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.
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.
* 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>
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.
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>
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
* 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>
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>
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>
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>
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).
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
* 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>
- 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()
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>
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.
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>
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>
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>
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>
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.
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
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.
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>
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.
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.
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>
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>
* feat(skills): add memento-flashcards skill
* docs(skills): clarify memento-flashcards interaction model
* fix: use HERMES_HOME env var for profile-safe data path
---------
Co-authored-by: Magnus Ahmad <magnus.ahmad@gmail.com>
Adds a config option to suppress the header/footer text that wraps
cron job responses when delivered to messaging platforms.
Set cron.wrap_response: false in config.yaml for clean output without
the 'Cronjob Response: <name>' header and 'The agent cannot see this
message' footer. Default is true (preserves current behavior).
Replace per-request aiohttp.ClientSession() in every WhatsApp adapter
method with a single persistent self._http_session, matching the pattern
used by Mattermost, HomeAssistant, and SMS adapters.
Changes:
- Create self._http_session in connect(), close in disconnect()
- All bridge HTTP calls (send, edit, send-media, typing, get_chat_info,
poll_messages) now use the shared session
- Explicitly cancel _poll_task on disconnect() instead of relying
solely on self._running = False
- Health-check sessions in connect() remain ephemeral (persistent
session not yet created at that point)
- Remove per-method ImportError guards for aiohttp (always available
when gateway runs via [messaging] extras)
Salvaged from PR #1851 by Himess. The _poll_task storage was already
on main from PR #3267; this adds the disconnect cancellation and the
persistent session.
Tests: 4 new tests for session close, already-closed skip, poll task
cancellation, and done-task skip.
Extends the single fallback_model mechanism into an ordered chain.
When the primary model fails, Hermes tries each fallback provider in
sequence until one succeeds or the chain is exhausted.
Config format (new):
fallback_providers:
- provider: openrouter
model: anthropic/claude-sonnet-4
- provider: openai
model: gpt-4o
Legacy single-dict fallback_model format still works unchanged.
Key fix vs original PR: the call sites in the retry loop now use
_fallback_index < len(_fallback_chain) instead of the old one-shot
_fallback_activated guard, so the chain actually advances through
all configured providers.
Changes:
- run_agent.py: _fallback_chain list + _fallback_index replaces
one-shot _fallback_model; _try_activate_fallback() advances
through chain; failed provider resolution skips to next entry;
call sites updated to allow chain advancement
- cli.py: reads fallback_providers with legacy fallback_model compat
- gateway/run.py: same
- hermes_cli/config.py: fallback_providers: [] in DEFAULT_CONFIG
- tests: 12 new chain tests + 6 existing test fixtures updated
Co-authored-by: uzaylisak <uzaylisak@users.noreply.github.com>
The honcho check_fn only checked runtime session state, which isn't
set until the agent initializes. At banner time, honcho tools showed
as red/disabled even when properly configured.
Now checks configuration (enabled + api_key/base_url) as a fallback
when the session context isn't active yet. Fast path (session active)
unchanged; slow path (config check) only runs at banner time.
Adds 4 tests covering: session active, configured but no session,
not configured, and import failure graceful fallback.
Closes#1843.
When a connected MCP server sends a ToolListChangedNotification (per the
MCP spec), Hermes now automatically re-fetches the tool list, deregisters
removed tools, and registers new ones — without requiring a restart.
This enables MCP servers with dynamic toolsets (e.g. GitHub MCP with
GITHUB_DYNAMIC_TOOLSETS=1) to add/remove tools at runtime.
Changes:
- registry.py: add ToolRegistry.deregister() for nuke-and-repave refresh
- mcp_tool.py: extract _register_server_tools() from
_discover_and_register_server() as a shared helper for both initial
discovery and dynamic refresh
- mcp_tool.py: add _make_message_handler() and _refresh_tools() on
MCPServerTask, wired into all 3 ClientSession sites (stdio, new HTTP,
deprecated HTTP)
- Graceful degradation: silently falls back to static discovery when the
MCP SDK lacks notification types or message_handler support
- 8 new tests covering registration, refresh, handler dispatch, and
deregister
Salvaged from PR #1794 by shivvor2.
Home channel env vars (SLACK_HOME_CHANNEL, SIGNAL_HOME_CHANNEL, etc.)
for Slack, Signal, Mattermost, Matrix, Email, and SMS were nested
inside the credential-env blocks, so they were ignored when the
platform was already configured via config.yaml.
Moved the home channel handling outside the credential blocks with a
Platform.X in config.platforms guard, matching the existing pattern
for Telegram and Discord.
Co-authored-by: cutepawss <cutepawss@users.noreply.github.com>
hermes mcp serve starts a stdio MCP server that lets any MCP client
(Claude Code, Cursor, Codex, etc.) interact with Hermes conversations.
Matches OpenClaw's 9-tool channel bridge surface:
Tools exposed:
- conversations_list: list active sessions across all platforms
- conversation_get: details on one conversation
- messages_read: read message history
- attachments_fetch: extract non-text content from messages
- events_poll: poll for new events since a cursor
- events_wait: long-poll / block until next event (near-real-time)
- messages_send: send to any platform via send_message_tool
- channels_list: browse available messaging targets
- permissions_list_open: list pending approval requests
- permissions_respond: allow/deny approvals
Architecture:
- EventBridge: background thread polls SessionDB for new messages,
maintains in-memory event queue with waiter support
- Reads sessions.json + SessionDB directly (no gateway dep for reads)
- Reuses send_message_tool for sending (same platform adapters)
- FastMCP server with stdio transport
- Zero new dependencies (uses existing mcp>=1.2.0 optional dep)
Files:
- mcp_serve.py: MCP server + EventBridge (~600 lines)
- hermes_cli/main.py: added serve sub-parser to hermes mcp
- hermes_cli/mcp_config.py: route serve action to run_mcp_server
- tests/test_mcp_serve.py: 53 tests
- docs: updated MCP page + CLI commands reference
SMTP connections in _send_email() and _send_email_with_attachment() leak
when login() or send_message() raises before quit() is reached. Both now
wrapped in try/finally with a close() fallback if quit() also fails.
IMAP connection in _fetch_new_messages() leaks when UID processing raises,
since logout() sits after the loop. Restructured with try/finally so
logout() runs unconditionally.
Co-authored-by: Himess <Himess@users.noreply.github.com>
* feat: show estimated tool token context in hermes tools checklist
Adds a live token estimate indicator to the bottom of the interactive
tool configuration checklist (hermes tools / hermes setup). As users
toggle toolsets on/off, the total estimated context cost updates in
real time.
Implementation:
- tools/registry.py: Add get_schema() for check_fn-free schema access
- hermes_cli/curses_ui.py: Add optional status_fn callback to
curses_checklist — renders at bottom-right of terminal, stays fixed
while items scroll
- hermes_cli/tools_config.py: Add _estimate_tool_tokens() using
tiktoken (cl100k_base, already installed) to count tokens in the
JSON-serialised OpenAI-format tool schemas. Results are cached
per-process. The status function deduplicates overlapping tools
(e.g. browser includes web_search) for accurate totals.
- 12 new tests covering estimation, caching, graceful degradation
when tiktoken is unavailable, status_fn wiring, deduplication,
and the numbered fallback display
* fix: use effective toolsets (includes plugins) for token estimation index mapping
The status_fn closure built ts_keys from CONFIGURABLE_TOOLSETS but the
checklist uses _get_effective_configurable_toolsets() which appends plugin
toolsets. With plugins present, the indices would mismatch, causing
IndexError when selecting a plugin toolset.
* fix(tools): implement send_message routing for Matrix, Mattermost, HomeAssistant, DingTalk
Matrix, Mattermost, HomeAssistant, and DingTalk were present in
platform_map but fell through to the "not yet implemented" else branch,
causing send_message tool calls to silently fail on these platforms.
Add four async sender functions:
- _send_mattermost: POST /api/v4/posts via Mattermost REST API
- _send_matrix: PUT /_matrix/client/v3/rooms/.../send via Matrix CS API
- _send_homeassistant: POST /api/services/notify/notify via HA REST API
- _send_dingtalk: POST to session webhook URL
Add routing in _send_to_platform() and 17 unit tests covering success,
HTTP errors, missing config, env var fallback, and Matrix txn_id uniqueness.
* fix: pass platform tokens explicitly to Mattermost/Matrix/HA senders
The original PR passed pconfig.extra to sender functions, but tokens
live at pconfig.token (not in extra). This caused the senders to always
fall through to env var lookup instead of using the gateway-resolved
token.
Changes:
- Mattermost/Matrix/HA: accept token as first arg, matching the
Telegram/Discord/Slack sender pattern
- DingTalk: add DINGTALK_WEBHOOK_URL env var fallback + docstring
explaining the session-webhook vs robot-webhook difference
- Tests updated for new signatures + new DingTalk env var test
---------
Co-authored-by: sprmn24 <oncuevtv@gmail.com>
- Skill invocation: no secret capture callback so SSH remote setup note is emitted
- Patch agent.skill_utils.sys for platform checks (skill_matches_platform)
- Skip CLAUDE.md priority test on Darwin (case-insensitive FS)
Made-with: Cursor
Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
Add skills.external_dirs config option — a list of additional directories
to scan for skills alongside ~/.hermes/skills/. External dirs are read-only:
skill creation/editing always writes to the local dir. Local skills take
precedence when names collide.
This lets users share skills across tools/agents without copying them into
Hermes's own directory (e.g. ~/.agents/skills, /shared/team-skills).
Changes:
- agent/skill_utils.py: add get_external_skills_dirs() and get_all_skills_dirs()
- agent/prompt_builder.py: scan external dirs in build_skills_system_prompt()
- tools/skills_tool.py: _find_all_skills() and skill_view() search external dirs;
security check recognizes configured external dirs as trusted
- agent/skill_commands.py: /skill slash commands discover external skills
- hermes_cli/config.py: add skills.external_dirs to DEFAULT_CONFIG
- cli-config.yaml.example: document the option
- tests/agent/test_external_skills.py: 11 tests covering discovery, precedence,
deduplication, and skill_view for external skills
Requested by community member primco.
Two related fixes for remote terminal backends (Modal/Docker):
1. NEW: Credential file mounting system
Skills declare required_credential_files in frontmatter. Files are
mounted into Docker (read-only bind mounts) and Modal (mounts at
creation + sync via exec on each command for mid-session changes).
Google Workspace skill updated with the new field.
2. FIX: Docker backend now includes env_passthrough vars
Skills that declare required_environment_variables (e.g. Notion with
NOTION_API_KEY) register vars in the env_passthrough system. The
local backend checked this, but Docker's forward_env was a separate
disconnected list. Now Docker exec merges both sources, so
skill-declared env vars are forwarded into containers automatically.
This fixes the reported issue where NOTION_API_KEY in ~/.hermes/.env
wasn't reaching the Docker container despite being registered via
the Notion skill's prerequisites.
Closes#3665
Fixes two Signal bugs:
1. SSE connection: URL-encode phone numbers so + isn't interpreted as space (400 Bad Request)
2. Attachment fetch: use 'id' parameter instead of 'attachmentId' (NullPointerException in signal-cli)
Also refactors Signal tests with shared helpers.
Adds MATTERMOST_REQUIRE_MENTION and MATTERMOST_FREE_RESPONSE_CHANNELS
env vars, matching Discord's existing mention gating pattern.
- MATTERMOST_REQUIRE_MENTION=false: respond to all channel messages
- MATTERMOST_FREE_RESPONSE_CHANNELS=id1,id2: specific channels where
bot responds without @mention even when require_mention is true
- DMs always respond regardless of mention settings
- @mention is now stripped from message text (clean agent input)
7 new tests for mention gating, free-response channels, DM bypass,
and mention stripping. Updated existing test for mention stripping.
Docs: updated mattermost.md with Mention Behavior section,
environment-variables.md with new vars, config.py with metadata.
Salvage of PR #3452 (kentimsit). Fixes skill readiness checks on remote backends — persisted env vars are no longer incorrectly marked as missing.
Co-Authored-By: kentimsit <kentimsit@users.noreply.github.com>
PR #3323 added retry with exponential backoff to cache_image_from_url
but missed the sibling function cache_audio_from_url 18 lines below in
the same file. A single transient 429/5xx/timeout loses voice messages
while image downloads now survive them.
Apply the same retry pattern: 3 attempts with 1.5s exponential backoff,
immediate raise on non-retryable 4xx.
Pasting text from rich-text editors (Google Docs, Word, etc.) can inject
lone surrogate characters (U+D800..U+DFFF) that are invalid UTF-8.
The OpenAI SDK serializes messages with ensure_ascii=False, then encodes
to UTF-8 for the HTTP body — surrogates crash this with:
UnicodeEncodeError: 'utf-8' codec can't encode character '\udce2'
Three-layer fix:
1. Primary: sanitize user_message at the top of run_conversation()
2. CLI: sanitize in chat() before appending to conversation_history
3. Safety net: catch UnicodeEncodeError in the API error handler,
sanitize the entire messages list in-place, and retry once.
Also exclude UnicodeEncodeError from is_local_validation_error
so it doesn't get classified as non-retryable.
Includes 14 new tests covering the sanitization helpers and the
integration with run_conversation().
Salvage of PR #3533 (binhnt92). Follow-up to #3480 — applies min(100, ...) to 5 remaining unclamped percentage display sites in context_compressor, cli /stats, gateway /stats, and memory tool. Defensive clamps now that the root cause (estimation heuristic) was already removed in #3480.
Co-Authored-By: binhnt92 <binhnt92@users.noreply.github.com>
When the plist is deleted (manual cleanup, failed upgrade),
hermes gateway start now regenerates it automatically instead of
failing. Also simplifies the returncode==3 error path since the
plist is guaranteed to exist at that point.
Co-authored-by: Bartok9 <Bartok9@users.noreply.github.com>
One-shot local execution built `printf FENCE; <cmd>; __hermes_rc=...`, so a
command ending in a heredoc produced a closing line like `EOF; __hermes_rc=...`,
which is not a valid delimiter. Bash then treated the rest of the wrapper as
heredoc body, leaking it into tool output (e.g. gh issue/PR flows).
Use newline-separated wrapper lines so the delimiter stays alone and the
trailer runs after the heredoc completes.
Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
Prevent the agent from accidentally killing its own process with
pkill -f gateway, killall hermes, etc. Adds a dangerous command
pattern that triggers the approval flow.
Co-authored-by: arasovic <arasovic@users.noreply.github.com>
Adds 'hermes webhook' CLI subcommand and a skill — zero new model tools.
CLI commands (require webhook platform to be enabled):
hermes webhook subscribe <name> [--events, --prompt, --deliver, ...]
hermes webhook list
hermes webhook remove <name>
hermes webhook test <name>
All commands gate on webhook platform being enabled in config. If not
configured, prints setup instructions (gateway setup wizard, manual
config.yaml, or env vars).
The agent uses these via terminal tool, guided by the webhook-subscriptions
skill which documents setup, common patterns (GitHub, Stripe, CI/CD,
monitoring), prompt template syntax, security, and troubleshooting.
Adapter enhancement: webhook.py hot-reloads dynamic subscriptions from
~/.hermes/webhook_subscriptions.json on each incoming request (mtime-gated).
Static config.yaml routes always take precedence.
Docs: updated webhooks.md with Dynamic Subscriptions section, added
hermes webhook to cli-commands.md reference.
No new model tools. No toolset changes.
24 new tests for CLI CRUD, persistence, enabled-gate, and adapter
dynamic route loading.
Two fixes for /skills install and /skills uninstall slash commands:
1. input() hangs indefinitely inside prompt_toolkit's TUI event loop,
soft-locking the CLI. The user typing the slash command is already
implicit consent, so confirmation is now always skipped.
2. Cache invalidation was unconditional — installing or uninstalling a
skill mid-session silently broke the prompt cache, increasing costs.
The slash handler now defers cache invalidation by default (skill
takes effect next session). Pass --now to invalidate immediately,
with a message explaining the cost tradeoff. The CLI argparse path
(hermes skills install) is unaffected and still invalidates.
Fixes#3474
Salvaged from PR #3496 by dlkakbs.
hermes update hangs on input() when run from cron, scripts, or piped
contexts. Check both stdin and stdout isatty(), catch EOFError as a
fallback, and print guidance to run 'hermes config migrate' later.
Co-authored-by: phippsbot-byte <phippsbot-byte@users.noreply.github.com>
When all messaging platforms exhaust retries and get queued for background
reconnection, exit with code 1 so systemd Restart=on-failure can restart
the process. Previously the gateway stayed alive as a zombie with no
connected platforms and exit code 0.
Salvaged from PR #3567 by kelsia14. Test updates added.
Co-authored-by: kelsia14 <kelsia14@users.noreply.github.com>
* fix: keep gateway running through telegram proxy failures
- continue gateway startup in degraded mode when Telegram cannot connect yet
- ensure Telegram fallback transport also honors proxy env vars
- support reconnect retries without taking down the whole gateway
* test(telegram): cover proxy env handling in fallback transport
---------
Co-authored-by: kufufu9 <pi@local>
Salvage of PR #2173 (hanai) and PR #3432 (timknip).
Injects PATH, VIRTUAL_ENV, and HERMES_HOME into the macOS launchd plist so gateway subprocesses find user-installed tools (node, ffmpeg, etc.). Matches systemd unit parity with venv/bin, node_modules/.bin, and resolved node dir in PATH. Includes 7 new tests and docs updates across 4 pages.
Co-Authored-By: Han <ihanai1991@gmail.com>
Co-Authored-By: timknip <timknip@users.noreply.github.com>
Ollama reuses index 0 for every tool call in a parallel batch,
distinguishing them only by id. The streaming accumulator now
detects a new non-empty id at an already-active index and redirects
it to a fresh slot, preventing names and arguments from being
concatenated into a single tool call.
No-op for normal providers that use incrementing indices.
Co-authored-by: dmater01 <dmater01@users.noreply.github.com>
* Fixing mattermost configuration parsing bugs
* fix: add homeassistant to skills_config + platform consistency tests
Follow-up for cherry-picked #3512:
- Add homeassistant to skills_config.py PLATFORMS (was in tools_config
but missing from skills_config)
- Add 3 consistency tests that verify all platforms in tools_config have
matching toolset definitions, gateway includes, and skills_config entries
— prevents this class of bug from recurring
---------
Co-authored-by: DaneelV3 <dannel@v3rtical.tech>
Commands sent directly to the bot in groups include @botname suffix
(e.g. /compress@TigerNanoBot). get_command() now strips the @anything
part before lookup, matching how Telegram bot menu generates commands.
Fixes all slash commands silently doing nothing when sent with @mention.
Co-authored-by: MacroAnarchy <MacroAnarchy@users.noreply.github.com>
Add X-Content-Type-Options: nosniff and Referrer-Policy: no-referrer
to all API server responses via a new security_headers_middleware.
Co-authored-by: Oktay Aydin <aydnOktay@users.noreply.github.com>
Adds Access-Control-Max-Age: 600 to CORS preflight responses, telling
browsers to cache the preflight for 10 minutes. Reduces redundant OPTIONS
requests and improves perceived latency for browser-based API clients.
Salvaged from PR #3514 by aydnOktay.
Co-authored-by: aydnOktay <xaydinoktay@gmail.com>
* feat: GPT tool-use steering + strip budget warnings from history
Two changes to improve tool reliability, especially for OpenAI GPT models:
1. GPT tool-use enforcement prompt: Adds GPT_TOOL_USE_GUIDANCE to the
system prompt when the model name contains 'gpt' and tools are loaded.
This addresses a known behavioral pattern where GPT models describe
intended actions ('I will run the tests') instead of actually making
tool calls. Inspired by similar steering in OpenCode (beast.txt) and
Cline (GPT-5.1 variant).
2. Budget warning history stripping: Budget pressure warnings injected by
_get_budget_warning() into tool results are now stripped when
conversation history is replayed via run_conversation(). Previously,
these turn-scoped signals persisted across turns, causing models to
avoid tool calls in all subsequent messages after any turn that hit
the 70-90% iteration threshold.
* fix: replace hardcoded ~/.hermes paths with get_hermes_home() for profile support
Prep for the upcoming profiles feature — each profile is a separate
HERMES_HOME directory, so all paths must respect the env var.
Fixes:
- gateway/platforms/matrix.py: Matrix E2EE store was hardcoded to
~/.hermes/matrix/store, ignoring HERMES_HOME. Now uses
get_hermes_home() so each profile gets its own Matrix state.
- gateway/platforms/telegram.py: Two locations reading config.yaml via
Path.home()/.hermes instead of get_hermes_home(). DM topic thread_id
persistence and hot-reload would read the wrong config in a profile.
- tools/file_tools.py: Security path for hub index blocking was
hardcoded to ~/.hermes, would miss the actual profile's hub cache.
- hermes_cli/gateway.py: Service naming now uses the profile name
(hermes-gateway-coder) instead of a cryptic hash suffix. Extracted
_profile_suffix() helper shared by systemd and launchd.
- hermes_cli/gateway.py: Launchd plist path and Label now scoped per
profile (ai.hermes.gateway-coder.plist). Previously all profiles
would collide on the same plist file on macOS.
- hermes_cli/gateway.py: Launchd plist now includes HERMES_HOME in
EnvironmentVariables — was missing entirely, making custom
HERMES_HOME broken on macOS launchd (pre-existing bug).
- All launchctl commands in gateway.py, main.py, status.py updated
to use get_launchd_label() instead of hardcoded string.
Test fixes: DM topic tests now set HERMES_HOME env var alongside
Path.home() mock. Launchd test uses get_launchd_label() for expected
commands.
PR #3566 intentionally routes suppressed content to stream_delta_callback
when tool calls are present, so reasoning tag extraction can fire during
streaming. The test was still asserting the old behavior where content
after tool calls was fully suppressed from the callback.
Updated the assertion to match: content IS delivered to the callback
(for tag extraction), with display-level suppression handled by the
CLI's _stream_delta.
Add GET /v1/health as an alias to the existing /health endpoint so
OpenAI-compatible health checks work out of the box.
Co-authored-by: Oktay Aydin <aydnOktay@users.noreply.github.com>
The TOOL_USE_ENFORCEMENT_GUIDANCE injection (added in #3528) was
hardcoded to only match gpt/codex model names. This makes it a
config option so users can turn it on for any model family.
New config key: agent.tool_use_enforcement
- "auto" (default): matches gpt/codex (existing behavior)
- true: inject for all models
- false: never inject
- list of strings: custom model-name substrings to match
e.g. ["gpt", "codex", "deepseek", "qwen"]
No version bump needed — deep merge provides the default
automatically for existing installs.
12 new tests covering all config modes.
* fix(gateway): preserve full transcript on /compress instead of overwriting
The /compress command calls _compress_context() which correctly ends the
old session (preserving its full transcript in SQLite) and creates a new
session_id for the continuation. However, it then immediately called
rewrite_transcript() on the OLD session_id, overwriting the preserved
transcript with the compressed version — destroying searchable history.
Auto-compression (triggered by context pressure) does not have this bug
because the gateway already handles the session_id swap via the
agent.session_id != session_id check after _run_agent_sync.
Fix: after _compress_context creates the new session, write the compressed
messages into the NEW session_id and update the session store pointer.
The old session's full transcript stays intact and searchable via
session_search.
Before: /compress destroys original messages, session_search can't find
details from compressed portions.
After: /compress behaves like /new for history — full transcript preserved,
compressed context for the live session.
* fix(gateway): preserve transcript on /compress and hygiene compression
Apply session_id swap after _compress_context in both /compress handler
and hygiene pre-compression. _compress_context creates a new session
(ending the old one), but both paths were calling rewrite_transcript on
the OLD session_id — overwriting the preserved transcript and destroying
searchable history.
Now follows the same pattern as the auto-compression handler (lines
5415-5423): detect the new session_id, update the session store entry,
and write compressed messages to the new session.
Also fix FakeCompressAgent test mock to include session_id attribute
and simulate the session_id change that real _compress_context performs.
Co-authored-by: MacroAnarchy <MacroAnarchy@users.noreply.github.com>
---------
Co-authored-by: MacroAnarchy <MacroAnarchy@users.noreply.github.com>
* fix(matrix): harden e2ee access-token handling
* fix: patch nio mock in e2ee maintenance sync loop test
The sync_loop now imports nio for SyncError checking (from PR #3280),
so the test needs to inject a fake nio module via sys.modules.
---------
Co-authored-by: Cortana <andrew+cortana@chalkley.org>
The minimax-specific auto-correction in runtime_provider.py was
preventing users from overriding to the OpenAI-compatible endpoint
via MINIMAX_BASE_URL. Users in certain regions get nginx 404 on
api.minimax.io/anthropic and need to switch to api.minimax.chat/v1.
The generic URL-suffix detection already handles /anthropic →
anthropic_messages, so the minimax-specific code was redundant for
the default path and harmful for the override path.
Now: default /anthropic URL works via generic detection, user
override to /v1 gets chat_completions mode naturally.
Closes#3546 (different approach — respects user overrides instead
of changing the default endpoint).
Drop the swe-rex dependency for Modal terminal backend and use the
Modal SDK directly (Sandbox.create + Sandbox.exec). This fixes:
- AsyncUsageWarning from synchronous App.lookup() in async context
- DeprecationError from unencrypted_ports / .url on unencrypted tunnels
(deprecated 2026-03-05)
The new implementation:
- Uses modal.App.lookup.aio() for async-safe app creation
- Uses Sandbox.create.aio() with 'sleep infinity' entrypoint
- Uses Sandbox.exec.aio() for direct command execution (no HTTP server
or tunnel needed)
- Keeps all existing features: persistent filesystem snapshots,
configurable resources (CPU/memory/disk), sudo support, interrupt
handling, _AsyncWorker for event loop safety
Consistent with the Docker backend precedent (PR #2804) where we
removed mini-swe-agent in favor of direct docker run.
Files changed:
- tools/environments/modal.py - core rewrite
- tools/terminal_tool.py - health check: modal instead of swerex
- hermes_cli/setup.py - install modal instead of swe-rex[modal]
- pyproject.toml - modal extra: modal>=1.0.0 instead of swe-rex[modal]
- scripts/kill_modal.sh - grep for hermes-agent instead of swe-rex
- tests/ - updated for new implementation
- environments/README.md - updated patches section
- website/docs - updated install command
The plugin system defined six lifecycle hooks but only pre_tool_call and
post_tool_call were invoked. This activates the remaining four so that
external plugins (e.g. memory systems) can hook into the conversation
loop without touching core code.
Hook semantics:
- on_session_start: fires once when a new session is created
- pre_llm_call: fires once per turn before the tool-calling loop;
plugins can return {"context": "..."} to inject into the ephemeral
system prompt (not cached, not persisted)
- post_llm_call: fires once per turn after the loop completes, with
user_message and assistant_response for sync/storage
- on_session_end: fires at the end of every run_conversation call
invoke_hook() now returns a list of non-None callback return values,
enabling pre_llm_call context injection while remaining backward
compatible (existing hooks that return None are unaffected).
Salvaged from PR #2823.
Co-authored-by: Nicolò Boschi <boschi1997@gmail.com>
Browser clients using the Idempotency-Key header for request
deduplication were blocked by CORS preflight because the header
was not listed in Access-Control-Allow-Headers.
Add Idempotency-Key to _CORS_HEADERS and add tests for both the
new header allowance and the existing Vary: Origin behavior.
Co-authored-by: aydnOktay <aydnOktay@users.noreply.github.com>
Co-authored-by: Hermes Agent <hermes@nousresearch.com>
Root cause: Anthropic buffers entire tool call arguments and goes silent
for minutes while thinking (verified: 167s gap with zero SSE events on
direct API). OpenRouter's upstream proxy times out after ~125s of
inactivity and drops the connection with 'Network connection lost'.
Fix: Send the x-anthropic-beta: fine-grained-tool-streaming-2025-05-14
header for Claude models on OpenRouter. This makes Anthropic stream
tool call arguments token-by-token instead of buffering them, keeping
the connection alive through OpenRouter's proxy.
Live-tested: the exact prompt that consistently failed at ~128s now
completes successfully — 2,972 lines written, 49K tokens, 8 minutes.
Additional improvements:
1. Send explicit max_tokens for Claude through OpenRouter. Without it,
OpenRouter defaults to 65,536 (confirmed via echo_upstream_body) —
only half of Opus 4.6's 128K limit.
2. Classify SSE 'Network connection lost' as retryable in the streaming
inner retry loop. The OpenAI SDK raises APIError from SSE error
events, which was bypassing our transient error retry logic.
3. Actionable diagnostic guidance when stream-drop retries exhaust.
Add ~/.local/bin, ~/.cargo/bin, ~/go/bin, ~/.npm-global/bin to the
systemd unit PATH so tools installed via uv/pipx/cargo/go are
discoverable by MCP servers and terminal commands.
Uses a _build_user_local_paths() helper that checks exists() before
adding, and correctly resolves home dir for both user and system
service types.
Co-authored-by: Kal Sze <ksze@users.noreply.github.com>
Cherry-pick of feat/gpt-tool-steering with modifications:
1. Tool-use enforcement prompt (refactored from GPT-specific):
- Renamed GPT_TOOL_USE_GUIDANCE -> TOOL_USE_ENFORCEMENT_GUIDANCE
- Added TOOL_USE_ENFORCEMENT_MODELS tuple: ('gpt', 'codex')
- Injection logic now checks against the tuple instead of hardcoding
'gpt' — adding new model families is a one-line change
- Addresses models describing actions instead of making tool calls
2. Budget warning history stripping:
- _strip_budget_warnings_from_history() strips _budget_warning JSON
keys and [BUDGET WARNING: ...] text from tool results at the start
of run_conversation()
- Prevents old budget warnings from poisoning subsequent turns
Based on PR #3479 by teknium1.
* fix: harden `hermes update` against diverged history, non-main branches, and gateway edge cases
The self-update command (`hermes update` / gateway `/update`) could fail
or silently corrupt state in several scenarios:
1. **Diverged history** — `git pull --ff-only` aborts with a cryptic
subprocess error when upstream has force-pushed or rebased. Now falls
back to `git reset --hard origin/main` since local changes are already
stashed.
2. **User on a feature branch / detached HEAD** — the old code would
either clobber the feature branch HEAD to point at origin/main, or
silently pull against a non-existent remote branch. Now auto-checkouts
main before pulling, with a clear warning.
3. **Fetch failures** — network or auth errors produced raw subprocess
tracebacks. Now shows user-friendly messages ("Network error",
"Authentication failed") with actionable hints.
4. **reset --hard failure** — if the fallback reset itself fails (disk
full, permissions), the old code would still attempt stash restore on
a broken working tree. Now skips restore and tells the user their
changes are safe in stash.
5. **Gateway /update stash conflicts** — non-interactive mode (Telegram
`/update`) called sys.exit(1) when stash restore had conflicts, making
the entire update report as failed even though the code update itself
succeeded. Now treats stash conflicts as non-fatal in non-interactive
mode (returns False instead of exiting).
* fix: restore stash and branch on 'already up to date' early return
The PR moved stash creation before the commit-count check (needed for
the branch-switching feature), but the 'already up to date' early return
didn't restore the stash or switch back to the original branch — leaving
the user stranded on main with changes trapped in a stash.
Now the early-return path restores the stash and checks out the original
branch when applicable.
---------
Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
- Change default inference_base_url from dashscope-intl Anthropic-compat
endpoint to coding-intl OpenAI-compat /v1 endpoint. The old Anthropic
endpoint 404'd when used with the OpenAI SDK (which appends
/chat/completions to a /apps/anthropic base URL).
- Update curated model list: remove models unavailable on coding-intl
(qwen3-max, qwen-plus-latest, qwen3.5-flash, qwen-vl-max), add
third-party models available on the platform (glm-5, glm-4.7,
kimi-k2.5, MiniMax-M2.5).
- URL-based api_mode auto-detection still works: overriding
DASHSCOPE_BASE_URL to an /apps/anthropic endpoint automatically
switches to anthropic_messages mode.
- Update provider description and env var descriptions to reflect the
coding-intl multi-provider platform.
- Update tests to match new default URL and test the anthropic override
path instead.
* fix: cap context pressure percentage at 100% in display
The forward-looking token estimate can overshoot the compaction threshold
(e.g. a large tool result pushes it from 70% to 109% in one step). The
progress bar was already capped via min(), but pct_int was not — causing
the user to see '109% to compaction' which is confusing.
Cap pct_int at 100 in both CLI and gateway display functions.
Reported by @JoshExile82.
* refactor: use real API token counts for compression decisions
Replace the rough chars/3 estimation with actual prompt_tokens +
completion_tokens from the API response. The estimation was needed to
predict whether tool results would push context past the threshold, but
the default 50% threshold leaves ample headroom — if tool results push
past it, the next API call reports real usage and triggers compression
then.
This removes all estimation from the compression and context pressure
paths, making both 100% data-driven from provider-reported token counts.
Also removes the dead _msg_count_before_tools variable.
When finish_reason='length' and the response contains only reasoning
(think blocks or empty content), the model exhausted its output token
budget on thinking with nothing left for the actual response.
Previously, this fell into either:
- chat_completions: 3 useless continuation retries (model hits same limit)
- anthropic/codex: generic 'Response truncated' error with rollback
Now: detect the think-only + length condition early and return immediately
with a targeted error message: 'Model used all output tokens on reasoning
with none left for the response. Try lowering reasoning effort or
increasing max_tokens.'
This saves 2 wasted API calls on the chat_completions path and gives
users actionable guidance instead of a cryptic error.
The existing think-only retry logic (finish_reason='stop') is unchanged —
that's a genuine model glitch where retrying can help.
Salvage of #3389 by @binhnt92 with reasoning fallback and retry logic added on top.
All 7 auxiliary LLM call sites now use extract_content_or_reasoning() which mirrors the main agent loop's behavior: extract content, strip think blocks, fall back to structured reasoning fields, retry on empty.
Closes#3389.
Show only agentic models that map to OpenRouter defaults:
Qwen/Qwen3.5-397B-A17B ↔ qwen/qwen3.5-plus
Qwen/Qwen3.5-35B-A3B ↔ qwen/qwen3.5-35b-a3b
deepseek-ai/DeepSeek-V3.2 ↔ deepseek/deepseek-chat
moonshotai/Kimi-K2.5 ↔ moonshotai/kimi-k2.5
MiniMaxAI/MiniMax-M2.5 ↔ minimax/minimax-m2.5
zai-org/GLM-5 ↔ z-ai/glm-5
XiaomiMiMo/MiMo-V2-Flash ↔ xiaomi/mimo-v2-pro
moonshotai/Kimi-K2-Thinking ↔ moonshotai/kimi-k2-thinking
Users can still pick any HF model via Enter custom model name.
Previously, tirith exit code 1 (block) immediately rejected the command
with no approval prompt — users saw 'BLOCKED: Command blocked by
security scan' and the agent moved on. This prevented gateway/CLI users
from approving pipe-to-shell installs like 'curl ... | sh' even when
they understood the risk.
Changes:
- Tirith 'block' and 'warn' now both go through the approval flow.
Users see the full tirith findings (severity, title, description,
safer alternatives) and can choose to approve or deny.
- New _format_tirith_description() builds rich descriptions from tirith
findings JSON so the approval prompt is informative.
- CLI startup now warns when tirith is enabled but not available, so
users know command scanning is degraded to pattern matching only.
The default approval choice is still deny, so the security posture is
unchanged for unattended/timeout scenarios.
Reported via Discord by pistrie — 'curl -fsSL https://mandex.dev/install.sh | sh'
was hard-blocked with no way to approve.
The Anthropic adapter defaulted to max_tokens=16384 when no explicit value
was configured. This severely limits thinking-enabled models where thinking
tokens count toward max_tokens:
- Claude Opus 4.6 supports 128K output but was capped at 16K
- Claude Sonnet 4.6 supports 64K output but was capped at 16K
With extended thinking (adaptive or budget-based), the model could exhaust
the entire 16K on reasoning, leaving zero tokens for the actual response.
This caused two user-visible errors:
- 'Response truncated (finish_reason=length)' — thinking consumed most tokens
- 'Response only contains think block with no content' — thinking consumed all
Fix: add _ANTHROPIC_OUTPUT_LIMITS lookup table (sourced from Anthropic docs
and Cline's model catalog) and use the model's actual output limit as the
default. Unknown future models default to 128K (the current maximum).
Also adds context_length clamping: if the user configured a smaller context
window (e.g. custom endpoint), max_tokens is clamped to context_length - 1
to avoid exceeding the window.
Closes#2706
Models like GLM-5/5.1 can think for 15+ minutes. The previous 900s
(15 min) default for HERMES_API_TIMEOUT killed legitimate requests.
Raised to 1800s (30 min) in both places that read the env var:
- _build_api_kwargs() timeout (non-streaming total timeout)
- _call_chat_completions() write timeout (streaming connection)
The streaming per-chunk read timeout (60s) and stale stream detector
(180-300s) are unchanged — those are appropriate for inter-chunk timing.
Salvage of PR #1747 (original PR #1171 by @davanstrien) onto current main.
Registers Hugging Face Inference Providers (router.huggingface.co/v1) as a named provider:
- hermes chat --provider huggingface (or --provider hf)
- 18 curated open models via hermes model picker
- HF_TOKEN in ~/.hermes/.env
- OpenAI-compatible endpoint with automatic failover (Groq, Together, SambaNova, etc.)
Files: auth.py, models.py, main.py, setup.py, config.py, model_metadata.py, .env.example, 5 docs pages, 17 new tests.
Co-authored-by: Daniel van Strien <davanstrien@gmail.com>
Salvage of #3399 by @binhnt92 with true agent interruption added on top.
When a streaming /v1/chat/completions client disconnects mid-stream, the agent is now interrupted via agent.interrupt() so it stops making LLM API calls, and the asyncio task wrapper is cancelled.
Closes#3399.
Two independent bugs caused the reasoning box to appear three times when
the model produced reasoning + tool_calls:
Bug A: _build_assistant_message() re-fired reasoning_callback with the full
reasoning text even when streaming had already displayed it. The original
guard only checked structured reasoning_content deltas, but reasoning also
arrives via content tag extraction (<REASONING_SCRATCHPAD>/<think> tags
in delta.content), which went through _fire_stream_delta not
_fire_reasoning_delta. Fix: skip the callback entirely when streaming is
active — both paths display reasoning during the stream. Any reasoning not
shown during streaming is caught by the CLI post-response fallback.
Bug B: The post-response reasoning display checked _reasoning_stream_started,
but that flag was reset by _reset_stream_state() during intermediate turn
boundaries (when stream_delta_callback(None) fires between tool calls).
Introduced _reasoning_shown_this_turn flag that persists across the tool
loop and is only reset at the start of each user turn.
Live-tested in PTY: reasoning now shows exactly once per API call, no
duplicates across tool-calling loops.
The OpenAI SDK's AsyncHttpxClientWrapper.__del__ schedules aclose() via
asyncio.get_running_loop().create_task(). When an AsyncOpenAI client is
garbage-collected while prompt_toolkit's event loop is running (the common
CLI idle state), the aclose() task runs on prompt_toolkit's loop but the
underlying TCP transport is bound to a different (dead) worker loop.
The transport's self._loop.call_soon() then raises RuntimeError('Event
loop is closed'), which prompt_toolkit surfaces as the disruptive
'Unhandled exception in event loop ... Press ENTER to continue...' error.
Three-layer fix:
1. neuter_async_httpx_del(): Monkey-patches __del__ to a no-op at CLI
startup before any AsyncOpenAI clients are created. Safe because
cached clients are explicitly cleaned via _force_close_async_httpx,
and uncached clients' TCP connections are cleaned by the OS on exit.
2. Custom asyncio exception handler: Installed on prompt_toolkit's event
loop to silently suppress 'Event loop is closed' RuntimeError.
Defense-in-depth for SDK upgrades that might change the class name.
3. cleanup_stale_async_clients(): Called after each agent turn (when the
agent thread joins) to proactively evict cache entries whose event
loop is closed, preventing stale clients from accumulating.
When a gateway crashes mid-job execution (before mark_job_run can persist
the updated next_run_at), the job would fire again on every restart attempt
within the grace window. For a daily 6:15 AM job with a 2-hour grace,
rapidly restarting the gateway could trigger dozens of duplicate runs.
Fix: call advance_next_run() BEFORE run_job() in tick(). For recurring
jobs (cron/interval), this preemptively advances next_run_at to the next
future occurrence and persists it to disk. If the process then crashes
during execution, the job won't be considered due on restart.
One-shot jobs are left unchanged — they still retry on restart since
there's no future occurrence to advance to.
This changes the scheduler from at-least-once to at-most-once semantics
for recurring jobs, which is the correct tradeoff: missing one daily
message is far better than sending it dozens of times.
python-telegram-bot's BadRequest inherits from NetworkError, so the
send() retry loop was catching 'Message thread not found' as a transient
network error and retrying 3 times before silently failing. This killed
all tool progress messages, streaming responses, and typing indicators
when the incoming message carried an invalid message_thread_id.
Now detect BadRequest inside the NetworkError handler:
- 'thread not found' + thread_id set → clear thread_id and retry once
(message still reaches the chat, just without topic threading)
- Other BadRequest errors → raise immediately (permanent, don't retry)
- True NetworkError → retry as before (transient)
252 silent failures in gateway.log traced to this on 2026-03-26.
5 new tests for thread fallback, non-thread BadRequest, no-thread sends,
network retry, and multi-chunk fallback.
