mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-29 18:46:59 +00:00
3c7cff843d
Follow-up to #69112. That PR hardened the shared gateway dispatch path in gateway/run.py against the *caller* being cancelled. A second, self-referential cancellation specific to PhotonAdapter sits one layer underneath it and survived that fix. PhotonAdapter is the only platform adapter that awaits _notify_fatal_error() inline, on the same task that detected the fault. Both _monitor_sidecar_health and _supervise_sidecar run as self._sidecar_health_task / self._sidecar_supervisor_task, and the notification routes into GatewayRunner._handle_adapter_fatal_error_impl, which tears the adapter down via _safe_adapter_disconnect -> disconnect(). disconnect() then cancels self._sidecar_health_task and awaits it -- which, when the health task is what raised the notification, means disconnect() cancels its own caller several plain-await frames up. disconnect()'s `task is not asyncio.current_task()` guard does not catch this. The current task where that guard evaluates is the wrapper _await_adapter_cleanup_with_timeout creates around disconnect() via asyncio.ensure_future, not the health task further up the chain, so the guard passes and the cancel lands. CancelledError stopped subclassing Exception in Python 3.8, so the `except Exception` that wrapped the inline notify call never saw it. The health task died silently mid-handoff: no log line, no "exception never retrieved" warning (cancellation is normal asyncio), and no retry. The platform stayed stranded until the gateway was restarted by hand. Fix: dispatch the notification onto a new task, the same pattern DiscordAdapter._handle_bot_task_done already uses for this reason. disconnect() can then cancel the health/supervisor task freely without that cancellation reaching the code still running the handoff, so the handoff always reaches the reconnect queue. Both Photon fatal call sites are converted: the health-poll path (observed wedging) and the sidecar-crash path (same shape, not yet observed). gateway/run.py is untouched. Observed twice on a self-hosted gateway, ~4h38m and ~52min of silent inbound outage, both cleared only by a manual restart, both post-dating #69112's merge. In each case the fatal log line appears and `queued for background reconnection` never does. Tests: new tests/plugins/platforms/photon/test_fatal_notify_self_cancel.py covers the self-cancellation (fails with CancelledError without this change), that the dispatch does not block its caller, that a failing notification warns rather than raising, and a source guard against reintroducing either inline await. Two assertions in test_overflow_recovery.py that drove these coroutines directly now drain pending tasks before asserting delivery, since the notification is deliberately no longer awaited inline. Prepared with agent assistance and reviewed before submission. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| acp | ||
| acp_adapter | ||
| agent | ||
| ci | ||
| cli | ||
| computer_use | ||
| conformance | ||
| cron | ||
| dashboard | ||
| docker | ||
| e2e | ||
| fakes | ||
| fixtures/plugins/example-dashboard/dashboard | ||
| gateway | ||
| hermes_cli | ||
| hermes_state | ||
| honcho_plugin | ||
| integration | ||
| manual | ||
| openviking_plugin | ||
| plugins | ||
| providers | ||
| run_agent | ||
| scripts | ||
| secret_sources | ||
| skills | ||
| state | ||
| stress | ||
| tools | ||
| tui_gateway | ||
| website | ||
| __init__.py | ||
| conftest.py | ||
| run_interrupt_test.py | ||
| test_account_usage.py | ||
| test_atomic_replace_symlinks.py | ||
| test_audio_playback_guard.py | ||
| test_background_review_list_shapes.py | ||
| test_background_review_session_isolation.py | ||
| test_base_url_hostname.py | ||
| test_batch_runner_checkpoint.py | ||
| test_bitwarden_secrets.py | ||
| test_cli_file_drop.py | ||
| test_cli_manual_compress.py | ||
| test_cli_skin_integration.py | ||
| test_code_skew.py | ||
| test_command_secret_source.py | ||
| test_conftest_wal_gate.py | ||
| test_copilot_initiator.py | ||
| test_credential_file_permissions.py | ||
| test_ctx_halving_fix.py | ||
| test_delegate_cascade_49148.py | ||
| test_dispatch_session_id.py | ||
| test_empty_model_fallback.py | ||
| test_empty_session_hygiene.py | ||
| test_env_loader_applied_homes.py | ||
| test_env_loader_op_bootstrap.py | ||
| test_env_loader_secret_sources.py | ||
| test_evidence_store.py | ||
| test_fast_safe_load.py | ||
| test_fts_cjk_bigram.py | ||
| test_gateway_streaming_nested_config.py | ||
| test_get_tool_definitions_cache_isolation.py | ||
| test_hermes_bootstrap.py | ||
| test_hermes_constants.py | ||
| test_hermes_home_profile_warning.py | ||
| test_hermes_logging.py | ||
| test_hermes_state.py | ||
| test_hermes_state_compression_locks.py | ||
| test_hermes_state_readonly_preflight.py | ||
| test_hermes_state_wal_fallback.py | ||
| test_honcho_client_concurrency.py | ||
| test_honcho_client_config.py | ||
| test_honcho_session_context.py | ||
| test_honcho_startup_fail_open.py | ||
| test_install_autostash_conflict_recovery.py | ||
| test_install_diverged_update.py | ||
| test_install_lockfile_churn.py | ||
| test_install_macos_launcher.py | ||
| test_install_no_initial_commit.py | ||
| test_install_ps1_ascii_only.py | ||
| test_install_ps1_native_stderr_eap.py | ||
| test_install_ps1_node_path_for_npm.py | ||
| test_install_ps1_python_fallback_venv.py | ||
| test_install_ps1_uv_powershell_host.py | ||
| test_install_ps1_web_server_syntax_probe.py | ||
| test_install_sh_acp_launcher.py | ||
| test_install_sh_bootstrap_marker.py | ||
| test_install_sh_browser_install.py | ||
| test_install_sh_install_method_stamp.py | ||
| test_install_sh_node_global_prefix.py | ||
| test_install_sh_pythonpath_sanitization.py | ||
| test_install_sh_root_fhs_uv_python_path.py | ||
| test_install_sh_setup_wizard_tty_probe.py | ||
| test_install_sh_symlink_stomp.py | ||
| test_install_sh_termux_network_prereqs.py | ||
| test_install_unmerged_index.py | ||
| test_ipv4_preference.py | ||
| test_iron_proxy.py | ||
| test_iron_proxy_cli.py | ||
| test_iron_proxy_e2e.py | ||
| test_lazy_session_regressions.py | ||
| test_lint_config.py | ||
| test_live_system_guard_self_test.py | ||
| test_mcp_serve.py | ||
| test_mini_swe_runner.py | ||
| test_minimax_model_validation.py | ||
| test_minimax_oauth.py | ||
| test_minisweagent_path.py | ||
| test_model_forces_max_completion_tokens.py | ||
| test_model_picker_scroll.py | ||
| test_model_tools.py | ||
| test_model_tools_async_bridge.py | ||
| test_ollama_num_ctx.py | ||
| test_onepassword_secrets.py | ||
| test_output_cap_parsing.py | ||
| test_packaging_build_guard.py | ||
| test_packaging_metadata.py | ||
| test_plugin_skills.py | ||
| test_plugin_utils.py | ||
| test_process_loop_event_loop_warning.py | ||
| test_profile_isolation_runtime.py | ||
| test_project_metadata.py | ||
| test_pty_keepalive_ws.py | ||
| test_pty_session.py | ||
| test_retry_utils.py | ||
| test_run_tests_parallel.py | ||
| test_sanitize_tool_error.py | ||
| test_search_slow_query_log.py | ||
| test_session_db_read_path_split.py | ||
| test_session_skill_previews.py | ||
| test_session_workspace_binding.py | ||
| test_slack_thread_require_mention.py | ||
| test_slash_worker_watchdog.py | ||
| test_sql_injection.py | ||
| test_sqlite_lock_safe_inspection.py | ||
| test_sqlite_wal_reset_gate.py | ||
| test_stale_utils_module_import.py | ||
| test_state_db_malformed_repair.py | ||
| test_subprocess_home_isolation.py | ||
| test_telegram_polling_progress_ptb.py | ||
| test_termux_all_extra_compat.py | ||
| test_timezone.py | ||
| test_tini_shim.py | ||
| test_toolset_distributions.py | ||
| test_toolsets.py | ||
| test_trajectory_compressor.py | ||
| test_trajectory_compressor_async.py | ||
| test_transform_llm_output_hook.py | ||
| test_transform_tool_result_hook.py | ||
| test_tui_entry_mcp_owner.py | ||
| test_tui_gateway_loop_noise.py | ||
| test_tui_gateway_queue_on_busy.py | ||
| test_tui_gateway_server.py | ||
| test_tui_gateway_ws.py | ||
| test_tui_mcp_late_refresh.py | ||
| test_utils_truthy_values.py | ||
| test_voice_max_recording_seconds.py | ||
| test_wal_checkpoint_strategy.py | ||
| test_web_server.py | ||
| test_web_server_sessiondb_eventloop.py | ||
| test_windows_subprocess_no_window_flags.py | ||
| test_yaml_indent_consistency_31999.py | ||
| test_yuanbao_integration.py | ||
| test_yuanbao_markdown.py | ||
| test_yuanbao_pipeline.py | ||
| test_yuanbao_proto.py | ||
| test_yuanbao_reconnect_set_active.py | ||
| test_yuanbao_shutdown.py | ||
| test_zeroed_state_db.py | ||