- print_success() hardcoded 'source ~/.bashrc' regardless of user's shell
- On macOS (default zsh), ~/.bashrc doesn't exist, leaving users unable to
find the hermes command after install
- Now detects $SHELL and shows the correct file (zshrc/bashrc)
- Also captures .[all] install failure output instead of silencing with
2>/dev/null, so users can diagnose why full extras failed
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>
The sidebar had all categories expanded by default (collapsed: false),
which on mobile created a 60+ item flat list when opening the sidebar.
Reported by danny on Discord.
Changes:
- Set all top-level categories to collapsed: true (tap to expand)
- Enable autoCollapseCategories: true (accordion — opening one section
closes others, prevents the overwhelming flat list)
- Enable hideable sidebar (swipe-to-dismiss on mobile)
- Add mobile CSS: larger touch targets (0.75rem padding), bolder
category headers, visible subcategory indentation with left border,
wider sidebar (85vw / 360px max), darker backdrop overlay
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.
- Combine apt-get update and install into single RUN with cache clearing
- Remove APT lists after installation
- Add --no-cache-dir to pip install
- Add --prefer-offline --no-audit to npm install
- Create .dockerignore to exclude unnecessary files from build context
- Update docker-publish.yml workflow to tag images with release names
- Ensure buildx caching is used (type=gha)
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>
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.
* feat(telegram): add webhook mode as alternative to polling
When TELEGRAM_WEBHOOK_URL is set, the adapter starts an HTTP webhook
server (via python-telegram-bot's start_webhook()) instead of long
polling. This enables cloud platforms like Fly.io and Railway to
auto-wake suspended machines on inbound HTTP traffic.
Polling remains the default — no behavior change unless the env var
is set.
Env vars:
TELEGRAM_WEBHOOK_URL Public HTTPS URL for Telegram to push to
TELEGRAM_WEBHOOK_PORT Local listen port (default 8443)
TELEGRAM_WEBHOOK_SECRET Secret token for update verification
Cherry-picked and adapted from PR #2022 by SHL0MS. Preserved all
current main enhancements (network error recovery, polling conflict
detection, DM topics setup).
Co-authored-by: SHL0MS <SHL0MS@users.noreply.github.com>
* fix: send_document call in background task delivery + vision download timeout
Two fixes salvaged from PR #2269 by amethystani:
1. gateway/run.py: adapter.send_file() → adapter.send_document()
send_file() doesn't exist on BasePlatformAdapter. Background task
media files were silently never delivered (AttributeError swallowed
by except Exception: pass).
2. tools/vision_tools.py: configurable image download timeout via
HERMES_VISION_DOWNLOAD_TIMEOUT env var (default 30s), plus guard
against raise None when max_retries=0.
The third fix in #2269 (opencode-go auth config) was already resolved
on main.
Co-authored-by: amethystani <amethystani@users.noreply.github.com>
* docs: expand terminal backends section + fix feishu MDX build error
---------
Co-authored-by: SHL0MS <SHL0MS@users.noreply.github.com>
Co-authored-by: amethystani <amethystani@users.noreply.github.com>
* 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.
* fix: use SKILLS_DIR not repo path for Telegram menu skill filter
Skills are synced to ~/.hermes/skills/ (SKILLS_DIR), not the repo's
skills/ directory. The previous filter compared against the repo path
so no skills matched. Now checks SKILLS_DIR and excludes .hub/
subdirectory (user-installed hub skills).
* fix: cap Telegram menu at 50 commands — API rejects above ~60
Telegram's setMyCommands returns BOT_COMMANDS_TOO_MUCH when
registering close to 100 commands despite docs claiming 100 is the
limit. Metadata overhead causes rejection above ~60. Cap at 50 for
reliability — remaining commands accessible via /commands.
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.
When the API doesn't provide a call_id for tool calls, the fallback
generated a random uuid4 hex. This made every API call's input unique
when replayed, preventing OpenAI's prompt cache from matching the
prefix across turns.
Replaced all four uuid4 fallback sites with a deterministic hash of
(function_name, arguments, position_index). The same tool call now
always produces the same fallback call_id, preserving cache-friendly
input stability.
Affected code paths:
- _chat_messages_to_responses_input() — Codex input reconstruction
- _normalize_codex_response() — function_call and custom_tool_call
- _build_assistant_message() — assistant message construction
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).
migrate_model_config() was writing `config["model"] = model_str` which
replaces the entire model dict (default, provider, base_url) with a
bare string. This causes 'str' object has no attribute 'get' errors
throughout Hermes when any code does model_cfg.get("default").
Now preserves the existing model dict and only updates the "default"
key, keeping provider/base_url intact.
* 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>
The WhatsApp bridge prepends '⚕ *Hermes Agent*\n────────────\n' to
every outgoing message. In self-chat mode this is necessary to
distinguish the bot's responses from the user's own messages. In bot
mode the messages already come from a different number, making the
prefix redundant and cluttered.
Now only prepends the prefix when WHATSAPP_MODE is 'self-chat' (the
default). Bot mode messages are sent clean.
input() hangs inside prompt_toolkit's TUI event loop — this is a known
pitfall (AGENTS.md). The /tools disable and /tools enable commands used
input() for a Y/N confirmation prompt, causing the terminal to freeze
with no way to type a response.
Fix: remove the confirmation prompt. The user typing '/tools disable web'
is implicit consent. The change is applied directly with a status message.
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
Salvaged from PR #2033 by yoannes. Adds multi-workspace Slack support
so a single Hermes instance can serve multiple Slack workspaces after
OAuth installs.
Changes:
- Support comma-separated bot tokens in SLACK_BOT_TOKEN env var
- Load additional OAuth-persisted tokens from HERMES_HOME/slack_tokens.json
- Route all Slack API calls through workspace-aware _get_client(chat_id)
instead of always using the primary app client
- Track channel → workspace mapping from incoming events
- Per-workspace bot_user_id for correct mention detection
- Workspace-aware file downloads (correct auth token per workspace)
Backward compatible: single-token setups work identically.
Token file format (slack_tokens.json):
{"T12345": {"token": "xoxb-...", "team_name": "My Workspace"}}
Fixed from original PR:
- Uses get_hermes_home() instead of hardcoded ~/.hermes/ path
Co-authored-by: yoannes <yoannes@users.noreply.github.com>
The model was interpreting [SILENT] as a metadata prefix and writing
full reports with [SILENT] slapped at the front. The old instruction
said 'optionally followed by a brief internal note' which gave too
much room. New instruction explicitly says: [SILENT] means nothing
else, do NOT combine it with a report.
* 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>
* 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>
- 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()
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>
Closes gaps that allowed an agent to expose Docker's Remote API to the
internet by writing to /etc/docker/daemon.json.
Terminal tool (approval.py):
- chmod: now catches 666 and symbolic modes (o+w, a+w), not just 777
- cp/mv/install: detected when targeting /etc/
- sed -i/--in-place: detected when targeting /etc/
File tools (file_tools.py):
- write_file and patch now refuse to write to sensitive system paths
(/etc/, /boot/, /usr/lib/systemd/, docker.sock)
- Directs users to the terminal tool (which has approval prompts) for
system file modifications
* add .aac audio file format support to transcription tool
* fix(agent): support full context length resolution for direct Gemini API endpoints
Add generativelanguage.googleapis.com to _URL_TO_PROVIDER so direct
Gemini API users get correct 1M+ context length instead of the 128K
unknown-proxy fallback.
Co-authored-by: bb873 <bb873@users.noreply.github.com>
---------
Co-authored-by: Adrian Scott <adrian@adrianscott.com>
Co-authored-by: bb873 <bb873@users.noreply.github.com>
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>
