasePlatformAdapter):
ephemeral_system_prompt=system_prompt,
session_id=session_id,
stream_delta_callback=_on_delta,
tool_progress_callback=_on_tool_progress,
agent_ref=agent_ref,
))
@@ -1194,6 +1206,7 @@ class APIServerAdapter(BasePlatformAdapter):
ephemeral_system_prompt: Optional[str] = None,
session_id: Optional[str] = None,
stream_delta_callback=None,
tool_progress_callback=None,
agent_ref: Optional[list] = None,
) -> tuple:
"""
@@ -1214,6 +1227,7 @@ class APIServerAdapter(BasePlatformAdapter):
ephemeral_system_prompt=ephemeral_system_prompt,
session_id=session_id,
stream_delta_callback=stream_delta_callback,
tool_progress_callback=tool_progress_callback,
)
if agent_ref is not None:
agent_ref[0] = agent
+43
View File
@@ -898,6 +898,26 @@ class BasePlatformAdapter(ABC):
except Exception:
pass
# ── Processing lifecycle hooks ──────────────────────────────────────────
# Subclasses override these to react to message processing events
# (e.g. Discord adds 👀/✅/❌ reactions).
async def on_processing_start(self, event: MessageEvent) -> None:
"""Hook called when background processing begins."""
async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
"""Hook called when background processing completes."""
async def _run_processing_hook(self, hook_name: str, *args: Any, **kwargs: Any) -> None:
"""Run a lifecycle hook without letting failures break message flow."""
hook = getattr(self, hook_name, None)
if not callable(hook):
return
try:
await hook(*args, **kwargs)
except Exception as e:
logger.warning("[%s] %s hook failed: %s", self.name, hook_name, e)
@staticmethod
def _is_retryable_error(error: Optional[str]) -> bool:
"""Return True if the error string looks like a transient network failure."""
@@ -1060,6 +1080,18 @@ class BasePlatformAdapter(ABC):
async def _process_message_background(self, event: MessageEvent, session_key: str) -> None:
"""Background task that actually processes the message."""
# Track delivery outcomes for the processing-complete hook
delivery_attempted = False
delivery_succeeded = False
def _record_delivery(result):
nonlocal delivery_attempted, delivery_succeeded
if result is None:
return
delivery_attempted = True
if getattr(result, "success", False):
delivery_succeeded = True
# Create interrupt event for this session
interrupt_event = asyncio.Event()
self._active_sessions[session_key] = interrupt_event
@@ -1069,6 +1101,8 @@ class BasePlatformAdapter(ABC):
typing_task = asyncio.create_task(self._keep_typing(event.source.chat_id, metadata=_thread_metadata))
try:
await self._run_processing_hook("on_processing_start", event)
# Call the handler (this can take a while with tool calls)
response = await self._message_handler(event)
@@ -1138,6 +1172,7 @@ class BasePlatformAdapter(ABC):
reply_to=event.message_id,
metadata=_thread_metadata,
)
_record_delivery(result)
# Human-like pacing delay between text and media
human_delay = self._get_human_delay()
@@ -1237,6 +1272,10 @@ class BasePlatformAdapter(ABC):
except Exception as file_err:
logger.error("[%s] Error sending local file %s: %s", self.name, file_path, file_err)
# Determine overall success for the processing hook
processing_ok = delivery_succeeded if delivery_attempted else not bool(response)
await self._run_processing_hook("on_processing_complete", event, processing_ok)
# Check if there's a pending message that was queued during our processing
if session_key in self._pending_messages:
pending_event = self._pending_messages.pop(session_key)
@@ -1253,7 +1292,11 @@ class BasePlatformAdapter(ABC):
await self._process_message_background(pending_event, session_key)
return # Already cleaned up
except asyncio.CancelledError:
await self._run_processing_hook("on_processing_complete", event, False)
raise
except Exception as e:
await self._run_processing_hook("on_processing_complete", event, False)
logger.error("[%s] Error handling message: %s", self.name, e, exc_info=True)
# Send the error to the user so they aren't left with radio silence
try:
+43
View File
@@ -660,6 +660,49 @@ class DiscordAdapter(BasePlatformAdapter):
pass
logger.info("[%s] Disconnected", self.name)
async def _add_reaction(self, message: Any, emoji: str) -> bool:
"""Add an emoji reaction to a Discord message."""
if not message or not hasattr(message, "add_reaction"):
return False
try:
await message.add_reaction(emoji)
return True
except Exception as e:
logger.debug("[%s] add_reaction failed (%s): %s", self.name, emoji, e)
return False
async def _remove_reaction(self, message: Any, emoji: str) -> bool:
"""Remove the bot's own emoji reaction from a Discord message."""
if not message or not hasattr(message, "remove_reaction") or not self._client or not self._client.user:
return False
try:
await message.remove_reaction(emoji, self._client.user)
return True
except Exception as e:
logger.debug("[%s] remove_reaction failed (%s): %s", self.name, emoji, e)
return False
def _reactions_enabled(self) -> bool:
"""Check if message reactions are enabled via config/env."""
return os.getenv("DISCORD_REACTIONS", "true").lower() not in ("false", "0", "no")
async def on_processing_start(self, event: MessageEvent) -> None:
"""Add an in-progress reaction for normal Discord message events."""
if not self._reactions_enabled():
return
message = event.raw_message
if hasattr(message, "add_reaction"):
await self._add_reaction(message, "👀")
async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
"""Swap the in-progress reaction for a final success/failure reaction."""
if not self._reactions_enabled():
return
message = event.raw_message
if hasattr(message, "add_reaction"):
await self._remove_reaction(message, "👀")
await self._add_reaction(message, "" if success else "")
async def send(
self,
File diff suppressed because it is too large Load Diff
+219 -12
View File
@@ -17,6 +17,8 @@ Environment variables:
from __future__ import annotations
import asyncio
import io
import json
import logging
import mimetypes
import os
@@ -47,6 +49,14 @@ _STORE_DIR = _get_hermes_dir("platforms/matrix/store", "matrix/store")
# Grace period: ignore messages older than this many seconds before startup.
_STARTUP_GRACE_SECONDS = 5
# E2EE key export file for persistence across restarts.
_KEY_EXPORT_FILE = _STORE_DIR / "exported_keys.txt"
_KEY_EXPORT_PASSPHRASE = "hermes-matrix-e2ee-keys"
# Pending undecrypted events: cap and TTL for retry buffer.
_MAX_PENDING_EVENTS = 100
_PENDING_EVENT_TTL = 300 # seconds — stop retrying after 5 min
def check_matrix_requirements() -> bool:
"""Return True if the Matrix adapter can be used."""
@@ -109,6 +119,10 @@ class MatrixAdapter(BasePlatformAdapter):
self._processed_events: deque = deque(maxlen=1000)
self._processed_events_set: set = set()
# Buffer for undecrypted events pending key receipt.
# Each entry: (room, event, timestamp)
self._pending_megolm: list = []
def _is_duplicate_event(self, event_id) -> bool:
"""Return True if this event was already processed. Tracks the ID otherwise."""
if not event_id:
@@ -230,6 +244,16 @@ class MatrixAdapter(BasePlatformAdapter):
logger.info("Matrix: E2EE crypto initialized")
except Exception as exc:
logger.warning("Matrix: crypto init issue: %s", exc)
# Import previously exported Megolm keys (survives restarts).
if _KEY_EXPORT_FILE.exists():
try:
await client.import_keys(
str(_KEY_EXPORT_FILE), _KEY_EXPORT_PASSPHRASE,
)
logger.info("Matrix: imported Megolm keys from backup")
except Exception as exc:
logger.debug("Matrix: could not import keys: %s", exc)
elif self._encryption:
logger.warning(
"Matrix: E2EE requested but crypto store is not loaded; "
@@ -284,6 +308,18 @@ class MatrixAdapter(BasePlatformAdapter):
except (asyncio.CancelledError, Exception):
pass
# Export Megolm keys before closing so the next restart can decrypt
# events that used sessions from this run.
if self._client and self._encryption and getattr(self._client, "olm", None):
try:
_STORE_DIR.mkdir(parents=True, exist_ok=True)
await self._client.export_keys(
str(_KEY_EXPORT_FILE), _KEY_EXPORT_PASSPHRASE,
)
logger.info("Matrix: exported Megolm keys for next restart")
except Exception as exc:
logger.debug("Matrix: could not export keys on disconnect: %s", exc)
if self._client:
await self._client.close()
self._client = None
@@ -512,8 +548,11 @@ class MatrixAdapter(BasePlatformAdapter):
reply_to: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None,
) -> SendResult:
"""Upload an audio file as a voice message."""
return await self._send_local_file(chat_id, audio_path, "m.audio", caption, reply_to, metadata=metadata)
"""Upload an audio file as a voice message (MSC3245 native voice)."""
return await self._send_local_file(
chat_id, audio_path, "m.audio", caption, reply_to,
metadata=metadata, is_voice=True
)
async def send_video(
self,
@@ -546,13 +585,16 @@ class MatrixAdapter(BasePlatformAdapter):
caption: Optional[str] = None,
reply_to: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None,
is_voice: bool = False,
) -> SendResult:
"""Upload bytes to Matrix and send as a media message."""
import nio
# Upload to homeserver.
resp = await self._client.upload(
data,
# nio expects a DataProvider (callable) or file-like object, not raw bytes.
# nio.upload() returns a tuple (UploadResponse|UploadError, Optional[Dict])
resp, maybe_encryption_info = await self._client.upload(
io.BytesIO(data),
content_type=content_type,
filename=filename,
)
@@ -574,6 +616,10 @@ class MatrixAdapter(BasePlatformAdapter):
},
}
# Add MSC3245 voice flag for native voice messages.
if is_voice:
msg_content["org.matrix.msc3245.voice"] = {}
if reply_to:
msg_content["m.relates_to"] = {
"m.in_reply_to": {"event_id": reply_to}
@@ -601,6 +647,7 @@ class MatrixAdapter(BasePlatformAdapter):
reply_to: Optional[str] = None,
file_name: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None,
is_voice: bool = False,
) -> SendResult:
"""Read a local file and upload it."""
p = Path(file_path)
@@ -613,7 +660,7 @@ class MatrixAdapter(BasePlatformAdapter):
ct = mimetypes.guess_type(fname)[0] or "application/octet-stream"
data = p.read_bytes()
return await self._upload_and_send(room_id, data, fname, ct, msgtype, caption, reply_to, metadata)
return await self._upload_and_send(room_id, data, fname, ct, msgtype, caption, reply_to, metadata, is_voice)
# ------------------------------------------------------------------
# Sync loop
@@ -652,17 +699,22 @@ class MatrixAdapter(BasePlatformAdapter):
Hermes uses a custom sync loop instead of matrix-nio's sync_forever(),
so we need to explicitly drive the key management work that sync_forever()
normally handles for encrypted rooms.
Also auto-trusts all devices (so senders share session keys with us)
and retries decryption for any buffered MegolmEvents.
"""
client = self._client
if not client or not self._encryption or not getattr(client, "olm", None):
return
did_query_keys = client.should_query_keys
tasks = [asyncio.create_task(client.send_to_device_messages())]
if client.should_upload_keys:
tasks.append(asyncio.create_task(client.keys_upload()))
if client.should_query_keys:
if did_query_keys:
tasks.append(asyncio.create_task(client.keys_query()))
if client.should_claim_keys:
@@ -678,6 +730,111 @@ class MatrixAdapter(BasePlatformAdapter):
except Exception as exc:
logger.warning("Matrix: E2EE maintenance task failed: %s", exc)
# After key queries, auto-trust all devices so senders share keys with
# us. For a bot this is the right default — we want to decrypt
# everything, not enforce manual verification.
if did_query_keys:
self._auto_trust_devices()
# Retry any buffered undecrypted events now that new keys may have
# arrived (from key requests, key queries, or to-device forwarding).
if self._pending_megolm:
await self._retry_pending_decryptions()
def _auto_trust_devices(self) -> None:
"""Trust/verify all unverified devices we know about.
When other clients see our device as verified, they proactively share
Megolm session keys with us. Without this, many clients will refuse
to include an unverified device in key distributions.
"""
client = self._client
if not client:
return
device_store = getattr(client, "device_store", None)
if not device_store:
return
own_device = getattr(client, "device_id", None)
trusted_count = 0
try:
# DeviceStore.__iter__ yields OlmDevice objects directly.
for device in device_store:
if getattr(device, "device_id", None) == own_device:
continue
if not getattr(device, "verified", False):
client.verify_device(device)
trusted_count += 1
except Exception as exc:
logger.debug("Matrix: auto-trust error: %s", exc)
if trusted_count:
logger.info("Matrix: auto-trusted %d new device(s)", trusted_count)
async def _retry_pending_decryptions(self) -> None:
"""Retry decrypting buffered MegolmEvents after new keys arrive."""
import nio
client = self._client
if not client or not self._pending_megolm:
return
now = time.time()
still_pending: list = []
for room, event, ts in self._pending_megolm:
# Drop events that have aged past the TTL.
if now - ts > _PENDING_EVENT_TTL:
logger.debug(
"Matrix: dropping expired pending event %s (age %.0fs)",
getattr(event, "event_id", "?"), now - ts,
)
continue
try:
decrypted = client.decrypt_event(event)
except Exception:
# Still missing the key — keep in buffer.
still_pending.append((room, event, ts))
continue
if isinstance(decrypted, nio.MegolmEvent):
# decrypt_event returned the same undecryptable event.
still_pending.append((room, event, ts))
continue
logger.info(
"Matrix: decrypted buffered event %s (%s)",
getattr(event, "event_id", "?"),
type(decrypted).__name__,
)
# Route to the appropriate handler based on decrypted type.
try:
if isinstance(decrypted, nio.RoomMessageText):
await self._on_room_message(room, decrypted)
elif isinstance(
decrypted,
(nio.RoomMessageImage, nio.RoomMessageAudio,
nio.RoomMessageVideo, nio.RoomMessageFile),
):
await self._on_room_message_media(room, decrypted)
else:
logger.debug(
"Matrix: decrypted event %s has unhandled type %s",
getattr(event, "event_id", "?"),
type(decrypted).__name__,
)
except Exception as exc:
logger.warning(
"Matrix: error processing decrypted event %s: %s",
getattr(event, "event_id", "?"), exc,
)
self._pending_megolm = still_pending
# ------------------------------------------------------------------
# Event callbacks
# ------------------------------------------------------------------
@@ -699,13 +856,29 @@ class MatrixAdapter(BasePlatformAdapter):
if event_ts and event_ts < self._startup_ts - _STARTUP_GRACE_SECONDS:
return
# Handle decrypted MegolmEvents — extract the inner event.
# Handle undecryptable MegolmEvents: request the missing session key
# and buffer the event for retry once the key arrives.
if isinstance(event, nio.MegolmEvent):
# Failed to decrypt.
logger.warning(
"Matrix: could not decrypt event %s in %s",
"Matrix: could not decrypt event %s in %s — requesting key",
event.event_id, room.room_id,
)
# Ask other devices in the room to forward the session key.
try:
resp = await self._client.request_room_key(event)
if hasattr(resp, "event_id") or not isinstance(resp, Exception):
logger.debug(
"Matrix: room key request sent for session %s",
getattr(event, "session_id", "?"),
)
except Exception as exc:
logger.debug("Matrix: room key request failed: %s", exc)
# Buffer for retry on next maintenance cycle.
self._pending_megolm.append((room, event, time.time()))
if len(self._pending_megolm) > _MAX_PENDING_EVENTS:
self._pending_megolm = self._pending_megolm[-_MAX_PENDING_EVENTS:]
return
# Skip edits (m.replace relation).
@@ -808,11 +981,19 @@ class MatrixAdapter(BasePlatformAdapter):
event_mimetype = (content_info.get("info") or {}).get("mimetype", "")
media_type = "application/octet-stream"
msg_type = MessageType.DOCUMENT
is_voice_message = False
if isinstance(event, nio.RoomMessageImage):
msg_type = MessageType.PHOTO
media_type = event_mimetype or "image/png"
elif isinstance(event, nio.RoomMessageAudio):
msg_type = MessageType.AUDIO
# Check for MSC3245 voice flag: org.matrix.msc3245.voice: {}
source_content = getattr(event, "source", {}).get("content", {})
if source_content.get("org.matrix.msc3245.voice") is not None:
is_voice_message = True
msg_type = MessageType.VOICE
else:
msg_type = MessageType.AUDIO
media_type = event_mimetype or "audio/ogg"
elif isinstance(event, nio.RoomMessageVideo):
msg_type = MessageType.VIDEO
@@ -850,6 +1031,31 @@ class MatrixAdapter(BasePlatformAdapter):
if relates_to.get("rel_type") == "m.thread":
thread_id = relates_to.get("event_id")
# For voice messages, cache audio locally for transcription tools.
# Use the authenticated nio client to download (Matrix requires auth for media).
media_urls = [http_url] if http_url else None
media_types = [media_type] if http_url else None
if is_voice_message and url and url.startswith("mxc://"):
try:
import nio
from gateway.platforms.base import cache_audio_from_bytes
resp = await self._client.download(mxc=url)
if isinstance(resp, nio.MemoryDownloadResponse):
# Extract extension from mimetype or default to .ogg
ext = ".ogg"
if media_type and "/" in media_type:
subtype = media_type.split("/")[1]
ext = f".{subtype}" if subtype else ".ogg"
local_path = cache_audio_from_bytes(resp.body, ext)
media_urls = [local_path]
logger.debug("Matrix: cached voice message to %s", local_path)
else:
logger.warning("Matrix: failed to download voice: %s", getattr(resp, "message", resp))
except Exception as e:
logger.warning("Matrix: failed to cache voice message, using HTTP URL: %s", e)
source = self.build_source(
chat_id=room.room_id,
chat_type=chat_type,
@@ -858,8 +1064,9 @@ class MatrixAdapter(BasePlatformAdapter):
thread_id=thread_id,
)
# Use cached local path for images, HTTP URL for other media types
media_urls = [cached_path] if cached_path else ([http_url] if http_url else None)
# Use cached local path for images (voice messages already handled above).
if cached_path:
media_urls = [cached_path]
media_types = [media_type] if media_urls else None
msg_event = MessageEvent(
+94 -31
View File
@@ -9,6 +9,7 @@ Uses slack-bolt (Python) with Socket Mode for:
"""
import asyncio
import json
import logging
import os
import re
@@ -73,6 +74,10 @@ class SlackAdapter(BasePlatformAdapter):
self._bot_user_id: Optional[str] = None
self._user_name_cache: Dict[str, str] = {} # user_id → display name
self._socket_mode_task: Optional[asyncio.Task] = None
# Multi-workspace support
self._team_clients: Dict[str, AsyncWebClient] = {} # team_id → WebClient
self._team_bot_user_ids: Dict[str, str] = {} # team_id → bot_user_id
self._channel_team: Dict[str, str] = {} # channel_id → team_id
async def connect(self) -> bool:
"""Connect to Slack via Socket Mode."""
@@ -82,16 +87,34 @@ class SlackAdapter(BasePlatformAdapter):
)
return False
bot_token = self.config.token
raw_token = self.config.token
app_token = os.getenv("SLACK_APP_TOKEN")
if not bot_token:
if not raw_token:
logger.error("[Slack] SLACK_BOT_TOKEN not set")
return False
if not app_token:
logger.error("[Slack] SLACK_APP_TOKEN not set")
return False
# Support comma-separated bot tokens for multi-workspace
bot_tokens = [t.strip() for t in raw_token.split(",") if t.strip()]
# Also load tokens from OAuth token file
from hermes_constants import get_hermes_home
tokens_file = get_hermes_home() / "slack_tokens.json"
if tokens_file.exists():
try:
saved = json.loads(tokens_file.read_text(encoding="utf-8"))
for team_id, entry in saved.items():
tok = entry.get("token", "") if isinstance(entry, dict) else ""
if tok and tok not in bot_tokens:
bot_tokens.append(tok)
team_label = entry.get("team_name", team_id) if isinstance(entry, dict) else team_id
logger.info("[Slack] Loaded saved token for workspace %s", team_label)
except Exception as e:
logger.warning("[Slack] Failed to read %s: %s", tokens_file, e)
try:
# Acquire scoped lock to prevent duplicate app token usage
from gateway.status import acquire_scoped_lock
@@ -104,12 +127,30 @@ class SlackAdapter(BasePlatformAdapter):
self._set_fatal_error('slack_token_lock', message, retryable=False)
return False
self._app = AsyncApp(token=bot_token)
# First token is the primary — used for AsyncApp / Socket Mode
primary_token = bot_tokens[0]
self._app = AsyncApp(token=primary_token)
# Get our own bot user ID for mention detection
auth_response = await self._app.client.auth_test()
self._bot_user_id = auth_response.get("user_id")
bot_name = auth_response.get("user", "unknown")
# Register each bot token and map team_id → client
for token in bot_tokens:
client = AsyncWebClient(token=token)
auth_response = await client.auth_test()
team_id = auth_response.get("team_id", "")
bot_user_id = auth_response.get("user_id", "")
bot_name = auth_response.get("user", "unknown")
team_name = auth_response.get("team", "unknown")
self._team_clients[team_id] = client
self._team_bot_user_ids[team_id] = bot_user_id
# First token sets the primary bot_user_id (backward compat)
if self._bot_user_id is None:
self._bot_user_id = bot_user_id
logger.info(
"[Slack] Authenticated as @%s in workspace %s (team: %s)",
bot_name, team_name, team_id,
)
# Register message event handler
@self._app.event("message")
@@ -134,7 +175,10 @@ class SlackAdapter(BasePlatformAdapter):
self._socket_mode_task = asyncio.create_task(self._handler.start_async())
self._running = True
logger.info("[Slack] Connected as @%s (Socket Mode)", bot_name)
logger.info(
"[Slack] Socket Mode connected (%d workspace(s))",
len(self._team_clients),
)
return True
except Exception as e: # pragma: no cover - defensive logging
@@ -161,6 +205,13 @@ class SlackAdapter(BasePlatformAdapter):
logger.info("[Slack] Disconnected")
def _get_client(self, chat_id: str) -> AsyncWebClient:
"""Return the workspace-specific WebClient for a channel."""
team_id = self._channel_team.get(chat_id)
if team_id and team_id in self._team_clients:
return self._team_clients[team_id]
return self._app.client # fallback to primary
async def send(
self,
chat_id: str,
@@ -197,7 +248,7 @@ class SlackAdapter(BasePlatformAdapter):
if broadcast and i == 0:
kwargs["reply_broadcast"] = True
last_result = await self._app.client.chat_postMessage(**kwargs)
last_result = await self._get_client(chat_id).chat_postMessage(**kwargs)
return SendResult(
success=True,
@@ -219,7 +270,7 @@ class SlackAdapter(BasePlatformAdapter):
if not self._app:
return SendResult(success=False, error="Not connected")
try:
await self._app.client.chat_update(
await self._get_client(chat_id).chat_update(
channel=chat_id,
ts=message_id,
text=content,
@@ -253,7 +304,7 @@ class SlackAdapter(BasePlatformAdapter):
return # Can only set status in a thread context
try:
await self._app.client.assistant_threads_setStatus(
await self._get_client(chat_id).assistant_threads_setStatus(
channel_id=chat_id,
thread_ts=thread_ts,
status="is thinking...",
@@ -295,7 +346,7 @@ class SlackAdapter(BasePlatformAdapter):
if not os.path.exists(file_path):
raise FileNotFoundError(f"File not found: {file_path}")
result = await self._app.client.files_upload_v2(
result = await self._get_client(chat_id).files_upload_v2(
channel=chat_id,
file=file_path,
filename=os.path.basename(file_path),
@@ -397,7 +448,7 @@ class SlackAdapter(BasePlatformAdapter):
if not self._app:
return False
try:
await self._app.client.reactions_add(
await self._get_client(channel).reactions_add(
channel=channel, timestamp=timestamp, name=emoji
)
return True
@@ -413,7 +464,7 @@ class SlackAdapter(BasePlatformAdapter):
if not self._app:
return False
try:
await self._app.client.reactions_remove(
await self._get_client(channel).reactions_remove(
channel=channel, timestamp=timestamp, name=emoji
)
return True
@@ -423,7 +474,7 @@ class SlackAdapter(BasePlatformAdapter):
# ----- User identity resolution -----
async def _resolve_user_name(self, user_id: str) -> str:
async def _resolve_user_name(self, user_id: str, chat_id: str = "") -> str:
"""Resolve a Slack user ID to a display name, with caching."""
if not user_id:
return ""
@@ -434,7 +485,8 @@ class SlackAdapter(BasePlatformAdapter):
return user_id
try:
result = await self._app.client.users_info(user=user_id)
client = self._get_client(chat_id) if chat_id else self._app.client
result = await client.users_info(user=user_id)
user = result.get("user", {})
# Prefer display_name → real_name → user_id
profile = user.get("profile", {})
@@ -498,7 +550,7 @@ class SlackAdapter(BasePlatformAdapter):
response = await client.get(image_url)
response.raise_for_status()
result = await self._app.client.files_upload_v2(
result = await self._get_client(chat_id).files_upload_v2(
channel=chat_id,
content=response.content,
filename="image.png",
@@ -558,7 +610,7 @@ class SlackAdapter(BasePlatformAdapter):
return SendResult(success=False, error=f"Video file not found: {video_path}")
try:
result = await self._app.client.files_upload_v2(
result = await self._get_client(chat_id).files_upload_v2(
channel=chat_id,
file=video_path,
filename=os.path.basename(video_path),
@@ -599,7 +651,7 @@ class SlackAdapter(BasePlatformAdapter):
display_name = file_name or os.path.basename(file_path)
try:
result = await self._app.client.files_upload_v2(
result = await self._get_client(chat_id).files_upload_v2(
channel=chat_id,
file=file_path,
filename=display_name,
@@ -627,7 +679,7 @@ class SlackAdapter(BasePlatformAdapter):
return {"name": chat_id, "type": "unknown"}
try:
result = await self._app.client.conversations_info(channel=chat_id)
result = await self._get_client(chat_id).conversations_info(channel=chat_id)
channel = result.get("channel", {})
is_dm = channel.get("is_im", False)
return {
@@ -660,6 +712,11 @@ class SlackAdapter(BasePlatformAdapter):
user_id = event.get("user", "")
channel_id = event.get("channel", "")
ts = event.get("ts", "")
team_id = event.get("team", "")
# Track which workspace owns this channel
if team_id and channel_id:
self._channel_team[channel_id] = team_id
# Determine if this is a DM or channel message
channel_type = event.get("channel_type", "")
@@ -676,11 +733,12 @@ class SlackAdapter(BasePlatformAdapter):
thread_ts = event.get("thread_ts") or ts # ts fallback for channels
# In channels, only respond if bot is mentioned
if not is_dm and self._bot_user_id:
if f"<@{self._bot_user_id}>" not in text:
bot_uid = self._team_bot_user_ids.get(team_id, self._bot_user_id)
if not is_dm and bot_uid:
if f"<@{bot_uid}>" not in text:
return
# Strip the bot mention from the text
text = text.replace(f"<@{self._bot_user_id}>", "").strip()
text = text.replace(f"<@{bot_uid}>", "").strip()
# Determine message type
msg_type = MessageType.TEXT
@@ -700,7 +758,7 @@ class SlackAdapter(BasePlatformAdapter):
if ext not in (".jpg", ".jpeg", ".png", ".gif", ".webp"):
ext = ".jpg"
# Slack private URLs require the bot token as auth header
cached = await self._download_slack_file(url, ext)
cached = await self._download_slack_file(url, ext, team_id=team_id)
media_urls.append(cached)
media_types.append(mimetype)
msg_type = MessageType.PHOTO
@@ -711,7 +769,7 @@ class SlackAdapter(BasePlatformAdapter):
ext = "." + mimetype.split("/")[-1].split(";")[0]
if ext not in (".ogg", ".mp3", ".wav", ".webm", ".m4a"):
ext = ".ogg"
cached = await self._download_slack_file(url, ext, audio=True)
cached = await self._download_slack_file(url, ext, audio=True, team_id=team_id)
media_urls.append(cached)
media_types.append(mimetype)
msg_type = MessageType.VOICE
@@ -742,7 +800,7 @@ class SlackAdapter(BasePlatformAdapter):
continue
# Download and cache
raw_bytes = await self._download_slack_file_bytes(url)
raw_bytes = await self._download_slack_file_bytes(url, team_id=team_id)
cached_path = cache_document_from_bytes(
raw_bytes, original_filename or f"document{ext}"
)
@@ -771,7 +829,7 @@ class SlackAdapter(BasePlatformAdapter):
logger.warning("[Slack] Failed to cache document from %s: %s", url, e, exc_info=True)
# Resolve user display name (cached after first lookup)
user_name = await self._resolve_user_name(user_id)
user_name = await self._resolve_user_name(user_id, chat_id=channel_id)
# Build source
source = self.build_source(
@@ -808,6 +866,11 @@ class SlackAdapter(BasePlatformAdapter):
text = command.get("text", "").strip()
user_id = command.get("user_id", "")
channel_id = command.get("channel_id", "")
team_id = command.get("team_id", "")
# Track which workspace owns this channel
if team_id and channel_id:
self._channel_team[channel_id] = team_id
# Map subcommands to gateway commands — derived from central registry.
# Also keep "compact" as a Slack-specific alias for /compress.
@@ -839,12 +902,12 @@ class SlackAdapter(BasePlatformAdapter):
await self.handle_message(event)
async def _download_slack_file(self, url: str, ext: str, audio: bool = False) -> str:
async def _download_slack_file(self, url: str, ext: str, audio: bool = False, team_id: str = "") -> str:
"""Download a Slack file using the bot token for auth, with retry."""
import asyncio
import httpx
bot_token = self.config.token
bot_token = self._team_clients[team_id].token if team_id and team_id in self._team_clients else self.config.token
last_exc = None
async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
@@ -874,12 +937,12 @@ class SlackAdapter(BasePlatformAdapter):
raise
raise last_exc
async def _download_slack_file_bytes(self, url: str) -> bytes:
async def _download_slack_file_bytes(self, url: str, team_id: str = "") -> bytes:
"""Download a Slack file and return raw bytes, with retry."""
import asyncio
import httpx
bot_token = self.config.token
bot_token = self._team_clients[team_id].token if team_id and team_id in self._team_clients else self.config.token
last_exc = None
async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
+240 -24
View File
@@ -8,6 +8,7 @@ Uses python-telegram-bot library for:
"""
import asyncio
import json
import logging
import os
import re
@@ -122,6 +123,8 @@ class TelegramAdapter(BasePlatformAdapter):
super().__init__(config, Platform.TELEGRAM)
self._app: Optional[Application] = None
self._bot: Optional[Bot] = None
self._webhook_mode: bool = False
self._mention_patterns = self._compile_mention_patterns()
self._reply_to_mode: str = getattr(config, 'reply_to_mode', 'first') or 'first'
# Buffer rapid/album photo updates so Telegram image bursts are handled
# as a single MessageEvent instead of self-interrupting multiple turns.
@@ -456,7 +459,19 @@ class TelegramAdapter(BasePlatformAdapter):
self._persist_dm_topic_thread_id(int(chat_id), topic_name, thread_id)
async def connect(self) -> bool:
"""Connect to Telegram and start polling for updates."""
"""Connect to Telegram via polling or webhook.
By default, uses long polling (outbound connection to Telegram).
If ``TELEGRAM_WEBHOOK_URL`` is set, starts an HTTP webhook server
instead. Webhook mode is useful for cloud deployments (Fly.io,
Railway) where inbound HTTP can wake a suspended machine.
Env vars for webhook mode::
TELEGRAM_WEBHOOK_URL Public HTTPS URL (e.g. https://app.fly.dev/telegram)
TELEGRAM_WEBHOOK_PORT Local listen port (default 8443)
TELEGRAM_WEBHOOK_SECRET Secret token for update verification
"""
if not TELEGRAM_AVAILABLE:
logger.error(
"[%s] python-telegram-bot not installed. Run: pip install python-telegram-bot",
@@ -550,37 +565,76 @@ class TelegramAdapter(BasePlatformAdapter):
else:
raise
await self._app.start()
loop = asyncio.get_running_loop()
def _polling_error_callback(error: Exception) -> None:
if self._polling_error_task and not self._polling_error_task.done():
return
if self._looks_like_polling_conflict(error):
self._polling_error_task = loop.create_task(self._handle_polling_conflict(error))
elif self._looks_like_network_error(error):
logger.warning("[%s] Telegram network error, scheduling reconnect: %s", self.name, error)
self._polling_error_task = loop.create_task(self._handle_polling_network_error(error))
else:
logger.error("[%s] Telegram polling error: %s", self.name, error, exc_info=True)
# Decide between webhook and polling mode
webhook_url = os.getenv("TELEGRAM_WEBHOOK_URL", "").strip()
# Store reference for retry use in _handle_polling_conflict
self._polling_error_callback_ref = _polling_error_callback
if webhook_url:
# ── Webhook mode ─────────────────────────────────────
# Telegram pushes updates to our HTTP endpoint. This
# enables cloud platforms (Fly.io, Railway) to auto-wake
# suspended machines on inbound HTTP traffic.
webhook_port = int(os.getenv("TELEGRAM_WEBHOOK_PORT", "8443"))
webhook_secret = os.getenv("TELEGRAM_WEBHOOK_SECRET", "").strip() or None
from urllib.parse import urlparse
webhook_path = urlparse(webhook_url).path or "/telegram"
await self._app.updater.start_polling(
allowed_updates=Update.ALL_TYPES,
drop_pending_updates=True,
error_callback=_polling_error_callback,
)
await self._app.updater.start_webhook(
listen="0.0.0.0",
port=webhook_port,
url_path=webhook_path,
webhook_url=webhook_url,
secret_token=webhook_secret,
allowed_updates=Update.ALL_TYPES,
drop_pending_updates=True,
)
self._webhook_mode = True
logger.info(
"[%s] Webhook server listening on 0.0.0.0:%d%s",
self.name, webhook_port, webhook_path,
)
else:
# ── Polling mode (default) ───────────────────────────
loop = asyncio.get_running_loop()
def _polling_error_callback(error: Exception) -> None:
if self._polling_error_task and not self._polling_error_task.done():
return
if self._looks_like_polling_conflict(error):
self._polling_error_task = loop.create_task(self._handle_polling_conflict(error))
elif self._looks_like_network_error(error):
logger.warning("[%s] Telegram network error, scheduling reconnect: %s", self.name, error)
self._polling_error_task = loop.create_task(self._handle_polling_network_error(error))
else:
logger.error("[%s] Telegram polling error: %s", self.name, error, exc_info=True)
# Store reference for retry use in _handle_polling_conflict
self._polling_error_callback_ref = _polling_error_callback
await self._app.updater.start_polling(
allowed_updates=Update.ALL_TYPES,
drop_pending_updates=True,
error_callback=_polling_error_callback,
)
# Register bot commands so Telegram shows a hint menu when users type /
# List is derived from the central COMMAND_REGISTRY — adding a new
# gateway command there automatically adds it to the Telegram menu.
try:
from telegram import BotCommand
from hermes_cli.commands import telegram_bot_commands
from hermes_cli.commands import telegram_menu_commands
# Telegram allows up to 100 commands but has an undocumented
# payload size limit. Skill descriptions are truncated to 40
# chars in telegram_menu_commands() to fit 100 commands safely.
menu_commands, hidden_count = telegram_menu_commands(max_commands=100)
await self._bot.set_my_commands([
BotCommand(name, desc) for name, desc in telegram_bot_commands()
BotCommand(name, desc) for name, desc in menu_commands
])
if hidden_count:
logger.info(
"[%s] Telegram menu: %d commands registered, %d hidden (over 100 limit). Use /commands for full list.",
self.name, len(menu_commands), hidden_count,
)
except Exception as e:
logger.warning(
"[%s] Could not register Telegram command menu: %s",
@@ -590,7 +644,8 @@ class TelegramAdapter(BasePlatformAdapter):
)
self._mark_connected()
logger.info("[%s] Connected and polling for Telegram updates", self.name)
mode = "webhook" if self._webhook_mode else "polling"
logger.info("[%s] Connected to Telegram (%s mode)", self.name, mode)
# Set up DM topics (Bot API 9.4 — Private Chat Topics)
# Runs after connection is established so the bot can call createForumTopic.
@@ -618,7 +673,7 @@ class TelegramAdapter(BasePlatformAdapter):
return False
async def disconnect(self) -> None:
"""Stop polling, cancel pending album flushes, and disconnect."""
"""Stop polling/webhook, cancel pending album flushes, and disconnect."""
pending_media_group_tasks = list(self._media_group_tasks.values())
for task in pending_media_group_tasks:
task.cancel()
@@ -762,6 +817,16 @@ class TelegramAdapter(BasePlatformAdapter):
)
effective_thread_id = None
continue
if "message to be replied not found" in err_lower and reply_to_id is not None:
# Original message was deleted before we
# could reply — clear reply target and retry
# so the response is still delivered.
logger.warning(
"[%s] Reply target deleted, retrying without reply_to: %s",
self.name, send_err,
)
reply_to_id = None
continue
# Other BadRequest errors are permanent — don't retry
raise
if _send_attempt < 2:
@@ -1315,6 +1380,148 @@ class TelegramAdapter(BasePlatformAdapter):
return text
# ── Group mention gating ──────────────────────────────────────────────
def _telegram_require_mention(self) -> bool:
"""Return whether group chats should require an explicit bot trigger."""
configured = self.config.extra.get("require_mention")
if configured is not None:
if isinstance(configured, str):
return configured.lower() in ("true", "1", "yes", "on")
return bool(configured)
return os.getenv("TELEGRAM_REQUIRE_MENTION", "false").lower() in ("true", "1", "yes", "on")
def _telegram_free_response_chats(self) -> set[str]:
raw = self.config.extra.get("free_response_chats")
if raw is None:
raw = os.getenv("TELEGRAM_FREE_RESPONSE_CHATS", "")
if isinstance(raw, list):
return {str(part).strip() for part in raw if str(part).strip()}
return {part.strip() for part in str(raw).split(",") if part.strip()}
def _compile_mention_patterns(self) -> List[re.Pattern]:
"""Compile optional regex wake-word patterns for group triggers."""
patterns = self.config.extra.get("mention_patterns")
if patterns is None:
raw = os.getenv("TELEGRAM_MENTION_PATTERNS", "").strip()
if raw:
try:
loaded = json.loads(raw)
except Exception:
loaded = [part.strip() for part in raw.splitlines() if part.strip()]
if not loaded:
loaded = [part.strip() for part in raw.split(",") if part.strip()]
patterns = loaded
if patterns is None:
return []
if isinstance(patterns, str):
patterns = [patterns]
if not isinstance(patterns, list):
logger.warning(
"[%s] telegram mention_patterns must be a list or string; got %s",
self.name,
type(patterns).__name__,
)
return []
compiled: List[re.Pattern] = []
for pattern in patterns:
if not isinstance(pattern, str) or not pattern.strip():
continue
try:
compiled.append(re.compile(pattern, re.IGNORECASE))
except re.error as exc:
logger.warning("[%s] Invalid Telegram mention pattern %r: %s", self.name, pattern, exc)
if compiled:
logger.info("[%s] Loaded %d Telegram mention pattern(s)", self.name, len(compiled))
return compiled
def _is_group_chat(self, message: Message) -> bool:
chat = getattr(message, "chat", None)
if not chat:
return False
chat_type = str(getattr(chat, "type", "")).split(".")[-1].lower()
return chat_type in ("group", "supergroup")
def _is_reply_to_bot(self, message: Message) -> bool:
if not self._bot or not getattr(message, "reply_to_message", None):
return False
reply_user = getattr(message.reply_to_message, "from_user", None)
return bool(reply_user and getattr(reply_user, "id", None) == getattr(self._bot, "id", None))
def _message_mentions_bot(self, message: Message) -> bool:
if not self._bot:
return False
bot_username = (getattr(self._bot, "username", None) or "").lstrip("@").lower()
bot_id = getattr(self._bot, "id", None)
def _iter_sources():
yield getattr(message, "text", None) or "", getattr(message, "entities", None) or []
yield getattr(message, "caption", None) or "", getattr(message, "caption_entities", None) or []
for source_text, entities in _iter_sources():
if bot_username and f"@{bot_username}" in source_text.lower():
return True
for entity in entities:
entity_type = str(getattr(entity, "type", "")).split(".")[-1].lower()
if entity_type == "mention" and bot_username:
offset = int(getattr(entity, "offset", -1))
length = int(getattr(entity, "length", 0))
if offset < 0 or length <= 0:
continue
if source_text[offset:offset + length].strip().lower() == f"@{bot_username}":
return True
elif entity_type == "text_mention":
user = getattr(entity, "user", None)
if user and getattr(user, "id", None) == bot_id:
return True
return False
def _message_matches_mention_patterns(self, message: Message) -> bool:
if not self._mention_patterns:
return False
for candidate in (getattr(message, "text", None), getattr(message, "caption", None)):
if not candidate:
continue
for pattern in self._mention_patterns:
if pattern.search(candidate):
return True
return False
def _clean_bot_trigger_text(self, text: Optional[str]) -> Optional[str]:
if not text or not self._bot or not getattr(self._bot, "username", None):
return text
username = re.escape(self._bot.username)
cleaned = re.sub(rf"(?i)@{username}\b[,:\-]*\s*", "", text).strip()
return cleaned or text
def _should_process_message(self, message: Message, *, is_command: bool = False) -> bool:
"""Apply Telegram group trigger rules.
DMs remain unrestricted. Group/supergroup messages are accepted when:
- the chat is explicitly allowlisted in ``free_response_chats``
- ``require_mention`` is disabled
- the message is a command
- the message replies to the bot
- the bot is @mentioned
- the text/caption matches a configured regex wake-word pattern
"""
if not self._is_group_chat(message):
return True
if str(getattr(getattr(message, "chat", None), "id", "")) in self._telegram_free_response_chats():
return True
if not self._telegram_require_mention():
return True
if is_command:
return True
if self._is_reply_to_bot(message):
return True
if self._message_mentions_bot(message):
return True
return self._message_matches_mention_patterns(message)
async def _handle_text_message(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle incoming text messages.
@@ -1324,14 +1531,19 @@ class TelegramAdapter(BasePlatformAdapter):
"""
if not update.message or not update.message.text:
return
if not self._should_process_message(update.message):
return
event = self._build_message_event(update.message, MessageType.TEXT)
event.text = self._clean_bot_trigger_text(event.text)
self._enqueue_text_event(event)
async def _handle_command(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle incoming command messages."""
if not update.message or not update.message.text:
return
if not self._should_process_message(update.message, is_command=True):
return
event = self._build_message_event(update.message, MessageType.COMMAND)
await self.handle_message(event)
@@ -1340,6 +1552,8 @@ class TelegramAdapter(BasePlatformAdapter):
"""Handle incoming location/venue pin messages."""
if not update.message:
return
if not self._should_process_message(update.message):
return
msg = update.message
venue = getattr(msg, "venue", None)
@@ -1483,6 +1697,8 @@ class TelegramAdapter(BasePlatformAdapter):
"""Handle incoming media messages, downloading images to local cache."""
if not update.message:
return
if not self._should_process_message(update.message):
return
msg = update.message
@@ -1506,7 +1722,7 @@ class TelegramAdapter(BasePlatformAdapter):
# Add caption as text
if msg.caption:
event.text = msg.caption
event.text = self._clean_bot_trigger_text(msg.caption)
# Handle stickers: describe via vision tool with caching
if msg.sticker:
+3
View File
@@ -135,6 +135,9 @@ def _normalize_fallback_ips(values: Iterable[str]) -> list[str]:
if addr.version != 4:
logger.warning("Ignoring non-IPv4 Telegram fallback IP: %s", raw)
continue
if addr.is_private or addr.is_loopback or addr.is_link_local or addr.is_unspecified:
logger.warning("Ignoring private/internal Telegram fallback IP: %s", raw)
continue
normalized.append(str(addr))
return normalized
File diff suppressed because it is too large Load Diff
+486 -88
View File
@@ -225,6 +225,49 @@ from gateway.session import (
from gateway.delivery import DeliveryRouter
from gateway.platforms.base import BasePlatformAdapter, MessageEvent, MessageType
def _normalize_whatsapp_identifier(value: str) -> str:
"""Strip WhatsApp JID/LID syntax down to its stable numeric identifier."""
return (
str(value or "")
.strip()
.replace("+", "", 1)
.split(":", 1)[0]
.split("@", 1)[0]
)
def _expand_whatsapp_auth_aliases(identifier: str) -> set:
"""Resolve WhatsApp phone/LID aliases using bridge session mapping files."""
normalized = _normalize_whatsapp_identifier(identifier)
if not normalized:
return set()
session_dir = _hermes_home / "whatsapp" / "session"
resolved = set()
queue = [normalized]
while queue:
current = queue.pop(0)
if not current or current in resolved:
continue
resolved.add(current)
for suffix in ("", "_reverse"):
mapping_path = session_dir / f"lid-mapping-{current}{suffix}.json"
if not mapping_path.exists():
continue
try:
mapped = _normalize_whatsapp_identifier(
json.loads(mapping_path.read_text(encoding="utf-8"))
)
except Exception:
continue
if mapped and mapped not in resolved:
queue.append(mapped)
return resolved
logger = logging.getLogger(__name__)
# Sentinel placed into _running_agents immediately when a session starts
@@ -258,6 +301,50 @@ def _resolve_runtime_agent_kwargs() -> dict:
}
def _check_unavailable_skill(command_name: str) -> str | None:
"""Check if a command matches a known-but-inactive skill.
Returns a helpful message if the skill exists but is disabled or only
available as an optional install. Returns None if no match found.
"""
# Normalize: command uses hyphens, skill names may use hyphens or underscores
normalized = command_name.lower().replace("_", "-")
try:
from tools.skills_tool import SKILLS_DIR, _get_disabled_skill_names
disabled = _get_disabled_skill_names()
# Check disabled built-in skills
for skill_md in SKILLS_DIR.rglob("SKILL.md"):
if any(part in ('.git', '.github', '.hub') for part in skill_md.parts):
continue
name = skill_md.parent.name.lower().replace("_", "-")
if name == normalized and name in disabled:
return (
f"The **{command_name}** skill is installed but disabled.\n"
f"Enable it with: `hermes skills config`"
)
# Check optional skills (shipped with repo but not installed)
from hermes_constants import get_hermes_home, get_optional_skills_dir
repo_root = Path(__file__).resolve().parent.parent
optional_dir = get_optional_skills_dir(repo_root / "optional-skills")
if optional_dir.exists():
for skill_md in optional_dir.rglob("SKILL.md"):
name = skill_md.parent.name.lower().replace("_", "-")
if name == normalized:
# Build install path: official/<category>/<name>
rel = skill_md.parent.relative_to(optional_dir)
parts = list(rel.parts)
install_path = f"official/{'/'.join(parts)}"
return (
f"The **{command_name}** skill is available but not installed.\n"
f"Install it with: `hermes skills install {install_path}`"
)
except Exception:
pass
return None
def _platform_config_key(platform: "Platform") -> str:
"""Map a Platform enum to its config.yaml key (LOCAL→"cli", rest→enum value)."""
return "cli" if platform == Platform.LOCAL else platform.value
@@ -277,20 +364,19 @@ def _load_gateway_config() -> dict:
def _resolve_gateway_model(config: dict | None = None) -> str:
"""Read model from env/config — mirrors the resolution in _run_agent_sync.
"""Read model from config.yaml — single source of truth.
Without this, temporary AIAgent instances (memory flush, /compress) fall
back to the hardcoded default ("anthropic/claude-opus-4.6") which fails
when the active provider is openai-codex.
back to the hardcoded default which fails when the active provider is
openai-codex.
"""
model = os.getenv("HERMES_MODEL") or os.getenv("LLM_MODEL") or "anthropic/claude-opus-4.6"
cfg = config if config is not None else _load_gateway_config()
model_cfg = cfg.get("model", {})
if isinstance(model_cfg, str):
model = model_cfg
return model_cfg
elif isinstance(model_cfg, dict):
model = model_cfg.get("default") or model_cfg.get("model") or model
return model
return model_cfg.get("default") or model_cfg.get("model") or ""
return ""
def _resolve_hermes_bin() -> Optional[list[str]]:
@@ -389,6 +475,8 @@ class GatewayRunner:
self._honcho_managers: Dict[str, Any] = {}
self._honcho_configs: Dict[str, Any] = {}
# Ensure tirith security scanner is available (downloads if needed)
try:
from tools.tirith_security import ensure_installed
@@ -983,6 +1071,8 @@ class GatewayRunner:
"EMAIL_ALLOWED_USERS",
"SMS_ALLOWED_USERS", "MATTERMOST_ALLOWED_USERS",
"MATRIX_ALLOWED_USERS", "DINGTALK_ALLOWED_USERS",
"FEISHU_ALLOWED_USERS",
"WECOM_ALLOWED_USERS",
"GATEWAY_ALLOWED_USERS")
)
_allow_all = os.getenv("GATEWAY_ALLOW_ALL_USERS", "").lower() in ("true", "1", "yes") or any(
@@ -991,7 +1081,9 @@ class GatewayRunner:
"WHATSAPP_ALLOW_ALL_USERS", "SLACK_ALLOW_ALL_USERS",
"SIGNAL_ALLOW_ALL_USERS", "EMAIL_ALLOW_ALL_USERS",
"SMS_ALLOW_ALL_USERS", "MATTERMOST_ALLOW_ALL_USERS",
"MATRIX_ALLOW_ALL_USERS", "DINGTALK_ALLOW_ALL_USERS")
"MATRIX_ALLOW_ALL_USERS", "DINGTALK_ALLOW_ALL_USERS",
"FEISHU_ALLOW_ALL_USERS",
"WECOM_ALLOW_ALL_USERS")
)
if not _any_allowlist and not _allow_all:
logger.warning(
@@ -1434,6 +1526,20 @@ class GatewayRunner:
return None
return DingTalkAdapter(config)
elif platform == Platform.FEISHU:
from gateway.platforms.feishu import FeishuAdapter, check_feishu_requirements
if not check_feishu_requirements():
logger.warning("Feishu: lark-oapi not installed or FEISHU_APP_ID/SECRET not set")
return None
return FeishuAdapter(config)
elif platform == Platform.WECOM:
from gateway.platforms.wecom import WeComAdapter, check_wecom_requirements
if not check_wecom_requirements():
logger.warning("WeCom: aiohttp not installed or WECOM_BOT_ID/SECRET not set")
return None
return WeComAdapter(config)
elif platform == Platform.MATTERMOST:
from gateway.platforms.mattermost import MattermostAdapter, check_mattermost_requirements
if not check_mattermost_requirements():
@@ -1500,6 +1606,8 @@ class GatewayRunner:
Platform.MATTERMOST: "MATTERMOST_ALLOWED_USERS",
Platform.MATRIX: "MATRIX_ALLOWED_USERS",
Platform.DINGTALK: "DINGTALK_ALLOWED_USERS",
Platform.FEISHU: "FEISHU_ALLOWED_USERS",
Platform.WECOM: "WECOM_ALLOWED_USERS",
}
platform_allow_all_map = {
Platform.TELEGRAM: "TELEGRAM_ALLOW_ALL_USERS",
@@ -1512,6 +1620,8 @@ class GatewayRunner:
Platform.MATTERMOST: "MATTERMOST_ALLOW_ALL_USERS",
Platform.MATRIX: "MATRIX_ALLOW_ALL_USERS",
Platform.DINGTALK: "DINGTALK_ALLOW_ALL_USERS",
Platform.FEISHU: "FEISHU_ALLOW_ALL_USERS",
Platform.WECOM: "WECOM_ALLOW_ALL_USERS",
}
# Per-platform allow-all flag (e.g., DISCORD_ALLOW_ALL_USERS=true)
@@ -1539,10 +1649,23 @@ class GatewayRunner:
if global_allowlist:
allowed_ids.update(uid.strip() for uid in global_allowlist.split(",") if uid.strip())
# WhatsApp JIDs have @s.whatsapp.net suffix — strip it for comparison
check_ids = {user_id}
if "@" in user_id:
check_ids.add(user_id.split("@")[0])
# WhatsApp: resolve phone↔LID aliases from bridge session mapping files
if source.platform == Platform.WHATSAPP:
normalized_allowed_ids = set()
for allowed_id in allowed_ids:
normalized_allowed_ids.update(_expand_whatsapp_auth_aliases(allowed_id))
if normalized_allowed_ids:
allowed_ids = normalized_allowed_ids
check_ids.update(_expand_whatsapp_auth_aliases(user_id))
normalized_user_id = _normalize_whatsapp_identifier(user_id)
if normalized_user_id:
check_ids.add(normalized_user_id)
return bool(check_ids & allowed_ids)
def _get_unauthorized_dm_behavior(self, platform: Optional[Platform]) -> str:
@@ -1573,6 +1696,11 @@ class GatewayRunner:
# In DMs: offer pairing code. In groups: silently ignore.
if source.chat_type == "dm" and self._get_unauthorized_dm_behavior(source.platform) == "pair":
platform_name = source.platform.value if source.platform else "unknown"
# Rate-limit ALL pairing responses (code or rejection) to
# prevent spamming the user with repeated messages when
# multiple DMs arrive in quick succession.
if self.pairing_store._is_rate_limited(platform_name, source.user_id):
return None
code = self.pairing_store.generate_code(
platform_name, source.user_id, source.user_name or ""
)
@@ -1594,6 +1722,8 @@ class GatewayRunner:
"Too many pairing requests right now~ "
"Please try again later!"
)
# Record rate limit so subsequent messages are silently ignored
self.pairing_store._record_rate_limit(platform_name, source.user_id)
return None
# PRIORITY handling when an agent is already running for this session.
@@ -1739,7 +1869,13 @@ class GatewayRunner:
if canonical == "help":
return await self._handle_help_command(event)
if canonical == "commands":
return await self._handle_commands_command(event)
if canonical == "profile":
return await self._handle_profile_command(event)
if canonical == "status":
return await self._handle_status_command(event)
@@ -1752,6 +1888,9 @@ class GatewayRunner:
if canonical == "verbose":
return await self._handle_verbose_command(event)
if canonical == "yolo":
return await self._handle_yolo_command(event)
if canonical == "provider":
return await self._handle_provider_command(event)
@@ -1822,6 +1961,9 @@ class GatewayRunner:
if canonical == "background":
return await self._handle_background_command(event)
if canonical == "btw":
return await self._handle_btw_command(event)
if canonical == "voice":
return await self._handle_voice_command(event)
@@ -1896,6 +2038,12 @@ class GatewayRunner:
if msg:
event.text = msg
# Fall through to normal message processing with skill content
else:
# Not an active skill — check if it's a known-but-disabled or
# uninstalled skill and give actionable guidance.
_unavail_msg = _check_unavailable_skill(command)
if _unavail_msg:
return _unavail_msg
except Exception as e:
logger.debug("Skill command check failed (non-fatal): %s", e)
@@ -2133,6 +2281,29 @@ class GatewayRunner:
_hyg_api_key = _hyg_runtime.get("api_key")
except Exception:
pass
# Check custom_providers per-model context_length
# (same fallback as run_agent.py lines 1171-1189).
# Must run after runtime resolution so _hyg_base_url is set.
if _hyg_config_context_length is None and _hyg_base_url:
try:
_hyg_custom_providers = _hyg_data.get("custom_providers")
if isinstance(_hyg_custom_providers, list):
for _cp in _hyg_custom_providers:
if not isinstance(_cp, dict):
continue
_cp_url = (_cp.get("base_url") or "").rstrip("/")
if _cp_url and _cp_url == _hyg_base_url.rstrip("/"):
_cp_models = _cp.get("models", {})
if isinstance(_cp_models, dict):
_cp_model_cfg = _cp_models.get(_hyg_model, {})
if isinstance(_cp_model_cfg, dict):
_cp_ctx = _cp_model_cfg.get("context_length")
if _cp_ctx is not None:
_hyg_config_context_length = int(_cp_ctx)
break
except (TypeError, ValueError):
pass
except Exception:
pass
@@ -2180,18 +2351,7 @@ class GatewayRunner:
f"{_compress_token_threshold:,}",
)
_hyg_adapter = self.adapters.get(source.platform)
_hyg_meta = {"thread_id": source.thread_id} if source.thread_id else None
if _hyg_adapter:
try:
await _hyg_adapter.send(
source.chat_id,
f"🗜️ Session is large ({_msg_count} messages, "
f"~{_approx_tokens:,} tokens). Auto-compressing...",
metadata=_hyg_meta,
)
except Exception:
pass
try:
from run_agent import AIAgent
@@ -2252,62 +2412,17 @@ class GatewayRunner:
f"{_approx_tokens:,}", f"{_new_tokens:,}",
)
if _hyg_adapter:
try:
await _hyg_adapter.send(
source.chat_id,
f"🗜️ Compressed: {_msg_count}"
f"{_new_count} messages, "
f"~{_approx_tokens:,}"
f"~{_new_tokens:,} tokens",
metadata=_hyg_meta,
)
except Exception:
pass
# Still too large after compression — warn user
if _new_tokens >= _warn_token_threshold:
logger.warning(
"Session hygiene: still ~%s tokens after "
"compression — suggesting /reset",
"compression",
f"{_new_tokens:,}",
)
if _hyg_adapter:
try:
await _hyg_adapter.send(
source.chat_id,
"⚠️ Session is still very large "
"after compression "
f"(~{_new_tokens:,} tokens). "
"Consider using /reset to start "
"fresh if you experience issues.",
metadata=_hyg_meta,
)
except Exception:
pass
except Exception as e:
logger.warning(
"Session hygiene auto-compress failed: %s", e
)
# Compression failed and session is dangerously large
if _approx_tokens >= _warn_token_threshold:
_hyg_adapter = self.adapters.get(source.platform)
_hyg_meta = {"thread_id": source.thread_id} if source.thread_id else None
if _hyg_adapter:
try:
await _hyg_adapter.send(
source.chat_id,
f"⚠️ Session is very large "
f"({_msg_count} messages, "
f"~{_approx_tokens:,} tokens) and "
"auto-compression failed. Consider "
"using /compress or /reset to avoid "
"issues.",
metadata=_hyg_meta,
)
except Exception:
pass
# First-message onboarding -- only on the very first interaction ever
if not history and not self.session_store.has_any_sessions():
@@ -2646,7 +2761,7 @@ class GatewayRunner:
{
"role": "session_meta",
"tools": tool_defs or [],
"model": os.getenv("HERMES_MODEL", ""),
"model": _resolve_gateway_model(),
"platform": source.platform.value if source.platform else "",
"timestamp": ts,
}
@@ -2921,6 +3036,36 @@ class GatewayRunner:
return f"{header}\n\n{session_info}"
return header
async def _handle_profile_command(self, event: MessageEvent) -> str:
"""Handle /profile — show active profile name and home directory."""
from hermes_constants import get_hermes_home, display_hermes_home
from pathlib import Path
home = get_hermes_home()
display = display_hermes_home()
# Detect profile name from HERMES_HOME path
# Profile paths look like: ~/.hermes/profiles/<name>
profiles_parent = Path.home() / ".hermes" / "profiles"
try:
rel = home.relative_to(profiles_parent)
profile_name = str(rel).split("/")[0]
except ValueError:
profile_name = None
if profile_name:
lines = [
f"👤 **Profile:** `{profile_name}`",
f"📂 **Home:** `{display}`",
]
else:
lines = [
"👤 **Profile:** default",
f"📂 **Home:** `{display}`",
]
return "\n".join(lines)
async def _handle_status_command(self, event: MessageEvent) -> str:
"""Handle /status command."""
source = event.source
@@ -2987,12 +3132,69 @@ class GatewayRunner:
from agent.skill_commands import get_skill_commands
skill_cmds = get_skill_commands()
if skill_cmds:
lines.append(f"\n⚡ **Skill Commands** ({len(skill_cmds)} installed):")
for cmd in sorted(skill_cmds):
lines.append(f"\n⚡ **Skill Commands** ({len(skill_cmds)} active):")
# Show first 10, then point to /commands for the rest
sorted_cmds = sorted(skill_cmds)
for cmd in sorted_cmds[:10]:
lines.append(f"`{cmd}` — {skill_cmds[cmd]['description']}")
if len(sorted_cmds) > 10:
lines.append(f"\n... and {len(sorted_cmds) - 10} more. Use `/commands` for the full paginated list.")
except Exception:
pass
return "\n".join(lines)
async def _handle_commands_command(self, event: MessageEvent) -> str:
"""Handle /commands [page] - paginated list of all commands and skills."""
from hermes_cli.commands import gateway_help_lines
raw_args = event.get_command_args().strip()
if raw_args:
try:
requested_page = int(raw_args)
except ValueError:
return "Usage: `/commands [page]`"
else:
requested_page = 1
# Build combined entry list: built-in commands + skill commands
entries = list(gateway_help_lines())
try:
from agent.skill_commands import get_skill_commands
skill_cmds = get_skill_commands()
if skill_cmds:
entries.append("")
entries.append("⚡ **Skill Commands**:")
for cmd in sorted(skill_cmds):
desc = skill_cmds[cmd].get("description", "").strip() or "Skill command"
entries.append(f"`{cmd}` — {desc}")
except Exception:
pass
if not entries:
return "No commands available."
from gateway.config import Platform
page_size = 15 if event.source.platform == Platform.TELEGRAM else 20
total_pages = max(1, (len(entries) + page_size - 1) // page_size)
page = max(1, min(requested_page, total_pages))
start = (page - 1) * page_size
page_entries = entries[start:start + page_size]
lines = [
f"📚 **Commands** ({len(entries)} total, page {page}/{total_pages})",
"",
*page_entries,
]
if total_pages > 1:
nav_parts = []
if page > 1:
nav_parts.append(f"`/commands {page - 1}` ← prev")
if page < total_pages:
nav_parts.append(f"next → `/commands {page + 1}`")
lines.extend(["", " | ".join(nav_parts)])
if page != requested_page:
lines.append(f"_(Requested page {requested_page} was out of range, showing page {page}.)_")
return "\n".join(lines)
async def _handle_provider_command(self, event: MessageEvent) -> str:
"""Handle /provider command - show available providers."""
@@ -3024,9 +3226,11 @@ class GatewayRunner:
except Exception:
current_provider = "openrouter"
# Detect custom endpoint
if current_provider == "openrouter" and os.getenv("OPENAI_BASE_URL", "").strip():
current_provider = "custom"
# Detect custom endpoint from config base_url
if current_provider == "openrouter":
_cfg_base = model_cfg.get("base_url", "") if isinstance(model_cfg, dict) else ""
if _cfg_base and "openrouter.ai" not in _cfg_base:
current_provider = "custom"
current_label = _PROVIDER_LABELS.get(current_provider, current_provider)
@@ -3813,7 +4017,7 @@ class GatewayRunner:
# Send media files
for media_path in (media_files or []):
try:
await adapter.send_file(
await adapter.send_document(
chat_id=source.chat_id,
file_path=media_path,
)
@@ -3838,6 +4042,167 @@ class GatewayRunner:
except Exception:
pass
async def _handle_btw_command(self, event: MessageEvent) -> str:
"""Handle /btw <question> — ephemeral side question in the same chat."""
question = event.get_command_args().strip()
if not question:
return (
"Usage: /btw <question>\n"
"Example: /btw what module owns session title sanitization?\n\n"
"Answers using session context. No tools, not persisted."
)
source = event.source
session_key = self._session_key_for_source(source)
# Guard: one /btw at a time per session
existing = getattr(self, "_active_btw_tasks", {}).get(session_key)
if existing and not existing.done():
return "A /btw is already running for this chat. Wait for it to finish."
if not hasattr(self, "_active_btw_tasks"):
self._active_btw_tasks: dict = {}
import uuid as _uuid
task_id = f"btw_{datetime.now().strftime('%H%M%S')}_{_uuid.uuid4().hex[:6]}"
_task = asyncio.create_task(self._run_btw_task(question, source, session_key, task_id))
self._background_tasks.add(_task)
self._active_btw_tasks[session_key] = _task
def _cleanup(task):
self._background_tasks.discard(task)
if self._active_btw_tasks.get(session_key) is task:
self._active_btw_tasks.pop(session_key, None)
_task.add_done_callback(_cleanup)
preview = question[:60] + ("..." if len(question) > 60 else "")
return f'💬 /btw: "{preview}"\nReply will appear here shortly.'
async def _run_btw_task(
self, question: str, source, session_key: str, task_id: str,
) -> None:
"""Execute an ephemeral /btw side question and deliver the answer."""
from run_agent import AIAgent
adapter = self.adapters.get(source.platform)
if not adapter:
logger.warning("No adapter for platform %s in /btw task %s", source.platform, task_id)
return
_thread_meta = {"thread_id": source.thread_id} if source.thread_id else None
try:
runtime_kwargs = _resolve_runtime_agent_kwargs()
if not runtime_kwargs.get("api_key"):
await adapter.send(
source.chat_id,
"❌ /btw failed: no provider credentials configured.",
metadata=_thread_meta,
)
return
user_config = _load_gateway_config()
model = _resolve_gateway_model(user_config)
platform_key = _platform_config_key(source.platform)
reasoning_config = self._load_reasoning_config()
turn_route = self._resolve_turn_agent_config(question, model, runtime_kwargs)
pr = self._provider_routing
# Snapshot history from running agent or stored transcript
running_agent = self._running_agents.get(session_key)
if running_agent and running_agent is not _AGENT_PENDING_SENTINEL:
history_snapshot = list(getattr(running_agent, "_session_messages", []) or [])
else:
session_entry = self.session_store.get_or_create_session(source)
history_snapshot = self.session_store.load_transcript(session_entry.session_id)
btw_prompt = (
"[Ephemeral /btw side question. Answer using the conversation "
"context. No tools available. Be direct and concise.]\n\n"
+ question
)
def run_sync():
agent = AIAgent(
model=turn_route["model"],
**turn_route["runtime"],
max_iterations=8,
quiet_mode=True,
verbose_logging=False,
enabled_toolsets=[],
reasoning_config=reasoning_config,
providers_allowed=pr.get("only"),
providers_ignored=pr.get("ignore"),
providers_order=pr.get("order"),
provider_sort=pr.get("sort"),
provider_require_parameters=pr.get("require_parameters", False),
provider_data_collection=pr.get("data_collection"),
session_id=task_id,
platform=platform_key,
session_db=None,
fallback_model=self._fallback_model,
skip_memory=True,
skip_context_files=True,
persist_session=False,
)
return agent.run_conversation(
user_message=btw_prompt,
conversation_history=history_snapshot,
task_id=task_id,
sync_honcho=False,
)
loop = asyncio.get_event_loop()
result = await loop.run_in_executor(None, run_sync)
response = (result.get("final_response") or "") if result else ""
if not response and result and result.get("error"):
response = f"Error: {result['error']}"
if not response:
response = "(No response generated)"
media_files, response = adapter.extract_media(response)
images, text_content = adapter.extract_images(response)
preview = question[:60] + ("..." if len(question) > 60 else "")
header = f'💬 /btw: "{preview}"\n\n'
if text_content:
await adapter.send(
chat_id=source.chat_id,
content=header + text_content,
metadata=_thread_meta,
)
elif not images and not media_files:
await adapter.send(
chat_id=source.chat_id,
content=header + "(No response generated)",
metadata=_thread_meta,
)
for image_url, alt_text in (images or []):
try:
await adapter.send_image(chat_id=source.chat_id, image_url=image_url, caption=alt_text)
except Exception:
pass
for media_path in (media_files or []):
try:
await adapter.send_file(chat_id=source.chat_id, file_path=media_path)
except Exception:
pass
except Exception as e:
logger.exception("/btw task %s failed", task_id)
try:
await adapter.send(
chat_id=source.chat_id,
content=f"❌ /btw failed: {e}",
metadata=_thread_meta,
)
except Exception:
pass
async def _handle_reasoning_command(self, event: MessageEvent) -> str:
"""Handle /reasoning command — manage reasoning effort and display toggle.
@@ -3921,6 +4286,16 @@ class GatewayRunner:
else:
return f"🧠 ✓ Reasoning effort set to `{effort}` (this session only)"
async def _handle_yolo_command(self, event: MessageEvent) -> str:
"""Handle /yolo — toggle dangerous command approval bypass."""
current = bool(os.environ.get("HERMES_YOLO_MODE"))
if current:
os.environ.pop("HERMES_YOLO_MODE", None)
return "⚠️ YOLO mode **OFF** — dangerous commands will require approval."
else:
os.environ["HERMES_YOLO_MODE"] = "1"
return "⚡ YOLO mode **ON** — all commands auto-approved. Use with caution."
async def _handle_verbose_command(self, event: MessageEvent) -> str:
"""Handle /verbose command — cycle tool progress display mode.
@@ -4407,8 +4782,8 @@ class GatewayRunner:
async def _handle_update_command(self, event: MessageEvent) -> str:
"""Handle /update command — update Hermes Agent to the latest version.
Spawns ``hermes update`` in a separate systemd scope so it survives the
gateway restart that ``hermes update`` may trigger at the end. Marker
Spawns ``hermes update`` in a detached session (via ``setsid``) so it
survives the gateway restart that ``hermes update`` may trigger. Marker
files are written so either the current gateway process or the next one
can notify the user when the update finishes.
"""
@@ -4416,6 +4791,10 @@ class GatewayRunner:
import shutil
import subprocess
from datetime import datetime
from hermes_cli.config import is_managed, format_managed_message
if is_managed():
return f"{format_managed_message('update Hermes Agent')}"
project_root = Path(__file__).parent.parent.resolve()
git_dir = project_root / '.git'
@@ -4444,28 +4823,28 @@ class GatewayRunner:
pending_path.write_text(json.dumps(pending))
exit_code_path.unlink(missing_ok=True)
# Spawn `hermes update` in a separate cgroup so it survives gateway
# restart. systemd-run --user --scope creates a transient scope unit.
# Spawn `hermes update` detached so it survives gateway restart.
# Use setsid for portable session detach (works under system services
# where systemd-run --user fails due to missing D-Bus session).
hermes_cmd_str = " ".join(shlex.quote(part) for part in hermes_cmd)
update_cmd = (
f"{hermes_cmd_str} update > {shlex.quote(str(output_path))} 2>&1; "
f"status=$?; printf '%s' \"$status\" > {shlex.quote(str(exit_code_path))}"
)
try:
systemd_run = shutil.which("systemd-run")
if systemd_run:
setsid_bin = shutil.which("setsid")
if setsid_bin:
# Preferred: setsid creates a new session, fully detached
subprocess.Popen(
[systemd_run, "--user", "--scope",
"--unit=hermes-update", "--",
"bash", "-c", update_cmd],
[setsid_bin, "bash", "-c", update_cmd],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
start_new_session=True,
)
else:
# Fallback: best-effort detach with start_new_session
# Fallback: start_new_session=True calls os.setsid() in child
subprocess.Popen(
["bash", "-c", f"nohup {update_cmd} &"],
["bash", "-c", update_cmd],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
start_new_session=True,
@@ -4941,6 +5320,14 @@ class GatewayRunner:
from hermes_cli.tools_config import _get_platform_tools
enabled_toolsets = sorted(_get_platform_tools(user_config, platform_key))
# Apply tool preview length config (0 = no limit)
try:
from agent.display import set_tool_preview_max_len
_tpl = user_config.get("display", {}).get("tool_preview_length", 0)
set_tool_preview_max_len(int(_tpl) if _tpl else 0)
except Exception:
pass
# Tool progress mode from config.yaml: "all", "new", "verbose", "off"
# Falls back to env vars for backward compatibility.
# YAML 1.1 parses bare `off` as boolean False — normalise before
@@ -4986,9 +5373,11 @@ class GatewayRunner:
return
if preview:
# Truncate preview to keep messages clean
if len(preview) > 80:
preview = preview[:77] + "..."
# Truncate preview unless config says unlimited
from agent.display import get_tool_preview_max_len
_pl = get_tool_preview_max_len()
if _pl > 0 and len(preview) > _pl:
preview = preview[:_pl - 3] + "..."
msg = f"{emoji} {tool_name}: \"{preview}\""
else:
msg = f"{emoji} {tool_name}..."
@@ -5446,7 +5835,9 @@ class GatewayRunner:
# If so, update the session store entry so the NEXT message loads
# the compressed transcript, not the stale pre-compression one.
agent = agent_holder[0]
_session_was_split = False
if agent and session_key and hasattr(agent, 'session_id') and agent.session_id != session_id:
_session_was_split = True
logger.info(
"Session split detected: %s%s (compression)",
session_id, agent.session_id,
@@ -5458,6 +5849,13 @@ class GatewayRunner:
effective_session_id = getattr(agent, 'session_id', session_id) if agent else session_id
# When compression created a new session, the messages list was
# shortened. Using the original history offset would produce an
# empty new_messages slice, causing the gateway to write only a
# user/assistant pair — losing the compressed summary and tail.
# Reset to 0 so the gateway writes ALL compressed messages.
_effective_history_offset = 0 if _session_was_split else len(agent_history)
# Auto-generate session title after first exchange (non-blocking)
if final_response and self._session_db:
try:
@@ -5479,7 +5877,7 @@ class GatewayRunner:
"messages": result_holder[0].get("messages", []) if result_holder[0] else [],
"api_calls": result_holder[0].get("api_calls", 0) if result_holder[0] else 0,
"tools": tools_holder[0] or [],
"history_offset": len(agent_history),
"history_offset": _effective_history_offset,
"last_prompt_tokens": _last_prompt_toks,
"input_tokens": _input_toks,
"output_tokens": _output_toks,
+5 -6
View File
@@ -1,12 +1,11 @@
#!/usr/bin/env python3
"""
Hermes Agent CLI Launcher
Hermes Agent CLI launcher.
This is a convenience wrapper to launch the Hermes CLI.
Usage: ./hermes [options]
This wrapper should behave like the installed `hermes` command, including
subcommands such as `gateway`, `cron`, and `doctor`.
"""
if __name__ == "__main__":
from cli import main
import fire
fire.Fire(main)
from hermes_cli.main import main
main()
+2 -2
View File
@@ -11,5 +11,5 @@ Provides subcommands for:
- hermes cron - Manage cron jobs
"""
__version__ = "0.5.0"
__release_date__ = "2026.3.28"
__version__ = "0.6.0"
__release_date__ = "2026.3.30"
+17 -9
View File
@@ -160,7 +160,7 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
id="alibaba",
name="Alibaba Cloud (DashScope)",
auth_type="api_key",
inference_base_url="https://coding-intl.dashscope.aliyuncs.com/v1",
inference_base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
api_key_env_vars=("DASHSCOPE_API_KEY",),
base_url_env_var="DASHSCOPE_BASE_URL",
),
@@ -696,6 +696,10 @@ def resolve_provider(
"hf": "huggingface", "hugging-face": "huggingface", "huggingface-hub": "huggingface",
"go": "opencode-go", "opencode-go-sub": "opencode-go",
"kilo": "kilocode", "kilo-code": "kilocode", "kilo-gateway": "kilocode",
# Local server aliases — route through the generic custom provider
"lmstudio": "custom", "lm-studio": "custom", "lm_studio": "custom",
"ollama": "custom", "vllm": "custom", "llamacpp": "custom",
"llama.cpp": "custom", "llama-cpp": "custom",
}
normalized = _PROVIDER_ALIASES.get(normalized, normalized)
@@ -742,7 +746,12 @@ def resolve_provider(
if has_usable_secret(os.getenv(env_var, "")):
return pid
return "openrouter"
raise AuthError(
"No inference provider configured. Run 'hermes model' to choose a "
"provider and model, or set an API key (OPENROUTER_API_KEY, "
"OPENAI_API_KEY, etc.) in ~/.hermes/.env.",
code="no_provider_configured",
)
# =============================================================================
@@ -2301,21 +2310,20 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
raise AuthError("No runtime API key available to fetch models",
provider="nous", code="invalid_token")
model_ids = fetch_nous_models(
inference_base_url=runtime_base_url,
api_key=runtime_key,
timeout_seconds=timeout_seconds,
verify=verify,
)
# Use curated model list (same as OpenRouter defaults) instead
# of the full /models dump which returns hundreds of models.
from hermes_cli.models import _PROVIDER_MODELS
model_ids = _PROVIDER_MODELS.get("nous", [])
print()
if model_ids:
print(f"Showing {len(model_ids)} curated models — use \"Enter custom model name\" for others.")
selected_model = _prompt_model_selection(model_ids)
if selected_model:
_save_model_choice(selected_model)
print(f"Default model set to: {selected_model}")
else:
print("No models were returned by the inference API.")
print("No curated models available for Nous Portal.")
except Exception as exc:
message = format_auth_error(exc) if isinstance(exc, AuthError) else str(exc)
print()
+2 -1
View File
@@ -432,10 +432,11 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
try:
behind = get_update_result(timeout=0.5)
if behind and behind > 0:
from hermes_cli.config import recommended_update_command
commits_word = "commit" if behind == 1 else "commits"
right_lines.append(
f"[bold yellow]⚠ {behind} {commits_word} behind[/]"
f"[dim yellow] — run [bold]hermes update[/bold] to update[/]"
f"[dim yellow] — run [bold]{recommended_update_command()}[/bold] to update[/]"
)
except Exception:
pass # Never break the banner over an update check
+2 -1
View File
@@ -241,7 +241,8 @@ def approval_callback(cli, command: str, description: str) -> str:
lock = cli._approval_lock
with lock:
timeout = 60
from cli import CLI_CONFIG
timeout = CLI_CONFIG.get("approvals", {}).get("timeout", 60)
response_queue = queue.Queue()
choices = ["once", "session", "always", "deny"]
if len(command) > 70:
+5
View File
@@ -5,6 +5,7 @@ toggleable list of items. Falls back to a numbered text UI when
curses is unavailable (Windows without curses, piped stdin, etc.).
"""
import sys
from typing import List, Set
from hermes_cli.colors import Colors, color
@@ -26,6 +27,10 @@ def curses_checklist(
The indices the user confirmed as checked. On cancel (ESC/q),
returns ``pre_selected`` unchanged.
"""
# Safety: return defaults when stdin is not a terminal.
if not sys.stdin.isatty():
return set(pre_selected)
try:
import curses
selected = set(pre_selected)
+265 -5
View File
@@ -4,14 +4,19 @@ Usage:
hermes claw migrate # Interactive migration from ~/.openclaw
hermes claw migrate --dry-run # Preview what would be migrated
hermes claw migrate --preset full --overwrite # Full migration, overwrite conflicts
hermes claw cleanup # Archive leftover OpenClaw directories
hermes claw cleanup --dry-run # Preview what would be archived
"""
import importlib.util
import logging
import shutil
import sys
from datetime import datetime
from pathlib import Path
from hermes_cli.config import get_hermes_home, get_config_path, load_config, save_config
from hermes_constants import get_optional_skills_dir
from hermes_cli.setup import (
Colors,
color,
@@ -19,6 +24,7 @@ from hermes_cli.setup import (
print_info,
print_success,
print_error,
print_warning,
prompt_yes_no,
)
@@ -27,8 +33,7 @@ logger = logging.getLogger(__name__)
PROJECT_ROOT = Path(__file__).parent.parent.resolve()
_OPENCLAW_SCRIPT = (
PROJECT_ROOT
/ "optional-skills"
get_optional_skills_dir(PROJECT_ROOT / "optional-skills")
/ "migration"
/ "openclaw-migration"
/ "scripts"
@@ -45,6 +50,18 @@ _OPENCLAW_SCRIPT_INSTALLED = (
/ "openclaw_to_hermes.py"
)
# Known OpenClaw directory names (current + legacy)
_OPENCLAW_DIR_NAMES = (".openclaw", ".clawdbot", ".moldbot")
# State files commonly found in OpenClaw workspace directories that cause
# confusion after migration (the agent discovers them and writes to them)
_WORKSPACE_STATE_GLOBS = (
"*/todo.json",
"*/sessions/*",
"*/memory/*.json",
"*/logs/*",
)
def _find_migration_script() -> Path | None:
"""Find the openclaw_to_hermes.py script in known locations."""
@@ -71,24 +88,105 @@ def _load_migration_module(script_path: Path):
return mod
def _find_openclaw_dirs() -> list[Path]:
"""Find all OpenClaw directories on disk."""
found = []
for name in _OPENCLAW_DIR_NAMES:
candidate = Path.home() / name
if candidate.is_dir():
found.append(candidate)
return found
def _scan_workspace_state(source_dir: Path) -> list[tuple[Path, str]]:
"""Scan an OpenClaw directory for workspace state files that cause confusion.
Returns a list of (path, description) tuples.
"""
findings: list[tuple[Path, str]] = []
# Direct state files in the root
for name in ("todo.json", "sessions", "logs"):
candidate = source_dir / name
if candidate.exists():
kind = "directory" if candidate.is_dir() else "file"
findings.append((candidate, f"Root {kind}: {name}"))
# State files inside workspace directories
for child in sorted(source_dir.iterdir()):
if not child.is_dir() or child.name.startswith("."):
continue
# Check for workspace-like subdirectories
for state_name in ("todo.json", "sessions", "logs", "memory"):
state_path = child / state_name
if state_path.exists():
kind = "directory" if state_path.is_dir() else "file"
rel = state_path.relative_to(source_dir)
findings.append((state_path, f"Workspace {kind}: {rel}"))
return findings
def _archive_directory(source_dir: Path, dry_run: bool = False) -> Path:
"""Rename an OpenClaw directory to .pre-migration.
Returns the archive path.
"""
timestamp = datetime.now().strftime("%Y%m%d")
archive_name = f"{source_dir.name}.pre-migration"
archive_path = source_dir.parent / archive_name
# If archive already exists, add timestamp
if archive_path.exists():
archive_name = f"{source_dir.name}.pre-migration-{timestamp}"
archive_path = source_dir.parent / archive_name
# If still exists (multiple runs same day), add counter
counter = 2
while archive_path.exists():
archive_name = f"{source_dir.name}.pre-migration-{timestamp}-{counter}"
archive_path = source_dir.parent / archive_name
counter += 1
if not dry_run:
source_dir.rename(archive_path)
return archive_path
def claw_command(args):
"""Route hermes claw subcommands."""
action = getattr(args, "claw_action", None)
if action == "migrate":
_cmd_migrate(args)
elif action in ("cleanup", "clean"):
_cmd_cleanup(args)
else:
print("Usage: hermes claw migrate [options]")
print("Usage: hermes claw <command> [options]")
print()
print("Commands:")
print(" migrate Migrate settings from OpenClaw to Hermes")
print(" cleanup Archive leftover OpenClaw directories after migration")
print()
print("Run 'hermes claw migrate --help' for migration options.")
print("Run 'hermes claw <command> --help' for options.")
def _cmd_migrate(args):
"""Run the OpenClaw → Hermes migration."""
source_dir = Path(getattr(args, "source", None) or Path.home() / ".openclaw")
# Check current and legacy OpenClaw directories
explicit_source = getattr(args, "source", None)
if explicit_source:
source_dir = Path(explicit_source)
else:
source_dir = Path.home() / ".openclaw"
if not source_dir.is_dir():
# Try legacy directory names
for legacy in (".clawdbot", ".moldbot"):
candidate = Path.home() / legacy
if candidate.is_dir():
source_dir = candidate
break
dry_run = getattr(args, "dry_run", False)
preset = getattr(args, "preset", "full")
overwrite = getattr(args, "overwrite", False)
@@ -198,6 +296,168 @@ def _cmd_migrate(args):
# Print results
_print_migration_report(report, dry_run)
# After successful non-dry-run migration, offer to archive the source directory
if not dry_run and report.get("summary", {}).get("migrated", 0) > 0:
_offer_source_archival(source_dir, getattr(args, "yes", False))
def _offer_source_archival(source_dir: Path, auto_yes: bool = False):
"""After migration, offer to rename the source directory to prevent state fragmentation.
OpenClaw workspace directories contain state files (todo.json, sessions, etc.)
that the agent may discover and write to, causing confusion. Renaming the
directory prevents this.
"""
if not source_dir.is_dir():
return
# Scan for state files that could cause problems
state_files = _scan_workspace_state(source_dir)
print()
print_header("Post-Migration Cleanup")
print_info("The OpenClaw directory still exists and contains workspace state files")
print_info("that can confuse the agent (todo lists, sessions, logs).")
if state_files:
print()
print(color(" Found state files:", Colors.YELLOW))
# Show up to 10 most relevant findings
for path, desc in state_files[:10]:
print(f" {desc}")
if len(state_files) > 10:
print(f" ... and {len(state_files) - 10} more")
print()
print_info(f"Recommend: rename {source_dir.name}/ to {source_dir.name}.pre-migration/")
print_info("This prevents the agent from discovering old workspace directories.")
print_info("You can always rename it back if needed.")
print()
if auto_yes or prompt_yes_no(f"Archive {source_dir} now?", default=True):
try:
archive_path = _archive_directory(source_dir)
print_success(f"Archived: {source_dir}{archive_path}")
print_info("The original directory has been renamed, not deleted.")
print_info(f"To undo: mv {archive_path} {source_dir}")
except OSError as e:
print_error(f"Could not archive: {e}")
print_info(f"You can do it manually: mv {source_dir} {source_dir}.pre-migration")
else:
print_info("Skipped. You can archive later with: hermes claw cleanup")
def _cmd_cleanup(args):
"""Archive leftover OpenClaw directories after migration.
Scans for OpenClaw directories that still exist after migration and offers
to rename them to .pre-migration to prevent state fragmentation.
"""
dry_run = getattr(args, "dry_run", False)
auto_yes = getattr(args, "yes", False)
explicit_source = getattr(args, "source", None)
print()
print(
color(
"┌─────────────────────────────────────────────────────────┐",
Colors.MAGENTA,
)
)
print(
color(
"│ ⚕ Hermes — OpenClaw Cleanup │",
Colors.MAGENTA,
)
)
print(
color(
"└─────────────────────────────────────────────────────────┘",
Colors.MAGENTA,
)
)
# Find OpenClaw directories
if explicit_source:
dirs_to_check = [Path(explicit_source)]
else:
dirs_to_check = _find_openclaw_dirs()
if not dirs_to_check:
print()
print_success("No OpenClaw directories found. Nothing to clean up.")
return
total_archived = 0
for source_dir in dirs_to_check:
print()
print_header(f"Found: {source_dir}")
# Scan for state files
state_files = _scan_workspace_state(source_dir)
# Show directory stats
try:
workspace_dirs = [
d for d in source_dir.iterdir()
if d.is_dir() and not d.name.startswith(".")
and any((d / name).exists() for name in ("todo.json", "SOUL.md", "MEMORY.md", "USER.md"))
]
except OSError:
workspace_dirs = []
if workspace_dirs:
print_info(f"Workspace directories: {len(workspace_dirs)}")
for ws in workspace_dirs[:5]:
items = []
if (ws / "todo.json").exists():
items.append("todo.json")
if (ws / "sessions").is_dir():
items.append("sessions/")
if (ws / "SOUL.md").exists():
items.append("SOUL.md")
if (ws / "MEMORY.md").exists():
items.append("MEMORY.md")
detail = ", ".join(items) if items else "empty"
print(f" {ws.name}/ ({detail})")
if len(workspace_dirs) > 5:
print(f" ... and {len(workspace_dirs) - 5} more")
if state_files:
print()
print(color(f" {len(state_files)} state file(s) that could cause confusion:", Colors.YELLOW))
for path, desc in state_files[:8]:
print(f" {desc}")
if len(state_files) > 8:
print(f" ... and {len(state_files) - 8} more")
print()
if dry_run:
archive_path = _archive_directory(source_dir, dry_run=True)
print_info(f"Would archive: {source_dir}{archive_path}")
else:
if auto_yes or prompt_yes_no(f"Archive {source_dir}?", default=True):
try:
archive_path = _archive_directory(source_dir)
print_success(f"Archived: {source_dir}{archive_path}")
total_archived += 1
except OSError as e:
print_error(f"Could not archive: {e}")
print_info(f"Try manually: mv {source_dir} {source_dir}.pre-migration")
else:
print_info("Skipped.")
# Summary
print()
if dry_run:
print_info(f"Dry run complete. {len(dirs_to_check)} directory(ies) would be archived.")
print_info("Run without --dry-run to archive them.")
elif total_archived:
print_success(f"Cleaned up {total_archived} OpenClaw directory(ies).")
print_info("Directories were renamed, not deleted. You can undo by renaming them back.")
else:
print_info("No directories were archived.")
def _print_migration_report(report: dict, dry_run: bool):
"""Print a formatted migration report."""
+4 -1
View File
@@ -12,6 +12,8 @@ import os
logger = logging.getLogger(__name__)
DEFAULT_CODEX_MODELS: List[str] = [
"gpt-5.4-mini",
"gpt-5.4",
"gpt-5.3-codex",
"gpt-5.2-codex",
"gpt-5.1-codex-max",
@@ -19,8 +21,9 @@ DEFAULT_CODEX_MODELS: List[str] = [
]
_FORWARD_COMPAT_TEMPLATE_MODELS: List[tuple[str, tuple[str, ...]]] = [
("gpt-5.3-codex", ("gpt-5.2-codex",)),
("gpt-5.4-mini", ("gpt-5.3-codex", "gpt-5.2-codex")),
("gpt-5.4", ("gpt-5.3-codex", "gpt-5.2-codex")),
("gpt-5.3-codex", ("gpt-5.2-codex",)),
("gpt-5.3-codex-spark", ("gpt-5.3-codex", "gpt-5.2-codex")),
]
+18 -2
View File
@@ -1,8 +1,24 @@
"""Shared ANSI color utilities for Hermes CLI modules."""
import os
import sys
def should_use_color() -> bool:
"""Return True when colored output is appropriate.
Respects the NO_COLOR environment variable (https://no-color.org/)
and TERM=dumb, in addition to the existing TTY check.
"""
if os.environ.get("NO_COLOR") is not None:
return False
if os.environ.get("TERM") == "dumb":
return False
if not sys.stdout.isatty():
return False
return True
class Colors:
RESET = "\033[0m"
BOLD = "\033[1m"
@@ -16,7 +32,7 @@ class Colors:
def color(text: str, *codes) -> str:
"""Apply color codes to text (only when output is a TTY)."""
if not sys.stdout.isatty():
"""Apply color codes to text (only when color output is appropriate)."""
if not should_use_color():
return text
return "".join(codes) + text + Colors.RESET
+70
View File
@@ -67,10 +67,13 @@ COMMAND_REGISTRY: list[CommandDef] = [
gateway_only=True),
CommandDef("background", "Run a prompt in the background", "Session",
aliases=("bg",), args_hint="<prompt>"),
CommandDef("btw", "Ephemeral side question using session context (no tools, not persisted)", "Session",
args_hint="<question>"),
CommandDef("queue", "Queue a prompt for the next turn (doesn't interrupt)", "Session",
aliases=("q",), args_hint="<prompt>"),
CommandDef("status", "Show session info", "Session",
gateway_only=True),
CommandDef("profile", "Show active profile name and home directory", "Info"),
CommandDef("sethome", "Set this chat as the home channel", "Session",
gateway_only=True, aliases=("set-home",)),
CommandDef("resume", "Resume a previously-named session", "Session",
@@ -90,6 +93,8 @@ COMMAND_REGISTRY: list[CommandDef] = [
CommandDef("verbose", "Cycle tool progress display: off -> new -> all -> verbose",
"Configuration", cli_only=True,
gateway_config_gate="display.tool_progress_command"),
CommandDef("yolo", "Toggle YOLO mode (skip all dangerous command approvals)",
"Configuration"),
CommandDef("reasoning", "Manage reasoning effort and display", "Configuration",
args_hint="[level|show|hide]",
subcommands=("none", "low", "minimal", "medium", "high", "xhigh", "show", "hide", "on", "off")),
@@ -118,6 +123,8 @@ COMMAND_REGISTRY: list[CommandDef] = [
"Tools & Skills", cli_only=True),
# Info
CommandDef("commands", "Browse all commands and skills (paginated)", "Info",
gateway_only=True, args_hint="[page]"),
CommandDef("help", "Show available commands", "Info"),
CommandDef("usage", "Show token usage for the current session", "Info"),
CommandDef("insights", "Show usage insights and analytics", "Info",
@@ -361,6 +368,69 @@ def telegram_bot_commands() -> list[tuple[str, str]]:
return result
def telegram_menu_commands(max_commands: int = 100) -> tuple[list[tuple[str, str]], int]:
"""Return Telegram menu commands capped to the Bot API limit.
Priority order (higher priority = never bumped by overflow):
1. Core CommandDef commands (always included)
2. Plugin slash commands (take precedence over skills)
3. Built-in skill commands (fill remaining slots, alphabetical)
Skills are the only tier that gets trimmed when the cap is hit.
User-installed hub skills are excluded accessible via /skills.
Returns:
(menu_commands, hidden_count) where hidden_count is the number of
skill commands omitted due to the cap.
"""
all_commands = list(telegram_bot_commands())
# Plugin slash commands get priority over skills
try:
from hermes_cli.plugins import get_plugin_manager
pm = get_plugin_manager()
plugin_cmds = getattr(pm, "_plugin_commands", {})
for cmd_name in sorted(plugin_cmds):
tg_name = cmd_name.replace("-", "_")
desc = "Plugin command"
if len(desc) > 40:
desc = desc[:37] + "..."
all_commands.append((tg_name, desc))
except Exception:
pass
# Remaining slots go to built-in skill commands (not hub-installed).
skill_entries: list[tuple[str, str]] = []
try:
from agent.skill_commands import get_skill_commands
from tools.skills_tool import SKILLS_DIR
_skills_dir = str(SKILLS_DIR.resolve())
_hub_dir = str((SKILLS_DIR / ".hub").resolve())
skill_cmds = get_skill_commands()
for cmd_key in sorted(skill_cmds):
info = skill_cmds[cmd_key]
skill_path = info.get("skill_md_path", "")
if not skill_path.startswith(_skills_dir):
continue
if skill_path.startswith(_hub_dir):
continue
name = cmd_key.lstrip("/").replace("-", "_")
desc = info.get("description", "")
# Keep descriptions short — setMyCommands has an undocumented
# total payload limit. 40 chars fits 100 commands safely.
if len(desc) > 40:
desc = desc[:37] + "..."
skill_entries.append((name, desc))
except Exception:
pass
# Skills fill remaining slots — they're the only tier that gets trimmed
remaining_slots = max(0, max_commands - len(all_commands))
hidden_count = max(0, len(skill_entries) - remaining_slots)
all_commands.extend(skill_entries[:remaining_slots])
return all_commands[:max_commands], hidden_count
def slack_subcommand_map() -> dict[str, str]:
"""Return subcommand -> /command mapping for Slack /hermes handler.
+86 -12
View File
@@ -34,6 +34,8 @@ _EXTRA_ENV_KEYS = frozenset({
"SIGNAL_ACCOUNT", "SIGNAL_HTTP_URL",
"SIGNAL_ALLOWED_USERS", "SIGNAL_GROUP_ALLOWED_USERS",
"DINGTALK_CLIENT_ID", "DINGTALK_CLIENT_SECRET",
"FEISHU_APP_ID", "FEISHU_APP_SECRET", "FEISHU_ENCRYPT_KEY", "FEISHU_VERIFICATION_TOKEN",
"WECOM_BOT_ID", "WECOM_SECRET",
"TERMINAL_ENV", "TERMINAL_SSH_KEY", "TERMINAL_SSH_PORT",
"WHATSAPP_MODE", "WHATSAPP_ENABLED",
"MATTERMOST_HOME_CHANNEL", "MATTERMOST_REPLY_MODE",
@@ -50,26 +52,86 @@ from hermes_cli.default_soul import DEFAULT_SOUL_MD
# Managed mode (NixOS declarative config)
# =============================================================================
_MANAGED_TRUE_VALUES = ("true", "1", "yes")
_MANAGED_SYSTEM_NAMES = {
"brew": "Homebrew",
"homebrew": "Homebrew",
"nix": "NixOS",
"nixos": "NixOS",
}
def get_managed_system() -> Optional[str]:
"""Return the package manager owning this install, if any."""
raw = os.getenv("HERMES_MANAGED", "").strip()
if raw:
normalized = raw.lower()
if normalized in _MANAGED_TRUE_VALUES:
return "NixOS"
return _MANAGED_SYSTEM_NAMES.get(normalized, raw)
managed_marker = get_hermes_home() / ".managed"
if managed_marker.exists():
return "NixOS"
return None
def is_managed() -> bool:
"""Check if hermes is running in Nix-managed mode.
"""Check if Hermes is running in package-manager-managed mode.
Two signals: the HERMES_MANAGED env var (set by the systemd service),
or a .managed marker file in HERMES_HOME (set by the NixOS activation
script, so interactive shells also see it).
"""
if os.getenv("HERMES_MANAGED", "").lower() in ("true", "1", "yes"):
return True
managed_marker = get_hermes_home() / ".managed"
return managed_marker.exists()
return get_managed_system() is not None
def get_managed_update_command() -> Optional[str]:
"""Return the preferred upgrade command for a managed install."""
managed_system = get_managed_system()
if managed_system == "Homebrew":
return "brew upgrade hermes-agent"
if managed_system == "NixOS":
return "sudo nixos-rebuild switch"
return None
def recommended_update_command() -> str:
"""Return the best update command for the current installation."""
return get_managed_update_command() or "hermes update"
def format_managed_message(action: str = "modify this Hermes installation") -> str:
"""Build a user-facing error for managed installs."""
managed_system = get_managed_system() or "a package manager"
raw = os.getenv("HERMES_MANAGED", "").strip().lower()
if managed_system == "NixOS":
env_hint = "true" if raw in _MANAGED_TRUE_VALUES else raw or "true"
return (
f"Cannot {action}: this Hermes installation is managed by NixOS "
f"(HERMES_MANAGED={env_hint}).\n"
"Edit services.hermes-agent.settings in your configuration.nix and run:\n"
" sudo nixos-rebuild switch"
)
if managed_system == "Homebrew":
env_hint = raw or "homebrew"
return (
f"Cannot {action}: this Hermes installation is managed by Homebrew "
f"(HERMES_MANAGED={env_hint}).\n"
"Use:\n"
" brew upgrade hermes-agent"
)
return (
f"Cannot {action}: this Hermes installation is managed by {managed_system}.\n"
"Use your package manager to upgrade or reinstall Hermes."
)
def managed_error(action: str = "modify configuration"):
"""Print user-friendly error for managed mode."""
print(
f"Cannot {action}: configuration is managed by NixOS (HERMES_MANAGED=true).\n"
"Edit services.hermes-agent.settings in your configuration.nix and run:\n"
" sudo nixos-rebuild switch",
file=sys.stderr,
)
print(format_managed_message(action), file=sys.stderr)
# =============================================================================
@@ -221,7 +283,8 @@ DEFAULT_CONFIG = {
"model": "", # e.g. "google/gemini-2.5-flash", "gpt-4o"
"base_url": "", # direct OpenAI-compatible endpoint (takes precedence over provider)
"api_key": "", # API key for base_url (falls back to OPENAI_API_KEY)
"timeout": 30, # seconds — increase for slow local vision models
"timeout": 30, # seconds — LLM API call timeout; increase for slow local vision models
"download_timeout": 30, # seconds — image HTTP download timeout; increase for slow connections
},
"web_extract": {
"provider": "auto",
@@ -285,6 +348,7 @@ DEFAULT_CONFIG = {
"show_cost": False, # Show $ cost in the status bar (off by default)
"skin": "default",
"tool_progress_command": False, # Enable /verbose command in messaging gateway
"tool_preview_length": 0, # Max chars for tool call previews (0 = no limit, show full paths/commands)
},
# Privacy settings
@@ -388,6 +452,7 @@ DEFAULT_CONFIG = {
"require_mention": True, # Require @mention to respond in server channels
"free_response_channels": "", # Comma-separated channel IDs where bot responds without mention
"auto_thread": True, # Auto-create threads on @mention in channels (like Slack)
"reactions": True, # Add 👀/✅/❌ reactions to messages during processing
},
# WhatsApp platform settings (gateway mode)
@@ -404,6 +469,7 @@ DEFAULT_CONFIG = {
# off — skip all approval prompts (equivalent to --yolo)
"approvals": {
"mode": "manual",
"timeout": 60,
},
# Permanently allowed dangerous command patterns (added via "always" approval)
@@ -701,6 +767,14 @@ OPTIONAL_ENV_VARS = {
"password": True,
"category": "tool",
},
"CAMOFOX_URL": {
"description": "Camofox browser server URL for local anti-detection browsing (e.g. http://localhost:9377)",
"prompt": "Camofox server URL",
"url": "https://github.com/jo-inc/camofox-browser",
"tools": ["browser_navigate", "browser_click"],
"password": False,
"category": "tool",
},
"FAL_KEY": {
"description": "FAL API key for image generation",
"prompt": "FAL API key",
+1 -1
View File
@@ -56,7 +56,7 @@ def cron_list(show_all: bool = False):
print()
for job in jobs:
job_id = job.get("id", "?")[:8]
job_id = job.get("id", "?")
name = job.get("name", "(unnamed)")
schedule = job.get("schedule_display", job.get("schedule", {}).get("value", "?"))
state = job.get("state", "scheduled" if job.get("enabled", True) else "paused")
+6
View File
@@ -4,6 +4,7 @@ Used by `hermes tools` and `hermes skills` for interactive checklists.
Provides a curses multi-select with keyboard navigation, plus a
text-based numbered fallback for terminals without curses support.
"""
import sys
from typing import Callable, List, Optional, Set
from hermes_cli.colors import Colors, color
@@ -31,6 +32,11 @@ def curses_checklist(
if cancel_returns is None:
cancel_returns = set(selected)
# Safety: curses and input() both hang or spin when stdin is not a
# terminal (e.g. subprocess pipe). Return defaults immediately.
if not sys.stdin.isatty():
return cancel_returns
try:
import curses
chosen = set(selected)
+15 -8
View File
@@ -406,8 +406,11 @@ def run_doctor(args):
if terminal_env == "docker":
if shutil.which("docker"):
# Check if docker daemon is running
result = subprocess.run(["docker", "info"], capture_output=True)
if result.returncode == 0:
try:
result = subprocess.run(["docker", "info"], capture_output=True, timeout=10)
except subprocess.TimeoutExpired:
result = None
if result is not None and result.returncode == 0:
check_ok("docker", "(daemon running)")
else:
check_fail("docker daemon not running")
@@ -426,12 +429,16 @@ def run_doctor(args):
ssh_host = os.getenv("TERMINAL_SSH_HOST")
if ssh_host:
# Try to connect
result = subprocess.run(
["ssh", "-o", "ConnectTimeout=5", "-o", "BatchMode=yes", ssh_host, "echo ok"],
capture_output=True,
text=True
)
if result.returncode == 0:
try:
result = subprocess.run(
["ssh", "-o", "ConnectTimeout=5", "-o", "BatchMode=yes", ssh_host, "echo ok"],
capture_output=True,
text=True,
timeout=15
)
except subprocess.TimeoutExpired:
result = None
if result is not None and result.returncode == 0:
check_ok(f"SSH connection to {ssh_host}")
else:
check_fail(f"SSH connection to {ssh_host}")
+53
View File
@@ -1322,6 +1322,59 @@ _PLATFORMS = [
"help": "The AppSecret from your DingTalk application credentials."},
],
},
{
"key": "feishu",
"label": "Feishu / Lark",
"emoji": "🪽",
"token_var": "FEISHU_APP_ID",
"setup_instructions": [
"1. Go to https://open.feishu.cn/ (or https://open.larksuite.com/ for Lark)",
"2. Create an app and copy the App ID and App Secret",
"3. Enable the Bot capability for the app",
"4. Choose WebSocket (recommended) or Webhook connection mode",
"5. Add the bot to a group chat or message it directly",
"6. Restrict access with FEISHU_ALLOWED_USERS for production use",
],
"vars": [
{"name": "FEISHU_APP_ID", "prompt": "App ID", "password": False,
"help": "The App ID from your Feishu/Lark application."},
{"name": "FEISHU_APP_SECRET", "prompt": "App Secret", "password": True,
"help": "The App Secret from your Feishu/Lark application."},
{"name": "FEISHU_DOMAIN", "prompt": "Domain — feishu or lark (default: feishu)", "password": False,
"help": "Use 'feishu' for Feishu China, or 'lark' for Lark international."},
{"name": "FEISHU_CONNECTION_MODE", "prompt": "Connection mode — websocket or webhook (default: websocket)", "password": False,
"help": "websocket is recommended unless you specifically need webhook mode."},
{"name": "FEISHU_ALLOWED_USERS", "prompt": "Allowed user IDs (comma-separated, or empty)", "password": False,
"is_allowlist": True,
"help": "Restrict which Feishu/Lark users can interact with the bot."},
{"name": "FEISHU_HOME_CHANNEL", "prompt": "Home chat ID (optional, for cron/notifications)", "password": False,
"help": "Chat ID for scheduled results and notifications."},
],
},
{
"key": "wecom",
"label": "WeCom (Enterprise WeChat)",
"emoji": "💬",
"token_var": "WECOM_BOT_ID",
"setup_instructions": [
"1. Go to WeCom Admin Console → Applications → Create AI Bot",
"2. Copy the Bot ID and Secret from the bot's credentials page",
"3. The bot connects via WebSocket — no public endpoint needed",
"4. Add the bot to a group chat or message it directly in WeCom",
"5. Restrict access with WECOM_ALLOWED_USERS for production use",
],
"vars": [
{"name": "WECOM_BOT_ID", "prompt": "Bot ID", "password": False,
"help": "The Bot ID from your WeCom AI Bot."},
{"name": "WECOM_SECRET", "prompt": "Secret", "password": True,
"help": "The secret from your WeCom AI Bot."},
{"name": "WECOM_ALLOWED_USERS", "prompt": "Allowed user IDs (comma-separated, or empty)", "password": False,
"is_allowlist": True,
"help": "Restrict which WeCom users can interact with the bot."},
{"name": "WECOM_HOME_CHANNEL", "prompt": "Home chat ID (optional, for cron/notifications)", "password": False,
"help": "Chat ID for scheduled results and notifications."},
],
},
]
+144 -61
View File
@@ -50,6 +50,23 @@ import sys
from pathlib import Path
from typing import Optional
def _require_tty(command_name: str) -> None:
"""Exit with a clear error if stdin is not a terminal.
Interactive TUI commands (hermes tools, hermes setup, hermes model) use
curses or input() prompts that spin at 100% CPU when stdin is a pipe.
This guard prevents accidental non-interactive invocation.
"""
if not sys.stdin.isatty():
print(
f"Error: 'hermes {command_name}' requires an interactive terminal.\n"
f"It cannot be run through a pipe or non-interactive subprocess.\n"
f"Run it directly in your terminal instead.",
file=sys.stderr,
)
sys.exit(1)
# Add project root to path
PROJECT_ROOT = Path(__file__).parent.parent.resolve()
sys.path.insert(0, str(PROJECT_ROOT))
@@ -617,6 +634,7 @@ def cmd_gateway(args):
def cmd_whatsapp(args):
"""Set up WhatsApp: choose mode, configure, install bridge, pair via QR."""
_require_tty("whatsapp")
import subprocess
from pathlib import Path
from hermes_cli.config import get_env_value, save_env_value
@@ -803,12 +821,25 @@ def cmd_whatsapp(args):
def cmd_setup(args):
"""Interactive setup wizard."""
_require_tty("setup")
from hermes_cli.setup import run_setup_wizard
run_setup_wizard(args)
def cmd_model(args):
"""Select default model — starts with provider selection, then model picker."""
_require_tty("model")
select_provider_and_model()
def select_provider_and_model():
"""Core provider selection + model picking logic.
Shared by ``cmd_model`` (``hermes model``) and the setup wizard
(``setup_model_provider`` in setup.py). Handles the full flow:
provider picker, credential prompting, model selection, and config
persistence.
"""
from hermes_cli.auth import (
resolve_provider, AuthError, format_auth_error,
)
@@ -838,7 +869,10 @@ def cmd_model(args):
except AuthError as exc:
warning = format_auth_error(exc)
print(f"Warning: {warning} Falling back to auto provider detection.")
active = resolve_provider("auto")
try:
active = resolve_provider("auto")
except AuthError:
active = "openrouter" # no provider yet; show full picker
# Detect custom endpoint
if active == "openrouter" and get_env_value("OPENAI_BASE_URL"):
@@ -1030,10 +1064,6 @@ def _model_flow_openrouter(config, current_model=""):
selected = _prompt_model_selection(openrouter_models, current_model=current_model)
if selected:
# Clear any custom endpoint and set provider to openrouter
if get_env_value("OPENAI_BASE_URL"):
save_env_value("OPENAI_BASE_URL", "")
save_env_value("OPENAI_API_KEY", "")
_save_model_choice(selected)
# Update config provider and deactivate any OAuth provider
@@ -1084,14 +1114,20 @@ def _model_flow_nous(config, current_model=""):
# login_nous already handles model selection + config update
return
# Already logged in — fetch models and select
print("Fetching models from Nous Portal...")
# Already logged in — use curated model list (same as OpenRouter defaults).
# The live /models endpoint returns hundreds of models; the curated list
# shows only agentic models users recognize from OpenRouter.
from hermes_cli.models import _PROVIDER_MODELS
model_ids = _PROVIDER_MODELS.get("nous", [])
if not model_ids:
print("No curated models available for Nous Portal.")
return
print(f"Showing {len(model_ids)} curated models — use \"Enter custom model name\" for others.")
# Verify credentials are still valid (catches expired sessions early)
try:
creds = resolve_nous_runtime_credentials(min_key_ttl_seconds=5 * 60)
model_ids = fetch_nous_models(
inference_base_url=creds.get("base_url", ""),
api_key=creds.get("api_key", ""),
)
except Exception as exc:
relogin = isinstance(exc, AuthError) and exc.relogin_required
msg = format_auth_error(exc) if isinstance(exc, AuthError) else str(exc)
@@ -1108,11 +1144,7 @@ def _model_flow_nous(config, current_model=""):
except Exception as login_exc:
print(f"Re-login failed: {login_exc}")
return
print(f"Could not fetch models: {msg}")
return
if not model_ids:
print("No models returned by the inference API.")
print(f"Could not verify credentials: {msg}")
return
selected = _prompt_model_selection(model_ids, current_model=current_model)
@@ -1121,10 +1153,6 @@ def _model_flow_nous(config, current_model=""):
# Reactivate Nous as the provider and update config
inference_url = creds.get("base_url", "")
_update_config_for_provider("nous", inference_url)
# Clear any custom endpoint that might conflict
if get_env_value("OPENAI_BASE_URL"):
save_env_value("OPENAI_BASE_URL", "")
save_env_value("OPENAI_API_KEY", "")
print(f"Default model set to: {selected} (via Nous Portal)")
else:
print("No change.")
@@ -1169,10 +1197,6 @@ def _model_flow_openai_codex(config, current_model=""):
if selected:
_save_model_choice(selected)
_update_config_for_provider("openai-codex", DEFAULT_CODEX_BASE_URL)
# Clear custom endpoint env vars that would otherwise override Codex.
if get_env_value("OPENAI_BASE_URL"):
save_env_value("OPENAI_BASE_URL", "")
save_env_value("OPENAI_API_KEY", "")
print(f"Default model set to: {selected} (via OpenAI Codex)")
else:
print("No change.")
@@ -1253,11 +1277,6 @@ def _model_flow_custom(config):
if probe.get("suggested_base_url"):
print(f" If this server expects /v1, try base URL: {probe['suggested_base_url']}")
if base_url:
save_env_value("OPENAI_BASE_URL", effective_url)
if api_key:
save_env_value("OPENAI_API_KEY", api_key)
if model_name:
_save_model_choice(model_name)
@@ -1269,14 +1288,33 @@ def _model_flow_custom(config):
cfg["model"] = model
model["provider"] = "custom"
model["base_url"] = effective_url
model["api_mode"] = "chat_completions"
if effective_key:
model["api_key"] = effective_key
model.pop("api_mode", None) # let runtime auto-detect from URL
save_config(cfg)
deactivate_provider()
# Sync the caller's config dict so the setup wizard's final
# save_config(config) preserves our model settings. Without
# this, the wizard overwrites model.provider/base_url with
# the stale values from its own config dict (#4172).
config["model"] = dict(model)
print(f"Default model set to: {model_name} (via {effective_url})")
else:
if base_url or api_key:
deactivate_provider()
# Even without a model name, persist the custom endpoint on the
# caller's config dict so the setup wizard doesn't lose it.
_caller_model = config.get("model")
if not isinstance(_caller_model, dict):
_caller_model = {"default": _caller_model} if _caller_model else {}
_caller_model["provider"] = "custom"
_caller_model["base_url"] = effective_url
if effective_key:
_caller_model["api_key"] = effective_key
_caller_model.pop("api_mode", None)
config["model"] = _caller_model
print("Endpoint saved. Use `/model` in chat or `hermes model` to set a model.")
# Auto-save to custom_providers so it appears in the menu next time
@@ -1417,9 +1455,6 @@ def _model_flow_named_custom(config, provider_info):
# If a model is saved, just activate immediately — no probing needed
if saved_model:
save_env_value("OPENAI_BASE_URL", base_url)
if api_key:
save_env_value("OPENAI_API_KEY", api_key)
_save_model_choice(saved_model)
cfg = load_config()
@@ -1429,6 +1464,8 @@ def _model_flow_named_custom(config, provider_info):
cfg["model"] = model
model["provider"] = "custom"
model["base_url"] = base_url
if api_key:
model["api_key"] = api_key
save_config(cfg)
deactivate_provider()
@@ -1491,9 +1528,6 @@ def _model_flow_named_custom(config, provider_info):
return
# Activate and save the model to the custom_providers entry
save_env_value("OPENAI_BASE_URL", base_url)
if api_key:
save_env_value("OPENAI_API_KEY", api_key)
_save_model_choice(model_name)
cfg = load_config()
@@ -1503,6 +1537,8 @@ def _model_flow_named_custom(config, provider_info):
cfg["model"] = model
model["provider"] = "custom"
model["base_url"] = base_url
if api_key:
model["api_key"] = api_key
save_config(cfg)
deactivate_provider()
@@ -1555,11 +1591,15 @@ _PROVIDER_MODELS = {
"kimi-k2-0905-preview",
],
"minimax": [
"MiniMax-M2.7",
"MiniMax-M2.7-highspeed",
"MiniMax-M2.5",
"MiniMax-M2.5-highspeed",
"MiniMax-M2.1",
],
"minimax-cn": [
"MiniMax-M2.7",
"MiniMax-M2.7-highspeed",
"MiniMax-M2.5",
"MiniMax-M2.5-highspeed",
"MiniMax-M2.1",
@@ -1807,11 +1847,6 @@ def _model_flow_copilot(config, current_model=""):
catalog=catalog,
api_key=api_key,
) or selected
# Clear stale custom-endpoint overrides so the Copilot provider wins cleanly.
if get_env_value("OPENAI_BASE_URL"):
save_env_value("OPENAI_BASE_URL", "")
save_env_value("OPENAI_API_KEY", "")
initial_cfg = load_config()
current_effort = _current_reasoning_effort(initial_cfg)
reasoning_efforts = github_model_reasoning_efforts(
@@ -2036,11 +2071,6 @@ def _model_flow_kimi(config, current_model=""):
selected = None
if selected:
# Clear custom endpoint if set (avoid confusion)
if get_env_value("OPENAI_BASE_URL"):
save_env_value("OPENAI_BASE_URL", "")
save_env_value("OPENAI_API_KEY", "")
_save_model_choice(selected)
# Update config with provider and base URL
@@ -2051,7 +2081,7 @@ def _model_flow_kimi(config, current_model=""):
cfg["model"] = model
model["provider"] = provider_id
model["base_url"] = effective_base
model["api_mode"] = "chat_completions"
model.pop("api_mode", None) # let runtime auto-detect from URL
save_config(cfg)
deactivate_provider()
@@ -2125,7 +2155,7 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
api_key_for_probe = existing_key or (get_env_value(key_env) if key_env else "")
live_models = fetch_api_models(api_key_for_probe, effective_base)
if live_models:
if live_models and len(live_models) >= len(curated):
model_list = live_models
print(f" Found {len(model_list)} model(s) from {pconfig.name} API")
else:
@@ -2143,11 +2173,6 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
selected = None
if selected:
# Clear custom endpoint if set (avoid confusion)
if get_env_value("OPENAI_BASE_URL"):
save_env_value("OPENAI_BASE_URL", "")
save_env_value("OPENAI_API_KEY", "")
_save_model_choice(selected)
# Update config with provider and base URL
@@ -2158,7 +2183,7 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
cfg["model"] = model
model["provider"] = provider_id
model["base_url"] = effective_base
model["api_mode"] = "chat_completions"
model.pop("api_mode", None) # let runtime auto-detect from URL
save_config(cfg)
deactivate_provider()
@@ -2359,11 +2384,6 @@ def _model_flow_anthropic(config, current_model=""):
selected = None
if selected:
# Clear custom endpoint if set
if get_env_value("OPENAI_BASE_URL"):
save_env_value("OPENAI_BASE_URL", "")
save_env_value("OPENAI_API_KEY", "")
_save_model_choice(selected)
# Update config with provider — clear base_url since
@@ -2445,10 +2465,14 @@ def cmd_version(args):
# Show update status (synchronous — acceptable since user asked for version info)
try:
from hermes_cli.banner import check_for_updates
from hermes_cli.config import recommended_update_command
behind = check_for_updates()
if behind and behind > 0:
commits_word = "commit" if behind == 1 else "commits"
print(f"Update available: {behind} {commits_word} behind — run 'hermes update'")
print(
f"Update available: {behind} {commits_word} behind — "
f"run '{recommended_update_command()}'"
)
elif behind == 0:
print("Up to date")
except Exception:
@@ -2457,6 +2481,7 @@ def cmd_version(args):
def cmd_uninstall(args):
"""Uninstall Hermes Agent."""
_require_tty("uninstall")
from hermes_cli.uninstall import run_uninstall
run_uninstall(args)
@@ -2798,6 +2823,11 @@ def _invalidate_update_cache():
def cmd_update(args):
"""Update Hermes Agent to the latest version."""
import shutil
from hermes_cli.config import is_managed, managed_error
if is_managed():
managed_error("update Hermes Agent")
return
print("⚕ Updating Hermes Agent...")
print()
@@ -3133,6 +3163,7 @@ def cmd_update(args):
_gw_service_name = get_service_name()
existing_pid = get_running_pid()
has_systemd_service = False
has_system_service = False
has_launchd_service = False
try:
@@ -3145,6 +3176,19 @@ def cmd_update(args):
except (FileNotFoundError, subprocess.TimeoutExpired):
pass
# Also check for a system-level service (hermes gateway install --system).
# This covers gateways running under system systemd where --user
# fails due to missing D-Bus session.
if not has_systemd_service and is_linux():
try:
check = subprocess.run(
["systemctl", "is-active", _gw_service_name],
capture_output=True, text=True, timeout=5,
)
has_system_service = check.stdout.strip() == "active"
except (FileNotFoundError, subprocess.TimeoutExpired):
pass
# Check for macOS launchd service
if is_macos():
try:
@@ -3159,7 +3203,7 @@ def cmd_update(args):
except (FileNotFoundError, subprocess.TimeoutExpired):
pass
if existing_pid or has_systemd_service or has_launchd_service:
if existing_pid or has_systemd_service or has_system_service or has_launchd_service:
print()
# When a service manager is handling the gateway, let it
@@ -3200,6 +3244,21 @@ def cmd_update(args):
print(" hermes gateway restart")
else:
print(" Try manually: hermes gateway restart")
elif has_system_service:
# System-level service (hermes gateway install --system).
# No D-Bus session needed — systemctl without --user talks
# directly to the system manager over /run/systemd/private.
print("→ Restarting system gateway service...")
restart = subprocess.run(
["systemctl", "restart", _gw_service_name],
capture_output=True, text=True, timeout=15,
)
if restart.returncode == 0:
print("✓ Gateway restarted (system service).")
else:
print(f"⚠ Gateway restart failed: {restart.stderr.strip()}")
print(" System services may require root. Try:")
print(f" sudo systemctl restart {_gw_service_name}")
elif has_launchd_service:
# Refresh the plist first (picks up --replace and other
# changes from the update we just pulled).
@@ -4129,6 +4188,7 @@ For more help on a command:
def cmd_skills(args):
# Route 'config' action to skills_config module
if getattr(args, 'skills_action', None) == 'config':
_require_tty("skills config")
from hermes_cli.skills_config import skills_command as skills_config_command
skills_config_command(args)
else:
@@ -4339,6 +4399,7 @@ For more help on a command:
from hermes_cli.tools_config import tools_disable_enable_command
tools_disable_enable_command(args)
else:
_require_tty("tools")
from hermes_cli.tools_config import tools_command
tools_command(args)
@@ -4678,6 +4739,28 @@ For more help on a command:
help="Skip confirmation prompts"
)
# claw cleanup
claw_cleanup = claw_subparsers.add_parser(
"cleanup",
aliases=["clean"],
help="Archive leftover OpenClaw directories after migration",
description="Scan for and archive leftover OpenClaw directories to prevent state fragmentation"
)
claw_cleanup.add_argument(
"--source",
help="Path to a specific OpenClaw directory to clean up"
)
claw_cleanup.add_argument(
"--dry-run",
action="store_true",
help="Preview what would be archived without making changes"
)
claw_cleanup.add_argument(
"--yes", "-y",
action="store_true",
help="Skip confirmation prompts"
)
def cmd_claw(args):
from hermes_cli.claw import claw_command
claw_command(args)
+4
View File
@@ -511,6 +511,10 @@ def _interpolate_value(value: str) -> str:
def cmd_mcp_configure(args):
"""Reconfigure which tools are enabled for an existing MCP server."""
import sys as _sys
if not _sys.stdin.isatty():
print("Error: 'hermes mcp configure' requires an interactive terminal.", file=_sys.stderr)
_sys.exit(1)
name = args.name
servers = _get_mcp_servers()
+4 -2
View File
@@ -27,6 +27,7 @@ GITHUB_MODELS_CATALOG_URL = COPILOT_MODELS_URL
# (model_id, display description shown in menus)
OPENROUTER_MODELS: list[tuple[str, str]] = [
("anthropic/claude-opus-4.6", "recommended"),
("anthropic/claude-sonnet-4.6", ""),
("anthropic/claude-sonnet-4.5", ""),
("anthropic/claude-haiku-4.5", ""),
("openai/gpt-5.4", ""),
@@ -56,6 +57,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
_PROVIDER_MODELS: dict[str, list[str]] = {
"nous": [
"anthropic/claude-opus-4.6",
"anthropic/claude-sonnet-4.6",
"anthropic/claude-sonnet-4.5",
"anthropic/claude-haiku-4.5",
"openai/gpt-5.4",
@@ -189,7 +191,7 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
"opencode-go": [
"glm-5",
"kimi-k2.5",
"minimax-m2.5",
"minimax-m2.7",
],
"ai-gateway": [
"anthropic/claude-opus-4.6",
@@ -347,7 +349,7 @@ def list_available_providers() -> list[dict[str, str]]:
try:
from hermes_cli.auth import get_auth_status, has_usable_secret
if pid == "custom":
custom_base_url = _get_custom_base_url() or os.getenv("OPENAI_BASE_URL", "")
custom_base_url = _get_custom_base_url() or ""
has_creds = bool(custom_base_url.strip())
elif pid == "openrouter":
has_creds = has_usable_secret(os.getenv("OPENROUTER_API_KEY", ""))
+29
View File
@@ -152,6 +152,34 @@ class PluginContext:
self._manager._plugin_tool_names.add(name)
logger.debug("Plugin %s registered tool: %s", self.manifest.name, name)
# -- message injection --------------------------------------------------
def inject_message(self, content: str, role: str = "user") -> bool:
"""Inject a message into the active conversation.
If the agent is idle (waiting for user input), this starts a new turn.
If the agent is running, this interrupts and injects the message.
This enables plugins (e.g. remote control viewers, messaging bridges)
to send messages into the conversation from external sources.
Returns True if the message was queued successfully.
"""
cli = self._manager._cli_ref
if cli is None:
logger.warning("inject_message: no CLI reference (not available in gateway mode)")
return False
msg = content if role == "user" else f"[{role}] {content}"
if getattr(cli, "_agent_running", False):
# Agent is mid-turn — interrupt with the message
cli._interrupt_queue.put(msg)
else:
# Agent is idle — queue as next input
cli._pending_input.put(msg)
return True
# -- hook registration --------------------------------------------------
def register_hook(self, hook_name: str, callback: Callable) -> None:
@@ -184,6 +212,7 @@ class PluginManager:
self._hooks: Dict[str, List[Callable]] = {}
self._plugin_tool_names: Set[str] = set()
self._discovered: bool = False
self._cli_ref = None # Set by CLI after plugin discovery
# -----------------------------------------------------------------------
# Public
+2 -1
View File
@@ -265,10 +265,11 @@ def cmd_install(identifier: str, force: bool = False) -> None:
)
sys.exit(1)
if mv_int > _SUPPORTED_MANIFEST_VERSION:
from hermes_cli.config import recommended_update_command
console.print(
f"[red]Error:[/red] Plugin '{plugin_name}' requires manifest_version "
f"{mv}, but this installer only supports up to {_SUPPORTED_MANIFEST_VERSION}.\n"
f"Run [bold]hermes update[/bold] to get a newer installer."
f"Run [bold]{recommended_update_command()}[/bold] to get a newer installer."
)
sys.exit(1)
+1 -1
View File
@@ -241,7 +241,7 @@ def _read_config_model(profile_dir: Path) -> tuple:
if isinstance(model_cfg, str):
return model_cfg, None
if isinstance(model_cfg, dict):
return model_cfg.get("model"), model_cfg.get("provider")
return model_cfg.get("default") or model_cfg.get("model"), model_cfg.get("provider")
return None, None
except Exception:
return None, None
+4 -10
View File
@@ -229,28 +229,22 @@ def _resolve_openrouter_runtime(
requested_norm = (requested_provider or "").strip().lower()
cfg_provider = cfg_provider.strip().lower()
env_openai_base_url = os.getenv("OPENAI_BASE_URL", "").strip()
env_openrouter_base_url = os.getenv("OPENROUTER_BASE_URL", "").strip()
# Use config base_url when available and the provider context matches.
# OPENAI_BASE_URL env var is no longer consulted — config.yaml is
# the single source of truth for endpoint URLs.
use_config_base_url = False
if cfg_base_url.strip() and not explicit_base_url:
if requested_norm == "auto":
if (not cfg_provider or cfg_provider == "auto") and not env_openai_base_url:
if not cfg_provider or cfg_provider == "auto":
use_config_base_url = True
elif requested_norm == "custom" and cfg_provider == "custom":
# provider: custom — use base_url from config (Fixes #1760).
use_config_base_url = True
# When the user explicitly requested the openrouter provider, skip
# OPENAI_BASE_URL — it typically points to a custom / non-OpenRouter
# endpoint and would prevent switching back to OpenRouter (#874).
skip_openai_base = requested_norm == "openrouter"
# For custom, prefer config base_url over env so config.yaml is honored (#1760).
base_url = (
(explicit_base_url or "").strip()
or (cfg_base_url.strip() if use_config_base_url else "")
or ("" if skip_openai_base else env_openai_base_url)
or env_openrouter_base_url
or OPENROUTER_BASE_URL
).rstrip("/")
+75 -915
View File
File diff suppressed because it is too large Load Diff
+2
View File
@@ -28,6 +28,8 @@ PLATFORMS = {
"mattermost": "💬 Mattermost",
"matrix": "💬 Matrix",
"dingtalk": "💬 DingTalk",
"feishu": "🪽 Feishu",
"wecom": "💬 WeCom",
}
# ─── Config Helpers ───────────────────────────────────────────────────────────
+17 -2
View File
@@ -354,7 +354,14 @@ def do_install(identifier: str, category: str = "", force: bool = False,
extra_metadata.update(getattr(bundle, "metadata", {}) or {})
# Quarantine the bundle
q_path = quarantine_bundle(bundle)
try:
q_path = quarantine_bundle(bundle)
except ValueError as exc:
c.print(f"[bold red]Installation blocked:[/] {exc}\n")
from tools.skills_hub import append_audit_log
append_audit_log("BLOCKED", bundle.name, bundle.source,
bundle.trust_level, "invalid_path", str(exc))
return
c.print(f"[dim]Quarantined to {q_path.relative_to(q_path.parent.parent.parent)}[/]")
# Scan
@@ -414,7 +421,15 @@ def do_install(identifier: str, category: str = "", force: bool = False,
return
# Install
install_dir = install_from_quarantine(q_path, bundle.name, category, bundle, result)
try:
install_dir = install_from_quarantine(q_path, bundle.name, category, bundle, result)
except ValueError as exc:
c.print(f"[bold red]Installation blocked:[/] {exc}\n")
shutil.rmtree(q_path, ignore_errors=True)
from tools.skills_hub import append_audit_log
append_audit_log("BLOCKED", bundle.name, bundle.source,
bundle.trust_level, "invalid_path", str(exc))
return
from tools.skills_hub import SKILLS_DIR
c.print(f"[bold green]Installed:[/] {install_dir.relative_to(SKILLS_DIR)}")
c.print(f"[dim]Files: {', '.join(bundle.files.keys())}[/]\n")
+23 -12
View File
@@ -254,6 +254,9 @@ def show_status(args):
"Slack": ("SLACK_BOT_TOKEN", None),
"Email": ("EMAIL_ADDRESS", "EMAIL_HOME_ADDRESS"),
"SMS": ("TWILIO_ACCOUNT_SID", "SMS_HOME_CHANNEL"),
"DingTalk": ("DINGTALK_CLIENT_ID", None),
"Feishu": ("FEISHU_APP_ID", "FEISHU_HOME_CHANNEL"),
"WeCom": ("WECOM_BOT_ID", "WECOM_HOME_CHANNEL"),
}
for name, (token_var, home_var) in platforms.items():
@@ -282,23 +285,31 @@ def show_status(args):
_gw_svc = get_service_name()
except Exception:
_gw_svc = "hermes-gateway"
result = subprocess.run(
["systemctl", "--user", "is-active", _gw_svc],
capture_output=True,
text=True
)
is_active = result.stdout.strip() == "active"
try:
result = subprocess.run(
["systemctl", "--user", "is-active", _gw_svc],
capture_output=True,
text=True,
timeout=5
)
is_active = result.stdout.strip() == "active"
except subprocess.TimeoutExpired:
is_active = False
print(f" Status: {check_mark(is_active)} {'running' if is_active else 'stopped'}")
print(" Manager: systemd (user)")
elif sys.platform == 'darwin':
from hermes_cli.gateway import get_launchd_label
result = subprocess.run(
["launchctl", "list", get_launchd_label()],
capture_output=True,
text=True
)
is_loaded = result.returncode == 0
try:
result = subprocess.run(
["launchctl", "list", get_launchd_label()],
capture_output=True,
text=True,
timeout=5
)
is_loaded = result.returncode == 0
except subprocess.TimeoutExpired:
is_loaded = False
print(f" Status: {check_mark(is_loaded)} {'loaded' if is_loaded else 'not loaded'}")
print(" Manager: launchd")
else:
+44 -3
View File
@@ -140,7 +140,9 @@ PLATFORMS = {
"homeassistant": {"label": "🏠 Home Assistant", "default_toolset": "hermes-homeassistant"},
"email": {"label": "📧 Email", "default_toolset": "hermes-email"},
"matrix": {"label": "💬 Matrix", "default_toolset": "hermes-matrix"},
"dingtalk": {"label": "💬 DingTalk", "default_toolset": "hermes-dingtalk"},
"dingtalk": {"label": "💬 DingTalk", "default_toolset": "hermes-dingtalk"},
"feishu": {"label": "🪽 Feishu", "default_toolset": "hermes-feishu"},
"wecom": {"label": "💬 WeCom", "default_toolset": "hermes-wecom"},
"api_server": {"label": "🌐 API Server", "default_toolset": "hermes-api-server"},
"mattermost": {"label": "💬 Mattermost", "default_toolset": "hermes-mattermost"},
}
@@ -271,6 +273,16 @@ TOOL_CATEGORIES = {
"browser_provider": "browser-use",
"post_setup": "browserbase",
},
{
"name": "Camofox",
"tag": "Local anti-detection browser (Firefox/Camoufox)",
"env_vars": [
{"key": "CAMOFOX_URL", "prompt": "Camofox server URL", "default": "http://localhost:9377",
"url": "https://github.com/jo-inc/camofox-browser"},
],
"browser_provider": "camofox",
"post_setup": "camofox",
},
],
},
"homeassistant": {
@@ -335,6 +347,28 @@ def _run_post_setup(post_setup_key: str):
elif not node_modules.exists():
_print_warning(" Node.js not found - browser tools require: npm install (in hermes-agent directory)")
elif post_setup_key == "camofox":
camofox_dir = PROJECT_ROOT / "node_modules" / "@askjo" / "camoufox-browser"
if not camofox_dir.exists() and shutil.which("npm"):
_print_info(" Installing Camofox browser server...")
import subprocess
result = subprocess.run(
["npm", "install", "--silent"],
capture_output=True, text=True, cwd=str(PROJECT_ROOT)
)
if result.returncode == 0:
_print_success(" Camofox installed")
else:
_print_warning(" npm install failed - run manually: npm install")
if camofox_dir.exists():
_print_info(" Start the Camofox server:")
_print_info(" npx @askjo/camoufox-browser")
_print_info(" First run downloads the Camoufox engine (~300MB)")
_print_info(" Or use Docker: docker run -p 9377:9377 jo-inc/camofox-browser")
elif not shutil.which("npm"):
_print_warning(" Node.js not found. Install Camofox via Docker:")
_print_info(" docker run -p 9377:9377 jo-inc/camofox-browser")
elif post_setup_key == "rl_training":
try:
__import__("tinker_atropos")
@@ -563,7 +597,9 @@ def _toolset_has_keys(ts_key: str) -> bool:
if cat:
for provider in cat.get("providers", []):
env_vars = provider.get("env_vars", [])
if env_vars and all(get_env_value(e["key"]) for e in env_vars):
if not env_vars:
return True # No-key provider (e.g. Local Browser, Edge TTS)
if all(get_env_value(e["key"]) for e in env_vars):
return True
return False
@@ -947,8 +983,13 @@ def _configure_simple_requirements(ts_key: str):
key_label = " OPENAI_API_KEY" if "api.openai.com" in base_url.lower() else " API key"
api_key = _prompt(key_label, password=True)
if api_key and api_key.strip():
save_env_value("OPENAI_BASE_URL", base_url)
save_env_value("OPENAI_API_KEY", api_key.strip())
# Save vision base URL to config (not .env — only secrets go there)
from hermes_cli.config import load_config, save_config
_cfg = load_config()
_aux = _cfg.setdefault("auxiliary", {}).setdefault("vision", {})
_aux["base_url"] = base_url
save_config(_cfg)
if "api.openai.com" in base_url.lower():
save_env_value("AUXILIARY_VISION_MODEL", "gpt-4o-mini")
_print_success(" Saved")
+14
View File
@@ -17,6 +17,20 @@ def get_hermes_home() -> Path:
return Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))
def get_optional_skills_dir(default: Path | None = None) -> Path:
"""Return the optional-skills directory, honoring package-manager wrappers.
Packaged installs may ship ``optional-skills`` outside the Python package
tree and expose it via ``HERMES_OPTIONAL_SKILLS``.
"""
override = os.getenv("HERMES_OPTIONAL_SKILLS", "").strip()
if override:
return Path(override)
if default is not None:
return default
return get_hermes_home() / "optional-skills"
def get_hermes_dir(new_subpath: str, old_name: str) -> Path:
"""Resolve a Hermes subdirectory with backward compatibility.
+22 -8
View File
@@ -10,16 +10,27 @@ import os
import sys
from pathlib import Path
from hermes_constants import get_hermes_home
from honcho_integration.client import resolve_config_path, GLOBAL_CONFIG_PATH
HOST = "hermes"
def _config_path() -> Path:
"""Return the active Honcho config path (instance-local or global)."""
"""Return the active Honcho config path for reading (instance-local or global)."""
return resolve_config_path()
def _local_config_path() -> Path:
"""Return the instance-local Honcho config path for writing.
Always returns $HERMES_HOME/honcho.json so each profile/instance gets
its own config file. The global ~/.honcho/config.json is only used as
a read fallback (via resolve_config_path) for cross-app interop.
"""
return get_hermes_home() / "honcho.json"
def _read_config() -> dict:
path = _config_path()
if path.exists():
@@ -31,7 +42,7 @@ def _read_config() -> dict:
def _write_config(cfg: dict, path: Path | None = None) -> None:
path = path or _config_path()
path = path or _local_config_path()
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text(
json.dumps(cfg, indent=2, ensure_ascii=False) + "\n",
@@ -95,13 +106,13 @@ def cmd_setup(args) -> None:
"""Interactive Honcho setup wizard."""
cfg = _read_config()
active_path = _config_path()
write_path = _local_config_path()
read_path = _config_path()
print("\nHoncho memory setup\n" + "" * 40)
print(" Honcho gives Hermes persistent cross-session memory.")
if active_path != GLOBAL_CONFIG_PATH:
print(f" Instance config: {active_path}")
else:
print(" Config is shared with other hosts at ~/.honcho/config.json")
print(f" Config: {write_path}")
if read_path != write_path and read_path.exists():
print(f" (seeding from existing config at {read_path})")
print()
if not _ensure_sdk_installed():
@@ -189,7 +200,7 @@ def cmd_setup(args) -> None:
hermes_host.setdefault("saveMessages", True)
_write_config(cfg)
print(f"\n Config written to {active_path}")
print(f"\n Config written to {write_path}")
# Test connection
print(" Testing connection... ", end="", flush=True)
@@ -237,6 +248,7 @@ def cmd_status(args) -> None:
cfg = _read_config()
active_path = _config_path()
write_path = _local_config_path()
if not cfg:
print(f" No Honcho config found at {active_path}")
@@ -259,6 +271,8 @@ def cmd_status(args) -> None:
print(f" Workspace: {hcfg.workspace_id}")
print(f" Host: {hcfg.host}")
print(f" Config path: {active_path}")
if write_path != active_path:
print(f" Write path: {write_path} (instance-local)")
print(f" AI peer: {hcfg.ai_peer}")
print(f" User peer: {hcfg.peer_name or 'not set'}")
print(f" Session key: {hcfg.resolve_session_name()}")
+1 -1
View File
@@ -252,7 +252,7 @@ def get_tool_definitions(
# Determine which tool names the caller wants
tools_to_include: set = set()
if enabled_toolsets:
if enabled_toolsets is not None:
for toolset_name in enabled_toolsets:
if validate_toolset(toolset_name):
resolved = resolve_toolset(toolset_name)
@@ -304,6 +304,29 @@ def ensure_parent(path: Path) -> None:
path.parent.mkdir(parents=True, exist_ok=True)
def resolve_secret_input(value: Any, env: Optional[Dict[str, str]] = None) -> Optional[str]:
"""Resolve an OpenClaw SecretInput value to a plain string.
SecretInput can be:
- A plain string: "sk-..."
- An env template: "${OPENROUTER_API_KEY}"
- A SecretRef object: {"source": "env", "id": "OPENROUTER_API_KEY"}
"""
if isinstance(value, str):
# Check for env template: "${VAR_NAME}"
m = re.match(r"^\$\{(\w+)\}$", value.strip())
if m and env:
return env.get(m.group(1), "").strip() or None
return value.strip() or None
if isinstance(value, dict):
source = value.get("source", "")
ref_id = value.get("id", "")
if source == "env" and ref_id and env:
return env.get(ref_id, "").strip() or None
# File/exec sources can't be resolved here — return None
return None
def load_yaml_file(path: Path) -> Dict[str, Any]:
if yaml is None or not path.exists():
return {}
@@ -890,14 +913,20 @@ class Migrator:
self.record("command-allowlist", source, destination, "migrated", "Would merge patterns", added_patterns=added)
def load_openclaw_config(self) -> Dict[str, Any]:
config_path = self.source_root / "openclaw.json"
if not config_path.exists():
return {}
try:
data = json.loads(config_path.read_text(encoding="utf-8"))
return data if isinstance(data, dict) else {}
except json.JSONDecodeError:
return {}
# Check current name and legacy config filenames
for name in ("openclaw.json", "clawdbot.json", "moldbot.json"):
config_path = self.source_root / name
if config_path.exists():
try:
data = json.loads(config_path.read_text(encoding="utf-8"))
return data if isinstance(data, dict) else {}
except json.JSONDecodeError:
continue
return {}
def load_openclaw_env(self) -> Dict[str, str]:
"""Load the OpenClaw .env file for secrets that live there instead of config."""
return parse_env_file(self.source_root / ".env")
def merge_env_values(self, additions: Dict[str, str], kind: str, source: Path) -> None:
destination = self.target_root / ".env"
@@ -1024,6 +1053,10 @@ class Migrator:
supported_targets=sorted(SUPPORTED_SECRET_TARGETS),
)
def _resolve_channel_secret(self, value: Any) -> Optional[str]:
"""Resolve a channel config value that may be a SecretRef."""
return resolve_secret_input(value, self.load_openclaw_env())
def migrate_discord_settings(self, config: Optional[Dict[str, Any]] = None) -> None:
config = config or self.load_openclaw_config()
additions: Dict[str, str] = {}
@@ -1118,15 +1151,17 @@ class Migrator:
secret_additions: Dict[str, str] = {}
# Extract provider API keys from models.providers
# Note: apiKey values can be strings, env templates, or SecretRef objects
openclaw_env = self.load_openclaw_env()
providers = config.get("models", {}).get("providers", {})
if isinstance(providers, dict):
for provider_name, provider_cfg in providers.items():
if not isinstance(provider_cfg, dict):
continue
api_key = provider_cfg.get("apiKey")
if not isinstance(api_key, str) or not api_key.strip():
raw_key = provider_cfg.get("apiKey")
api_key = resolve_secret_input(raw_key, openclaw_env)
if not api_key:
continue
api_key = api_key.strip()
base_url = provider_cfg.get("baseUrl", "")
api_type = provider_cfg.get("api", "")
@@ -1170,6 +1205,50 @@ class Migrator:
if isinstance(oai_key, str) and oai_key.strip():
secret_additions["VOICE_TOOLS_OPENAI_KEY"] = oai_key.strip()
# Also check the OpenClaw .env file — many users store keys there
# instead of inline in openclaw.json
openclaw_env = self.load_openclaw_env()
env_key_mapping = {
"OPENROUTER_API_KEY": "OPENROUTER_API_KEY",
"OPENAI_API_KEY": "OPENAI_API_KEY",
"ANTHROPIC_API_KEY": "ANTHROPIC_API_KEY",
"ELEVENLABS_API_KEY": "ELEVENLABS_API_KEY",
"TELEGRAM_BOT_TOKEN": "TELEGRAM_BOT_TOKEN",
"DEEPSEEK_API_KEY": "DEEPSEEK_API_KEY",
"GEMINI_API_KEY": "GEMINI_API_KEY",
"ZAI_API_KEY": "ZAI_API_KEY",
"MINIMAX_API_KEY": "MINIMAX_API_KEY",
}
for oc_key, hermes_key in env_key_mapping.items():
val = openclaw_env.get(oc_key, "").strip()
if val and hermes_key not in secret_additions:
secret_additions[hermes_key] = val
# Check per-agent auth-profiles.json for additional credentials
auth_profiles_path = self.source_root / "agents" / "main" / "agent" / "auth-profiles.json"
if auth_profiles_path.exists():
try:
profiles = json.loads(auth_profiles_path.read_text(encoding="utf-8"))
if isinstance(profiles, dict):
# auth-profiles.json wraps profiles in a "profiles" key
profile_entries = profiles.get("profiles", profiles) if isinstance(profiles.get("profiles"), dict) else profiles
for profile_name, profile_data in profile_entries.items():
if not isinstance(profile_data, dict):
continue
# Canonical field is "key", "apiKey" is accepted as alias
api_key = profile_data.get("key", "") or profile_data.get("apiKey", "")
if not isinstance(api_key, str) or not api_key.strip():
continue
name_lower = profile_name.lower()
if "openrouter" in name_lower and "OPENROUTER_API_KEY" not in secret_additions:
secret_additions["OPENROUTER_API_KEY"] = api_key.strip()
elif "openai" in name_lower and "OPENAI_API_KEY" not in secret_additions:
secret_additions["OPENAI_API_KEY"] = api_key.strip()
elif "anthropic" in name_lower and "ANTHROPIC_API_KEY" not in secret_additions:
secret_additions["ANTHROPIC_API_KEY"] = api_key.strip()
except (json.JSONDecodeError, OSError):
pass
if secret_additions:
self.merge_env_values(secret_additions, "provider-keys", self.source_root / "openclaw.json")
else:
@@ -1218,7 +1297,11 @@ class Migrator:
if self.execute:
backup_path = self.maybe_backup(destination)
hermes_config["model"] = model_str
existing_model = hermes_config.get("model")
if isinstance(existing_model, dict):
existing_model["default"] = model_str
else:
hermes_config["model"] = {"default": model_str}
dump_yaml_file(destination, hermes_config)
self.record("model-config", source_path, destination, "migrated", backup=str(backup_path) if backup_path else "", model=model_str)
else:
@@ -1244,22 +1327,44 @@ class Migrator:
if isinstance(provider, str) and provider in ("elevenlabs", "openai", "edge"):
tts_data["provider"] = provider
elevenlabs = tts.get("elevenlabs", {})
# TTS provider settings live under messages.tts.providers.{provider}
# in OpenClaw (not messages.tts.elevenlabs directly)
providers = tts.get("providers") or {}
# Also check the top-level "talk" config which has provider settings too
talk_cfg = (config or self.load_openclaw_config()).get("talk") or {}
talk_providers = talk_cfg.get("providers") or {}
# Merge: messages.tts.providers takes priority, then talk.providers,
# then legacy flat keys (messages.tts.elevenlabs, etc.)
elevenlabs = (
(providers.get("elevenlabs") or {})
if isinstance(providers.get("elevenlabs"), dict) else
(talk_providers.get("elevenlabs") or {})
if isinstance(talk_providers.get("elevenlabs"), dict) else
(tts.get("elevenlabs") or {})
)
if isinstance(elevenlabs, dict):
el_settings: Dict[str, str] = {}
voice_id = elevenlabs.get("voiceId")
voice_id = elevenlabs.get("voiceId") or talk_cfg.get("voiceId")
if isinstance(voice_id, str) and voice_id.strip():
el_settings["voice_id"] = voice_id.strip()
model_id = elevenlabs.get("modelId")
model_id = elevenlabs.get("modelId") or talk_cfg.get("modelId")
if isinstance(model_id, str) and model_id.strip():
el_settings["model_id"] = model_id.strip()
if el_settings:
tts_data["elevenlabs"] = el_settings
openai_tts = tts.get("openai", {})
openai_tts = (
(providers.get("openai") or {})
if isinstance(providers.get("openai"), dict) else
(talk_providers.get("openai") or {})
if isinstance(talk_providers.get("openai"), dict) else
(tts.get("openai") or {})
)
if isinstance(openai_tts, dict):
oai_settings: Dict[str, str] = {}
oai_model = openai_tts.get("model")
oai_model = openai_tts.get("model") or openai_tts.get("modelId")
if isinstance(oai_model, str) and oai_model.strip():
oai_settings["model"] = oai_model.strip()
oai_voice = openai_tts.get("voice")
@@ -1268,7 +1373,11 @@ class Migrator:
if oai_settings:
tts_data["openai"] = oai_settings
edge_tts = tts.get("edge", {})
edge_tts = (
(providers.get("edge") or {})
if isinstance(providers.get("edge"), dict) else
(tts.get("edge") or {})
)
if isinstance(edge_tts, dict):
edge_voice = edge_tts.get("voice")
if isinstance(edge_voice, str) and edge_voice.strip():
@@ -1298,15 +1407,29 @@ class Migrator:
self.record("tts-config", source_path, destination, "migrated", "Would set TTS config", settings=list(tts_data.keys()))
def migrate_shared_skills(self) -> None:
source_root = self.source_root / "skills"
# Check all OpenClaw skill sources: managed, personal, project-level
skill_sources = [
(self.source_root / "skills", "shared-skills", "managed skills"),
(Path.home() / ".agents" / "skills", "personal-skills", "personal cross-project skills"),
(self.source_root / "workspace" / ".agents" / "skills", "project-skills", "project-level shared skills"),
(self.source_root / "workspace.default" / ".agents" / "skills", "project-skills", "project-level shared skills"),
]
found_any = False
for source_root, kind_label, desc in skill_sources:
if source_root.exists():
found_any = True
self._import_skill_directory(source_root, kind_label, desc)
if not found_any:
destination_root = self.target_root / "skills" / SKILL_CATEGORY_DIRNAME
self.record("shared-skills", None, destination_root, "skipped", "No shared OpenClaw skills directories found")
def _import_skill_directory(self, source_root: Path, kind_label: str, desc: str) -> None:
"""Import skills from a single source directory into openclaw-imports."""
destination_root = self.target_root / "skills" / SKILL_CATEGORY_DIRNAME
if not source_root.exists():
self.record("shared-skills", None, destination_root, "skipped", "No shared OpenClaw skills directory found")
return
skill_dirs = [p for p in sorted(source_root.iterdir()) if p.is_dir() and (p / "SKILL.md").exists()]
if not skill_dirs:
self.record("shared-skills", source_root, destination_root, "skipped", "No shared skills with SKILL.md found")
self.record(kind_label, source_root, destination_root, "skipped", f"No skills with SKILL.md found in {desc}")
return
for skill_dir in skill_dirs:
@@ -1314,7 +1437,7 @@ class Migrator:
final_destination = destination
if destination.exists():
if self.skill_conflict_mode == "skip":
self.record("shared-skill", skill_dir, destination, "conflict", "Destination skill already exists")
self.record(kind_label, skill_dir, destination, "conflict", "Destination skill already exists")
continue
if self.skill_conflict_mode == "rename":
final_destination = self.resolve_skill_destination(destination)
@@ -1329,19 +1452,19 @@ class Migrator:
details: Dict[str, Any] = {"backup": str(backup_path) if backup_path else ""}
if final_destination != destination:
details["renamed_from"] = str(destination)
self.record("shared-skill", skill_dir, final_destination, "migrated", **details)
self.record(kind_label, skill_dir, final_destination, "migrated", **details)
else:
if final_destination != destination:
self.record(
"shared-skill",
kind_label,
skill_dir,
final_destination,
"migrated",
"Would copy shared skill directory under a renamed folder",
f"Would copy {desc} directory under a renamed folder",
renamed_from=str(destination),
)
else:
self.record("shared-skill", skill_dir, final_destination, "migrated", "Would copy shared skill directory")
self.record(kind_label, skill_dir, final_destination, "migrated", f"Would copy {desc} directory")
desc_path = destination_root / "DESCRIPTION.md"
if self.execute:
@@ -1518,6 +1641,7 @@ class Migrator:
self.source_candidate("workspace/IDENTITY.md", "workspace.default/IDENTITY.md"),
self.source_candidate("workspace/TOOLS.md", "workspace.default/TOOLS.md"),
self.source_candidate("workspace/HEARTBEAT.md", "workspace.default/HEARTBEAT.md"),
self.source_candidate("workspace/BOOTSTRAP.md", "workspace.default/BOOTSTRAP.md"),
]
for candidate in candidates:
if candidate:
@@ -1789,8 +1913,9 @@ class Migrator:
human_delay = defaults.get("humanDelay") or {}
if human_delay:
hd = hermes_cfg.get("human_delay") or {}
if human_delay.get("enabled"):
hd["mode"] = "natural"
hd_mode = human_delay.get("mode") or ("natural" if human_delay.get("enabled") else None)
if hd_mode and hd_mode != "off":
hd["mode"] = hd_mode
if human_delay.get("minMs"):
hd["min_ms"] = human_delay["minMs"]
if human_delay.get("maxMs"):
@@ -1804,11 +1929,11 @@ class Migrator:
changes = True
# Map terminal/exec settings
exec_cfg = defaults.get("exec") or (config.get("tools") or {}).get("exec") or {}
exec_cfg = (config.get("tools") or {}).get("exec") or {}
if exec_cfg:
terminal_cfg = hermes_cfg.get("terminal") or {}
if exec_cfg.get("timeout"):
terminal_cfg["timeout"] = exec_cfg["timeout"]
if exec_cfg.get("timeoutSec") or exec_cfg.get("timeout"):
terminal_cfg["timeout"] = exec_cfg.get("timeoutSec") or exec_cfg.get("timeout")
changes = True
hermes_cfg["terminal"] = terminal_cfg
@@ -1883,24 +2008,34 @@ class Migrator:
sr = hermes_cfg.get("session_reset") or {}
changes = False
reset_triggers = session.get("resetTriggers") or session.get("reset_triggers") or {}
if reset_triggers:
daily = reset_triggers.get("daily") or {}
idle = reset_triggers.get("idle") or {}
# OpenClaw uses session.reset (structured) and session.resetTriggers (string array)
reset = session.get("reset") or {}
reset_triggers = session.get("resetTriggers") or session.get("reset_triggers") or []
if daily.get("enabled") and idle.get("enabled"):
sr["mode"] = "both"
elif daily.get("enabled"):
if reset:
# Structured reset config: has mode, atHour, idleMinutes
mode = reset.get("mode", "")
if mode == "daily":
sr["mode"] = "daily"
elif idle.get("enabled"):
elif mode == "idle":
sr["mode"] = "idle"
else:
sr["mode"] = "none"
if daily.get("hour") is not None:
sr["at_hour"] = daily["hour"]
if idle.get("minutes") or idle.get("timeoutMinutes"):
sr["idle_minutes"] = idle.get("minutes") or idle.get("timeoutMinutes")
sr["mode"] = mode or "none"
if reset.get("atHour") is not None:
sr["at_hour"] = reset["atHour"]
if reset.get("idleMinutes"):
sr["idle_minutes"] = reset["idleMinutes"]
changes = True
elif isinstance(reset_triggers, list) and reset_triggers:
# Simple string triggers: ["daily", "idle"]
has_daily = "daily" in reset_triggers
has_idle = "idle" in reset_triggers
if has_daily and has_idle:
sr["mode"] = "both"
elif has_daily:
sr["mode"] = "daily"
elif has_idle:
sr["mode"] = "idle"
changes = True
if changes:
@@ -2092,11 +2227,12 @@ class Migrator:
browser_hermes = hermes_cfg.get("browser") or {}
changed = False
if browser.get("inactivityTimeoutMs"):
browser_hermes["inactivity_timeout"] = browser["inactivityTimeoutMs"] // 1000
# Map fields that have Hermes equivalents
if browser.get("cdpUrl"):
browser_hermes["cdp_url"] = browser["cdpUrl"]
changed = True
if browser.get("commandTimeoutMs"):
browser_hermes["command_timeout"] = browser["commandTimeoutMs"] // 1000
if browser.get("headless") is not None:
browser_hermes["headless"] = browser["headless"]
changed = True
if changed:
@@ -2107,9 +2243,9 @@ class Migrator:
self.record("browser-config", "openclaw.json browser.*", "config.yaml browser",
"migrated")
# Archive advanced browser settings
# Archive remaining browser settings
advanced = {k: v for k, v in browser.items()
if k not in ("inactivityTimeoutMs", "commandTimeoutMs") and v}
if k not in ("cdpUrl", "headless") and v}
if advanced and self.archive_dir:
if self.execute:
self.archive_dir.mkdir(parents=True, exist_ok=True)
@@ -2130,18 +2266,22 @@ class Migrator:
hermes_cfg = load_yaml_file(hermes_cfg_path)
changed = False
# Map exec timeout -> terminal timeout
# Map exec timeout -> terminal timeout (field is timeoutSec in OpenClaw)
exec_cfg = tools.get("exec") or {}
if exec_cfg.get("timeout"):
timeout_val = exec_cfg.get("timeoutSec") or exec_cfg.get("timeout")
if timeout_val:
terminal_cfg = hermes_cfg.get("terminal") or {}
terminal_cfg["timeout"] = exec_cfg["timeout"]
terminal_cfg["timeout"] = timeout_val
hermes_cfg["terminal"] = terminal_cfg
changed = True
# Map web search API key
web_cfg = tools.get("webSearch") or tools.get("web") or {}
if web_cfg.get("braveApiKey") and self.migrate_secrets:
self._set_env_var("BRAVE_API_KEY", web_cfg["braveApiKey"], "tools.webSearch.braveApiKey")
# Map web search API key (path: tools.web.search.brave.apiKey in OpenClaw)
web_cfg = tools.get("web") or tools.get("webSearch") or {}
search_cfg = web_cfg.get("search") or web_cfg if not web_cfg.get("search") else web_cfg["search"]
brave_cfg = search_cfg.get("brave") or {}
brave_key = brave_cfg.get("apiKey") or search_cfg.get("braveApiKey") or web_cfg.get("braveApiKey")
if brave_key and isinstance(brave_key, str) and self.migrate_secrets:
self._set_env_var("BRAVE_API_KEY", brave_key, "tools.web.search.brave.apiKey")
if changed and self.execute:
self.maybe_backup(hermes_cfg_path)
@@ -2169,8 +2309,9 @@ class Migrator:
hermes_cfg_path = self.target_root / "config.yaml"
hermes_cfg = load_yaml_file(hermes_cfg_path)
# Map approval mode
mode = approvals.get("mode") or approvals.get("defaultMode")
# Map approval mode (nested under approvals.exec.mode in OpenClaw)
exec_approvals = approvals.get("exec") or {}
mode = (exec_approvals.get("mode") if isinstance(exec_approvals, dict) else None) or approvals.get("mode") or approvals.get("defaultMode")
if mode:
mode_map = {"auto": "off", "always": "manual", "smart": "smart", "manual": "manual"}
hermes_mode = mode_map.get(mode, "manual")
@@ -2314,9 +2455,24 @@ class Migrator:
notes.append("")
notes.extend([
"## IMPORTANT: Archive the OpenClaw Directory",
"",
"After migration, your OpenClaw directory still exists on disk with workspace",
"state files (todo.json, sessions, logs). If the Hermes agent discovers these",
"directories, it may read/write to them instead of the Hermes state, causing",
"confusion (e.g., cron jobs reading a different todo list than interactive sessions).",
"",
"**Strongly recommended:** Run `hermes claw cleanup` to rename the OpenClaw",
"directory to `.openclaw.pre-migration`. This prevents the agent from finding it.",
"The directory is renamed, not deleted — you can undo this at any time.",
"",
"If you skip this step and notice the agent getting confused about workspaces",
"or todo lists, run `hermes claw cleanup` to fix it.",
"",
"## Hermes-Specific Setup",
"",
"After migration, you may want to:",
"- Run `hermes claw cleanup` to archive the OpenClaw directory (prevents state confusion)",
"- Run `hermes setup` to configure any remaining settings",
"- Run `hermes mcp list` to verify MCP servers were imported correctly",
"- Run `hermes cron` to recreate scheduled tasks (see archive/cron-config.json)",

Some files were not shown because too many files have changed in this diff Show More