mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-21 16:18:55 +00:00
452861fdc1
Address the hermes-sweeper review of #61233: the bounded retry budget is now a clean-exit-specific streak, not a share of the unified consecutive_failures counter. - detect_crashed_workers stamps a protocol_violation marker into the violation run's metadata (via the event payload _end_run copies); _protocol_violation_streak derives the streak from run history: consecutive most-recent violation runs, rate_limited runs neutral (mirroring their unified-counter treatment), any other closed run resets it. Mixed failure kinds can neither consume nor extend the budget. - Below-budget violations no longer call _record_task_failure at all: the task returns to ready with last_failure_error stamped directly (including the corrective retry guidance wording adopted from #61817, which build_worker_context surfaces to the retry worker) and the unified counter is untouched, keeping the two budgets independent. - At the bound the trip funnels through _record_task_failure with a new keyword-only force_trip=True: the reaper has already resolved the per-task max_retries override against the violation streak itself, so the threshold comparison is skipped rather than double-applied. max_retries keeps its documented top precedence in both directions: max_retries=1 blocks on the first violation, max_retries=5 blocks on the fifth consecutive one, unset uses the default bound of 3. - Replace the first-violation-blocks regression test with five tests: first occurrence retries (ready + guidance stamped + no gave_up + unified counter untouched); streak trips exactly at the bound with protocol_violations/protocol_violation_limit in the gave_up payload and the auto-blocked side channel set; a prior nonzero crash does not consume the violation budget; a non-violation failure between violations resets the streak; max_retries precedence both directions. All five fail against the previously reviewed diff and pass with this follow-up. The test harness resolves hermes_cli.kanban_db fresh and uses that single module object for the exit registry, liveness patch, and reaper — earlier suite tests reload the module, and the old mixed-object harness made _classify_worker_exit return unknown (the reason the old test failed in full-suite runs on main). Kanban suite: zero introduced failures vs upstream/main tip (62 vs 63 pre-existing environmental failures — the one no longer failing is the old violation test this replaces; 662 passed vs 657). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| acp | ||
| acp_adapter | ||
| agent | ||
| ci | ||
| cli | ||
| computer_use | ||
| 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 | ||
| stress | ||
| tools | ||
| tui_gateway | ||
| website | ||
| __init__.py | ||
| conftest.py | ||
| run_interrupt_test.py | ||
| test_account_usage.py | ||
| test_assistant_ui_tap_compat.py | ||
| test_atomic_replace_symlinks.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_copilot_initiator.py | ||
| test_ctx_halving_fix.py | ||
| test_dashboard_sidecar_close_on_disconnect.py | ||
| test_delegate_cascade_49148.py | ||
| test_desktop_electron_pin.py | ||
| test_desktop_mac_entitlements.py | ||
| test_dispatch_session_id.py | ||
| test_empty_model_fallback.py | ||
| test_empty_session_hygiene.py | ||
| test_env_loader_op_bootstrap.py | ||
| test_env_loader_secret_sources.py | ||
| test_evidence_store.py | ||
| test_fast_safe_load.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_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_diverged_update.py | ||
| test_install_lockfile_churn.py | ||
| test_install_no_initial_commit.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_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_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_package_json_lazy_deps.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_session_workspace_binding.py | ||
| test_setup_temporary_outputs.py | ||
| test_slash_worker_watchdog.py | ||
| test_sql_injection.py | ||
| test_stale_utils_module_import.py | ||
| test_state_db_malformed_repair.py | ||
| test_subprocess_home_isolation.py | ||
| test_termux_all_extra_compat.py | ||
| test_timezone.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_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_web_server.py | ||
| test_wheel_locales_e2e.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 | ||