139a5e37a47972730f9d716ef9d96f42b32a21c3
5 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Teknium
|
0dd26c9495 |
fix(tests): fix 78 CI test failures and remove dead test (#9036)
Production fixes: - voice_mode.py: add is_recording property to AudioRecorder (parity with TermuxAudioRecorder) - cronjob_tools.py: add sms example to deliver description Test fixes: - test_real_interrupt_subagent: add missing _execution_thread_id (fixes 19 cascading failures from leaked _build_system_prompt patch) - test_anthropic_error_handling: add _FakeMessages, override _interruptible_streaming_api_call (6 fixes) - test_ctx_halving_fix: add missing request_overrides attribute (4 fixes) - test_context_token_tracking: set _disable_streaming=True for non-streaming test path (4 fixes) - test_dict_tool_call_args: set _disable_streaming=True (1 fix) - test_provider_parity: add model='gpt-4o' for AIGateway tests to meet 64K minimum context (4 fixes) - test_session_race_guard: add user_id to SessionSource (5 fixes) - test_restart_drain/helpers: add user_id to SessionSource (2 fixes) - test_telegram_photo_interrupts: add user_id to SessionSource - test_interrupt: target thread_id for per-thread interrupt system (2 fixes) - test_zombie_process_cleanup: rewrite with object.__new__ for refactored GatewayRunner.stop() (1 fix) - test_browser_camofox_state: update config version 15->17 (1 fix) - test_trajectory_compressor_async: widen lookback window 10->20 for line-shifted AsyncOpenAI (1 fix) - test_voice_mode: fixed by production is_recording addition (5 fixes) - test_voice_cli_integration: add _attached_images to CLI stub (2 fixes) - test_hermes_logging: explicit propagation/level reset for cross-test pollution defense (1 fix) - test_run_agent: add base_url for OpenRouter detection tests (2 fixes) Deleted: - test_inline_think_blocks_reasoning_only_accepted: tested unimplemented inline <think> handling |
||
|
Teknium
|
fd73937ec8 |
feat: component-separated logging with session context and filtering (#7991)
* feat: component-separated logging with session context and filtering Phase 1 — Gateway log isolation: - gateway.log now only receives records from gateway.* loggers (platform adapters, session management, slash commands, delivery) - agent.log remains the catch-all (all components) - errors.log remains WARNING+ catch-all - Moved gateway.log handler creation from gateway/run.py into hermes_logging.setup_logging(mode='gateway') with _ComponentFilter Phase 2 — Session ID injection: - Added set_session_context(session_id) / clear_session_context() API using threading.local() for per-thread session tracking - _SessionFilter enriches every log record with session_tag attribute - Log format: '2026-04-11 10:23:45 INFO [session_id] logger.name: msg' - Session context set at start of run_conversation() in run_agent.py - Thread-isolated: gateway conversations on different threads don't leak Phase 3 — Component filtering in hermes logs: - Added --component flag: hermes logs --component gateway|agent|tools|cli|cron - COMPONENT_PREFIXES maps component names to logger name prefixes - Works with all existing filters (--level, --session, --since, -f) - Logger name extraction handles both old and new log formats Files changed: - hermes_logging.py: _SessionFilter, _ComponentFilter, COMPONENT_PREFIXES, set/clear_session_context(), gateway.log creation in setup_logging() - gateway/run.py: removed redundant gateway.log handler (now in hermes_logging) - run_agent.py: set_session_context() at start of run_conversation() - hermes_cli/logs.py: --component filter, logger name extraction - hermes_cli/main.py: --component argument on logs subparser Addresses community request for component-separated, filterable logging. Zero changes to existing logger names — __name__ already provides hierarchy. * fix: use LogRecord factory instead of per-handler _SessionFilter The _SessionFilter approach required attaching a filter to every handler we create. Any handler created outside our _add_rotating_handler (like the gateway stderr handler, or third-party handlers) would crash with KeyError: 'session_tag' if it used our format string. Replace with logging.setLogRecordFactory() which injects session_tag into every LogRecord at creation time — process-global, zero per-handler wiring needed. The factory is installed at import time (before setup_logging) so session_tag is available from the moment hermes_logging is imported. - Idempotent: marker attribute prevents double-wrapping on module reload - Chains with existing factory: won't break third-party record factories - Removes _SessionFilter from _add_rotating_handler and setup_verbose_logging - Adds tests: record factory injection, idempotency, arbitrary handler compat |
||
|
Siddharth Balyan
|
1789c2699a |
feat(nix): shared-state permission model for interactive CLI users (#6796)
* feat(nix): shared-state permission model for interactive CLI users Enable interactive CLI users in the hermes group to share full read-write state (sessions, memories, logs, cron) with the gateway service via a setgid + group-writable permission model. Changes: nix/nixosModules.nix: - Directories use setgid 2770 (was 0750) so new files inherit the hermes group. home/ stays 0750 (no interactive write needed). - Activation script creates HERMES_HOME subdirs (cron, sessions, logs, memories) — previously Python created them but managed mode now skips mkdir. - Activation migrates existing runtime files to group-writable (chmod g+rw). Nix-managed files (config.yaml, .env, .managed) stay 0640/0644. - Gateway systemd unit gets UMask=0007 so files it creates are 0660. hermes_cli/config.py: - ensure_hermes_home() splits into managed/unmanaged paths. Managed mode verifies dirs exist (raises RuntimeError if not) instead of creating them. Scoped umask(0o007) ensures SOUL.md is created as 0660. hermes_logging.py: - _ManagedRotatingFileHandler subclass applies chmod 0660 after log rotation in managed mode. RotatingFileHandler.doRollover() creates new files via open() which uses the process umask (0022 → 0644), not the scoped umask from ensure_hermes_home(). Verified with a 13-subtest NixOS VM integration test covering setgid, interactive writes, file ownership, migration, and gateway coexistence. Refs: #6044 * Fix managed log file mode on initial open Co-authored-by: Siddharth Balyan <alt-glitch@users.noreply.github.com> * refactor: simplify managed file handler and merge activation loops - Cache is_managed() result in handler __init__ instead of lazy-importing on every _open()/_chmod_if_managed() call. Avoids repeated stat+env checks on log rotation. - Merge two for-loops over the same subdir list in activation script into a single loop (mkdir + chown + chmod + find in one pass). --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Siddharth Balyan <alt-glitch@users.noreply.github.com> |
||
|
Teknium
|
caded0a5e7 |
fix: repair 57 failing CI tests across 14 files (#5823)
* fix: repair 57 failing CI tests across 14 files
Categories of fixes:
**Test isolation under xdist (-n auto):**
- test_hermes_logging: Strip ALL RotatingFileHandlers before each test
to prevent handlers leaked from other xdist workers from polluting counts
- test_code_execution: Force TERMINAL_ENV=local in setUp — prevents Modal
AuthError when another test leaks TERMINAL_ENV=modal
- test_timezone: Same TERMINAL_ENV fix for execute_code timezone tests
- test_codex_execution_paths: Mock _resolve_turn_agent_config to ensure
model resolution works regardless of xdist worker state
**Matrix adapter tests (nio not installed in CI):**
- Add _make_fake_nio() helper with real response classes for isinstance()
checks in production code
- Replace MagicMock(spec=nio.XxxResponse) with fake_nio instances
- Wrap production method calls with patch.dict('sys.modules', {'nio': ...})
so import nio succeeds in method bodies
- Use try/except instead of pytest.importorskip for nio.crypto imports
(importorskip can be fooled by MagicMock in sys.modules)
- test_matrix_voice: Skip entire file if nio is a mock, not just missing
**Stale test expectations:**
- test_cli_provider_resolution: _prompt_provider_choice now takes **kwargs
(default param added); mock getpass.getpass alongside input
- test_anthropic_oauth_flow: Mock getpass.getpass (code switched from input)
- test_gemini_provider: Mock models.dev + OpenRouter API lookups to test
hardcoded defaults without external API variance
- test_code_execution: Add notify_on_complete to blocked terminal params
- test_setup_openclaw_migration: Mock prompt_choice to select 'Full setup'
(new quick-setup path leads to _require_tty → sys.exit in CI)
- test_skill_manager_tool: Patch get_all_skills_dirs alongside SKILLS_DIR
so _find_skill searches tmp_path, not real ~/.hermes/skills/
**Missing attributes in object.__new__ test runners:**
- test_platform_reconnect: Add session_store to _make_runner()
- test_session_race_guard: Add hooks, _running_agents_ts, session_store,
delivery_router to _make_runner()
**Production bug fix (gateway/run.py):**
- Fix sentinel eviction race: _AGENT_PENDING_SENTINEL was immediately
evicted by the stale-detection logic because sentinels have no
get_activity_summary() method, causing _stale_idle=inf >= timeout.
Guard _should_evict with 'is not _AGENT_PENDING_SENTINEL'.
* fix: address remaining CI failures
- test_setup_openclaw_migration: Also mock _offer_launch_chat (called at
end of both quick and full setup paths)
- test_code_execution: Move TERMINAL_ENV=local to module level to protect
ALL test classes (TestEnvVarFiltering, TestExecuteCodeEdgeCases,
TestInterruptHandling, TestHeadTailTruncation) from xdist env leaks
- test_matrix: Use try/except for nio.crypto imports (importorskip can be
fooled by MagicMock in sys.modules under xdist)
|
||
|
Teknium
|
9c96f669a1 |
feat: centralized logging, instrumentation, hermes logs CLI, gateway noise fix (#5430)
Adds comprehensive logging infrastructure to Hermes Agent across 4 phases: **Phase 1 — Centralized logging** - New hermes_logging.py with idempotent setup_logging() used by CLI, gateway, and cron - agent.log (INFO+) and errors.log (WARNING+) with RotatingFileHandler + RedactingFormatter - config.yaml logging: section (level, max_size_mb, backup_count) - All entry points wired (cli.py, main.py, gateway/run.py, run_agent.py) - Fixed debug_helpers.py writing to ./logs/ instead of ~/.hermes/logs/ **Phase 2 — Event instrumentation** - API calls: model, provider, tokens, latency, cache hit % - Tool execution: name, duration, result size (both sequential + concurrent) - Session lifecycle: turn start (session/model/provider/platform), compression (before/after) - Credential pool: rotation events, exhaustion tracking **Phase 3 — hermes logs CLI command** - hermes logs / hermes logs -f / hermes logs errors / hermes logs gateway - --level, --session, --since filters - hermes logs list (file sizes + ages) **Phase 4 — Gateway bug fix + noise reduction** - fix: _async_flush_memories() called with wrong arg count — sessions never flushed - Batched session expiry logs: 6 lines/cycle → 2 summary lines - Added inbound message + response time logging 75 new tests, zero regressions on the full suite. |