hermes-agent/tests
Teknium bd7e480236
fix(compression): give fallback candidates their own timeout budget + escalate repeat-timeout cooldowns (#65143)
Fixes #62452. Two amplifiers turned one slow auxiliary route into a
per-turn multi-minute stall:

1. Fallback candidates inherited the exact effective_timeout the primary
   was called with. When the primary's deadline was short (tuned or
   already burned), an independently healthy fallback died on the same
   clock — the reporter's 163k-token compression needed ~90s on the
   fallback and got the primary's 30s, every turn. fallback_chain
   entries may now declare their own 'timeout' (seconds); both fallback
   candidate call sites (sync + async) resolve it via
   _fallback_entry_timeout, label-scoped so only configured-chain
   candidates are affected. No entry timeout → task-level timeout,
   preserving existing behavior.

2. A session whose transcript structurally cannot be summarized within
   the deadline re-attempted every 60s, re-burning the full timeout on
   every subsequent turn. Consecutive timeout-class failures now
   escalate the cooldown 60s → 300s → 900s (capped); any successful
   summary or session reset clears the streak. Timeout classification
   takes precedence over the streaming-closed 30s rung ('timed out'
   also matches _is_connection_error) and now recognizes the SDK's
   'Request timed out.' phrasing.

Fail-safe behavior is unchanged: all messages are preserved when every
candidate fails; the cooldown only spaces out retries.
2026-07-15 12:28:09 -07:00
..
acp fix(acp): don't let a malformed tool argument abort the tool-call render 2026-07-15 00:10:22 -07:00
acp_adapter
…
agent fix(compression): give fallback candidates their own timeout budget + escalate repeat-timeout cooldowns (#65143) 2026-07-15 12:28:09 -07:00
ci
…
cli fix(cli): scope async delegation delivery to session 2026-07-14 22:14:10 -07:00
computer_use
…
cron feat(config): support per-model reasoning_effort overrides 2026-07-14 11:46:40 -07:00
dashboard
…
docker
…
e2e
…
fakes
…
fixtures/plugins/example-dashboard/dashboard
…
gateway fix(gateway): import PairingStore in _start_secondary_profile_adapters (#65118) 2026-07-15 12:11:16 -07:00
hermes_cli fix(dashboard): add HTTP MCP authentication (#65146) 2026-07-16 00:02:09 +05:30
hermes_state
…
honcho_plugin
…
integration
…
manual
…
openviking_plugin
…
plugins fix(auxiliary): route direct-create aux callers through call_llm (#65029) 2026-07-15 07:39:17 -07:00
providers
…
run_agent fix(agent): dedup codex incomplete interims on visible content 2026-07-15 09:49:11 -07:00
scripts
…
secret_sources
…
skills
…
stress
…
tools fix(computer-use): target Linux app windows reliably (#63725) 2026-07-16 00:34:20 +05:30
tui_gateway feat(config): support per-model reasoning_effort overrides 2026-07-14 11:46:40 -07:00
website
…
__init__.py
…
conftest.py
…
run_interrupt_test.py
…
test_account_usage.py
…
test_assistant_ui_tap_compat.py fix(tests): make @assistant-ui tap invariant workspace-nesting aware 2026-07-15 02:34:15 -04:00
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 chore: restore test_ctx_halving_fix.py to main 2026-07-14 03:58:54 +05:30
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 feat(models): catalog-labeled silent default — GLM-5.2 marked "default": true in the model catalog 2026-07-15 00:10:31 -07:00
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 refactor(reasoning): unify per-model reasoning resolution behind a single chokepoint 2026-07-14 11:46:40 -07:00
test_hermes_home_profile_warning.py
…
test_hermes_logging.py
…
test_hermes_state.py test(gateway): cover ws_orphan_reap session recovery (#63207) 2026-07-14 16:58:47 +05:30
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 fix(nemo-relay): align dynamic plugin configuration 2026-07-13 17:01:08 -06:00
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_telegram_polling_progress_ptb.py test(telegram): gate slots premise assert on runtimes without instance __dict__ 2026-07-14 21:25:44 -07:00
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(input): preservation regressions and prompt.submit boundary (#62557) 2026-07-15 07:39:42 -07:00
test_tui_gateway_ws.py
…
test_tui_mcp_late_refresh.py
…
test_utils_truthy_values.py
…
test_wal_checkpoint_strategy.py fix(state): use PASSIVE checkpoint for periodic WAL flush to prevent B-tree corruption 2026-07-15 04:55:46 -07:00
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
…