* 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>
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.
Commit ed27b826 introduced patch-tool redaction corruption that:
- Replaced max_token_length=16000 with max_token_length=***
- Truncated api_key=os.getenv(...) to api_key=os.get...EY
- Truncated tokenizer_name to NousRe...1-8B
- Deleted 409 lines including _run_tests(), _eval_with_timeout(),
evaluate(), wandb_log(), and the __main__ entry point
Restores the file from pre-corruption state (ed27b826^) and re-applies
the two legitimate changes from subsequent commits:
- eval_concurrency config field (from ed27b826)
- docker_image registration in register_task_env_overrides (from ed27b826)
- ManagedServer branching for vLLM/SGLang backends (from 13f54596)
Closes#1737, #1740.
Replace all 5 plain open(config_path, 'w') calls in gateway command
handlers with atomic_yaml_write() from utils.py. This uses the
established tempfile + fsync + os.replace pattern to ensure config.yaml
is never left half-written if the process is killed mid-write.
Affected handlers: /personality (clear + set), /sethome, /reasoning
(_save_config_key helper), /verbose (tool_progress cycling).
Also fixes missing encoding='utf-8' on the /personality clear write.
Salvaged from PR #1211 by albatrosjj.
Replace all 5 plain open(config_path, 'w') calls in gateway command
handlers with atomic_yaml_write() from utils.py. This uses the
established tempfile + fsync + os.replace pattern to ensure config.yaml
is never left half-written if the process is killed mid-write.
Affected handlers: /personality (clear + set), /sethome, /reasoning
(_save_config_key helper), /verbose (tool_progress cycling).
Also fixes missing encoding='utf-8' on the /personality clear write.
Salvaged from PR #1211 by albatrosjj.
Adds a Canvas LMS integration skill under optional-skills/productivity/canvas/
with a Python CLI wrapper (canvas_api.py) for listing courses and assignments
via personal access token auth.
Cherry-picked from PR #1250 by Alicorn-Max-S with:
- Moved from skills/ to optional-skills/ (niche educational integration)
- Fixed hardcoded ~/.hermes/ path to use $HERMES_HOME
- Removed Canvas env vars from .env.example (optional skill)
- Cleaned stale 'mini-swe-agent backend' reference from .env.example header
Co-authored-by: Alicorn-Max-S <Alicorn-Max-S@users.noreply.github.com>
Adds a structured 1-3-1 decision-making framework as an optional skill.
Produces: one problem statement, three options with trade-offs, one
recommendation with definition of done and implementation plan.
Moved to optional-skills/ (niche communication framework, not broadly
needed by default). Improved description with clearer trigger conditions
and replaced implementation-specific example with a generic one.
Based on PR #1262 by Willardgmoore.
Co-authored-by: Willard Moore <willardgmoore@users.noreply.github.com>
* 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>
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.
Community review (devoruncommented) correctly identified that the Slack
adapter re-read SLACK_APP_TOKEN from os.getenv() during disconnect,
which could differ from the value used during connect if the environment
changed. Discord had the same pattern with self.config.token (less risky
but still not bulletproof).
Both now follow the Telegram pattern: store the token identity on self
at acquire time, use the stored value for release, clear after release.
Also fixes docs: alias naming was hermes-<name> in docs but actual
implementation creates <name> directly (e.g. ~/.local/bin/coder not
~/.local/bin/hermes-coder).
The docs incorrectly showed aliases as 'hermes-work' when the actual
implementation creates 'work' (profile name directly, no prefix).
Rewrote the user guide to lead with the alias pattern:
hermes profile create coder → coder chat, coder setup, etc.
Also clarified that the banner shows 'Profile: coder' and the prompt
shows 'coder ❯' when a non-default profile is active.
Fixed alias paths in command reference (hermes-work → work).
The gateway now ships with a built-in boot-md hook that checks for
~/.hermes/BOOT.md on every startup. If the file exists, the agent
executes its instructions in a background thread. No installation
or configuration needed — just create the file.
No BOOT.md = zero overhead (the hook silently returns).
Implementation:
- gateway/builtin_hooks/boot_md.py: handler with boot prompt,
background thread, [SILENT] suppression, error handling
- gateway/hooks.py: _register_builtin_hooks() called at the start
of discover_and_load() to wire in built-in hooks
- Docs updated: hooks page documents BOOT.md as a built-in feature
Add two new optional skills:
- siyuan (optional-skills/productivity/): SiYuan Note knowledge base
API skill — search, read, create, and manage blocks/documents in a
self-hosted SiYuan instance via curl. Requires SIYUAN_TOKEN.
- scrapling (optional-skills/research/): Intelligent web scraping skill
using the Scrapling library — anti-bot fetching, Cloudflare bypass,
CSS/XPath selectors, spider framework for multi-page crawling.
Placed in optional-skills/ (not bundled) since both are niche tools
that require external dependencies.
Co-authored-by: FEUAZUR <FEUAZUR@users.noreply.github.com>
* fix(discord): clean up deferred "thinking..." after slash commands complete
After a slash command is deferred (interaction.response.defer), the
"thinking..." indicator persisted indefinitely because the code used
followup.send() which creates a separate message instead of replacing
or removing the deferred response.
Fix: use edit_original_response() to replace "thinking..." with the
confirmation text when provided, or delete_original_response() to
remove it when there is no confirmation. Also consolidated /reasoning
and /voice handlers to use _run_simple_slash instead of duplicating
the defer+dispatch pattern.
Fixes#3595.
* docs: update skills catalog — add red-teaming category and all 16 optional skills
The skills catalog was missing:
- red-teaming category with the godmode jailbreaking skill
- The entire optional skills section (16 skills across 10 categories)
Added both with descriptions sourced from each SKILL.md frontmatter.
Verified against the actual skills/ and optional-skills/ directories.
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>
- 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.
Three docs pages updated:
- security.md: New 'Credential File Passthrough' section, updated
sandbox filter table to include Docker/Modal rows, added info box
about Docker env_passthrough merge
- creating-skills.md: New 'Credential File Requirements' section
with frontmatter examples and guidance on when to use env vars
vs credential files
- environment-variables.md: Updated TERMINAL_DOCKER_FORWARD_ENV
description to note auto-passthrough from skills
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
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.
After a slash command is deferred (interaction.response.defer), the
"thinking..." indicator persisted indefinitely because the code used
followup.send() which creates a separate message instead of replacing
or removing the deferred response.
Fix: use edit_original_response() to replace "thinking..." with the
confirmation text when provided, or delete_original_response() to
remove it when there is no confirmation. Also consolidated /reasoning
and /voice handlers to use _run_simple_slash instead of duplicating
the defer+dispatch pattern.
Fixes#3595.
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.
parallel-cli is a paid third-party vendor skill that requires
PARALLEL_API_KEY, but it was shipped in the default skills/ directory
with no env-var gate. This caused it to appear in every user's system
prompt even when they have no Parallel account or API key.
Move it to optional-skills/ so it is only visible through the Skills
Hub and must be explicitly installed. Also remove it from the default
skills catalog docs.
Adds a complete Docker packaging for Hermes Agent:
- Dockerfile based on debian:13.4 with all deps
- Entrypoint that bootstraps .env, config.yaml, SOUL.md on first run
- CI workflow to build, test, and push to DockerHub
- Documentation for interactive, gateway, and upgrade workflows
Closes#850, #913.
Changes vs original PR:
- Removed pre-created legacy cache/platform dirs from entrypoint
(image_cache, audio_cache, pairing, whatsapp/session) — these are
now created on demand by the application using the consolidated
layout from get_hermes_dir()
- Moved docs from docs/docker.md to website/docs/user-guide/docker.md
and added to Docusaurus sidebar
Co-authored-by: benbarclay <benbarclay@users.noreply.github.com>
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.
Switch MCP HTTP transport from the deprecated streamablehttp_client()
(mcp < 1.24.0) to the new streamable_http_client() API that accepts a
pre-built httpx.AsyncClient.
Changes vs the original PR #3391:
- Separate try/except imports so mcp < 1.24.0 doesn't break (graceful
fallback to deprecated API instead of losing HTTP MCP entirely)
- Wrap httpx.AsyncClient in async-with for proper lifecycle management
(the new SDK API explicitly skips closing caller-provided clients)
- Match SDK's own create_mcp_http_client defaults: follow_redirects=True,
Timeout(connect_timeout, read=300.0)
- Keep deprecated code path as fallback for older SDK versions
Co-authored-by: HenkDz <HenkDz@users.noreply.github.com>
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>
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>
Background agent's KawaiiSpinner wrote \r-based animation and stop()
messages through StdoutProxy, colliding with prompt_toolkit's status bar.
Two fixes:
- display.py: use isinstance(out, StdoutProxy) instead of fragile
hasattr+name check for detecting prompt_toolkit's stdout wrapper
- cli.py: silence bg agent's raw spinner (_print_fn=no-op) and route
thinking updates through the TUI widget only when no foreground
agent is active; clear spinner text in finally block with same guard
Closes#2718
Co-authored-by: kshitijk4poor <kshitijk4poor@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.
* 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>
Salvage of PR #3310 (luojiesi). When DISCORD_IGNORE_NO_MENTION=true (default), messages that @mention other users but not the bot are silently skipped in server channels. DMs excluded — mentions there are just references.
Co-Authored-By: luojiesi <luojiesi@users.noreply.github.com>
Activation script, tmpfiles, and container entrypoint now agree on
0750 for all directories. Tighten config.yaml and workspace documents
from 0644 to 0640 (group-readable, no world access). Add explicit
chmod for .managed marker and container $TARGET_HOME to eliminate
umask dependence. Secrets (auth.json, .env) remain 0600.
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().
The _on_text_changed fallback only detected pastes when all characters
arrived in a single event (chars_added > 1). Some terminals (notably
VSCode integrated terminal in certain configs) may deliver paste data
differently, causing the fallback to miss.
Add a second heuristic: if the newline count jumps by 4+ in a single
text-change event, treat it as a paste. Alt+Enter only adds 1 newline
per event, so this never false-positives on manual multi-line input.
Also fixes: the fallback path was missing _paste_just_collapsed flag
set before replacing buffer text, which could cause a re-trigger loop.
New installs get a cleaner structure:
cache/images/ (was image_cache/)
cache/audio/ (was audio_cache/)
cache/documents/ (was document_cache/)
cache/screenshots/ (was browser_screenshots/)
platforms/whatsapp/session/ (was whatsapp/session/)
platforms/matrix/store/ (was matrix/store/)
platforms/pairing/ (was pairing/)
Existing installs are unaffected -- get_hermes_dir() checks for the
old path first and uses it if present. No migration needed.
Adds get_hermes_dir(new_subpath, old_name) helper to hermes_constants.py
for reuse by any future subsystem.
Add the gstack community skills repo to the default tap list and fix
skill_identifier construction for repos with an empty path prefix.
Co-authored-by: Tugrul Guner <tugrulguner@users.noreply.github.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>
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 exiting a session that has a title (auto-generated or manual),
the exit summary now also shows:
hermes -c "Session Title"
alongside the existing hermes --resume <id> command.
Also adds the title to the session info block.
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>
