* feat: add Vercel AI Gateway as a first-class provider
Adds AI Gateway (ai-gateway.vercel.sh) as a new inference provider
with AI_GATEWAY_API_KEY authentication, live model discovery, and
reasoning support via extra_body.reasoning.
Based on PR #1492 by jerilynzheng.
* feat: add AI Gateway to setup wizard, doctor, and fallback providers
* test: add AI Gateway to api_key_providers test suite
* feat: add AI Gateway to hermes model CLI and model metadata
Wire AI Gateway into the interactive model selection menu and add
context lengths for AI Gateway model IDs in model_metadata.py.
* feat: use claude-haiku-4.5 as AI Gateway auxiliary model
* revert: use gemini-3-flash as AI Gateway auxiliary model
* fix: move AI Gateway below established providers in selection order
---------
Co-authored-by: jerilynzheng <jerilynzheng@users.noreply.github.com>
Co-authored-by: jerilynzheng <zheng.jerilyn@gmail.com>
The URL is now the primary element — displayed in a bordered box
before the browser auto-open attempt. Works for users who SSH into
remote servers where webbrowser.open() silently fails.
Put the authorization URL front and center instead of treating it as
a fallback. Most Hermes users run on remote servers via SSH where
webbrowser.open() silently fails.
Adds our own OAuth login and token refresh flow, independent of Claude
Code CLI. Mirrors the PKCE flow used by pi-ai (clawdbot) and OpenCode:
- run_hermes_oauth_login(): full PKCE authorization code flow
- Opens browser to claude.ai/oauth/authorize
- User pastes code#state back
- Exchanges for access + refresh tokens
- Stores in ~/.hermes/.anthropic_oauth.json (our own file)
- Also writes to ~/.claude/.credentials.json for backward compat
- refresh_hermes_oauth_token(): automatic token refresh
- POST to console.anthropic.com/v1/oauth/token with refresh_token
- Updates both credential files on success
- Credential resolution priority updated:
1. ANTHROPIC_TOKEN env var
2. CLAUDE_CODE_OAUTH_TOKEN env var
3. Hermes OAuth credentials (~/.hermes/.anthropic_oauth.json) ← NEW
4. Claude Code credentials (~/.claude/.credentials.json)
5. ANTHROPIC_API_KEY env var
Uses same CLIENT_ID, endpoints, scopes, and PKCE parameters as
Claude Code / OpenCode / pi-ai. Token refresh happens automatically
before each API call via _try_refresh_anthropic_client_credentials.
* feat: add optional smart model routing
Add a conservative cheap-vs-strong routing option that can send very short/simple turns to a cheaper model across providers while keeping the primary model for complex work. Wire it through CLI, gateway, and cron, and document the config.yaml workflow.
* fix(gateway): remove recursive ExecStop from systemd units, extend TimeoutStopSec to 60s
* fix(gateway): avoid recursive ExecStop in user systemd unit
* fix: extend ExecStop removal and TimeoutStopSec=60 to system unit
The cherry-picked PR #1448 fix only covered the user systemd unit.
The system unit had the same TimeoutStopSec=15 and could benefit
from the same 60s timeout for clean shutdown. Also adds a regression
test for the system unit.
---------
Co-authored-by: Ninja <ninja@local>
* feat(skills): add blender-mcp optional skill for 3D modeling
Control a running Blender instance from Hermes via socket connection
to the blender-mcp addon (port 9876). Supports creating 3D objects,
materials, animations, and running arbitrary bpy code.
Placed in optional-skills/ since it requires Blender 4.3+ desktop
with a third-party addon manually started each session.
* feat(acp): support slash commands in ACP adapter (#1532)
Adds /help, /model, /tools, /context, /reset, /compact, /version
to the ACP adapter (VS Code, Zed, JetBrains). Commands are handled
directly in the server without instantiating the TUI — each command
queries agent/session state and returns plain text.
Unrecognized /commands fall through to the LLM as normal messages.
/model uses detect_provider_for_model() for auto-detection when
switching models, matching the CLI and gateway behavior.
Fixes#1402
* fix(logging): improve error logging in session search tool (#1533)
* fix(gateway): restart on retryable startup failures (#1517)
* feat(email): add skip_attachments option via config.yaml
* feat(email): add skip_attachments option via config.yaml
Adds a config.yaml-driven option to skip email attachments in the
gateway email adapter. Useful for malware protection and bandwidth
savings.
Configure in config.yaml:
platforms:
email:
skip_attachments: true
Based on PR #1521 by @an420eth, changed from env var to config.yaml
(via PlatformConfig.extra) to match the project's config-first pattern.
* docs: document skip_attachments option for email adapter
* fix(telegram): retry on transient TLS failures during connect and send
Add exponential-backoff retry (3 attempts) around initialize() to
handle transient TLS resets during gateway startup. Also catches
TimedOut and OSError in addition to NetworkError.
Add exponential-backoff retry (3 attempts) around send_message() for
NetworkError during message delivery, wrapping the existing Markdown
fallback logic.
Both imports are guarded with try/except ImportError for test
environments where telegram is mocked.
Based on PR #1527 by cmd8. Closes#1526.
* feat: permissive block_anchor thresholds and unicode normalization (#1539)
Salvaged from PR #1528 by an420eth. Closes#517.
Improves _strategy_block_anchor in fuzzy_match.py:
- Add unicode normalization (smart quotes, em/en-dashes, ellipsis,
non-breaking spaces → ASCII) so LLM-produced unicode artifacts
don't break anchor line matching
- Lower thresholds: 0.10 for unique matches (was 0.70), 0.30 for
multiple candidates — if first/last lines match exactly, the
block is almost certainly correct
- Use original (non-normalized) content for offset calculation to
preserve correct character positions
Tested: 3 new scenarios fixed (em-dash anchors, non-breaking space
anchors, very-low-similarity unique matches), zero regressions on
all 9 existing fuzzy match tests.
Co-authored-by: an420eth <an420eth@users.noreply.github.com>
* feat(cli): add file path autocomplete in the input prompt (#1545)
When typing a path-like token (./ ../ ~/ / or containing /),
the CLI now shows filesystem completions in the dropdown menu.
Directories show a trailing slash and 'dir' label; files show
their size. Completions are case-insensitive and capped at 30
entries.
Triggered by tokens like:
edit ./src/ma → shows ./src/main.py, ./src/manifest.json, ...
check ~/doc → shows ~/docs/, ~/documents/, ...
read /etc/hos → shows /etc/hosts, /etc/hostname, ...
open tools/reg → shows tools/registry.py
Slash command autocomplete (/help, /model, etc.) is unaffected —
it still triggers when the input starts with /.
Inspired by OpenCode PR #145 (file path completion menu).
Implementation:
- hermes_cli/commands.py: _extract_path_word() detects path-like
tokens, _path_completions() yields filesystem Completions with
size labels, get_completions() routes to paths vs slash commands
- tests/hermes_cli/test_path_completion.py: 26 tests covering
path extraction, prefix filtering, directory markers, home
expansion, case-insensitivity, integration with slash commands
* feat(privacy): redact PII from LLM context when privacy.redact_pii is enabled
Add privacy.redact_pii config option (boolean, default false). When
enabled, the gateway redacts personally identifiable information from
the system prompt before sending it to the LLM provider:
- Phone numbers (user IDs on WhatsApp/Signal) → hashed to user_<sha256>
- User IDs → hashed to user_<sha256>
- Chat IDs → numeric portion hashed, platform prefix preserved
- Home channel IDs → hashed
- Names/usernames → NOT affected (user-chosen, publicly visible)
Hashes are deterministic (same user → same hash) so the model can
still distinguish users in group chats. Routing and delivery use
the original values internally — redaction only affects LLM context.
Inspired by OpenClaw PR #47959.
* fix(privacy): skip PII redaction on Discord/Slack (mentions need real IDs)
Discord uses <@user_id> for mentions and Slack uses <@U12345> — the LLM
needs the real ID to tag users. Redaction now only applies to WhatsApp,
Signal, and Telegram where IDs are pure routing metadata.
Add 4 platform-specific tests covering Discord, WhatsApp, Signal, Slack.
* feat: smart approvals + /stop command (inspired by OpenAI Codex)
* feat: smart approvals — LLM-based risk assessment for dangerous commands
Adds a 'smart' approval mode that uses the auxiliary LLM to assess
whether a flagged command is genuinely dangerous or a false positive,
auto-approving low-risk commands without prompting the user.
Inspired by OpenAI Codex's Smart Approvals guardian subagent
(openai/codex#13860).
Config (config.yaml):
approvals:
mode: manual # manual (default), smart, off
Modes:
- manual — current behavior, always prompt the user
- smart — aux LLM evaluates risk: APPROVE (auto-allow), DENY (block),
or ESCALATE (fall through to manual prompt)
- off — skip all approval prompts (equivalent to --yolo)
When smart mode auto-approves, the pattern gets session-level approval
so subsequent uses of the same pattern don't trigger another LLM call.
When it denies, the command is blocked without user prompt. When
uncertain, it escalates to the normal manual approval flow.
The LLM prompt is carefully scoped: it sees only the command text and
the flagged reason, assesses actual risk vs false positive, and returns
a single-word verdict.
* feat: make smart approval model configurable via config.yaml
Adds auxiliary.approval section to config.yaml with the same
provider/model/base_url/api_key pattern as other aux tasks (vision,
web_extract, compression, etc.).
Config:
auxiliary:
approval:
provider: auto
model: '' # fast/cheap model recommended
base_url: ''
api_key: ''
Bridged to env vars in both CLI and gateway paths so the aux client
picks them up automatically.
* feat: add /stop command to kill all background processes
Adds a /stop slash command that kills all running background processes
at once. Currently users have to process(list) then process(kill) for
each one individually.
Inspired by OpenAI Codex's separation of interrupt (Ctrl+C stops current
turn) from /stop (cleans up background processes). See openai/codex#14602.
Ctrl+C continues to only interrupt the active agent turn — background
dev servers, watchers, etc. are preserved. /stop is the explicit way
to clean them all up.
* feat: first-class plugin architecture + hide status bar cost by default (#1544)
The persistent status bar now shows context %, token counts, and
duration but NOT $ cost by default. Cost display is opt-in via:
display:
show_cost: true
in config.yaml, or: hermes config set display.show_cost true
The /usage command still shows full cost breakdown since the user
explicitly asked for it — this only affects the always-visible bar.
Status bar without cost:
⚕ claude-sonnet-4 │ 12K/200K │ 6% │ 15m
Status bar with show_cost: true:
⚕ claude-sonnet-4 │ 12K/200K │ 6% │ $0.06 │ 15m
* feat: improve memory prioritization + aggressive skill updates (inspired by OpenAI Codex)
* feat: improve memory prioritization — user preferences over procedural knowledge
Inspired by OpenAI Codex's memory prompt improvements (openai/codex#14493)
which focus memory writes on user preferences and recurring patterns
rather than procedural task details.
Key insight: 'Optimize for reducing future user steering — the most
valuable memory prevents the user from having to repeat themselves.'
Changes:
- MEMORY_GUIDANCE (prompt_builder.py): added prioritization hierarchy
and the core principle about reducing user steering
- MEMORY_SCHEMA (memory_tool.py): reordered WHEN TO SAVE list to put
corrections first, added explicit PRIORITY guidance
- Memory nudge (run_agent.py): now asks specifically about preferences,
corrections, and workflow patterns instead of generic 'anything'
- Memory flush (run_agent.py): now instructs to prioritize user
preferences and corrections over task-specific details
* feat: more aggressive skill creation and update prompting
Press harder on skill updates — the agent should proactively patch
skills when it encounters issues during use, not wait to be asked.
Changes:
- SKILLS_GUIDANCE: 'consider saving' → 'save'; added explicit instruction
to patch skills immediately when found outdated/wrong
- Skills header: added instruction to update loaded skills before finishing
if they had missing steps or wrong commands
- Skill nudge: more assertive ('save the approach' not 'consider saving'),
now also prompts for updating existing skills used in the task
- Skill nudge interval: lowered default from 15 to 10 iterations
- skill_manage schema: added 'patch it immediately' to update triggers
* feat: first-class plugin architecture (#1555)
Plugin system for extending Hermes with custom tools, hooks, and
integrations — no source code changes required.
Core system (hermes_cli/plugins.py):
- Plugin discovery from ~/.hermes/plugins/, .hermes/plugins/, and
pip entry_points (hermes_agent.plugins group)
- PluginContext with register_tool() and register_hook()
- 6 lifecycle hooks: pre/post tool_call, pre/post llm_call,
on_session_start/end
- Namespace package handling for relative imports in plugins
- Graceful error isolation — broken plugins never crash the agent
Integration (model_tools.py):
- Plugin discovery runs after built-in + MCP tools
- Plugin tools bypass toolset filter via get_plugin_tool_names()
- Pre/post tool call hooks fire in handle_function_call()
CLI:
- /plugins command shows loaded plugins, tool counts, status
- Added to COMMANDS dict for autocomplete
Docs:
- Getting started guide (build-a-hermes-plugin.md) — full tutorial
building a calculator plugin step by step
- Reference page (features/plugins.md) — quick overview + tables
- Covers: file structure, schemas, handlers, hooks, data files,
bundled skills, env var gating, pip distribution, common mistakes
Tests: 16 tests covering discovery, loading, hooks, tool visibility.
* fix: hermes update causes dual gateways on macOS (launchd)
Three bugs worked together to create the dual-gateway problem:
1. cmd_update only checked systemd for gateway restart, completely
ignoring launchd on macOS. After killing the PID it would print
'Restart it with: hermes gateway run' even when launchd was about
to auto-respawn the process.
2. launchd's KeepAlive.SuccessfulExit=false respawns the gateway
after SIGTERM (non-zero exit), so the user's manual restart
created a second instance.
3. The launchd plist lacked --replace (systemd had it), so the
respawned gateway didn't kill stale instances on startup.
Fixes:
- Add --replace to launchd ProgramArguments (matches systemd)
- Add launchd detection to cmd_update's auto-restart logic
- Print 'auto-restart via launchd' instead of manual restart hint
* fix: add launchd plist auto-refresh + explicit restart in cmd_update
Two integration issues with the initial fix:
1. Existing macOS users with old plist (no --replace) would never
get the fix until manual uninstall/reinstall. Added
refresh_launchd_plist_if_needed() — mirrors the existing
refresh_systemd_unit_if_needed(). Called from launchd_start(),
launchd_restart(), and cmd_update.
2. cmd_update relied on KeepAlive respawn after SIGTERM rather than
explicit launchctl stop/start. This caused races: launchd would
respawn the old process before the PID file was cleaned up.
Now does explicit stop+start (matching how systemd gets an
explicit systemctl restart), with plist refresh first so the
new --replace flag is picked up.
---------
Co-authored-by: Ninja <ninja@local>
Co-authored-by: alireza78a <alireza78a@users.noreply.github.com>
Co-authored-by: Oktay Aydin <113846926+aydnOktay@users.noreply.github.com>
Co-authored-by: JP Lew <polydegen@protonmail.com>
Co-authored-by: an420eth <an420eth@users.noreply.github.com>
* feat: improve memory prioritization — user preferences over procedural knowledge
Inspired by OpenAI Codex's memory prompt improvements (openai/codex#14493)
which focus memory writes on user preferences and recurring patterns
rather than procedural task details.
Key insight: 'Optimize for reducing future user steering — the most
valuable memory prevents the user from having to repeat themselves.'
Changes:
- MEMORY_GUIDANCE (prompt_builder.py): added prioritization hierarchy
and the core principle about reducing user steering
- MEMORY_SCHEMA (memory_tool.py): reordered WHEN TO SAVE list to put
corrections first, added explicit PRIORITY guidance
- Memory nudge (run_agent.py): now asks specifically about preferences,
corrections, and workflow patterns instead of generic 'anything'
- Memory flush (run_agent.py): now instructs to prioritize user
preferences and corrections over task-specific details
* feat: more aggressive skill creation and update prompting
Press harder on skill updates — the agent should proactively patch
skills when it encounters issues during use, not wait to be asked.
Changes:
- SKILLS_GUIDANCE: 'consider saving' → 'save'; added explicit instruction
to patch skills immediately when found outdated/wrong
- Skills header: added instruction to update loaded skills before finishing
if they had missing steps or wrong commands
- Skill nudge: more assertive ('save the approach' not 'consider saving'),
now also prompts for updating existing skills used in the task
- Skill nudge interval: lowered default from 15 to 10 iterations
- skill_manage schema: added 'patch it immediately' to update triggers
Salvaged from PR #1104 by kshitijk4poor. Closes#683.
Adds a persistent status bar to the CLI showing model name, context
window usage with visual bar, estimated cost, and session duration.
Responsive layout degrades gracefully for narrow terminals.
Changes:
- agent/usage_pricing.py: shared pricing table, cost estimation with
Decimal arithmetic, duration/token formatting helpers
- agent/insights.py: refactored to reuse usage_pricing (eliminates
duplicate pricing table and formatting logic)
- cli.py: status bar with FormattedTextControl fragments, color-coded
context thresholds (green/yellow/orange/red), enhanced /usage with
cost breakdown, 1Hz idle refresh for status bar updates
- tests/test_cli_status_bar.py: status bar snapshot, width collapsing,
usage report with/without pricing, zero-priced model handling
- tests/test_insights.py: verify zero-priced providers show as unknown
Salvage fixes:
- Resolved conflict with voice status bar (both coexist in layout)
- Import _format_context_length from hermes_cli.banner (moved since PR)
Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>
- Add 'emoji' field to ToolEntry and 'get_emoji()' to ToolRegistry
- Add emoji= to all 50+ registry.register() calls across tool files
- Add get_tool_emoji() helper in agent/display.py with 3-tier resolution:
skin override → registry default → hardcoded fallback
- Replace hardcoded emoji maps in run_agent.py, delegate_tool.py, and
gateway/run.py with centralized get_tool_emoji() calls
- Add 'tool_emojis' field to SkinConfig so skins can override per-tool
emojis (e.g. ares skin could use swords instead of wrenches)
- Add 11 tests (5 registry emoji, 6 display/skin integration)
- Update AGENTS.md skin docs table
Based on the approach from PR #1061 by ForgingAlex (emoji centralization
in registry). This salvage fixes several issues from the original:
- Does NOT split the cronjob tool (which would crash on missing schemas)
- Does NOT change image_generate toolset/requires_env/is_async
- Does NOT delete existing tests
- Completes the centralization (gateway/run.py was missed)
- Hooks into the skin system for full customizability
Add base_url/api_key overrides for auxiliary tasks and delegation so users can
route those flows straight to a custom OpenAI-compatible endpoint without
having to rely on provider=main or named custom providers.
Also clear gateway session env vars in test isolation so the full suite stays
deterministic when run from a messaging-backed agent session.
Allow cron runs to keep using send_message for additional destinations, but
skip same-target sends when the scheduler will already auto-deliver the final
response there. Add prompt/tool guidance, docs, and regression coverage for
origin/home-channel resolution and thread-aware comparisons.
Remove diary-style memory framing from the system prompt and memory tool
schema, explicitly steer task/session logs to session_search, and clarify
that session_search is for cross-session recall after checking the current
conversation first. Add regression tests for the updated guidance text.
Seed ~/.hermes/SOUL.md when missing, load SOUL only from HERMES_HOME, and inject raw SOUL content without wrapper text. If the file exists but is empty, nothing is added to the system prompt.
Adapt PR #916 onto current main by replacing the old context summary marker
with a clearer handoff wrapper, updating the summarization prompt for
resume-oriented summaries, and preserving the current call_llm-based
compression path.
* fix: Home Assistant event filtering now closed by default
Previously, when no watch_domains or watch_entities were configured,
ALL state_changed events passed through to the agent, causing users
to be flooded with notifications for every HA entity change.
Now events are dropped by default unless the user explicitly configures:
- watch_domains: list of domains to monitor (e.g. climate, light)
- watch_entities: list of specific entity IDs to monitor
- watch_all: true (new option — opt-in to receive all events)
A warning is logged at connect time if no filters are configured,
guiding users to set up their HA platform config.
All 49 gateway HA tests + 52 HA tool tests pass.
* docs: update Home Assistant integration documentation
- homeassistant.md: Fix event filtering docs to reflect closed-by-default
behavior. Add watch_all option. Replace Python dict config example with
YAML. Fix defaults table (was incorrectly showing 'all'). Add required
configuration warning admonition.
- environment-variables.md: Add HASS_TOKEN and HASS_URL to Messaging section.
- messaging/index.md: Add Home Assistant to description, architecture
diagram, platform toolsets table, and Next Steps links.
* fix(terminal): strip provider env vars from background and PTY subprocesses
Extends the env var blocklist from #1157 to also cover the two remaining
leaky paths in process_registry.py:
- spawn_local() PTY path (line 156)
- spawn_local() background Popen path (line 197)
Both were still using raw os.environ, leaking provider vars to background
processes and interactive PTY sessions. Now uses the same dynamic
_HERMES_PROVIDER_ENV_BLOCKLIST from local.py.
Explicit env_vars passed to spawn_local() still override the blocklist,
matching the existing behavior for callers that intentionally need these.
Gap identified by PR #1004 (@PeterFile).
* feat(delegate): add observability metadata to subagent results
Enrich delegate_task results with metadata from the child AIAgent:
- model: which model the child used
- exit_reason: completed | interrupted | max_iterations
- tokens.input / tokens.output: token counts
- tool_trace: per-tool-call trace with byte sizes and ok/error status
Tool trace uses tool_call_id matching to correctly pair parallel tool
calls with their results, with a fallback for messages without IDs.
Cherry-picked from PR #872 by @omerkaz, with fixes:
- Fixed parallel tool call trace pairing (was always updating last entry)
- Removed redundant 'iterations' field (identical to existing 'api_calls')
- Added test for parallel tool call trace correctness
Co-authored-by: omerkaz <omerkaz@users.noreply.github.com>
* feat(stt): add free local whisper transcription via faster-whisper
Replace OpenAI-only STT with a dual-provider system mirroring the TTS
architecture (Edge TTS free / ElevenLabs paid):
STT: faster-whisper local (free, default) / OpenAI Whisper API (paid)
Changes:
- tools/transcription_tools.py: Full rewrite with provider dispatch,
config loading, local faster-whisper backend, and OpenAI API backend.
Auto-downloads model (~150MB for 'base') on first voice message.
Singleton model instance reused across calls.
- pyproject.toml: Add faster-whisper>=1.0.0 as core dependency
- hermes_cli/config.py: Expand stt config to match TTS pattern with
provider selection and per-provider model settings
- agent/context_compressor.py: Fix .strip() crash when LLM returns
non-string content (dict from llama.cpp, None). Fixes#1100 partially.
- tests/: 23 new tests for STT providers + 2 for compressor fix
- docs/: Updated Voice & TTS page with STT provider table, model sizes,
config examples, and fallback behavior
Fallback behavior:
- Local not installed → OpenAI API (if key set)
- OpenAI key not set → local whisper (if installed)
- Neither → graceful error message to user
Co-authored-by: Jah-yee <Jah-yee@users.noreply.github.com>
---------
Co-authored-by: omerkaz <omerkaz@users.noreply.github.com>
Co-authored-by: Jah-yee <Jah-yee@users.noreply.github.com>
* fix: prevent model/provider mismatch when switching providers during active gateway
When _update_config_for_provider() writes the new provider and base_url
to config.yaml, the gateway (which re-reads config per-message) can pick
up the change before model selection completes. This causes the old model
name (e.g. 'anthropic/claude-opus-4.6') to be sent to the new provider's
API (e.g. MiniMax), which fails.
Changes:
- _update_config_for_provider() now accepts an optional default_model
parameter. When provided and the current model.default is empty or
uses OpenRouter format (contains '/'), it sets a safe default model
for the new provider.
- All setup.py callers for direct-API providers (zai, kimi, minimax,
minimax-cn, anthropic) now pass a provider-appropriate default model.
- _setup_provider_model_selection() now validates the 'Keep current'
choice: if the current model uses OpenRouter format and wouldn't work
with the new provider, it warns and switches to the provider's first
default model instead of silently keeping the incompatible name.
Reported by a user on Home Assistant whose gateway started sending
'anthropic/claude-opus-4.6' to MiniMax's API after running hermes setup.
* fix: auxiliary client uses main model for custom/local endpoints instead of gpt-4o-mini
When a user runs a local server (e.g. Qwen3.5-9B via OPENAI_BASE_URL),
the auxiliary client (context compression, vision, session search) would
send requests for 'gpt-4o-mini' or 'google/gemini-3-flash-preview' to
the local server, which only serves one model — causing 404 errors
mid-task.
Changes:
- _try_custom_endpoint() now reads the user's configured main model via
_read_main_model() (checks OPENAI_MODEL → HERMES_MODEL → LLM_MODEL →
config.yaml model.default) instead of hardcoding 'gpt-4o-mini'.
- resolve_provider_client() auto mode now detects when an OpenRouter-
formatted model override (containing '/') would be sent to a non-
OpenRouter provider (like a local server) and drops it in favor of
the provider's default model.
- Test isolation fixes: properly clear env vars in 'nothing available'
tests to prevent host environment leakage.
When a skill declares required_environment_variables in its YAML
frontmatter, missing env vars trigger a secure TUI prompt (identical
to the sudo password widget) when the skill is loaded. Secrets flow
directly to ~/.hermes/.env, never entering LLM context.
Key changes:
- New required_environment_variables frontmatter field for skills
- Secure TUI widget (masked input, 120s timeout)
- Gateway safety: messaging platforms show local setup guidance
- Legacy prerequisites.env_vars normalized into new format
- Remote backend handling: conservative setup_needed=True
- Env var name validation, file permissions hardened to 0o600
- Redact patterns extended for secret-related JSON fields
- 12 existing skills updated with prerequisites declarations
- ~48 new tests covering skip, timeout, gateway, remote backends
- Dynamic panel widget sizing (fixes hardcoded width from original PR)
Cherry-picked from PR #723 by kshitijk4poor, rebased onto current main
with conflict resolution.
Fixes#688
Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>
anthropic/claude-opus-4.6 (OpenRouter format) was being sent as
claude-opus-4.6 to the Anthropic API, which expects claude-opus-4-6
(hyphens, not dots).
normalize_model_name() now converts dots to hyphens after stripping
the provider prefix, matching Anthropic's naming convention.
Fixes 404: 'model: claude-opus-4.6 was not found'
Fixes Anthropic OAuth/subscription authentication end-to-end:
Auth failures (401 errors):
- Add missing 'claude-code-20250219' beta header for OAuth tokens. Both
clawdbot and OpenCode include this alongside 'oauth-2025-04-20' — without
it, Anthropic's API rejects OAuth tokens with 401 authentication errors.
- Fix _fetch_anthropic_models() to use canonical beta headers from
_COMMON_BETAS + _OAUTH_ONLY_BETAS instead of hardcoding.
Token refresh:
- Add _refresh_oauth_token() — when Claude Code credentials from
~/.claude/.credentials.json are expired but have a refresh token,
automatically POST to console.anthropic.com/v1/oauth/token to get
a new access token. Uses the same client_id as Claude Code / OpenCode.
- Add _write_claude_code_credentials() — writes refreshed tokens back
to ~/.claude/.credentials.json, preserving other fields.
- resolve_anthropic_token() now auto-refreshes expired tokens before
returning None.
Config contamination:
- Anthropic's _model_flow_anthropic() no longer saves base_url to config.
Since resolve_runtime_provider() always hardcodes Anthropic's URL, the
stale base_url was contaminating other providers when users switched
without re-running 'hermes model' (e.g., Codex hitting api.anthropic.com).
- _update_config_for_provider() now pops base_url when passed empty string.
- Same fix in setup.py.
Flow/UX (hermes model command):
- CLAUDE_CODE_OAUTH_TOKEN env var now checked in credential detection
- Reauthentication option when existing credentials found
- run_oauth_setup_token() runs 'claude setup-token' as interactive
subprocess, then auto-detects saved credentials
- Clean has_creds/needs_auth flow in both main.py and setup.py
Tests (14 new):
- Beta header assertions for claude-code-20250219
- Token refresh: successful refresh with credential writeback, failed
refresh returns None, no refresh token returns None
- Credential writeback: new file creation, preserving existing fields
- Auto-refresh integration in resolve_anthropic_token()
- CLAUDE_CODE_OAUTH_TOKEN fallback, credential file auto-discovery
- run_oauth_setup_token() (5 scenarios)
Haiku models don't support extended thinking at all. Without this
guard, claude-haiku-4-5-20251001 would receive type=enabled +
budget_tokens and return a 400 error.
Incorporates the fix from PR #1127 (by frizynn) on top of #1128's
adaptive thinking refactor.
Verified live with Claude Code OAuth:
claude-opus-4-6 → adaptive thinking ✓
claude-haiku-4-5 → no thinking params ✓
claude-sonnet-4 → enabled thinking ✓
For Claude 4.6 models (Opus and Sonnet), the Anthropic API rejects
budget_tokens when thinking.type is 'adaptive'. This was causing a
400 error: 'thinking.adaptive.budget_tokens: Extra inputs are not
permitted'.
Changes:
- Send thinking: {type: 'adaptive'} without budget_tokens for 4.6
- Move effort control to output_config: {effort: ...} per Anthropic docs
- Map Hermes effort levels to Anthropic effort levels (xhigh->max, etc.)
- Narrow adaptive detection to 4.6 models only (4.5 still uses manual)
- Add tests for adaptive thinking on 4.6 and manual thinking on pre-4.6
Fixes#1126
