Teknium 4e7eb39947 refactor(code-execution): session kernels always on — kernel_mode knob retired (#96787) ...

* refactor(code-execution): retire kernel_mode — session kernels always on for local runs (remote per-call is a tracked gap, not a mode)

* test(code-execution): env-filtering probes use reset=true — kernel env is frozen at spawn, so env rules are only observable on a fresh kernel

* test(code-execution): kernel-aware fixes for mode/pythonpath suites — reset=true on frozen-at-spawn probes, per-test kernel disposal, abort-after-capture fake Popen

* test(code-execution): strict-mode cwd is a behavior contract (staging tmpdir, not session cwd) — kernel stages in hermes_kernel_*, per-call in hermes_sandbox_*

2026-08-27 22:22:39 -07:00

..

__init__.py

…

conftest.py

feat(web): TTL result caching for web_search + web_extract

2026-08-25 04:21:45 -07:00

test_a2a_reason_roundtrip.py

feat(bots): typed failure reasons reach the sending agent on A2A calls (#93091)

2026-08-23 20:07:21 -07:00

test_accretion_caps.py

…

test_allowlist_quoted_metachars.py

…

test_annotate_preview_tool.py

feat(tools): drive_preview and annotate_preview — the agent can use the page it opened

2026-08-20 05:26:37 -05:00

test_ansi_strip.py

…

test_apply_layout_tool.py

feat(desktop): agent-applied layout presets — apply_layout joins the desktop_ui toolset

2026-08-18 21:06:18 -05:00

test_approval_config_readonly.py

…

test_approval_deny_rules.py

…

test_approval_hook_session_id.py

…

test_approval_interrupt.py

…

test_approval_mode_parity.py

…

test_approval_outcome_parity.py

fix(approval): machine-readable outcome parity on the gateway tails + sudo human-wait exclusion (#85125 2e)

2026-08-25 13:27:20 +05:30

test_approval_plugin_hooks.py

…

test_approval_timeout_overflow.py

fix(approval): fail closed when the deadline import is unavailable; log clamp engagement

2026-08-24 16:18:45 +05:30

test_approval_windows.py

…

test_approval.py

fix(gateway): close order-dependency + missing-verb gap in launchctl lifecycle guards

2026-08-23 17:56:36 -07:00

test_approved_command_clean_slate.py

fix(code-exec): preserve interrupt cancellation source

2026-08-23 18:25:19 -07:00

test_async_delegation_fd_leak.py

…

test_async_delegation.py

fix(delegation): expose state durability barriers

2026-08-27 13:48:51 -07:00

test_audio_container.py

…

test_base_environment.py

test(tools): shared sanitizer contract + singularity overlay coverage

2026-08-23 21:12:32 -07:00

test_binary_document_write_guard.py

…

test_blocked_command_guidance.py

…

test_blueprints.py

…

test_bot_dm_payload_cache.py

fix(bot-mode): reap orphaned DM payloads from gateway housekeeping

2026-08-23 03:57:43 -07:00

test_bot_failure_reasons.py

fix(bot-mode): require status-code context for bare numeric classifier rules

2026-08-24 00:57:15 +05:30

test_bot_mode_dm.py

fix(bot-mode): keep delivery runner on host backend

2026-08-27 13:49:04 -07:00

test_bot_mode_probe.py

feat(bot-mode): message_agent tool — structured, Bot-Chat-only agent-to-agent DMs

2026-08-21 15:23:51 -07:00

test_bot_relay_windows_paths.py

fix(bot-relay): add shutil.which step to CLI resolution and pin utf-8 decoding on delivery subprocess

2026-08-24 03:21:37 -07:00

test_bot_relay.py

fix(gateway): stop multiplex allowlist leak and bot-relay python -c injection

2026-08-23 20:00:30 -07:00

test_bot_retry_policy.py

test(bot-relay): match delivery CLI by basename in argv filters

2026-08-24 03:21:37 -07:00

test_bot_turn_lock.py

fix(bot-relay): Windows path SyntaxError in waiter + PATH-less delivery ENOENT

2026-08-24 03:21:37 -07:00

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_chromium_autoinstall.py

…

test_browser_chromium_check.py

…

test_browser_cleanup.py

…

test_browser_cloud_fallback.py

…

test_browser_cloud_provider_cache.py

…

test_browser_command_timeout_race.py

…

test_browser_console_ssrf.py

…

test_browser_console.py

fix(browser): cap browser_vision native embeds for history reuse

2026-08-23 13:27:04 +05:30

test_browser_content_none_guard.py

feat: browser snapshots drop LLM summarization — truncate-and-store like web_extract; auxiliary.web_extract slot removed

2026-08-24 20:11:18 -07:00

test_browser_eval_ssrf.py

…

test_browser_eval_supervisor_path.py

…

test_browser_extension_router_wiring.py

fix(browser): pass encoding to detector subprocesses and accept local_browser in test spies

2026-08-26 19:25:33 -07:00

test_browser_extension_router.py

fix(browser): bind the extension lane at controller registration, not transport auth

2026-08-21 22:33:45 +05:30

test_browser_get_images_ssrf.py

…

test_browser_hardening.py

fix(tools): route browser snapshot storage through the symlink-safe writer

2026-08-24 21:45:56 -07:00

test_browser_headed_mode.py

…

test_browser_homebrew_paths.py

…

test_browser_hybrid_routing.py

…

test_browser_lightpanda.py

…

test_browser_npx_warmup.py

refactor(deadline): consolidate site-local tree-kills onto agent.deadline.kill_process_tree (#85125 4d)

2026-08-25 01:34:56 +05:30

test_browser_open_timeout.py

fix(browser): reset sessions after command timeout

2026-08-27 16:11:16 +05:30

test_browser_orphan_reaper.py

…

test_browser_private_page_action_guard.py

…

test_browser_real_profile.py

feat(browser): close-with-approval flow for Windows real-profile (toggle arms, agent asks, blocked if still locked) [proof do-not-merge]

2026-08-26 19:25:33 -07:00

test_browser_secret_exfil.py

feat: browser snapshots drop LLM summarization — truncate-and-store like web_extract; auxiliary.web_extract slot removed

2026-08-24 20:11:18 -07:00

test_browser_snapshot_ssrf.py

…

test_browser_snapshot_threshold.py

feat(browser): make snapshot threshold configurable

2026-08-24 21:51:44 -07:00

test_browser_ssrf_local.py

…

test_browser_supervisor_healthcheck.py

…

test_browser_supervisor.py

…

test_browser_suspect_recycle.py

fix(browser): suspect-session recycle + wedged-daemon tree-kill on timeout (#85125 3b-browser/4c)

2026-08-27 16:11:16 +05:30

test_browser_type_redaction.py

…

test_browser_use_cli.py

fix(browser): floor browser-use CLI subprocess PATH with sane system dirs

2026-08-23 18:25:35 -07:00

test_browser_use_session_expiry.py

…

test_budget_config.py

feat: MCP tool results spill at 50K and carry upstream-elision warnings

2026-08-19 16:31:16 -07:00

test_build_subprocess_env.py

test(cron): e2e regression — scrubbed child env resolves bare hermes under minimal parent PATH

2026-08-23 18:27:15 -07:00

test_checkpoint_manager.py

fix(checkpoints): display failed deletes to users and stabilize result keys

2026-08-26 18:02:17 +05:30

test_clarify_gateway.py

…

test_clarify_tool.py

refactor(clarify): schema diet + single questions[] interface (880 → 335 tok/call, −62%) (#95907)

2026-08-26 16:42:44 -07:00

test_cli_approval_exec_ask_leak.py

fix(approval): align the execute_code CLI fall-through with its sibling guards

2026-08-20 01:16:25 +05:30

test_clipboard.py

…

test_close_preview_tool.py

feat(tools): close_preview so the agent can dismiss the pane it opened

2026-08-19 14:59:51 -05:00

test_code_execution_modes.py

refactor(code-execution): session kernels always on — kernel_mode knob retired (#96787)

2026-08-27 22:22:39 -07:00

test_code_execution_windows_env.py

…

test_code_execution.py

refactor(code-execution): session kernels always on — kernel_mode knob retired (#96787)

2026-08-27 22:22:39 -07:00

test_code_kernel.py

refactor(code-execution): session kernels always on — kernel_mode knob retired (#96787)

2026-08-27 22:22:39 -07:00

test_command_guards.py

…

test_computer_use_approval_isolation.py

…

test_computer_use_capture_routing.py

…

test_computer_use_cua_0_9.py

refactor(computer_use): drop the cua_browser_* route — browser work goes through browser_exec

2026-08-26 19:25:33 -07:00

test_computer_use_cua_0_10_permissions.py

refactor(computer_use): drop the cua_browser_* route — browser work goes through browser_exec

2026-08-26 19:25:33 -07:00

test_computer_use_cua_backend_linux.py

…

test_computer_use_cua_macos_identity.py

test(computer-use): cover CUA signature security paths

2026-08-27 23:26:40 +08:00

test_computer_use_delivery_ladder.py

refactor(computer_use): diet schema + delete prompt block (~1.4K tok/call); remove max_elements, ladder moves to response verdicts

2026-08-26 04:50:13 -07:00

test_computer_use_display_count_guard.py

…

test_computer_use_empty_discovery_diagnosis.py

…

test_computer_use_fullscreen_capture.py

feat(computer_use): guide models from full-screen grabs to interactive lanes

2026-08-25 02:31:34 -07:00

test_computer_use_input_target_guard.py

…

test_computer_use_null_pid_windows.py

…

test_computer_use_placeholder_ids.py

…

test_computer_use_vision_routing.py

…

test_computer_use_zero_bounds.py

…

test_computer_use.py

refactor(computer_use): drop the cua_browser_* route — browser work goes through browser_exec

2026-08-26 19:25:33 -07:00

test_config_null_guard.py

…

test_container_cwd_sanitize.py

…

test_credential_files.py

…

test_credential_pool_env_fallback.py

…

test_cron_approval_mode.py

…

test_cron_prompt_injection.py

…

test_cronjob_run_background.py

…

test_cronjob_run_immediate.py

…

test_cronjob_tools.py

test: assert omitted attach_to_session stays absent from formatted list output

2026-08-26 16:06:41 +05:30

test_cross_profile_guard.py

…

test_daemon_pool.py

…

test_daytona_environment.py

…

test_debug_helpers.py

…

test_deferral_fixes.py

test(tool-search): make salvage-seam tests order- and stem-robust

2026-08-25 16:39:12 -07:00

test_delegate_apiserver_background.py

…

test_delegate_batch_validation.py

refactor(delegate_task): tasks-only interface + depth-derived delegation (1,201 → 773 tok/call, −36%) (#96424)

2026-08-27 07:38:53 -07:00

test_delegate_composite_toolsets.py

…

test_delegate_control_actions.py

refactor(delegate_task): tasks-only interface + depth-derived delegation (1,201 → 773 tok/call, −36%) (#96424)

2026-08-27 07:38:53 -07:00

test_delegate_cost_footer.py

…

test_delegate_cron_sync_fallback.py

…

test_delegate_kanban_isolation.py

…

test_delegate_output_schema.py

refactor(delegate_task): tasks-only interface + depth-derived delegation (1,201 → 773 tok/call, −36%) (#96424)

2026-08-27 07:38:53 -07:00

test_delegate_subagent_timeout_diagnostic.py

…

test_delegate_summary_budget.py

…

test_delegate_toolset_scope.py

…

test_delegate.py

refactor(delegate_task): tasks-only interface + depth-derived delegation (1,201 → 773 tok/call, −36%) (#96424)

2026-08-27 07:38:53 -07:00

test_delegation_live_log.py

…

test_denial_circuit_breaker.py

…

test_desktop_ui.py

…

test_discord_send_message_caption.py

…

test_discord_tool.py

…

test_docker_cgroup_limits.py

…

test_docker_config_migrate.py

…

test_docker_daemon_redirect.py

…

test_docker_environment.py

fix(docker): digest-suffix shared-container identity labels so distinct keys never collide

2026-08-25 04:00:27 -07:00

test_docker_find.py

…

test_docker_network_config.py

…

test_docker_orphan_reaper_integration.py

…

test_docker_rebootstrap_nous_session.py

…

test_docker_session_isolation.py

…

test_dockerfile_immutable_install.py

…

test_dockerfile_node_modules_perms.py

…

test_dockerfile_pid1_reaping.py

…

test_drive_preview_tool.py

feat(desktop): durable element handles, and a delta instead of the whole page

2026-08-20 05:26:37 -05:00

test_ensure_task_env.py

…

test_env_passthrough.py

…

test_env_probe.py

…

test_execute_code_approval_cluster.py

…

test_execution_flag_detection.py

…

test_fal_common.py

…

test_feishu_tools.py

…

test_file_operations_edge_cases.py

…

test_file_operations.py

…

test_file_ops_cwd_tracking.py

…

test_file_read_guards.py

…

test_file_staleness.py

…

test_file_state_registry.py

…

test_file_sync_back.py

…

test_file_sync_perf.py

…

test_file_sync_sigint.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_tilde_profile.py

…

test_file_tools.py

fix(tools): pass single_query_deny_message to the ssh-config write approval gate

2026-08-23 17:54:20 -07:00

test_file_write_safety.py

fix(approval): stop the CLI and ACP offering a scope the protected gate discards

2026-08-23 17:45:47 -05:00

test_file_write_surrogate_roundtrip.py

…

test_find_shell.py

…

test_focus_pane_tool.py

…

test_force_dangerous_override.py

…

test_fuzzy_match.py

…

test_gateway_cwd_contract.py

…

test_generation_source_confinement.py

…

test_gnu_long_option_abbreviation_bypass.py

…

test_hardline_blocklist.py

fix(tools): widen the command-position anchor to the whole hardline class

2026-08-24 03:20:14 -07:00

test_heartbeat_stale_thresholds.py

…

test_hermes_subprocess_env.py

…

test_hidden_dir_filter.py

…

test_homeassistant_tool.py

…

test_hook_output_spill.py

…

test_hub_lock_non_utf8_68053.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_plugin_dispatch.py

…

test_image_generation.py

test: drop the upscale-defaults-off catalog invariant

2026-08-19 10:07:30 -07:00

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_redaction.py

…

test_kanban_tools.py

…

test_lazy_deps_durable_target.py

…

test_lazy_deps_managed.py

…

test_lazy_deps.py

…

test_line_ending_preservation.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(cron): keep hermes console script on child PATH

2026-08-23 18:27:15 -07:00

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

fix(terminal): sweep setsid descendants after local timeout group-kill (#85125 4b)

2026-08-25 01:34:56 +05:30

test_local_shell_init.py

…

test_local_tempdir.py

…

test_macos_protected_search.py

fix(search): path-scoped grep pruning + execution-backend gating for macOS TCC exclusions

2026-08-26 06:26:02 -07:00

test_managed_browserbase_and_modal.py

…

test_managed_media_gateways.py

test(tools): pin strict provider-string selection per category

2026-08-19 16:10:01 -07:00

test_managed_modal_environment.py

…

test_managed_tool_gateway.py

refactor(tools): remove expired BFL FLUX 3 promo core tools (migration v39); FLUX 3 stays via video_gen/FAL for subscribers (#94599)

2026-08-25 02:45:10 -07:00

test_mcp_bridge_single_failure.py

…

test_mcp_cancelled_error_propagation.py

…

test_mcp_capability_gating.py

…

test_mcp_cimd.py

fix: never evict pinned CIMD sockets from the callback reservation FIFO

2026-08-18 20:03:18 -07:00

test_mcp_circuit_breaker.py

…

test_mcp_client_cert.py

…

test_mcp_config_whitespace_warning.py

…

test_mcp_dashboard_oauth.py

…

test_mcp_discovery_cross_process.py

…

test_mcp_dynamic_discovery.py

…

test_mcp_elicitation.py

…

test_mcp_empty_error_message.py

…

test_mcp_failure_classification.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_loop_profile_override.py

…

test_mcp_oauth_bidirectional.py

…

test_mcp_oauth_cold_load_expiry.py

…

test_mcp_oauth_integration.py

…

test_mcp_oauth_manager.py

…

test_mcp_oauth_metadata.py

…

test_mcp_oauth_user_agent.py

feat(mcp): per-server oauth.user_agent for token-endpoint requests (#75576)

2026-08-18 21:57:53 -07:00

test_mcp_oauth.py

MCP CIMD auth

2026-08-18 20:03:18 -07:00

test_mcp_parked_self_probe.py

fix(tests): set _ever_connected in reconnect-scenario test mocks

2026-08-26 08:40:07 -07:00

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_reconnect_log_hygiene.py

fix(tests): set _ever_connected in reconnect-scenario test mocks

2026-08-26 08:40:07 -07:00

test_mcp_reconnect_retry_reset.py

fix(tests): set _ever_connected in reconnect-scenario test mocks

2026-08-26 08:40:07 -07:00

test_mcp_reconnect_signal.py

…

test_mcp_register_wakes_stale.py

…

test_mcp_resource_content.py

…

test_mcp_result_size_limit.py

feat: MCP tool results spill at 50K and carry upstream-elision warnings

2026-08-19 16:31:16 -07:00

test_mcp_schema_cache_ttl.py

…

test_mcp_schema_cache.py

…

test_mcp_server_log_notifications.py

…

test_mcp_sse_transport.py

…

test_mcp_stability.py

…

test_mcp_stdio_children_dead.py

test(mcp): absorb watcher-consumer and fail-open liveness cases from #94521/#94661

2026-08-27 14:08:20 +05:30

test_mcp_stdio_encoding_handler.py

…

test_mcp_stdio_fastfail_reconnect.py

review: tighten pre-call gate comment; drop redundant _ReadyAdapter test stub

2026-08-27 21:36:35 +05:30

test_mcp_stdio_init_timeout.py

…

test_mcp_stdio_watchdog.py

…

test_mcp_streamable_http_arity.py

…

test_mcp_structured_content.py

…

test_mcp_timeout_resolution.py

fix(mcp): resolve tool-call timeouts via the unified deadline layer (#85125 2g)

2026-08-24 17:12:15 +05:30

test_mcp_tool_401_handling.py

…

test_mcp_tool_issue_948.py

…

test_mcp_tool_session_expired.py

…

test_mcp_tool.py

test(tools): guard _ever_connected set in reconnect regression mock so it bites on pre-fix code (#94671 hardening)

2026-08-26 08:40:07 -07:00

test_mcp_transport_group_reconnect.py

…

test_mcp_trust_gating.py

…

test_mcp_utility_capability_gating.py

…

test_media_caption_split.py

…

test_memory_tool_import_fallback.py

…

test_memory_tool_schema.py

…

test_memory_tool.py

…

test_microsoft_graph_auth.py

…

test_microsoft_graph_client.py

fix(teams): request supported transcript content format

2026-08-26 02:54:35 +05:30

test_modal_bulk_upload.py

…

test_modal_sandbox_fixes.py

fix: 7 GitHub-adjacent tests no longer fail on developer machines

2026-08-19 01:19:28 -07:00

test_modal_snapshot_isolation.py

…

test_notify_on_complete.py

refactor(terminal): honest schema, pager defaults in the env, unified notify arg (837 → 670 tok/call, −20%) (#95937)

2026-08-26 19:23:39 -07:00

test_oneshot_completion_linger.py

fix(cli): one-shot runs linger for notify_on_complete background processes so Bot Mode replies survive parent exit

2026-08-23 03:56:37 -07:00

test_open_preview_tool.py

…

test_osv_check.py

…

test_parse_env_var.py

…

test_patch_already_applied.py

…

test_patch_failure_tracking.py

…

test_patch_multimatch_locations.py

…

test_patch_parser.py

…

test_patch_ws_diagnosis.py

…

test_plugin_guard.py

fix(skills_guard): --host flags no longer flagged as DNS exfiltration

2026-08-22 11:15:44 -07:00

test_pr_6656_regressions.py

…

test_pre_transcription_hook.py

…

test_process_registry_write_stdin_surrogates.py

fix(tests): remove four shared-state and lifetime faults at high concurrency

2026-08-22 02:25:12 -04:00

test_process_registry.py

…

test_process_wait_clarity.py

…

test_react_to_message_tool.py

…

test_read_binary_type_disclosure.py

…

test_read_extract.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

…

test_registry.py

…

test_request_tool_approval.py

…

test_resolve_path.py

…

test_restored_delegation_ownership.py

…

test_rollback_all_directories.py

fix(checkpoints): bare /rollback falls back to a labeled all-directories view (#10505, reapply #10633)

2026-08-19 22:41:13 -07:00

test_safe_getcwd_permission_error.py

fix(terminal): tolerate macOS TCC PermissionError in _safe_getcwd

2026-08-26 04:51:41 -07:00

test_sandbox_failure_hints.py

…

test_schema_sanitizer.py

…

test_search_auto_multiline.py

…

test_search_budget_truncation.py

…

test_search_error_guard.py

…

test_search_hidden_dirs.py

…

test_search_zero_match_and_multipath.py

…

test_self_repo_guard.py

…

test_send_message_cross_loop.py

fix(send_message): cross-loop dispatch to live WeCom adapter

2026-08-27 07:33:36 -07:00

test_send_message_missing_platforms.py

…

test_send_message_plugin_extensibility.py

fix(cron): mirror continuable-cron briefs for origin-fallback and opted-in explicit targets

2026-08-26 16:06:09 +05:30

test_send_message_react.py

…

test_send_message_slack.py

…

test_send_message_target_parse.py

…

test_send_message_telegram_proxy.py

…

test_send_message_tool.py

fix(signal): chunk long standalone sends and cover both delivery paths (salvage #57929 + #67279)

2026-08-24 20:03:24 -07:00

test_session_cwd_store.py

…

test_session_search.py

…

test_setup_mcp_tool.py

…

test_shared_container_task_id.py

feat(terminal): wire shared-container key into profile-scoped resolver and MEDIA delivery

2026-08-25 04:00:27 -07:00

test_shell_bypass_denylist.py

…

test_signal_media.py

…

test_single_query_approval_mode.py

…

test_singularity_persistent_overlay.py

test(tools): shared sanitizer contract + singularity overlay coverage

2026-08-23 21:12:32 -07:00

test_singularity_preflight.py

…

test_skill_bundle_provenance.py

…

test_skill_env_passthrough.py

feat(skills): rewrite AgentMail optional skill CLI-first

2026-08-27 07:09:26 -07:00

test_skill_improvements.py

test(skills): cover umask and explicit skill paths

2026-08-18 12:52:53 -07:00

test_skill_ledger.py

…

test_skill_linter.py

…

test_skill_manager_tool.py

fix(skills): preserve review marks across contexts

2026-08-24 23:55:39 -07:00

test_skill_provenance.py

…

test_skill_size_limits.py

…

test_skill_usage.py

…

test_skill_view_dedup.py

…

test_skill_view_path_check.py

…

test_skill_view_traversal.py

…

test_skillevaluator_scan.py

…

test_skills_ast_audit.py

…

test_skills_guard.py

…

test_skills_hub_browse_sh.py

…

test_skills_hub_clawhub.py

test(skills): cover same-name inspect/install provenance mixup

2026-08-19 01:23:17 +05:30

test_skills_hub.py

…

test_skills_list_modified_diff.py

…

test_skills_sync_client.py

…

test_skills_sync.py

fix: dashboard console skills commands no longer act on the wrong profile (#65828)

2026-08-18 14:14:42 -07:00

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

fix(approval): enforce explicit timeout on smart-approval guardian call and log its outcome

2026-08-27 14:28:22 +05:30

test_snapshot_multiline_session_env_injection.py

…

test_snapshot_session_id_leak.py

fix(browser): preserve controller work across reconnects

2026-08-21 22:33:45 +05:30

test_spill_safety.py

…

test_spotify_client.py

…

test_ssh_bulk_upload.py

…

test_ssh_environment.py

…

test_stage2_hook_api_server_keygen.py

fix(docker): stage2 API_SERVER_KEY bootstrap no longer depends on .env existing (OOF-285) (#88926)

2026-08-21 14:56:28 +10:00

test_stage2_hook_seed_one_symlinks.py

…

test_stage2_hook_symlink_chown.py

…

test_startup_latency_regressions.py

…

test_strict_provider_selection.py

fix(tools): honor raw stt.provider: local; finish _reconfigure_provider provider-string migration

2026-08-19 16:10:01 -07:00

test_stt_cloud_trim.py

…

test_stt_default_language.py

…

test_stt_idle_unload.py

…

test_stt_language_resolution.py

…

test_stt_silence_hallucinations.py

…

test_subagent_steer.py

…

test_subagent_sudo_prompt.py

fix(terminal): subagents no longer hijack the tty with an interactive sudo prompt

2026-08-23 19:00:47 -07:00

test_subagent_worktree.py

…

test_subprocess_stdin_guard.py

…

test_subprocess_utf8_encoding.py

…

test_symlink_prefix_confusion.py

…

test_sync_back_backends.py

…

test_telegram_send_message_caption.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_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_requirements.py

…

test_terminal_self_repo_guard.py

…

test_terminal_signal_exit.py

…

test_terminal_task_cwd.py

fix(bot-mode): keep delivery runner on host backend

2026-08-27 13:49:04 -07:00

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_termux_api_detection.py

…

test_threaded_process_handle.py

…

test_threat_patterns.py

…

test_tip_tool.py

feat(desktop): make the idle tip rotation opt-in, ungate the tool

2026-08-27 21:50:18 -05:00

test_tirith_security.py

…

test_todo_tool_type_coercion.py

…

test_todo_tool.py

…

test_tool_backend_helpers.py

…

test_tool_output_limits.py

…

test_tool_result_storage.py

feat: MCP tool results spill at 50K and carry upstream-elision warnings

2026-08-19 16:31:16 -07:00

test_tool_search_context_provider.py

…

test_tool_search_multiquery.py

test(tool-search): make salvage-seam tests order- and stem-robust

2026-08-25 16:39:12 -07:00

test_tool_search.py

refactor(tool-search): keep batch caps internal

2026-08-25 16:39:12 -07:00

test_tour_tool.py

fix(tour): an unanswered tour bridge no longer costs 45s per action

2026-08-19 11:20:28 -05:00

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): surface the selection-specific error for explicit openai STT

2026-08-23 18:25:35 -07:00

test_transcription.py

test(tools): repin selector/picker tests to the provider-string contract

2026-08-19 16:10:01 -07:00

test_tts_command_providers.py

…

test_tts_container_repair.py

…

test_tts_deepinfra.py

…

test_tts_dotenv_fallback.py

…

test_tts_gemini.py

…

test_tts_instructions.py

…

test_tts_kittentts.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(tools): pin strict provider-string selection per category

2026-08-19 16:10:01 -07:00

test_tts_opus_routing.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_provider_base_urls.py

…

test_tts_pythonpath_fallback.py

…

test_tts_response_body_cap.py

…

test_tts_speed.py

…

test_tts_streaming_e2e.py

…

test_tts_streaming.py

…

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_generation_dispatch.py

…

test_video_generation_dynamic_schema.py

…

test_video_generation_tool_surface_matrix.py

…

test_vision_native_fast_path.py

fix(vision): size native embeds for history reuse

2026-08-23 13:27:04 +05:30

test_vision_region.py

fix(vision): size native embeds for history reuse

2026-08-23 13:27:04 +05:30

test_vision_scale_disclosure.py

…

test_vision_tools.py

fix(vision): review follow-ups — LA/PA JPEG guard, third embed site

2026-08-23 15:06:03 +05:30

test_voice_cli_integration.py

…

test_voice_client_config.py

test: pin the relay verdict, not the host-dependent reason string

2026-08-23 03:54:52 -07:00

test_voice_credential_pool_resolution.py

…

test_voice_mode_playback_env_scrub.py

…

test_voice_mode.py

…

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

refactor(terminal): honest schema, pager defaults in the env, unified notify arg (837 → 670 tok/call, −20%) (#95937)

2026-08-26 19:23:39 -07:00

test_web_extract_robustness.py

…

test_web_keyless_fallback.py

test: pin ring entry vendor in provider-routing tests (ring rotation made direct-callable mocks stale)

2026-08-20 00:20:17 -07:00

test_web_keyless_rescue.py

feat: keyed web backends get a one-shot keyless rescue on failure — never sticky

2026-08-20 02:04:32 -07:00

test_web_providers_brave_free.py

…

test_web_providers_ddgs.py

…

test_web_providers_searxng.py

feat: web search/extract now work keyless on fresh installs via Parallel + Exa free tiers

2026-08-19 15:15:27 -07:00

test_web_providers_xai.py

…

test_web_providers.py

feat: keyless web tier becomes a 5-vendor round-robin ring (adds Tavily, Firecrawl, Keenable)

2026-08-20 00:17:25 -07:00

test_web_result_cache.py

feat(web): cache_exempt_hosts — always-live fetches for staging/tunnel sites

2026-08-25 04:21:45 -07:00

test_web_tools_config.py

fix(doctor): web readiness reflects the selected provider's real state (#78412)

2026-08-19 23:03:58 -07:00

test_web_tools_dict_urls.py

…

test_web_tools_tavily.py

feat: keyless web tier becomes a 5-vendor round-robin ring (adds Tavily, Firecrawl, Keenable)

2026-08-20 00:17:25 -07:00

test_web_tools_truncate.py

…

test_whatsapp_send_message_media.py

…

test_windows_agent_loop_papercuts.py

…

test_windows_compat.py

…

test_windows_native_support.py

…

test_working_diff.py

…

test_write_approval.py

fix(memory): enforce independent built-in store permissions

2026-08-20 20:20:23 -07:00

test_write_deny.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_yolo_mode.py

…

test_zombie_process_cleanup.py

…