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.
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
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.
* 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.
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>
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.
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).
* 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.
* 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>
* 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>
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>
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
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>
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
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.
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.
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>
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
Tools from check_fn-gated toolsets (honcho, homeassistant) showed as
red (disabled) in the startup banner even when properly configured.
This happened because check_fn runs lazily after session context is
set, but the banner renders before agent init.
Now distinguishes three states:
- red: truly unavailable (missing env var, no API key)
- yellow: lazy-initialized (check_fn pending, will activate on use)
- normal: available and ready
Only the banner fix was salvaged from the original PR; unrelated
bundled changes (context_compressor, STT config, auth default_model,
SessionResetPolicy) were discarded.
Co-authored-by: Jah-yee <Jah-yee@users.noreply.github.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).
Third report of gateway crashing with:
ImportError: cannot import name 'get_hermes_home' from 'hermes_constants'
Root cause: stale .pyc bytecode files survive code updates. When Python
loads a cached .pyc that references names from the old source, the import
fails and the gateway won't start.
Two bugs fixed:
1. Git update path: no cache clearing at all after git pull
2. ZIP update path: __pycache__ was explicitly in the preserve set
Added _clear_bytecode_cache() helper that removes all __pycache__ dirs
under PROJECT_ROOT (skipping venv/node_modules/.git/.worktrees). Called
in both git and ZIP update paths, before pip install.
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>
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
* Add new Gemini 3.1 model entries to models.py
* fix: also add Gemini 3.1 models to nous provider list
---------
Co-authored-by: Andrei Ignat <andrei@ignat.se>
* 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.
When a user runs 'hermes update', the Python process caches old modules
in sys.modules. After git pull updates files on disk, lazy imports of
newly-updated modules fail because they try to import display_hermes_home
from the cached (old) hermes_constants which doesn't have the function.
This specifically broke the gateway auto-restart in cmd_update — importing
hermes_cli/gateway.py triggered the top-level 'from hermes_constants
import display_hermes_home' against the cached old module. The ImportError
was silently caught, so the gateway was never restarted after update.
Users with a running gateway then hit the ImportError on their next
Telegram/Discord message when the stale gateway process lazily loaded
run_agent.py (new version) which also had the top-level import.
Fixes:
- hermes_cli/gateway.py: lazy import at call site (line 940)
- run_agent.py: lazy import at call site (line 6927)
- tools/terminal_tool.py: lazy imports at 3 call sites
- tools/tts_tool.py: static schema string (no module-level call)
- hermes_cli/auth.py: lazy import at call site (line 2024)
- hermes_cli/main.py: reload hermes_constants after git pull in cmd_update
Also fixes 4 pre-existing test failures in test_parse_env_var caused by
NameError on display_hermes_home in terminal_tool.py.
When switching providers via 'hermes model', the previous provider's
api_mode persisted in config.yaml. Switching from Copilot
(codex_responses) to a chat_completions provider like Z.AI would send
requests to the wrong endpoint (404).
Set api_mode = chat_completions in the 4 provider flows that were
missing it: OpenRouter, custom endpoint, Kimi, and api_key_provider.
Co-authored-by: Nour Eddine Hamaidi <HenkDz@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.
Prep for profiles: user-facing messages now use display_hermes_home() so
diagnostic output shows the correct path for each profile.
New helper: display_hermes_home() in hermes_constants.py
12 files swept, ~30 user-facing string replacements.
Includes dynamic TTS schema description.
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.
Self-hosted Honcho on localhost doesn't require authentication, but
both the activation gates and the SDK client required an API key.
Combined fix from three contributor PRs:
- Relax all 8 activation gates to accept (api_key OR base_url) as
valid credentials (#3482 by @cameronbergh)
- Use 'local' placeholder for the SDK client when base_url points to
localhost/127.0.0.1/::1 (#3570 by @ygd58)
Files changed: run_agent.py (2 gates), cli.py (1 gate),
gateway/run.py (1 gate), honcho_integration/cli.py (2 gates),
hermes_cli/doctor.py (2 gates), honcho_integration/client.py (SDK).
Co-authored-by: cameronbergh <cameronbergh@users.noreply.github.com>
Co-authored-by: ygd58 <ygd58@users.noreply.github.com>
Co-authored-by: devorun <devorun@users.noreply.github.com>
Adds Exa (https://exa.ai) as a fourth web backend alongside Parallel,
Firecrawl, and Tavily. Follows the exact same integration pattern:
- Backend selection: config web.backend=exa or auto-detect from EXA_API_KEY
- Search: _exa_search() with highlights for result descriptions
- Extract: _exa_extract() with full text content extraction
- Lazy singleton client with x-exa-integration header
- Wired into web_search_tool and web_extract_tool dispatchers
- check_web_api_key() and requires_env updated
- CLI: hermes setup summary, hermes tools config, hermes config show
- config.py: EXA_API_KEY in OPTIONAL_ENV_VARS with metadata
- pyproject.toml: exa-py>=2.9.0,<3 in dependencies
Salvaged from PR #1850.
Co-authored-by: louiswalsh <louiswalsh@users.noreply.github.com>
* fix(sessions): support stdout when output path is '-' in session export
* fix: style cleanup + extend stdout support to snapshot export
Follow-up for salvaged PR #3617:
- Fix import sys; on one line (style consistency)
- Update help text to mention - for stdout
- Apply same stdout support to hermes skills snapshot export
---------
Co-authored-by: ygd58 <buraysandro9@gmail.com>
Users intuitively write model: { model: my-model } instead of
model: { default: my-model } and it silently falls back to the
hardcoded default. Now both spellings work across all three config
consumers: runtime_provider, CLI, and gateway.
Co-authored-by: ygd58 <ygd58@users.noreply.github.com>
Some environments lose pip inside the venv. Before invoking pip install,
check pip --version and bootstrap with ensurepip if missing. Applied to
both update code paths (_update_via_zip and cmd_update).
Salvaged from PR #3359.
Co-authored-by: Git-on-my-level <Git-on-my-level@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>
Local/custom OpenAI-compatible providers (Ollama, LM Studio, vLLM) that
don't require auth were hitting empty api_key rejections from the OpenAI
SDK, especially when used as smart model routing targets.
Uses the same 'no-key-required' placeholder already used in
_resolve_openrouter_runtime() for the identical scenario.
Salvaged from PR #3543.
Co-authored-by: scottlowry <scottlowry@users.noreply.github.com>
Add per-task timeout settings under auxiliary.{task}.timeout in config.yaml
instead of hardcoded values. Users with slow local models (Ollama, llama.cpp)
can now increase timeouts for compression, vision, session search, etc.
Defaults:
- auxiliary.compression.timeout: 120s (was hardcoded 45s)
- auxiliary.vision.timeout: 30s (unchanged)
- all other aux tasks: 30s (was hardcoded 30s)
- title_generator: 30s (was hardcoded 15s)
call_llm/async_call_llm now auto-resolve timeout from config when not
explicitly passed. Callers can still override with an explicit timeout arg.
Based on PR #3406 by alanfwilliams. Converted from env vars to config.yaml
per project conventions.
Co-authored-by: alanfwilliams <alanfwilliams@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>
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>
* 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>
* 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.
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.
dict.get(key, default) only returns default when key is ABSENT.
When YAML has 'key:' with no value, it parses as None — .get()
returns None, then .strip() crashes with AttributeError.
Use (x or '') pattern to handle both missing and null cases.
Salvaged from PR #3217.
Co-authored-by: erosika <erosika@users.noreply.github.com>
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>
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>
* 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.
Matrix platform was missing from the PLATFORMS config, causing a
KeyError in _get_platform_tools() when handling Matrix messages.
Every other platform (telegram, discord, slack, etc.) was present
but matrix was overlooked.
Co-authored-by: williamtwomey <williamtwomey@users.noreply.github.com>
hermes tools and _get_platform_tools() call get_plugin_toolsets() /
_get_plugin_toolset_keys() without first ensuring plugins have been
discovered. discover_plugins() only runs as a side effect of importing
model_tools.py, which hermes tools never does. This means:
- hermes tools TUI never shows plugin toolsets (invisible to users)
- _get_platform_tools() in standalone processes misses plugin toolsets
Fix: call discover_plugins() (idempotent) in both
_get_plugin_toolset_keys() and _get_effective_configurable_toolsets()
before accessing plugin state. In the gateway/CLI where model_tools.py
is already imported, the call is a no-op (discover_and_load checks
_discovered flag).
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.
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>
The API server adapter was creating agents without specifying
enabled_toolsets, causing ALL tools to load — including clarify,
send_message, and text_to_speech which don't work without interactive
callbacks or gateway dispatch.
Changes:
- toolsets.py: Add hermes-api-server toolset (core tools minus clarify,
send_message, text_to_speech)
- api_server.py: Resolve toolsets from config.yaml platform_toolsets
via _get_platform_tools() — same path as all other gateway platforms.
Falls back to hermes-api-server default when no override configured.
- tools_config.py: Add api_server to PLATFORMS dict so users can
customize via 'hermes tools' or platform_toolsets.api_server in
config.yaml
- 12 tests covering toolset definition, config resolution, and
user override
Reported by thatwolfieguy on Discord.
Two changes:
1. Fix /queue command: remove the _agent_running guard that rejected
/queue after the agent finished. The prompt was deferred in
_pending_input until the agent completed, then the handler checked
_agent_running (now False) and rejected it. /queue now always queues
regardless of timing.
2. Add display.busy_input_mode config (CLI-only):
- 'interrupt' (default): Enter while busy interrupts the current run
(preserves existing behavior)
- 'queue': Enter while busy queues the message for the next turn,
with a 'Queued for the next turn: ...' confirmation
Ctrl+C always interrupts regardless of this setting.
Salvaged from PR #3037 by StefanoChiodino. Key differences:
- Default is 'interrupt' (preserves existing behavior) not 'queue'
- No config version bump (unnecessary for new key in existing section)
- Simpler normalization (no alias map)
- /queue fix is simpler: just remove the guard instead of intercepting
commands during busy state
Two bugs caused the OpenClaw migration during first-time setup to be
ineffective, forcing users to reconfigure everything manually:
1. The setup wizard created config.yaml with all defaults BEFORE running
the migration, then the migrator ran with overwrite=False. Every config
setting was reported as a 'conflict' against the defaults and skipped.
Fix: use overwrite=True during setup-time migration (safe because only
defaults exist at that point). The hermes claw migrate CLI command
still defaults to overwrite=False for post-setup use.
2. After migration, the full setup wizard ran all 5 sections unconditionally,
forcing the user through model/terminal/agent/messaging/tools configuration
even when those settings were just imported.
Fix: add _get_section_config_summary() and _skip_configured_section()
helpers. After migration, each section checks if it's already configured
(API keys present, non-default values, platform tokens) and offers
'Reconfigure? [y/N]' with default No. Unconfigured sections still run
normally.
Reported by Dev Bredda on social media.
- add managed modal and gateway-backed tool integrations\n- improve CLI setup, auth, and configuration for subscriber flows\n- expand tests and docs for managed tool support
* feat: config-gated /verbose command for messaging gateway
Add gateway_config_gate field to CommandDef, allowing cli_only commands
to be conditionally available in the gateway based on a config value.
- CommandDef gains gateway_config_gate: str | None — a config dotpath
that, when truthy, overrides cli_only for gateway surfaces
- /verbose uses gateway_config_gate='display.tool_progress_command'
- Default is off (cli_only behavior preserved)
- When enabled, /verbose cycles tool_progress mode (off/new/all/verbose)
in the gateway, saving to config.yaml — same cycle as the CLI
- Gateway helpers (help, telegram menus, slack mapping) dynamically
check config to include/exclude config-gated commands
- GATEWAY_KNOWN_COMMANDS always includes config-gated commands so
the gateway recognizes them and can respond appropriately
- Handles YAML 1.1 bool coercion (bare 'off' parses as False)
- 8 new tests for the config gate mechanism + gateway handler
* docs: document gateway_config_gate and /verbose messaging support
- AGENTS.md: add gateway_config_gate to CommandDef fields
- slash-commands.md: note /verbose can be enabled for messaging, update Notes
- configuration.md: add tool_progress_command to display section + usage note
- cli.md: cross-link to config docs for messaging enablement
- messaging/index.md: show tool_progress_command in config snippet
- plugins.md: add gateway_config_gate to register_command parameter table
When third-party tools (Paperclip orchestrator, etc.) spawn hermes chat
as a subprocess, their sessions pollute user session history and search.
- hermes chat --source <tag> (also HERMES_SESSION_SOURCE env var)
- exclude_sources parameter on list_sessions_rich() and search_messages()
- Sessions with source=tool hidden from sessions list/browse/search
- Third-party adapters pass --source tool to isolate agent sessions
Cherry-picked from PR #3208 by HenkDz.
Co-authored-by: Henkey <noonou7@gmail.com>
Nous Portal now passes through OpenRouter model names and routes from
there. Update the static fallback model list and auxiliary client default
to use OpenRouter-format slugs (provider/model) instead of bare names.
- _PROVIDER_MODELS['nous']: full OpenRouter catalog
- _NOUS_MODEL: google/gemini-3-flash-preview (was gemini-3-flash)
- Updated 4 test assertions for the new default model name
Validate each ZIP member's resolved path against the extraction directory
before extracting. A crafted ZIP with paths like ../../etc/passwd would
previously write outside the target directory.
Fixes#3075
Co-authored-by: Hiren <hiren.thakore58@gmail.com>
* fix(skills): reduce skills.sh resolution churn and preserve trust for wrapped identifiers
- Accept common skills.sh prefix typos (skils-sh/, skils.sh/)
- Strip skills-sh/ prefix in _resolve_trust_level() so trusted repos
stay trusted when installed through skills.sh
- Use resolved identifier (from bundle/meta) for scan_skill source
- Prefer tree search before root scan in _discover_identifier()
- Add _resolve_github_meta() consolidation for inspect flow
Cherry-picked from PR #3001 by kshitijk4poor.
* fix: restore candidate loop in SkillsShSource.fetch() for consistency
The cherry-picked PR only tried the first candidate identifier in
fetch() while inspect() (via _resolve_github_meta) tried all four.
This meant skills at repo/skills/path would be found by inspect but
missed by fetch, forcing it through the heavier _discover_identifier
flow. Restore the candidate loop so both paths behave identically.
Updated the test assertion to match.
---------
Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
Gateway sessions had their own inline toolset resolution that only read
platform_toolsets from config, which never includes MCP server names.
MCP tools were discovered and registered but invisible to the model.
- Replace duplicated gateway toolset resolution in _run_agent() and
_run_background_task() with calls to the shared _get_platform_tools()
- Extend _get_platform_tools() to include globally enabled MCP servers
at runtime (include_default_mcp_servers=True), while config-editing
flows use include_default_mcp_servers=False to avoid persisting
implicit MCP defaults into platform_toolsets
- Add homeassistant to PLATFORMS dict (was missing, caused KeyError)
- Fix CLI entry point to use _get_platform_tools() as well, so MCP
tools are visible in CLI mode too
- Remove redundant platform_key reassignment in _run_background_task
Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>
The default SOUL.md seeded for new users should match
DEFAULT_AGENT_IDENTITY — a short, neutral identity paragraph.
The elaborate voice spec (avoid lists, dialogue examples, symbol
conventions) was never intended as the default for all users.
Users who want a custom persona write their own SOUL.md.
Three categories of cleanup, all zero-behavioral-change:
1. F-strings without placeholders (154 fixes across 29 files)
- Converted f'...' to '...' where no {expression} was present
- Heaviest files: run_agent.py (24), cli.py (20), honcho_integration/cli.py (34)
2. Simplify defensive patterns in run_agent.py
- Added explicit self._is_anthropic_oauth = False in __init__ (before
the api_mode branch that conditionally sets it)
- Replaced 7x getattr(self, '_is_anthropic_oauth', False) with direct
self._is_anthropic_oauth (attribute always initialized now)
- Added _is_openrouter_url() and _is_anthropic_url() helper methods
- Replaced 3 inline 'openrouter' in self._base_url_lower checks
3. Remove dead code in small files
- hermes_cli/claw.py: removed unused 'total' computation
- tools/fuzzy_match.py: removed unused strip_indent() function and
pattern_stripped variable
Full test suite: 6184 passed, 0 failures
E2E PTY: banner clean, tool calls work, zero garbled ANSI
sessions delete and prune call input() for confirmation without
catching EOFError. When stdin isn't a TTY (piped input, CI/CD, cron),
input() throws EOFError and the command crashes.
Extract a _confirm_prompt() helper that handles EOFError and
KeyboardInterrupt, defaulting to cancel. Both call sites now use it.
Salvaged from PR #2622 by dieutx (improved from duplicated try/except
to shared helper). Closes#2565.
The update commands called bare 'pip' as fallback when uv wasn't found.
On modern Debian/Ubuntu enforcing PEP 668, this resolves to system pip
which refuses to install in an externally-managed environment.
Use sys.executable -m pip to ensure the venv's pip is used. Fixed in
both cmd_update and _update_via_zip (the PR only caught one instance).
Salvaged from PR #2655 by devorun. Fixes#2648.
Cherry-picked from PR #2542 by ReqX. Adds glm-5-turbo to the direct
zai provider curated model list so /model zai:glm-5-turbo validates
correctly. The model was already in _OPENROUTER_UPSTREAM_MODELS but
missing from the direct provider list.
cmd_update calls input() unconditionally during config migration.
In headless environments (Telegram gateway, systemd), there's no TTY,
so input() throws EOFError and the update crashes.
Guard with sys.stdin.isatty(), default to skipping the migration
prompt when non-interactive.
Salvaged from PR #2850 by devorun. Closes#2848.
The /model command is removed from both the interactive CLI and
messenger gateway (Telegram/Discord/Slack/WhatsApp). Users can
still change models via 'hermes model' CLI subcommand or by
editing config.yaml directly.
Removed:
- CommandDef entry from COMMAND_REGISTRY
- CLI process_command() handler and model autocomplete logic
- Gateway _handle_model_command() and dispatch
- SlashCommandCompleter model_completer_provider parameter
- Two-stage Tab completion and ghost text for /model
- All /model-specific tests
Unaffected:
- /provider command (read-only, shows current model + providers)
- ACP adapter _cmd_model (separate system for VS Code/Zed/JetBrains)
- model_switch.py module (used by ACP)
- 'hermes model' CLI subcommand
Author: Teknium
Centralizes two widely-duplicated patterns into hermes_constants.py:
1. get_hermes_home() — Path resolution for ~/.hermes (HERMES_HOME env var)
- Was copy-pasted inline across 30+ files as:
Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))
- Now defined once in hermes_constants.py (zero-dependency module)
- hermes_cli/config.py re-exports it for backward compatibility
- Removed local wrapper functions in honcho_integration/client.py,
tools/website_policy.py, tools/tirith_security.py, hermes_cli/uninstall.py
2. parse_reasoning_effort() — Reasoning effort string validation
- Was copy-pasted in cli.py, gateway/run.py, cron/scheduler.py
- Same validation logic: check against (xhigh, high, medium, low, minimal, none)
- Now defined once in hermes_constants.py, called from all 3 locations
- Warning log for unknown values kept at call sites (context-specific)
31 files changed, net +31 lines (125 insertions, 94 deletions)
Full test suite: 6179 passed, 0 failed
* feat: nix flake, uv2nix build, dev shell and home manager
* fixed nix run, updated docs for setup
* feat(nix): NixOS module with persistent container mode, managed guards, checks
- Replace homeModules.nix with nixosModules.nix (two deployment modes)
- Mode A (native): hardened systemd service with ProtectSystem=strict
- Mode B (container): persistent Ubuntu container with /nix/store bind-mount,
identity-hash-based recreation, GC root protection, symlink-based updates
- Add HERMES_MANAGED guards blocking CLI config mutation (config set, setup,
gateway install/uninstall) when running under NixOS module
- Add nix/checks.nix with build-time verification (binary, CLI, managed guard)
- Remove container.nix (no Nix-built OCI image; pulls ubuntu:24.04 at runtime)
- Simplify packages.nix (drop fetchFromGitHub submodules, PYTHONPATH wrappers)
- Rewrite docs/nixos-setup.md with full options reference, container
architecture, secrets management, and troubleshooting guide
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Update config.py
* feat(nix): add CI workflow and enhanced build checks
- GitHub Actions workflow for nix flake check + build on linux/macOS
- Entry point sync check to catch pyproject.toml drift
- Expanded managed-guard check to cover config edit
- Wrap hermes-acp binary in Nix package
- Fix Path type mismatch in is_managed()
* Update MCP server package name; bundled skills support
* fix reading .env. instead have container user a common mounted .env file
* feat(nix): container entrypoint with privilege drop and sudo provisioning
Container was running as non-root via --user, which broke apt/pip installs
and caused crashes when $HOME didn't exist. Replace --user with a Nix-built
entrypoint script that provisions the hermes user, sudo (NOPASSWD), and
/home/hermes inside the container on first boot, then drops privileges via
setpriv. Writable layer persists so setup only runs once.
Also expands MCP server options to support HTTP transport and sampling.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix group and user creation in container mode
* feat(nix): persistent /home/hermes and MESSAGING_CWD in container mode
Container mode now bind-mounts ${stateDir}/home to /home/hermes so the
agent's home directory survives container recreation. Previously it lived
in the writable layer and was lost on image/volume/options changes.
Also passes MESSAGING_CWD to the container so the agent finds its
workspace and documents, matching native mode behavior.
Other changes:
- Extract containerDataDir/containerHomeDir bindings (no more magic strings)
- Fix entrypoint chown to run unconditionally (volume mounts always exist)
- Add schema field to container identity hash for auto-recreation
- Add idempotency test (Scenario G) to config-roundtrip check
* docs: add Nix & NixOS setup guide to docs site
Add comprehensive Nix documentation to the Docusaurus site at
website/docs/getting-started/nix-setup.md, covering nix run/profile
install, NixOS module (native + container modes), declarative settings,
secrets management, MCP servers, managed mode, container architecture,
dev shell, flake checks, and full options reference.
- Register nix-setup in sidebar after installation page
- Add Nix callout tip to installation.md linking to new guide
- Add canonical version pointer in docs/nixos-setup.md
* docs: remove docs/nixos-setup.md, consolidate into website docs
Backfill missing details (restart/restartSec in full example,
gateway.pid, 0750 permissions, docker inspect commands) into
the canonical website/docs/getting-started/nix-setup.md and
delete the old standalone file.
* fix(nix): add compression.protect_last_n and target_ratio to config-keys.json
New keys were added to DEFAULT_CONFIG on main, causing the
config-drift check to fail in CI.
* fix(nix): skip checks on aarch64-darwin (onnxruntime wheel missing)
The full Python venv includes onnxruntime (via faster-whisper/STT)
which lacks a compatible uv2nix wheel on aarch64-darwin. Gate all
checks behind stdenv.hostPlatform.isLinux. The package and devShell
still evaluate on macOS.
* fix(nix): skip flake check and build on macOS CI
onnxruntime (transitive dep via faster-whisper) lacks a compatible
uv2nix wheel on aarch64-darwin. Run full checks and build on Linux
only; macOS CI verifies the flake evaluates without building.
* fix(nix): preserve container writable layer across nixos-rebuild
The container identity hash included the entrypoint's Nix store path,
which changes on every nixpkgs update (due to runtimeShell/stdenv
input-addressing). This caused false-positive identity mismatches,
triggering container recreation and losing the persistent writable layer.
- Use stable symlink (current-entrypoint) like current-package already does
- Remove entrypoint from identity hash (only image/volumes/options matter)
- Add GC root for entrypoint so nix-collect-garbage doesn't break it
- Remove global HERMES_HOME env var from addToSystemPackages (conflicted
with interactive CLI use, service already sets its own)
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Each subagent now gets its own IterationBudget instead of sharing the
parent's. The per-subagent cap is controlled by delegation.max_iterations
in config.yaml (default 50). Total iterations across parent + subagents
can exceed the parent's max_iterations, but the user retains control via
the config setting.
Previously, subagents shared the parent's budget, so three parallel
subagents configured for max_iterations=50 racing against a parent that
already used 60 of 90 would each only get ~10 iterations.
Inspired by PR #2928 (Bartok9) which identified the issue (#2873).
- threshold: 0.80 → 0.50 (compress at 50%, not 80%)
- target_ratio: 0.40 → 0.20, now relative to threshold not total context
(20% of 50% = 10% of context as tail budget)
- summary ceiling: 32K → 12K (Gemini can't output more than ~12K)
- Updated DEFAULT_CONFIG, config display, example config, and tests
PR #2554 made these configurable via config.yaml but didn't add them
to DEFAULT_CONFIG or the config display. Users couldn't discover the
new knobs without reading the source.
- threshold: 0.80 (compress at 80% context usage)
- target_ratio: 0.40 (preserve 40% of context as recent tail)
- protect_last_n: 20 (keep last 20 messages uncompressed)
- Updated hermes config display to show all three fields
Move OpenRouter to position 1 in the setup wizard's provider list
to match hermes model ordering. Update default selection index and
fix test expectations for the new ordering.
Setup order: OpenRouter → Nous Portal → Codex → Custom → ...
* feat: env var passthrough for skills and user config
Skills that declare required_environment_variables now have those vars
passed through to sandboxed execution environments (execute_code and
terminal). Previously, execute_code stripped all vars containing KEY,
TOKEN, SECRET, etc. and the terminal blocklist removed Hermes
infrastructure vars — both blocked skill-declared env vars.
Two passthrough sources:
1. Skill-scoped (automatic): when a skill is loaded via skill_view and
declares required_environment_variables, vars that are present in
the environment are registered in a session-scoped passthrough set.
2. Config-based (manual): terminal.env_passthrough in config.yaml lets
users explicitly allowlist vars for non-skill use cases.
Changes:
- New module: tools/env_passthrough.py — shared passthrough registry
- hermes_cli/config.py: add terminal.env_passthrough to DEFAULT_CONFIG
- tools/skills_tool.py: register available skill env vars on load
- tools/code_execution_tool.py: check passthrough before filtering
- tools/environments/local.py: check passthrough in _sanitize_subprocess_env
and _make_run_env
- 19 new tests covering all layers
* docs: add environment variable passthrough documentation
Document the env var passthrough feature across four docs pages:
- security.md: new 'Environment Variable Passthrough' section with
full explanation, comparison table, and security considerations
- code-execution.md: update security section, add passthrough subsection,
fix comparison table
- creating-skills.md: add tip about automatic sandbox passthrough
- skills.md: add note about passthrough after secure setup docs
Live-tested: launched interactive CLI, loaded a skill with
required_environment_variables, verified TEST_SKILL_SECRET_KEY was
accessible inside execute_code sandbox (value: passthrough-test-value-42).
Complete cleanup after dropping the mini-swe-agent submodule (PR #2804):
- Remove MSWEA_SILENT_STARTUP and MSWEA_GLOBAL_CONFIG_DIR env var
settings from cli.py, run_agent.py, hermes_cli/main.py, doctor.py
- Remove mini-swe-agent health check from hermes doctor
- Remove 'minisweagent' from logger suppression lists
- Remove litellm/typer/platformdirs from requirements.txt
- Remove mini-swe-agent install steps from install.ps1 (Windows)
- Remove mini-swe-agent install steps from website docs
- Update all stale comments/docstrings referencing mini-swe-agent
in terminal_tool.py, tools/__init__.py, code_execution_tool.py,
environments/README.md, environments/agent_loop.py
- Remove mini_swe_runner from pyproject.toml py-modules
(still exists as standalone script for RL training use)
- Shrink test_minisweagent_path.py to empty stub
The orphaned mini-swe-agent/ directory on disk needs manual removal:
rm -rf mini-swe-agent/
browser_vision and other browser commands had a hardcoded 30-second
subprocess timeout that couldn't be overridden. Users with slower
machines (local Chromium without GPU) would hit timeouts on screenshot
capture even when setting browser.command_timeout in config.yaml,
because nothing read that value.
Changes:
- Add browser.command_timeout to DEFAULT_CONFIG (default: 30s)
- Add _get_command_timeout() helper that reads config, falls back to 30s
- _run_browser_command() now defaults to config value instead of constant
- browser_vision screenshot no longer hardcodes timeout=30
- browser_navigate uses max(config_timeout, 60) as floor for navigation
Reported by Gamer1988.
Phase 4 of the /model command overhaul.
Both the CLI (cli.py) and gateway (gateway/run.py) /model handlers
had ~50 lines of duplicated core logic: parsing, provider detection,
credential resolution, and model validation. This extracts that
pipeline into hermes_cli/model_switch.py.
New module exports:
- ModelSwitchResult: dataclass with all fields both handlers need
- CustomAutoResult: dataclass for bare '/model custom' results
- switch_model(): core pipeline — parse → detect → resolve → validate
- switch_to_custom_provider(): resolve endpoint + auto-detect model
The shared functions are pure (no I/O side effects). Each caller
handles its own platform-specific concerns:
- CLI: sets self.model/provider/etc, calls save_config_value(), prints
- Gateway: writes config.yaml directly, sets env vars, returns markdown
Net result: -244 lines from handlers, +234 lines in shared module.
The handlers are now ~80 lines each (down from ~150+) and can't drift
apart on core logic.
Fixes#2492.
`generate_systemd_unit()` and `get_python_path()` hardcoded `venv`
as the virtualenv directory name. When the virtualenv is `.venv`
(which `setup-hermes.sh` and `.gitignore` both reference), the
generated systemd unit had incorrect VIRTUAL_ENV and PATH variables.
Introduce `_detect_venv_dir()` which:
1. Checks `sys.prefix` vs `sys.base_prefix` to detect the active venv
2. Falls back to probing `.venv` then `venv` under PROJECT_ROOT
Both `get_python_path()` and `generate_systemd_unit()` now use
this detection instead of hardcoded paths.
Co-authored-by: Hermes <hermes@nousresearch.ai>
* feat(model): persist base_url on /model switch, auto-detect for bare /model custom
Phase 2+3 of the /model command overhaul:
Phase 2 — Persist base_url on model switch:
- CLI: save model.base_url when switching to a non-OpenRouter endpoint;
clear it when switching away from custom to prevent stale URLs
leaking into the new provider's resolution
- Gateway: same logic using direct YAML write
Phase 3 — Better feedback and edge cases:
- Bare '/model custom' now auto-detects the model from the endpoint
using _auto_detect_local_model() and saves all three config values
(model, provider, base_url) atomically
- Shows endpoint URL in success messages when switching to/from
custom providers (both CLI and gateway)
- Clear error messages when no custom endpoint is configured
- Updated test assertions for the additional save_config_value call
Fixes#2562 (Phase 2+3)
* feat(model): support custom:name:model triple syntax for named custom providers
Phase 5 of the /model command overhaul.
Extends parse_model_input() to handle the triple syntax:
/model custom:local-server:qwen → provider='custom:local-server', model='qwen'
/model custom:my-model → provider='custom', model='my-model' (unchanged)
The 'custom:local-server' provider string is already supported by
_get_named_custom_provider() in runtime_provider.py, which matches
it against the custom_providers list in config.yaml. This just wires
the parsing so users can do it from the /model slash command.
Added 4 tests covering single, triple, whitespace, and empty model cases.
resolve_provider('custom') was silently returning 'openrouter', causing
users who set provider: custom in config.yaml to unknowingly route
through OpenRouter instead of their local/custom endpoint. The display
showed 'via openrouter' even when the user explicitly chose custom.
Changes:
- auth.py: Split the conditional so 'custom' returns 'custom' as-is
- runtime_provider.py: _resolve_named_custom_runtime now returns
provider='custom' instead of 'openrouter'
- runtime_provider.py: _resolve_openrouter_runtime returns
provider='custom' when that was explicitly requested
- Add 'no-key-required' placeholder for keyless local servers
- Update existing test + add 5 new tests covering the fix
Fixes#2562
