hermes-agent

Files

T

Teknium 9d6d772837 feat(computer_use): follow cua-driver's verify → escalate ladder (#67123 )

Hermes' computer_use wrapper dropped cua-driver's structured action verdicts,
exposed no delivery_mode, and injected background-only guidance — so the agent
reported unverified no-ops as success and concluded cua-driver 'cannot drive'
Electron/Chromium surfaces (observed live on tldraw offline). Fixes #67052.

Phase A — preserve the result contract:
- ActionResult carries verified/effect/escalation/path/degraded/code/delivery_mode
- CuaDriverBackend._action() reads structuredContent (was data-only); a helper
  normalizes it, additive and None-safe on old drivers
- _text_response surfaces the fields additively (ok stays transport-only)

Phase B — bounded, model-reachable foreground:
- delivery_mode (background|foreground) + bring_to_front on the schema, dispatcher,
  ABC, and all input methods
- foreground is capability-gated (input.delivery_mode); old drivers get a
  structured foreground_unsupported refusal, never a silent background downgrade
- no automatic/hidden foreground retry — the model selects it from the signal

Phase C — guidance + isolation:
- system prompt (prompt_builder) and bundled skills/computer-use/SKILL.md go from
  background-ONLY to background-FIRST, teaching the AX→PX→foreground ladder driven
  by returned effect/escalation, not predicted from the app being Electron
- foreground approval scoped by (action, delivery_mode): a background approval
  never silently authorizes foreground
- approval state keyed per session_id so concurrent gateway runs don't leak unlocks

Tests: tests/tools/test_computer_use_delivery_ladder.py (15) cover confirmed/
unverifiable/suspected_noop/degraded/old-driver verdicts, delivery_mode gating +
foreground_unsupported, and session-scoped foreground approval. Existing 265
computer_use tests still green.

Live E2E (real cua-driver 0.8.3 + tldraw offline on Linux/X11): a background click
returned effect='unverifiable'/path='ax' (no fabricated success), and a foreground
request returned code='foreground_unsupported' — correct on a driver that predates
the input.delivery_mode capability.

2026-07-18 13:59:35 -07:00

__init__.py

…

conftest.py

test(tools): centralize disable_lazy_stt_install fixture in conftest

2026-05-22 03:33:01 -07:00

test_accretion_caps.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_ansi_strip.py

fix(cli): sanitize terminal escapes when replaying stored history (/resume recap, /status recap)

2026-07-17 04:53:38 -07:00

test_approval_deny_rules.py

feat(approvals): user-defined deny rules that block commands even under yolo (#59164 )

2026-07-05 14:48:40 -07:00

test_approval_heartbeat.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_approval_interrupt.py

fix(approval): honor canonical gateway timeout

2026-07-12 22:43:57 -07:00

test_approval_plugin_hooks.py

test(approval): isolate smart observer redaction failure

2026-07-13 04:31:55 -07:00

test_approval.py

fix(approval): unify execution-bearing option detection

2026-07-17 04:53:04 -07:00

test_approved_command_clean_slate.py

fix(interrupt): run user-approved commands from a clean interrupt slate

2026-07-06 04:58:42 -07:00

test_async_delegation.py

test: deflake async-delegation interrupt test under CI load (#64767 )

2026-07-14 23:36:37 -07:00

test_base_environment.py

fix(terminal): stop writing the cwd temp file entirely

2026-07-16 01:28:24 -07:00

test_blueprints.py

refactor(cron): rebrand Cron Recipes -> Automation Blueprints

2026-06-11 10:49:47 -07:00

test_browser_camofox_auth.py

fix(browser): send Authorization header in Camofox HTTP calls when CAMOFOX_API_KEY is set

2026-06-29 01:26:24 -07:00

test_browser_camofox_ensure_tab.py

fix(tools): send listItemId instead of sessionKey in Camofox tab creation

2026-06-29 01:26:24 -07:00

test_browser_camofox_persistence.py

test(camofox): accept headers= kwarg in persistence test mocks

2026-06-29 01:26:24 -07:00

test_browser_camofox_private_page_guard.py

fix(browser): block Camofox input on private pages

2026-07-03 03:27:47 -07:00

test_browser_camofox_state.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_browser_camofox_timeout.py

fix(tools): read browser.command_timeout in Camofox HTTP client

2026-06-29 01:26:24 -07:00

test_browser_camofox.py

fix(browser): force secret-pattern redaction on browser_type display

2026-06-25 22:02:22 -07:00

test_browser_cdp_override.py

security(browser): enforce cloud-metadata floor on all backends; CDP is non-local

2026-07-01 05:09:35 -07:00

test_browser_cdp_tool.py

fix(browser): apply private-page guard to browser_cdp frame_id routing

2026-07-03 03:27:47 -07:00

test_browser_chromium_autoinstall.py

feat(browser): auto-install Chromium binary on local cold-start failure

2026-06-28 12:25:15 -05:00

test_browser_chromium_check.py

fix(windows): cover remaining console-flash spawn legs (#54417 )

2026-06-28 13:49:08 -07:00

test_browser_cleanup.py

…

test_browser_cloud_fallback.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_browser_cloud_provider_cache.py

fix(browser_tool): fall through to autodetect on config read failure

2026-05-09 13:35:39 -07:00

test_browser_command_timeout_race.py

fix(browser_tool): resolve race in _get_command_timeout cache returning None (#14331 )

2026-06-29 02:24:57 -07:00

test_browser_console_ssrf.py

fix(browser): extend private-network guard to browser_console

2026-07-01 05:23:17 -07:00

test_browser_console.py

feat(browser): store full snapshots on truncation; make eval denylist opt-in (#65923 )

2026-07-16 23:41:26 -07:00

test_browser_content_none_guard.py

feat(browser): store full snapshots on truncation; make eval denylist opt-in (#65923 )

2026-07-16 23:41:26 -07:00

test_browser_eval_ssrf.py

fix(browser): guard Camofox eval private pages

2026-07-02 13:10:30 +05:30

test_browser_eval_supervisor_path.py

fix(browser): recover from CDP DOM-node serialization crash in browser_console (#35385 )

2026-05-30 07:31:25 -07:00

test_browser_get_images_ssrf.py

fix(browser): extend private-network guard to browser_get_images

2026-06-28 14:25:10 -07:00

test_browser_hardening.py

feat(browser): store full snapshots on truncation; make eval denylist opt-in (#65923 )

2026-07-16 23:41:26 -07:00

test_browser_headed_mode.py

fix: widen headed-mode gate to config, add browser.headed default, tests, docs

2026-07-18 10:07:46 -07:00

test_browser_homebrew_paths.py

fix(windows): cover remaining console-flash spawn legs (#54417 )

2026-06-28 13:49:08 -07:00

test_browser_hybrid_routing.py

fix(browser): harden browser tool safety boundaries

2026-07-01 05:04:41 -07:00

test_browser_lightpanda.py

…

test_browser_open_timeout.py

test(browser): cover open timeout diagnostics and failed navigate title

2026-06-28 12:14:21 -05:00

test_browser_orphan_reaper.py

fix(browser): verify daemon identity before orphan reaper kills a PID (#14073 )

2026-06-21 15:23:47 -07:00

test_browser_private_page_action_guard.py

security(browser): re-check private-network guard after browser_back navigation

2026-07-01 20:01:55 +03:00

test_browser_secret_exfil.py

fix(browser): narrow credential-query denylist to unambiguous names

2026-07-01 05:04:41 -07:00

test_browser_snapshot_ssrf.py

fix(browser): allow local sidecar sessions to bypass SSRF guard

2026-06-28 02:42:01 -07:00

test_browser_ssrf_local.py

fix(browser): enable SSRF guard when terminal runs in container

2026-06-21 07:26:18 -07:00

test_browser_supervisor_healthcheck.py

…

test_browser_supervisor.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_browser_type_redaction.py

fix(browser): force secret-pattern redaction on browser_type display

2026-06-25 22:02:22 -07:00

test_budget_config.py

fix(agent): scale tool-output budget to the model context window (#23767 )

2026-06-21 17:46:38 +05:30

test_checkpoint_manager.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_clarify_gateway.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_clarify_tool.py

fix(clarify): unwrap dict choices at the source so every surface gets clean text

2026-06-19 06:31:08 -07:00

test_clipboard.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_code_execution_modes.py

test(execute-code): cover session cwd record precedence in project mode

2026-07-16 04:24:07 -07:00

test_code_execution_windows_env.py

fix(code-exec): restore approval context in execute_code RPC threads + guard entry

2026-05-29 03:44:49 -07:00

test_code_execution.py

fix(code-exec): expose truncated stdout metadata

2026-07-16 04:25:19 -07:00

test_command_guards.py

fix(approval): honor glob command allowlist entries (#43051 )

2026-06-18 12:48:36 +10:00

test_computer_use_capture_routing.py

feat(computer_use): cross-platform cua-driver (macOS/Windows/Linux)

2026-06-22 06:42:30 -07:00

test_computer_use_delivery_ladder.py

feat(computer_use): follow cua-driver's verify → escalate ladder (#67123 )

2026-07-18 13:59:35 -07:00

test_computer_use_null_pid_windows.py

Fix computer-use crash on X11 windows with null PID

2026-07-04 02:37:33 -07:00

test_computer_use_vision_routing.py

fix(computer_use): honor custom vision routing

2026-06-07 02:09:20 -07:00

test_computer_use.py

fix(computer-use): target Linux app windows reliably (#63725 )

2026-07-16 00:34:20 +05:30

test_config_null_guard.py

fix(deepinfra): harden multimodal provider routing

2026-07-14 02:59:39 +05:30

test_container_cwd_sanitize.py

refactor(terminal,file-tools): delete legacy env-side cwd tracking (step 4)

2026-07-16 00:18:38 -07:00

test_credential_files.py

fix(hermes-home): only honour legacy dir layout when it has content

2026-06-27 04:57:15 +05:30

test_credential_pool_env_fallback.py

test(credential_pool): cover Anthropic env auth_type classification

2026-06-30 17:29:03 -07:00

test_cron_approval_mode.py

fix(approval): honour tirith_fail_open in cron-deny tirith path + tests

2026-07-01 00:13:36 -07:00

test_cron_prompt_injection.py

fix(security): align cron invisible-unicode set with install-time scanner

2026-06-26 01:11:11 -07:00

test_cronjob_run_immediate.py

fix(cron): execute job immediately on action='run'

2026-06-21 13:28:04 +05:30

test_cronjob_tools.py

security(cron): block base_url overrides that exfiltrate provider credentials

2026-07-01 14:23:01 +05:30

test_cross_profile_guard.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_daemon_pool.py

fix(cli): reliable interrupts, bounded exit, and exit feedback (#57000 )

2026-07-02 04:20:43 -07:00

test_daytona_environment.py

fix(daytona): quote single-upload mkdir parent path (#54440 )

2026-06-28 14:33:03 -07:00

test_debug_helpers.py

…

test_delegate_composite_toolsets.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_delegate_subagent_timeout_diagnostic.py

feat(desktop): stream subagent activity into watch windows (#47060 )

2026-06-16 14:30:11 -04:00

test_delegate_summary_budget.py

fix(delegation): budget subagent summaries against parent context headroom

2026-06-30 03:07:40 -07:00

test_delegate_toolset_scope.py

fix(delegate): route subagent progress lines through _safe_print for ACP stdio

2026-06-30 03:16:22 -07:00

test_delegate.py

fix(delegation): stop mixed platform bundles from re-exposing blocked tools to leaf children

2026-07-18 01:30:17 -07:00

test_discord_send_message_caption.py

feat(gateway): attach MEDIA: caption to the media bubble on standalone sends

2026-07-09 15:38:32 +05:30

test_discord_tool.py

fix(discord): bound REST response reads

2026-07-07 02:40:04 -07:00

test_docker_cgroup_limits.py

fix(docker): gate resource limit flags on cgroup controller availability (#54516 )

2026-06-29 11:01:08 +10:00

test_docker_config_migrate.py

test(docker): assert boot migration keeps .env byte-identical across reboots

2026-06-24 15:23:23 +10:00

test_docker_environment.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_docker_find.py

…

test_docker_network_config.py

fix(docker): widen docker_network to file/code-exec paths + guard container reuse

2026-07-05 14:41:51 -07:00

test_docker_orphan_reaper_integration.py

fix(docker): startup orphan reaper for crashed-process containers

2026-05-29 11:49:54 +10:00

test_docker_rebootstrap_nous_session.py

fix(auth): apply newer hosted bootstrap session (#64612 )

2026-07-16 08:52:47 +10:00

test_dockerfile_immutable_install.py

refactor(ci): faster docker builds via --link and chmod removal

2026-06-26 19:15:18 -07:00

test_dockerfile_node_modules_perms.py

Harden hosted Docker install tree against self-modification (#47490 )

2026-06-18 09:09:21 +10:00

test_dockerfile_pid1_reaping.py

fix(docker): pre-install matrix deps in Docker image (#30399 ) (#42413 )

2026-06-10 19:23:06 +10:00

test_env_passthrough.py

fix(security): strip dynamic Hermes secrets from all subprocess spawn env

2026-07-01 14:37:22 +05:30

test_env_probe.py

feat(prompt): universal task-completion guidance + local Python toolchain probe (#34340 )

2026-05-28 22:26:09 -07:00

test_execute_code_approval_cluster.py

fix(approval): scope smart deny owner overrides to one operation

2026-07-13 04:31:55 -07:00

test_execution_flag_detection.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_feishu_tools.py

…

test_file_operations_edge_cases.py

perf(read_file): compact line-number gutter — ~14% fewer tokens per read (#35368 )

2026-05-30 07:01:22 -07:00

test_file_operations.py

fix(windows): bash-safe snapshot paths after #63113

2026-07-13 01:59:58 -04:00

test_file_ops_cwd_tracking.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_file_read_guards.py

fix: disclose mid-line clamp in truncation hint

2026-07-05 14:42:05 -07:00

test_file_staleness.py

refactor(terminal,file-tools): delete legacy env-side cwd tracking (step 4)

2026-07-16 00:18:38 -07:00

test_file_state_registry.py

…

test_file_sync_back.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_file_sync_perf.py

…

test_file_sync_sigint.py

fix(file-sync): re-deliver deferred Ctrl+C via raise_signal, not os.kill (Windows hard-kill)

2026-07-06 01:55:58 -07:00

test_file_sync.py

fix remote sync-back credential overwrite

2026-07-01 01:00:31 -07:00

test_file_tools_container_config.py

fix(tools): respect session cwd in file tools

2026-06-15 14:00:42 +05:30

test_file_tools_cwd_resolution.py

refactor(terminal,file-tools): delete legacy env-side cwd tracking (step 4)

2026-07-16 00:18:38 -07:00

test_file_tools_live.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_file_tools_tilde_profile.py

refactor(terminal,file-tools): delete legacy env-side cwd tracking (step 4)

2026-07-16 00:18:38 -07:00

test_file_tools.py

refactor(terminal,file-tools): delete legacy env-side cwd tracking (step 4)

2026-07-16 00:18:38 -07:00

test_file_write_safety.py

test(file-safety): add integration tests for safe-root denial messages

2026-07-14 17:09:40 +05:30

test_find_shell.py

fix(install): detect Git Bash Mandatory ASLR failures (#64651 )

2026-07-16 22:46:46 -04:00

test_force_dangerous_override.py

…

test_fuzzy_match.py

fix(patch): preserve file Unicode when unicode_normalized strategy matches

2026-07-01 17:48:32 +05:30

test_gateway_cwd_contract.py

test(tools): characterize tool-surface TERMINAL_CWD contract (#29265 )

2026-06-01 16:55:04 -07:00

test_gnu_long_option_abbreviation_bypass.py

fix(approval): catch GNU long-flag abbreviations for chown --recursive and git push --force

2026-06-30 17:32:28 -07:00

test_hardline_blocklist.py

fix(approval): require exact ./.. segments in the root-collapse hardline token (#56179 )

2026-07-05 02:24:00 -07:00

test_heartbeat_stale_thresholds.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_hermes_subprocess_env.py

fix(security): strip dynamic Hermes secrets from all subprocess spawn env

2026-07-01 14:37:22 +05:30

test_hidden_dir_filter.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_homeassistant_tool.py

test: use subprocesses for each test file (#29016 )

2026-05-21 16:40:04 +05:30

test_hook_output_spill.py

feat(hooks): spill oversized hook-injected context to disk (#20468 )

2026-07-05 13:51:26 -07:00

test_image_generation_artifacts.py

feat(image-gen): add image-to-image / editing to image_generate (#48705 )

2026-06-18 22:13:07 -07:00

test_image_generation_env.py

feat(image-gen): actionable setup message when no FAL backend is reachable (#26222 )

2026-05-15 01:33:13 -07:00

test_image_generation_image_to_image.py

fix(tools): never let a model whitelist strip the prompt / source images

2026-06-19 16:59:54 -07:00

test_image_generation_plugin_dispatch.py

fix(deepinfra): harden multimodal provider routing

2026-07-14 02:59:39 +05:30

test_image_generation.py

krea

2026-06-25 12:38:33 -07:00

test_image_source.py

fix(vision): bound the sandbox exec-read at the ingest cap

2026-07-04 15:30:50 -07:00

test_init_session_cwd_respect.py

…

test_interrupt.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_kanban_redaction.py

fix(security): redact secrets in kanban tool payloads before persistence

2026-06-21 12:02:30 -07:00

test_kanban_tools.py

fix(tools/kanban): sync kanban_unblock response status with DB state

2026-07-17 15:47:39 -07:00

test_lazy_deps_durable_target.py

test(lazy-deps): make durable-target tests network-free

2026-06-25 09:20:13 +10:00

test_lazy_deps.py

fix(honcho): update SDK and restore CI coverage

2026-07-16 12:48:48 -07:00

test_line_ending_preservation.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_llm_content_none_guard.py

feat(moa): expose MoA presets as selectable virtual models (#46081 )

2026-06-25 13:52:06 -07:00

test_local_background_child_hang.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_local_cwd_permission_fallback.py

fix(terminal): fall back when the configured cwd is unenterable, not just missing (#66306 )

2026-07-17 06:54:51 -07:00

test_local_env_blocklist.py

fix(terminal): stop stripping CLAUDE_CODE_OAUTH_TOKEN from spawned subprocesses (#56935 )

2026-07-02 02:13:30 -07:00

test_local_env_cwd_recovery.py

fix(local): stop re-reading cwd marker file

2026-07-16 01:28:24 -07:00

test_local_env_relative_cwd.py

fix: normalize local terminal relative cwd

2026-07-16 01:28:13 -07:00

test_local_env_session_leak.py

fix(tools): close the same session leak on the hermes_subprocess_env spawn surface (review)

2026-07-01 15:42:19 +05:30

test_local_env_windows_msys.py

fix(local): stop re-reading cwd marker file

2026-07-16 01:28:24 -07:00

test_local_interrupt_cleanup.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_local_shell_init.py

fix(coding): teach agents terminal env state persists

2026-06-11 19:50:08 -05:00

test_local_tempdir.py

…

test_managed_browserbase_and_modal.py

test(approval): regression for shell-escape denylist bypass (#36846 , #36847 )

2026-06-07 03:57:21 -07:00

test_managed_media_gateways.py

fix(tts): coerce direct-only OpenAI model on the managed audio gateway

2026-07-03 05:30:16 -05:00

test_managed_modal_environment.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_managed_tool_gateway.py

fix(managed-gateway): keep tool availability scans off the Nous token-refresh path

2026-05-30 07:58:08 -07:00

test_mcp_cancelled_error_propagation.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_mcp_capability_gating.py

test(mcp): cover 'unknown method' ping keepalive fallback (#50028 )

2026-06-21 16:02:56 +05:30

test_mcp_circuit_breaker.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_mcp_client_cert.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_mcp_dashboard_oauth.py

fix(mcp): preserve live OAuth state during reauth

2026-07-17 04:50:47 -07:00

test_mcp_dynamic_discovery.py

feat(mcp): adopt mcp__server__tool naming convention

2026-07-05 13:40:21 -07:00

test_mcp_elicitation.py

feat(tools): MCP elicitation handler with gateway-aware approval routing

2026-06-19 11:46:25 -07:00

test_mcp_empty_error_message.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_mcp_image_content.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_mcp_invalid_url.py

fix(mcp): validate remote URLs up-front with a clear error (#27105 )

2026-05-16 13:06:56 -07:00

test_mcp_list_pagination.py

fix(mcp): follow nextCursor pagination in tools/resources/prompts discovery

2026-07-17 04:57:12 -07:00

test_mcp_loop_profile_override.py

fix(mcp): propagate HERMES_HOME override onto the MCP event loop (#44220 )

2026-06-11 04:37:01 -07:00

test_mcp_oauth_bidirectional.py

…

test_mcp_oauth_cold_load_expiry.py

…

test_mcp_oauth_integration.py

fix(mcp): fail fast for noninteractive oauth without tokens

2026-06-15 04:22:07 -07:00

test_mcp_oauth_manager.py

fix(mcp): preserve concurrent OAuth manager refresh

2026-07-17 04:50:47 -07:00

test_mcp_oauth_metadata.py

…

test_mcp_oauth.py

fix(mcp): close hosted OAuth lifecycle gaps

2026-07-17 04:50:47 -07:00

test_mcp_parked_self_probe.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_mcp_preflight_content_type.py

docs+test(mcp): document skip_preflight and cover the bypass with a test

2026-07-05 21:36:19 -07:00

test_mcp_probe.py

fix(mcp): preserve loop during probes

2026-06-14 02:09:45 -07:00

test_mcp_reconnect_retry_reset.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_mcp_reconnect_signal.py

…

test_mcp_register_wakes_stale.py

fix(mcp): wake stale cached servers on session startup + AUTHOR_MAP

2026-07-05 21:48:36 -07:00

test_mcp_resource_content.py

fix(mcp): use real wire name in ResourceLink marker + surface resource text in isError path

2026-07-14 13:59:38 -07:00

test_mcp_server_log_notifications.py

feat(mcp): surface MCP server log notifications in agent.log (#57416 )

2026-07-05 02:06:39 -07:00

test_mcp_sse_transport.py

fix(mcp): forward OAuth auth and bump sse_read_timeout on SSE transport (#21323 )

2026-05-07 07:08:04 -07:00

test_mcp_stability.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_mcp_stdio_init_timeout.py

fix(mcp): bound stdio initialize handshake to stop subprocess/FD leak

2026-07-07 15:16:00 -07:00

test_mcp_stdio_watchdog.py

fix(mcp): use direct parent identity in stdio watchdog

2026-07-18 04:15:13 -07:00

test_mcp_structured_content.py

fix(async): close unscheduled coroutines in all threadsafe bridges (#26584 )

2026-05-15 14:00:01 -07:00

test_mcp_tool_401_handling.py

…

test_mcp_tool_issue_948.py

fix(mcp): reap orphaned stdio MCP children on ungraceful parent death

2026-07-07 15:16:00 -07:00

test_mcp_tool_session_expired.py

fix: reconnect stale MCP sessions before retry

2026-07-05 21:48:36 -07:00

test_mcp_tool.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_mcp_utility_capability_gating.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_media_caption_split.py

feat(gateway): attach MEDIA: caption to the media bubble on standalone sends

2026-07-09 15:38:32 +05:30

test_memory_tool_import_fallback.py

…

test_memory_tool_schema.py

feat(memory): batch operations for single-turn memory updates (#48507 )

2026-06-18 10:19:33 -07:00

test_memory_tool.py

fix: default memory null target to memory store (#46356 )

2026-07-07 02:10:43 -07:00

test_microsoft_graph_auth.py

test(msgraph): cover concurrent token cache reuse

2026-05-08 09:27:26 -07:00

test_microsoft_graph_client.py

fix(msgraph): stream download_to_file body instead of buffering

2026-05-08 09:27:26 -07:00

test_modal_bulk_upload.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_modal_sandbox_fixes.py

test: deflake CI and dev-machine flaky tests in bulk (11 tests, 10 files) (#61816 )

2026-07-09 20:03:11 -07:00

test_modal_snapshot_isolation.py

…

test_notify_on_complete.py

fix(process): keep CLI drain dedup after poll goes read-only (#10156 )

2026-06-21 11:11:23 -07:00

test_osv_check.py

fix(osv_check): honor npx --package/-p install target when parsing package arg (#40567 )

2026-06-06 18:30:39 -07:00

test_parse_env_var.py

…

test_patch_failure_tracking.py

feat(patch): indentation preservation, CRLF preservation, per-file failure escalation (#507 ) (#32273 )

2026-05-25 15:18:45 -07:00

test_patch_parser.py

fix(patch): ignore inert context-only hunks (#63678 )

2026-07-13 02:42:18 -07:00

test_pr_6656_regressions.py

test(skills): widen assertion in PR#6656 regression to accept new validator msg

2026-05-25 06:13:36 -07:00

test_process_registry.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_read_extract.py

feat(read): extract notebook and office documents (#37082 )

2026-06-13 14:42:51 -07:00

test_read_loop_detection.py

feat(search_files): headroom compression evaluation report + lossless densification (#47866 )

2026-06-17 13:45:25 -07:00

test_refresh_agent_mcp_tools.py

fix(mcp): address adversarial review round 2 (stale-publish race, parity holes)

2026-06-19 11:57:43 -07:00

test_registry.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_request_tool_approval.py

feat(plugins): pass approve rule keys to approval gate

2026-07-07 15:14:30 -07:00

test_resolve_path.py

refactor(terminal,file-tools): delete legacy env-side cwd tracking (step 4)

2026-07-16 00:18:38 -07:00

test_restored_delegation_ownership.py

fix(delegation): fail closed on restored completions + stamp CLI dispatch identity

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

test_schema_sanitizer.py

fix(schema): preserve multi-type arrays as anyOf instead of dropping branches

2026-07-07 02:52:17 -07:00

test_search_budget_truncation.py

fix(search): keep partial results on search timeout (#36142 )

2026-06-13 14:35:21 -07:00

test_search_error_guard.py

fix: warn on line-oriented newline search patterns

2026-06-20 23:23:47 -07:00

test_search_hidden_dirs.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_send_message_missing_platforms.py

refactor(gateway): migrate slack/dingtalk/whatsapp/matrix/feishu/telegram/wecom/email/sms adapters to bundled plugins

2026-06-20 10:26:45 -07:00

test_send_message_react.py

feat(messaging): expose action='unreact' in send_message + react dispatch tests

2026-06-12 01:07:38 -07:00

test_send_message_target_parse.py

fix: harden WhatsApp target alias salvage

2026-06-15 05:51:47 -07:00

test_send_message_telegram_proxy.py

test+release: align send_message mocks for MessageEntity import; map @fonhal

2026-05-18 22:19:50 -07:00

test_send_message_tool.py

feat(gateway): attach MEDIA: caption to the media bubble on standalone sends

2026-07-09 15:38:32 +05:30

test_session_cwd_store.py

refactor(terminal,file-tools): delete legacy env-side cwd tracking (step 4)

2026-07-16 00:18:38 -07:00

test_session_search.py

fix(session_search): demote cron below interactive sessions in discover ranking (#53597 )

2026-06-27 04:41:22 -07:00

test_shared_container_task_id.py

fix(terminal): collapse CWD-only overrides to shared container

2026-06-07 23:04:54 -07:00

test_shell_bypass_denylist.py

fix(approval): detect shell-expanded command names (#36846 )

2026-07-01 01:39:10 -07:00

test_signal_media.py

refactor(gateway): migrate slack/dingtalk/whatsapp/matrix/feishu/telegram/wecom/email/sms adapters to bundled plugins

2026-06-20 10:26:45 -07:00

test_singularity_preflight.py

chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355 )

2026-05-17 02:29:41 -07:00

test_skill_bundle_provenance.py

fix(skills): bind bundles to exact files and origins

2026-07-12 02:59:27 -07:00

test_skill_env_passthrough.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_skill_improvements.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_skill_manager_tool.py

test: add coverage for manual-skill curator guard

2026-07-18 20:17:22 +05:30

test_skill_provenance.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_skill_size_limits.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_skill_usage.py

fix(curator): protect external skills from background curation

2026-06-25 22:03:02 -07:00

test_skill_view_path_check.py

…

test_skill_view_traversal.py

fix(skills): block path traversal via skill_view name argument (#40566 )

2026-06-06 18:29:52 -07:00

test_skills_ast_audit.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_skills_guard.py

fix: remove dead f-string prefixes via ruff F541 (216 sites) (#52336 )

2026-07-05 13:42:46 -07:00

test_skills_hub_browse_sh.py

fix(browse-sh): fetch SKILL.md via /api/skills/{slug}+skillMdUrl

2026-05-19 14:17:38 -07:00

test_skills_hub_clawhub.py

fix(skills): let ClawHub index build walk past the 12s browse budget (#44500 )

2026-06-11 18:03:11 -04:00

test_skills_hub.py

fix(skills): don't request Brotli for the centralized skills index

2026-07-05 22:21:05 -07:00

test_skills_list_modified_diff.py

test(skills): cover list-modified + diff for bundled skills

2026-06-18 12:26:20 +05:30

test_skills_sync.py

fix(skills): skip shadowing when external_dirs provides the skill

2026-06-27 21:07:53 -07:00

test_skills_tool_discovery_cache.py

fix: return per-call copies from the skill-discovery cache

2026-07-09 15:38:14 +05:30

test_skills_tool_profile_scope.py

fix(skills): resolve skills dir from active profile

2026-07-07 05:14:00 -07:00

test_skills_tool.py

fix(skills): strip UTF-8 BOM before parsing SKILL.md frontmatter

2026-07-17 04:52:02 -07:00

test_slash_confirm.py

…

test_smart_approval_injection.py

fix(security): harden smart approval guard against prompt injection

2026-06-21 16:39:48 -07:00

test_spotify_client.py

docs(spotify): document 6-month re-auth cycle and add client-level invalid_grant test

2026-06-20 23:23:47 -07:00

test_ssh_bulk_upload.py

fix(ssh): handle WinError 1314 symlink failure with shutil.copy2 fallback

2026-06-04 18:06:21 -07:00

test_ssh_environment.py

…

test_stage2_hook_seed_one_symlinks.py

fix(docker): skip symlinked stage2 chown targets (#52789 )

2026-06-26 12:09:52 +10:00

test_stage2_hook_symlink_chown.py

fix(docker): skip symlinked stage2 chown targets (#52789 )

2026-06-26 12:09:52 +10:00

test_subprocess_stdin_guard.py

test: guard OAuth setup-token stays interactive + marker exemption

2026-06-08 22:46:57 -07:00

test_symlink_prefix_confusion.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_sync_back_backends.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_telegram_send_message_caption.py

feat(gateway): attach MEDIA: caption to the media bubble on standalone sends

2026-07-09 15:38:32 +05:30

test_terminal_compound_background.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_terminal_config_env_sync.py

fix(terminal): bridge docker_extra_args to TERMINAL_DOCKER_EXTRA_ARGS in CLI + gateway (#50631 )

2026-06-22 15:41:23 +10:00

test_terminal_env_bridge.py

fix(terminal): bridge terminal.backend config in serve/desktop processes lacking a launcher env bridge

2026-07-16 08:55:10 -07:00

test_terminal_exit_semantics.py

…

test_terminal_foreground_timeout_cap.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_terminal_none_command_guard.py

…

test_terminal_output_transform_hook.py

fix(terminal): bound foreground output capture

2026-07-14 22:00:28 -07:00

test_terminal_requirements.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_terminal_task_cwd.py

refactor(terminal,file-tools): delete legacy env-side cwd tracking (step 4)

2026-07-16 00:18:38 -07:00

test_terminal_timeout_output.py

…

test_terminal_tool_pty_fallback.py

…

test_terminal_tool_requirements.py

fix(tools): suppress transient check_fn flakes so subagents keep file/terminal tools

2026-06-27 19:29:00 -07:00

test_terminal_tool.py

fix(ssh): preserve remote tilde cwd

2026-07-04 14:17:11 +05:30

test_threaded_process_handle.py

…

test_threat_patterns.py

fix: bound threat-pattern/FTS5 regex input and cover V4A Move-File edits

2026-07-01 01:05:28 -07:00

test_tirith_security.py

fix(security): add circuit breaker for tirith crashes to prevent agent hangs (#41400 )

2026-06-26 15:26:08 +05:30

test_todo_tool_type_coercion.py

fix(tools): defensive type coercion in todo_tool for malformed LLM input (#14185 )

2026-06-25 23:42:42 +05:30

test_todo_tool.py

hardening(todo): bound TodoStore item content length and count

2026-06-07 18:06:27 -07:00

test_tool_backend_helpers.py

fix(tools): guard Path.home() against PermissionError in has_direct_modal_credentials (#33528 )

2026-05-29 13:35:39 +10:00

test_tool_output_limits.py

fix(gateway): detach pending_watchers batch + normalize LRU caches + align test fixtures + AUTHOR_MAP

2026-05-31 00:50:19 -07:00

test_tool_result_storage.py

fix: keep persisted tool results inside their storage directory

2026-06-30 16:39:41 -07:00

test_tool_search.py

test: restore unrelated trailing newlines in cwd/tool-search tests

2026-06-03 06:36:46 -07:00

test_transcription_command_providers.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_transcription_deepinfra.py

feat(providers): Support DeepInfra as an LLM provider

2026-07-14 02:59:39 +05:30

test_transcription_dotenv_fallback.py

Add Hermes desktop app (#20059 )

2026-05-31 17:46:56 -05:00

test_transcription_plugin_dispatch.py

feat(stt): add register_transcription_provider() plugin hook

2026-05-25 01:41:19 -07:00

test_transcription_tools.py

Add Hermes desktop app (#20059 )

2026-05-31 17:46:56 -05:00

test_transcription.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_tts_command_providers.py

fix(deepinfra): align refresh and TTS availability

2026-07-14 02:59:39 +05:30

test_tts_deepinfra.py

fix(deepinfra): align refresh and TTS availability

2026-07-14 02:59:39 +05:30

test_tts_dotenv_fallback.py

fix(deepinfra): align refresh and TTS availability

2026-07-14 02:59:39 +05:30

test_tts_gemini.py

fix(gemini): restrict TTS client context to official host

2026-07-13 22:26:19 -07:00

test_tts_kittentts.py

test(ci): stabilize shared optional dependency baselines

2026-05-13 17:32:22 -07:00

test_tts_max_text_length.py

test: port voice-reply suffix assertions, fix change-detector cap test, add AUTHOR_MAP entry

2026-06-10 02:57:39 -07:00

test_tts_mistral.py

fix(deepinfra): align refresh and TTS availability

2026-07-14 02:59:39 +05:30

test_tts_opus_routing.py

fix(tts): keep native audio outside Telegram voice delivery

2026-05-18 22:29:45 -07:00

test_tts_path_traversal.py

fix(tts): reject '..' traversal in output_path

2026-05-25 05:15:55 -07:00

test_tts_piper.py

fix(deepinfra): align refresh and TTS availability

2026-07-14 02:59:39 +05:30

test_tts_plugin_dispatch.py

feat(tts): add register_tts_provider() plugin hook (closes #30398 )

2026-05-24 18:04:54 -07:00

test_tts_speed.py

fix(tts): coerce direct-only OpenAI model on the managed audio gateway

2026-07-03 05:30:16 -05:00

test_tts_xai_speech_tags.py

feat(tts): add xAI TTS speed and optimize_streaming_latency config knobs

2026-06-19 07:26:56 -07:00

test_url_safety.py

fix: repair URL authority whitespace before web fetches (#46363 )

2026-07-07 02:39:36 -07:00

test_video_analyze.py

security(vision): route local-file inputs through the shared credential-read guard

2026-07-05 00:47:54 -07:00

test_video_generation_dispatch.py

feat(xai): Imagine public-URL storage, chaining & video edit/extend

2026-06-29 21:11:58 -07:00

test_video_generation_dynamic_schema.py

feat(providers): Support DeepInfra as an LLM provider

2026-07-14 02:59:39 +05:30

test_video_generation_tool_surface_matrix.py

feat(xai): Imagine public-URL storage, chaining & video edit/extend

2026-06-29 21:11:58 -07:00

test_vision_native_fast_path.py

fix(vision): address review — restore bare relative paths, remove dead code, async I/O

2026-07-04 15:30:50 -07:00

test_vision_tools.py

security(vision): route local-file inputs through the shared credential-read guard

2026-07-05 00:47:54 -07:00

test_voice_cli_integration.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_voice_mode.py

fix(ci): make tests, workflows, and attribution reliable under load (#66373 )

2026-07-17 20:55:24 +00:00

test_watch_patterns.py

chore: prune unused imports and duplicate import redefinitions

2026-05-28 22:26:25 -07:00

test_web_extract_robustness.py

fix(web_extract): bound stored full-text size + give concrete read_file offset

2026-06-30 00:19:49 -07:00

test_web_providers_brave_free.py

fix(test): patch async_is_safe_url in web-provider SSRF mocks

2026-06-04 18:04:47 -07:00

test_web_providers_ddgs.py

fix(ddgs): bound DuckDuckGo search with a wall-clock timeout (#36776 )

2026-06-25 01:45:06 +05:30

test_web_providers_searxng.py

revert(web): remove keyless Parallel search fallback (#46350 )

2026-06-14 16:47:57 -07:00

test_web_providers_xai.py

fix(auth): make xAI OAuth pools multi-account resilient

2026-07-17 11:37:25 +05:30

test_web_providers.py

fix(web): correct 'disabled plugin' diagnosis for web backends (#59573 )

2026-07-06 04:38:17 -07:00

test_web_tools_config.py

fix(web): don't crash on a null web/backend config value

2026-07-09 20:28:44 -07:00

test_web_tools_dict_urls.py

fix(web): preserve extract result input order

2026-07-10 19:14:06 +05:30

test_web_tools_tavily.py

feat(web_extract): truncate-and-store instead of LLM summarization (#54843 )

2026-06-29 10:00:49 -07:00

test_web_tools_truncate.py

feat(web_extract): truncate-and-store instead of LLM summarization (#54843 )

2026-06-29 10:00:49 -07:00

test_website_policy.py

test: adapt salvaged SSRF test to current web_extract_tool signature

2026-07-01 00:49:38 -07:00

test_whatsapp_send_message_media.py

feat(gateway): attach MEDIA: caption to the media bubble on standalone sends

2026-07-09 15:38:32 +05:30

test_windows_compat.py

fix(tools): use start_new_session instead of preexec_fn to prevent SIGSEGV in multi-threaded processes

2026-06-27 03:08:41 +05:30

test_windows_native_support.py

revert(windows): roll back terminal-popup PRs #53791 #53810 #53829 (#53853 )

2026-06-27 15:59:00 -07:00

test_write_approval.py

test(tools): add unit tests for skill_gist

2026-07-08 06:17:56 -07:00

test_write_deny.py

fix(file-safety): relax user-write deny policy (#45947 )

2026-06-14 02:07:32 -07:00

test_write_file_syntax_gate.py

fix(tools): make the YAML write gate syntax-only so multi-doc/tagged YAML isn't refused

2026-07-07 22:14:33 -07:00

test_x_search_tool.py

fix(x_search): surface degraded results + validate dates

2026-05-21 02:38:45 +05:30

test_xai_http_storage.py

feat(xai): Imagine public-URL storage, chaining & video edit/extend

2026-06-29 21:11:58 -07:00

test_yolo_mode.py

fix(approval): harden YOLO bypass, LLM parsing, auto-approve audit, pipe pattern (#23835 )

2026-05-25 03:35:33 -07:00

test_zombie_process_cleanup.py

fix(session): finalize owned SQLite session rows on AIAgent.close()

2026-06-21 11:35:09 -07:00