Evan b4410f64d4

fix(agents): keep the delegation ledger exact across HITL approval and reused call ids (#8128) ...

* fix(agents): count each delegation once when a provider reuses its call id

Tool-call ids are unique per response, not per conversation. Some providers
number every response's calls from call_0, so two task calls in one run can
share an id.

The delegation ledger used (run_id, tool_call_id) as a delegation's identity:

- extract_delegations built one id -> entry map over the whole run, so a
  later call_0 replaced the earlier delegation's description and took its
  result while it was still running.
- merge_delegations replaced the same (run_id, id), keeping one entry.
- SubagentLimitMiddleware counted distinct ids, so the per-run cap
  (subagents.max_total_per_run) never advanced past the first call_0 and a
  run could launch any number of subagents one response at a time.

Each entry now also records dispatch_message_id, the AIMessage that issued the
call, and results pair through pair_tool_call_results, which answers a call
only from its own response. The reducer, DurableContext's change filter and
the cap use the extended identity. An entry without a dispatch id still
updates its run's entry for that call id, and a dispatch-scoped entry adopts a
ledger entry written before the field existed, so runs in flight across the
upgrade are not counted twice. The steer path names the dispatching AIMessage
from the tool request's state, so its delegation update and the graph's own
capture stay one entry.

* fix(agents): close an earlier run's dangling dispatch by its own response

_close_delegations_left_by_earlier_runs decided "answered" by
(run_id, tool_call_id). When a stopped run had dispatched call_0 twice,
the first reply kept the second, dangling entry in_progress, so the
lead kept hearing "already delegated" for work nothing would finish.

Entries that carry dispatch_message_id are now decided by pairing that
response's calls through pair_tool_call_results. Legacy entries and
dispatches no longer in history keep the id-based inference.

Also pin that two runs reusing call_0 stay two ledger entries, and
cross-reference the three delegation identity helpers.

* fix(agents): settle an approval-gated task delegation in the ledger

With `task` in `hitl_approval.tools`, the paused run records the dispatch
as in_progress and the resume run executes it. The resume run opens with
no HumanMessage, so its capture window starts after the pre-existing
messages and never contains the dispatching AIMessage: the result was
dropped and the entry stayed in_progress with no result_brief, forever.

DurableContext now pairs results the resumed window receives with the
last pre-existing dispatch and settles the issuing run's entry, keeping
its run_id instead of re-tagging it. HITL denials of `task` carry
`cancelled` subagent status, so a rejected or denied delegation settles
too.

* fix(agents): address review on the delegation ledger

- Steer path: hold each wait's dispatch AIMessage locally and pass it to
  the observer, so a later response reusing the call id while the first
  call is still observed cannot take over its args or dispatch id.
- New-turn close: a dispatch whose reply carries subagent status settles
  from that reply instead of staying in_progress, covering a crash
  between the tools checkpoint and the next capture.
- Reuse thread_state.delegation_key instead of a duplicate identity
  helper in DurableContext.
- CHANGELOG: reference #8128.

* docs(changelog): drop the #8128 entry per review

2026-11-12 19:46:58 +08:00

..

blocking_io

fix(subagents): resolve the inherit-path app config off the event loop (#8134)

2026-11-12 16:59:02 +08:00

fixtures

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

monocle

…

support

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

_agent_e2e_helpers.py

…

_approval_test_helpers.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

_gateway_shutdown_budget.py

fix(sandbox): leave SIGTERM/SIGINT teardown to the Gateway lifespan (#7560)

2026-10-26 20:38:32 +08:00

_host_path_helpers.py

test(mounts): compare host paths separator-agnostically in provisioner and mount suites (#5413)

2026-09-14 11:10:41 +08:00

_readable_helpers.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

_replay_fixture.py

…

_repository_race_helpers.py

fix(persistence): retry feedback and conversation upserts that lose a race (#6852)

2026-10-14 12:19:26 +08:00

_router_auth_helpers.py

fix(mcp): close thread-scoped MCP sessions on thread deletion (#5956)

2026-09-29 16:53:18 +08:00

_run_message_pagination_helpers.py

…

_scheduled_rows.py

feat(scheduled-tasks): finish the user-facing side of conversation schedules (RFC #6340, 1/2) (#6378)

2026-10-07 07:47:32 +08:00

_thread_checkpoint_helpers.py

fix(client): count threads, not checkpoints, in list_threads (#6426)

2026-10-07 17:16:48 +08:00

_windows_acl_helpers.py

fix(sandbox): platform-aware Lark CLI runtime validation for Windows hosts (#5442)

2026-09-15 07:26:08 +08:00

AGENTS.md

docs: turn README into an index and move reference detail to docs/guide (#8113)

2026-11-11 13:26:17 +08:00

conftest.py

feature(gateway): issue request trace ids unconditionally (#5119)

2026-09-01 16:49:39 +08:00

manual_browser_live_check.py

…

poc_external_system_message_injection.py

fix(security): prevent external system-role message injection (#5651)

2026-09-22 10:38:16 +08:00

replay_provider.py

…

seed_runs_router.py

…

test_acceptance_build_summaries.py

fix(subagents): require test evidence beyond build success (#6868)

2026-10-14 17:15:59 +08:00

test_acceptance_checks.py

fix(acceptance): reject nonpassing unittest summaries (#6916)

2026-10-15 15:26:47 +08:00

test_acceptance_evidence_reused_call_ids.py

fix(subagents): keep tests_passed evidence per call when a provider reuses its id (#8012)

2026-11-09 19:59:47 +08:00

test_acp_config.py

…

test_acquire_serialization.py

fix(opensandbox): mirror thread outputs before warm reuse (#6699)

2026-10-12 22:16:33 +08:00

test_activation_decisions.py

feat(authz): construction-enforced async decision batches (ActivationDecisions) (#6508)

2026-10-09 16:09:17 +08:00

test_additional_channel_connections.py

fix(channels): keep IM binding codes on screen and report goal state in replies (#7591)

2026-10-27 09:46:58 +08:00

test_admin_users_router.py

fix(auth): allow demoting disabled administrators (#7769)

2026-11-02 09:26:00 +08:00

test_agent_assembly_descriptor.py

fix(skills): strip a leading BOM from the SKILL.md content handed to the model (#6984)

2026-10-18 22:03:27 +08:00

test_agent_display_name.py

feat(agents): support Unicode display names for custom agents (#5324)

2026-09-12 11:09:41 +08:00

test_agent_guidance_check.py

docs: turn README into an index and move reference detail to docs/guide (#8113)

2026-11-11 13:26:17 +08:00

test_agent_knowledge_scope.py

fix(agents): clear incompatible knowledge defaults on self-update (#6995)

2026-10-18 11:12:57 +08:00

test_agent_model_settings.py

feat(agents): allow custom agents to disable memory (#5167)

2026-09-14 18:17:54 +08:00

test_agent_storage_backend.py

fix(agents): validate the agent name in FileAgentStore.get_soul (#7265)

2026-10-23 14:54:21 +08:00

test_agent_store_sql.py

fix(agents): store an explicit null description as empty (#7638)

2026-11-01 23:34:59 +08:00

test_agent_teams_plugin.py

fix(extensions): roll back shared state mutations on budget check failure (#7902)

2026-11-05 16:06:20 +08:00

test_agent_tool_groups_router.py

feat(deer-flow): configure agent tool access (#6630)

2026-10-12 19:00:54 +08:00

test_agents_router_model_settings.py

feat(capabilities): unify catalog, plugin configuration and agent selection (#5497)

2026-09-19 12:14:24 +08:00

test_agents_router_write_drain.py

feat(agents): add portable custom agent packages (#6127)

2026-10-06 10:20:38 +08:00

test_aio_bash_capacity.py

fix(sandbox): run scoped env commands concurrently (#7841)

2026-11-09 20:18:30 +08:00

test_aio_sandbox_local_backend.py

fix(sandbox): make failed AIO teardown safely retryable (#7001)

2026-10-18 09:57:12 +08:00

test_aio_sandbox_network_proxy.py

feat(sandbox): add controlled egress with approvals (#5152)

2026-09-04 23:46:57 +08:00

test_aio_sandbox_provider.py

fix(sandbox): run scoped env commands concurrently (#7841)

2026-11-09 20:18:30 +08:00

test_aio_sandbox_readiness.py

fix(sandbox): honor the readiness budget on a monotonic clock (#6823)

2026-10-14 06:43:07 +08:00

test_aio_sandbox_recovery_errors.py

fix(sandbox): bound AIO list_dir with a directory deadline (#5662)

2026-09-22 19:49:00 +08:00

test_aio_sandbox_restricted_creation_ports.py

fix(sandbox): retain ports when restricted cleanup is unconfirmed (#7917)

2026-11-07 16:07:15 +08:00

test_aio_sandbox_spawn_ports.py

fix(sandbox): retain ports when restricted cleanup is unconfirmed (#7917)

2026-11-07 16:07:15 +08:00

test_aio_sandbox.py

fix(sandbox): run scoped env commands concurrently (#7841)

2026-11-09 20:18:30 +08:00

test_aio_scoped_env_concurrency.py

fix(sandbox): run scoped env commands concurrently (#7841)

2026-11-09 20:18:30 +08:00

test_allowed_users.py

fix(buzz): a single mention_free_channels ID was split into characters, a numeric one stopped the connector (#6776)

2026-10-13 14:55:49 +08:00

test_api_route_setup_wizard.py

feat: add API Route setup wizard preset (#6579)

2026-10-18 09:26:45 +08:00

test_app_config_boolean_thresholds.py

fix(config): reject boolean integer settings in app_config (#6171)

2026-10-03 14:29:41 +08:00

test_app_config_explicit_path.py

fix(config): pin explicit app config path across get_app_config (#7092)

2026-10-24 22:04:48 +08:00

test_app_config_name_indexes.py

…

test_app_config_reload.py

feat(extensions): scope configured middlewares to lead or subagent (#7661)

2026-10-31 08:46:16 +08:00

test_artifact_archive.py

fix(goal,artifacts): verify completion and artifact handoff (#7961)

2026-11-07 18:21:49 +08:00

test_artifact_ascii_delimiters.py

fix(artifacts): preserve balanced ASCII delimiters in references (#6967)

2026-10-18 19:23:19 +08:00

test_artifact_capture_middleware.py

feat(agents): persist tool artifacts as resolvable handles (#4676) (#4929)

2026-09-27 11:09:41 +08:00

test_artifact_integration.py

fix(artifacts): keep sandbox paths inside CJK corner brackets whole (#7377)

2026-10-24 20:45:02 +08:00

test_artifact_registry.py

fix(artifacts): keep sandbox paths inside CJK corner brackets whole (#7377)

2026-10-24 20:45:02 +08:00

test_artifact_resolution_middleware.py

feat(agents): persist tool artifacts as resolvable handles (#4676) (#4929)

2026-09-27 11:09:41 +08:00

test_artifact_review_regressions.py

feat(agents): persist tool artifacts as resolvable handles (#4676) (#4929)

2026-09-27 11:09:41 +08:00

test_artifact_safety_review.py

feat(agents): persist tool artifacts as resolvable handles (#4676) (#4929)

2026-09-27 11:09:41 +08:00

test_artifacts_router.py

fix(artifacts): bind ranged reads to validated generation (#7978)

2026-11-09 21:18:57 +08:00

test_assembly_io.py

fix(tools): run tool assembly off-loop at async entry points (#5224)

2026-09-12 07:41:24 +08:00

test_assistant_payload_replay.py

…

test_assistants_compat.py

fix(backend): validate assistant search pagination (#5506)

2026-09-17 22:13:53 +08:00

test_atomic_admission_authority.py

fix(runtime): recover terminal Redis streams after producer loss (#7093)

2026-10-19 15:53:54 +08:00

test_atomic_admission_worker.py

ci: split backend unit tests into six shards (#8164)

2026-11-12 11:08:31 +08:00

test_atomic_cleanup_census.py

fix(persistence): discard the staged temp when the write itself fails (#7504)

2026-10-27 11:47:28 +08:00

test_atomic_cleanup_preserves_primary_error.py

fix(uploads,integrations): keep atomic-write cleanup from replacing the caller's outcome (#7200)

2026-10-22 16:03:43 +08:00

test_atomic_cleanup_writers.py

fix(gateway,integrations): keep temp cleanup from replacing the caller's outcome (#7505)

2026-10-25 22:13:26 +08:00

test_auth_config.py

fix(security): add DEER_FLOW_CREDENTIALS_KEY and wire the channel credentials cipher (#6611)

2026-10-10 20:51:09 +08:00

test_auth_errors.py

fix(auth): treat a signed token with wrong claims as malformed (#7266)

2026-10-22 19:31:37 +08:00

test_auth_me_permissions.py

fix(authz): cover create/run/memory/agent routes with permission checks; scope USER.md per user (#4989)

2026-09-23 15:37:26 +08:00

test_auth_middleware.py

feat(authz): account disable/enable across every authentication surface (#4063 gap 3) (#6566)

2026-10-10 16:43:04 +08:00

test_auth_type_system.py

feat(authz): admin role-assignment API for configured custom roles (#4063 gap 2) (#6382)

2026-10-07 14:59:16 +08:00

test_auth.py

fix(frontend): return SSO sign-ins to their next path (#7467)

2026-10-26 19:24:35 +08:00

test_authenticated_user_context.py

feat(weknora): allow opt-in shared retrieval for authenticated users (#7944)

2026-11-09 17:06:05 +08:00

test_authorization_enforcement.py

feat(authz): middleware-declared tool path Layer 1 now covers tools declared by middlewares (#6105)

2026-10-01 18:26:58 +08:00

test_authorization_outcome.py

feat(extensions): let an out-of-tree extension observe what the agent did (#4863)

2026-08-23 09:57:12 +08:00

test_authorization_principal.py

…

test_authorization_provider.py

…

test_authorization_route_permissions.py

fix(gateway): read the route authorization config off the event loop (#7557)

2026-10-26 18:44:09 +08:00

test_authorization_runtime.py

…

test_authorization_tool_filter.py

…

test_background_task_status_filter.py

feat(mcp): filter background tasks by status (#6527)

2026-10-10 08:53:51 +08:00

test_background_tasks_tool.py

fix(mcp): scope sessions and task access by thread incarnation (#5556)

2026-09-23 08:33:20 +08:00

test_base_to_dict.py

…

test_batch_acceptance.py

feat(acceptance): verify required CSV header columns (#6714)

2026-10-13 19:52:22 +08:00

test_batch_continuation.py

feat(subagents): continue requested batch work and schedule explicit prerequisites (#7839)

2026-11-05 15:10:21 +08:00

test_batch_dependencies.py

feat(subagents): continue requested batch work and schedule explicit prerequisites (#7839)

2026-11-05 15:10:21 +08:00

test_batch_extension_snapshot.py

feat(agent): add read-only run status introspection (phase 1) (#7297)

2026-10-23 22:06:00 +08:00

test_batch_followup_host.py

feat(hitl): add human-in-the-loop approval for high-risk tool calls (#7979)

2026-11-09 09:52:35 +08:00

test_batch_goal_wakeup.py

feat(subagents): continue requested batch work and schedule explicit prerequisites (#7839)

2026-11-05 15:10:21 +08:00

test_batch_lease_lifecycle.py

fix(subagents): recover expired attempts in paused batches (#7686)

2026-10-30 21:50:39 +08:00

test_batch_rag_evidence.py

feat(subagents): preserve RAG evidence in durable batch exports (#6413)

2026-10-07 18:37:31 +08:00

test_batch_result_reader.py

feat(subagents): add bounded same-thread batch result inspection (#6416)

2026-10-07 18:43:31 +08:00

test_batch_task_tool.py

feat(subagents): continue requested batch work and schedule explicit prerequisites (#7839)

2026-11-05 15:10:21 +08:00

test_bench_checkpoint_channels.py

test(checkpoint): measure postgres storage growth (#5051)

2026-09-01 22:36:31 +08:00

test_bench_checkpoint_production.py

fix(runtime): keep agent construction off event loop (#5217)

2026-09-12 21:09:05 +08:00

test_bench_concurrency.py

fix(auth): correct OAuth conflict error message + validate multi-worker Postgres claim with real concurrency benchmark (#5026)

2026-09-03 08:17:26 +08:00

test_bench_context_memory_comparison.py

feat(benchmark): add offline memory vs project-context comparison suite (part of #7884) (#8058)

2026-11-10 14:45:56 +08:00

test_bench_context_snapshot.py

fix(eval): distinguish booleans from numbers in snapshot grading (#7358)

2026-10-23 22:02:50 +08:00

test_bench_deermem_eviction_contracts.py

eval(memory): add a reproducible hybrid eviction evaluation (#4810)

2026-08-29 14:36:38 +08:00

test_bench_deermem_eviction_dataset.py

eval(memory): add a reproducible hybrid eviction evaluation (#4810)

2026-08-29 14:36:38 +08:00

test_bench_deermem_eviction_grading.py

eval(memory): add a reproducible hybrid eviction evaluation (#4810)

2026-08-29 14:36:38 +08:00

test_bench_deermem_eviction_policy.py

eval(memory): add a reproducible hybrid eviction evaluation (#4810)

2026-08-29 14:36:38 +08:00

test_bench_deermem_eviction_protocol.py

eval(memory): add a reproducible hybrid eviction evaluation (#4810)

2026-08-29 14:36:38 +08:00

test_bench_deermem_eviction_published_results.py

eval(memory): add a reproducible hybrid eviction evaluation (#4810)

2026-08-29 14:36:38 +08:00

test_bench_deermem_eviction_qa.py

eval(memory): add a reproducible hybrid eviction evaluation (#4810)

2026-08-29 14:36:38 +08:00

test_bench_deermem_eviction_report.py

eval(memory): add a reproducible hybrid eviction evaluation (#4810)

2026-08-29 14:36:38 +08:00

test_bench_deermem_eviction_results.py

eval(memory): add a reproducible hybrid eviction evaluation (#4810)

2026-08-29 14:36:38 +08:00

test_bench_deermem_scope_isolation.py

feat(memory): add DeerMem scope-isolation benchmark (#5564)

2026-09-20 20:01:28 +08:00

test_bench_opensandbox.py

fix(benchmark): validate sandbox timing options (#7651)

2026-10-28 20:47:59 +08:00

test_bench_sandbox_prewarm.py

test(sandbox): make prewarm clock regression deterministic (#7513)

2026-10-25 22:29:14 +08:00

test_bench_sandbox_provider.py

feat(sandbox): add bounded AIO prewarming and lifecycle benchmarks (#6998)

2026-10-18 08:10:56 +08:00

test_bench_sandbox_resources.py

feat(sandbox): add bounded AIO prewarming and lifecycle benchmarks (#6998)

2026-10-18 08:10:56 +08:00

test_bench_scheduled_budget_evidence.py

feat(goal): show why a chat goal stopped and when it was met, and redact the goal evaluator and continuation input (#6556)

2026-10-10 00:20:45 +08:00

test_bench_scheduled_tasks.py

fix(goal,artifacts): verify completion and artifact handoff (#7961)

2026-11-07 18:21:49 +08:00

test_bench_tool_result_probe_cleanup.py

test(checkpoint): retention deletion contract + growth baseline (#4189 item 3) (#5255)

2026-09-08 19:21:57 +08:00

test_bench_worker.py

fix(auth): correct OAuth conflict error message + validate multi-worker Postgres claim with real concurrency benchmark (#5026)

2026-09-03 08:17:26 +08:00

test_blob_store.py

fix(storage): resolve single-module colon backend imports (#7017)

2026-10-20 09:35:56 +08:00

test_bookmark_plugin.py

feat(plugins): full-stack plugin APIs and bookmarks (#5647)

2026-09-22 11:18:57 +08:00

test_boolean_guards.py

refactor(config): converge the boolean guards into one shared helper (#6226)

2026-10-04 09:09:15 +08:00

test_boxlite_provider.py

fix(sandbox): recover BoxLite VMs on the provider event loop (#8072)

2026-11-10 15:05:33 +08:00

test_boxlite_recovery_sdk.py

fix(sandbox): recover BoxLite VMs on the provider event loop (#8072)

2026-11-10 15:05:33 +08:00

test_branch_history_seed.py

…

test_brave_response_shapes.py

fix(brave): contain malformed web search results (#6550)

2026-10-10 09:52:40 +08:00

test_brave_tools.py

fix(tools): make the search coercion guards catch OverflowError (#5957)

2026-09-28 14:35:42 +08:00

test_browser_assets.py

test(plugins): guard symlink-dependent browser asset cases (#6267)

2026-10-04 19:27:54 +08:00

test_browser_automation.py

fix(browser): preserve the browser context after login popups close (#7674)

2026-10-30 07:20:02 +08:00

test_browser_ci_runner.py

feat(knowledge): add independent Wiki and entity relation retrieval tools (#7171)

2026-10-22 16:54:58 +08:00

test_browser_close_cancellation.py

fix(browser): keep session teardown alive across caller cancellation (#5444)

2026-09-15 08:14:42 +08:00

test_browser_egress.py

fix(browser): isolate egress DNS workers (#6301)

2026-10-30 22:18:54 +08:00

test_browser_outputs_atomic.py

fix(browser): preserve publication errors during failed cleanup (#6871)

2026-10-19 16:27:15 +08:00

test_browser_readonly_security.py

fix(browser): drain live cleanup before releasing session (#6284)

2026-10-05 12:15:21 +08:00

test_browser_router.py

fix(browser): pin browser connections to the SSRF-vetted addresses (#6201)

2026-10-03 10:05:47 +08:00

test_browser_screenshot_no_overwrite.py

fix(browser): never replace an existing output file with browser_screenshot (#6913)

2026-10-18 10:52:22 +08:00

test_browserless_capture_name_reservation.py

fix(utils):Keep the timestamped output-name fallbacks distinct on a coarse clock (#7071)

2026-10-25 16:17:15 +08:00

test_browserless_client.py

fix(browserless): reject timeouts httpx cannot use (#8025)

2026-11-11 19:43:53 +08:00

test_bump_version_lockfile_sync.py

chore(release): keep deerflow-harness in the version-source lockstep (#7696)

2026-10-29 21:11:45 +08:00

test_business_plugins.py

feat(capabilities): unify catalog, plugin configuration and agent selection (#5497)

2026-09-19 12:14:24 +08:00

test_buzz_channel.py

fix(channels): keep IM binding codes on screen and report goal state in replies (#7591)

2026-10-27 09:46:58 +08:00

test_buzz_nostr.py

feat(channels): add Buzz (Nostr) channel connector (#4649)

2026-08-05 08:29:22 +08:00

test_buzz_seen_events.py

fix(buzz): page a saturated history instead of skipping the oldest (#6792)

2026-10-14 15:59:46 +08:00

test_cached_history_saver_integration.py

test(checkpoint): delta-history cache migration coverage + pin two open DeltaChannel defects (#5797)

2026-09-24 15:16:08 +08:00

test_cached_history_saver.py

fix(runtime): preserve canonical delta-history order in cache (#6774)

2026-10-13 08:34:05 +08:00

test_cancel_run_idempotent.py

…

test_cancelled_batch_retry.py

fix(harness): keep a cancelled batch cancelled when retrying a failed item (#7792)

2026-11-02 10:05:05 +08:00

test_capability_api.py

fix(mcp): preserve server binding history across gateway workers (#6617)

2026-10-11 11:45:28 +08:00

test_capability_registry.py

feat(capabilities): unify catalog, plugin configuration and agent selection (#5497)

2026-09-19 12:14:24 +08:00

test_cargo_acceptance.py

fix(test): widen the cargo acceptance sandbox timeout (#7243)

2026-10-22 08:37:40 +08:00

test_changelog_reference_links.py

fix(changelog): define the missing [#7022] reference link (#7710)

2026-10-30 08:40:00 +08:00

test_channel_capabilities.py

feat(channels): generalize group notifications and add opt-in task/goal IM notices (#6903)

2026-10-15 10:30:55 +08:00

test_channel_config_reload_cancellation.py

fix(channels): keep config reload publication under lifecycle lock (#6390)

2026-10-07 08:26:53 +08:00

test_channel_connection_context.py

feat(channels): control IM notifications and add WeChat/QQ delivery (#6850)

2026-10-14 11:14:48 +08:00

test_channel_connections_config.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

test_channel_connections_repository.py

fix(persistence): retry feedback and conversation upserts that lose a race (#6852)

2026-10-14 12:19:26 +08:00

test_channel_connections_router.py

feat(channels): share encrypted runtime channel config across Gateway instances (#6988)

2026-10-18 11:10:31 +08:00

test_channel_credential_staging.py

test(channels): drop the POSIX-only utime flag that breaks 9 tests on Windows (#7750)

2026-11-01 23:25:44 +08:00

test_channel_credentials_wiring.py

feat(channels): arbitrate IM transports with a per-provider leader lease (#6843)

2026-10-14 13:51:42 +08:00

test_channel_file_attachments.py

fix(wecom): raise the image upload cap to the platform's 10 MB (#8174)

2026-11-12 17:16:42 +08:00

test_channel_hidden_human_input.py

feat(channels): Feishu interactive clarification cards (#6670)

2026-10-11 23:58:54 +08:00

test_channel_inbound_idempotency.py

fix(channels): run each IM message once across instances, restarts and late redeliveries (#7104)

2026-10-19 22:57:19 +08:00

test_channel_intake_backpressure.py

fix(channels): share chat-to-thread bindings through the database (#6558)

2026-10-10 14:00:00 +08:00

test_channel_leader_lease_config.py

feat(channels): add channels.leader_lease and gate an explicitly disabled lease under multi-process signals (#6746)

2026-10-12 23:05:16 +08:00

test_channel_leader_lease_service.py

feat(channels): add channels.leader_lease and gate an explicitly disabled lease under multi-process signals (#6746)

2026-10-12 23:05:16 +08:00

test_channel_leadership.py

feat(channels): arbitrate IM transports with a per-provider leader lease (#6843)

2026-10-14 13:51:42 +08:00

test_channel_lease_repository.py

feat(channels): arbitrate IM transports with a per-provider leader lease (#6843)

2026-10-14 13:51:42 +08:00

test_channel_reply_locale.py

fix(channels): keep IM binding codes on screen and report goal state in replies (#7591)

2026-10-27 09:46:58 +08:00

test_channel_runtime_config_db_store.py

fix(channels): recover from undecodable runtime config and WeChat state (#7273)

2026-10-22 19:26:38 +08:00

test_channel_runtime_config_encoding.py

fix(channels): persist runtime configuration as UTF-8 (#5803)

2026-09-24 15:11:49 +08:00

test_channel_runtime_config_replicas.py

feat(channels): share encrypted runtime channel config across Gateway instances (#6988)

2026-10-18 11:10:31 +08:00

test_channel_runtime_config_store_lock.py

fix(channels): retry the runtime config file lock instead of failing after ~10s on Windows (#6888)

2026-10-25 11:05:04 +08:00

test_channel_runtime_config_store_peers.py

fix(channels): merge runtime channel config saves across Gateway workers (#6844)

2026-10-14 10:21:02 +08:00

test_channel_service_leader_lease.py

feat(channels): arbitrate IM transports with a per-provider leader lease (#6843)

2026-10-14 13:51:42 +08:00

test_channel_service_restart_stop_fence.py

fix(channels): fence restart during service shutdown (#6503)

2026-10-08 22:29:49 +08:00

test_channel_service_start_stop_shutdown_generation_fence.py

fix(channels): fence manager startup across completed shutdown (#6521)

2026-10-10 07:43:05 +08:00

test_channel_service_startup_cancellation.py

fix(channels): rollback partial service startup across cancellation (#5537)

2026-09-19 10:29:02 +08:00

test_channel_staging_cleanup.py

test(channels): assert the blocked-rename error portably on Windows (#7276)

2026-10-25 10:26:23 +08:00

test_channel_state_atomic_publish.py

fix(channels): publish Discord and WeChat JSON state atomically (#7595)

2026-10-30 14:54:41 +08:00

test_channel_state_encoding.py

fix(channels): publish Discord and WeChat JSON state atomically (#7595)

2026-10-30 14:54:41 +08:00

test_channel_stream_errors.py

fix(runtime): present outputs before a loop wrap-up and explain step-limit stops (#7588)

2026-10-27 10:34:34 +08:00

test_channel_thread_binding_store.py

fix(channels): recover from undecodable thread-binding state (#7233)

2026-10-21 21:56:12 +08:00

test_channel_thread_claim.py

fix(channels): run each IM message once across instances, restarts and late redeliveries (#7104)

2026-10-19 22:57:19 +08:00

test_channel_undecodable_state.py

fix(channels): recover from undecodable runtime config and WeChat state (#7273)

2026-10-22 19:26:38 +08:00

test_channel_user_id_env.py

fix(sandbox): expose DEERFLOW_USER_ID to every bash command (#6058)

2026-09-30 14:56:03 +08:00

test_channels_router.py

feat(channels): arbitrate IM transports with a per-provider leader lease (#6843)

2026-10-14 13:51:42 +08:00

test_channels.py

fix(channels): keep Gateway calls off the environment proxy (#7877)

2026-11-08 22:10:10 +08:00

test_check_script.py

fix(scripts): make check.py and setup_wizard.py --help print usage (#8152)

2026-11-12 06:15:52 +08:00

test_checkpoint_cache_config.py

feat(checkpoint): checkpoint history cache (#4638)

2026-08-02 22:25:02 +08:00

test_checkpoint_cache_memory_concurrency.py

fix(checkpoints): serialize shared memory history cache operations (#6708)

2026-10-18 08:13:27 +08:00

test_checkpoint_cache_memory.py

feat(checkpoint): checkpoint history cache (#4638)

2026-08-02 22:25:02 +08:00

test_checkpoint_cache_payload_isolation.py

fix(checkpoints): isolate cached history payloads from state readers (#7259)

2026-10-25 22:00:14 +08:00

test_checkpoint_cache_provider.py

feat(checkpoint): checkpoint history cache (#4638)

2026-08-02 22:25:02 +08:00

test_checkpoint_cache_redis_literal_purge.py

fix(checkpoints): confine Redis history purge to literal namespaces (#6709)

2026-10-15 07:52:29 +08:00

test_checkpoint_cache_redis.py

fix(checkpoints): skip unserializable Redis history cache entries (#7014)

2026-10-18 10:30:14 +08:00

test_checkpoint_lineage.py

fix(gateway): classify duration-only checkpoints without the Postgres-dropped marker (#5988)

2026-10-09 20:30:19 +08:00

test_checkpoint_mode.py

feat(extensions): let an out-of-tree extension observe what the agent did (#4863)

2026-08-23 09:57:12 +08:00

test_checkpoint_patches.py

…

test_checkpoint_retention_contract.py

test(checkpoint): retention deletion contract + growth baseline (#4189 item 3) (#5255)

2026-09-08 19:21:57 +08:00

test_checkpoint_retention_service.py

fix(checkpoints): run conservative retention after completion (#6051)

2026-10-20 22:23:47 +08:00

test_checkpoint_state.py

feat(agents): allow custom agents to disable memory (#5167)

2026-09-14 18:17:54 +08:00

test_checkpointer_none_fix.py

…

test_checkpointer.py

chore(checkpoint): require fixed DeltaChannel replay backends (#8139)

2026-11-12 17:49:41 +08:00

test_ci_uv_version_pin.py

feat(extensions): add gateway contribution points and packaged extension management (#4780)

2026-08-13 23:55:30 +08:00

test_clarification_drop_siblings_graph_integration.py

fix(clarification): drop sibling tool calls before interrupt (#4908)

2026-08-24 07:37:35 +08:00

test_clarification_middleware.py

fix(clarification): keep each question when a provider reuses a call ID (#7762)

2026-11-01 12:41:34 +08:00

test_clarification_reused_call_id_graph_integration.py

fix(clarification): keep each question when a provider reuses a call ID (#7762)

2026-11-01 12:41:34 +08:00

test_claude_fd_encoding.py

fix(models): skip undecodable Claude descriptor handoffs (#6323)

2026-10-05 20:21:31 +08:00

test_claude_keychain_export.py

fix(scripts): reject invalid Claude Keychain credential containers (#6281)

2026-10-05 15:39:32 +08:00

test_claude_provider_oauth_betas.py

fix(models): keep the OAuth betas when a Claude request sends its own betas (#8061)

2026-11-12 18:29:48 +08:00

test_claude_provider_oauth_billing.py

…

test_claude_provider_prompt_caching.py

fix(models): exclude thinking blocks from Claude cache breakpoints (#6339)

2026-10-06 09:05:55 +08:00

test_claude_provider_retry_after.py

fix(middleware): guard OverflowError when parsing non-finite Retry-After hints (#6455)

2026-10-08 18:16:21 +08:00

test_claude_provider_thinking.py

fix(models): validate Claude extended-thinking budgets (#6060)

2026-10-08 10:24:16 +08:00

test_claude_retry_after_dates.py

fix(models): honor HTTP-date Retry-After hints in Claude retries (#7295)

2026-10-23 15:21:44 +08:00

test_cleanup_containers_script.py

fix(scripts): select sandbox containers by anchored name (#7189)

2026-10-21 20:57:02 +08:00

test_cli_auth_providers.py

fix(models): reject blank Codex CLI tokens (#5959)

2026-09-28 16:16:15 +08:00

test_client_context_injection.py

feat(context): support client context capabilities (#7051)

2026-10-19 10:41:18 +08:00

test_client_context.py

feat(context): support client context capabilities (#7051)

2026-10-19 10:41:18 +08:00

test_client_e2e.py

fix(mcp): preserve server binding history across gateway workers (#6617)

2026-10-11 11:45:28 +08:00

test_client_langfuse_metadata.py

fix(tracing): tag graph runs with the effective model (#5902)

2026-09-27 08:06:03 +08:00

test_client_live_policy.py

ci: split backend unit tests into six shards (#8164)

2026-11-12 11:08:31 +08:00

test_client_live.py

fix(tests): require explicit opt-in for live client tests (#4482)

2026-07-29 22:16:48 +08:00

test_client_message_serialization.py

…

test_client_stream_usage.py

fix(client): accumulate incremental streaming token usage (#6939)

2026-10-16 10:38:10 +08:00

test_client_upload_companion_collisions.py

fix(uploads): never truncate an existing upload on same-name collision (#7388)

2026-10-24 20:57:27 +08:00

test_client_upload_snapshot.py

fix(uploads): never truncate an existing upload on same-name collision (#7388)

2026-10-24 20:57:27 +08:00

test_client_upload_unsafe_skip.py

fix(client): keep a decided batch outcome through capture cleanup (#7517)

2026-10-26 17:03:45 +08:00

test_client.py

fix(client): scope memory management to the named agent's bucket (#8146)

2026-11-12 09:21:28 +08:00

test_codex_provider.py

fix(models): omit Codex tool results with blank call IDs (#6234)

2026-10-04 12:44:05 +08:00

test_codex_retry_after.py

fix(codex): honor Retry-After in the provider retry loop (#7151)

2026-10-20 10:01:47 +08:00

test_codex_stream_terminal_events.py

fix(models): tolerate null Codex response usage (#6335)

2026-10-06 08:11:05 +08:00

test_codex_tool_choice.py

fix(models): preserve Codex tool_choice in requests (#6898)

2026-10-15 09:58:16 +08:00

test_codex_tool_strict.py

fix(models): preserve explicit Codex function tool strictness (#6360)

2026-10-06 16:53:45 +08:00

test_command_tool_result_semantics.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_compact_interrupted_thread.py

feat(hitl): add human-in-the-loop approval for high-risk tool calls (#7979)

2026-11-09 09:52:35 +08:00

test_compaction_event_identity.py

fix(extensions): hand compaction observers the live task store and name the task in CompactionEvent (#7831)

2026-11-03 15:06:52 +08:00

test_completed_evidence_admission.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_completed_run_evidence.py

feat(hitl): add human-in-the-loop approval for high-risk tool calls (#7979)

2026-11-09 09:52:35 +08:00

test_compose_auth_trusted_proxies.py

fix(auth): key the compose login lockout by client, not by nginx (#6519)

2026-10-09 17:22:45 +08:00

test_compose_credentials_key.py

fix(security): add DEER_FLOW_CREDENTIALS_KEY and wire the channel credentials cipher (#6611)

2026-10-10 20:51:09 +08:00

test_compose_default_bind_host.py

feat(deploy): select production Compose env files (#6522)

2026-10-21 15:58:30 +08:00

test_compose_default_workers.py

fix(deploy): wire the multi-replica prerequisites into the Helm chart and compose (#6347)

2026-10-06 11:21:51 +08:00

test_compose_extensions_config_writable.py

fix(docker): let the Gateway write extensions_config.json in production (#4852)

2026-08-23 15:08:39 +08:00

test_compose_nginx_image_pin.py

fix(docker): pin nginx to 1.31.2-alpine before the musl 1.2.6 pwritev2 build, closes #7615 (#7643)

2026-10-28 18:52:13 +08:00

test_compose_nginx_ipv6_guard.py

fix(docker): strip the IPv6 listen in the production nginx launcher too (#5900)

2026-09-27 07:36:35 +08:00

test_config_atomic_cleanup.py

fix(config): keep atomic-write cleanup from replacing the caller's outcome (#7279)

2026-10-25 19:23:44 +08:00

test_config_version.py

test(config): skip the config-upgrade cases that need Git Bash (#7246)

2026-10-22 07:37:37 +08:00

test_configure_script.py

fix(scripts): make configure.py --help print usage without generating files (#7404)

2026-10-24 13:29:48 +08:00

test_configured_extensions.py

feat(extensions): scope configured middlewares to lead or subagent (#7661)

2026-10-31 08:46:16 +08:00

test_configured_middleware_scope.py

feat(extensions): scope configured middlewares to lead or subagent (#7661)

2026-10-31 08:46:16 +08:00

test_console_router.py

fix(console): tolerate malformed usage counters and pricing (#7736)

2026-10-31 18:05:16 +08:00

test_context_compaction_observation.py

fix(extensions): hand compaction observers the live task store and name the task in CompactionEvent (#7831)

2026-11-03 15:06:52 +08:00

test_context_compaction.py

feat(hitl): add human-in-the-loop approval for high-risk tool calls (#7979)

2026-11-09 09:52:35 +08:00

test_conversation_access_edge_cases.py

fix(conversation): tolerate malformed event metadata (#7721)

2026-10-31 18:25:31 +08:00

test_conversation_access.py

feat(hitl): add human-in-the-loop approval for high-risk tool calls (#7979)

2026-11-09 09:52:35 +08:00

test_conversation_message_continuation.py

fix(events): rebase RunEvent snapshot isolation onto current main (#7423)

2026-10-28 20:59:10 +08:00

test_conversation_reader.py

fix(conversation): tolerate malformed event metadata (#7721)

2026-10-31 18:25:31 +08:00

test_conversation_references_context_channel.py

feat(gateway): accept conversation references in run context and report the capability (#5463)

2026-09-16 15:37:57 +08:00

test_converters.py

…

test_crawl4ai_tools.py

fix(crawl4ai): report a format error for non-object 200 payloads (#7065)

2026-10-19 07:07:11 +08:00

test_create_deerflow_agent_live.py

…

test_create_deerflow_agent.py

fix(mcp): stop persisting URL-sourced ResourceLink blocks and heal bricked threads (#6606)

2026-10-10 21:23:27 +08:00

test_credential_file_encoding.py

fix(models): decode CLI credential files as UTF-8 (#6277)

2026-10-05 14:47:14 +08:00

test_credential_loader.py

fix(models): fall through an unusable credential source instead of ending the lookup (#7140)

2026-10-20 10:30:52 +08:00

test_credentials_key.py

fix(security): add DEER_FLOW_CREDENTIALS_KEY and wire the channel credentials cipher (#6611)

2026-10-10 20:51:09 +08:00

test_csrf_middleware.py

fix(gateway): reject non-ASCII tokens instead of raising in constant-time compares (#6076)

2026-09-30 17:41:11 +08:00

test_csv_acceptance.py

feat(acceptance): verify required CSV header columns (#6714)

2026-10-13 19:52:22 +08:00

test_custom_agent.py

fix(agents): store an explicit null description as empty (#7638)

2026-11-01 23:34:59 +08:00

test_custom_events.py

fix(subagents): isolate background tasks from reused tool call IDs (#4758)

2026-08-12 09:25:05 +08:00

test_dangling_tool_call_middleware.py

fix(middleware): skip raw tool-call fallback when invalid view carries the same call (#4693)

2026-08-08 21:07:55 +08:00

test_db_event_store_lock_lifecycle.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_db_run_event_empty_filter.py

fix(events): honor empty event type filters in DB store (#7352)

2026-10-23 22:34:23 +08:00

test_ddg_image_search_urls.py

fix(image-search): keep the source page URL in DuckDuckGo and Serper results (#6915)

2026-10-15 14:56:46 +08:00

test_ddg_search_tools.py

fix(search): surface DuckDuckGo search failures instead of reporting an empty result (#6648)

2026-10-15 15:06:51 +08:00

test_deermem_self_contained.py

fix(memory): reject duplicate fact IDs during import (#8151)

2026-11-12 11:42:55 +08:00

test_deferred_catalog_regex_limits.py

fix(tools): bound deferred catalog regex execution (#6676)

2026-10-11 16:10:26 +08:00

test_deferred_catalog.py

…

test_deferred_filter_middleware.py

fix(harness): scope deferred tool promotion to user turn (#6977)

2026-10-18 11:24:41 +08:00

test_deferred_keyword_search.py

feat(tools): add opt-in literal keyword discovery (#6659)

2026-10-11 11:48:57 +08:00

test_deferred_promotion_integration.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_deferred_setup.py

…

test_deferred_tool_crosscontext.py

feature(skills): keep allowed-tools as compatibility metadata (#6935)

2026-10-20 19:34:28 +08:00

test_deferred_tool_promotion_real_llm.py

…

test_delegation_ledger_live.py

…

test_delegation_ledger.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_delegation_reused_call_ids.py

fix(agents): keep the delegation ledger exact across HITL approval and reused call ids (#8128)

2026-11-12 19:46:58 +08:00

test_delta_channel_checkpointers.py

chore(checkpoint): require fixed DeltaChannel replay backends (#8139)

2026-11-12 17:49:41 +08:00

test_delta_channel_state.py

feat(checkpoint): make delta snapshot_frequency configurable (#4516)

2026-07-28 23:21:23 +08:00

test_delta_resume_pending_execution.py

fix(gateway): preserve null input for static continuation (#7578)

2026-10-26 21:32:25 +08:00

test_deploy_dotenv_secrets.py

fix(security): add DEER_FLOW_CREDENTIALS_KEY and wire the channel credentials cipher (#6611)

2026-10-10 20:51:09 +08:00

test_deploy_env_file.py

feat(deploy): select production Compose env files (#6522)

2026-10-21 15:58:30 +08:00

test_deploy_home_writability.py

fix(security): add DEER_FLOW_CREDENTIALS_KEY and wire the channel credentials cipher (#6611)

2026-10-10 20:51:09 +08:00

test_deploy_uv_extras.py

test(scripts): resolve Git Bash instead of the WSL launcher for Windows shell-script tests (#5404)

2026-09-14 06:55:57 +08:00

test_detect_blocking_io_static.py

test(blocking-io): compare the emitted path portably (#6427)

2026-10-07 18:22:15 +08:00

test_detect_thread_boundaries.py

feat: complete backend thread-boundary inventory (#4562)

2026-07-29 22:33:45 +08:00

test_detect_uv_extras.py

fix(startup): detect extras for browser-configured IM channels (#7280)

2026-10-23 07:55:51 +08:00

test_detector_repo_root.py

feat: complete backend thread-boundary inventory (#4562)

2026-07-29 22:33:45 +08:00

test_dev_entrypoint.py

fix(startup): detect extras for browser-configured IM channels (#7280)

2026-10-23 07:55:51 +08:00

test_dev_multi_instance_script.py

fix(scripts): include nginx logs in dev_multi_instance.sh logs all (#7723)

2026-10-30 21:48:31 +08:00

test_dingtalk_channel.py

fix(dingtalk): verify recipient status for file sends (#8089)

2026-11-10 17:50:40 +08:00

test_disabled_admin_demotion_auth.py

fix(auth): allow demoting disabled administrators (#7769)

2026-11-02 09:26:00 +08:00

test_discord_channel_connections.py

fix(channels): run Discord connection-repository work on the Gateway loop (#6214)

2026-10-03 17:14:19 +08:00

test_discord_channel.py

fix(channels): run each IM message once across instances, restarts and late redeliveries (#7104)

2026-10-19 22:57:19 +08:00

test_discord_inbound_attachments.py

fix(discord): accept inbound attachments and file-only messages (#6857)

2026-10-14 23:01:02 +08:00

test_discord_thread_mapping_cancellation.py

fix(discord): drain thread mapping persistence across cancellation (#6356)

2026-10-06 15:49:27 +08:00

test_docker_sandbox_mode_detection.py

fix(docker): handle inline YAML comments in sandbox mode detection (#8103)

2026-11-11 20:11:53 +08:00

test_dockerignore_excludes_runtime_data.py

IssueHunter candidate 771965045901: fix for issue #7995 (#7996)

2026-11-08 14:06:04 +08:00

test_doctor_script.py

fix(memory): make doctor validates the selected backend config (#7965)

2026-11-08 10:25:19 +08:00

test_doctor.py

feat(community): add SpecStream web search and fetch provider (#7968)

2026-11-09 20:32:22 +08:00

test_durable_context_middleware.py

fix(goal): show the active goal to the agent on every model call (#5917)

2026-09-27 13:38:32 +08:00

test_dynamic_context_middleware.py

feat(context): support client context capabilities (#7051)

2026-10-19 10:41:18 +08:00

test_e2b_capacity_store_redis.py

refactor(sandbox): name the E2B ledger meta-field count (#4764)

2026-08-11 21:52:12 +08:00

test_e2b_sandbox_provider.py

fix(sandbox): leave SIGTERM/SIGINT teardown to the Gateway lifespan (#7560)

2026-10-26 20:38:32 +08:00

test_ensure_admin.py

…

test_ensure_sandbox_initialized.py

fix(sandbox): scope restored references to authenticated threads (#5736)

2026-09-23 09:53:49 +08:00

test_env_file.py

fix(config): accept a UTF-8 BOM in operator-authored env and secret files (#7085) (#7112)

2026-10-19 15:48:10 +08:00

test_exa_tools.py

feat(exa): support a configurable Exa-compatible base URL (#7306)

2026-10-23 16:51:36 +08:00

test_executor_starvation.py

fix(runtime): add deterministic executor starvation regressions (#5335)

2026-09-12 10:59:31 +08:00

test_extended_length_paths.py

fix(memory): rank capacity eviction per record, not per fact_id (#7454)

2026-10-25 13:20:15 +08:00

test_extension_agent_runs.py

fix(runtime): keep assembly evidence from reviving a run a peer reclaimed (#8046)

2026-11-11 07:56:53 +08:00

test_extension_api_contracts.py

feat(extensions): add versioned team file handoffs (#7817)

2026-11-05 14:50:09 +08:00

test_extension_api_state.py

feat(extensions): add middleware plugin foundation (#4636)

2026-08-04 22:33:26 +08:00

test_extension_api_surface.py

feat(extensions): allow ModelTool plugins to return structured artifacts (#6861)

2026-10-14 17:24:32 +08:00

test_extension_app_loading.py

feature(gateway): issue request trace ids unconditionally (#5119)

2026-09-01 16:49:39 +08:00

test_extension_artifact_imports.py

feat(extensions): add versioned team file handoffs (#7817)

2026-11-05 14:50:09 +08:00

test_extension_atomic_write_cleanup.py

fix(extensions): keep atomic-write cleanup from replacing the save error (#7164)

2026-10-24 07:38:10 +08:00

test_extension_check_script.py

feat(extensions): show package-owned usage in extension details (#8031)

2026-11-10 18:41:27 +08:00

test_extension_config.py

feat(extensions): observe task lifecycle and system model calls (#4684)

2026-08-11 16:33:22 +08:00

test_extension_dependency_sync.py

fix(tests): skip POSIX-host-bound contract tests on Windows dev hosts (#5931)

2026-09-27 10:43:19 +08:00

test_extension_documentation.py

feat(extensions): show package-owned usage in extension details (#8031)

2026-11-10 18:41:27 +08:00

test_extension_execution_fence.py

fix(tests): isolate backend configuration and nested Make controls (#7567)

2026-10-26 20:53:09 +08:00

test_extension_gateway_wiring.py

feat(extensions): expose incremental run evidence reader (#5405)

2026-09-16 21:18:05 +08:00

test_extension_host_access.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_extension_injection.py

feat(extensions): add middleware plugin foundation (#4636)

2026-08-04 22:33:26 +08:00

test_extension_isolation.py

feat(extensions): add middleware plugin foundation (#4636)

2026-08-04 22:33:26 +08:00

test_extension_list_json.py

feat(extensions): add JSON output for configured extension inventory (#7351)

2026-10-24 07:19:45 +08:00

test_extension_loader.py

feat(extensions): let an out-of-tree extension observe what the agent did (#4863)

2026-08-23 09:57:12 +08:00

test_extension_manager.py

feat(community): add bounded retries for Jina web fetch (#6143)

2026-10-02 21:35:56 +08:00

test_extension_model_invocation.py

feat(extensions): grant bounded host model invocation (#5796)

2026-09-25 15:24:09 +08:00

test_extension_notify_shutdown_cancellation.py

fix(extensions): make notify dispatch admission atomic with shutdown (#7383)

2026-10-24 11:36:06 +08:00

test_extension_ordering.py

feature(skills): keep allowed-tools as compatibility metadata (#6935)

2026-10-20 19:34:28 +08:00

test_extension_package_ci.py

fix(examples): keep the extension example's tests passing as the contract grows (#7364)

2026-10-24 11:07:26 +08:00

test_extension_placement_guarantees.py

feat(authz): middleware-declared tool path Layer 1 now covers tools declared by middlewares (#6105)

2026-10-01 18:26:58 +08:00

test_extension_registry.py

feat(extensions): add gateway contribution points and packaged extension management (#4780)

2026-08-13 23:55:30 +08:00

test_extension_request_evidence.py

feat(extensions): add request-scoped run evidence access (#5727)

2026-09-23 15:25:45 +08:00

test_extension_route_principal.py

feat(extensions): add request-scoped run evidence access (#5727)

2026-09-23 15:25:45 +08:00

test_extension_snapshot_restore.py

fix(extensions): publish a snapshot restore atomically (#6366)

2026-10-06 20:12:39 +08:00

test_extension_stack_wiring.py

fix(agents): treat a null max_total_subagents override as unset (#6088)

2026-09-30 16:10:29 +08:00

test_extension_subagent_lifecycle.py

feat(authz): middleware-declared tool path Layer 1 now covers tools declared by middlewares (#6105)

2026-10-01 18:26:58 +08:00

test_extension_system_model_calls.py

fix(summarization): build the summary model off the Gateway event loop (#7874)

2026-11-04 21:54:47 +08:00

test_extension_task_lifecycle.py

fix(extensions): classify a spent notification budget without a clock recheck (#6469)

2026-10-08 10:22:48 +08:00

test_extension_task_store_runtime.py

feat(authz): middleware-declared tool path Layer 1 now covers tools declared by middlewares (#6105)

2026-10-01 18:26:58 +08:00

test_extensions_config_atomic_write.py

fix(docker): let the Gateway write extensions_config.json in production (#4852)

2026-08-23 15:08:39 +08:00

test_extensions_config_freshness.py

fix(config): revalidate the extensions config singleton by file signature (#6386)

2026-10-07 09:39:26 +08:00

test_extensions_config_raw_writes.py

fix(config): accept UTF-8 BOM in extensions configuration (#5983)

2026-09-28 15:25:06 +08:00

test_extensions_config_signed_read.py

fix(config): bind extensions cache to parsed revision (#6420)

2026-10-07 18:28:48 +08:00

test_external_system_message_boundary.py

fix(security): prevent external system-role message injection (#5651)

2026-09-22 10:38:16 +08:00

test_externalize_failure_cleanup.py

fix(middleware): derive the externalized filename from the tool call id (#6107)

2026-10-06 09:06:33 +08:00

test_fastcrw_tools.py

fix(community): Fail closed on delegated fetch backends to close SSRF gap (#6531)

2026-10-10 18:45:58 +08:00

test_features_router.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_feedback_router.py

fix(feedback): return 409 instead of 500 when feedback is POSTed twice (#8064)

2026-11-10 07:47:01 +08:00

test_feedback.py

fix(feedback): return 409 instead of 500 when feedback is POSTed twice (#8064)

2026-11-10 07:47:01 +08:00

test_feishu_card_delivery.py

feat(channels): Feishu interactive clarification cards (#6670)

2026-10-11 23:58:54 +08:00

test_feishu_card_interaction.py

feat(channels): add thread-scoped discard and lifecycle helpers for Feishu pending card registry (#7357)

2026-10-24 11:41:49 +08:00

test_feishu_card_size.py

fix(channels): keep Feishu cards within the card size limit (#7798)

2026-11-07 15:52:59 +08:00

test_feishu_notifications.py

feat(channels): generalize group notifications and add opt-in task/goal IM notices (#6903)

2026-10-15 10:30:55 +08:00

test_feishu_parser.py

fix(feishu): clear msg.files after receive_file downloads them (#7804)

2026-11-06 11:27:36 +08:00

test_feishu_upload_key_checks.py

fix(channels): surface Feishu upload log_id and missing keys (#7731)

2026-10-31 19:16:29 +08:00

test_file_conversion_cancellation.py

fix(uploads): offload document conversion for every file size (#6924)

2026-10-17 19:58:50 +08:00

test_file_conversion.py

fix(uploads): offload document conversion for every file size (#6924)

2026-10-17 19:58:50 +08:00

test_file_io.py

feat(projects): Projects MVP Phase 2 — instructions, document shelf, promotion, trash (#5443)

2026-09-16 18:46:18 +08:00

test_file_lock_retry.py

fix(lark): retry the Windows install lock instead of failing after ~10s (#6881)

2026-10-15 08:03:10 +08:00

test_file_outline_atx.py

fix(uploads): recognize valid ATX headings in document outlines (#5316)

2026-09-12 12:50:22 +08:00

test_file_outline_bold_wrappers.py

fix(uploads): preserve separate bold spans in outline titles (#7150)

2026-10-20 16:39:33 +08:00

test_file_outline_encoding.py

fix(uploads): handle UTF-8 BOM in document summaries (#5541)

2026-09-19 10:08:09 +08:00

test_file_outline_html_comments.py

fix(uploads): skip HTML comment blocks in document outlines (#6470)

2026-10-08 10:10:07 +08:00

test_file_outline_indented_bold.py

fix(uploads): exclude indented bold lines from outlines (#6194)

2026-10-04 14:54:08 +08:00

test_file_outline_split_bold.py

fix(uploads): exclude punctuated numeric columns from document outlines (#6266)

2026-10-05 13:20:00 +08:00

test_file_outline_text_budget.py

fix(uploads): bound document outline and preview text (#5323)

2026-09-12 14:28:15 +08:00

test_file_outline.py

fix(uploads): exclude fenced code from document outlines (#5281)

2026-09-08 17:06:28 +08:00

test_file_signature.py

fix(tests): write file_signature fixtures as bytes so CRLF never leaks in (#6042)

2026-09-29 21:01:18 +08:00

test_firecrawl_tools.py

fix(community): strip provider API keys before they reach a header (#7981)

2026-11-08 08:44:56 +08:00

test_gateway_checkpoint_mode.py

feat: show real-time context window usage (#3125) (#3183)

2026-07-31 21:57:22 +08:00

test_gateway_config_freshness.py

fix(config): sign the bytes the config cache parsed, not a second read (#5848)

2026-09-25 14:58:06 +08:00

test_gateway_docs_toggle.py

fix(gateway): treat a blank GATEWAY_HOST/GATEWAY_PORT as unset (#5801)

2026-09-24 15:56:38 +08:00

test_gateway_extension_service_lifecycle.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_gateway_health.py

fix(gateway): probe the Redis stream bridge and provisioner in /health/ready (#6447)

2026-10-08 06:56:33 +08:00

test_gateway_imports.py

fix(workspace-changes): keep the package importable as a first import (#6602) (#6608)

2026-10-10 21:27:35 +08:00

test_gateway_knowledge_scope_admission.py

fix(gateway): name the agent problem when run admission rejects agent_name (#8087)

2026-11-12 19:34:10 +08:00

test_gateway_lifespan_shutdown.py

fix(mcp): keep rotating OAuth refresh tokens across restarts and Gateway instances (#7207)

2026-10-21 18:17:29 +08:00

test_gateway_memory_shutdown_cancellation.py

fix(memory): drain shutdown workers across cancellation (#5531)

2026-09-18 17:19:10 +08:00

test_gateway_path_utils.py

test: skip symlink-planting cases where the host cannot create symlinks (#5414)

2026-09-14 11:01:31 +08:00

test_gateway_request_path.py

feat(extensions): add gateway contribution points and packaged extension management (#4780)

2026-08-13 23:55:30 +08:00

test_gateway_run_drain_repeated_cancellation.py

fix(gateway): keep run drain alive across repeated cancellation (#5487)

2026-09-17 21:26:52 +08:00

test_gateway_run_drain_shutdown.py

fix(runtime): drain staged-terminal runs on shutdown before checkpointer teardown (#6620)

2026-10-10 19:59:55 +08:00

test_gateway_run_recovery.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_gateway_runtime_cleanup.py

feat(extensions): add gateway contribution points and packaged extension management (#4780)

2026-08-13 23:55:30 +08:00

test_gateway_sandbox_shutdown.py

fix(sandbox): leave SIGTERM/SIGINT teardown to the Gateway lifespan (#7560)

2026-10-26 20:38:32 +08:00

test_gateway_secret_masking.py

fix(memory): mask backend secrets in the memory config responses (#7665)

2026-10-30 14:53:33 +08:00

test_gateway_services.py

feat(projects): add visible project memory with extraction controls (#8117)

2026-11-12 09:09:44 +08:00

test_gateway_sigterm_delivery.py

fix(deploy): exec the gateway server so SIGTERM reaches uvicorn (#6836)

2026-10-14 15:59:08 +08:00

test_gateway_skill_export.py

test(skills): skip the skill-export capture suite where fd-based walking is unavailable (#5372)

2026-09-12 14:32:05 +08:00

test_gateway_startup.py

fix(deploy): exec the gateway server so SIGTERM reaches uvicorn (#6836)

2026-10-14 15:59:08 +08:00

test_gateway_utils.py

fix(gateway): reject non-ASCII tokens instead of raising in constant-time compares (#6076)

2026-09-30 17:41:11 +08:00

test_gemini_config_example.py

fix(config): correct Gemini official endpoint reasoning example (#6161)

2026-10-02 22:32:21 +08:00

test_generalization_memory_evidence.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_generalization_report_policy.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_generalization_runtime_evidence.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_generalization_tool_evidence.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_github_agents_config.py

…

test_github_app_auth.py

…

test_github_channel.py

…

test_github_dispatcher.py

fix(github): match repository bindings case-insensitively (#7982)

2026-11-08 13:45:59 +08:00

test_github_identity.py

…

test_github_prompts.py

…

test_github_registry.py

…

test_github_token_plumbing.py

fix(sandbox): run scoped env commands concurrently (#7841)

2026-11-09 20:18:30 +08:00

test_github_triggers.py

…

test_github_webhooks.py

fix(gateway): reject non-ASCII tokens instead of raising in constant-time compares (#6076)

2026-09-30 17:41:11 +08:00

test_go_acceptance.py

fix(acceptance): reject all-skipped go test records as evidence (#6957)

2026-10-16 09:10:35 +08:00

test_goal_checkpoint_resume.py

fix(goal): validate goal text and preserve the current goal on message replay (#6685)

2026-10-11 18:39:54 +08:00

test_goal_continuation_pii.py

feat(goal): show why a chat goal stopped and when it was met, and redact the goal evaluator and continuation input (#6556)

2026-10-10 00:20:45 +08:00

test_goal_delivery_consistency.py

fix(goal,artifacts): verify completion and artifact handoff (#7961)

2026-11-07 18:21:49 +08:00

test_goal_evaluator_accounting.py

fix(goal): retain supplied evidence and retry one malformed evaluator verdict (#7345)

2026-10-23 20:29:35 +08:00

test_goal_input_validation.py

fix(goal): validate goal text and preserve the current goal on message replay (#6685)

2026-10-11 18:39:54 +08:00

test_goal_loop_stop_probe.py

fix(runtime): stop Goal continuations after loop hard stops (#7167)

2026-10-20 16:55:13 +08:00

test_goal_operation_progress_worker.py

fix(goal): base no-progress counting on successful operations (#7271)

2026-10-23 00:14:32 +08:00

test_goal_operation_progress.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_goal_pii.py

feat(goal): show why a chat goal stopped and when it was met, and redact the goal evaluator and continuation input (#6556)

2026-10-10 00:20:45 +08:00

test_goal_runtime.py

fix(goal,artifacts): verify completion and artifact handoff (#7961)

2026-11-07 18:21:49 +08:00

test_goal_status.py

fix(goal): fall back gracefully for an unsupported reply locale (#7745)

2026-10-31 19:19:42 +08:00

test_goal_sync_checkpointer_cancellation.py

feat(goal): show why a chat goal stopped and when it was met, and redact the goal evaluator and continuation input (#6556)

2026-10-10 00:20:45 +08:00

test_goal_worker.py

chore(deps): bump langgraph from 1.2.9 to 1.2.14 in /backend (#7703)

2026-10-30 06:42:38 +08:00

test_groundroute_response_shapes.py

feat(community): migrate GroundRoute tools to httpx.AsyncClient (#7183)

2026-10-21 23:08:27 +08:00

test_groundroute_tools.py

feat(community): migrate GroundRoute tools to httpx.AsyncClient (#7183)

2026-10-21 23:08:27 +08:00

test_guardrail_middleware.py

feat(extensions): let an out-of-tree extension observe what the agent did (#4863)

2026-08-23 09:57:12 +08:00

test_harness_boundary.py

…

test_harness_guard_middleware.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_harness_packaging.py

feat(sandbox): add OpenSandbox provider (#4877)

2026-08-23 15:46:10 +08:00

test_helm_credentials_key.py

fix(security): add DEER_FLOW_CREDENTIALS_KEY and wire the channel credentials cipher (#6611)

2026-10-10 20:51:09 +08:00

test_helm_database_secret_precedence.py

fix(helm): give each Secret pair one precedence chain (#7291)

2026-10-23 00:26:48 +08:00

test_helm_extensions_config_writable.py

fix(docker): let the Gateway write extensions_config.json in production (#4852)

2026-08-23 15:08:39 +08:00

test_helm_image_pull_secrets.py

fix(helm): apply image.pullSecrets to the nginx Deployment (#8123)

2026-11-11 11:10:31 +08:00

test_helm_init_containers.py

fix(helm): make the gateway init containers' image and resources conf… (#8161)

2026-11-12 16:44:42 +08:00

test_helm_memory_retrieval_index.py

fix(memory): keep the retrieval index Pod-local and refresh scopes written by peers (#6494)

2026-10-08 21:20:45 +08:00

test_helm_multi_replica_prereqs.py

fix(deploy): wire the multi-replica prerequisites into the Helm chart and compose (#6347)

2026-10-06 11:21:51 +08:00

test_helm_provisioner_api_key.py

fix(helm): wire PROVISIONER_API_KEY through the chart's app Secret so a default install can create sandboxes (#6365)

2026-10-07 07:10:05 +08:00

test_helm_provisioner_lark_cli_images.py

fix(helm): plumb lark-cli runtime images into the provisioner (#5835)

2026-09-30 09:16:00 +08:00

test_helm_provisioner_replicas.py

fix(helm): let the sandbox provisioner run with several replicas (#6543)

2026-10-09 18:26:23 +08:00

test_helm_redis_existing_secret.py

fix(helm): give each Secret pair one precedence chain (#7291)

2026-10-23 00:26:48 +08:00

test_history_batch_queries.py

fix(events): rebase RunEvent snapshot isolation onto current main (#7423)

2026-10-28 20:59:10 +08:00

test_history_seed_fencing.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_history_seed_gateway.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_hitl_approval_api.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_hitl_resolution_history.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_hitl_task_delegation_ledger.py

fix(agents): keep the delegation ledger exact across HITL approval and reused call ids (#8128)

2026-11-12 19:46:58 +08:00

test_honcho_hidden_messages.py

fix(memory): exclude hidden framework messages from Honcho writes (#7159)

2026-10-22 16:51:47 +08:00

test_honcho_incremental_capture.py

fix(memory): avoid replaying Honcho checkpoint history (#7687)

2026-10-30 07:33:41 +08:00

test_honcho_memory_backend.py

fix(memory): avoid replaying Honcho checkpoint history (#7687)

2026-10-30 07:33:41 +08:00

test_honcho_search_metadata_policy.py

fix(memory): apply Honcho read policies to malformed search metadata (#7890)

2026-11-05 07:04:15 +08:00

test_human_input.py

…

test_im_notification_preferences.py

feat(channels): generalize group notifications and add opt-in task/goal IM notices (#6903)

2026-10-15 10:30:55 +08:00

test_image_download_limit.py

fix(sandbox): enforce image byte limits during downloads (#6712)

2026-10-12 18:49:41 +08:00

test_image_result_idna_hosts.py

fix(image-search): keep the source page URL in DuckDuckGo and Serper results (#6915)

2026-10-15 14:56:46 +08:00

test_image_result_url_safety.py

feat(community): add SpecStream web search and fetch provider (#7968)

2026-11-09 20:32:22 +08:00

test_image_search_errors.py

fix(image-search): distinguish DDG failures from empty results (#6680)

2026-10-21 22:06:16 +08:00

test_image_search.py

fix(image-search): keep the source page URL in DuckDuckGo and Serper results (#6915)

2026-10-15 14:56:46 +08:00

test_inbound_dedupe.py

fix(gateway): gate declared multi-instance deployments and require the redis stream bridge (#6328)

2026-10-05 22:34:57 +08:00

test_infoquest_client.py

fix(infoquest): contain malformed search payloads instead of crashing on them (#6932)

2026-10-17 09:00:50 +08:00

test_infoquest_config_timeout_coercion.py

fix(community): coerce InfoQuest crawl timeouts before comparing them (#5883)

2026-09-28 15:50:42 +08:00

test_infoquest_fetch_content.py

fix(infoquest): reject invalid extracted fetch content (#6760)

2026-10-19 06:59:40 +08:00

test_infoquest_http_timeout.py

feat(community): migrate infoquest client to httpx.AsyncClient (#5782)

2026-09-25 20:58:17 +08:00

test_infoquest_result_url_safety.py

fix(infoquest): screen result URLs through the shared public-URL owner (#7031)

2026-10-18 09:55:27 +08:00

test_initialize_admin.py

fix(auth): claim the first admin atomically instead of counting first (#5776)

2026-09-24 16:30:36 +08:00

test_inline_skill_references.py

fix(skills): keep a slash skill activation when the model call is retried (#6506)

2026-10-08 19:44:52 +08:00

test_input_polish_router.py

fix(utils): skip malformed response block types (#6614)

2026-10-11 08:25:53 +08:00

test_input_sanitization_middleware.py

fix(agents): drop empty typed text blocks from user content (#8066)

2026-11-10 08:04:43 +08:00

test_inspect_run_status.py

feat(agent): add read-only run status introspection (phase 1) (#7297)

2026-10-23 22:06:00 +08:00

test_interaction_policy.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_internal_auth.py

…

test_interrupt_serialization.py

…

test_invoke_acp_agent_tool.py

fix(acp): fail fast when an ACP agent exits and drain its stderr (#7354)

2026-10-23 22:30:26 +08:00

test_jev_classify_extension.py

feat(plugins): add standalone Jev text classification example (#5735)

2026-09-24 16:36:30 +08:00

test_jev_context_extension.py

fix(summarization): cover all selected history before compaction (#6918)

2026-10-16 09:41:20 +08:00

test_jev_result_screening_extension.py

fix(examples): harden the Jev fetched-content screening example (#5858)

2026-09-25 19:58:36 +08:00

test_jev_screening_pipeline.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_jev_screening_policy.py

feat(examples): add opt-in advisory fetched-content screening (#5833)

2026-09-25 14:38:59 +08:00

test_jina_client.py

feat(jina): add bounded crawl completion diagnostics (#6504)

2026-10-27 10:10:26 +08:00

test_jina_diagnostics.py

feat(jina): add bounded crawl completion diagnostics (#6504)

2026-10-27 10:10:26 +08:00

test_jina_request_admission.py

fix(community): build remaining search clients off the event loop (#7933)

2026-11-09 10:08:59 +08:00

test_jina_response_limit.py

fix(jina): classify retry budget expiry reliably on Windows (#6789)

2026-10-13 22:26:28 +08:00

test_jina_retries.py

fix(jina): classify retry budget expiry reliably on Windows (#6789)

2026-10-13 22:26:28 +08:00

test_jina_retry_after.py

fix(models): keep Claude retries behind request admission (#6545)

2026-10-09 21:55:42 +08:00

test_json_acceptance.py

feat: add bounded JSON syntax acceptance criteria (#5947)

2026-09-28 15:13:34 +08:00

test_json_integer_matching.py

fix(persistence): match integer metadata without overflowing stored values (#6000)

2026-10-07 14:34:24 +08:00

test_json_think_tag_stripping.py

fix(parsing): keep literal think tags inside JSON string values (#7907)

2026-11-06 21:19:52 +08:00

test_jsonify_tools.py

feat(community): add Jsonify dataset rows tool (#7253)

2026-10-22 19:23:56 +08:00

test_jsonl_event_store_async_io.py

fix(threads): clean persisted records safely on thread deletion (#5535)

2026-09-18 18:32:42 +08:00

test_jsonl_event_store_cancellation.py

fix(events): preserve JSONL sequences after run deletion and restart (#6546)

2026-10-10 08:00:47 +08:00

test_jsonl_event_store_lock_lifecycle.py

fix(events): keep JSONL lock generation stable across deletion (#5455)

2026-09-16 15:18:29 +08:00

test_jsonl_event_store_seq_watermark.py

fix(events): preserve JSONL sequences after run deletion and restart (#6546)

2026-10-10 08:00:47 +08:00

test_jsonl_event_store_tail_recovery.py

fix(events): preserve JSONL framing after interrupted appends (#6520)

2026-10-10 00:02:23 +08:00

test_jsonl_event_store_unicode.py

fix(events): preserve Unicode separators in JSONL event records (#5429)

2026-09-14 18:24:51 +08:00

test_knowledge_center_extension.py

feat(knowledge): add optional ingestion and status center (#7518)

2026-11-02 10:42:21 +08:00

test_knowledge_citation_budget.py

fix(knowledge): scope ragflow link cleanup to its native citation namespace (#6886)

2026-10-15 09:32:03 +08:00

test_knowledge_contract_live.py

feat(knowledge): unify read-only retrieval and source contracts (phase 1) (#6716)

2026-10-14 14:16:08 +08:00

test_knowledge_contract.py

fix(knowledge): retain later evidence that fits the output budget (#7942)

2026-11-07 16:01:47 +08:00

test_knowledge_management_extension_live.py

feat(knowledge): add optional ingestion and processing extension (#7293)

2026-10-24 08:19:02 +08:00

test_knowledge_management_extension.py

fix(knowledge): accept case-insensitive upload media types (#7397)

2026-10-25 08:47:15 +08:00

test_knowledge_phase1_live.py

feat(knowledge): add independent Wiki and entity relation retrieval tools (#7171)

2026-10-22 16:54:58 +08:00

test_knowledge_platform_extension.py

feat(knowledge): add optional platform connections and hierarchical spaces (phase 3) (#7417)

2026-10-25 19:52:31 +08:00

test_knowledge_provider_router.py

feat(knowledge): decouple scope and read-only catalogs (phase 2) (#6904)

2026-10-15 15:10:39 +08:00

test_knowledge_provider.py

feat(knowledge): decouple scope and read-only catalogs (phase 2) (#6904)

2026-10-15 15:10:39 +08:00

test_knowledge_retrieval_tools.py

feat(knowledge): add independent Wiki and entity relation retrieval tools (#7171)

2026-10-22 16:54:58 +08:00

test_knowledge_router.py

feat(knowledge): decouple scope and read-only catalogs (phase 2) (#6904)

2026-10-15 15:10:39 +08:00

test_knowledge_scope_middleware.py

feat(knowledge): add per-message RAGFlow retrieval scope (#5238)

2026-09-18 16:59:31 +08:00

test_knowledge_scope.py

feat(knowledge): add per-message RAGFlow retrieval scope (#5238)

2026-09-18 16:59:31 +08:00

test_label_declarations.py

fix(ci): label every harness tree as backend (#8029)

2026-11-09 18:28:54 +08:00

test_langgraph_auth.py

feat(knowledge): decouple scope and read-only catalogs (phase 2) (#6904)

2026-10-15 15:10:39 +08:00

test_langgraph_graph_entrypoint.py

fix: restore standalone LangGraph Studio compatibility (#4760)

2026-08-15 21:20:34 +08:00

test_langgraph_studio_lifespan.py

fix: support Studio file-based app loading (#4838)

2026-08-16 23:54:06 +08:00

test_langgraph_studio_routes.py

test(studio): stop the dev server gracefully so its persistence flush lands on Windows (#6197)

2026-10-02 22:45:26 +08:00

test_lark_auth_lifecycle_failures.py

fix(harness): complete Lark device auth via a single-flight login run (#7182)

2026-10-21 21:00:35 +08:00

test_lark_auth_singleflight.py

fix(harness): complete Lark device auth via a single-flight login run (#7182)

2026-10-21 21:00:35 +08:00

test_lark_broker_image.py

fix(docker): bundle Lark broker runtime helpers (#7542)

2026-10-27 00:19:23 +08:00

test_lark_broker.py

fix(lark): match broker subcommand denylist through separate option values (#6212)

2026-10-03 15:58:01 +08:00

test_lark_cli_atomic_publish.py

docs(lark): pin atomic publish cleanup so it cannot mask the error (#7329)

2026-10-24 10:23:31 +08:00

test_lark_cli_install_lock.py

fix(lark): retry the Windows install lock instead of failing after ~10s (#6881)

2026-10-15 08:03:10 +08:00

test_lark_cli_integration.py

fix(skills): sniff executable binaries past leading filler bytes (#7081)

2026-10-22 08:43:42 +08:00

test_lark_cli_subprocess_encoding.py

fix(lark): keep Windows SID lookup working with non-ASCII account names (#7845)

2026-11-05 15:09:13 +08:00

test_lark_credential_tree_churn.py

fix(harness): complete Lark device auth via a single-flight login run (#7182)

2026-10-21 21:00:35 +08:00

test_lark_install_cancellation.py

fix(integrations): drain Lark install across cancellation (#6408)

2026-10-07 17:02:23 +08:00

test_lark_shim_atomic.py

test: fix six Windows-host failures across sandbox, read_file, lark shim, skill review, and extension checks (#6787)

2026-10-14 06:19:43 +08:00

test_lark_skill_manifest_atomic.py

fix(lark): publish the skill file and manifest atomically (#6683)

2026-10-11 17:46:29 +08:00

test_layer2_tool_provenance.py

feat(authz): middleware-declared tool path Layer 1 now covers tools declared by middlewares (#6105)

2026-10-01 18:26:58 +08:00

test_lazy_aio_skill_projection.py

fix(sandbox): defer fresh AIO skill-policy acquisition (#7782)

2026-11-05 15:37:13 +08:00

test_lead_agent_model_resolution.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_lead_agent_prompt.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_lead_agent_skills.py

feature(skills): keep allowed-tools as compatibility metadata (#6935)

2026-10-20 19:34:28 +08:00

test_lead_prompt_script_guidance.py

fix(agent,goal): stop coaching scripts when no bash tool is bound, and show the goal evaluator Human Input Card answers (#6082)

2026-09-30 17:54:42 +08:00

test_lead_token_budget.py

fix: include completed child usage in lead budget checks (#6218)

2026-10-04 21:14:35 +08:00

test_lightrag_client.py

feat(knowledge): add read-only LightRAG retrieval, fixes #5208 (#5209)

2026-09-06 10:21:58 +08:00

test_lightrag_relations_extension.py

feat(knowledge): add independent Wiki and entity relation retrieval tools (#7171)

2026-10-22 16:54:58 +08:00

test_lightrag_tools.py

fix(community): reject booleans in the knowledge_search provider settings (#7042)

2026-10-20 23:17:51 +08:00

test_list_uploaded_files_tool.py

fix(uploads): preserve separate bold spans in outline titles (#7150)

2026-10-20 16:39:33 +08:00

test_llm_call_telemetry.py

feat(runtime): add per-LLM-call telemetry and summarization no-op event (#6236)

2026-10-04 14:52:04 +08:00

test_llm_error_handling_middleware.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_load_memory_sample.py

fix(memory): keep sample import backups unique per run (#7418)

2026-10-24 21:50:27 +08:00

test_local_bash_tool_loading.py

…

test_local_command_path_spaces.py

fix(sandbox): preserve mapped path spaces in PowerShell commands (#7245)

2026-10-22 14:49:47 +08:00

test_local_dev_loopback_bind.py

test(backend): fix three more Windows-host test failures (#7008)

2026-10-18 10:25:26 +08:00

test_local_grep_io_errors.py

fix(tests): isolate backend configuration and nested Make controls (#7567)

2026-10-26 20:53:09 +08:00

test_local_grep_long_lines.py

fix(sandbox): search long lines for literal grep patterns (#6969)

2026-10-18 20:58:35 +08:00

test_local_registration_gate.py

…

test_local_sandbox_atomic_writes.py

fix(sandbox): keep document bytes when write_file translates paths (#7462)

2026-10-25 15:13:41 +08:00

test_local_sandbox_command_timeout.py

fix(sandbox): use saved process group id on timeout (#7353)

2026-10-23 22:35:10 +08:00

test_local_sandbox_content_path_translation.py

fix(sandbox): keep document bytes when write_file translates paths (#7462)

2026-10-25 15:13:41 +08:00

test_local_sandbox_encoding.py

fix(sandbox): decode cmd.exe output with the ANSI code page under UTF-8 mode (#6777)

2026-10-13 14:27:26 +08:00

test_local_sandbox_path_regex_cache.py

fix(sandbox): reverse-resolve forward-slash spellings of Windows host paths (#5373)

2026-09-14 07:30:34 +08:00

test_local_sandbox_pipe_fd_lifecycle.py

fix(sandbox): close pipe fds once after post-spawn failures (#7430)

2026-10-25 11:49:44 +08:00

test_local_sandbox_provider_mounts.py

test: fix six Windows-host failures across sandbox, read_file, lark shim, skill review, and extension checks (#6787)

2026-10-14 06:19:43 +08:00

test_local_sandbox_skill_search.py

fix(sandbox): search the skills root across category mounts (#7338)

2026-10-23 21:41:24 +08:00

test_local_sandbox_virtual_path_contract.py

fix(sandbox): let the local ls tool list the /mnt/user-data root (#6991)

2026-10-18 07:48:06 +08:00

test_local_skill_storage_write.py

test: skip symlink-planting cases where the host cannot create symlinks (#5414)

2026-09-14 11:01:31 +08:00

test_logging_config.py

fix(logging): redact credential-bearing header values in urllib3's header-parse dump (#5752)

2026-09-26 15:06:48 +08:00

test_logging_level_from_config.py

…

test_login_throttle_config.py

fix(auth): count login lockouts in the database across Gateway replicas (#6501)

2026-10-08 22:35:19 +08:00

test_login_throttle_store.py

fix(auth): count login lockouts in the database across Gateway replicas (#6501)

2026-10-08 22:35:19 +08:00

test_loop_detection_config.py

fix(config): reject boolean loop detection thresholds (#6017)

2026-10-02 07:30:10 +08:00

test_loop_detection_middleware.py

fix(runtime): present outputs before a loop wrap-up and explain step-limit stops (#7588)

2026-10-27 10:34:34 +08:00

test_loop_detection_stop_reason.py

…

test_make_clean_guard.py

fix(make): name what make clean deletes and refuse under a live gateway (#6351)

2026-10-06 15:32:46 +08:00

test_make_install.py

fix(setup): run pre-commit through uv and clarify Node advice (#5767)

2026-09-23 17:58:00 +08:00

test_make_test_parallel.py

fix(tests): isolate backend configuration and nested Make controls (#7567)

2026-10-26 20:53:09 +08:00

test_makefile_shell_script_invocation.py

fix(scripts): make start-daemon wrapper use production mode (#7261)

2026-10-22 15:43:19 +08:00

test_managed_deepseek_live.py

fix(models): support official DeepSeek managed profiles (#5718)

2026-09-22 17:53:21 +08:00

test_managed_deepseek.py

fix(managed-models): map DeepSeek "minimal" effort to "low" (#6717)

2026-10-19 15:45:56 +08:00

test_managed_models.py

feat(models): register managed models with provider presets (#6757)

2026-10-13 08:14:23 +08:00

test_managed_moonshot.py

feat(models): add managed Kimi K3.1 Pro capabilities (#7566)

2026-10-27 14:57:29 +08:00

test_managed_openai_gpt6.py

fix(models): route managed OpenAI GPT-6 presets through Responses (#7870)

2026-11-05 14:30:42 +08:00

test_managed_presets_live.py

feat(models): register managed models with provider presets (#6757)

2026-10-13 08:14:23 +08:00

test_managed_provider_presets.py

feat(models): add StepFun provider preset (#7988)

2026-11-08 09:49:43 +08:00

test_managed_subagent_create_race.py

fix(subagents): prevent concurrent file-backed creates from overwriting definitions (#8132)

2026-11-12 14:39:25 +08:00

test_managed_subagent_file_probe.py

fix(subagents): prevent concurrent file-backed creates from overwriting definitions (#8132)

2026-11-12 14:39:25 +08:00

test_managed_subagent_registry.py

feat: add managed subagents and delegation scopes (#4887)

2026-08-24 11:04:23 +08:00

test_managed_subagent_store.py

fix(subagents): reject Windows reserved device names in managed subagent creation (#7959)

2026-11-08 21:55:46 +08:00

test_mcp_artifact_capture.py

fix(lark): retry the Windows install lock instead of failing after ~10s (#6881)

2026-10-15 08:03:10 +08:00

test_mcp_audio_content.py

fix(mcp): reject unsupported inline audio results (#7628)

2026-10-28 14:00:34 +08:00

test_mcp_binding_fencing.py

fix(mcp): preserve active calls during session eviction (#6900)

2026-10-14 22:55:43 +08:00

test_mcp_blob_missing_mime_type.py

fix(mcp): degrade a blob without mimeType instead of failing the tool call (#7800)

2026-11-05 21:40:32 +08:00

test_mcp_cache_discovery.py

feat(mcp): reuse unchanged per-server tool discovery results (#6795)

2026-10-14 08:44:21 +08:00

test_mcp_cache_reconciliation.py

feat(mcp): reuse unchanged per-server tool discovery results (#6795)

2026-10-14 08:44:21 +08:00

test_mcp_cache_tool_assembly.py

fix(mcp): invalidate cache only for effective MCP config changes (#5750)

2026-09-24 17:19:01 +08:00

test_mcp_cache.py

feat(mcp): reuse unchanged per-server tool discovery results (#6795)

2026-10-14 08:44:21 +08:00

test_mcp_client_config.py

fix(mcp): honor configured stdio working directories (#5643)

2026-09-22 11:15:06 +08:00

test_mcp_config_error_details.py

fix(mcp): keep host paths out of the MCP config mutation 500 details (#7275)

2026-10-23 07:20:21 +08:00

test_mcp_config_secrets.py

fix(skills): create a missing extensions_config.json in the project root (#7048)

2026-10-21 22:43:49 +08:00

test_mcp_context_headers.py

feat(mcp): manage servers from Settings (#5022)

2026-09-01 23:24:49 +08:00

test_mcp_cross_worker_generation.py

fix(mcp): preserve server binding history across gateway workers (#6617)

2026-10-11 11:45:28 +08:00

test_mcp_custom_interceptors.py

refactor(mcp): expose per-server tool discovery results (#6734)

2026-10-13 08:38:36 +08:00

test_mcp_cwd.py

fix(mcp): keep a tool argument named runtime out of LangGraph's runtime injection (#7677)

2026-11-01 12:45:14 +08:00

test_mcp_file_migration.py

fix(mcp): preserve remote URLs during local file rewriting (#6878)

2026-10-17 08:13:35 +08:00

test_mcp_header_names.py

fix(mcp): reject credentials that cannot travel as HTTP header values (#5066)

2026-08-31 15:07:30 +08:00

test_mcp_lifecycle_invalid.py

feat(mcp): reuse unchanged per-server tool discovery results (#6795)

2026-10-14 08:44:21 +08:00

test_mcp_lifecycle_writers.py

fix(mcp): keep rotating OAuth refresh tokens across restarts and Gateway instances (#7207)

2026-10-21 18:17:29 +08:00

test_mcp_lifecycle.py

fix(mcp): preserve server binding history across gateway workers (#6617)

2026-10-11 11:45:28 +08:00

test_mcp_oauth_token_store.py

fix(mcp): keep rotating OAuth refresh tokens across restarts and Gateway instances (#7207)

2026-10-21 18:17:29 +08:00

test_mcp_oauth.py

test(mcp): cover failed-owner retry across event loops (#7458)

2026-10-25 11:32:39 +08:00

test_mcp_per_server_discovery.py

fix(mcp): drop cross-server duplicate bound tool names instead of silently shadowing (#8135)

2026-11-12 19:07:32 +08:00

test_mcp_routing_auto_promote.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_mcp_routing_config.py

…

test_mcp_routing_index_normalization.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_mcp_routing_metadata.py

…

test_mcp_routing_prompt.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_mcp_scope.py

fix(mcp): close thread-scoped MCP sessions on thread deletion (#5956)

2026-09-29 16:53:18 +08:00

test_mcp_session_pool_active_calls.py

fix(mcp): preserve active calls during session eviction (#6900)

2026-10-14 22:55:43 +08:00

test_mcp_session_pool_loop_isolation.py

fix(mcp): preserve active calls during session eviction (#6900)

2026-10-14 22:55:43 +08:00

test_mcp_session_pool.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_mcp_session_timeouts.py

fix(mcp): bring-up has no timeout and externalized tool outputs are counted as undelivered artifacts (#4657)

2026-08-05 08:56:18 +08:00

test_mcp_sync_wrapper.py

fix(mcp): keep a tool argument named runtime out of LangGraph's runtime injection (#7677)

2026-11-01 12:45:14 +08:00

test_mcp_task_config.py

feat(mcp): add ordinary durable task driver (#4690)

2026-08-15 14:26:38 +08:00

test_mcp_task_lease_lifecycle.py

fix(mcp): retain durable control claims through slow calls and cancellation (#6780)

2026-10-21 22:03:21 +08:00

test_mcp_task_models.py

fix(mcp): scope sessions and task access by thread incarnation (#5556)

2026-09-23 08:33:20 +08:00

test_mcp_task_oauth.py

fix(mcp): keep rotating OAuth refresh tokens across restarts and Gateway instances (#7207)

2026-10-21 18:17:29 +08:00

test_mcp_task_ordinary_driver.py

fix(mcp): isolate personal connections from deployment configuration (#5966)

2026-09-28 16:02:34 +08:00

test_mcp_task_ordinary_e2e.py

fix(mcp): restore task owners for background credential selection (#5870)

2026-09-26 15:37:52 +08:00

test_mcp_task_postgres.py

fix(mcp): skip tasks a cancel released while the poll claim was in flight (#6859)

2026-10-15 09:42:46 +08:00

test_mcp_task_repository.py

fix(mcp): fence notification claims on SQLite (#7859)

2026-11-05 14:19:05 +08:00

test_mcp_task_runtime_config.py

fix(mcp): invalidate cache only for effective MCP config changes (#5750)

2026-09-24 17:19:01 +08:00

test_mcp_task_service.py

fix(mcp): drain compensation work during service shutdown (#7662)

2026-10-29 14:40:09 +08:00

test_mcp_task_tool_caller.py

fix(mcp): fail durable tasks whose connection no longer resolves (#7058)

2026-10-19 11:32:28 +08:00

test_mcp_task_tool_wrapping.py

fix(mcp): keep a tool argument named runtime out of LangGraph's runtime injection (#7677)

2026-11-01 12:45:14 +08:00

test_mcp_task_toolset_config.py

feat(mcp): add ordinary durable task driver (#4690)

2026-08-15 14:26:38 +08:00

test_mcp_tasks_router.py

feat(mcp): filter background tasks by status (#6527)

2026-10-10 08:53:51 +08:00

test_mcp_tasks_status_filter.py

feat(mcp): filter background tasks by status (#6527)

2026-10-10 08:53:51 +08:00

test_mcp_tool_name_prefix.py

fix(mcp): isolate pooled sessions by ownership domain (#6133)

2026-10-06 09:08:25 +08:00

test_mcp_tool_name_validation.py

fix(mcp): drop cross-server duplicate bound tool names instead of silently shadowing (#8135)

2026-11-12 19:07:32 +08:00

test_mcp_user_scoped_auth.py

feat(mcp): manage servers from Settings (#5022)

2026-09-01 23:24:49 +08:00

test_mem0_context_record_ids.py

fix(memory): honor Mem0 read policies during context deduplication (#7561)

2026-10-26 19:44:01 +08:00

test_mem0_memory_backend.py

feat(memory): scope management API by agent (#5565)

2026-09-30 16:50:07 +08:00

test_mem0_record_policy.py

fix(memory): apply Mem0 read policies to record conversion failures (#7307)

2026-10-23 17:57:14 +08:00

test_mem0_response_policy.py

fix(memory): honor Mem0 failure policies for malformed JSON responses (#7202)

2026-10-23 16:58:19 +08:00

test_memory_admission_depth.py

fix(memory): avoid recursive tool-argument admission (#7928)

2026-11-06 21:24:57 +08:00

test_memory_cancel_by_agent.py

fix(memory): cancel buffered extraction when agent is deleted or cleared (#5123)

2026-09-03 08:00:25 +08:00

test_memory_confidence_overflow.py

fix(memory): tolerate unbounded stored fact confidence (#7764)

2026-11-01 15:04:16 +08:00

test_memory_consolidation.py

fix(memory): prevent task-scoped data from entering long-term memory (#4604)

2026-08-01 08:39:28 +08:00

test_memory_documentation.py

fix(provisioner): keep POSIX hostPath values POSIX on Windows hosts (#7905)

2026-11-06 11:19:13 +08:00

test_memory_emergency_backlog.py

fix(memory): preserve consecutive pre-compaction snapshots (#7152)

2026-10-20 10:24:16 +08:00

test_memory_emergency_snapshots.py

fix(memory): preserve consecutive pre-compaction snapshots (#7152)

2026-10-20 10:24:16 +08:00

test_memory_eviction.py

fix(memory): rank capacity eviction per record, not per fact_id (#7454)

2026-10-25 13:20:15 +08:00

test_memory_fact_dedup.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_memory_get_tool.py

feat(memory): add scoped fact lookup by ID (#6443)

2026-10-08 09:25:12 +08:00

test_memory_import.py

fix(memory): reject duplicate fact IDs during import (#8151)

2026-11-12 11:42:55 +08:00

test_memory_index_startup_failures.py

fix(memory): preserve retrieval indexes on operational startup failures (#8084)

2026-11-10 15:14:52 +08:00

test_memory_manager_interface.py

feat(memory): add opt-in relevance-aware retrieval ranking (#5251)

2026-09-18 11:32:04 +08:00

test_memory_manager_pluggable.py

…

test_memory_markdown_migration_cli.py

…

test_memory_middleware.py

feature(gateway): issue request trace ids unconditionally (#5119)

2026-09-01 16:49:39 +08:00

test_memory_normalize.py

feat(memory): add cognitiveStyle for collaboration preferences (#3182)

2026-09-23 18:29:12 +08:00

test_memory_pii_redaction.py

fix(tests): isolate backend configuration and nested Make controls (#7567)

2026-10-26 20:53:09 +08:00

test_memory_prescreen_eval_script.py

feat(memory): add Jev pre-screening and signal classification over a shared TypeSafe client (#5906)

2026-09-27 20:28:05 +08:00

test_memory_prescreen.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_memory_prompt_injection.py

fix(memory): enforce the token budget when truncating summaries (#7709)

2026-10-30 07:32:51 +08:00

test_memory_queue_deadlines.py

fix(memory): prevent cross-conversation debounce starvation (#6672)

2026-10-11 17:16:25 +08:00

test_memory_queue_user_isolation.py

fix(memory): prevent cross-conversation debounce starvation (#6672)

2026-10-11 17:16:25 +08:00

test_memory_queue.py

fix(memory): prevent cross-conversation debounce starvation (#6672)

2026-10-11 17:16:25 +08:00

test_memory_relevance_retrieval.py

fix(memory): drop punctuation tokens from jieba relevance ranking (#6388)

2026-10-07 06:58:59 +08:00

test_memory_relevance_review.py

feat(memory): add opt-in relevance-aware retrieval ranking (#5251)

2026-09-18 11:32:04 +08:00

test_memory_retrieval_adapter.py

fix(memory): recall CJK sub-phrases when jieba is not installed (#8022)

2026-11-10 09:50:46 +08:00

test_memory_retrieval_index_local.py

fix(memory): keep the retrieval index Pod-local and refresh scopes written by peers (#6494)

2026-10-08 21:20:45 +08:00

test_memory_router.py

fix(memory): reject duplicate fact IDs during import (#8151)

2026-11-12 11:42:55 +08:00

test_memory_run_event_snapshot_isolation.py

fix(events): rebase RunEvent snapshot isolation onto current main (#7423)

2026-10-28 20:59:10 +08:00

test_memory_run_store_replacement_index.py

fix(runs): move thread index membership on snapshot replacement (#7622)

2026-10-28 20:47:01 +08:00

test_memory_scope_gate.py

fix(memory): prevent task-scoped data from entering long-term memory (#4604)

2026-08-01 08:39:28 +08:00

test_memory_search.py

…

test_memory_staleness_review.py

feat(memory): add hybrid fact eviction policy (#4789)

2026-08-17 08:20:42 +08:00

test_memory_storage_markdown.py

fix(memory): treat facts deleted during unlocked DeerMem scans as removed (#6255)

2026-10-04 12:37:33 +08:00

test_memory_storage_user_isolation.py

…

test_memory_storage.py

fix(memory): quarantine unreadable memory summaries (#7076)

2026-10-20 11:25:01 +08:00

test_memory_stream_payload_isolation.py

fix(streaming): isolate in-memory replay payloads (#7644)

2026-10-31 08:15:24 +08:00

test_memory_stream_reconnect_boundary.py

fix(streaming): avoid false replay gaps after cursor eviction (#6812)

2026-10-19 15:27:56 +08:00

test_memory_stream_retirement.py

fix(streaming): avoid false replay gaps after cursor eviction (#6812)

2026-10-19 15:27:56 +08:00

test_memory_thread_meta_isolation.py

feat(persistence): add expand-phase thread incarnation storage (#5216)

2026-09-09 15:52:09 +08:00

test_memory_tool_call_intent.py

fix(memory): exclude invalid and raw assistant tool calls (#6379)

2026-10-06 20:43:27 +08:00

test_memory_tool_call_redaction.py

fix(memory): redact invalid and legacy tool-call arguments (#6387)

2026-10-07 07:23:56 +08:00

test_memory_tools.py

feat(hitl): add human-in-the-loop approval for high-risk tool calls (#7979)

2026-11-09 09:52:35 +08:00

test_memory_update_normalization.py

fix(memory): drop unusable numbers in stale extensions and consolidation confidence (#7442)

2026-10-25 16:16:09 +08:00

test_memory_updater_user_isolation.py

…

test_memory_updater.py

fix(memory): reject duplicate fact ids in imports regardless of entry order (#8153)

2026-11-12 19:23:44 +08:00

test_memory_upload_filtering.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_message_bus_outbound_lifecycle.py

fix(channels): snapshot outbound listeners per message (#6502)

2026-10-08 20:22:28 +08:00

test_message_processing_signals.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_message_processing.py

feat(memory): add hybrid fact eviction policy (#4789)

2026-08-17 08:20:42 +08:00

test_message_provenance.py

fix(security): prevent external system-role message injection (#5651)

2026-09-22 10:38:16 +08:00

test_middleware_declared_tools.py

feat(authz): middleware-declared tool path Layer 1 now covers tools declared by middlewares (#6105)

2026-10-01 18:26:58 +08:00

test_middleware_documentation.py

fix(subagents): report model output length caps (#7355)

2026-10-23 21:42:11 +08:00

test_middleware_release_policy.py

fix(agent): prevent todo reminders from resuming runs after hard stops (#7955)

2026-11-07 21:43:16 +08:00

test_migration_0004_run_ownership_dedupe.py

feat(persistence): add expand-phase thread incarnation storage (#5216)

2026-09-09 15:52:09 +08:00

test_migration_0007_scheduled_run_active_dedupe.py

feat(persistence): add expand-phase thread incarnation storage (#5216)

2026-09-09 15:52:09 +08:00

test_migration_0009_webhook_dedupe.py

…

test_migration_0015_scheduled_task_enqueue.py

feat(persistence): add expand-phase thread incarnation storage (#5216)

2026-09-09 15:52:09 +08:00

test_migration_0017_personal_access_tokens.py

feat(auth): add personal access tokens for programmatic API access (#5041)

2026-08-29 23:50:45 +08:00

test_migration_0018_oauth_identity_pg_partial.py

fix(auth): correct OAuth conflict error message + validate multi-worker Postgres claim with real concurrency benchmark (#5026)

2026-09-03 08:17:26 +08:00

test_migration_0019_0020_projects.py

feat(projects): add visible project memory with extraction controls (#8117)

2026-11-12 09:09:44 +08:00

test_migration_0019_thread_incarnations.py

feat(persistence): add expand-phase thread incarnation storage (#5216)

2026-09-09 15:52:09 +08:00

test_migration_0021_batch_acceptance.py

fix(scheduler): reconcile stuck once tasks from committed run outcome (#5035)

2026-09-12 07:35:07 +08:00

test_migration_0022_scheduled_occurrence_seq.py

feat(scheduler): create conversation schedules and support agent self-stop (#6229)

2026-10-04 06:46:13 +08:00

test_migration_0023_run_change_seq.py

feat(scheduler): create conversation schedules and support agent self-stop (#6229)

2026-10-04 06:46:13 +08:00

test_migration_0024_project_documents.py

feat(projects): best-effort LLM summaries for shelf documents (#6581)

2026-10-10 07:11:02 +08:00

test_migration_0025_repair_run_change_seq.py

fix(auth): count login lockouts in the database across Gateway replicas (#6501)

2026-10-08 22:35:19 +08:00

test_migration_0026_mcp_task_lease_tokens.py

fix(mcp): keep rotating OAuth refresh tokens across restarts and Gateway instances (#7207)

2026-10-21 18:17:29 +08:00

test_migration_0027_0028_notification_outbox.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_migration_0029_scheduler_agent_tasks.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_migration_0031_scheduled_streak_boundary.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

test_migration_0032_activity_and_task_events.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_migration_0033_batch_result_artifact.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_migration_0034_run_event_seq_watermark.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_migration_0035_login_throttle.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_migration_0036_run_idempotency_request.py

fix(gateway): make resume retries idempotent (#6499)

2026-10-09 17:11:00 +08:00

test_migration_0037_project_document_summaries.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_migration_0038_channel_thread_bindings.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_migration_0040_scheduled_group_notice.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_migration_0041_im_notice_preferences.py

feat(channels): control IM notifications and add WeChat/QQ delivery (#6850)

2026-10-14 11:14:48 +08:00

test_migration_0042_channel_leases.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_migration_0044_channel_runtime_configs.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_migration_0046_skill_mutations.py

fix(mcp): keep rotating OAuth refresh tokens across restarts and Gateway instances (#7207)

2026-10-21 18:17:29 +08:00

test_migration_0047_mcp_oauth_tokens.py

feat(projects): add visible project memory with extraction controls (#8117)

2026-11-12 09:09:44 +08:00

test_migration_0049_run_producer_fencing.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_migration_0050_history_seed_authority.py

feat(subagents): continue requested batch work and schedule explicit prerequisites (#7839)

2026-11-05 15:10:21 +08:00

test_migration_0051_run_inputs_fencing.py

feat(projects): add visible project memory with extraction controls (#8117)

2026-11-12 09:09:44 +08:00

test_migration_0054_project_memory.py

feat(projects): add visible project memory with extraction controls (#8117)

2026-11-12 09:09:44 +08:00

test_migration_user_isolation.py

fix(migration): read thread owners from the configured database (#6450)

2026-10-08 10:27:10 +08:00

test_mindie_newline_fences.py

fix(mindie): decode escaped newlines correctly inside tilde-fenced code blocks (#7285)

2026-10-24 11:41:35 +08:00

test_mindie_provider.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_model_catalog.py

feat(models): add StepFun provider preset (#7988)

2026-11-08 09:49:43 +08:00

test_model_config.py

feat: show real-time context window usage (#3125) (#3183)

2026-07-31 21:57:22 +08:00

test_model_content_compatibility_middleware.py

fix(mcp): stop persisting URL-sourced ResourceLink blocks and heal bricked threads (#6606)

2026-10-10 21:23:27 +08:00

test_model_factory.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_model_length_finish_reason_middleware.py

fix(middlewares): prevent todo retries after text-only output caps (#7605)

2026-11-02 10:46:59 +08:00

test_model_length_responses.py

fix(middlewares): prevent todo retries after text-only output caps (#7605)

2026-11-02 10:46:59 +08:00

test_model_length_termination_detectors.py

fix(harness): stop length-capped Responses tool calls (#6946)

2026-10-16 09:37:18 +08:00

test_model_request_admission_fifo_atomic.py

fix(models): preserve FIFO across request-admission handoff (#5459)

2026-09-16 22:07:42 +08:00

test_model_request_admission.py

fix(models): keep Claude retries behind request admission (#6545)

2026-10-09 21:55:42 +08:00

test_model_response.py

fix(agents): skip content blocks with unhashable type values (#6664)

2026-10-11 17:45:06 +08:00

test_model_selection.py

feat(models): add scoped model controls to Web chats (#7249)

2026-10-22 08:08:23 +08:00

test_models_authorization.py

feat(models): add scoped model controls to Web chats (#7249)

2026-10-22 08:08:23 +08:00

test_models_router_reasoning.py

feat(models): add scoped model controls to Web chats (#7249)

2026-10-22 08:08:23 +08:00

test_monocle_tracing.py

fix(sandbox): enforce disabled skills in filesystem views (#4178)

2026-07-31 17:55:24 +08:00

test_multi_pod_inbound_dedupe.py

fix(channels): run each IM message once across instances, restarts and late redeliveries (#7104)

2026-10-19 22:57:19 +08:00

test_multi_worker_postgres_gate.py

fix(mcp): keep rotating OAuth refresh tokens across restarts and Gateway instances (#7207)

2026-10-21 18:17:29 +08:00

test_multi_worker_run_ownership.py

fix(runtime): keep assembly evidence from reviving a run a peer reclaimed (#8046)

2026-11-11 07:56:53 +08:00

test_multiturn_message_stream_graph_integration.py

…

test_nginx_browser_websocket.py

fix(helm): forward Live Browser WebSocket upgrades (#7148)

2026-10-20 13:17:54 +08:00

test_nginx_compression.py

perf(frontend): bound delivery, bundles, and long-running UI work (#4622)

2026-08-01 22:19:59 +08:00

test_nginx_langgraph_body_size.py

fix(docker): give project-document uploads their own nginx location so they are not capped at 1 MB (#5934)

2026-09-27 10:58:54 +08:00

test_nginx_local_temp_paths.py

fix(nginx): use checkout-local temp paths for local development (#8075)

2026-11-10 09:47:37 +08:00

test_nginx_loopback_canonical.py

fix(scripts): bind local make dev and make start to loopback (#6587)

2026-10-10 15:47:30 +08:00

test_nginx_project_documents_body_size.py

fix(docker): give project-document uploads their own nginx location so they are not capped at 1 MB (#5934)

2026-09-27 10:58:54 +08:00

test_node_test_acceptance.py

fix(subagents): keep tests_passed evidence per call when a provider reuses its id (#8012)

2026-11-09 19:59:47 +08:00

test_notification_deliveries_repository.py

feat(channels): arbitrate IM transports with a per-provider leader lease (#6843)

2026-10-14 13:51:42 +08:00

test_notification_delivery_transactions.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

test_notification_delivery_worker_lifecycle.py

fix(scheduler): serialize notification worker lifecycle (#6433)

2026-10-08 09:26:31 +08:00

test_notification_delivery_worker.py

feat(channels): generalize group notifications and add opt-in task/goal IM notices (#6903)

2026-10-15 10:30:55 +08:00

test_notification_groups.py

feat(channels): generalize group notifications and add opt-in task/goal IM notices (#6903)

2026-10-15 10:30:55 +08:00

test_notification_text.py

feat(channels): generalize group notifications and add opt-in task/goal IM notices (#6903)

2026-10-15 10:30:55 +08:00

test_null_tool_result_pairing.py

fix(agents): pair null call IDs with empty result IDs (#7837)

2026-11-05 14:07:15 +08:00

test_numeric_config_guards.py

test(config): make refresh_skew rejection test load-bearing (#6080)

2026-09-30 17:21:43 +08:00

test_oidc_auth.py

fix(frontend): return SSO sign-ins to their next path (#7467)

2026-10-26 19:24:35 +08:00

test_openai_decisions.py

feat(decisions): add an OpenAI Decisions backend for the decision slots (#7127)

2026-10-20 11:50:46 +08:00

test_openai_response_guard.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_openapi_operation_ids.py

fix(runs): reject cancel actions on GET stream joins (#5092)

2026-09-01 15:51:37 +08:00

test_opensandbox_provider.py

feat(opensandbox): add opt-in secure_access sandbox option (#8162)

2026-11-12 09:49:33 +08:00

test_openviking_mcp_integration.py

feat(mcp): add official OpenViking tools integration (#4745)

2026-08-11 13:56:02 +08:00

test_openviking_memory_backend.py

fix(tests): isolate backend configuration and nested Make controls (#7567)

2026-10-26 20:53:09 +08:00

test_output_names.py

fix(utils):Keep the timestamped output-name fallbacks distinct on a coarse clock (#7071)

2026-10-25 16:17:15 +08:00

test_owner_isolation.py

…

test_parallel_mcp_user_agent.py

feat(mcp): identify DeerFlow in Parallel request headers (#5501)

2026-09-17 11:35:13 +08:00

test_pat_auth.py

feat(projects): add visible project memory with extraction controls (#8117)

2026-11-12 09:09:44 +08:00

test_patched_deepseek.py

fix(models): preserve Moonshot cache_write_tokens in usage metadata (#7428)

2026-10-25 19:04:13 +08:00

test_patched_mimo.py

…

test_patched_minimax.py

fix(models): preserve MiniMax reasoning_content responses (#6071)

2026-10-09 16:00:32 +08:00

test_patched_openai.py

…

test_patched_stepfun.py

feat(models): add StepFun provider preset (#7988)

2026-11-08 09:49:43 +08:00

test_paths_user_isolation.py

fix(config): delete thread dir through extended-length path to avoid WinError 145 (#8144)

2026-11-12 14:24:24 +08:00

test_paused_batch_lease_recovery.py

fix(subagents): recover expired attempts in paused batches (#7686)

2026-10-30 21:50:39 +08:00

test_persistence_autogen_script.py

…

test_persistence_bootstrap_concurrency.py

fix(persistence): drain alembic workers across cancellation (#5631)

2026-09-22 22:17:11 +08:00

test_persistence_bootstrap_pg_lock.py

fix(persistence): wait out a peer's Postgres bootstrap past command_timeout (#6306)

2026-10-05 15:33:29 +08:00

test_persistence_bootstrap_regression.py

feat(persistence): add expand-phase thread incarnation storage (#5216)

2026-09-09 15:52:09 +08:00

test_persistence_bootstrap_sqlite_lock.py

…

test_persistence_bootstrap_url.py

feat(persistence): support custom postgres schema (#3442)

2026-07-30 13:51:17 +08:00

test_persistence_bootstrap.py

fix(persistence): compare safe_add_column drift as the database spells it (#6865)

2026-10-14 17:56:25 +08:00

test_persistence_engine_auto_create_cancellation.py

fix(persistence): drain the auto-create maintenance dispose across cancellation (#5649)

2026-09-23 10:14:35 +08:00

test_persistence_engine_auto_create_postgres.py

fix(persistence): auto-create the Postgres database only when it is missing (#7410)

2026-10-24 21:18:18 +08:00

test_persistence_engine_auto_create_race.py

fix(persistence): treat a peer's database creation as success (#7489)

2026-10-25 23:00:40 +08:00

test_persistence_engine_close_cancellation.py

fix(persistence): drain engine close across cancellation (#5576)

2026-09-20 19:19:29 +08:00

test_persistence_engine_postgres_config.py

fix(persistence): auto-create the Postgres database only when it is missing (#7410)

2026-10-24 21:18:18 +08:00

test_persistence_forward_revision_compat.py

fix(scheduler): reconcile stuck once tasks from committed run outcome (#5035)

2026-09-12 07:35:07 +08:00

test_persistence_json_safe_dumps.py

fix(persistence): normalize non-finite floats before every JSON column write (#7733)

2026-10-31 18:12:32 +08:00

test_persistence_migrations_env.py

feat(extensions): let an out-of-tree extension observe what the agent did (#4863)

2026-08-23 09:57:12 +08:00

test_persistence_retry_dispose_cancellation.py

fix(persistence): auto-create the Postgres database only when it is missing (#7410)

2026-10-24 21:18:18 +08:00

test_persistence_scaffold.py

fix(persistence): apply postgres schema to sync agent stores (#5678)

2026-09-22 10:59:41 +08:00

test_persistence_timezone.py

fix(runtime): preserve run event timestamp offsets in SQLite (#6894)

2026-10-15 10:19:26 +08:00

test_personal_access_tokens_repository.py

fix(authz): cover create/run/memory/agent routes with permission checks; scope USER.md per user (#4989)

2026-09-23 15:37:26 +08:00

test_personal_mcp_access.py

feat(authz): admin role-assignment API for configured custom roles (#4063 gap 2) (#6382)

2026-10-07 14:59:16 +08:00

test_personal_mcp_network.py

fix(community): refuse non-global addresses in the shared SSRF guard (#6202)

2026-10-03 10:29:56 +08:00

test_personal_mcp.py

fix(mcp): keep a tool argument named runtime out of LangGraph's runtime injection (#7677)

2026-11-01 12:45:14 +08:00

test_pg_schema_integration.py

feat(persistence): support custom postgres schema (#3442)

2026-07-30 13:51:17 +08:00

test_pii_redaction_middleware.py

fix(middleware): scan PII emails in linear time (#8006)

2026-11-08 22:09:02 +08:00

test_plugin_action_authorization.py

feat(authz): add plugin resource targets, provenance, action and management enforcement (#5842)

2026-09-25 14:46:12 +08:00

test_plugin_contributions.py

feat(workflows): add Phase 2 approvals, immutable artifacts and configuration evidence (#6920)

2026-10-17 09:41:15 +08:00

test_plugin_diagnostics.py

feat(plugins): add redacted administrator diagnostics (#7612)

2026-10-27 21:29:21 +08:00

test_plugin_management_guard.py

feat(authz): add plugin resource targets, provenance, action and management enforcement (#5842)

2026-09-25 14:46:12 +08:00

test_plugin_targets.py

feat(authz): add plugin resource targets, provenance, action and management enforcement (#5842)

2026-09-25 14:46:12 +08:00

test_plugin_tools.py

feat(agent): add read-only run status introspection (phase 1) (#7297)

2026-10-23 22:06:00 +08:00

test_pnpm_script.py

fix(scripts): bind local make dev and make start to loopback (#6587)

2026-10-10 15:47:30 +08:00

test_poc_external_system_message_injection.py

fix(security): prevent external system-role message injection (#5651)

2026-09-22 10:38:16 +08:00

test_port_allocator_bounds.py

fix(sandbox): stop port allocation at the TCP port limit (#6424)

2026-10-07 17:26:57 +08:00

test_postgres_asyncpg_url.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_postgres_schema_helper.py

fix(runtime): strip the SQLAlchemy driver suffix from sync and store DSNs (#6917)

2026-10-15 23:45:09 +08:00

test_present_file_tool_core_logic.py

fix(tools): resolve presented files with runtime user (#4677)

2026-08-05 07:43:54 +08:00

test_present_files_e2e_user_isolation.py

fix(tools): resolve presented files with runtime user (#4677)

2026-08-05 07:43:54 +08:00

test_project_context_injection.py

feat(projects): Projects MVP Phase 2 — instructions, document shelf, promotion, trash (#5443)

2026-09-16 18:46:18 +08:00

test_project_document_attach_cleanup.py

fix(projects): keep shelf staging cleanup best-effort across the routes (#7229)

2026-10-24 11:07:09 +08:00

test_project_document_char_cache.py

fix(projects): synchronize document character-count cache (#6315)

2026-10-06 08:09:15 +08:00

test_project_document_search.py

feat(projects): search shelf documents by keyword (#7286)

2026-10-24 18:07:00 +08:00

test_project_document_staging_cancellation.py

fix(projects): drain shelf staging on cancellation (#7360)

2026-10-24 10:47:40 +08:00

test_project_document_tools.py

fix(projects): preserve conversion outcomes through staging cleanup (#7659)

2026-10-28 22:07:44 +08:00

test_project_documents_promotion.py

fix(projects): drain shelf staging on cancellation (#7360)

2026-10-24 10:47:40 +08:00

test_project_documents_repo.py

test(backend): fix three more Windows-host test failures (#7008)

2026-10-18 10:25:26 +08:00

test_project_documents_router.py

fix(projects): preserve document upload outcomes during cleanup (#7141)

2026-10-20 13:15:40 +08:00

test_project_memory.py

feat(projects): add visible project memory with extraction controls (#8117)

2026-11-12 09:09:44 +08:00

test_project_shelf_index.py

feat(projects): best-effort LLM summaries for shelf documents (#6581)

2026-10-10 07:11:02 +08:00

test_project_summaries.py

fix(projects): drain summary shutdown across caller cancellation (#7684)

2026-10-31 17:34:49 +08:00

test_project_trash_reconciliation_cancellation.py

fix(projects): drain trash reconciliation before cancellation returns (#5511)

2026-09-18 09:05:26 +08:00

test_project_trash.py

fix(projects): keep referenced originals when the trash sweep walks a symlinked tree (#7732)

2026-10-31 19:16:50 +08:00

test_projects_config.py

feat(projects): add visible project memory with extraction controls (#8117)

2026-11-12 09:09:44 +08:00

test_projects_context.py

feat(projects): add visible project memory with extraction controls (#8117)

2026-11-12 09:09:44 +08:00

test_projects_repo.py

feat(projects): project workspaces with scoped chats and thread membership (#5265)

2026-09-08 17:00:26 +08:00

test_projects_router.py

feat(projects): Projects MVP Phase 2 — instructions, document shelf, promotion, trash (#5443)

2026-09-16 18:46:18 +08:00

test_prompt_external.py

…

test_prompt_overlays.py

feat(prompts): add operator overlays for core system prompts (#5794)

2026-09-25 09:51:11 +08:00

test_provider_api_key_whitespace.py

fix(community): strip provider API keys before they reach a header (#7981)

2026-11-08 08:44:56 +08:00

test_provider_credentials_single_owner.py

refactor(community): give retrieval credential handling a single owner (#6638)

2026-10-11 11:09:49 +08:00

test_provisioner_kubeconfig.py

…

test_provisioner_mount_contract.py

refactor: remove unused proxy policy and private constants (#7554)

2026-10-26 17:02:39 +08:00

test_provisioner_namespace.py

fix(multi-instance): publish skill_manage cache resets and tolerate a concurrent namespace create (#7099)

2026-10-19 22:28:19 +08:00

test_provisioner_pvc_volumes.py

fix(provisioner): keep POSIX hostPath values POSIX on Windows hosts (#7905)

2026-11-06 11:19:13 +08:00

test_provisioner_request_threading.py

fix(sandbox): run scoped env commands concurrently (#7841)

2026-11-09 20:18:30 +08:00

test_provisioner_sandbox_responses.py

fix(sandbox): attest lark broker mode per Pod and quarantine uncertain shell outcomes (#6436)

2026-10-10 07:56:09 +08:00

test_qq_binding.py

feat(channels): generalize group notifications and add opt-in task/goal IM notices (#6903)

2026-10-15 10:30:55 +08:00

test_qq_channel_live.py

feat(channel): add QQ WebSocket channel (#6081)

2026-10-03 14:32:44 +08:00

test_qq_channel.py

fix(qq): parse allowed_users with the shared fail-closed allowlist (#6730)

2026-10-12 22:19:11 +08:00

test_qq_lifecycle.py

fix(channels): share chat-to-thread bindings through the database (#6558)

2026-10-10 14:00:00 +08:00

test_qq_notifications.py

feat(channels): generalize group notifications and add opt-in task/goal IM notices (#6903)

2026-10-15 10:30:55 +08:00

test_quarantine_retire_race_regression.py

fix(sandbox): keep quarantine teardown idempotent when a peer finishes first (#7313)

2026-10-23 22:55:45 +08:00

test_ragflow_client.py

feat(knowledge): decouple scope and read-only catalogs (phase 2) (#6904)

2026-10-15 15:10:39 +08:00

test_ragflow_tools.py

fix(community): reject booleans in the knowledge_search provider settings (#7042)

2026-10-20 23:17:51 +08:00

test_rbac_authorization_provider.py

feat(authz): add plugin resource targets, provenance, action and management enforcement (#5842)

2026-09-25 14:46:12 +08:00

test_read_before_write_cancellation.py

fix(agents): avoid executor starvation in file-gate waits (#6511)

2026-10-09 17:46:35 +08:00

test_read_before_write_coordination.py

fix(agents): avoid executor starvation in file-gate waits (#6511)

2026-10-09 17:46:35 +08:00

test_read_before_write_middleware.py

fix(agents): bind read marks to the current tool call (#6363)

2026-10-07 07:07:53 +08:00

test_read_conversation_tool.py

feat(conversation): continue reading a cut message by offset (#5434)

2026-09-15 08:25:08 +08:00

test_read_file_json_result_meta.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_read_file_line_range.py

feat(sandbox): show source line numbers for short read_file ranges (#8109)

2026-11-11 11:08:39 +08:00

test_read_file_tool_binary.py

test(backend): preserve LF endings in read_file fixtures on Windows (#6438) (#6949)

2026-10-16 09:01:28 +08:00

test_read_file_truncation_continuation.py

test(backend): preserve LF endings in read_file fixtures on Windows (#6438) (#6949)

2026-10-16 09:01:28 +08:00

test_read_mark_tool_call_correlation.py

fix(agents): bind read marks to the current tool call (#6363)

2026-10-07 07:07:53 +08:00

test_readability.py

fix(readability): cache unavailable Node extraction (#7617)

2026-10-28 07:33:41 +08:00

test_reasoning_capture_single_owner.py

refactor(models): give reasoning capture plumbing a single owner (#6639)

2026-10-11 10:53:00 +08:00

test_reasoning_contract.py

feat(models): add declarative reasoning capability contract (#5780)

2026-09-24 20:39:30 +08:00

test_receipt_verification.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_recovery_terminal_pool.py

fix(runtime): backfill run.terminal after confirmed recovery takeover (#7500)

2026-10-25 23:22:02 +08:00

test_redis_checkpoint_history_cache_corrupt_entries.py

fix(checkpoints): treat corrupt Redis history cache entries as misses (#6592)

2026-10-10 16:32:00 +08:00

test_redis_history_record_validation.py

fix(checkpoints): validate cached delta history before replay (#7548)

2026-10-27 00:28:03 +08:00

test_redis_stream_cleanup_gap.py

fix(runtime): recover terminal Redis streams after producer loss (#7093)

2026-10-19 15:53:54 +08:00

test_redis_stream_future_cursor.py

fix(streaming): report replay gap for future Redis Last-Event-ID (#6605)

2026-10-10 22:28:47 +08:00

test_reflection_resolvers.py

fix(reflection): reject malformed variable paths before diagnosing them (#7016)

2026-10-22 08:05:17 +08:00

test_reload_boundary.py

feature(gateway): issue request trace ids unconditionally (#5119)

2026-09-01 16:49:39 +08:00

test_remote_artifact_snapshots.py

feat(extensions): add versioned team file handoffs (#7817)

2026-11-05 14:50:09 +08:00

test_remote_list_dir.py

fix(sandbox): prune ignored entries before the listing limit (#5676)

2026-09-22 10:56:49 +08:00

test_remote_read_file_line_numbers.py

fix(sandbox): number remote read_file line ranges like LocalSandbox (#6585)

2026-10-10 07:51:46 +08:00

test_remote_sandbox_backend.py

fix(sandbox): attest lark broker mode per Pod and quarantine uncertain shell outcomes (#6436)

2026-10-10 07:56:09 +08:00

test_remote_search_record_framing.py

fix(sandbox): frame remote search records on LF only (#6595)

2026-10-10 14:29:57 +08:00

test_remote_search.py

fix(sandbox): wrap implicit-session probe commands in a subshell to prevent wedged shell (#1433 family) (#5546)

2026-09-20 19:07:48 +08:00

test_replay_golden.py

…

test_replay_provider.py

…

test_report_sections_extension.py

feat(plugins): add sectioned long-form report writing example (#7371)

2026-10-24 08:50:56 +08:00

test_resource_placeholder.py

fix(mcp): stop persisting URL-sourced ResourceLink blocks and heal bricked threads (#6606)

2026-10-10 21:23:27 +08:00

test_retrieval_plugin_artifacts.py

feat(knowledge): decouple scope and read-only catalogs (phase 2) (#6904)

2026-10-15 15:10:39 +08:00

test_review_changed_public_skills_utf8.py

fix(skills): decode skill-review analyzer output as UTF-8 (#7432)

2026-10-25 09:06:19 +08:00

test_review_changed_public_skills.py

test(mounts): compare host paths separator-agnostically in provisioner and mount suites (#5413)

2026-09-14 11:10:41 +08:00

test_review_skill_package_tool.py

test: route four unguarded symlink fixtures through symlink_or_skip (#6619)

2026-10-10 20:52:17 +08:00

test_run_admission_isolation.py

fix(runtime): isolate run admission from unrelated heartbeats (#7664)

2026-10-29 22:19:10 +08:00

test_run_change_repair_history.py

feat(scheduler): create conversation schedules and support agent self-stop (#6229)

2026-10-04 06:46:13 +08:00

test_run_creation_route_contract.py

fix(gateway): enforce run-create authorization on stateless endpoints (#5030)

2026-08-27 14:59:31 +08:00

test_run_duration_checkpoint.py

fix(gateway): preserve exact history attribution beyond event page limits (#4953)

2026-08-25 08:22:57 +08:00

test_run_event_store_by_run_index.py

…

test_run_event_store_cursor_window.py

fix(runtime): honor both cursors when reading thread messages (#6136)

2026-10-01 20:11:10 +08:00

test_run_event_store_filter.py

…

test_run_event_store_pagination.py

…

test_run_event_store.py

fix(web): preserve tool-result identity when provider call IDs repeat (#7672)

2026-10-31 08:41:07 +08:00

test_run_event_stream_contract.py

feat(hitl): add human-in-the-loop approval for high-risk tool calls (#7979)

2026-11-09 09:52:35 +08:00

test_run_events_endpoint.py

fix(runs): trim event_types filter entries before querying (#7758)

2026-11-01 23:27:00 +08:00

test_run_evidence_reader.py

feat(extensions): add request-scoped run evidence access (#5727)

2026-09-23 15:25:45 +08:00

test_run_input_graph.py

fix(agents): keep the delegation ledger exact across HITL approval and reused call ids (#8128)

2026-11-12 19:46:58 +08:00

test_run_inputs.py

fix(gateway): keep retryable thread inputs ahead of terminal receipts (#7972) (#8008)

2026-11-09 20:28:09 +08:00

test_run_journal_skill_usage.py

feat(skills): show loaded skill snapshots in answer details (#5758)

2026-09-24 17:49:52 +08:00

test_run_journal_visible_summary.py

fix(runtime): omit leading reasoning from run summaries (#6419)

2026-10-07 17:20:11 +08:00

test_run_journal.py

fix(runtime): persist a rejected HITL call in the resume run's history (#8073)

2026-11-10 15:11:09 +08:00

test_run_manager.py

fix(threads): evict in-memory runs when a thread is deleted (#8036)

2026-11-09 20:21:07 +08:00

test_run_metadata_secret_safety.py

feat(context): support client context capabilities (#7051)

2026-10-19 10:41:18 +08:00

test_run_naming.py

…

test_run_origin.py

fix(channels): share chat-to-thread bindings through the database (#6558)

2026-10-10 14:00:00 +08:00

test_run_producer_cutover_cli.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_run_producer_cutover.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_run_producer_fencing.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_run_producer_off.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_run_producer_postgres.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_run_producer_worker.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_run_recursion_capped.py

fix(runtime): present outputs before a loop wrap-up and explain step-limit stops (#7588)

2026-10-27 10:34:34 +08:00

test_run_repository.py

fix(runtime): keep assembly evidence from reviving a run a peer reclaimed (#8046)

2026-11-11 07:56:53 +08:00

test_run_request_validation.py

fix(gateway): answer malformed run bodies with 4xx instead of 500 (#7362)

2026-10-24 10:12:05 +08:00

test_run_terminal_protocol.py

fix(runtime): backfill run.terminal after confirmed recovery takeover (#7500)

2026-10-25 23:22:02 +08:00

test_run_worker_delivery.py

feat(hitl): add human-in-the-loop approval for high-risk tool calls (#7979)

2026-11-09 09:52:35 +08:00

test_run_worker_delta_resume.py

feat(agents): allow custom agents to disable memory (#5167)

2026-09-14 18:17:54 +08:00

test_run_worker_finalization_cancellation.py

feat(runtime): publish owner-confirmed run.terminal evidence (#7134)

2026-10-25 00:12:26 +08:00

test_run_worker_mcp_tasks.py

fix(gateway): preserve null input for static continuation (#7578)

2026-10-26 21:32:25 +08:00

test_run_worker_rollback.py

fix(runtime): retain interrupted assistant output (#7153)

2026-10-22 11:47:53 +08:00

test_run_worker_sync_checkpointer_cancellation.py

fix(runtime): drain sync checkpoint mutations across cancellation (#5664)

2026-09-22 11:02:16 +08:00

test_runs_api_endpoints.py

fix(gateway):unify thread id validation (#4589)

2026-08-01 19:42:44 +08:00

test_runtime_cancellation.py

fix(runtime): drain DB provider context exits across cancellation (#5757)

2026-09-24 08:11:47 +08:00

test_runtime_channel_config_merge.py

…

test_runtime_db_provider_close_cancellation.py

fix(runtime): drain postgres schema-setup connection exit across cancellation (#5812)

2026-09-24 17:34:06 +08:00

test_runtime_im_notifications.py

feat(channels): generalize group notifications and add opt-in task/goal IM notices (#6903)

2026-10-15 10:30:55 +08:00

test_runtime_keyed_lock.py

fix(tools): run tool assembly off-loop at async entry points (#5224)

2026-09-12 07:41:24 +08:00

test_runtime_lifecycle_e2e.py

fix(gateway): name the agent problem when run admission rejects agent_name (#8087)

2026-11-12 19:34:10 +08:00

test_runtime_paths.py

fix(skills): create a missing extensions_config.json in the project root (#7048)

2026-10-21 22:43:49 +08:00

test_runtime_provider_close_cancellation.py

fix(streaming): make Redis stream END publication idempotent (#7572)

2026-10-27 00:16:53 +08:00

test_safety_finish_reason_graph_integration.py

fix(agent): prevent todo reminders from resuming runs after hard stops (#7955)

2026-11-07 21:43:16 +08:00

test_safety_finish_reason_middleware.py

fix(agent): prevent todo reminders from resuming runs after hard stops (#7955)

2026-11-07 21:43:16 +08:00

test_safety_responses.py

fix(agent): prevent todo reminders from resuming runs after hard stops (#7955)

2026-11-07 21:43:16 +08:00

test_safety_termination_detectors.py

fix(safety): handle native Responses content-filter termination (#6965)

2026-10-27 10:11:56 +08:00

test_sandbox_audit_middleware.py

fix(sandbox): treat a fetched process substitution as an interpreter program (#7290)

2026-10-23 21:08:17 +08:00

test_sandbox_authorization.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_sandbox_colon_joined_path_lists.py

fix(sandbox): resolve every entry of colon-joined path lists in forward path translation (#7002)

2026-10-18 07:46:57 +08:00

test_sandbox_command_cancellation.py

fix(sandbox): stop owned command processes when a run is cancelled (#7772)

2026-11-01 23:09:25 +08:00

test_sandbox_direct_release_cancellation.py

fix(sandbox): drain direct release across cancellation (#6348)

2026-10-06 11:22:46 +08:00

test_sandbox_environment_passthrough.py

fix(sandbox): run scoped env commands concurrently (#7841)

2026-11-09 20:18:30 +08:00

test_sandbox_glob_patterns.py

fix(sandbox): make glob patterns root-relative with recursive ** (#6046)

2026-09-29 21:50:59 +08:00

test_sandbox_identity.py

feat(sandbox): share sandbox identity derivation and acquire serialization (#4741) (#5089)

2026-08-30 10:30:34 +08:00

test_sandbox_lease_rebind_cancellation.py

fix(sandbox): drain previous release during async rebind (#5498)

2026-09-17 22:33:18 +08:00

test_sandbox_leases.py

fix(sandbox): attest lark broker mode per Pod and quarantine uncertain shell outcomes (#6436)

2026-10-10 07:56:09 +08:00

test_sandbox_line_endings.py

fix(sandbox): keep line endings in local sandbox reads, writes and str_replace (#6343)

2026-10-06 09:45:47 +08:00

test_sandbox_memory_profile_script.py

…

test_sandbox_middleware.py

fix(sandbox): defer fresh AIO skill-policy acquisition (#7782)

2026-11-05 15:37:13 +08:00

test_sandbox_network_config.py

feat(sandbox): add controlled egress with approvals (#5152)

2026-09-04 23:46:57 +08:00

test_sandbox_network_policy_cancellation.py

fix(sandbox): drain network policy mutations across cancellation (#5899)

2026-09-27 07:58:15 +08:00

test_sandbox_network_proxy_workflow.py

feat(sandbox): add controlled egress with approvals (#5152)

2026-09-04 23:46:57 +08:00

test_sandbox_orphan_reconciliation_e2e.py

…

test_sandbox_orphan_reconciliation.py

fix(sandbox): measure warm-pool idle age on a monotonic clock (#7035)

2026-10-20 19:36:04 +08:00

test_sandbox_ownership_store.py

fix(sandbox): reject overflowing ownership lease TTL (#5104)

2026-09-24 18:11:35 +08:00

test_sandbox_path_patterns.py

fix(sandbox): require a path start before translating virtual and host roots (#7582)

2026-10-27 08:44:29 +08:00

test_sandbox_prewarm_config.py

feat(sandbox): add bounded AIO prewarming and lifecycle benchmarks (#6998)

2026-10-18 08:10:56 +08:00

test_sandbox_prewarm.py

feat(sandbox): add bounded AIO prewarming and lifecycle benchmarks (#6998)

2026-10-18 08:10:56 +08:00

test_sandbox_provider_lifecycle.py

fix(sandbox): leave SIGTERM/SIGINT teardown to the Gateway lifespan (#7560)

2026-10-26 20:38:32 +08:00

test_sandbox_quarantine.py

fix(sandbox): truncate quarantine path keys to stay under Windows MAX_PATH (#6880)

2026-10-15 11:00:01 +08:00

test_sandbox_reference_ownership.py

fix(sandbox): scope restored references to authenticated threads (#5736)

2026-09-23 09:53:49 +08:00

test_sandbox_rollback_release_cancellation.py

fix(sandbox): drain direct release across cancellation (#6348)

2026-10-06 11:22:46 +08:00

test_sandbox_search_contract.py

fix(sandbox): search long lines for literal grep patterns (#6969)

2026-10-18 20:58:35 +08:00

test_sandbox_search_tools.py

fix(sandbox): surface local directory search permission errors (#7234)

2026-10-22 08:38:35 +08:00

test_sandbox_skill_sync_cancellation.py

fix(sandbox): drain skill sync before cancellation (#5350)

2026-09-12 10:54:39 +08:00

test_sandbox_tools_security.py

fix(sandbox): exempt expression division after closers from the host-bash guard (#7448)

2026-11-08 09:49:07 +08:00

test_sandbox_windows_path_normalization.py

…

test_scan_changed_blocking_io.py

…

test_scanner_text_cache_atomic.py

fix(workspace): publish the snapshot text cache byte-exactly on every host (#7110)

2026-10-22 15:42:32 +08:00

test_scheduled_goal_handoff.py

fix(runtime): attribute terminal commits and isolate lease renewals (#6919)

2026-10-19 15:06:35 +08:00

test_scheduled_goal_notes_contract.py

fix(runtime): present outputs before a loop wrap-up and explain step-limit stops (#7588)

2026-10-27 10:34:34 +08:00

test_scheduled_goal_slow_rollback.py

fix(runtime): attribute terminal commits and isolate lease renewals (#6919)

2026-10-19 15:06:35 +08:00

test_scheduled_launch_recovery_fence.py

fix(scheduler): fence expired launch recovery against fresh claims (#6975)

2026-10-18 10:46:32 +08:00

test_scheduled_occurrence_sequence.py

fix(scheduler): reconcile stuck once tasks from committed run outcome (#5035)

2026-09-12 07:35:07 +08:00

test_scheduled_recovery_confirmation.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_scheduled_recovery_fencing.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_scheduled_task_claims.py

…

test_scheduled_task_cron_preview.py

feat(scheduled-tasks): finish the user-facing side of conversation schedules (RFC #6340, 1/2) (#6378)

2026-10-07 07:47:32 +08:00

test_scheduled_task_dispatch_race.py

fix(scheduler): re-read the run row under the writer before guarding update_status (#5860)

2026-09-27 21:00:09 +08:00

test_scheduled_task_errors_contract.py

feat(scheduled-tasks): finish the user-facing side of conversation schedules (RFC #6340, 1/2) (#6378)

2026-10-07 07:47:32 +08:00

test_scheduled_task_events.py

feat(channels): control IM notifications and add WeChat/QQ delivery (#6850)

2026-10-14 11:14:48 +08:00

test_scheduled_task_group_targets.py

feat(channels): generalize group notifications and add opt-in task/goal IM notices (#6903)

2026-10-15 10:30:55 +08:00

test_scheduled_task_lifecycle.py

…

test_scheduled_task_models.py

fix(scheduler): enqueue busy scheduled task runs (#4918)

2026-08-24 15:38:32 +08:00

test_scheduled_task_once_edits.py

fix(scheduler): preserve unchanged once schedules near execution (#6686)

2026-10-11 19:18:32 +08:00

test_scheduled_task_postgres.py

fix(runtime): backfill run.terminal after confirmed recovery takeover (#7500)

2026-10-25 23:22:02 +08:00

test_scheduled_task_queue.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

test_scheduled_task_repository.py

fix(runtime): backfill run.terminal after confirmed recovery takeover (#7500)

2026-10-25 23:22:02 +08:00

test_scheduled_task_router_behavior.py

fix(scheduler): reject nonexistent local times at admission (#7281)

2026-10-23 09:13:37 +08:00

test_scheduled_task_router.py

…

test_scheduled_task_run_listing.py

feat(scheduled-tasks): finish the user-facing side of conversation schedules (RFC #6340, 1/2) (#6378)

2026-10-07 07:47:32 +08:00

test_scheduled_task_run_status_filter.py

feat(scheduled-tasks): finish the user-facing side of conversation schedules (RFC #6340, 1/2) (#6378)

2026-10-07 07:47:32 +08:00

test_scheduled_task_schedules.py

fix(scheduler): pause a task whose schedule no longer computes (#7993)

2026-11-08 13:39:34 +08:00

test_scheduled_task_service.py

fix(scheduler): keep manual-trial launch origins stable across retries (#7492)

2026-10-25 22:56:58 +08:00

test_scheduled_task_wall_times.py

fix(scheduler): reject nonexistent local times at admission (#7281)

2026-10-23 09:13:37 +08:00

test_scheduler_admission_metadata.py

feat(scheduler): create conversation schedules and support agent self-stop (#6229)

2026-10-04 06:46:13 +08:00

test_scheduler_agent_quota_routes.py

feat(scheduled-tasks): finish the user-facing side of conversation schedules (RFC #6340, 1/2) (#6378)

2026-10-07 07:47:32 +08:00

test_scheduler_agent_repository.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

test_scheduler_agent_service.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

test_scheduler_capability_access.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_scheduler_completion_atomicity.py

fix(scheduler): reconcile running occurrences from terminal durable runs (#7269)

2026-10-24 20:56:35 +08:00

test_scheduler_completion_consistency.py

fix(scheduler): reconcile stuck once tasks from committed run outcome (#5035)

2026-09-12 07:35:07 +08:00

test_scheduler_config_boolean_integers.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

test_scheduler_config.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

test_scheduler_gateway_stop_recovery.py

feat(scheduled-tasks): finish the user-facing side of conversation schedules (RFC #6340, 1/2) (#6378)

2026-10-07 07:47:32 +08:00

test_scheduler_goal_recovery_hook.py

feat(scheduler): create conversation schedules and support agent self-stop (#6229)

2026-10-04 06:46:13 +08:00

test_scheduler_goal_runtime.py

feat(runtime): publish owner-confirmed run.terminal evidence (#7134)

2026-10-25 00:12:26 +08:00

test_scheduler_manual_once_trial.py

fix(scheduler): preserve recurring cadence after manual trials (#7209)

2026-10-22 16:06:09 +08:00

test_scheduler_occurrence_ordering.py

fix(scheduler): keep a one-time task's scheduled run after an early trial (#6512)

2026-10-08 23:34:32 +08:00

test_scheduler_poll_batch_isolation.py

fix(scheduler): isolate a malformed stored schedule from the poll batch (#7999)

2026-11-09 20:25:32 +08:00

test_scheduler_shutdown_timeout.py

fix(sandbox): leave SIGTERM/SIGINT teardown to the Gateway lifespan (#7560)

2026-10-26 20:38:32 +08:00

test_scheduler_tools.py

feat(scheduled-tasks): finish the user-facing side of conversation schedules (RFC #6340, 1/2) (#6378)

2026-10-07 07:47:32 +08:00

test_scheduler_unschedulable_task.py

fix(scheduler): pause a task whose schedule no longer computes (#7993)

2026-11-08 13:39:34 +08:00

test_search_max_results_single_owner.py

fix(serply): delegate max_results coercion to shared owner (#7869) (#7872)

2026-11-10 14:09:40 +08:00

test_searxng_client.py

fix(searxng): contain malformed search payloads instead of crashing on them (#6931)

2026-10-18 13:12:23 +08:00

test_secret_file.py

fix(config): accept a UTF-8 BOM in operator-authored env and secret files (#7085) (#7112)

2026-10-19 15:48:10 +08:00

test_security_scanner.py

fix(skills): parse Responses API content blocks in moderation scanner (#4936)

2026-08-24 21:27:43 +08:00

test_serialization.py

fix(runtime): normalize non-finite floats in canonical serializer (#7670)

2026-10-30 08:49:30 +08:00

test_serialize_message_content.py

…

test_serper_domain_filters.py

fix(community): screen web_search result URLs in every provider (#7037)

2026-10-22 09:23:31 +08:00

test_serper_endpoints.py

feat: support configurable Serper base URL (#6483)

2026-10-08 21:08:03 +08:00

test_serper_retries.py

feat(serper): add opt-in bounded transient retries (#6456)

2026-10-10 10:10:28 +08:00

test_serper_tools.py

refactor(community): fold serper onto the shared max_results owner (#6966)

2026-10-16 08:57:16 +08:00

test_serply_tools.py

fix(serply): delegate max_results coercion to shared owner (#7869) (#7872)

2026-11-10 14:09:40 +08:00

test_serve_config_presence.py

fix(scripts): read the checkout .env as data in serve.sh (#7606)

2026-10-27 22:19:33 +08:00

test_serve_dotenv.py

fix(scripts): read the checkout .env as data in serve.sh (#7606)

2026-10-27 22:19:33 +08:00

test_serve_frontend_skip_build.py

feat(scripts): support skipping frontend build on make start (#5053)

2026-08-28 10:44:30 +08:00

test_serve_gateway_startup_timeout.py

fix(scripts): read the checkout .env as data in serve.sh (#7606)

2026-10-27 22:19:33 +08:00

test_serve_nginx_stop.py

fix(scripts): bind local make dev and make start to loopback (#6587)

2026-10-10 15:47:30 +08:00

test_serve_pick_python.py

test(scripts): resolve Git Bash instead of the WSL launcher for Windows shell-script tests (#5404)

2026-09-14 06:55:57 +08:00

test_serve_worktree_roots.py

fix(dev): keep whole worktree paths when serve.sh builds DEERFLOW_ROOTS (#5856)

2026-09-25 22:49:12 +08:00

test_session_pool_singleton_lifecycle.py

…

test_setup_agent_atomic_cleanup.py

fix(setup-agent): keep a failed discard from replacing the publish outcome (#7564)

2026-10-26 23:33:49 +08:00

test_setup_agent_e2e_user_isolation.py

…

test_setup_agent_http_e2e_real_server.py

…

test_setup_agent_tool.py

fix(tools): publish the default agent's SOUL.md atomically (#6668)

2026-10-11 14:49:41 +08:00

test_setup_sandbox.py

fix(setup): accept successful Apple Container image pulls (#5804)

2026-09-24 15:10:25 +08:00

test_setup_script_encoding.py

fix(config): avoid Unicode failure after generating configuration (#7102)

2026-10-21 16:03:39 +08:00

test_setup_wizard_script.py

fix(scripts): make check.py and setup_wizard.py --help print usage (#8152)

2026-11-12 06:15:52 +08:00

test_setup_wizard.py

fix(wizard): replace retired Claude Sonnet 4 default with claude-sonnet-5-5 (#7585)

2026-10-27 10:38:03 +08:00

test_shared_artifact_handoff.py

fix(goal,artifacts): verify completion and artifact handoff (#7961)

2026-11-07 18:21:49 +08:00

test_shared_reset_marker.py

test: route four unguarded symlink fixtures through symlink_or_skip (#6619)

2026-10-10 20:52:17 +08:00

test_should_ignore_name.py

…

test_should_ignore_path_under_root.py

fix(sandbox): scope ignore patterns to the search root in glob/grep (#5667)

2026-10-03 14:35:09 +08:00

test_skill_archive_upload_cleanup.py

fix(extensions): keep atomic-write cleanup from replacing the save error (#7164)

2026-10-24 07:38:10 +08:00

test_skill_asset_versions.py

fix(skills): capture package digests without POSIX-only dir_fd (#7583)

2026-10-29 22:08:06 +08:00

test_skill_catalog.py

feat(skills): rank deferred discovery by agent intent (#5369)

2026-09-17 07:59:58 +08:00

test_skill_container_path_defaults.py

…

test_skill_context.py

fix(skills): pair a tool result with its own response's calls (#7929)

2026-11-06 19:53:32 +08:00

test_skill_creator_quick_validate.py

fix(skills): align skill-creator validation with the runtime schema (#7180)

2026-10-22 09:24:04 +08:00

test_skill_describe.py

feature(skills): keep allowed-tools as compatibility metadata (#6935)

2026-10-20 19:34:28 +08:00

test_skill_discovery_cycles.py

fix(skills): prune ancestor cycles during discovery (#5921)

2026-09-27 09:25:00 +08:00

test_skill_evolution_host_integration.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_skill_export.py

fix(skills): keep a required secret when an optional duplicate precedes it (#7569)

2026-10-26 21:25:46 +08:00

test_skill_frontmatter_boundaries.py

fix(skills): require complete frontmatter delimiter lines (#6817)

2026-10-14 07:51:50 +08:00

test_skill_history_jsonl.py

fix(skills): preserve Unicode separators in JSONL history (#6615)

2026-10-10 17:33:55 +08:00

test_skill_load_diagnostics.py

feat(skills): show YAML load errors for owned custom skills (#6623)

2026-10-11 12:52:48 +08:00

test_skill_manage_tool.py

fix(skills): reject Windows device names when creating a skill (#7948)

2026-11-08 08:54:08 +08:00

test_skill_manage_write_file_executable_gate.py

fix(skills): treat only top-level scripts/ paths as executable in skill_manage (#7088)

2026-10-23 00:28:20 +08:00

test_skill_metadata_prompt_injection.py

…

test_skill_mutation_admin.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_skill_mutation_async_reads.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_skill_mutation_guard.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_skill_mutation_host_lifecycle.py

test: skip POSIX-only skill mutation tests on Windows (#7154)

2026-10-20 10:03:05 +08:00

test_skill_mutation_package_cost.py

test: skip POSIX-only skill mutation tests on Windows (#7154)

2026-10-20 10:03:05 +08:00

test_skill_mutation_postgres.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_skill_mutation_process_crash.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_skill_mutation_scanner.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_skill_mutation_topology.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_skill_mutation_validation.py

test: skip POSIX-only skill mutation tests on Windows (#7154)

2026-10-20 10:03:05 +08:00

test_skill_mutation_workers.py

feat(skills): add guarded evolution host APIs (#5645)

2026-10-18 21:17:02 +08:00

test_skill_mutations.py

test: skip POSIX-only skill mutation tests on Windows (#7154)

2026-10-20 10:03:05 +08:00

test_skill_name_portability.py

fix(skills): reject Windows device names when creating a skill (#7948)

2026-11-08 08:54:08 +08:00

test_skill_package_paths.py

fix(skills): windows interpreter scripts outside scripts/ escape security scanning (#6321)

2026-10-06 07:17:22 +08:00

test_skill_permissions.py

test(skills): skip POSIX mode-bit assertions on Windows (#5244)

2026-09-08 09:21:38 +08:00

test_skill_policy_deferred_discovery.py

feature(skills): keep allowed-tools as compatibility metadata (#6935)

2026-10-20 19:34:28 +08:00

test_skill_projection_manifest_cleanup.py

fix(browser): preserve publication errors during failed cleanup (#6871)

2026-10-19 16:27:15 +08:00

test_skill_projection.py

fix(skills): read undecodable skill state as missing (#7963)

2026-11-09 21:49:46 +08:00

test_skill_publication_cleanup.py

fix(skills): keep a failed discard from replacing the publish outcome (#7586)

2026-10-27 09:01:11 +08:00

test_skill_request_scoped_secrets.py

fix(skills): keep a required secret when an optional duplicate precedes it (#7569)

2026-10-26 21:25:46 +08:00

test_skill_review_core.py

test: fix six Windows-host failures across sandbox, read_file, lark shim, skill review, and extension checks (#6787)

2026-10-14 06:19:43 +08:00

test_skill_review_waivers.py

ci(skills): preapprove combined evaluator digest for #7043 (#7630)

2026-10-28 10:53:51 +08:00

test_skill_reviewer_public_skill.py

…

test_skill_script_ci.py

ci: run public skill script tests in Skill Review CI (#7350)

2026-10-23 16:55:18 +08:00

test_skill_sdk_enrollment.py

test: skip POSIX-only skill mutation tests on Windows (#7154)

2026-10-20 10:03:05 +08:00

test_skill_storage_atomic_write_cleanup.py

fix(extensions): keep atomic-write cleanup from replacing the save error (#7164)

2026-10-24 07:38:10 +08:00

test_skill_storage_delete_symlinked_package.py

fix(skills): unlink a symlinked custom skill package on delete (#5881)

2026-09-26 11:44:48 +08:00

test_skill_storage_lifecycle.py

fix(skills): refresh user storage after config reload (#4972)

2026-08-25 19:46:04 +08:00

test_skill_storage_support_files.py

test: skip POSIX-only skill mutation tests on Windows (#7154)

2026-10-20 10:03:05 +08:00

test_skill_tool_authority.py

feature(skills): keep allowed-tools as compatibility metadata (#6935)

2026-10-20 19:34:28 +08:00

test_skill_usage.py

feat(skills): show loaded skill snapshots in answer details (#5758)

2026-09-24 17:49:52 +08:00

test_skills_archive_root.py

…

test_skills_authorization.py

fix(subagents): apply tool policies to middleware-declared tools (#8136)

2026-11-12 19:12:02 +08:00

test_skills_bundled.py

fix(skills): align Vercel deploy name and mounted script path (#5656)

2026-09-22 22:39:49 +08:00

test_skills_cache_shared_reset.py

fix(multi-instance): publish skill_manage cache resets and tolerate a concurrent namespace create (#7099)

2026-10-19 22:28:19 +08:00

test_skills_custom_multiprocess.py

fix(skills): record the content actually overwritten in custom-skill history (#6153)

2026-10-10 10:32:31 +08:00

test_skills_custom_router.py

fix(skills): create a missing extensions_config.json in the project root (#7048)

2026-10-21 22:43:49 +08:00

test_skills_disabled_fail_closed.py

fix(skills): keep disabled skills disabled when the extensions config cannot be read (#7705)

2026-11-05 15:07:07 +08:00

test_skills_installer.py

fix(skills): sniff executable binaries past leading filler bytes (#7081)

2026-10-22 08:43:42 +08:00

test_skills_listing_authorization.py

feat(capabilities): unify catalog, plugin configuration and agent selection (#5497)

2026-09-19 12:14:24 +08:00

test_skills_loader.py

fix(skills): safely tokenize portable allowed-tools patterns (#4984)

2026-08-28 08:58:59 +08:00

test_skills_parser.py

fix(skills): load SKILL.md saved as UTF-8 with a BOM (#5588)

2026-09-24 15:47:33 +08:00

test_skills_reload.py

fix(skills): share skill cache invalidation across Gateway replicas (#6495)

2026-10-08 19:43:04 +08:00

test_skills_router_authz.py

feat(authz): filter per-caller skill visibility on the skill listing surfaces (#4063 Phase 4) (#5489)

2026-09-18 08:02:52 +08:00

test_skills_validation.py

fix(skills): load SKILL.md saved as UTF-8 with a BOM (#5588)

2026-09-24 15:47:33 +08:00

test_skillscan_curl_pipe_shell.py

fix(skills): read one shell vocabulary in the curl-pipe-shell rule (#7378)

2026-10-24 08:03:36 +08:00

test_skillscan_env_launcher.py

fix(tests): make oversized-payload tests pass on Windows hosts (#6654)

2026-10-11 17:47:20 +08:00

test_skillscan_env_review_regressions.py

fix(skillscan): classify env command launchers (#6428)

2026-10-08 09:57:13 +08:00

test_skillscan_fork_bomb.py

fix(skillscan): match fork bombs by shape, not spelling (#6689)

2026-10-11 23:27:06 +08:00

test_skillscan_native.py

fix(skills): give a bracketed literal in the userinfo slot no host on every Python (#8017)

2026-11-09 16:49:37 +08:00

test_skillscan_secret_assignment_formats.py

fix(skill-creator): preserve recorded token counts in benchmarks (#7033)

2026-10-18 20:44:39 +08:00

test_skillscan_shell_env_dump.py

fix(skills): stop reporting an env path, shebang or flag as an env dump (#6297)

2026-10-05 12:25:41 +08:00

test_slack_channel_connections.py

fix(channels): retain Slack connect work through shutdown (#6808)

2026-10-13 22:05:40 +08:00

test_slack_channel_lifecycle.py

fix(channels): retain Slack connect work through shutdown (#6808)

2026-10-13 22:05:40 +08:00

test_slack_file_share.py

fix(slack): accept file_share events and download inbound files (#6855)

2026-10-15 08:28:36 +08:00

test_slash_skill_contract.py

…

test_slash_skills.py

fix(skills): strip a leading BOM from the SKILL.md content handed to the model (#6984)

2026-10-18 22:03:27 +08:00

test_sofya_tools.py

fix(sofya): report a format error for a results list with no usable objects (#6719)

2026-10-12 21:00:24 +08:00

test_soul_prompt_injection.py

feat(prompts): add operator overlays for core system prompts (#5794)

2026-09-25 09:51:11 +08:00

test_specstream_tools.py

feat(community): add SpecStream web search and fetch provider (#7968)

2026-11-09 20:32:22 +08:00

test_sqlite_capabilities.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

test_sse_format.py

fix(runtime): normalize non-finite floats in canonical serializer (#7670)

2026-10-30 08:49:30 +08:00

test_sse_observer_disconnect.py

fix(runtime): recover terminal Redis streams after producer loss (#7093)

2026-10-19 15:53:54 +08:00

test_sse_response_headers.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

test_stale_active_renewal.py

fix(runtime): isolate run admission from unrelated heartbeats (#7664)

2026-10-29 22:19:10 +08:00

test_stateless_run_wait_errors.py

fix: propagate current run failures from wait endpoints (#6217)

2026-10-04 07:46:59 +08:00

test_stateless_runs_owner_isolation.py

feat(gateway): seed checkpoint history (#4590)

2026-07-31 17:25:07 +08:00

test_stop_rule.py

feat(scheduled-tasks): finish the user-facing side of conversation schedules (RFC #6340, 1/2) (#6378)

2026-10-07 07:47:32 +08:00

test_str_replace_empty_file.py

…

test_stream_bridge.py

fix(streaming): make Redis stream END publication idempotent (#7572)

2026-10-27 00:16:53 +08:00

test_stream_cleanup.py

fix(runtime): drain agent stream close across cancellation (#5806)

2026-09-25 12:43:04 +08:00

test_stream_get_action_rejected.py

fix(runs): reject cancel actions on GET stream joins (#5092)

2026-09-01 15:51:37 +08:00

test_subagent_acceptance_followup.py

fix(subagents): preserve actionable acceptance gaps after compaction (#5287)

2026-09-08 16:11:49 +08:00

test_subagent_batch_repository.py

fix(harness): keep a cancelled batch cancelled when retrying a failed item (#7792)

2026-11-02 10:05:05 +08:00

test_subagent_batch_service.py

fix(middlewares): prevent todo retries after text-only output caps (#7605)

2026-11-02 10:46:59 +08:00

test_subagent_batch_shutdown_timeout.py

fix(sandbox): leave SIGTERM/SIGINT teardown to the Gateway lifespan (#7560)

2026-10-26 20:38:32 +08:00

test_subagent_batches_router.py

feat(subagents): continue requested batch work and schedule explicit prerequisites (#7839)

2026-11-05 15:10:21 +08:00

test_subagent_capacity_config.py

fix(agents): treat a null max_total_subagents override as unset (#6088)

2026-09-30 16:10:29 +08:00

test_subagent_capacity.py

fix(subagents): drain abandoned capacity waiters before cancellation (#7900)

2026-11-07 23:34:41 +08:00

test_subagent_checkpointer_isolation.py

feat(authz): middleware-declared tool path Layer 1 now covers tools declared by middlewares (#6105)

2026-10-01 18:26:58 +08:00

test_subagent_context_snapshot.py

fix(subagents): exclude ambiguous tool calls from parent context snapshots (#7372)

2026-10-24 10:26:21 +08:00

test_subagent_declared_tool_policy.py

fix(subagents): apply tool policies to middleware-declared tools (#8136)

2026-11-12 19:12:02 +08:00

test_subagent_deferred_promotion_integration.py

fix(harness): scope deferred tool promotion to user turn (#6977)

2026-10-18 11:24:41 +08:00

test_subagent_description_injection.py

…

test_subagent_direct_results.py

fix(subagents): preserve direct-return tool results (#6083)

2026-10-01 10:05:39 +08:00

test_subagent_execution_capacity.py

feat(ci): split backend unit tests into parallel shards (#5137)

2026-09-02 11:54:40 +08:00

test_subagent_executor.py

feat(weknora): allow opt-in shared retrieval for authenticated users (#7944)

2026-11-09 17:06:05 +08:00

test_subagent_limit_middleware.py

fix(agents): remove provider tool-call blocks when guards strip calls (#5447)

2026-09-15 22:22:12 +08:00

test_subagent_model_length_capped.py

fix(subagents): report model output length caps (#7355)

2026-10-23 21:42:11 +08:00

test_subagent_prompt_security.py

fix(tests): isolate backend configuration and nested Make controls (#7567)

2026-10-26 20:53:09 +08:00

test_subagent_report_contract.py

feat(harness): subagent report contract and delegation acceptance criteria (#5090)

2026-08-30 11:39:25 +08:00

test_subagent_routing_prompt.py

feat(subagents): continue requested batch work and schedule explicit prerequisites (#7839)

2026-11-05 15:10:21 +08:00

test_subagent_runtime.py

fix(subagents): drain owned batch stop across cancellation (#5525)

2026-09-18 14:27:33 +08:00

test_subagent_skills_config.py

…

test_subagent_status_contract.py

fix(subagents): report model output length caps (#7355)

2026-10-23 21:42:11 +08:00

test_subagent_step_events.py

…

test_subagent_thinking_config.py

feat(subagents): configure thinking and reasoning effort for native workers (#7668)

2026-10-29 22:26:12 +08:00

test_subagent_timeout_config.py

…

test_subagent_token_collector.py

…

test_subagent_turn_budget.py

fix(subagents): scale max_turns into the graph's super-step budget (#5485)

2026-09-17 09:05:25 +08:00

test_subagents_acp_boolean_backstops.py

fix(config): reject booleans for the subagent and ACP invocation backstops (#6242)

2026-10-04 12:41:13 +08:00

test_subagents_hitl_approval.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_subagents_router.py

fix(subagents): reject Windows reserved device names in managed subagent creation (#7959)

2026-11-08 21:55:46 +08:00

test_suggestions_model_authorization.py

fix(suggestions): enforce model use authorization (#5816)

2026-09-24 16:11:46 +08:00

test_suggestions_router.py

fix(parsing): keep literal think tags inside JSON string values (#7907)

2026-11-06 21:19:52 +08:00

test_summarization_chunk_cooldown.py

fix(summarization): cover all selected history before compaction (#6918)

2026-10-16 09:41:20 +08:00

test_summarization_cost_recovery.py

fix(summarization): cover all selected history before compaction (#6918)

2026-10-16 09:41:20 +08:00

test_summarization_middleware.py

feat(summarization): align built-in compaction prompt to preserve user requirements and approval conditions (#8114) (#8114)

2026-11-11 19:36:32 +08:00

test_summarization_noop_skip.py

perf(summarization): skip the summarizer LLM call for an input already proven no-op (#6318)

2026-10-05 22:04:36 +08:00

test_summarization_rolling_contract.py

fix(summarization): cover all selected history before compaction (#6918)

2026-10-16 09:41:20 +08:00

test_summarization_source_coverage.py

fix(summarization): preserve native document text during compaction (#7825)

2026-11-06 21:42:13 +08:00

test_summarization_summary_text.py

fix(summarization): cover all selected history before compaction (#6918)

2026-10-16 09:41:20 +08:00

test_summarize_checkpoint_channels.py

…

test_summarize_checkpoint_production.py

…

test_support_bundle.py

fix(scripts): read the checkout .env as data in serve.sh (#7606)

2026-10-27 22:19:33 +08:00

test_support_compose.py

fix(deploy): let make up start on a checkout without .env files (#6370)

2026-10-07 07:28:29 +08:00

test_support_postgres.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

test_support_shell.py

fix(scripts): find Git Bash under a PortableGit mingw64 layout (#7214)

2026-10-21 22:39:00 +08:00

test_support_symlinks.py

test: skip symlink-planting cases where the host cannot create symlinks (#5414)

2026-09-14 11:01:31 +08:00

test_sync_labels_script.py

fix(scripts): keep sync_labels.py from crashing on non-UTF-8 stdio (#7473)

2026-10-25 15:30:07 +08:00

test_system_message_coalescing_middleware.py

feat(extensions): let an out-of-tree extension observe what the agent did (#4863)

2026-08-23 09:57:12 +08:00

test_task_continuity.py

fix(task-continuity): count distinct archived search sources (#7956)

2026-11-09 09:07:20 +08:00

test_task_note_capacity.py

fix: preserve existing task notes during parallel additions (#5954)

2026-09-30 20:03:35 +08:00

test_task_tool_core_logic.py

feat(task_tool): introduce read-only preflight validation before delegation side effects (#8120)

2026-11-12 18:59:04 +08:00

test_task_tool_usage_recorder.py

…

test_tavily_response_shapes.py

fix(tavily): contain malformed web search and fetch payloads (#6645)

2026-10-11 15:53:01 +08:00

test_tavily_tools.py

fix(community): strip provider API keys before they reach a header (#7981)

2026-11-08 08:44:56 +08:00

test_team_artifact_execution.py

feat(extensions): add versioned team file handoffs (#7817)

2026-11-05 14:50:09 +08:00

test_telegram_channel_connections.py

fix(telegram): retain polling worker on stop timeout (#6333)

2026-10-06 07:00:09 +08:00

test_telegram_deleted_reply.py

fix(telegram): allow deleted reply targets in private chats (#6791)

2026-10-14 10:32:30 +08:00

test_telegram_message_length.py

fix(telegram): measure the rich-message cap in UTF-16 code units (#6174)

2026-10-02 22:31:40 +08:00

test_telegram_photo_fallback.py

fix(telegram): deliver rejected photos as documents (#8056)

2026-11-11 08:03:40 +08:00

test_telegram_polling_shutdown.py

fix(channels): clean up interrupted Telegram initialization (#6810)

2026-10-14 06:20:33 +08:00

test_telegram_reply_threads.py

fix(telegram): preserve group reply conversation context (#7654)

2026-10-30 00:16:45 +08:00

test_telegram_send_retry_after.py

fix(telegram): wait for retry_after before retrying a new message (#7990)

2026-11-08 09:51:43 +08:00

test_tencent_wsa_tools.py

fix(tencent_wsa): fall back when digit-class max_results cannot parse (#6973)

2026-10-18 10:51:13 +08:00

test_tenki_lifecycle.py

fix(tenki): retain cleanup ownership across provider retirement (#7311)

2026-10-24 08:49:35 +08:00

test_tenki_provider.py

fix(sandbox): measure warm-pool idle age on a monotonic clock (#7035)

2026-10-20 19:36:04 +08:00

test_terminal_commit_authority.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_terminal_completion_capability.py

fix(runtime): attribute terminal commits and isolate lease renewals (#6919)

2026-10-19 15:06:35 +08:00

test_terminal_event_confirmation.py

fix(runtime): backfill run.terminal after confirmed recovery takeover (#7500)

2026-10-25 23:22:02 +08:00

test_terminal_response_middleware.py

fix(runtime): harden model response recovery at provider boundaries (#5080)

2026-09-18 07:29:34 +08:00

test_terminal_store_contract.py

fix(runtime): attribute terminal commits and isolate lease renewals (#6919)

2026-10-19 15:06:35 +08:00

test_test_config_version_script.py

test(scripts): pin the config-version wrapper's uv index isolation (#7453)

2026-10-25 14:53:19 +08:00

test_text_writes_keep_lf_bytes.py

fix(persistence): keep LF bytes in skill and agent text writes (#7501)

2026-10-26 18:45:49 +08:00

test_think_tag_boundaries.py

fix(llm): preserve unrelated think-prefixed tags (#6505)

2026-10-08 20:59:50 +08:00

test_thread_activity_router.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

test_thread_archive.py

feat(chats): add archive and restore (#5236)

2026-09-06 22:30:26 +08:00

test_thread_create_cross_owner_conflict.py

fix(gateway): return 404 on cross-owner thread_id instead of 500 (#8057)

2026-11-10 06:22:24 +08:00

test_thread_create_idempotency.py

fix(threads): preserve concurrent create idempotency in memory mode (#7691)

2026-10-30 08:39:03 +08:00

test_thread_create_run_metadata_race.py

fix(threads): preserve concurrent create idempotency in memory mode (#7691)

2026-10-30 08:39:03 +08:00

test_thread_data_middleware.py

fix(middleware): preserve human message metadata (#5823)

2026-09-25 14:18:09 +08:00

test_thread_goal_contract.py

fix(runtime): present outputs before a loop wrap-up and explain step-limit stops (#7588)

2026-10-27 10:34:34 +08:00

test_thread_id_route_contract.py

feat(projects): Projects MVP Phase 2 — instructions, document shelf, promotion, trash (#5443)

2026-09-16 18:46:18 +08:00

test_thread_id_validation.py

fix(harness): reject Windows reserved device names in thread ID validation (#7892)

2026-11-05 14:13:23 +08:00

test_thread_messages_feedback.py

…

test_thread_messages_page.py

fix(gateway): stamp turn_duration on last AI message only in /messages/page (#4755)

2026-08-11 22:00:57 +08:00

test_thread_meta_repo.py

fix(persistence): match integer metadata without overflowing stored values (#6000)

2026-10-07 14:34:24 +08:00

test_thread_operation_release_recovery.py

fix(runtime): recover completed thread reservations on admission (#8068)

2026-11-10 15:40:34 +08:00

test_thread_reads_repository.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

test_thread_regenerate_prepare.py

feat(goal): show why a chat goal stopped and when it was met, and redact the goal evaluator and continuation input (#6556)

2026-10-10 00:20:45 +08:00

test_thread_run_idempotency.py

feat(hitl): add human-in-the-loop approval for high-risk tool calls (#7979)

2026-11-09 09:52:35 +08:00

test_thread_run_messages_pagination.py

fix(conversation): tolerate malformed event metadata (#7721)

2026-10-31 18:25:31 +08:00

test_thread_run_query_validation.py

fix(gateway): scope per-run reads to the run's data identity (#6282)

2026-10-05 10:23:55 +08:00

test_thread_run_wait_errors.py

fix(runtime): present outputs before a loop wrap-up and explain step-limit stops (#7588)

2026-10-27 10:34:34 +08:00

test_thread_runs_internal_scope.py

fix(gateway): scope per-run reads to the run's data identity (#6282)

2026-10-05 10:23:55 +08:00

test_thread_runs_page.py

feat(context): support client context capabilities (#7051)

2026-10-19 10:41:18 +08:00

test_thread_state_promoted.py

fix(harness): scope deferred tool promotion to user turn (#6977)

2026-10-18 11:24:41 +08:00

test_thread_state_reducers.py

fix(agents): bound viewed image context per model request (#6828)

2026-10-14 10:10:25 +08:00

test_thread_token_usage.py

fix(gateway): preserve owner isolation when thread metadata is missing (#5484)

2026-09-18 09:39:14 +08:00

test_threads_checkpoint_mode.py

feat(checkpoint): make delta snapshot_frequency configurable (#4516)

2026-07-28 23:21:23 +08:00

test_threads_router.py

fix(gateway): return 404 on cross-owner thread_id instead of 500 (#8057)

2026-11-10 06:22:24 +08:00

test_three_way_skills_mount_e2e.py

fix(sandbox): stop pinning a stale agent skill view once host bash is allowed (#6344)

2026-10-06 10:03:56 +08:00

test_tiktoken_cache_and_count_tokens.py

…

test_title_generation.py

fix(config): reject boolean title max_words/max_chars (#6187)

2026-10-02 19:25:14 +08:00

test_title_middleware_core_logic.py

feat(title): use filenames for attachment-only conversations (#5304)

2026-09-12 09:22:27 +08:00

test_todo_compaction.py

fix: discard stale todo reminders during context compaction (#5614)

2026-09-22 17:45:01 +08:00

test_todo_goal_continuation.py

fix(agents): keep todo reminders in Goal turns after an earlier provider stop (#8004)

2026-11-08 19:19:56 +08:00

test_todo_input_validation.py

fix(gateway): strip server-owned metadata from run input todos and goal (#7803 follow-up) (#7904)

2026-11-06 21:14:28 +08:00

test_todo_middleware.py

fix(agents): keep todo reminders in Goal turns after an earlier provider stop (#8004)

2026-11-08 19:19:56 +08:00

test_token_budget_middleware.py

fix(agents): keep queued guard warnings when a model call is retried (#5433)

2026-09-16 15:52:17 +08:00

test_token_budget_reused_message_ids.py

fix(agents): count model calls independently of reused message IDs (#8050)

2026-11-10 07:31:47 +08:00

test_token_usage_by_model.py

…

test_token_usage_config.py

…

test_token_usage_middleware.py

fix(todos): keep an unusable stored todo list from failing every model call (#7803)

2026-11-05 07:28:33 +08:00

test_token_usage.py

feat(checkpoint): make delta snapshot_frequency configurable (#4516)

2026-07-28 23:21:23 +08:00

test_tool_approval_call_ids.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_tool_approval_migration.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_tool_approval_policy.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_tool_approval_review_regressions.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_tool_approval_reviewer.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_tool_approval_runtime.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_tool_approval_store.py

feat(approvals): add Ask, Auto and Full tool permission modes (#8033)

2026-11-11 20:59:05 +08:00

test_tool_args_schema_no_pydantic_warning.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_tool_call_args.py

feat(agents): elide superseded write_file payloads from model-bound requests (#5374)

2026-09-13 18:04:51 +08:00

test_tool_call_json_depth.py

fix(agents): tolerate deeply nested JSON in tool-call normalization (#7742)

2026-11-01 23:32:00 +08:00

test_tool_call_metadata.py

fix(agents): remove provider tool-call blocks when guards strip calls (#5447)

2026-09-15 22:22:12 +08:00

test_tool_deduplication.py

feat(mcp): complete durable task notifications and chat UI (#4833)

2026-08-22 16:53:32 +08:00

test_tool_documentation.py

docs(tutorials): add required tool names and groups (#7922)

2026-11-06 21:10:30 +08:00

test_tool_error_handling_middleware.py

feat(harness): introduce HarnessGuardMiddleware for pre-write syntax validation and anti-doom-loop (#7624)

2026-11-04 20:13:19 +08:00

test_tool_error_handling_subagent_stamp.py

…

test_tool_output_budget_middleware.py

fix(tool-output): preserve prompt prefixes by default (#7455)

2026-10-27 10:09:03 +08:00

test_tool_output_config_limits.py

fix(config): reject invalid tool output budgets (#6172)

2026-10-03 16:38:00 +08:00

test_tool_output_externalized_filename.py

fix(middleware): derive the externalized filename from the tool call id (#6107)

2026-10-06 09:06:33 +08:00

test_tool_output_restore_permissions.py

fix(middleware): preserve mounted output permissions on blob restore (#7390)

2026-10-25 19:22:11 +08:00

test_tool_output_synopsis_budget.py

fix(agents): bound structured tool-output previews (#6422)

2026-10-07 17:07:59 +08:00

test_tool_output_truncation.py

fix(sandbox): cut read_file output at a line boundary and name the next start_line (#5474)

2026-09-16 23:57:38 +08:00

test_tool_progress_entry_fence.py

fix(agents): fence late progress assessments across graph entries (#8083)

2026-11-10 22:04:04 +08:00

test_tool_progress_middleware.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_tool_promotion_audit_middleware.py

feat(runtime): persist tool-progress phase transitions (#5214)

2026-09-15 08:45:08 +08:00

test_tool_provenance.py

feat(authz): add plugin resource targets, provenance, action and management enforcement (#5842)

2026-09-25 14:46:12 +08:00

test_tool_receipt_middleware.py

feat(harness): subagent receipt citation verification (#5076)

2026-08-29 16:56:56 +08:00

test_tool_receipt.py

feat(harness): subagent receipt citation verification (#5076)

2026-08-29 16:56:56 +08:00

test_tool_result_identity.py

feat(runtime): support Queue and Steer during active Web runs (#7729)

2026-10-31 11:35:36 +08:00

test_tool_result_meta_json_depth.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_tool_result_meta.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_tool_result_model_view.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_tool_result_sanitization_middleware.py

fix(security): sanitize MCP-sourced tool results through the same trust boundary (#4839)

2026-09-01 09:49:32 +08:00

test_tool_search.py

…

test_tool_transform_meta.py

feat(extensions): let an out-of-tree extension observe what the agent did (#4863)

2026-08-23 09:57:12 +08:00

test_trace_context.py

feature(gateway): issue request trace ids unconditionally (#5119)

2026-09-01 16:49:39 +08:00

test_trace_entry_points.py

fix(channels): share chat-to-thread bindings through the database (#6558)

2026-10-10 14:00:00 +08:00

test_trace_middleware.py

feature(gateway): issue request trace ids unconditionally (#5119)

2026-09-01 16:49:39 +08:00

test_tracing_config.py

…

test_tracing_factory.py

…

test_tracing_metadata.py

…

test_trash_router.py

fix(projects): defer trash cleanup when retention config is unavailable (#7683)

2026-10-31 18:08:11 +08:00

test_tui_app.py

fix(tui): let quit skip an interrupted run's unfinished step (#7326)

2026-10-23 20:33:07 +08:00

test_tui_cli_main.py

fix(cli): exit non-zero when a headless run ends in an LLM error fallback (#6056)

2026-09-30 19:48:32 +08:00

test_tui_cli.py

fix(tui): keep every word of an unquoted --print/--json message (#6636)

2026-10-11 12:52:11 +08:00

test_tui_command_registry.py

fix(tui): accept whitespace separators in slash commands (#7117)

2026-10-20 11:19:45 +08:00

test_tui_composer.py

fix(tui): preserve multiline pasted input (carries #4630 forward) (#6168)

2026-10-03 08:29:29 +08:00

test_tui_input_history.py

fix(tui): preserve cursor and undo on unchanged history recalls (#6248)

2026-10-04 17:04:58 +08:00

test_tui_interrupted_run_drain.py

fix(tui): let quit skip an interrupted run's unfinished step (#7326)

2026-10-23 20:33:07 +08:00

test_tui_message_format.py

…

test_tui_overlays.py

fix(tui): show picker labels as written instead of parsing markup (#7631)

2026-10-28 20:23:31 +08:00

test_tui_palette_render.py

…

test_tui_palette.py

…

test_tui_persistence.py

fix(tui): cancel pending persistence work when the bridge times out (#6927)

2026-10-17 19:25:18 +08:00

test_tui_render.py

fix(tui): append streamed assistant deltas verbatim (#7325)

2026-10-23 18:29:08 +08:00

test_tui_run_isolation.py

fix(tui): let quit skip an interrupted run's unfinished step (#7326)

2026-10-23 20:33:07 +08:00

test_tui_runtime.py

fix(tui): append streamed assistant deltas verbatim (#7325)

2026-10-23 18:29:08 +08:00

test_tui_session.py

fix(client): count threads, not checkpoints, in list_threads (#6426)

2026-10-07 17:16:48 +08:00

test_tui_thread_switching.py

fix(tui): guard conversation switching and invalid resume references (#6249)

2026-10-04 19:28:32 +08:00

test_tui_transparent.py

feat(tui): add transparent terminal background (#4631)

2026-08-05 08:15:28 +08:00

test_tui_view_state.py

fix(tui): append streamed assistant deltas verbatim (#7325)

2026-10-23 18:29:08 +08:00

test_typesafe_client.py

feat(memory): add Jev pre-screening and signal classification over a shared TypeSafe client (#5906)

2026-09-27 20:28:05 +08:00

test_typesafe_config.py

feat(decisions): add an OpenAI Decisions backend for the decision slots (#7127)

2026-10-20 11:50:46 +08:00

test_typesafe_guardrail_provider.py

feat(memory): add Jev pre-screening and signal classification over a shared TypeSafe client (#5906)

2026-09-27 20:28:05 +08:00

test_typesafe_risk_eval_script.py

feat(typesafe): make the risk-gate eval rubric-calibratable and its policy reproducible (#6179)

2026-10-02 22:56:24 +08:00

test_ui_language_preference.py

feat(runtime): honor the web UI language in replies and DeerMem updates (#7294)

2026-10-26 13:24:30 +08:00

test_unbrowse_target_status.py

fix(unbrowse): bound target error final URLs (#7399)

2026-10-24 16:41:35 +08:00

test_unbrowse_tools.py

feat(community): add Unbrowse web fetch provider (#5981)

2026-09-28 15:08:49 +08:00

test_unittest_acceptance.py

fix(acceptance): reject nonpassing unittest summaries (#6916)

2026-10-15 15:26:47 +08:00

test_update_agent_e2e_user_isolation.py

…

test_update_agent_tool.py

feat(agents): support Unicode display names for custom agents (#5324)

2026-09-12 11:09:41 +08:00

test_updater_truncation.py

…

test_updater_watermark.py

fix(memory): persist the DeerMem extraction watermark across restarts and replicas (#7205)

2026-10-21 07:26:44 +08:00

test_upload_companions.py

fix(uploads): invalidate edited markdown companions (#7348)

2026-10-25 22:08:31 +08:00

test_upload_copy_publication.py

fix(uploads): stop Windows replacement uploads from being skipped by the multi-link guard (#6821)

2026-10-14 08:43:26 +08:00

test_upload_ingestion_cancellation.py

fix(uploads): make companion record removal best-effort (#7409)

2026-10-24 21:56:38 +08:00

test_upload_metadata_admission.py

fix(uploads): keep malformed metadata from aborting chat turns (#6882)

2026-10-15 10:56:26 +08:00

test_upload_windows_staging_aliases.py

fix(uploads): reject Windows staging aliases before batch ingestion (#6149)

2026-10-02 22:50:30 +08:00

test_uploads_manager.py

fix(uploads): keep dedupe counter before compound archive suffix (#8042)

2026-11-10 09:52:01 +08:00

test_uploads_middleware_core_logic.py

fix: track converted upload ownership for outlines and listings (#6101)

2026-10-01 20:36:35 +08:00

test_uploads_router.py

fix(uploads): report rejected filenames and make success mean "a file was stored" (#7165)

2026-10-24 10:07:10 +08:00

test_url_safety.py

fix(community): return an error for malformed URLs in the SSRF guard (#8079)

2026-11-12 17:51:19 +08:00

test_user_context.py

fix(runtime): honor LangGraph Server identity for user-scoped data (#4538)

2026-07-28 22:59:14 +08:00

test_user_oauth_partial_index.py

fix(auth): correct OAuth conflict error message + validate multi-worker Postgres claim with real concurrency benchmark (#5026)

2026-09-03 08:17:26 +08:00

test_user_preferences.py

feat(scheduled-tasks): signals, honest notices and fair queueing for server-started runs (RFC #6340, 2/2) (#6393)

2026-10-07 10:22:15 +08:00

test_user_scoped_skill_storage.py

fix(skills): honor skills.container_path in user-scoped skill storage (#6770)

2026-10-25 15:30:20 +08:00

test_user_scoped_skills_fail_closed.py

fix(skills): keep disabled skills disabled when the extensions config cannot be read (#7705)

2026-11-05 15:07:07 +08:00

test_utils_bash_exit_boundaries.py

test(utils): cover goal-objective and bash-exit input boundaries (#8048)

2026-11-11 19:04:09 +08:00

test_utils_goal_objective_boundaries.py

test(utils): cover goal-objective and bash-exit input boundaries (#8048)

2026-11-11 19:04:09 +08:00

test_utils_llm_text.py

fix(utils): skip malformed response block types (#6614)

2026-10-11 08:25:53 +08:00

test_utils_messages.py

fix(utils): return empty text for content-less messages (#5563)

2026-09-19 10:56:21 +08:00

test_utils_time.py

…

test_uvicorn_reload_exclude.py

feat(extensions): add gateway contribution points and packaged extension management (#4780)

2026-08-13 23:55:30 +08:00

test_verification_config.py

feat(harness): deterministic tool receipts with model-visible ledger (RFC #4651, layer 1) (#4659)

2026-08-23 15:43:37 +08:00

test_verify_versions_lockfile.py

chore(release): keep deerflow-harness in the version-source lockstep (#7696)

2026-10-29 21:11:45 +08:00

test_view_image_middleware.py

fix(agents): bound viewed image context per model request (#6828)

2026-10-14 10:10:25 +08:00

test_view_image_provider_error_classification.py

fix(sandbox): enforce image byte limits during downloads (#6712)

2026-10-12 18:49:41 +08:00

test_view_image_remote_sandbox.py

fix(sandbox): enforce image byte limits during downloads (#6712)

2026-10-12 18:49:41 +08:00

test_view_image_sandbox_authorization_regression.py

fix(sandbox): scope viewed image host reads to the current thread (#5824)

2026-09-24 20:38:12 +08:00

test_view_image_tool_cancellation.py

fix(sandbox): enforce image byte limits during downloads (#6712)

2026-10-12 18:49:41 +08:00

test_view_image_tool.py

feat(storage): persist viewed images as shared blobs (#6160)

2026-10-05 19:06:16 +08:00

test_vllm_provider.py

fix(summarization): count replayed vLLM reasoning (#8077)

2026-11-10 15:08:00 +08:00

test_wait_disconnect_handling.py

fix(runtime): mark cancel takeovers with the orphan-recovery stop reason (#6674)

2026-10-11 18:30:09 +08:00

test_warm_pool_lifecycle.py

fix(tenki): retain cleanup ownership across provider retirement (#7311)

2026-10-24 08:49:35 +08:00

test_web_fetch_error_shell_meta.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

test_web_fetch_relative_links.py

fix(readability): cache unavailable Node extraction (#7617)

2026-10-28 07:33:41 +08:00

test_web_search_time_range.py

feat(community): add Sofya web search provider (#5239)

2026-09-08 10:50:03 +08:00

test_webz_tools.py

feat(search): add Webz news search provider and setup integration (#5880)

2026-10-10 18:49:59 +08:00

test_wechat_allowed_file_extensions.py

fix(wechat): a scalar allowed_file_extensions config silently widens back to all 37 defaults (#6737)

2026-10-13 07:26:59 +08:00

test_wechat_channel.py

fix(channels): ignore non-finite WeChat server longpoll timeouts (#7898)

2026-11-05 12:07:31 +08:00

test_wechat_cursor_persistence_cancellation.py

fix(wechat): drain poll-state persistence across cancellation (#6389)

2026-10-07 08:18:55 +08:00

test_wechat_inbound_staging_cleanup.py

fix(wechat): isolate downloaded attachments before inbound ingestion (#7055)

2026-10-19 16:31:48 +08:00

test_wechat_notifications.py

feat(channels): control IM notifications and add WeChat/QQ delivery (#6850)

2026-10-14 11:14:48 +08:00

test_wechat_outbound_bounded_reads.py

fix(wechat): enforce outbound limits while reading attachments (#6309)

2026-10-06 07:45:18 +08:00

test_wechat_qr_login.py

fix(wechat): extend QR-code status request timeout (#6783)

2026-10-14 06:18:58 +08:00

test_wecom_content_limit.py

fix(channels): cap WeCom outbound content at the 20480-byte protocol limit (#5148)

2026-09-12 09:59:58 +08:00

test_wecom_conversation_keys.py

fix(channels): key WeCom group conversations by chatid, not the sender (#7794)

2026-11-06 21:36:19 +08:00

test_wecom_group_bindings.py

fix(channels): key WeCom group conversations by chatid, not the sender (#7794)

2026-11-06 21:36:19 +08:00

test_wecom_ws_text.py

fix(wecom): treat "@bot /new" in group chats as a command (#8118)

2026-11-12 08:01:39 +08:00

test_weknora_document_concurrency.py

perf(knowledge): bound concurrent WeKnora document checks (#7707)

2026-10-30 07:08:01 +08:00

test_weknora_extension_live.py

feat(knowledge): add WeKnora read-only extension (phase 3) (#6950)

2026-10-18 10:28:30 +08:00

test_weknora_extension.py

feat(knowledge): add independent Wiki and entity relation retrieval tools (#7171)

2026-10-22 16:54:58 +08:00

test_weknora_shared_access.py

feat(weknora): allow opt-in shared retrieval for authenticated users (#7944)

2026-11-09 17:06:05 +08:00

test_worker_langfuse_metadata.py

fix(runtime): persist the effective model name for every run (#6980)

2026-10-18 11:10:38 +08:00

test_worker_stream_subgraph_namespace.py

feat(authz): middleware-declared tool path Layer 1 now covers tools declared by middlewares (#6105)

2026-10-01 18:26:58 +08:00

test_worker_subagent_event_flush_cancellation.py

fix(runtime): drain subagent event flush on cancellation (#5950)

2026-09-27 21:04:39 +08:00

test_worker_subagent_persistence.py

…

test_worker_trace_binding.py

feat(agents): allow custom agents to disable memory (#5167)

2026-09-14 18:17:54 +08:00

test_workflow_acceptance_routing.py

feat(workflows): add multi-Gateway coordination and session-authorized failover (#7138)

2026-10-23 23:31:43 +08:00

test_workflow_boundaries.py

test(backend): skip the POSIX-only output-capture boundary test on Windows (#7013)

2026-10-17 20:53:43 +08:00

test_workflow_cluster.py

feat(workflows): add multi-Gateway coordination and session-authorized failover (#7138)

2026-10-23 23:31:43 +08:00

test_workflow_gateway_acceptance.py

feat(workflows): add multi-Gateway coordination and session-authorized failover (#7138)

2026-10-23 23:31:43 +08:00

test_workflow_plugin.py

fix(workflows): align sequential Agent handoff size limits (#7231)

2026-10-21 19:02:26 +08:00

test_workflow_recovery.py

feat(workflows): add durable restart recovery (Phase 3) (#7075)

2026-10-19 15:24:53 +08:00

test_workspace_changes.py

fix(workspace): don't infer created or deleted files from truncated snapshots (#7172)

2026-10-22 16:52:53 +08:00

test_write_file_tool_budget_annotation.py

fix(tools): ignore unusable output budget limits (#6516)

2026-10-09 07:10:54 +08:00

test_write_file_tool_placeholder_guard.py

fix(sandbox): reject write_file payloads that are the elision placeholder (#7374)

2026-10-25 21:15:14 +08:00

test_write_file_tool_size_guard.py

…

test_youcom_tools.py

feat(community): migrate You.com tools to httpx.AsyncClient (#7186)

2026-10-23 17:59:14 +08:00