hermes-admin/hermes-agent
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity
Files
ca3d6209d49ada09aefd2e1f60f09d6bac1723ee
hermes-agent/tests/tools
History
teknium1 3e1bfb2935 fix(execute_code): report in-script tool errors the script ignored 
A script that calls hermes_tools.write_file/patch and never prints the
returned {"error": ...} got status=success with empty output, so the
model believed the write happened. In a cross-agent bench this cost 3 of
18 Opus runs 4-6 extra turns (write_file refused by the read-before-write
guard, then re-probing and re-emitting whole files). The result now
carries tool_errors for that cell, and the in-script write_file doc says
existing files must be read first.
2026-09-28 10:11:33 -07:00
..
environments
…
__init__.py
…
_child_env_fixtures.py
test(code-execution): let RunToCompletionEnv accept stdin_data
2026-09-27 00:56:31 +05:30
conftest.py
…
file_ops_fakes.py
…
test_a2a_reason_roundtrip.py
…
test_accretion_caps.py
…
test_allowlist_legacy_config.py
…
test_allowlist_quoted_metachars.py
…
test_annotate_preview_tool.py
…
test_ansi_strip.py
…
test_apply_layout_tool.py
…
test_approval_bun_deno_eval.py
…
test_approval_cancelled_attribution.py
…
test_approval_config_readonly.py
…
test_approval_deny_rules.py
…
test_approval_gateway_wait_late_choice.py
…
test_approval_grep_in_substitution.py
…
test_approval_hook_session_id.py
…
test_approval_interrupt.py
…
test_approval_launchctl_performance.py
…
test_approval_mode_parity.py
…
test_approval_outcome_parity.py
…
test_approval_plugin_hooks.py
…
test_approval_timeout_overflow.py
…
test_approval_user_summary.py
…
test_approval_windows.py
…
test_approval.py
…
test_approved_command_clean_slate.py
…
test_async_batch_task_failure_notice.py
…
test_async_delegation_failed_surface.py
fix(tui-gateway): report recently failed async delegations in subagent.list
2026-09-26 20:40:40 -05:00
test_async_delegation_fd_leak.py
…
test_async_delegation_orphan_sweep.py
fix(delegation): hand a dropped orphan offer back to the sweep
2026-09-24 02:41:14 -05:00
test_async_delegation_retirement.py
…
test_async_delegation_stale_profile_scope.py
…
test_async_delegation.py
test(delegation): consumers restore the ledger before reading the completion queue (#123265)
2026-09-28 05:37:55 -07:00
test_audio_container.py
…
test_base_environment.py
fix(environments): route heredoc stdin to compound commands
2026-09-25 14:14:06 -04:00
test_binary_document_write_guard.py
…
test_blocked_command_guidance.py
…
test_blueprints.py
…
test_bot_delivery_install_launcher.py
fix(bot-mode): avoid selecting batch shims for literal delivery argv
2026-09-27 13:48:28 -05:00
test_bot_desktop_browser_fence.py
…
test_bot_desktop_browser.py
Merge remote-tracking branch 'origin/main' into ethie/pm-clean
2026-09-24 02:23:44 -04:00
test_bot_desktop_idle.py
…
test_bot_desktop_install.py
fix(encoding): read kernel pseudo-files as plain utf-8
2026-09-24 11:50:30 -04:00
test_bot_desktop_launcher_seed.py
…
test_bot_desktop_launcher_xvnc.py
…
test_bot_desktop_lease.py
…
test_bot_desktop_placement.py
feat(bot_desktop): Bot Screen, computer_use and the browser run inside the terminal backend (#121169)
2026-09-28 03:34:07 -07:00
test_bot_desktop_resources.py
Merge remote-tracking branch 'origin/main' into ethie/pm-clean
2026-09-24 02:23:44 -04:00
test_bot_desktop_rfb_filter_limits.py
…
test_bot_desktop_runtime.py
Merge remote-tracking branch 'origin/main' into ethie/pm-clean
2026-09-24 02:23:44 -04:00
test_bot_desktop_thumbnail.py
…
test_bot_dm_payload_cache.py
…
test_bot_failure_reasons.py
…
test_bot_live_owner_delivery.py
…
test_bot_mode_canonical_chat_resolution.py
…
test_bot_mode_dm.py
test(bot-mode): isolate fallback-ladder probes from the checkout's published launcher
2026-09-27 13:48:28 -05:00
test_bot_mode_probe.py
fix(bot-chat): deliver toolset changes to the canonical Bot Chat
2026-09-28 06:06:17 -07:00
test_bot_mode_refusal_contract.py
…
test_bot_relay_windows_paths.py
test(bot-mode): isolate fallback-ladder probes from the checkout's published launcher
2026-09-27 13:48:28 -05:00
test_bot_relay.py
…
test_bot_retry_policy.py
…
test_bot_turn_lock.py
…
test_browser_camofox_auth.py
…
test_browser_camofox_ensure_tab.py
…
test_browser_camofox_persistence.py
…
test_browser_camofox_private_page_guard.py
…
test_browser_camofox_state.py
…
test_browser_camofox_timeout.py
…
test_browser_camofox.py
…
test_browser_cdp_override.py
…
test_browser_cdp_tool.py
…
test_browser_cleanup.py
…
test_browser_cloud_fallback.py
…
test_browser_cloud_provider_cache.py
…
test_browser_command_timeout_race.py
…
test_browser_computer_use_profile_cache_keys.py
…
test_browser_console_ssrf.py
…
test_browser_console.py
…
test_browser_env_loopback_no_proxy.py
…
test_browser_eval_shim_args.py
…
test_browser_eval_ssrf.py
…
test_browser_eval_supervisor_path.py
…
test_browser_extension_router_wiring.py
…
test_browser_extension_router.py
…
test_browser_get_images_ssrf.py
…
test_browser_hardening.py
…
test_browser_headed_mode.py
…
test_browser_hybrid_routing.py
…
test_browser_lightpanda_serve.py
…
test_browser_lightpanda.py
…
test_browser_open_timeout.py
…
test_browser_orphan_reaper.py
…
test_browser_pm.py
…
test_browser_private_page_action_guard.py
…
test_browser_process_tree.py
…
test_browser_real_profile_pin.py
…
test_browser_real_profile.py
…
test_browser_secret_exfil.py
…
test_browser_snapshot_ssrf.py
…
test_browser_snapshot_threshold.py
…
test_browser_ssrf_local.py
…
test_browser_supervisor_healthcheck.py
…
test_browser_supervisor_reconnect.py
…
test_browser_supervisor.py
…
test_browser_suspect_recycle.py
…
test_browser_type_redaction.py
…
test_browser_use_cli.py
fix(browser): ship the Browser Use CLI engine in every install, Desktop included
2026-09-27 23:53:40 -07:00
test_browser_use_harness.py
fix(browser): ship the Browser Use CLI engine in every install, Desktop included
2026-09-27 23:53:40 -07:00
test_browser_use_session_expiry.py
…
test_browser_vault.py
…
test_budget_config.py
…
test_build_subprocess_env.py
…
test_capability_fingerprint_skill_scope.py
…
test_checkpoint_footprint_notice.py
refactor: separate checkpoint store maintenance from snapshots
2026-09-24 01:55:51 -04:00
test_checkpoint_manager.py
refactor: separate checkpoint store maintenance from snapshots
2026-09-24 01:55:51 -04:00
test_checkpoint_path_roundtrip.py
…
test_checkpoint_size_cap.py
refactor: separate checkpoint store maintenance from snapshots
2026-09-24 01:55:51 -04:00
test_checkpoint_store_ownership.py
refactor: separate checkpoint store maintenance from snapshots
2026-09-24 01:55:51 -04:00
test_clarify_gateway.py
…
test_clarify_tool.py
…
test_clawhub_owner_http.py
…
test_clawhub_zip_stream.py
…
test_cli_approval_exec_ask_leak.py
…
test_clipboard.py
…
test_close_preview_tool.py
…
test_code_execution_file_rpc.py
fix(code-execution): always send remote-write payloads as stdin_data
2026-09-27 00:56:31 +05:30
test_code_execution_hermes_home.py
…
test_code_execution_modes.py
…
test_code_execution_pm_runtime.py
fix(execute-code): preserve PM runtime dependencies for own kernel
2026-09-28 06:42:00 -07:00
test_code_execution_windows_env.py
…
test_code_execution.py
test(code-execution): cover cell-ship eviction and fail-closed setup
2026-09-27 00:56:31 +05:30
test_code_kernel_remote.py
test(code-execution): a failed result cleanup does not re-run the cell
2026-09-27 00:56:31 +05:30
test_code_kernel.py
fix(execute_code): report in-script tool errors the script ignored
2026-09-28 10:11:33 -07:00
test_command_guards.py
…
test_compaction_tool_refresh.py
…
test_completed_process_results.py
test: distinguish background notice replay from redelivery
2026-09-24 06:15:21 -04:00
test_computer_use_approval_isolation.py
…
test_computer_use_ax_walk_bound.py
…
test_computer_use_backend_lifecycle.py
…
test_computer_use_backend_rebind.py
…
test_computer_use_capture_fence.py
…
test_computer_use_capture_routing.py
…
test_computer_use_cua_0_9.py
…
test_computer_use_cua_0_10_permissions.py
…
test_computer_use_cua_backend_linux.py
…
test_computer_use_cua_macos_identity.py
…
test_computer_use_delivery_ladder.py
…
test_computer_use_display_count_guard.py
…
test_computer_use_doctor_stale_units.py
…
test_computer_use_empty_discovery_diagnosis.py
…
test_computer_use_fullscreen_capture.py
…
test_computer_use_input_target_guard.py
…
test_computer_use_native_platform.py
…
test_computer_use_null_pid_windows.py
…
test_computer_use_placeholder_ids.py
…
test_computer_use_screenshot_dedup.py
…
test_computer_use_vision_routing.py
…
test_computer_use_zero_bounds.py
…
test_computer_use.py
…
test_config_null_guard.py
…
test_connector_bridge_wiring.py
…
test_connector_dispatch_policy.py
…
test_connector_local_batches.py
…
test_connector_names.py
…
test_connector_session_scope.py
…
test_connectors_catalog.py
…
test_connectors_contract.py
…
test_connectors_gateway_client.py
…
test_connectors_gateway_merge.py
…
test_connectors_gateway_wire.py
…
test_connectors_live.py
…
test_connectors_managed.py
…
test_connectors_mcp.py
…
test_connectors_operation.py
…
test_connectors_tool.py
…
test_container_cwd_sanitize.py
…
test_credential_files.py
fix(agent): admit and sync gateway-staged attachments on remote execution backends (#110174)
2026-09-26 18:00:17 -05:00
test_credential_pool_env_fallback.py
…
test_cron_approval_mode.py
…
test_cron_not_interactive.py
…
test_cron_prompt_injection.py
…
test_cronjob_job_args.py
…
test_cronjob_run_background.py
…
test_cronjob_run_delivery_notice.py
…
test_cronjob_run_immediate.py
fix(review): ticker heartbeat proves liveness only while its writer is alive; routed hand-off never trusts an unknown probe; satellite manual runs get the ticker's routed grant
2026-09-28 05:28:05 -07:00
test_cronjob_run_primary_routed.py
fix(review): ticker heartbeat proves liveness only while its writer is alive; routed hand-off never trusts an unknown probe; satellite manual runs get the ticker's routed grant
2026-09-28 05:28:05 -07:00
test_cronjob_tools.py
…
test_cross_profile_guard.py
…
test_daemon_pool.py
…
test_daytona_environment.py
test(environments): trim payload-stdin tests to two invariants
2026-09-26 23:44:55 +05:30
test_debug_helpers.py
…
test_deferral_fixes.py
…
test_delegate_apiserver_background.py
…
test_delegate_batch_tag.py
…
test_delegate_batch_validation.py
…
test_delegate_capability_inheritance.py
…
test_delegate_capacity_interrupt.py
…
test_delegate_child_cache_ttl.py
…
test_delegate_child_compression_cap.py
…
test_delegate_child_transcript_release.py
…
test_delegate_composite_toolsets.py
…
test_delegate_control_actions.py
…
test_delegate_cost_footer.py
…
test_delegate_cron_sync_fallback.py
…
test_delegate_depth_prompt.py
…
test_delegate_external_provider.py
…
test_delegate_failure_copy.py
…
test_delegate_fallback_matrix.py
…
test_delegate_group_schema.py
…
test_delegate_images.py
…
test_delegate_interrupted_partial_output.py
…
test_delegate_kanban_isolation.py
…
test_delegate_late_child_inherits_stop.py
…
test_delegate_liveness_timeout.py
…
test_delegate_native_vision.py
…
test_delegate_output_schema.py
…
test_delegate_parallel_interrupt_join.py
…
test_delegate_request_overrides.py
…
test_delegate_stale_wait_release.py
…
test_delegate_subagent_timeout_diagnostic.py
test(delegate): tidy #121572 follow-ups
2026-09-27 18:17:20 +05:30
test_delegate_summary_budget.py
…
test_delegate_sync_failure_echo_policy.py
…
test_delegate_timeout_cleanup.py
…
test_delegate_toolset_scope.py
…
test_delegate.py
…
test_delegation_live_log.py
…
test_delegation_recovery_diagnostics.py
…
test_denial_circuit_breaker.py
…
test_desktop_tools_diet.py
…
test_desktop_ui.py
…
test_discord_send_message_caption.py
…
test_discord_tool.py
…
test_display_toggles.py
…
test_docker_cgroup_limits.py
…
test_docker_config_migrate.py
Merge remote-tracking branch 'origin/main' into ethie/pm-clean
2026-09-24 06:08:20 -04:00
test_docker_daemon_redirect.py
…
test_docker_environment.py
…
test_docker_find.py
…
test_docker_mounted_host_session_cwd.py
fix(docker): remap a mounted host session cwd to /workspace
2026-09-26 17:34:46 -05:00
test_docker_network_config.py
feat(bot_desktop): Bot Screen, computer_use and the browser run inside the terminal backend (#121169)
2026-09-28 03:34:07 -07:00
test_docker_orphan_reaper_integration.py
…
test_docker_rebootstrap_nous_session.py
…
test_docker_session_isolation.py
fix(terminal,api-server): trim profile qualification of session-derived sandbox keys (#123989, salvage #124057 + #123991)
2026-09-28 04:34:30 -07:00
test_docker_teardown_drain.py
…
test_docker_windows_cwd_mount.py
test(docker): a mounted host dir follows the fallback mount
2026-09-26 18:27:10 -05:00
test_drain_fd_windows.py
…
test_drive_preview_tool.py
…
test_ensure_task_env.py
…
test_env_passthrough.py
…
test_env_probe.py
…
test_execute_code_approval_cluster.py
…
test_execute_code_lifecycle_guard_deadline.py
…
test_execute_helper_contract.py
…
test_execution_flag_detection.py
…
test_fal_common.py
…
test_fal_sdk.py
…
test_file_operations_delete.py
fix(file_tools): a trailing '.' still names the Delete/Move entry, not its target
2026-09-27 01:10:56 +05:30
test_file_operations_edge_cases.py
fix: Hermes's own lint, activate, tui and MCP launchers use PM's node/npx/uv, never the user's
2026-09-27 22:30:55 -07:00
test_file_operations.py
fix(file-ops): verify the byte-exact read against the file's own byte count
2026-09-25 14:58:09 -04:00
test_file_ops_cwd_tracking.py
…
test_file_ops_env_not_ready.py
…
test_file_ops_single_roundtrip.py
fix(environments): deliver heredoc stdin byte-exact
2026-09-25 14:14:06 -04:00
test_file_read_guards.py
…
test_file_staleness.py
…
test_file_state_registry.py
…
test_file_sync_back.py
…
test_file_sync_sigint.py
…
test_file_sync_upload_snapshot.py
…
test_file_sync.py
…
test_file_tools_container_config.py
…
test_file_tools_cwd_resolution.py
fix(file_tools): a trailing '.' still names the Delete/Move entry, not its target
2026-09-27 01:10:56 +05:30
test_file_tools_live.py
…
test_file_tools_plugin_container_cwd.py
…
test_file_tools_tilde_profile.py
…
test_file_tools.py
…
test_file_write_safety.py
fix(file-ops): keep fenced byte-exact reads usable under xtrace
2026-09-27 02:39:29 +05:30
test_file_write_surrogate_roundtrip.py
test(environments): cover Vercel stdin staging instead of the local contract
2026-09-26 23:44:55 +05:30
test_find_shell.py
…
test_finite_delegation_outcomes.py
…
test_focus_pane_tool.py
…
test_fuzzy_match.py
test(fuzzy_match): cover 3-char expansion boundary in the same invariant test
2026-09-24 15:58:26 +05:30
test_gateway_cwd_contract.py
…
test_generation_source_confinement.py
…
test_git_consumer_environment.py
…
test_gnu_long_option_abbreviation_bypass.py
…
test_hardline_blocklist.py
…
test_hardline_escaped_quote_state.py
…
test_hermes_subprocess_env.py
…
test_homeassistant_tool.py
…
test_hook_output_spill.py
…
test_hub_lock_non_utf8.py
…
test_image_generate_schema.py
…
test_image_generation_artifacts.py
…
test_image_generation_env.py
…
test_image_generation_image_to_image.py
…
test_image_generation_interrupt.py
…
test_image_generation_managed.py
…
test_image_generation_plugin_dispatch.py
…
test_image_generation.py
…
test_image_source.py
…
test_init_session_cwd_respect.py
…
test_interrupt.py
…
test_interrupted_command_cwd.py
…
test_kanban_comment_injection.py
…
test_kanban_complete_parents_tool.py
…
test_kanban_descendant_scope.py
…
test_kanban_persisted_identity.py
…
test_kanban_provenance.py
…
test_kanban_redaction.py
…
test_kanban_tools.py
fix(kanban): a worker the dispatcher never recorded registers itself instead of being run twice
2026-09-26 11:16:45 -07:00
test_kanban_toolset_opt_in.py
…
test_kanban_unknown_arguments.py
…
test_kill_verify_tree_death.py
…
test_known_file_write_baseline.py
…
test_launchctl_guard_diagnostic.py
…
test_line_ending_preservation.py
…
test_live_env_cwd_override_sanitize.py
…
test_llm_content_none_guard.py
…
test_local_background_child_hang.py
…
test_local_cwd_permission_fallback.py
…
test_local_env_blocklist.py
…
test_local_env_cwd_recovery.py
…
test_local_env_relative_cwd.py
…
test_local_env_session_leak.py
…
test_local_env_windows_msys.py
…
test_local_interrupt_cleanup.py
Merge origin/main into ethie/pm-clean
2026-09-23 21:55:59 -04:00
test_local_setsid_descendant_sweep.py
…
test_local_shell_init.py
…
test_local_temp_dir.py
…
test_macos_protected_search.py
…
test_managed_browserbase_and_modal.py
…
test_managed_media_gateways.py
…
test_managed_modal_environment.py
…
test_managed_tool_gateway.py
…
test_mcp_app_gate.py
…
test_mcp_bridge_single_failure.py
…
test_mcp_cancelled_error_propagation.py
…
test_mcp_capability_gating.py
…
test_mcp_cimd.py
…
test_mcp_circuit_breaker.py
…
test_mcp_client_cert.py
…
test_mcp_config_change_rebind.py
…
test_mcp_config_whitespace_warning.py
…
test_mcp_connect_secret_scope.py
fix(review): MCP owner rebuild keeps the launch profile's env-only credentials (#119092 review)
2026-09-28 05:24:26 -07:00
test_mcp_dashboard_oauth.py
…
test_mcp_death_supervisor.py
…
test_mcp_device_flow.py
…
test_mcp_dynamic_discovery.py
…
test_mcp_elicitation.py
…
test_mcp_empty_error_message.py
…
test_mcp_enabled_reader.py
…
test_mcp_failure_classification.py
…
test_mcp_google_offline_access.py
…
test_mcp_http_body_cap.py
…
test_mcp_http_proxy.py
…
test_mcp_identity_header.py
…
test_mcp_image_content.py
…
test_mcp_initial_connect_shutdown.py
…
test_mcp_invalid_url.py
…
test_mcp_lazy_start.py
…
test_mcp_list_pagination.py
…
test_mcp_liveness_catalog.py
…
test_mcp_liveness.py
fix(tools): say 'MCP connection missing' when only the MCP connection is missing
2026-09-27 06:26:52 -05:00
test_mcp_loop_profile_override.py
…
test_mcp_multiplex_connection_keys.py
fix(mcp): resolve the adopter's identity in its own scope, and never abort the pass on it
2026-09-26 22:40:54 +05:30
test_mcp_node_abi.py
fix(mcp): name the rebuild when a stdio server's native addon was built for another Node
2026-09-27 21:30:10 -07:00
test_mcp_npx_cached_bin.py
…
test_mcp_oauth_bidirectional.py
…
test_mcp_oauth_callback_latch.py
…
test_mcp_oauth_cold_load_expiry.py
…
test_mcp_oauth_discovery_requests.py
…
test_mcp_oauth_integration.py
fix(mcp): seed OAuth disk-watch baseline before reload
2026-09-25 14:27:51 +05:30
test_mcp_oauth_issuer_binding.py
…
test_mcp_oauth_issuer_origin.py
…
test_mcp_oauth_manager.py
fix(mcp): reload OAuth provider on first sight when no tokens in memory (#39551)
2026-09-25 14:27:51 +05:30
test_mcp_oauth_metadata.py
…
test_mcp_oauth_missing_iss.py
…
test_mcp_oauth_stdin_console.py
…
test_mcp_oauth_user_agent.py
…
test_mcp_oauth.py
…
test_mcp_park_log_dedupe.py
…
test_mcp_parked_probe_no_browser.py
…
test_mcp_parked_probe_skips_disabled.py
…
test_mcp_parked_self_probe.py
…
test_mcp_poll_loop_oom_integration.py
…
test_mcp_preflight_content_type.py
…
test_mcp_probe.py
…
test_mcp_protocol_negotiation.py
…
test_mcp_rapid_drop_budget.py
…
test_mcp_reconcile_with_config.py
…
test_mcp_reconnect_log_hygiene.py
…
test_mcp_reconnect_retry_reset.py
…
test_mcp_reconnect_signal.py
…
test_mcp_register_wakes_stale.py
…
test_mcp_resource_content.py
…
test_mcp_result_size_limit.py
…
test_mcp_schema_cache_ttl.py
…
test_mcp_schema_cache.py
…
test_mcp_server_log_notifications.py
…
test_mcp_server_reconnecting_predicate.py
…
test_mcp_shared_connection_resolved_identity.py
test(mcp): keep the two end-to-end adoption invariants
2026-09-26 22:40:54 +05:30
test_mcp_sse_fallback.py
…
test_mcp_sse_transport.py
…
test_mcp_stability.py
…
test_mcp_startup_summary_names_failures.py
…
test_mcp_stderr_lifecycle.py
fix(logs): hermes logs --since/--level handle unstamped lines and MCP output
2026-09-28 19:02:20 +05:30
test_mcp_stdio_children_dead.py
…
test_mcp_stdio_dead_reconnect.py
…
test_mcp_stdio_encoding_handler.py
…
test_mcp_stdio_fastfail_reconnect.py
…
test_mcp_stdio_init_timeout.py
…
test_mcp_streamable_http_arity.py
…
test_mcp_structured_content.py
…
test_mcp_timeout_resolution.py
…
test_mcp_tool_401_handling.py
…
test_mcp_tool_errors.py
…
test_mcp_tool_issue_948.py
fix: Hermes's own lint, activate, tui and MCP launchers use PM's node/npx/uv, never the user's
2026-09-27 22:30:55 -07:00
test_mcp_tool_session_expired.py
…
test_mcp_tool.py
fix: Hermes's own lint, activate, tui and MCP launchers use PM's node/npx/uv, never the user's
2026-09-27 22:30:55 -07:00
test_mcp_transport_group_reconnect.py
…
test_mcp_trust_gating.py
…
test_mcp_utility_capability_gating.py
…
test_mcp_windows_orphan_fix.py
fix(mcp): kill Windows stdio MCP orphan trees (#61059)
2026-09-26 20:58:16 -04:00
test_media_caption_split.py
…
test_memory_tool_import_fallback.py
…
test_memory_tool_schema.py
…
test_memory_tool.py
fix(memory): refuse unpinned legacy replace/remove at approval
2026-09-24 15:38:22 +05:30
test_microsoft_graph_auth.py
…
test_microsoft_graph_client.py
…
test_modal_bulk_upload.py
test(environments): cover Vercel stdin staging instead of the local contract
2026-09-26 23:44:55 +05:30
test_modal_sandbox_fixes.py
…
test_modal_snapshot_isolation.py
…
test_model_tools.py
…
test_multiplex_tool_cache_scope.py
…
test_multiplex_tool_credential_scope.py
…
test_multiplex_tool_memo_scope.py
test: preserve skill schema cache stability across profiles
2026-09-24 04:38:23 -04:00
test_multiplex_turn_parity.py
fix(agent): preserve configured context cwd on desktop compaction
2026-09-28 11:29:49 -05:00
test_notebook_recovery_path.py
…
test_notify_on_complete.py
…
test_oneshot_completion_linger.py
Merge remote-tracking branch 'origin/main' into ethie/pm-clean
2026-09-24 06:55:33 -04:00
test_open_preview_tool.py
test(tools): pin open_preview missing-path emit (#95853)
2026-09-26 16:51:19 -05:00
test_osv_check.py
…
test_parse_env_var.py
…
test_patch_already_applied.py
…
test_patch_multimatch_locations.py
…
test_patch_parser.py
fix(file-ops): a failed byte-exact read is not an absent file
2026-09-25 14:58:09 -04:00
test_patch_v4a_gate.py
…
test_patch_ws_diagnosis.py
…
test_permanent_allowlist_reconcile.py
…
test_persist_on_release.py
fix(processes): persist_on_release keeps background jobs alive across lifecycle kill sweeps (#41225)
2026-09-25 13:49:31 -05:00
test_plugin_compat_warning.py
…
test_plugin_guard_block_reason.py
…
test_plugin_guard.py
…
test_plugin_skills.py
…
test_pr_6656_regressions.py
…
test_pre_transcription_hook.py
…
test_process_checkpoint_readopt.py
fix(process): kill a re-adopted PID whose start time is unreadable
2026-09-26 17:19:34 -05:00
test_process_heartbeat.py
fix(process): heartbeats wake the agent only on new output, and never as a user bubble
2026-09-26 22:19:53 -05:00
test_process_registry_lazy_restore.py
fix(review): replay the launch ledger regardless of the first consumer's profile scope (#123265)
2026-09-28 05:37:55 -07:00
test_process_registry_list_exit.py
…
test_process_registry_windows_live.py
…
test_process_registry_write_stdin_surrogates.py
…
test_process_registry.py
…
test_process_schema_diet.py
…
test_process_wait_clarity.py
…
test_profile_gate_env_isolation.py
…
test_profile_gate_env_shape.py
…
test_project_tools.py
fix(projects): CLI and pathless switches move the active project again
2026-09-24 03:52:03 -05:00
test_pty_query_responder.py
…
test_react_to_message_tool.py
…
test_read_binary_type_disclosure.py
…
test_read_extract.py
…
test_read_file_schema_gating.py
…
test_read_file_utf8_binary_regression.py
…
test_read_loop_detection.py
…
test_read_past_eof_note.py
…
test_read_preview_tool.py
…
test_read_shell_line_clamp.py
…
test_read_special_file_guard.py
…
test_read_unicode_filename_retry.py
…
test_read_window_tool.py
…
test_refresh_agent_mcp_tools.py
fix: key the tools[] pin by code version; never re-add config-excluded tools
2026-09-23 15:43:51 -07:00
test_registry.py
…
test_remote_binary_write_guard.py
test(file-tools): pin remote NEW binary-extension creation as allowed
2026-09-26 22:26:05 +05:30
test_removed_backend_migration.py
…
test_request_tool_approval.py
…
test_resolve_path.py
…
test_restored_delegation_ownership.py
…
test_rollback_all_directories.py
…
test_safe_getcwd_permission_error.py
…
test_sandbox_failure_hints.py
…
test_schema_boolean_required.py
…
test_schema_sanitizer.py
…
test_search_auto_multiline.py
…
test_search_budget_truncation.py
…
test_search_error_guard.py
…
test_search_files_cpu_windows.py
…
test_search_files_engine_selection.py
…
test_search_giant_line_containment.py
…
test_search_hidden_dirs.py
…
test_search_native_rg.py
…
test_search_zero_match_and_multipath.py
…
test_self_repo_guard.py
…
test_send_message_cross_loop.py
…
test_send_message_missing_platforms.py
…
test_send_message_multiplex_profile_adapter.py
…
test_send_message_plugin_extensibility.py
…
test_send_message_react.py
…
test_send_message_relay_target_authz.py
…
test_send_message_slack.py
…
test_send_message_surrogate_sanitization.py
…
test_send_message_target_parse.py
…
test_send_message_telegram_proxy.py
…
test_send_message_tool.py
…
test_session_cwd_store.py
…
test_session_search.py
…
test_shared_container_task_id.py
…
test_shell_arg_transport.py
…
test_shell_bypass_denylist.py
…
test_signal_media.py
…
test_single_query_approval_mode.py
…
test_singularity_persistent_overlay.py
…
test_singularity_preflight.py
…
test_skill_bundle_provenance.py
…
test_skill_create_dir.py
fix: stabilize Python e2e entrypoints and skill schema
2026-09-24 03:42:38 -04:00
test_skill_env_passthrough.py
…
test_skill_improvements.py
…
test_skill_ledger_delta.py
…
test_skill_ledger.py
…
test_skill_linter.py
…
test_skill_manage_batch.py
fix(skills): batch rollback undoes every file it wrote into an adopted dir
2026-09-24 16:49:18 +05:30
test_skill_manage_schema_diet.py
…
test_skill_manager_tool.py
Merge remote-tracking branch 'origin/main' into ethie/pm-clean
2026-09-24 07:39:33 -04:00
test_skill_provenance.py
…
test_skill_size_limits.py
…
test_skill_usage.py
…
test_skill_view_dedup.py
test(compression): drop mock-only codex compaction skill_view test
2026-09-27 00:19:50 +05:30
test_skill_view_traversal.py
…
test_skillevaluator_scan.py
…
test_skills_ast_audit.py
…
test_skills_guard_agent_config.py
…
test_skills_guard.py
…
test_skills_hub_browse_sh.py
…
test_skills_hub_clawhub.py
…
test_skills_hub.py
…
test_skills_list_modified_diff.py
…
test_skills_runtime_cache.py
…
test_skills_sync_client.py
…
test_skills_sync.py
fix(skills): keep built-in provenance for skills the catalog dropped
2026-09-25 14:24:56 -05:00
test_skills_tool_discovery_cache.py
…
test_skills_tool_profile_scope.py
…
test_skills_tool.py
…
test_slack_send_message_media.py
…
test_slash_confirm.py
…
test_smart_approval_injection.py
…
test_smart_approval_policy.py
…
test_snapshot_multiline_session_env_injection.py
…
test_snapshot_session_id_leak.py
…
test_spill_safety.py
…
test_spotify_client.py
…
test_ssh_bulk_upload.py
…
test_ssh_environment.py
…
test_ssh_remote_cwd.py
test: pin ssh path and cwd resolution to two invariants
2026-09-26 06:20:21 +05:30
test_stage2_hook_api_server_keygen.py
…
test_stage2_hook_nous_routing_env.py
…
test_stage2_hook_seed_one_symlinks.py
…
test_stage2_hook_symlink_chown.py
…
test_startup_latency_regressions.py
…
test_strict_provider_selection.py
…
test_stt_cloud_trim.py
…
test_stt_idle_unload.py
…
test_stt_language_resolution.py
…
test_stt_resolution_passive.py
…
test_stt_silence_hallucinations.py
…
test_subagent_process_handoff.py
…
test_subagent_steer.py
…
test_subagent_sudo_prompt.py
…
test_subagent_worktree.py
…
test_subprocess_home_isolation.py
…
test_subprocess_stdin_guard.py
…
test_subprocess_utf8_encoding.py
…
test_sync_back_backends.py
…
test_telegram_send_message_caption.py
…
test_telegram_send_message_video_metadata.py
…
test_terminal_backend_unavailable_reason.py
…
test_terminal_bounded_execute.py
…
test_terminal_compound_background.py
…
test_terminal_config_env_sync.py
…
test_terminal_cwd_echo.py
…
test_terminal_degraded_mode.py
…
test_terminal_env_bridge.py
…
test_terminal_environment_recreated_notice.py
…
test_terminal_error_redaction.py
…
test_terminal_exit_semantics.py
…
test_terminal_foreground_timeout_cap.py
…
test_terminal_heredoc_background_guard.py
…
test_terminal_hints.py
…
test_terminal_none_command_guard.py
…
test_terminal_output_transform_hook.py
…
test_terminal_pre_guard_deadline.py
…
test_terminal_requirements.py
…
test_terminal_sandbox_builder_dispatch.py
…
test_terminal_scope_multiplex.py
fix(terminal): persistent Docker keys a routed profile's cron work to its profile container
2026-09-23 16:58:12 -07:00
test_terminal_self_repo_guard.py
…
test_terminal_signal_exit.py
…
test_terminal_task_cwd.py
…
test_terminal_timeout_output.py
…
test_terminal_tool_exception_redaction.py
…
test_terminal_tool_pty_fallback.py
…
test_terminal_tool_requirements.py
…
test_terminal_tool.py
…
test_terminal_truncation_spill.py
…
test_terminal_watcher_arming.py
…
test_terminal_yield_to_background.py
…
test_termux_api_detection.py
…
test_threaded_process_handle.py
…
test_threat_patterns.py
…
test_timeout_transport_drain.py
…
test_tip_tool.py
…
test_tirith_security.py
…
test_tirith_verdicts.py
…
test_todo_nested.py
…
test_todo_tool_type_coercion.py
…
test_todo_tool.py
…
test_tool_backend_helpers.py
…
test_tool_output_limits.py
…
test_tool_output_truncate.py
…
test_tool_result_storage.py
fix(tools): spill MCP result envelopes as pageable text
2026-09-27 01:29:25 -04:00
test_tool_search_context_provider.py
…
test_tool_search_multiquery.py
…
test_tool_search.py
…
test_toolset_distributions.py
…
test_toolsets.py
…
test_tour_tool.py
…
test_transcription_command_providers.py
…
test_transcription_deepinfra.py
…
test_transcription_dotenv_fallback.py
…
test_transcription_plugin_dispatch.py
…
test_transcription_tools.py
fix(stt): never stringify a structured STT error response into the transcript
2026-09-27 03:45:07 -04:00
test_transcription.py
…
test_translate_execute_context.py
…
test_truncation_footer_sandbox_paths.py
…
test_tts_command_providers.py
…
test_tts_container_repair.py
…
test_tts_deepinfra.py
…
test_tts_dotenv_fallback.py
fix(tts): keep the Gemini API key out of request URLs
2026-09-26 06:19:34 +05:30
test_tts_gemini.py
test(tts): keep Gemini tests on the tools.tts_tool import path
2026-09-26 06:19:34 +05:30
test_tts_importers.py
…
test_tts_instructions.py
…
test_tts_kittentts.py
…
test_tts_lifecycle_leases.py
Merge remote-tracking branch 'origin/main' into ethie/pm-clean
2026-09-24 03:48:31 -04:00
test_tts_long_form_chunking.py
…
test_tts_macos_output.py
…
test_tts_max_text_length.py
…
test_tts_minimax_region.py
…
test_tts_mistral.py
…
test_tts_model_cache_lru.py
…
test_tts_openai_config.py
…
test_tts_opus_routing.py
…
test_tts_output_dir_profile_scope.py
…
test_tts_output_timestamp.py
…
test_tts_path_traversal.py
…
test_tts_piper.py
…
test_tts_plugin_dispatch.py
…
test_tts_prepare_spoken.py
…
test_tts_pythonpath_fallback.py
…
test_tts_requirements_passive.py
…
test_tts_response_body_cap.py
…
test_tts_speed.py
…
test_tts_streaming.py
fix(tts): drop unterminated <think> tail on streaming chunker flush (#73962)
2026-09-26 06:19:34 +05:30
test_tts_text_normalize.py
fix(desktop): read table headers aloud instead of dropping tables silently
2026-09-23 18:30:12 -05:00
test_tts_xai_speech_tags.py
…
test_unicode_tag_strip.py
…
test_url_safety.py
…
test_utf16_read.py
…
test_vercel_sandbox_environment.py
test(environments): cover Vercel stdin staging instead of the local contract
2026-09-26 23:44:55 +05:30
test_video_analyze.py
…
test_video_generate_schema.py
…
test_video_generation_dispatch.py
…
test_video_generation_dynamic_schema.py
…
test_video_generation_tool_surface_matrix.py
…
test_vision_history_budget.py
…
test_vision_native_fast_path.py
…
test_vision_region.py
…
test_vision_scale_disclosure.py
…
test_vision_tools.py
…
test_voice_cli_integration.py
…
test_voice_client_config.py
…
test_voice_credential_pool_resolution.py
…
test_voice_max_recording_seconds.py
…
test_voice_mode_playback_env_scrub.py
…
test_voice_mode.py
test(voice): trim #75541 recorder-stream tests to two invariants
2026-09-26 06:19:34 +05:30
test_voice_stop_phrase.py
…
test_voice_thinking_sound.py
…
test_voice_tts_echo_guard.py
…
test_voice_wsl_pipewire.py
…
test_wake_word.py
…
test_watch_patterns.py
…
test_web_backend_capability_isolation.py
…
test_web_extract_robustness.py
…
test_web_extract_timeout.py
…
test_web_keyless_fallback.py
…
test_web_keyless_rescue.py
…
test_web_managed_routing.py
feat(web): serve managed search through Perplexity
2026-09-24 16:17:16 -04:00
test_web_providers_brave_free.py
…
test_web_providers_ddgs.py
…
test_web_providers_searxng.py
…
test_web_providers_xai.py
…
test_web_providers.py
…
test_web_result_cache.py
…
test_web_tools_config.py
…
test_web_tools_dict_urls.py
…
test_web_tools_perplexity.py
…
test_web_tools_tavily.py
…
test_web_tools_truncate.py
…
test_whatsapp_send_message_media.py
…
test_windows_agent_loop_papercuts.py
…
test_windows_native_support.py
docs(tests): name platforms() instead of the retired OS markers
2026-09-24 11:50:30 -04:00
test_working_diff.py
…
test_write_approval.py
Merge remote-tracking branch 'origin/main' into ethie/pm-clean
2026-09-24 06:14:42 -04:00
test_write_deny.py
…
test_write_file_rewrite_hint.py
…
test_write_file_syntax_gate.py
…
test_write_verification.py
…
test_x_search_tool.py
…
test_xai_http_credentials.py
…
test_xai_http_storage.py
…
test_xlsx_phonetic_text.py
…
test_yolo_mode.py
…
test_zombie_process_cleanup.py
test(tools): bind config on the hand-built runner in test_gateway_stop_calls_close
2026-09-28 04:34:30 -07:00