Salvaged fixes from community PRs:
- fix(model_switch): _read_auth_store → _load_auth_store + fix auth store
key lookup (was checking top-level dict instead of store['providers']).
OAuth providers now correctly detected in /model picker.
Cherry-picked from PR #5911 by Xule Lin (linxule).
- fix(ollama): pass num_ctx to override 2048 default context window.
Ollama defaults to 2048 context regardless of model capabilities. Now
auto-detects from /api/show metadata and injects num_ctx into every
request. Config override via model.ollama_num_ctx. Fixes#2708.
Cherry-picked from PR #5929 by kshitij (kshitijk4poor).
- fix(aux): normalize provider aliases for vision/auxiliary routing.
Adds _normalize_aux_provider() with 17 aliases (google→gemini,
claude→anthropic, glm→zai, etc). Fixes vision routing failure when
provider is set to 'google' instead of 'gemini'.
Cherry-picked from PR #5793 by e11i (Elizabeth1979).
- fix(aux): rewrite MiniMax /anthropic base URLs to /v1 for OpenAI SDK.
MiniMax's inference_base_url ends in /anthropic (Anthropic Messages API),
but auxiliary client uses OpenAI SDK which appends /chat/completions →
404 at /anthropic/chat/completions. Generic _to_openai_base_url() helper
rewrites terminal /anthropic to /v1 for OpenAI-compatible endpoint.
Inspired by PR #5786 by Lempkey.
Added debug logging to silent exception blocks across all fixes.
Co-authored-by: Hermes Agent <hermes@nousresearch.com>
Currently, MCP servers are included on all platforms by default. If a
platform's toolset list does not explicitly name any MCP servers, every
globally enabled MCP server is injected. There is no way to opt a
platform out of MCP servers entirely.
This matters for the API server platform when used as an execution
backend — each spawned agent session gets the full MCP tool schema
injected into its system prompt, dramatically inflating token usage
(e.g. 57K tokens vs 9K without MCP tools) and slowing response times.
Add a "no_mcp" sentinel value for platform_toolsets. When present in a
platform's toolset list, all MCP servers are excluded for that platform.
Other platforms are unaffected.
Usage in config.yaml:
platform_toolsets:
api_server:
- terminal
- file
- web
- no_mcp # exclude all MCP servers
The sentinel is filtered out of the final toolset — it does not appear
as an actual toolset name.
* fix(cli): route error messages through ChatConsole inside patch_stdout
Cherry-pick of PR #5798 by @icn5381.
Replace self.console.print() with ChatConsole().print() for 11 error/status
messages reachable during the interactive session. Inside patch_stdout,
self.console (plain Rich Console) writes raw ANSI escapes that StdoutProxy
mangles into garbled text. ChatConsole uses prompt_toolkit's native
print_formatted_text which renders correctly.
Same class of bug as #2262 — that fix covered agent output but missed
these error paths in _ensure_runtime_credentials, _init_agent, quick
commands, skill loading, and plan mode.
* fix(model-picker): add scrolling viewport to curses provider menu
Cherry-pick of PR #5790 by @Lempkey. Fixes#5755.
_curses_prompt_choice rendered items starting unconditionally from index 0
with no scroll offset. The 'More providers' submenu has 13 entries. On
terminals shorter than ~16 rows, items past the fold were never drawn.
When UP-arrow wrapped cursor from 0 to the last item (Cancel, index 12),
the highlight rendered off-screen — appearing as if only Cancel existed.
Adds scroll_offset tracking that adjusts each frame to keep the cursor
inside the visible window.
* feat(cli): skin-aware compact banner + git state in startup banner
Combined salvage of PR #5922 by @ASRagab and PR #5877 by @xinbenlv.
Compact banner changes (from #5922):
- Read active skin colors and branding instead of hardcoding gold/NOUS HERMES
- Default skin preserves backward-compatible legacy branding
- Non-default skins use their own agent_name and colors
Git state in banner (from #5877):
- New format_banner_version_label() shows upstream/local git hashes
- Full banner title now includes git state (upstream hash, carried commits)
- Compact banner line2 shows the version label with git state
- Widen compact banner max width from 64 to 88 to fit version info
Both the full Rich banner and compact fallback are now skin-aware
and show git state.
- Add 7 unit tests for _profile_arg: default home, named profile,
hash path, nested path, invalid name, systemd integration, launchd integration
- Add stt.local.language to config.yaml (empty = auto-detect)
- Both STT code paths now read config.yaml first, env var fallback,
then default (auto-detect for faster-whisper, 'en' for CLI command)
- HERMES_LOCAL_STT_LANGUAGE env var still works as backward-compat fallback
generate_launchd_plist() and generate_systemd_unit() were missing the
--profile <name> argument in ProgramArguments/ExecStart, causing
hermes gateway start to regenerate plists that fell back to
~/.hermes/active_profile instead of the intended profile.
Fix:
- Add _profile_arg(hermes_home?) helper returning '--profile <name>'
only for ~/.hermes/profiles/<name> paths, empty string otherwise.
- Update generate_launchd_plist() to build ProgramArguments array
dynamically with --profile when applicable.
- Update generate_systemd_unit() both user and system service
branches with {profile_arg} in ExecStart.
This ensures hermes --profile <name> gateway start produces a
service definition that correctly scopes to the named profile.
Replace 10 callsites across 6 files that manually opened config.yaml,
called yaml.safe_load(), and handled missing-file/parse-error fallbacks
with the new read_raw_config() helper from hermes_cli/config.py.
Each migrated site previously had 5-8 lines of boilerplate:
config_path = get_hermes_home() / 'config.yaml'
if config_path.exists():
import yaml
with open(config_path) as f:
cfg = yaml.safe_load(f) or {}
Now reduced to:
from hermes_cli.config import read_raw_config
cfg = read_raw_config()
Migrated files:
- tools/browser_tool.py (4 sites): command_timeout, cloud_provider,
allow_private_urls, record_sessions
- tools/env_passthrough.py: terminal.env_passthrough
- tools/credential_files.py: terminal.credential_files
- tools/transcription_tools.py: stt.model
- hermes_cli/commands.py: config-gated command resolution
- hermes_cli/auth.py (2 sites): model config read + provider reset
Skipped (intentionally):
- gateway/run.py: 10+ sites with local aliases, critical path
- hermes_cli/profiles.py: profile-specific config path
- hermes_cli/doctor.py: reads raw then writes fixes back
- agent/model_metadata.py: different file (context_length_cache.yaml)
- tools/website_policy.py: custom config_path param + error types
Move _PS_CHECK_IMAGE and _PS_EXTRACT_IMAGE above both the native Windows
and WSL2 sections so both can share them. Removes the duplicate
_WIN_PS_CHECK / _WIN_PS_EXTRACT constants.
Add win32 platform branch to clipboard.py so Ctrl+V image paste
works on native Windows (PowerShell / Windows Terminal), not just
WSL2.
Uses the same .NET System.Windows.Forms.Clipboard approach as the
WSL path but calls PowerShell directly instead of powershell.exe
(the WSL cross-call path). Tries 'powershell' first (Windows
PowerShell 5.1, always available), then 'pwsh' (PowerShell 7+).
PowerShell executable is discovered once and cached for the process
lifetime.
Includes 14 new tests covering:
- Platform dispatch (save_clipboard_image + has_clipboard_image)
- Image detection via PowerShell .NET check
- Base64 PNG extraction and decode
- Edge cases: no PowerShell, empty output, invalid base64, timeout
16 callsites across 14 files were re-deriving the hermes home path
via os.environ.get('HERMES_HOME', ...) instead of using the canonical
get_hermes_home() from hermes_constants. This breaks profiles — each
profile has its own HERMES_HOME, and the inline fallback defaults to
~/.hermes regardless.
Fixed by importing and calling get_hermes_home() at each site. For
files already inside the hermes process (agent/, hermes_cli/, tools/,
gateway/, plugins/), this is always safe. Files that run outside the
process context (mcp_serve.py, mcp_oauth.py) already had correct
try/except ImportError fallbacks and were left alone.
Skipped: hermes_constants.py (IS the implementation), env_loader.py
(bootstrap), profiles.py (intentionally manipulates the env var),
standalone scripts (optional-skills/, skills/), and tests.
Comprehensive cleanup across 80 files based on automated (ruff, pyflakes, vulture)
and manual analysis of the entire codebase.
Changes by category:
Unused imports removed (~95 across 55 files):
- Removed genuinely unused imports from all major subsystems
- agent/, hermes_cli/, tools/, gateway/, plugins/, cron/
- Includes imports in try/except blocks that were truly unused
(vs availability checks which were left alone)
Unused variables removed (~25):
- Removed dead variables: connected, inner, channels, last_exc,
source, new_server_names, verify, pconfig, default_terminal,
result, pending_handled, temperature, loop
- Dropped unused argparse subparser assignments in hermes_cli/main.py
(12 instances of add_parser() where result was never used)
Dead code removed:
- run_agent.py: Removed dead ternary (None if False else None) and
surrounding unreachable branch in identity fallback
- run_agent.py: Removed write-only attribute _last_reported_tool
- hermes_cli/providers.py: Removed dead @property decorator on
module-level function (decorator has no effect outside a class)
- gateway/run.py: Removed unused MCP config load before reconnect
- gateway/platforms/slack.py: Removed dead SessionSource construction
Undefined name bugs fixed (would cause NameError at runtime):
- batch_runner.py: Added missing logger = logging.getLogger(__name__)
- tools/environments/daytona.py: Added missing Dict and Path imports
Unnecessary global statements removed (14):
- tools/terminal_tool.py: 5 functions declared global for dicts
they only mutated via .pop()/[key]=value (no rebinding)
- tools/browser_tool.py: cleanup thread loop only reads flag
- tools/rl_training_tool.py: 4 functions only do dict mutations
- tools/mcp_oauth.py: only reads the global
- hermes_time.py: only reads cached values
Inefficient patterns fixed:
- startswith/endswith tuple form: 15 instances of
x.startswith('a') or x.startswith('b') consolidated to
x.startswith(('a', 'b'))
- len(x)==0 / len(x)>0: 13 instances replaced with pythonic
truthiness checks (not x / bool(x))
- in dict.keys(): 5 instances simplified to in dict
- Redefined unused name: removed duplicate _strip_mdv2 import in
send_message_tool.py
Other fixes:
- hermes_cli/doctor.py: Replaced undefined logger.debug() with pass
- hermes_cli/config.py: Consolidated chained .endswith() calls
Test results: 3934 passed, 17 failed (all pre-existing on main),
19 skipped. Zero regressions.
check_nous_free_tier() now caches its result for 180 seconds to avoid
redundant Portal API calls during a session (auxiliary client init,
model selection, login flow all call it independently).
The TTL is short enough that an account upgrade from free to paid is
reflected within 3 minutes. clear_nous_free_tier_cache() is exposed
for explicit invalidation on login/logout.
Adds 4 tests for cache hit, TTL expiry, explicit clear, and TTL bound.
- Show pricing during initial Nous Portal login (was missing from
_login_nous, only shown in the already-logged-in hermes model path)
- Filter free models for paid subscribers: non-allowlisted free models
are hidden; allowlisted models (xiaomi/mimo-v2-pro, xiaomi/mimo-v2-omni)
only appear when actually priced as free
- Detect free-tier accounts via portal api/oauth/account endpoint
(monthly_charge == 0); free-tier users see only free models as
selectable, with paid models shown dimmed and unselectable
- Use xiaomi/mimo-v2-omni as the auxiliary vision model for free-tier
Nous users so vision_analyze and browser_vision work without paid
model access (replaces the default google/gemini-3-flash-preview)
- Unavailable models rendered via print() before TerminalMenu to avoid
simple_term_menu line-width padding artifacts; upgrade URL resolved
from auth state portal_base_url (supports staging/custom portals)
- Add 21 tests covering filter_nous_free_models, is_nous_free_tier,
and partition_nous_models_by_tier
* feat: switch managed browser provider from Browserbase to Browser Use
The Nous subscription tool gateway now routes browser automation through
Browser Use instead of Browserbase. This commit:
- Adds managed Nous gateway support to BrowserUseProvider (idempotency
keys, X-BB-API-Key auth header, external_call_id persistence)
- Removes managed gateway support from BrowserbaseProvider (now
direct-only via BROWSERBASE_API_KEY/BROWSERBASE_PROJECT_ID)
- Updates browser_tool.py fallback: prefers Browser Use over Browserbase
- Updates nous_subscription.py: gateway vendor 'browser-use', auto-config
sets cloud_provider='browser-use' for new subscribers
- Updates tools_config.py: Nous Subscription entry now uses Browser Use
- Updates setup.py, cli.py, status.py, prompt_builder.py display strings
- Updates all affected tests to match new behavior
Browserbase remains fully functional for users with direct API credentials.
The change only affects the managed/subscription path.
* chore: remove redundant Browser Use hint from system prompt
* fix: upgrade Browser Use provider to v3 API
- Base URL: api/v2 -> api/v3 (v2 is legacy)
- Unified all endpoints to use native Browser Use paths:
- POST /browsers (create session, returns cdpUrl)
- PATCH /browsers/{id} with {action: stop} (close session)
- Removed managed-mode branching that used Browserbase-style
/v1/sessions paths — v3 gateway now supports /browsers directly
- Removed unused managed_mode variable in close_session
* fix(browser-use): use X-Browser-Use-API-Key header for managed mode
The managed gateway expects X-Browser-Use-API-Key, not X-BB-API-Key
(which is a Browserbase-specific header). Using the wrong header caused
a 401 AUTH_ERROR on every managed-mode browser session create.
Simplified _headers() to always use X-Browser-Use-API-Key regardless
of direct vs managed mode.
* fix(nous_subscription): browserbase explicit provider is direct-only
Since managed Nous gateway now routes through Browser Use, the
browserbase explicit provider path should not check managed_browser_available
(which resolves against the browser-use gateway). Simplified to direct-only
with managed=False.
* fix(browser-use): port missing improvements from PR #5605
- CDP URL normalization: resolve HTTP discovery URLs to websocket after
cloud provider create_session() (prevents agent-browser failures)
- Managed session payload: send timeout=5 and proxyCountryCode=us for
gateway-backed sessions (prevents billing overruns)
- Update prompt builder, browser_close schema, and module docstring to
replace remaining Browserbase references with Browser Use
- Dynamic /browser status detection via _get_cloud_provider() instead
of hardcoded env var checks (future-proof for new providers)
- Rename post_setup key from 'browserbase' to 'agent_browser'
- Update setup hint to mention Browser Use alongside Browserbase
- Add tests: CDP normalization, browserbase direct-only guard,
managed browser-use gateway, direct browserbase fallback
---------
Co-authored-by: rob-maron <132852777+rob-maron@users.noreply.github.com>
The filter in cmd_update() excluded is_default profiles from the
cross-profile skill sync loop. When running 'hermes update' from a
named profile (e.g. hermes -p coder update), the default profile
(~/.hermes) never received new bundled skills.
Remove the 'not p.is_default' condition so all profiles — including
default — are synced regardless of which profile runs the update.
Reported by olafgeibig.
The credential pool seeder and runtime credential resolver hardcoded
api.z.ai/api/paas/v4 for all Z.AI keys. Keys on the Coding Plan (or CN
endpoint) would hit the wrong endpoint, causing 401/429 errors on the
first request even though a working endpoint exists.
Add _resolve_zai_base_url() that:
- Respects GLM_BASE_URL env var (no probe when explicitly set)
- Probes all candidate endpoints (global, cn, coding-global, coding-cn)
via detect_zai_endpoint() to find one that returns HTTP 200
- Caches the detected endpoint in provider state (auth.json) keyed on
a SHA-256 hash of the API key so subsequent starts skip the probe
- Falls back to the default URL if all probes fail
Wire into both _seed_from_env() in the credential pool and
resolve_api_key_provider_credentials() in the runtime resolver,
matching the pattern from the kimi-coding fix (PR #5566).
Fixes the same class of bug as #5561 but for the zai provider.
When resolve_runtime_provider is called with requested='auto' and
auth.json has a stale active_provider (nous or openai-codex) whose
OAuth refresh token has been revoked, the AuthError now falls through
to the next provider in the chain (e.g. OpenRouter via env vars)
instead of propagating to the user as a blocking error.
When the user explicitly requested the OAuth provider, the error
still propagates so they know to re-authenticate.
Root cause: resolve_provider('auto') checks auth.json for an active
OAuth provider before checking env vars. get_nous_auth_status()
reports logged_in=True if any access_token exists (even expired),
so the Nous path is taken. resolve_nous_runtime_credentials() then
tries to refresh the token, fails with 'Refresh session has been
revoked', and the AuthError bubbles up to the CLI bold-red display.
Adds 3 tests: Nous fallthrough, Codex fallthrough, explicit-request
still raises.
signal-cli is not available via apt or snap. Replace the incorrect
'sudo apt install signal-cli' with the official install method:
downloading from GitHub releases (Linux) or brew (macOS).
Updated both signal.md docs and the gateway.py setup hint.
Inspired by PR #4225 (which proposed snap, also incorrect).
Three bugs causing OpenAI Codex sessions to fail silently:
1. Credential pool vs legacy store disconnect: hermes auth and hermes
model store device_code tokens in the credential pool, but
get_codex_auth_status(), resolve_codex_runtime_credentials(), and
_model_flow_openai_codex() only read from the legacy provider state.
Fresh pool tokens were invisible to the auth status checks and model
selection flow.
2. _import_codex_cli_tokens() imported expired tokens from ~/.codex/
without checking JWT expiry. Combined with _login_openai_codex()
saying 'Login successful!' for expired credentials, users got stuck
in a loop of dead tokens being recycled.
3. _login_openai_codex() accepted expired tokens from
resolve_codex_runtime_credentials() without validating expiry before
telling the user login succeeded.
Fixes:
- get_codex_auth_status() now checks credential pool first, falls back
to legacy provider state
- _model_flow_openai_codex() uses pool-aware auth status for token
retrieval when fetching model lists
- _import_codex_cli_tokens() validates JWT exp claim, rejects expired
- _login_openai_codex() verifies resolved token isn't expiring before
accepting existing credentials
- _run_codex_stream() logs response.incomplete/failed terminal events
with status and incomplete_details for diagnostics
- Codex empty output recovery: captures streamed text during streaming
and synthesizes a response when get_final_response() returns empty
output (handles chatgpt.com backend-api edge cases)
Two fixes:
1. Replace all stale 'hermes login' references with 'hermes auth' across
auth.py, auxiliary_client.py, delegate_tool.py, config.py, run_agent.py,
and documentation. The 'hermes login' command was deprecated; 'hermes auth'
now handles OAuth credential management.
2. Fix credential removal not persisting for singleton-sourced credentials
(device_code for openai-codex/nous, hermes_pkce for anthropic).
auth_remove_command already cleared env vars for env-sourced credentials,
but singleton credentials stored in the auth store were re-seeded by
_seed_from_singletons() on the next load_pool() call. Now clears the
underlying auth store entry when removing singleton-sourced credentials.
Two issues caused Matrix E2EE to silently not work in encrypted rooms:
1. When matrix-nio is installed without the [e2e] extra (no python-olm /
libolm), nio.crypto.ENCRYPTION_ENABLED is False and client.olm is
never initialized. The adapter logged warnings but returned True from
connect(), so the bot appeared online but could never decrypt messages.
Now: check_matrix_requirements() and connect() both hard-fail with a
clear error message when MATRIX_ENCRYPTION=true but E2EE deps are
missing.
2. Without a stable device_id, the bot gets a new device identity on each
restart. Other clients see it as "unknown device" and refuse to share
Megolm session keys. Now: MATRIX_DEVICE_ID env var lets users pin a
stable device identity that persists across restarts and is passed to
nio.AsyncClient constructor + restore_login().
Changes:
- gateway/platforms/matrix.py: add _check_e2ee_deps(), hard-fail in
connect() and check_matrix_requirements(), MATRIX_DEVICE_ID support
in constructor + restore_login
- gateway/config.py: plumb MATRIX_DEVICE_ID into platform extras
- hermes_cli/config.py: add MATRIX_DEVICE_ID to OPTIONAL_ENV_VARS
Closes#3521
When the Codex CLI (or VS Code extension) consumes a refresh token before
Hermes can use it, Hermes previously surfaced a generic 401 error with no
actionable guidance.
- In `refresh_codex_oauth_pure`: detect `refresh_token_reused` from the
OAuth endpoint and raise an AuthError explaining the cause and the exact
steps to recover (run `codex` to refresh, then `hermes login`).
- In `run_agent.py`: when provider is `openai-codex` and HTTP 401 is
received, show Codex-specific recovery steps instead of the generic
"check your API key" message.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Follow-up to PR #5470. Replaces hardcoded ~/.hermes/.env references with
display_hermes_home() for correct behavior under profiles. Also updates
PluginManifest.requires_env type hint to List[Union[str, Dict[str, Any]]]
to document the rich format introduced in #5470.
* feat(tools): add Firecrawl cloud browser provider
Adds Firecrawl (https://firecrawl.dev) as a cloud browser provider
alongside Browserbase and Browser Use. All browser tools route through
Firecrawl's cloud browser via CDP when selected.
- tools/browser_providers/firecrawl.py — FirecrawlProvider
- tools/browser_tool.py — register in _PROVIDER_REGISTRY
- hermes_cli/tools_config.py — add to onboarding provider picker
- hermes_cli/setup.py — add to setup summary
- hermes_cli/config.py — add FIRECRAWL_BROWSER_TTL config
- website/docs/ — browser docs and env var reference
Based on #4490 by @developersdigest.
Co-Authored-By: Developers Digest <124798203+developersdigest@users.noreply.github.com>
* refactor: simplify FirecrawlProvider.emergency_cleanup
Use self._headers() and self._api_url() instead of duplicating
env-var reads and header construction.
* fix: recognize Firecrawl in subscription browser detection
_resolve_browser_feature_state() now handles "firecrawl" as a direct
browser provider (same pattern as "browser-use"), so hermes setup
summary correctly shows "Browser Automation (Firecrawl)" instead of
misreporting as "Local browser".
Also fixes test_config_version_unchanged assertion (11 → 12).
---------
Co-authored-by: Developers Digest <124798203+developersdigest@users.noreply.github.com>
Skills can now declare config.yaml settings via metadata.hermes.config
in their SKILL.md frontmatter. Values are stored under skills.config.*
namespace, prompted during hermes config migrate, shown in hermes config
show, and injected into the skill context at load time.
Also adds the llm-wiki skill (Karpathy's LLM Wiki pattern) as the first
skill to use the new config interface, declaring wiki.path.
Skill config interface (new):
- agent/skill_utils.py: extract_skill_config_vars(), discover_all_skill_config_vars(),
resolve_skill_config_values(), SKILL_CONFIG_PREFIX
- agent/skill_commands.py: _inject_skill_config() injects resolved values
into skill messages as [Skill config: ...] block
- hermes_cli/config.py: get_missing_skill_config_vars(), skill config
prompting in migrate_config(), Skill Settings in show_config()
LLM Wiki skill (skills/research/llm-wiki/SKILL.md):
- Three-layer architecture (raw sources, wiki pages, schema)
- Three operations (ingest, query, lint)
- Session orientation, page thresholds, tag taxonomy, update policy,
scaling guidance, log rotation, archiving workflow
Docs: creating-skills.md, configuration.md, skills.md, skills-catalog.md
Closes#5100
When an alias like 'claude' can't be resolved on the current provider,
_resolve_alias_fallback() tries other providers. Previously it hardcoded
('openrouter', 'nous') — so '/model claude' on z.ai would resolve to
openrouter even if the user doesn't have openrouter credentials but does
have anthropic.
Now the fallback uses the user's actual authenticated providers (detected
via list_authenticated_providers which is backed by the models.dev
in-memory cache). If no authenticated providers are found, falls back to
the old ('openrouter', 'nous') for backwards compatibility.
New helper: get_authenticated_provider_slugs() returns just the slug
strings from list_authenticated_providers().
launchctl kickstart returns exit code 113 ("Could not find service") when
the plist exists but the job hasn't been bootstrapped into the runtime domain.
The existing recovery path only caught exit code 3 ("unloaded"), causing an
unhandled CalledProcessError.
Exit code 113 means the same thing practically -- the service definition needs
bootstrapping before it can be kicked. Add it to the same recovery path that
already handles exit 3, matching the existing pattern in launchd_stop().
Follow-up: add a unit test covering the 113 recovery path.
Centralize the skill → slash command registration that Telegram already had
in commands.py so Discord uses the exact same priority system, filtering,
and cap enforcement:
1. Core/built-in commands (never trimmed)
2. Plugin commands (never trimmed)
3. Skill commands (fill remaining slots, alphabetical, only tier trimmed)
Changes:
hermes_cli/commands.py:
- Rename _TG_NAME_LIMIT → _CMD_NAME_LIMIT (32 chars shared by both platforms)
- Rename _clamp_telegram_names → _clamp_command_names (generic)
- Extract _collect_gateway_skill_entries() — shared plugin + skill
collection with platform filtering, name sanitization, description
truncation, and cap enforcement
- Refactor telegram_menu_commands() to use the shared helper
- Add discord_skill_commands() that returns (name, desc, cmd_key) triples
- Preserve _sanitize_telegram_name() for Telegram-specific name cleaning
gateway/platforms/discord.py:
- Call discord_skill_commands() from _register_slash_commands()
- Create app_commands.Command per skill entry with cmd_key callback
- Respect 100-command global Discord limit
- Log warning when skills are skipped due to cap
Backward-compat aliases preserved for _TG_NAME_LIMIT and
_clamp_telegram_names.
Tests: 9 new tests (7 Discord + 2 backward-compat), 98 total pass.
Inspired by PR #5498 (sprmn24). Closes#5480.
Telegram Bot API requires command names to contain only lowercase a-z,
digits 0-9, and underscores. Skill/plugin names containing characters
like +, /, @, or . caused set_my_commands to fail with
Bot_command_invalid.
Two-layer fix:
- scan_skill_commands(): strip non-alphanumeric/non-hyphen chars from
cmd_key at source, collapse consecutive hyphens, trim edges, skip
names that sanitize to empty string
- _sanitize_telegram_name(): centralized helper used by all 3 Telegram
name generation sites (core commands, plugin commands, skill commands)
with empty-name guard at each call site
Closes#5534
OpenCode Go model names with dots (minimax-m2.7, glm-4.5, kimi-k2.5)
were being mangled to hyphens (minimax-m2-7), causing HTTP 401 errors.
Two code paths were affected:
1. model_normalize.py: opencode-go was incorrectly in DOT_TO_HYPHEN_PROVIDERS
2. run_agent.py: _anthropic_preserve_dots() did not check for opencode-go
Fix:
- Remove opencode-go from _DOT_TO_HYPHEN_PROVIDERS (dots are correct for Go)
- Add opencode-go to _anthropic_preserve_dots() provider check
- Add opencode.ai/zen/go to base_url fallback check
- Add regression tests in tests/test_model_normalize.py
Co-authored-by: jacob3712 <jacob3712@users.noreply.github.com>
When agent_key is missing from auth state (expired, not yet minted,
or mint failed silently), the fallback chain fell through to
access_token — an OAuth bearer token for the Nous portal API, not
an inference credential. The Nous inference API returns 404 because
the OAuth token is not a valid inference key.
Remove the access_token fallback so an empty agent_key correctly
triggers resolve_nous_runtime_credentials() to mint a fresh key.
Closes#5562
After restarting a service-managed gateway (systemd/launchd), the
stale-process sweep calls find_gateway_pids() which returns ALL gateway
PIDs via ps aux — including the one just spawned by the service manager.
The sweep kills it, leaving the user with a stopped gateway and a
confusing 'Restart manually' message.
Fix: add _get_service_pids() to query systemd MainPID and launchd PID
for active gateway services, then exclude those PIDs from the sweep.
Also add exclude_pids parameter to find_gateway_pids() and
kill_gateway_processes() so callers can skip known service-managed PIDs.
Adds 9 targeted tests covering:
- _get_service_pids() for systemd, launchd, empty, and zero-PID cases
- find_gateway_pids() exclude_pids filtering
- cmd_update integration: service PID not killed after restart
- cmd_update integration: manual PID killed while service PID preserved
- Rename per-LLM-call hooks from pre_llm_request/post_llm_request for clarity vs pre_llm_call
- Emit summary kwargs only (counts, usage dict from normalize_usage); keep env_var_enabled for HERMES_DUMP_REQUESTS
- Add is_truthy_value/env_var_enabled to utils; wire hermes_cli.plugins._env_enabled through it
- Update Langfuse local setup doc; add scripts/langfuse_smoketest.py and optional ~/.hermes plugin tests
Made-with: Cursor
Add validate_config_structure() that catches common config.yaml mistakes:
- custom_providers as dict instead of list (missing '-' in YAML)
- fallback_model accidentally nested inside another section
- custom_providers entries missing required fields (name, base_url)
- Missing model section when custom_providers is configured
- Root-level keys that look like misplaced custom_providers fields
Surface these diagnostics at three levels:
1. Startup: print_config_warnings() runs at CLI and gateway module load,
so users see issues before hitting cryptic errors
2. Error time: 'Unknown provider' errors in auth.py and model_switch.py
now include config diagnostics with fix suggestions
3. Doctor: 'hermes doctor' shows a Config Structure section with all
issues and fix hints
Also adds a warning log in runtime_provider.py when custom_providers
is a dict (previously returned None silently).
Motivated by a Discord user who had malformed custom_providers YAML
and got only 'Unknown Provider' with no guidance on what was wrong.
17 new tests covering all validation paths.
All 35 subprocess.run() calls in hermes_cli/gateway.py lacked timeout
parameters. If systemctl, launchctl, loginctl, wmic, or ps blocks,
hermes gateway start/stop/restart/status/install/uninstall hangs
indefinitely with no feedback.
Timeouts tiered by operation type:
- 10s: instant queries (is-active, status, list, ps, tail, journalctl)
- 30s: fast lifecycle (daemon-reload, enable, start, bootstrap, kickstart)
- 90s: graceful shutdown (stop, restart, bootout, kickstart -k) — exceeds
our TimeoutStopSec=60 to avoid premature timeout during shutdown
Special handling: _is_service_running() and launchd_status() catch
TimeoutExpired and treat it as not-running/not-loaded, consistent with
how non-zero return codes are already handled.
Inspired by PR #3732 (dlkakbs) and issue #4057 (SHL0MS).
Reimplemented on current main which has significantly changed launchctl
handling (bootout/bootstrap/kickstart vs legacy load/unload/start/stop).
The _login_nous() call site was pre-filling portal_base_url,
inference_base_url, client_id, and scope with pconfig defaults before
passing them to _nous_device_code_login(). Since pconfig defaults are
always truthy, the env var checks inside the function (HERMES_PORTAL_BASE_URL,
NOUS_PORTAL_BASE_URL, NOUS_INFERENCE_BASE_URL) could never take effect.
Fix: pass None from the call site when no CLI flag is provided, letting
the function's own priority chain handle defaults correctly:
explicit CLI flag > env var > pconfig default.
Addresses the issue reported in PR #5397 by jquesnelle.
Display live per-million-token pricing from /v1/models when listing
models for OpenRouter or Nous Portal. Prices are shown in a
column-aligned table with decimal points vertically aligned for
easy comparison.
Pricing appears in three places:
- /provider slash command (table with In/Out headers)
- hermes model picker (aligned columns in both TerminalMenu and
numbered fallback)
Implementation:
- Add fetch_models_with_pricing() in models.py with per-base_url
module-level cache (one network call per endpoint per session)
- Add _format_price_per_mtok() with fixed 2-decimal formatting
- Add format_model_pricing_table() for terminal table display
- Add get_pricing_for_provider() convenience wrapper
- Update _prompt_model_selection() to accept optional pricing dict
- Wire pricing through _model_flow_openrouter/nous in main.py
- Update test mocks for new pricing parameter
The gateway previously used a hard wall-clock asyncio.wait_for timeout
that killed agents after a fixed duration regardless of activity. This
punished legitimate long-running tasks (subagent delegation, reasoning
models, multi-step research).
Now uses an inactivity-based polling loop that checks the agent's
built-in activity tracker (get_activity_summary) every 5 seconds. The
agent can run indefinitely as long as it's actively calling tools or
receiving API responses. Only fires when the agent has been completely
idle for the configured duration.
Changes:
- Replace asyncio.wait_for with asyncio.wait poll loop checking
agent idle time via get_activity_summary()
- Add agent.gateway_timeout config.yaml key (default 1800s, 0=unlimited)
- Update stale session eviction to use agent idle time instead of
pure wall-clock (prevents evicting active long-running tasks)
- Preserve all existing diagnostic logging and user-facing context
Inspired by PR #4864 (Mibayy) and issue #4815 (BongSuCHOI).
Reimplemented on current main using existing _touch_activity()
infrastructure rather than a parallel tracker.
