1. Fully lazy imports: sounddevice, numpy, elevenlabs, edge_tts, and
openai are never imported at module level. Each is imported only when
the feature is explicitly activated, preventing crashes in headless
environments (SSH, Docker, WSL, no PortAudio).
2. No core agent loop changes: streaming TTS path extracted from
_interruptible_api_call() into separate _streaming_api_call() method.
The original method is restored to its upstream form.
3. Configurable key binding: push-to-talk key changed from Ctrl+R
(conflicts with readline reverse-search) to Ctrl+B by default.
Configurable via voice.push_to_talk_key in config.yaml.
4. Environment detection: new detect_audio_environment() function checks
for SSH, Docker, WSL, and missing audio devices before enabling voice
mode. Auto-disables with clear warnings in incompatible environments.
5. Graceful degradation: every audio touchpoint (sd.play, sd.InputStream,
sd.OutputStream) wrapped in try/except with ImportError/OSError
handling. Failures produce warnings, not crashes.
- Fix Gemini streaming tool call merge bug: multiple tool calls with same
index but different IDs are now parsed as separate calls instead of
concatenating names (e.g. ha_call_serviceha_call_service)
- Handle partial results in voice mode: show error and stop continuous
mode when agent returns partial/failed results with empty response
- Fix error display during streaming TTS: error messages are shown in
full response box even when streaming box was already opened
- Add duplicate sentence filter in TTS: skip near-duplicate sentences
from LLM repetition
- Fix fake HA server state mutation: turn_on/turn_off/set_temperature
correctly update entity states; temperature sensor simulates change
when thermostat is adjusted
- Audio cues: beep on record start (880Hz), double beep on stop (660Hz)
- Silence detection: auto-stop recording after 3s of silence (RMS-based)
- Continuous mode: auto-restart recording after agent responds
- Ctrl+R starts continuous mode, Ctrl+R during recording exits it
- Waits for TTS to finish before restarting to avoid recording speaker
- Tests: 7 new tests for beep generation and silence detection
The test was failing because GROQ_API_KEY leaked from the environment.
Now both VOICE_TOOLS_OPENAI_KEY and GROQ_API_KEY are removed to
properly test the "no STT key" scenario.
* feat: improve context compaction handoff summaries
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: clearer error when docker backend is unavailable
* fix: preserve docker discovery in backend preflight
Follow up on salvaged PR #940 by reusing find_docker() during the new
availability check so non-PATH Docker Desktop installs still work. Add
a regression test covering the resolved executable path.
* test: make gateway async tests xdist-safe
Replace sync test usage of asyncio.get_event_loop().run_until_complete()
with asyncio.run() so tests do not depend on an ambient current event loop.
Also create the email disconnect poll task inside a running loop. This fixes
xdist/CI failures where workers have no current loop in MainThread.
* feat(skills): add phone-calls skill for outbound AI voice calls
Reformulated from core tool (PR #847 feedback) into a skill with a
standalone helper script. No new dependencies — uses only Python stdlib.
Two providers supported:
- Bland.ai (default): simple setup, one API key
- Vapi: flexible, better voice quality via ElevenLabs/Deepgram + Twilio
Includes:
- SKILL.md with full procedure, safety rules, provider docs, pitfalls
- scripts/phone_call.py CLI helper (call, status, diagnose commands)
* feat(skills): expand phone-calls into optional telephony skill
Follow up on salvaged PR #965 by moving the capability into optional-skills
and broadening it from outbound AI calling to a full telephony skill. Add
Twilio number provisioning, env/state persistence, SMS/MMS, inbound SMS
polling, Vapi import helpers, and a provider decision tree while keeping
telephony out of core runtime code.
* docs(skills): clarify Hermes TTS telephony workflow
---------
Co-authored-by: aydnOktay <xaydinoktay@gmail.com>
Co-authored-by: mormio <morganemoss@gmai.com>
- prevent raw MEDIA tag leakage outside the gateway pipeline
- make extract_media handle quoted/backticked paths and optional whitespace
- send Telegram media natively with explicit error/warning handling
- add regression tests for Telegram media dispatch and MEDIA parsing
Follow-up on salvaged PR #975.
Bridge quick_commands from config.yaml into load_gateway_config(),
normalize non-dict quick command config at runtime, and add coverage
for GatewayConfig round-trips plus config.yaml bridging. This makes the
GatewayConfig quick-command fix complete for the real user-facing config
path implicated by issue #973.
Salvaged from PR #932 by Wayne onto current main.
Apply skin-aware prompt symbols and live prompt_toolkit color refresh,
replace lingering hardcoded accent output with active-skin colors, keep
ANSI-safe response rendering, preserve secret-capture and approval-prompt
state handling, and add integration coverage for prompt state and style
refresh behavior.
* feat: improve context compaction handoff summaries
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: clearer error when docker backend is unavailable
* fix: preserve docker discovery in backend preflight
Follow up on salvaged PR #940 by reusing find_docker() during the new
availability check so non-PATH Docker Desktop installs still work. Add
a regression test covering the resolved executable path.
* test: make gateway async tests xdist-safe
Replace sync test usage of asyncio.get_event_loop().run_until_complete()
with asyncio.run() so tests do not depend on an ambient current event loop.
Also create the email disconnect poll task inside a running loop. This fixes
xdist/CI failures where workers have no current loop in MainThread.
---------
Co-authored-by: aydnOktay <xaydinoktay@gmail.com>
* feat: improve context compaction handoff summaries
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: clearer error when docker backend is unavailable
* fix: preserve docker discovery in backend preflight
Follow up on salvaged PR #940 by reusing find_docker() during the new
availability check so non-PATH Docker Desktop installs still work. Add
a regression test covering the resolved executable path.
---------
Co-authored-by: aydnOktay <xaydinoktay@gmail.com>
Use asyncio.run in sync tests that were relying on an implicit current event loop. This makes the gateway send-image and Slack connect tests pass reliably under Python 3.11+ and xdist workers.
Add a /reasoning command across gateway adapters so users can
inspect or change reasoning effort without editing config by hand.
Reload reasoning settings from config.yaml before each agent run,
including background tasks, so the next message picks up the new
value consistently.
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.
hermes setup hung indefinitely on headless SSH sessions, Docker
containers, and CI/CD environments because the interactive provider
selection menu could not receive input.
Two-layer fix:
1. sys.stdin.isatty() check — auto-detects non-interactive environments
2. --non-interactive flag support — already in CLI parser, now honored
In both cases the wizard exits immediately with helpful guidance
pointing users to 'hermes config set' commands.
Closes#905
Restore gateway/run.py to current main behavior while keeping tirith startup
and pattern_keys replay, preserve yolo and non-interactive bypass semantics in
the combined guard, and add regression tests for yolo and view-full flows.
- store cron-run sessions with source=cron instead of falling back to cli
- close the per-run SessionDB after completion
- add regression coverage for cron session_db/platform wiring
Integrate tirith as a pre-execution security scanner that detects
homograph URLs, pipe-to-interpreter patterns, terminal injection,
zero-width Unicode, and environment variable manipulation — threats
the existing 50-pattern dangerous command detector doesn't cover.
Architecture: gather-then-decide — both tirith and the dangerous
command detector run before any approval prompt, preventing gateway
force=True replay from bypassing one check when only the other was
shown to the user.
New files:
- tools/tirith_security.py: subprocess wrapper with auto-installer,
mandatory cosign provenance verification, non-blocking background
download, disk-persistent failure markers with retryable-cause
tracking (cosign_missing auto-clears when cosign appears on PATH)
- tests/tools/test_tirith_security.py: 62 tests covering exit code
mapping, fail_open, cosign verification, background install,
HERMES_HOME isolation, and failure recovery
- tests/tools/test_command_guards.py: 21 integration tests for the
combined guard orchestration
Modified files:
- tools/approval.py: add check_all_command_guards() orchestrator,
add allow_permanent parameter to prompt_dangerous_approval()
- tools/terminal_tool.py: replace _check_dangerous_command with
consolidated check_all_command_guards
- cli.py: update _approval_callback for allow_permanent kwarg,
call ensure_installed() at startup
- gateway/run.py: iterate pattern_keys list on replay approval,
call ensure_installed() at startup
- hermes_cli/config.py: add security config defaults, split
commented sections for independent fallback
- cli-config.yaml.example: document tirith security config
Restore the ACP editor-integration implementation that was present on the
original PR branch but did not actually land in main.
Includes:
- acp_adapter/ server, session manager, event bridge, auth, permissions,
and tool helpers
- hermes acp subcommand and hermes-acp entry point
- hermes-acp curated toolset
- ACP registry manifest, setup guide, and ACP test suite
- jupyter-live-kernel data science skill from the original branch
Also updates the revived ACP code for current main by:
- resolving runtime providers through the modern shared provider router
- binding ACP sessions to per-session cwd task overrides
- tracking duplicate same-name tool calls with FIFO IDs
- restoring terminal approval callbacks after prompts
- normalizing supporting docs/skill metadata
Validated with tests/acp and the full pytest suite (-n0).
- Introduced _approval_lock to ensure that approval prompts are handled sequentially, preventing state clobbering from parallel delegation subtasks.
- Updated approval_callback and HermesCLI methods to utilize the lock for managing approval state and deadlines.
- Added tests for the config bridging logic to ensure correct environment variable mapping from config.yaml.
Salvage of PR #1246 by ChatGPT (teknium1 session), resolved against
current main which already includes #1239.
Changes:
- Add minisweagent_path.py: worktree-aware helper that finds
mini-swe-agent/src from either the current checkout or the main
checkout behind a git worktree
- Use the helper in tools/terminal_tool.py and mini_swe_runner.py
instead of naive path-relative lookup that fails in worktrees
- Clean up check_terminal_requirements():
- local: return True (no minisweagent dep, per #1239)
- singularity/ssh: remove unnecessary minisweagent imports
- docker/modal: use importlib.util.find_spec with clear error
- Add regression tests for worktree path discovery and tool resolution
- update managed-server compatibility tests to match the current
ServerManager.tool_parser wiring used by hermes_base_env
- make quick-command CLI assertions accept Rich Text objects, which is how
ANSI-safe output is rendered now
- set HERMES_HOME explicitly in the Discord auto-thread config bridge test
so it loads the intended temporary config file
Validated with the targeted test set and the full pytest suite.
Create a new session DB row when starting fresh from the CLI, reset the
agent DB flush cursor and todo state, and update session timing/session ID
bookkeeping so follow-up logging stays correct.
Also update slash-command descriptions and add regression tests for /new,
/reset, and /clear.
Supersedes PR #899.
Closes#641.
Attach later-turn Honcho recall to the current-turn user message at API
call time instead of appending it to the system prompt. This preserves the
stable system-prefix cache while keeping Honcho continuity context
available for the turn.
Also adds regression coverage for the injection helper and for continuing
sessions so Honcho recall stays out of the system prompt.
Add an integration-style regression test that runs prompt caching output
through the Anthropic adapter for an assistant tool-call turn with empty
content. This locks in the empty-text-block hotfix merged in PR #1216.
Tell the agent what it CANNOT do on Slack and Discord — no searching
channel history, no pinning messages, no managing channels/roles.
Prevents the agent from hallucinating capabilities it doesn't have
and promising actions it can't deliver.
Addresses user feedback: agent says 'I'll search your Slack history'
then goes silent because no Slack-specific tools exist.
* 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.
- Add /thread slash command that creates a Discord thread and starts a
new Hermes session in it. The starter message (if provided) becomes
the first user input in the new session.
- Add discord.auto_thread config option (DISCORD_AUTO_THREAD env var):
when enabled, every message in a text channel automatically creates
a thread, allowing parallel isolated sessions.
- Fix Discord media method signatures to accept metadata kwarg
(send_voice, send_image_file, send_image) — prevents TypeError
when the base adapter passes platform metadata.
- Fix test mock isolation: add app_commands and ForumChannel to
discord mocks so tests pass in full-suite runs.
Based on PRs #866 and #1109 by insecurejezza, modified per review:
removed /channel command (unsafe), added auto_thread feature,
made /thread dispatch new sessions.
Co-authored-by: insecurejezza <insecurejezza@users.noreply.github.com>
Set HERMES_INTERACTIVE=1 via setdefault in run_doctor() so CLI-gated
tool checks (like cronjob) see the same context as the interactive CLI.
Cherry-picked from PR #895 by @stablegenius49.
Fixes#878
Co-authored-by: stablegenius49 <stablegenius49@users.noreply.github.com>
* 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>
---------
Co-authored-by: omerkaz <omerkaz@users.noreply.github.com>
Terminal subprocesses inherit OPENAI_BASE_URL and other provider env
vars loaded from ~/.hermes/.env, silently misrouting external CLIs
like codex. Build a blocklist dynamically from the provider registry
so new providers are automatically covered. Callers that truly need
a blocked var can opt in via the _HERMES_FORCE_ prefix.
Closes#1002
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
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.
The old message referenced 'hermes setup' which doesn't handle
skill-specific env vars. Updated to direct users to load the skill
in the local CLI (which triggers the secure prompt) or add the key
to ~/.hermes/.env manually.
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'
When the model returns multiple tool calls in a single response, they are
now executed concurrently using a thread pool instead of sequentially.
This significantly reduces wall-clock time when multiple independent tools
are batched (e.g. parallel web_search, read_file, terminal calls).
Architecture:
- _execute_tool_calls() dispatches to sequential or concurrent path
- Single tool calls and batches containing 'clarify' use sequential path
- Multiple non-interactive tools use ThreadPoolExecutor (max 8 workers)
- Results are collected and appended to messages in original order
- _invoke_tool() extracted as shared tool invocation helper
Safety:
- Pre-flight interrupt check skips all tools if interrupted
- Per-tool exception handling: one failure doesn't crash the batch
- Result truncation (100k char limit) applied per tool
- Budget pressure injection after all tools complete
- Checkpoints taken before file-mutating tools
- CLI spinner shows batch progress, then per-tool completion messages
Tests: 10 new tests covering dispatch logic, ordering, error handling,
interrupt behavior, truncation, and _invoke_tool routing.
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)
Doctor-only override so honcho shows as available when configured,
even outside a live agent session. Runtime tool gate unchanged.
Cherry-picked from PR #962 by PeterFile, rebased onto current main
(post-#736 merge) with conflict resolution.
Fixes#961
Co-authored-by: PeterFile <PeterFile@users.noreply.github.com>
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
Remove 50 lines of unreachable duplicate model selection logic in
setup_model_provider() for zai/kimi-coding/minimax/minimax-cn providers.
The code referenced undefined `is_coding_plan` variable, crashing setup.
_setup_provider_model_selection() already handles these providers correctly
via _DEFAULT_PROVIDER_MODELS dict.
Fallback paths in send_image_file, send_video, and send_document called
super() without metadata, causing replies to appear outside the thread
when file upload fails. Use self.send() with metadata instead to preserve
thread_ts context.
- Pass self.max_tokens to build_anthropic_kwargs instead of hardcoded None
- Add anthropic case to _try_activate_fallback (was only handling openai-codex)
- Remove 'anthropic in base_url' filter that blocked custom proxy URLs
- Increase MAX_MESSAGE_LENGTH from 3,900 to 39,000 (Slack API allows 40k)
- Implement real typing indicator using assistant.threads.setStatus API
- Shows 'BotName is thinking...' next to the bot name in threads
- Auto-clears when the bot sends a reply
- Requires assistant:write or chat:write scope
- Falls back silently if scope unavailable (reactions still work)
- 4 new tests for typing indicator
Fixes from comprehensive code review and cross-referencing with
clawdbot/OpenCode implementations:
CRITICAL:
- Add one-shot guard (anthropic_auth_retry_attempted) to prevent
infinite 401 retry loops when credentials keep changing
- Fix _is_oauth_token(): managed keys from ~/.claude.json are NOT
regular API keys (don't start with sk-ant-api). Inverted the logic:
only sk-ant-api* is treated as API key auth, everything else uses
Bearer auth + oauth beta headers
HIGH:
- Wrap json.loads(args) in try/except in message conversion — malformed
tool_call arguments no longer crash the entire conversation
- Raise AuthError in runtime_provider when no Anthropic token found
(was silently passing empty string, causing confusing API errors)
- Remove broken _try_anthropic() from auxiliary vision chain — the
centralized router creates an OpenAI client for api_key providers
which doesn't work with Anthropic's Messages API
MEDIUM:
- Handle empty assistant message content — Anthropic rejects empty
content blocks, now inserts '(empty)' placeholder
- Fix setup.py existing_key logic — set to 'KEEP' sentinel instead
of None to prevent falling through to the auth choice prompt
- Add debug logging to _fetch_anthropic_models on failure
Tests: 43 adapter tests (2 new for token detection), 3197 total passed
Feedback fixes:
1. Revert _convert_vision_content — vision is handled by the vision_analyze
tool, not by converting image blocks inline in conversation messages.
Removed the function and its tests.
2. Add Anthropic to 'hermes model' (cmd_model in main.py):
- Added to provider_labels dict
- Added to providers selection list
- Added _model_flow_anthropic() with Claude Code credential auto-detection,
API key prompting, and model selection from catalog.
3. Wire up Anthropic as a vision-capable auxiliary provider:
- Added _try_anthropic() to auxiliary_client.py using claude-sonnet-4
as the vision model (Claude natively supports multimodal)
- Added to the get_vision_auxiliary_client() auto-detection chain
(after OpenRouter/Nous, before Codex/custom)
Cache tracking note: the Anthropic cache metrics branch in run_agent.py
(cache_read_input_tokens / cache_creation_input_tokens) is in the correct
place — it's response-level parsing, same location as the existing
OpenRouter cache tracking. auxiliary_client.py has no cache tracking.
* fix: use session_key instead of chat_id for adapter interrupt lookups
monitor_for_interrupt() in _run_agent was using source.chat_id to query
the adapter's has_pending_interrupt() and get_pending_message() methods.
But the adapter stores interrupt events under build_session_key(source),
which produces a different string (e.g. 'agent:main:telegram:dm' vs '123456').
This key mismatch meant the interrupt was never detected through the
adapter path, which is the only active interrupt path for all adapter-based
platforms (Telegram, Discord, Slack, etc.). The gateway-level interrupt
path (in dispatch_message) is unreachable because the adapter intercepts
the 2nd message in handle_message() before it reaches dispatch_message().
Result: sending a new message while subagents were running had no effect —
the interrupt was silently lost.
Fix: replace all source.chat_id references in the interrupt-related code
within _run_agent() with the session_key parameter, which matches the
adapter's storage keys.
Also adds regression tests verifying session_key vs chat_id consistency.
* debug: add file-based logging to CLI interrupt path
Temporary instrumentation to diagnose why message-based interrupts
don't seem to work during subagent execution. Logs to
~/.hermes/interrupt_debug.log (immune to redirect_stdout).
Two log points:
1. When Enter handler puts message into _interrupt_queue
2. When chat() reads it and calls agent.interrupt()
This will reveal whether the message reaches the queue and
whether the interrupt is actually fired.
* fix: accept unlisted models with warning instead of rejecting
validate_requested_model() previously hard-rejected any model not found
in the provider's API listing. This was too aggressive — users on higher
plan tiers (e.g. Z.AI Pro/Max) may have access to models not shown in
the public listing (like glm-5 on coding endpoints).
Changes:
- validate_requested_model: accept unlisted models with a warning note
instead of blocking. The model is saved to config and used immediately.
- Z.AI setup: always offer glm-5 in the model list regardless of whether
a coding endpoint was detected. Pro/Max plans support it.
- Z.AI setup detection message: softened from 'GLM-5 is not available'
to 'GLM-5 may still be available depending on your plan tier'
After studying clawdbot (OpenClaw) and OpenCode implementations:
## Beta headers
- Add interleaved-thinking-2025-05-14 and fine-grained-tool-streaming-2025-05-14
as common betas (sent with ALL auth types, not just OAuth)
- OAuth tokens additionally get oauth-2025-04-20
- API keys now also get the common betas (previously got none)
## Vision/image support
- Add _convert_vision_content() to convert OpenAI multimodal format
(image_url blocks) to Anthropic format (image blocks with base64/url source)
- Handles both data: URIs (base64) and regular URLs
## Role alternation enforcement
- Anthropic strictly rejects consecutive same-role messages (400 error)
- Add post-processing step that merges consecutive user/assistant messages
- Handles string, list, and mixed content types during merge
## Tool choice support
- Add tool_choice parameter to build_anthropic_kwargs()
- Maps OpenAI values: auto→auto, required→any, none→omit, name→tool
## Cache metrics tracking
- Anthropic uses cache_read_input_tokens / cache_creation_input_tokens
(different from OpenRouter's prompt_tokens_details.cached_tokens)
- Add api_mode-aware branch in run_agent.py cache stats logging
## Credential refresh on 401
- On 401 error during anthropic_messages mode, re-read credentials
via resolve_anthropic_token() (picks up refreshed Claude Code tokens)
- Rebuild client if new token differs from current one
- Follows same pattern as Codex/Nous 401 refresh handlers
## Tests
- 44 adapter tests (8 new: vision conversion, role alternation, tool choice)
- Updated beta header tests to verify new structure
- Full suite: 3198 passed, 0 regressions
* fix: use session_key instead of chat_id for adapter interrupt lookups
monitor_for_interrupt() in _run_agent was using source.chat_id to query
the adapter's has_pending_interrupt() and get_pending_message() methods.
But the adapter stores interrupt events under build_session_key(source),
which produces a different string (e.g. 'agent:main:telegram:dm' vs '123456').
This key mismatch meant the interrupt was never detected through the
adapter path, which is the only active interrupt path for all adapter-based
platforms (Telegram, Discord, Slack, etc.). The gateway-level interrupt
path (in dispatch_message) is unreachable because the adapter intercepts
the 2nd message in handle_message() before it reaches dispatch_message().
Result: sending a new message while subagents were running had no effect —
the interrupt was silently lost.
Fix: replace all source.chat_id references in the interrupt-related code
within _run_agent() with the session_key parameter, which matches the
adapter's storage keys.
Also adds regression tests verifying session_key vs chat_id consistency.
* debug: add file-based logging to CLI interrupt path
Temporary instrumentation to diagnose why message-based interrupts
don't seem to work during subagent execution. Logs to
~/.hermes/interrupt_debug.log (immune to redirect_stdout).
Two log points:
1. When Enter handler puts message into _interrupt_queue
2. When chat() reads it and calls agent.interrupt()
This will reveal whether the message reaches the queue and
whether the interrupt is actually fired.
Follow-up to PR #862 (local skills classification by arceus77-7):
- Remove unnecessary isinstance guard on _read_manifest() return value —
it always returns Dict[str, str], so set() on it suffices.
- Extract repeated hub-dir monkeypatching into a shared pytest fixture (hub_env).
- Add three_source_env fixture for source-classification tests.
- Add _read_manifest monkeypatch to test_do_list_initializes_hub_dir
(was fragile — relied on empty skills list masking the real manifest).
- Add test coverage for --source hub and --source builtin filters.
- Extract _capture() helper to reduce console/StringIO boilerplate.
5 tests, all green.
When a dangerous command is detected and the user is prompted for
approval, long commands are truncated (80 chars in fallback, 70 chars
in the TUI). Users had no way to see the full command before deciding.
This adds a 'View full command' option across all approval interfaces:
- CLI fallback (tools/approval.py): [v]iew option in the prompt menu.
Shows the full command and re-prompts for approval decision.
- CLI TUI (cli.py): 'Show full command' choice in the arrow-key
selection panel. Expands the command display in-place and removes
the view option after use.
- CLI callbacks (callbacks.py): 'view' choice added to the list when
the command exceeds 70 characters.
- Gateway (gateway/run.py): 'full', 'show', 'view' responses reveal
the complete command while keeping the approval pending.
Includes 7 new tests covering view-then-approve, view-then-deny,
short command fallthrough, and double-view behavior.
Closes community feedback about the 80-char cap on dangerous commands.
* fix: /reasoning command output ordering, display, and inline think extraction
Three issues with the /reasoning command:
1. Output interleaving: The command echo used print() while feedback
used _cprint(), causing them to render out-of-order under
prompt_toolkit's patch_stdout. Changed echo to use _cprint() so
all output renders through the same path in correct order.
2. Reasoning display not working: /reasoning show toggled a flag
but reasoning never appeared for models that embed thinking in
inline <think> blocks rather than structured API fields. Added
fallback extraction in _build_assistant_message to capture
<think> block content as reasoning when no structured reasoning
fields (reasoning, reasoning_content, reasoning_details) are
present. This feeds into both the reasoning callback (during
tool loops) and the post-response reasoning box display.
3. Feedback clarity: Added checkmarks to confirm actions, persisted
show/hide to config (was session-only before), and aligned the
status display for readability.
Tests: 7 new tests for inline think block extraction (41 total).
* feat: add /reasoning command to gateway (Telegram/Discord/etc)
The /reasoning command only existed in the CLI — messaging platforms
had no way to view or change reasoning settings. This adds:
1. /reasoning command handler in the gateway:
- No args: shows current effort level and display state
- /reasoning <level>: sets reasoning effort (none/low/medium/high/xhigh)
- /reasoning show|hide: toggles reasoning display in responses
- All changes saved to config.yaml immediately
2. Reasoning display in gateway responses:
- When show_reasoning is enabled, prepends a 'Reasoning' block
with the model's last_reasoning content before the response
- Collapses long reasoning (>15 lines) to keep messages readable
- Uses last_reasoning from run_conversation result dict
3. Plumbing:
- Added _show_reasoning attribute loaded from config at startup
- Propagated last_reasoning through _run_agent return dict
- Added /reasoning to help text and known_commands set
- Uses getattr for _show_reasoning to handle test stubs
4 test files spawn real processes or make live API calls that hang
indefinitely in batch/CI runs. Skip them with pytestmark:
- tests/tools/test_code_execution.py (subprocess spawns)
- tests/tools/test_file_tools_live.py (live LocalEnvironment)
- tests/test_413_compression.py (blocks on process)
- tests/test_agent_loop_tool_calling.py (live OpenRouter API calls)
Also added global 30s signal.alarm timeout in conftest.py as a safety
net, and removed stale nous-api test that hung on OAuth browser login.
Suite now runs in ~55s with no hangs.
- Remove test_nous_api_setup_preserves_model_provider_metadata (nous-api
provider no longer exists, test selected Nous OAuth which hangs waiting
for browser login)
- Fix test_nous_oauth_setup prompt_choice index: 1→0 (Nous Portal is
now first option after nous-api removal)
- gateway/run.py: Take main's _resolve_gateway_model() helper
- hermes_cli/setup.py: Re-apply nous-api removal after merge brought
it back. Fix provider_idx offset (Custom is now index 3, not 4).
- tests/hermes_cli/test_setup.py: Fix custom setup test index (3→4)
Both /model and /provider now show the same unified display:
Current: anthropic/claude-opus-4.6 via OpenRouter
Authenticated providers & models:
[openrouter] ← active
anthropic/claude-opus-4.6 ← current
anthropic/claude-sonnet-4.5
...
[nous]
claude-opus-4-6
gemini-3-flash
...
[openai-codex]
gpt-5.2-codex
gpt-5.1-codex-mini
...
Not configured: Z.AI / GLM, Kimi / Moonshot, ...
Switch model: /model <model-name>
Switch provider: /model <provider>:<model-name>
Example: /model nous:claude-opus-4-6
Users can see all authenticated providers and their models at a glance,
making it easy to switch mid-conversation.
Also added curated model lists for Nous Portal and OpenAI Codex to
hermes_cli/models.py.
Model selection now comes exclusively from config.yaml (set via
'hermes model' or 'hermes setup'). The LLM_MODEL env var is no longer
read or written anywhere in production code.
Why: env vars are per-process/per-user and would conflict in
multi-agent or multi-tenant setups. Config.yaml is file-based and
can be scoped per-user or eventually per-session.
Changes:
- cli.py: Read model from CLI_CONFIG only, not LLM_MODEL/OPENAI_MODEL
- hermes_cli/auth.py: _save_model_choice() no longer writes LLM_MODEL
to .env
- hermes_cli/setup.py: Remove 12 save_env_value('LLM_MODEL', ...)
calls from all provider setup flows
- gateway/run.py: Remove LLM_MODEL fallback (HERMES_MODEL still works
for gateway process runtime)
- cron/scheduler.py: Same
- agent/auxiliary_client.py: Remove LLM_MODEL from custom endpoint
model detection
Phase 2 of the provider router migration — route the main agent's
client construction and fallback activation through
resolve_provider_client() instead of duplicated ad-hoc logic.
run_agent.py:
- __init__: When no explicit api_key/base_url, use
resolve_provider_client(provider, raw_codex=True) for client
construction. Explicit creds (from CLI/gateway runtime provider)
still construct directly.
- _try_activate_fallback: Replace _resolve_fallback_credentials and
its duplicated _FALLBACK_API_KEY_PROVIDERS / _FALLBACK_OAUTH_PROVIDERS
dicts with a single resolve_provider_client() call. The router
handles all provider types (API-key, OAuth, Codex) centrally.
- Remove _resolve_fallback_credentials method and both fallback dicts.
agent/auxiliary_client.py:
- Add raw_codex parameter to resolve_provider_client(). When True,
returns the raw OpenAI client for Codex providers instead of wrapping
in CodexAuxiliaryClient. The main agent needs this for direct
responses.stream() access.
3251 passed, 2 pre-existing unrelated failures.
Update 14 test files to use the new call_llm/async_call_llm mock
patterns instead of the old get_text_auxiliary_client/
get_vision_auxiliary_client tuple returns.
- vision_tools tests: mock async_call_llm instead of _aux_async_client
- browser tests: mock call_llm instead of _aux_vision_client
- flush_memories tests: mock call_llm instead of get_text_auxiliary_client
- session_search tests: mock async_call_llm with RuntimeError
- mcp_tool tests: fix whitelist model config, use side_effect for
multi-response tests
- auxiliary_config_bridge: update for model=None (resolved in router)
3251 passed, 2 pre-existing unrelated failures.
Add centralized call_llm() and async_call_llm() functions that own the
full LLM request lifecycle:
1. Resolve provider + model from task config or explicit args
2. Get or create a cached client for that provider
3. Format request args (max_tokens handling, provider extra_body)
4. Make the API call with max_tokens/max_completion_tokens retry
5. Return the response
Config: expanded auxiliary section with provider:model slots for all
tasks (compression, vision, web_extract, session_search, skills_hub,
mcp, flush_memories). Config version bumped to 7.
Migrated all auxiliary consumers:
- context_compressor.py: uses call_llm(task='compression')
- vision_tools.py: uses async_call_llm(task='vision')
- web_tools.py: uses async_call_llm(task='web_extract')
- session_search_tool.py: uses async_call_llm(task='session_search')
- browser_tool.py: uses call_llm(task='vision'/'web_extract')
- mcp_tool.py: uses call_llm(task='mcp')
- skills_guard.py: uses call_llm(provider='openrouter')
- run_agent.py flush_memories: uses call_llm(task='flush_memories')
Tests updated for context_compressor and MCP tool. Some test mocks
still need updating (15 remaining failures from mock pattern changes,
2 pre-existing).
Prevent stale Honcho tool exposure in context/local modes, restore reliable async write retry behavior, and ensure SOUL.md migration uploads target the AI peer instead of the user peer. Also align Honcho CLI key checks with host-scoped apiKey resolution and lock the fixes with regression tests.
Made-with: Cursor
When a new user runs 'hermes setup' for the first time and ~/.openclaw/
exists, the wizard now asks if they want to import their OpenClaw data
before API/tool configuration begins.
If accepted, the existing migration script from optional-skills/ is
loaded dynamically and run with the 'full' preset — importing settings,
memories, skills, API keys, and platform configs. Config is reloaded
afterward so imported values (like API keys) are available for the
remaining setup steps.
The migration is only offered on first-time setup (not returning users)
and handles errors gracefully without blocking setup completion.
Closes#829
Matches Hermes' native session naming (title if set, otherwise
session-scoped). Not a breaking change -- no memory data is lost,
old sessions remain in Honcho.
When hermes-agent runs as a systemd service, Docker container, or
headless daemon, the stdout pipe can become unavailable (idle timeout,
buffer exhaustion, socket reset). Any print() call then raises
OSError: [Errno 5] Input/output error, crashing run_conversation()
and causing cron jobs to fail.
Rather than wrapping individual print() calls (68 in run_conversation
alone), this adds a transparent _SafeWriter wrapper installed once at
the start of run_conversation(). It delegates all writes to the real
stdout and silently catches OSError. Zero overhead on the happy path,
comprehensive coverage of all print calls including future ones.
Fixes#845
Co-authored-by: J0hnLawMississippi <J0hnLawMississippi@users.noreply.github.com>
- Forum parent channel IDs now match free-response list (add a forum
channel ID and all its threads respond without mention)
- Better thread chat names: 'Guild / forum / thread' for forum threads
- Add discord.require_mention and discord.free_response_channels to
config.yaml (bridged to env vars, env vars still override)
- Keep require_mention defaulting to true (safe for shared servers)
Cherry-picked from PR #867 by insecurejezza with default fix and
config.yaml integration.
Co-authored-by: insecurejezza <insecurejezza@users.noreply.github.com>
Address merge-blocking review feedback by removing unsafe signal handler overrides, wiring next-turn Honcho prefetch, restoring per-directory session defaults, and exposing all Honcho tools to the model surface. Also harden prefetch cache access with public thread-safe accessors and remove duplicate browser cleanup code.
Made-with: Cursor
Three new tests for the naive timestamp fix (PR #807):
- test_ensure_aware_naive_preserves_absolute_time: verifies UTC equivalent
is preserved when interpreting naive datetimes as system-local time
- test_ensure_aware_normalizes_aware_to_hermes_tz: verifies already-aware
datetimes are normalized to Hermes tz without shifting the instant
- test_ensure_aware_due_job_not_skipped_when_system_ahead: end-to-end
regression test for the original bug scenario
_discover_one() caught all exceptions and returned [], making
asyncio.gather(return_exceptions=True) redundant. The
isinstance(result, Exception) branch in _discover_all() was dead
code, so failed_count was always 0. This caused:
- No summary printed when all servers fail (silent failure)
- ok_servers always equaling total_servers (misleading count)
- Unused variables transport_desc and transport_type
Fix: let exceptions propagate to gather() so failed_count increments
correctly. Move per-server failure logging to _discover_all(). Remove
dead variables.
Two fixes for context overflow handling:
1. Proactive compression after tool execution: The compression check now
estimates the next prompt size using real token counts from the last API
response (prompt_tokens + completion_tokens) plus a conservative estimate
of newly appended tool results (chars // 3 for JSON-heavy content).
Previously, should_compress() only checked last_prompt_tokens which
didn't account for tool results — so a 130k prompt + 100k chars of tool
output would pass the 140k threshold check but fail the 200k API limit.
2. Safety net: Added 'prompt is too long' to context-length error detection
phrases. Anthropic returns 'prompt is too long: N tokens > M maximum'
on HTTP 400, which wasn't matched by existing phrases. This ensures
compression fires even if the proactive check underestimates.
Fixes#813
- test_agent_loop_tool_calling.py: import atroposlib at module level
to trigger skip (environments.agent_loop is now importable without
atroposlib due to __init__.py graceful fallback)
- test_modal_sandbox_fixes.py: skip TestToolResolution tests when
minisweagent not installed
- environments/__init__.py: try/except on atroposlib imports so
submodules like tool_call_parsers remain importable standalone
- test_agent_loop.py, test_tool_call_parsers.py,
test_managed_server_tool_support.py: skip at module level when
atroposlib is missing
Guard all test files that import from environments/ or atroposlib
with try/except + pytest.skip(allow_module_level=True) so they
gracefully skip instead of crashing when deps aren't available.
Tests hit a real vLLM server (Qwen/Qwen3-4B-Thinking-2507) via
ManagedServer Phase 2. Auto-skip if server isn't running.
Tests verify:
- Single tool call through full agent loop
- Multi-tool calls across turns
- ManagedServer produces SequenceNodes with tokens/logprobs
- Direct response without tools
- Thinking model produces <think> blocks
Also adds fallback parser in agent_loop.py: when ManagedServer's
ToolCallTranslator can't parse (vLLM not installed), hermes-agent's
standalone parsers extract <tool_call> tags from raw content.
Real LLM calls via OpenRouter using stepfun/step-3.5-flash:free (zero cost).
Falls back to paid models if free model is unavailable.
Tests: single tool call, multi-tool single turn, multi-turn chains,
unknown tool rejection, max_turns limit, direct response (no tools),
tool error handling, AgentResult structure, conversation history.
The weaker assertion (r.exc_info is not None) passes even when
exc_info is (None, None, None). Check r.exc_info[0] is not None
to verify actual exception info is present.
The _aux_async_client mock was already applied on main.
Co-authored-by: OutThisLife <nickolasgustafsson@gmail.com>
