Brooklyn Nicholson f26a0949a4 fix(tools): gate the set_value verdict on type_text_incomplete ...

kokhlo's measurement on the trimmed PR: the zero-delivery gate also catches
type_text_synthesis_budget_exceeded, whose delivered_chars is pinned to 0
because the bounded synthesis budget declined to emit at all. That target is
not dropping synthetic keystrokes, and re-routing it to set_value replaces the
driver's own chunk recommendation with a different write path and a wrong
explanation. The gate now keys on the driver's own partial-delivery verdict;
the hint also names set_value as an action rather than a delivery rung.

2026-10-06 23:49:41 -05:00

..

environments

…

__init__.py

…

_child_env_fixtures.py

test(child-env): fixture isolates the process-wide skill passthrough set

2026-10-05 16:46:53 -05:00

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

refactor(security): remove the bundled tirith scanner from core

2026-10-06 14:22:13 -07:00

test_approval_deny_rules.py

…

test_approval_gateway_wait_late_choice.py

…

test_approval_global_flag_scan.py

fix(approval): give global-flag runs one parse in dangerous-command rules

2026-09-30 21:33:08 -04:00

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

refactor(security): remove the bundled tirith scanner from core

2026-10-06 14:22:13 -07:00

test_approval_timeout_overflow.py

…

test_approval_user_summary.py

…

test_approval_windows.py

…

test_approval.py

feat(approvals): flag credential uploads and invisible Unicode in terminal commands

2026-10-06 14:22:13 -07:00

test_approved_command_clean_slate.py

…

test_async_batch_task_failure_notice.py

…

test_async_delegation_failed_surface.py

…

test_async_delegation_fd_leak.py

…

test_async_delegation_orphan_sweep.py

…

test_async_delegation_retirement.py

…

test_async_delegation_stale_profile_scope.py

…

test_async_delegation.py

…

test_audio_container.py

…

test_base_environment.py

…

test_binary_document_write_guard.py

…

test_blocked_command_guidance.py

…

test_blueprints.py

…

test_bot_delivery_install_launcher.py

…

test_bot_desktop_browser_fence.py

…

test_bot_desktop_browser.py

…

test_bot_desktop_idle.py

…

test_bot_desktop_install.py

…

test_bot_desktop_launcher_seed.py

…

test_bot_desktop_launcher_xvnc.py

…

test_bot_desktop_lease.py

…

test_bot_desktop_placement.py

…

test_bot_desktop_resources.py

…

test_bot_desktop_rfb_filter_limits.py

…

test_bot_desktop_runtime.py

…

test_bot_desktop_thumbnail.py

…

test_bot_dm_payload_cache.py

…

test_bot_failure_reasons.py

fix(bot-relay): classify the named-secret spelling of a scope refusal too

2026-10-01 16:18:46 +05:30

test_bot_live_owner_delivery.py

fix(bot-mode): carry late live DM replies to sender

2026-09-30 09:57:30 -05:00

test_bot_mode_canonical_chat_resolution.py

…

test_bot_mode_dm_entry.py

…

test_bot_mode_dm.py

test(bot-mode): live DM retry test no longer hangs CI on a slow runner

2026-10-04 21:29:04 -07:00

test_bot_mode_probe.py

…

test_bot_mode_refusal_contract.py

…

test_bot_relay_windows_paths.py

…

test_bot_relay.py

test(bot-relay): pin that a home override beats the launch-home fallback

2026-10-01 16:18:46 +05:30

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

fix(tools): preserve agent-browser session for CDP commands to resolve snapshot refs

2026-10-01 03:18:09 -05:00

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: drop tests that cannot fail or duplicate a same-file keeper

2026-09-29 15:58:55 +05:30

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: drop tests that cannot fail or duplicate a same-file keeper

2026-09-29 15:58:55 +05:30

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 tree-kill unit tests no longer SIGKILL real processes under PID 999

2026-10-06 04:36:02 -07:00

test_browser_real_profile_pin.py

…

test_browser_real_profile.py

fix(browser): bound real-profile resolver lock wait

2026-10-02 22:54:53 -05:00

test_browser_secret_exfil.py

…

test_browser_snapshot_ssrf.py

…

test_browser_snapshot_threshold.py

…

test_browser_ssrf_local.py

…

test_browser_supervisor_capture.py

feat(browser): public captured CDP call seam for trusted plugins

2026-10-05 17:10:58 -07:00

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): /browser connect and disconnect retarget browser_exec

2026-10-02 11:06:58 -05:00

test_browser_use_harness.py

…

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

…

test_checkpoint_gitlinks.py

fix(checkpoints): refuse an empty restore selection and delete read-only test repos

2026-09-29 14:12:41 -04:00

test_checkpoint_manager.py

fix(checkpoints): scope nested repo restore refusal

2026-09-29 14:12:41 -04:00

test_checkpoint_path_roundtrip.py

…

test_checkpoint_size_cap.py

…

test_checkpoint_store_ownership.py

…

test_clarify_gateway.py

Clarify: one question shape and one result shape on every surface (skip, cancel, timeout and undelivered are told apart) (#127760)

2026-09-29 18:33:44 +05:30

test_clarify_tool.py

fix(tools): reject all-blank and over-limit clarify choices instead of dropping them silently

2026-09-29 19:44:05 -05:00

test_clawhub_owner_http.py

…

test_clawhub_zip_stream.py

…

test_cli_approval_exec_ask_leak.py

refactor(security): remove the bundled tirith scanner from core

2026-10-06 14:22:13 -07:00

test_clipboard.py

…

test_close_preview_tool.py

…

test_code_execution_file_rpc.py

…

test_code_execution_hermes_home.py

…

test_code_execution_modes.py

…

test_code_execution_pm_runtime.py

…

test_code_execution_windows_env.py

test: restore five contracts the preservation review found uncovered

2026-09-29 15:58:55 +05:30

test_code_execution.py

…

test_code_kernel_remote.py

…

test_code_kernel.py

…

test_command_guards.py

refactor(security): remove the bundled tirith scanner from core

2026-10-06 14:22:13 -07:00

test_compaction_tool_refresh.py

…

test_completed_process_results.py

…

test_computer_use_approval_isolation.py

…

test_computer_use_ax_walk_bound.py

…

test_computer_use_backend_lifecycle.py

…

test_computer_use_backend_plugins.py

feat(computer-use): pluggable single-select computer-use providers

2026-10-05 17:20:30 -07:00

test_computer_use_backend_rebind.py

…

test_computer_use_capture_fence.py

…

test_computer_use_capture_routing.py

…

test_computer_use_capture_self_window.py

fix(computer-use): skip driver self-windows in implicit capture

2026-10-02 20:30:25 -05:00

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

feat(computer-use): pluggable single-select computer-use providers

2026-10-05 17:20:30 -07:00

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

feat(computer-use): pluggable single-select computer-use providers

2026-10-05 17:20:30 -07:00

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_zero_delivery_verdict.py

fix(tools): gate the set_value verdict on type_text_incomplete

2026-10-06 23:49:41 -05:00

test_computer_use.py

feat(computer-use): pluggable single-select computer-use providers

2026-10-05 17:20:30 -07:00

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

fix(catalog): sessions off the desktop no longer see manage_catalog through tool_search (review)

2026-10-07 01:01:14 +05:30

test_connectors_contract.py

…

test_connectors_gateway_client.py

…

test_connectors_gateway_merge.py

…

test_connectors_gateway_wire.py

…

test_connectors_import_deadlock.py

refactor(connectors): trim lazy-surface docstrings and test path setup

2026-10-03 16:56:51 +05:30

test_connectors_live.py

…

test_connectors_managed.py

…

test_connectors_mcp.py

…

test_connectors_operation.py

feat(desktop): every desktop chat can install catalog plugins; tools gated by session platform

2026-10-07 01:01:14 +05:30

test_connectors_tool.py

…

test_container_cwd_sanitize.py

…

test_credential_files.py

fix(gateway): deliver and bound-sync generated media in cache/generated

2026-10-02 01:18:03 +05:30

test_credential_pool_env_fallback.py

…

test_cron_approval_mode.py

refactor(security): remove the bundled tirith scanner from core

2026-10-06 14:22:13 -07:00

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

…

test_cronjob_run_primary_routed.py

…

test_cronjob_tools.py

fix(config): skip a configured provider URL that urlparse rejects instead of raising

2026-10-03 16:31:09 +05:30

test_cross_profile_guard.py

…

test_daemon_pool.py

…

test_daytona_environment.py

…

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_heartbeat_collect.py

fix(delegation): collect a child's real result in a grace window after the stale-heartbeat verdict

2026-10-05 16:40:38 -05:00

test_delegate_stale_wait_release.py

…

test_delegate_subagent_timeout_diagnostic.py

…

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

fix(delegate): preserve inherited fixed child credentials

2026-10-02 20:24:30 -05:00

test_delegation_live_log.py

fix(delegation): type-validate the parent db_path before pinning the live home

2026-10-02 21:49:36 -05:00

test_delegation_recovery_diagnostics.py

test(delegation): read the owner's git state from a throwaway repo

2026-10-02 01:24:41 +05:30

test_denial_circuit_breaker.py

refactor(security): remove the bundled tirith scanner from core

2026-10-06 14:22:13 -07:00

test_desktop_tools_diet.py

…

test_desktop_ui.py

fix(desktop): route message.reaction events by session id, not window id

2026-10-01 01:53:55 -05:00

test_discord_send_message_caption.py

…

test_discord_tool.py

…

test_display_toggles.py

…

test_docker_cgroup_limits.py

…

test_docker_config_migrate.py

refactor(cli): move the config version stamp into config_version_stamp

2026-10-06 14:57:23 -05:00

test_docker_daemon_redirect.py

…

test_docker_environment.py

fix(docker): keep per-process temp mounts out of the reuse fingerprint

2026-10-02 21:43:34 -05:00

test_docker_find.py

…

test_docker_mounted_host_session_cwd.py

…

test_docker_network_config.py

…

test_docker_orphan_reaper_integration.py

…

test_docker_rebootstrap_nous_session.py

…

test_docker_session_isolation.py

…

test_docker_teardown_drain.py

…

test_docker_windows_cwd_mount.py

…

test_drain_fd_windows.py

…

test_drive_preview_tool.py

fix(tools): split the merged preview/terminal bridge timeout errors into the two cases they conflate

2026-09-29 12:25:29 -05:00

test_ensure_task_env.py

…

test_env_passthrough.py

fix(skills): make env_passthrough registrations visible across tool context snapshots

2026-10-05 16:46:53 -05:00

test_env_probe.py

…

test_execute_code_approval_cluster.py

refactor(security): remove the bundled tirith scanner from core

2026-10-06 14:22:13 -07:00

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

…

test_file_operations_edge_cases.py

fix(file-ops): refuse JSON NaN/Infinity only when the write introduces it

2026-10-02 01:15:39 +05:30

test_file_operations.py

fix(tools): keep the find lane's depth-0 match; exclude the root by identity

2026-10-02 21:47:39 -05:00

test_file_ops_cwd_tracking.py

…

test_file_ops_env_not_ready.py

…

test_file_ops_single_roundtrip.py

…

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

…

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

…

test_file_write_surrogate_roundtrip.py

…

test_find_shell.py

…

test_finite_delegation_outcomes.py

test(delegate): sync the parent-interrupt case on the collected sibling, not its close()

2026-10-04 05:13:55 -07:00

test_focus_pane_tool.py

…

test_fuzzy_match.py

refactor(tools): pass each region to the Unicode-preserving replacement

2026-10-02 01:15:39 +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

fix: HASS_TOKEN stays out of child processes when the Home Assistant plugin is absent

2026-10-04 00:08:20 -07:00

test_hook_output_spill.py

…

test_hub_lock_non_utf8.py

…

test_human_input_hooks.py

feat(plugins): on_human_input_request / on_human_input_resolved hooks

2026-10-05 01:15:16 -07:00

test_image_generate_schema.py

test(image_gen): state the creative-controls schema relationship as a subset check

2026-10-01 16:22:28 +05:30

test_image_generation_artifacts.py

test(agent): trim generated-media salvage tests to two invariants

2026-10-02 01:18:03 +05:30

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_gen): state the creative-controls schema relationship as a subset check

2026-10-01 16:22:28 +05:30

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): bind auto-subscriptions to the live session after a compaction fork

2026-10-02 20:24:01 -05:00

test_kanban_toolset_opt_in.py

…

test_kanban_unknown_arguments.py

…

test_kill_verify_tree_death.py

…

test_known_file_write_baseline.py

fix(tools): a task's own patch keeps its full-file write baseline

2026-10-06 15:39:24 +00:00

test_launchctl_guard_diagnostic.py

…

test_lazy_deps_runtime.py

fix(update): mark current updater frames with a sentinel, not missing locals

2026-09-29 16:47:48 +05:30

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

fix: HASS_TOKEN stays out of child processes when the Home Assistant plugin is absent

2026-10-04 00:08:20 -07:00

test_local_env_bot_desktop.py

fix(terminal): route GUI launches to the running Bot Desktop screen

2026-09-29 18:49:11 -05:00

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

…

test_local_setsid_descendant_sweep.py

Address PR review feedback (#119150)

2026-10-05 16:42:57 -05:00

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

…

test_mcp_dashboard_oauth.py

…

test_mcp_death_supervisor.py

…

test_mcp_device_flow.py

…

test_mcp_dynamic_discovery.py

fix: a user plugin cannot mark a core platform trusted_inbound

2026-10-04 00:08:20 -07:00

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

feat(plugins): requires.gpu gates a plugin server on the host's GPU vendor

2026-10-03 10:26:12 -07:00

test_mcp_loop_profile_override.py

…

test_mcp_multiplex_connection_keys.py

…

test_mcp_node_abi.py

…

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

test: fold private-predicate and replayed-contract tests into their keepers

2026-09-29 15:58:55 +05:30

test_mcp_oauth_issuer_binding.py

…

test_mcp_oauth_issuer_origin.py

…

test_mcp_oauth_manager.py

test: fold private-predicate and replayed-contract tests into their keepers

2026-09-29 15:58:55 +05:30

test_mcp_oauth_metadata.py

…

test_mcp_oauth_missing_iss.py

…

test_mcp_oauth_stdin_console.py

test: fold private-predicate and replayed-contract tests into their keepers

2026-09-29 15:58:55 +05:30

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_sse_fallback.py

…

test_mcp_sse_transport.py

…

test_mcp_stability.py

fix(mcp): SIGKILL a dead MCP server's descendants that ignored SIGTERM

2026-10-03 09:38:33 -07:00

test_mcp_startup_summary_names_failures.py

…

test_mcp_stderr_lifecycle.py

…

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(mcp): drive user-hit candidates from the child env's PATHEXT

2026-10-04 12:42:25 -05:00

test_mcp_tool_session_expired.py

…

test_mcp_tool.py

fix(mcp): make sampling.tools capability opt-in via expose_client_tools

2026-10-05 16:47:32 -05:00

test_mcp_transport_group_reconnect.py

…

test_mcp_trust_gating.py

fix(mcp): read readOnlyHint from mcp 2.x snake_case annotations

2026-10-05 15:28:17 -07:00

test_mcp_utility_capability_gating.py

…

test_mcp_windows_orphan_fix.py

…

test_media_caption_split.py

…

test_memory_tool_import_fallback.py

…

test_memory_tool_schema.py

…

test_memory_tool.py

fix(memory): punctuation-only old_text never selects an entry; consolidate tests

2026-10-05 15:36:45 -07:00

test_microsoft_graph_auth.py

…

test_microsoft_graph_client.py

…

test_modal_bulk_upload.py

…

test_modal_sandbox_fixes.py

refactor(security): remove the bundled tirith scanner from core

2026-10-06 14:22:13 -07:00

test_modal_snapshot_isolation.py

…

test_model_tools.py

…

test_multiplex_tool_cache_scope.py

refactor(security): remove the bundled tirith scanner from core

2026-10-06 14:22:13 -07:00

test_multiplex_tool_credential_scope.py

…

test_multiplex_tool_memo_scope.py

…

test_multiplex_turn_parity.py

…

test_notebook_recovery_path.py

…

test_notify_on_complete.py

…

test_oneshot_completion_linger.py

test: keep one ordering contract for single-query finalize

2026-09-30 10:32:09 -05:00

test_open_preview_tool.py

…

test_osv_check.py

…

test_parse_env_var.py

…

test_patch_already_applied.py

…

test_patch_multimatch_locations.py

…

test_patch_parser.py

…

test_patch_v4a_gate.py

…

test_patch_ws_diagnosis.py

…

test_permanent_allowlist_reconcile.py

…

test_persist_on_release.py

…

test_pgid_starttime_drift.py

fix(mcp): SIGKILL a dead MCP server's descendants that ignored SIGTERM

2026-10-03 09:38:33 -07:00

test_plugin_guard_block_reason.py

…

test_plugin_guard.py

fix(plugin-guard): Google installed-app OAuth client secrets no longer hard-block a plugin install

2026-10-03 09:43:03 -07:00

test_plugin_skills.py

refactor(tui): keep the plugin-skill salvage to the slash surface

2026-10-05 00:23:05 -07:00

test_pr_6656_regressions.py

…

test_pre_transcription_hook.py

…

test_preview_scope_gate.py

fix(tools): tool_call scope gate names the missing GUI surface for preview tools

2026-09-30 23:07:09 -05:00

test_process_checkpoint_readopt.py

…

test_process_heartbeat.py

fix(process): first heartbeat carries output produced before arming

2026-10-03 10:52:57 -07:00

test_process_registry_completion_races.py

fix(process): a kill's result stands on every backend, and a failed scope stop never counts as stopped (#133648)

2026-10-06 00:00:57 -04:00

test_process_registry_lazy_restore.py

…

test_process_registry_list_exit.py

fix(process): a reconcile during the reader's final drain no longer truncates the output

2026-10-05 14:35:39 -04:00

test_process_registry_owner_chain.py

test: drop issue number from test filename (layout guard)

2026-10-01 00:52:58 -05:00

test_process_registry_pty_kill.py

fix(process_registry): drop dashboard/serve worker scoping; make the hang test catch the hang

2026-10-03 17:03:54 -04:00

test_process_registry_windows_live.py

…

test_process_registry_write_stdin_surrogates.py

…

test_process_registry.py

Address PR review feedback (#119150)

2026-10-05 16:42:57 -05:00

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

…

test_protected_instruction_cli_channel.py

fix(terminal): hermes chat -q never waits on a sudo prompt nobody answers

2026-10-05 20:08:11 +05:30

test_pty_query_responder.py

…

test_qqbot_send_message_media.py

fix(qqbot): degrade media send failure to text + warning instead of dropping it

2026-10-05 18:39:43 -05:00

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

fix(tools): word the read_preview hint so the Windows footgun lint doesn't read it as open()

2026-09-29 12:25:29 -05:00

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

…

test_registry.py

…

test_remote_binary_write_guard.py

…

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

fix(clarify): drop maxLength from the choices schema so llama.cpp can parse the grammar (#131286)

2026-10-04 13:18:57 -04:00

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

refactor: move Home Assistant out of core into the homeassistant catalog plugin

2026-10-04 00:08:20 -07:00

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

fix: send_message to a Home Assistant target names the install command while its plugin is absent

2026-10-04 00:08:20 -07:00

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

refactor(security): remove the bundled tirith scanner from core

2026-10-06 14:22:13 -07:00

test_singularity_persistent_overlay.py

…

test_singularity_preflight.py

…

test_skill_bundle_provenance.py

…

test_skill_create_dir.py

…

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

…

test_skill_manage_schema_diet.py

…

test_skill_manager_tool.py

test(skills): pin ambiguous display-name lookup — refuse to guess

2026-10-06 12:00:47 -04:00

test_skill_pending_diff_batch.py

fix(skills): preview a staged patch through the approval matcher

2026-09-30 23:05:43 -05:00

test_skill_provenance_external.py

test(learning-graph): force the external-mount-first scan order

2026-09-30 23:10:24 -05:00

test_skill_provenance.py

…

test_skill_size_limits.py

…

test_skill_usage.py

…

test_skill_view_dedup.py

…

test_skill_view_traversal.py

…

test_skillevaluator_scan.py

…

test_skills_ast_audit.py

…

test_skills_guard_agent_config.py

…

test_skills_guard.py

fix(skills-guard): detect bare-~ destructive rm and inline-shell auto-exec DSL

2026-09-29 20:57:45 -05:00

test_skills_hub_browse_sh.py

…

test_skills_hub_clawhub.py

…

test_skills_hub_generic_dir.py

fix(skills): one install name per skills.sh skill; never swap a gone GitHub path for another skill

2026-10-05 15:56:28 -07:00

test_skills_hub.py

fix(skills): one install name per skills.sh skill; never swap a gone GitHub path for another skill

2026-10-05 15:56:28 -07:00

test_skills_list_modified_diff.py

…

test_skills_runtime_cache.py

…

test_skills_sync.py

…

test_skills_tool_discovery_cache.py

…

test_skills_tool_profile_scope.py

…

test_skills_tool.py

perf(skills): memoize the shadow identity decision, not only the warning

2026-10-04 02:54:56 +05:30

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_spawn_site_child_env.py

…

test_spill_safety.py

…

test_spotify_client.py

…

test_ssh_bulk_upload.py

…

test_ssh_environment.py

fix(desktop): secure SSH workspace browsing

2026-09-29 15:28:19 -05:00

test_ssh_remote_cwd.py

…

test_ssh_session_cwd.py

fix(tools): coerce restored SSH session working directories

2026-10-03 16:30:40 +02:00

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

fix(stt): xAI format=true only with a language; accurate model-default notes

2026-10-06 12:08:49 -07:00

test_stt_resolution_passive.py

…

test_stt_silence_hallucinations.py

…

test_subagent_process_handoff.py

…

test_subagent_steer.py

…

test_subagent_sudo_prompt.py

fix(terminal): hermes chat -q never waits on a sudo prompt nobody answers

2026-10-05 20:08:11 +05:30

test_subagent_worktree.py

…

test_subprocess_home_isolation.py

…

test_subprocess_stdin_guard.py

fix(lint): stdin guard catches calls whose arguments start on the next line (review)

2026-10-07 01:03:03 +05:30

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: tighten the audit's new assertions after review

2026-09-29 15:58:55 +05:30

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_macos_open.py

fix(terminal): report the open outcome from the final observed frontmost state

2026-10-02 22:42:55 -05:00

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

…

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_todo_nested.py

…

test_todo_tool_type_coercion.py

Inline agent tools get the shared argument repair (clarify, todo, memory, session_search) (#127781)

2026-09-29 22:07:30 +05:30

test_todo_tool.py

test(todo): add atomicity and whitespace-merge tests per review feedback

2026-10-06 09:53:34 -04:00

test_tool_backend_helpers.py

…

test_tool_output_limits.py

…

test_tool_output_truncate.py

…

test_tool_result_storage.py

…

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

fix(tour): gui_tour rejects preset with steps, and the docs describe the built-in tour (review)

2026-10-07 01:02:34 +05:30

test_transcription_chunking.py

fix(stt): long recordings fit each provider's upload cap instead of failing

2026-10-06 12:08:49 -07:00

test_transcription_command_providers.py

fix(stt): opt-in 16 kHz mono normalization for command STT providers

2026-10-05 16:40:15 -05:00

test_transcription_deepinfra.py

…

test_transcription_dotenv_fallback.py

…

test_transcription_plugin_dispatch.py

fix(stt): long recordings fit each provider's upload cap instead of failing

2026-10-06 12:08:49 -07:00

test_transcription_streaming.py

feat(stt): live transcription while you speak on CLI, TUI and Desktop (stt.streaming)

2026-10-06 12:50:31 -07:00

test_transcription_tools.py

fix(stt): preserve xAI model override compatibility

2026-10-06 12:08:49 -07:00

test_transcription_whisper_cpp.py

refactor(stt): look up whisper.cpp through pm directly

2026-10-05 12:37:46 -04:00

test_transcription.py

fix(stt): normalize local command language hints

2026-10-06 12:08:04 -05:00

test_translate_execute_context.py

…

test_truncation_footer_sandbox_paths.py

…

test_tts_command_providers.py

fix(tts): hide the console window on Windows command-provider spawns

2026-10-02 18:35:34 -05:00

test_tts_container_repair.py

…

test_tts_deepinfra.py

…

test_tts_dotenv_fallback.py

…

test_tts_gemini.py

…

test_tts_identifier_speech.py

fix(tts): silence identifier-dense tokens in both speech normalizers

2026-09-30 23:02:33 -05:00

test_tts_importers.py

…

test_tts_instructions.py

…

test_tts_kittentts.py

…

test_tts_lifecycle_leases.py

…

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

fix(tts): validate a plugin's stream rate once; keep nous off plugin routing

2026-10-06 00:52:41 -07:00

test_tts_prepare_spoken.py

…

test_tts_provider_authority.py

fix(tts): make tts.provider the authoritative backend selector

2026-10-05 16:42:22 -05:00

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): plugin PCM streamers keep the sync dispatcher's voice and routing

2026-10-06 00:52:41 -07:00

test_tts_text_normalize.py

…

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_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

feat(stt): pin xAI transcription to grok-voice-transcribe-2.0

2026-10-06 12:08:49 -07:00

test_voice_credential_pool_resolution.py

…

test_voice_max_recording_seconds.py

…

test_voice_mode_playback_env_scrub.py

…

test_voice_mode.py

fix(voice): recognise deepinfra in the CLI voice gate so stt.provider=deepinfra can arm voice mode

2026-10-06 12:08:49 -07:00

test_voice_silence_threshold_stop.py

fix(voice): honor configured silence_threshold and stop gating streaming TTS on sounddevice

2026-10-02 18:35:45 -05:00

test_voice_stop_phrase.py

…

test_voice_thinking_sound.py

…

test_voice_tts_echo_guard.py

…

test_voice_wsl_pipewire.py

…

test_wake_word_stream_recovery.py

fix(wake): keep the halt hook armed on the recovered capture

2026-09-29 19:14:28 -05:00

test_wake_word.py

fix(voice): fall back to blocking reads when read_available never advances

2026-09-29 19:14:28 -05:00

test_watch_patterns.py

…

test_web_backend_capability_isolation.py

…

test_web_extract_robustness.py

…

test_web_extract_timeout.py

…

test_web_free_fast_search.py

refactor(web): drop the gate's leftovers and keep the tier rules tested

2026-10-04 00:10:54 +05:30

test_web_keyless_fallback.py

Web search: keyless search moves to the next free vendor on 402, 5xx and Keenable refusals (#134048)

2026-10-07 00:59:32 +05:30

test_web_keyless_rescue.py

…

test_web_managed_routing.py

fix(web): restore free fast search for anonymous guest users

2026-10-04 00:10:54 +05:30

test_web_picker_active_rows.py

fix(tools): web picker stops marking unconfigured rows active or ready

2026-10-06 04:15:29 -07:00

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

fix(web/firecrawl): accept the server timeout in the keyless scrape client

2026-10-02 21:12:48 -05:00

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

fix(whatsapp): body-read timeouts, Windows and failed /health keep ownership

2026-10-03 23:43:03 -04:00

test_windows_agent_loop_papercuts.py

…

test_windows_native_support.py

…

test_working_diff.py

…

test_write_approval.py

refactor(approval): one "no user can answer" helper for every CLI-callback prompt

2026-10-05 20:08:11 +05:30

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

refactor(security): remove the bundled tirith scanner from core

2026-10-06 14:22:13 -07:00

test_zombie_process_cleanup.py

…