ethernet
890bbbda1f
Merge remote-tracking branch 'origin/main' into ethie/pm-clean
...
# Conflicts:
# apps/desktop/e2e/archived-hidden-session-recoverable.spec.ts
# apps/desktop/e2e/bot-chat-message-agent-friendly-name.spec.ts
# apps/desktop/e2e/bot-mailbox-unreadable-ticket.spec.ts
# apps/desktop/e2e/bot-mode-roster-localized.spec.ts
# apps/desktop/e2e/bot-mode-row-click-mirrors-registry.spec.ts
# apps/desktop/e2e/bot-mode-tab-shows-bot-name.spec.ts
# apps/desktop/e2e/bot-roster-group-row-organisation.spec.ts
# apps/desktop/e2e/bot-roster-ignores-infra-dirs.spec.ts
# apps/desktop/e2e/bot-roster-timestamp-meta.spec.ts
# apps/desktop/e2e/bot-roster-user-sections.spec.ts
# apps/desktop/e2e/bot-routines-pane-narrow.spec.ts
# apps/desktop/e2e/bot-row-open-recent-session.spec.ts
# apps/desktop/e2e/bot-tile-ignores-ambient-composer-model.spec.ts
# apps/desktop/e2e/group-composer-auto-grow.spec.ts
# apps/desktop/e2e/group-create-gate-remote-roster.spec.ts
# apps/desktop/e2e/group-prompt-renamed-primary-handle.spec.ts
# apps/desktop/e2e/hosted-room-backend-continuity.spec.ts
# apps/desktop/e2e/hosted-room-legacy-store-migration.spec.ts
# apps/desktop/e2e/settings-scope-chips-bot-title.spec.ts
# apps/desktop/e2e/worktree-branch-status.spec.ts
# apps/desktop/electron/backend-probes.test.ts
# apps/desktop/electron/connection-apply.test.ts
# apps/desktop/electron/desktop-electron-pin.test.ts
# apps/desktop/electron/desktop-uninstall.test.ts
# apps/desktop/electron/gateway-file-download-transport.test.ts
# apps/desktop/electron/gateway-stop-before-update.test.ts
# apps/desktop/electron/github-api-auth.test.ts
# apps/desktop/electron/registry-primary-profile-scope.test.ts
# apps/desktop/electron/update-api-check.test.ts
# apps/desktop/electron/update-handoff-marker.test.ts
# apps/desktop/electron/venv-blocker-scan.test.ts
# apps/desktop/scripts/after-extract.test.mjs
# apps/desktop/scripts/local-pack-publish.test.mjs
# apps/desktop/scripts/tasks-scroll.test.mjs
# apps/desktop/src/app/settings/model-settings.test.tsx
# apps/desktop/src/app/updates-overlay.blockers.test.tsx
# apps/desktop/src/components/desktop-install-overlay.test.tsx
# apps/desktop/src/lib/update-copy.test.ts
# scripts/ci/check_os_marker_fakes.py
# tests-js/desktop-mac-usage-descriptions.test.ts
# tests-js/node-engine-alignment.test.ts
# tests/agent/lsp/test_install_and_lint_fixes.py
# tests/agent/test_command_token_source.py
# tests/agent/test_compression_boundary_hook.py
# tests/agent/test_create_openai_client_ssl_verify.py
# tests/agent/test_custom_provider_ca_probes.py
# tests/agent/test_endpoint_blackhole.py
# tests/agent/test_estimator_parity.py
# tests/agent/test_in_place_compaction.py
# tests/agent/test_moa_loop_mode.py
# tests/agent/test_model_metadata.py
# tests/agent/test_skill_session_platform_gate.py
# tests/agent/test_skill_utils.py
# tests/agent/test_ssl_ca_guard.py
# tests/computer_use/test_doctor.py
# tests/cron/test_codex_execution_paths.py
# tests/cron/test_cron_bot_chat_delivery.py
# tests/cron/test_cron_script.py
# tests/cron/test_media_delivery_parity.py
# tests/cron/test_misfire_catchup.py
# tests/cron/test_parallel_pool.py
# tests/cron/test_recurring_eagain_redispatch.py
# tests/gateway/test_choice_picker.py
# tests/gateway/test_control_socket_windows_live.py
# tests/gateway/test_dingtalk.py
# tests/gateway/test_feishu.py
# tests/gateway/test_feishu_onboard.py
# tests/gateway/test_gateway_shutdown.py
# tests/gateway/test_matrix.py
# tests/gateway/test_model_command_custom_providers.py
# tests/gateway/test_reasoning_command.py
# tests/gateway/test_runtime_footer.py
# tests/gateway/test_session.py
# tests/gateway/test_session_hygiene.py
# tests/gateway/test_status.py
# tests/gateway/test_teams.py
# tests/gateway/test_turn_lease.py
# tests/gateway/test_whatsapp_connect.py
# tests/hermes_cli/test_approvals_command.py
# tests/hermes_cli/test_auth_store_lock_concurrent.py
# tests/hermes_cli/test_backup.py
# tests/hermes_cli/test_banner_git_state.py
# tests/hermes_cli/test_certifi_repair.py
# tests/hermes_cli/test_cmd_update.py
# tests/hermes_cli/test_compat_manifest_targets.py
# tests/hermes_cli/test_computer_use_cli.py
# tests/hermes_cli/test_cpr_local_leak.py
# tests/hermes_cli/test_dashboard_auth_gate.py
# tests/hermes_cli/test_dashboard_procs_kill_grace.py
# tests/hermes_cli/test_desktop_lifecycle_windows_live.py
# tests/hermes_cli/test_doctor.py
# tests/hermes_cli/test_doctor_command_install.py
# tests/hermes_cli/test_fleet_config_migration_windows_live.py
# tests/hermes_cli/test_gateway.py
# tests/hermes_cli/test_gateway_platform_gating.py
# tests/hermes_cli/test_gateway_restart_loop.py
# tests/hermes_cli/test_gateway_task_probe.py
# tests/hermes_cli/test_gateway_wsl.py
# tests/hermes_cli/test_gui_command.py
# tests/hermes_cli/test_install_cua_driver.py
# tests/hermes_cli/test_kanban_db.py
# tests/hermes_cli/test_lazy_command_exports.py
# tests/hermes_cli/test_lazy_refresh_venv_repair.py
# tests/hermes_cli/test_linux_desktop_entry.py
# tests/hermes_cli/test_local_runtime.py
# tests/hermes_cli/test_local_runtime_updates.py
# tests/hermes_cli/test_managed_uv.py
# tests/hermes_cli/test_mcp_reload_confirm_gate.py
# tests/hermes_cli/test_nous_subscription.py
# tests/hermes_cli/test_npm_engine.py
# tests/hermes_cli/test_personality_none.py
# tests/hermes_cli/test_pet_toggle.py
# tests/hermes_cli/test_plan_reconciliation_windows_live.py
# tests/hermes_cli/test_plugin_event_bus.py
# tests/hermes_cli/test_plugin_manifest_v2.py
# tests/hermes_cli/test_plugin_packs.py
# tests/hermes_cli/test_plugins_cmd.py
# tests/hermes_cli/test_plugins_cmd_enable_disable_nested.py
# tests/hermes_cli/test_process_identity.py
# tests/hermes_cli/test_profiles.py
# tests/hermes_cli/test_profiles_sidebar_cache.py
# tests/hermes_cli/test_pty_bridge.py
# tests/hermes_cli/test_resolve_turn_limit.py
# tests/hermes_cli/test_serve_runtime_inventory.py
# tests/hermes_cli/test_session_vacuum_config.py
# tests/hermes_cli/test_set_config_value.py
# tests/hermes_cli/test_signal_handler_kanban_worker.py
# tests/hermes_cli/test_slash_confirm_windows.py
# tests/hermes_cli/test_stale_pid_guard.py
# tests/hermes_cli/test_startup_fast_guards.py
# tests/hermes_cli/test_status.py
# tests/hermes_cli/test_telegram_managed_bot.py
# tests/hermes_cli/test_tools_config.py
# tests/hermes_cli/test_update_apply_shallow_count.py
# tests/hermes_cli/test_update_autostash.py
# tests/hermes_cli/test_update_concurrent_quarantine.py
# tests/hermes_cli/test_update_fetch_failure_classifier.py
# tests/hermes_cli/test_update_fleet_probe_resume_token.py
# tests/hermes_cli/test_update_handoff_backend_reap.py
# tests/hermes_cli/test_update_handoff_desktop_rebuild.py
# tests/hermes_cli/test_update_head_moved_gate.py
# tests/hermes_cli/test_update_host_obligation.py
# tests/hermes_cli/test_update_import_guard.py
# tests/hermes_cli/test_update_interrupted_recovery.py
# tests/hermes_cli/test_update_inventory.py
# tests/hermes_cli/test_update_launchd_unloaded_gateway.py
# tests/hermes_cli/test_update_missing_configured_deps.py
# tests/hermes_cli/test_update_modified_notice.py
# tests/hermes_cli/test_update_multiplex_migration_hook.py
# tests/hermes_cli/test_update_no_gateway_restart.py
# tests/hermes_cli/test_update_orphan_backend_reap.py
# tests/hermes_cli/test_update_parked_branch_guard.py
# tests/hermes_cli/test_update_post_pull_syntax_guard.py
# tests/hermes_cli/test_update_receipt.py
# tests/hermes_cli/test_update_self_lock.py
# tests/hermes_cli/test_update_shim_fail_closed.py
# tests/hermes_cli/test_update_shim_self_lock.py
# tests/hermes_cli/test_update_sqlite_remediation.py
# tests/hermes_cli/test_update_stale_dashboard.py
# tests/hermes_cli/test_update_stale_virtualenv.py
# tests/hermes_cli/test_update_venv_health.py
# tests/hermes_cli/test_update_venv_ownership_preflight.py
# tests/hermes_cli/test_update_wedged_gateway.py
# tests/hermes_cli/test_update_yes_flag.py
# tests/hermes_cli/test_update_zip_two_phase.py
# tests/hermes_cli/test_urllib_security.py
# tests/hermes_cli/test_ux_messages_auth_config.py
# tests/hermes_cli/test_ux_messages_startup.py
# tests/hermes_cli/test_venv_holder_classifier.py
# tests/hermes_cli/test_verify_console_scripts.py
# tests/hermes_cli/test_verify_core_dependencies.py
# tests/hermes_cli/test_web_server.py
# tests/hermes_cli/test_web_server_console_ws.py
# tests/hermes_cli/test_web_server_ws_ping.py
# tests/hermes_cli/test_web_ui_build.py
# tests/hermes_state/test_fts_rebuild_admission.py
# tests/hermes_state/test_hermes_state.py
# tests/plugins/memory/test_memory_lazy_install.py
# tests/plugins/test_google_meet_plugin.py
# tests/plugins/test_langfuse_plugin.py
# tests/plugins/test_security_guidance_plugin.py
# tests/plugins/test_transform_llm_output_hook.py
# tests/scripts/desktop_update/test_desktop_update_windows_gateway_flag.py
# tests/scripts/desktop_update/test_desktop_update_windows_python_handoff.py
# tests/scripts/desktop_update/test_desktop_update_windows_timestamp.py
# tests/scripts/install/test_install_clone_throttle_fallback.py
# tests/scripts/install/test_install_lockfile_churn.py
# tests/scripts/install/test_install_no_initial_commit.py
# tests/scripts/install/test_install_sh_browser_install.py
# tests/scripts/install/test_install_sh_node_prerelease.py
# tests/scripts/install/test_install_sh_symlink_stomp.py
# tests/scripts/install/test_install_sh_uv_lock_config.py
# tests/scripts/install/test_install_unmerged_index.py
# tests/scripts/test_contributor_map.py
# tests/scripts/test_run_tests_parallel.py
# tests/skills/test_competitor_news_monitor_skill.py
# tests/skills/test_document_to_action_items_skill.py
# tests/skills/test_google_workspace_setup.py
# tests/skills/test_google_workspace_setup_deps.py
# tests/skills/test_grounded_citations_skill.py
# tests/skills/test_ip_as_logo_skill.py
# tests/skills/test_live_dashboard_skill.py
# tests/skills/test_mcp_oauth_remote_gateway_skill.py
# tests/skills/test_office_document_skills.py
# tests/skills/test_openclaw_migration.py
# tests/skills/test_product_price_monitor_skill.py
# tests/skills/test_scrollcraft_skill.py
# tests/skills/test_setup_wizard_generator_skill.py
# tests/skills/test_weekly_review_planning_skill.py
# tests/test_engines_satisfiable.py
# tests/test_fast_safe_load.py
# tests/test_hermes_bootstrap.py
# tests/test_hermes_constants.py
# tests/test_hermes_logging.py
# tests/test_managed_runtime_resolution.py
# tests/test_model_tools_async_bridge.py
# tests/test_packaging_build_guard.py
# tests/test_packaging_metadata.py
# tests/test_yaml_indent_consistency.py
# tests/tools/test_approval_timeout_overflow.py
# tests/tools/test_base_environment.py
# tests/tools/test_bot_mode_dm.py
# tests/tools/test_browser_chromium_check.py
# tests/tools/test_browser_hardening.py
# tests/tools/test_browser_homebrew_paths.py
# tests/tools/test_browser_npx_warmup.py
# tests/tools/test_browser_orphan_reaper.py
# tests/tools/test_browser_real_profile.py
# tests/tools/test_browser_use_cli.py
# tests/tools/test_clipboard.py
# tests/tools/test_code_execution.py
# tests/tools/test_code_execution_modes.py
# tests/tools/test_code_execution_windows_env.py
# tests/tools/test_computer_use.py
# tests/tools/test_delegate_liveness_timeout.py
# tests/tools/test_execute_code_approval_cluster.py
# tests/tools/test_execution_flag_detection.py
# tests/tools/test_fal_common.py
# tests/tools/test_file_operations.py
# tests/tools/test_file_tools.py
# tests/tools/test_file_tools_cwd_resolution.py
# tests/tools/test_file_tools_live.py
# tests/tools/test_lazy_deps.py
# tests/tools/test_lazy_deps_durable_target.py
# tests/tools/test_lazy_deps_managed.py
# tests/tools/test_local_env_blocklist.py
# tests/tools/test_local_tempdir.py
# tests/tools/test_macos_protected_search.py
# tests/tools/test_mcp_npx_cached_bin.py
# tests/tools/test_oneshot_completion_linger.py
# tests/tools/test_process_registry.py
# tests/tools/test_read_file_schema_gating.py
# tests/tools/test_skill_improvements.py
# tests/tools/test_skills_sync.py
# tests/tools/test_termux_api_detection.py
# tests/tools/test_tirith_security.py
# tests/tools/test_transcription_tools.py
# tests/tools/test_tts_streaming.py
# tests/tools/test_wake_word.py
# tests/tui_gateway/test_compute_host_borrowed_lease.py
# tests/tui_gateway/test_compute_host_turn_protocol.py
# tests/tui_gateway/test_isolated_orphan_activity.py
# tests/tui_gateway/test_protocol.py
# tests/tui_gateway/test_slash_worker_profile_home.py
# tests/tui_gateway/test_subprocess_encoding.py
# tests/tui_gateway/test_tui_gateway_server.py
# ui-tui/src/__tests__/terminalParity.test.ts
# ui-tui/src/__tests__/termuxComposerLayout.test.ts
# ui-tui/src/__tests__/textInputFastEcho.test.ts
2026-09-23 07:02:44 -04:00
teknium1
524c38a98a
test: purge low-value tests, lane py16 (624 removed)
...
Change-detectors, tautologies, source-reading tests, redundant duplicates,
mock-echo tests and dead/unrunnable tests. Per-test rationale in the lane
ledger (category + reason for every removal).
2026-09-23 03:15:26 -07:00
aniruddhaadak80
a26154aceb
fix(batch_runner): teach the resume content scan to honor discard tombstones
...
Complete the #93527 fix: the tombstone now carries the human prompt
text via _entry_prompt_text (handling flat prompt, ShareGPT, and
chat-style shapes), _scan_completed_prompts_by_content counts
discarded rows as completed instead of only reading ShareGPT
conversations, and the merge step reports excluded tombstones in the
combined-count summary. Adds a dedicated regression suite covering the
tombstone round-trip, the all-discarded-batch resume path, and merge
exclusion.
Salvaged from #93579 (issue reporter's PR), building on #93542 .
Fixes #93527
2026-08-24 03:21:07 -07:00
chelsealong
316d52faf2
fix(batch_runner): write a discard tombstone so resume skips no-reasoning prompts
...
The no-reasoning discard branch in _process_batch_worker continued
before writing any JSONL row, so run(resume=True) — which filters
solely via _scan_completed_prompts_by_content over batch_*.jsonl —
never saw discarded prompts and re-ran them at full cost on every
resume. Write a tombstone row on discard, exclude tombstones from the
trajectories.jsonl merge, and report discarded_no_reasoning in
final statistics.
Salvaged from #93542 .
Fixes #93527
2026-08-24 03:21:07 -07:00
Teknium
6b81590c55
test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions
...
Systematic prune per AGENTS.md test policy, one pass over every major
test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli,
cron, tui_gateway, honcho/openviking, root-level):
- DELETE: source-reading tests (read_text/getsource on prod files),
change-detector tests (exact catalog counts, model-name snapshots,
config version literals), mock-echo tests (assert a mock returns what
it was told), assertion-free/trivial tests, near-duplicate
parametrizations (boundaries + one representative kept), async/sync
twin duplicates, cosmetic within-file variations.
- KEEP (mandatory): security/redaction/approval guards, message-role
alternation invariants, prompt-caching/deterministic-call-id
invariants, issue-number regression tests (deduped), E2E tests.
- 6 test files deleted outright (script-style/no-assert or fully
redundant); conftest.py, fakes/, fixtures/ untouched.
- tests/acp/conftest.py added: autouse fixture stubs the live
models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server
tests performed on every session create — test_server.py 147s → 3.4s,
and the tests are now genuinely hermetic.
- Sleep-based slowness shrunk where safe (codex_ttfb_watchdog,
compression_concurrent_fork, etc.); no wall-clock assertion tightened.
Verification: full hermetic suite via scripts/run_tests.sh —
2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall
(baseline: 583s wall, 13,564s subprocess CPU).
2026-07-29 13:10:23 -07:00
kshitijk4poor
66827f8947
chore: prune unused imports and duplicate import redefinitions
...
Remove unused imports (F401) and duplicate/shadowed import
redefinitions (F811) across the codebase using ruff's safe
autofixes. No behavioral changes -- imports only.
- ~1400 safe autofixes applied across 644 files (net -1072 lines)
- __init__.py re-exports preserved (excluded from F401 removal so
public re-export surfaces stay intact)
- Re-exports that are imported or monkeypatched by tests but look
unused in their defining module are kept with explicit # noqa:
F401 (gateway/run.py load_dotenv; run_agent re-exports from
agent.message_sanitization, agent.context_compressor,
agent.retry_utils, agent.prompt_builder, agent.process_bootstrap,
agent.codex_responses_adapter)
- Unsafe F841 (unused-variable) fixes deliberately skipped -- those
can change behavior when the RHS has side effects
- ruff lints remain disabled in pyproject.toml (only PLW1514 is
selected); this is a one-time cleanup, not a config change
Verification:
- python -m compileall: clean
- pytest --collect-only: all 27161 tests collect (zero import errors)
- core entry points import clean (run_agent, model_tools, cli,
toolsets, hermes_state, batch_runner, gateway)
- static scan: every name any test imports directly from an edited
module still resolves
2026-05-28 22:26:25 -07:00
Teknium
ef9355455b
test: regression coverage for checkpoint dedup and inf/nan coercion
...
Covers the two bugs salvaged from PR #15161 :
- test_batch_runner_checkpoint: TestFinalCheckpointNoDuplicates asserts
the final aggregated completed_prompts list has no duplicate indices,
and keeps a sanity anchor test documenting the pre-fix pattern so a
future refactor that re-introduces it is caught immediately.
- test_model_tools: TestCoerceNumberInfNan asserts _coerce_number
returns the original string for inf/-inf/nan/Infinity inputs and that
the result round-trips through strict (allow_nan=False) json.dumps.
2026-04-24 14:32:21 -07:00
houguokun
6cdab70320
fix(batch_runner): mark discarded no-reasoning prompts as completed ( #9950 )
...
Cherry-picked from PR #10005 by @houziershi.
Discarded prompts (has_any_reasoning=False) were skipped by `continue`
before being added to completed_in_batch. On --resume they were retried
forever. Now they are added to completed_in_batch before the continue.
- Added AUTHOR_MAP entry for @houziershi
Closes #9950
2026-04-20 04:56:06 -07:00
Adavya Sharma
358dab52ce
fix: sanitize chat payloads and provider precedence
2026-03-13 23:59:12 -07:00
teknium1
d63b363cde
refactor: extract atomic_json_write helper, add 24 checkpoint tests
...
Extract the duplicated temp-file + fsync + os.replace pattern from
batch_runner.py (1 instance) and process_registry.py (2 instances) into
a shared utils.atomic_json_write() function.
Add 12 tests for atomic_json_write covering: valid JSON, parent dir
creation, overwrite, crash safety (original preserved on error), no temp
file leaks, string paths, unicode, custom indent, concurrent writes.
Add 12 tests for batch_runner checkpoint behavior covering:
_save_checkpoint (valid JSON, last_updated, overwrite, lock/no-lock,
parent dirs, no temp leaks), _load_checkpoint (missing file, existing
data, corrupt JSON), and resume logic (preserves prior progress,
different run_name starts fresh).
2026-03-06 05:50:12 -08:00
