deer-flow

mirror of https://github.com/bytedance/deer-flow.git synced 2026-09-15 00:19:14 +00:00

History

feat(harness): subagent report contract and delegation acceptance criteria (#5090 )

* feat(harness): subagent report contract and delegation acceptance criteria (RFC #4651 PR3)

Layer 1 receipt verification is inert unless subagents actually cite their
execution record. This lands the prompt layer that closes the adoption gap:

- New subagents/report_contract.py owns the model-facing contract text,
  derived from the single-owner citation format (format_citation /
  receipt_id) so prompts can never drift from the verifier. The executor
  injects <report_contract> into every subagent system prompt — built-in
  and custom alike — requiring [rN tool_name] citations for action claims,
  verifiable handles (absolute path, URL, ID, HTTP status) for
  deliverables, and explicit failure reporting; the citation clause
  follows verification.receipts_enabled.
- The task tool gains an optional keyword-only acceptance_criteria
  parameter, handed to the SubagentExecutor constructor and rendered into
  the subagent's SystemMessage (stripped, capped 20 items x 500 chars) —
  deliberately never the task HumanMessage, which InputSanitizationMiddleware
  classes as genuine user input and would HTML-escape into untrusted-input
  framing. The docstring frames subagent results as self-reports, states
  the citation cross-check's evidence boundary (resolved = the call
  happened, not that the claim is correct), and documents when to attach
  criteria with the canonical leaf forms. Deterministic leaf checking
  remains a separate layer.
- The lead delegation workflow now instructs reading the ledger citation
  line as execution evidence only and spot-checking verifiable handles
  before synthesizing.
- report_contract / acceptance_criteria are registered as blocked
  framework-authority tags in input sanitization so untrusted input
  cannot forge the verification contract.

* fix(harness): neutralize acceptance criteria before system-channel injection

render_acceptance_criteria_section interpolated lead-model-supplied acceptance_criteria verbatim into the subagent SystemMessage after only stripping/capping. A criterion such as '</acceptance_criteria><system>...</system>' could close the wrapper and open a framework authority tag, bypassing InputSanitizationMiddleware.

Route each criterion through neutralize_untrusted_tags (the shared prompt-injection primitive) so blocked authority tags are HTML-escaped before interpolation. Add regression tests at the renderer and the executor _build_initial_state path.

* fix(harness): keep model-supplied criteria off the system channel

- Move acceptance_criteria values into the task HumanMessage — the
  untrusted channel InputSanitizationMiddleware escapes and
  boundary-frames. The subagent SystemMessage now carries only a
  framework-owned <acceptance_criteria> pointer note (no criterion
  text), so natural-language injection inside a criterion keeps
  task-data priority and cannot override framework instructions
  (PR #5090 review, willem-bd P1).
- Condition the lead delegation workflow's citation verification
  guidance on verification.receipts_enabled and qualify the task
  tool's result-reading text with the enabled state, so a
  receipts-disabled configuration no longer tells the lead to
  require citation evidence that cannot exist (P2).

* fix(harness): drop execution-record promise from report contract when receipts are disabled

The <report_contract> opening was emitted unconditionally, so a
verification.receipts_enabled=false subagent was told its report would
be cross-checked against an execution record that cannot exist in that
mode (terminal_receipts() returns None; no verdict, no ledger citation
line). The opening now follows receipts_enabled: enabled keeps the
cross-check language, disabled describes the handle-only review mode
(PR #5090 review, willem-bd P2).

* docs: record the prompt-layer trust-boundary self-check

Generalizes the PR #5090 review outcome: before adding prompt text, ask
of every data source in it what trust level it has and which channel it
should ride — model/user-influenceable values ride the untrusted
sanitized data channel, never framework-owned system text. Added to the
PR template (Agents/LangGraph surface) and agents/AGENTS.md.

2026-08-30 11:39:25 +08:00

blocking_io

feat(sandbox): share sandbox identity derivation and acquire serialization (#4741 ) (#5089 )

2026-08-30 10:30:34 +08:00

fixtures/replay

feat(uploads): lazy-load historical files via list_uploaded_files tool (#4174 )

2026-07-22 14:02:56 +08:00

monocle

Add trace-based behavioral tests with Monocle Test Tools (#4025 )

2026-07-19 18:26:26 +08:00

support

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

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

_agent_e2e_helpers.py

fix(agents): make update_agent honor runtime.context user_id like setup_agent (#2867 )

2026-05-12 23:18:54 +08:00

_replay_fixture.py

fix: surface length-capped model responses (#4309 )

2026-07-26 14:43:08 +08:00

_router_auth_helpers.py

fix the lint error in backend

2026-04-26 15:09:25 +08:00

_run_message_pagination_helpers.py

fix: load paginated run history messages (#3305 )

2026-06-01 15:50:39 +08:00

conftest.py

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

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

manual_browser_live_check.py

feat(browser): add agentic browser control (#4187 )

2026-07-21 11:46:33 +08:00

replay_provider.py

fix(security): inject system context as SystemMessage for role isolation (#3630 ) (#3661 )

2026-06-21 20:56:42 +08:00

seed_runs_router.py

test(e2e): deterministic record/replay front-back contract verification (#3365 )

2026-06-08 12:35:03 +08:00

test_acp_config.py

fix(harness): add timeout to invoke_acp_agent to prevent indefinite hangs (#4238 )

2026-07-22 14:47:08 +08:00

test_acquire_serialization.py

feat(sandbox): share sandbox identity derivation and acquire serialization (#4741 ) (#5089 )

2026-08-30 10:30:34 +08:00

test_additional_channel_connections.py

fix(channels): don't treat a bare "connect" as a bind command (#4251 )

2026-07-17 15:11:15 +08:00

test_agent_assembly_descriptor.py

feat: add managed subagents and delegation scopes (#4887 )

2026-08-24 11:04:23 +08:00

test_agent_guidance_check.py

fix(ci): fix the Agents.md size check test error (#4978 )

2026-08-24 08:52:01 +08:00

test_agent_model_settings.py

feat: add managed subagents and delegation scopes (#4887 )

2026-08-24 11:04:23 +08:00

test_agent_storage_backend.py

feat: add managed subagents and delegation scopes (#4887 )

2026-08-24 11:04:23 +08:00

test_agent_store_sql.py

fix(agents): make SQL store signatures content-sensitive (#4709 )

2026-08-08 20:36:13 +08:00

test_agents_router_model_settings.py

feat: add managed subagents and delegation scopes (#4887 )

2026-08-24 11:04:23 +08:00

test_aio_sandbox_local_backend.py

fix(sandbox): harden local Docker sandbox containers and port binding (#4986 )

2026-08-27 22:53:47 +08:00

test_aio_sandbox_provider.py

feat(sandbox): share sandbox identity derivation and acquire serialization (#4741 ) (#5089 )

2026-08-30 10:30:34 +08:00

test_aio_sandbox_readiness.py

fix(sandbox): bypass proxies for local AIO traffic (#4444 )

2026-07-27 07:47:39 +08:00

test_aio_sandbox.py

fix(sandbox): push read_file ranges into sandbox reads (#3824 )

2026-07-30 07:53:10 +08:00

test_app_config_name_indexes.py

perf(config): index AppConfig.get_*_config by name (O(n) -> O(1)) (#3688 )

2026-06-23 10:39:40 +08:00

test_app_config_reload.py

feat(persistence): support custom postgres schema (#3442 )

2026-07-30 13:51:17 +08:00

test_artifacts_router.py

fix(artifacts): serve SHA-256 via ETag so preview/edit work on non-secure contexts (#4865 )

2026-08-24 07:45:30 +08:00

test_assistant_payload_replay.py

refactor(provider): share assistant payload replay matching (#3307 )

2026-05-29 23:05:59 +08:00

test_auth_config.py

fix(auth): persist auto-generated JWT secret to survive restarts (#2933 )

2026-05-16 09:24:40 +08:00

test_auth_errors.py

feat(auth): release-validation pass for 2.0-rc — 12 blockers + simplify follow-ups (#2008 )

2026-04-26 11:08:11 +08:00

test_auth_middleware.py

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

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

test_auth_type_system.py

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

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

test_auth.py

security: harden auth next-path validation (#4587 )

2026-07-30 23:53:52 +08:00

test_authorization_enforcement.py

feat(authz): enforce tool authorization at assembly and runtime (#4370 )

2026-07-23 22:51:35 +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

feat(authz): propagate trusted authorization principal context (#4203 )

2026-07-17 14:49:51 +08:00

test_authorization_provider.py

feat(authz): propagate trusted authorization principal context (#4203 )

2026-07-17 14:49:51 +08:00

test_authorization_route_permissions.py

fix(gateway): enforce run-create authorization on stateless endpoints (#5030 )

2026-08-27 14:59:31 +08:00

test_authorization_runtime.py

feat(authz): enforce tool authorization at assembly and runtime (#4370 )

2026-07-23 22:51:35 +08:00

test_authorization_tool_filter.py

feat(authz): enforce tool authorization at assembly and runtime (#4370 )

2026-07-23 22:51:35 +08:00

test_background_tasks_tool.py

feat(mcp): complete durable task notifications and chat UI (#4833 )

2026-08-22 16:53:32 +08:00

test_base_to_dict.py

feat(persistence): wire alembic migrations, bootstrap schema on startup (#3706 )

2026-06-24 13:57:12 +08:00

test_batch_task_tool.py

feat(subagents): add unified capacity and durable batch execution (#4998 )

2026-08-25 07:49:38 +08:00

test_bench_checkpoint_channels.py

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

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

test_bench_checkpoint_production.py

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

2026-08-23 09:57:12 +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_sandbox_provider.py

bench(checkpoint): production-shaped full/delta benchmark with configurable snapshot frequency (#4467 )

2026-07-27 11:47:49 +08:00

test_boxlite_provider.py

feat(sandbox): share sandbox identity derivation and acquire serialization (#4741 ) (#5089 )

2026-08-30 10:30:34 +08:00

test_branch_history_seed.py

fix(gateway): scope branch history seed run ids per inherited turn (#4459 )

2026-07-26 08:00:48 +08:00

test_brave_tools.py

feat(community): add Brave image search community tool (#3866 )

2026-07-02 11:00:49 +08:00

test_browser_automation.py

perf(browser): encode progress frames as JPEG (#4836 )

2026-08-15 21:41:21 +08:00

test_browser_router.py

perf(frontend): bound delivery, bundles, and long-running UI work (#4622 )

2026-08-01 22:19:59 +08:00

test_browserless_client.py

fix(browserless): accept the timeout config key and harden coercion (#4519 )

2026-07-28 07:56:04 +08:00

test_buzz_channel.py

fix(channels): bound inbound intake and worker lifecycle (#4800 )

2026-08-14 12:35:24 +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): drop replayed events across reconnects with a persistent seen-id store (#4888 )

2026-08-22 16:34:45 +08:00

test_cached_history_saver_integration.py

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

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

test_cached_history_saver.py

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

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

test_cancel_run_idempotent.py

fix(runs): cancel degrades to lease takeover for multi-worker (#4064 )

2026-07-14 07:37:59 +08:00

test_channel_connections_config.py

fix(channels): require bound identity for user-owned IM messages (#3578 )

2026-06-16 23:04:39 +08:00

test_channel_connections_repository.py

fix(channels): make channel connect flow deterministic (#3582 )

2026-06-18 10:15:31 +08:00

test_channel_connections_router.py

fix(channels): validate channel provider before resolving its config (#4100 )

2026-07-12 08:54:03 +08:00

test_channel_file_attachments.py

fix(telegram): receive inbound attachments (#4392 )

2026-07-25 21:55:31 +08:00

test_channel_intake_backpressure.py

fix(channels): await real cross-thread tasks on shutdown (#4816 )

2026-08-14 23:29:04 +08:00

test_channel_user_id_env.py

feat(authz): propagate trusted authorization principal context (#4203 )

2026-07-17 14:49:51 +08:00

test_channels_router.py

fix(channels): harden runtime credential management APIs (#3581 )

2026-06-18 10:45:33 +08:00

test_channels.py

fix(channels): synchronize ChannelStore reads (#5083 )

2026-08-29 08:01:38 +08:00

test_check_script.py

fix: resolve diagnostic paths from any cwd (#4736 )

2026-08-11 21:56:20 +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.py

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

2026-08-02 22:25:02 +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.py

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

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

test_checkpoint_lineage.py

fix(gateway): replay edit and rerun from a settled checkpoint (#4534 )

2026-07-28 22:12:27 +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

fix(checkpoint): unwrap Overwrite first writes into empty channels (#4383 )

2026-07-26 10:44:50 +08:00

test_checkpoint_state.py

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

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

test_checkpointer_none_fix.py

fix(config): Make the sync checkpointer honor the unified database config (#3994 )

2026-07-12 08:15:32 +08:00

test_checkpointer.py

fix(test):fix the unit test error on the main

2026-08-11 21:04:55 +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): drop sibling tool calls before interrupt (#4908 )

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

test_claude_provider_oauth_billing.py

fix(oauth): Harden Claude OAuth cache-control handling (#1583 )

2026-03-30 07:41:18 +08:00

test_claude_provider_prompt_caching.py

fix: cap prompt caching breakpoints at 4 to prevent API 400 errors (#2449 )

2026-04-25 19:40:06 +08:00

test_cli_auth_providers.py

fix(provider): preserve streamed Codex output when response.completed.output is empty (#1928 )

2026-04-07 18:21:22 +08:00

test_client_e2e.py

feat(uploads): lazy-load historical files via list_uploaded_files tool (#4174 )

2026-07-22 14:02:56 +08:00

test_client_langfuse_metadata.py

feat(authz): enforce tool authorization at assembly and runtime (#4370 )

2026-07-23 22:51:35 +08:00

test_client_live_policy.py

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

2026-07-29 22:16:48 +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

feat: refine token usage display modes (#2329 )

2026-05-04 09:56:16 +08:00

test_client.py

feat(subagents): add unified capacity and durable batch execution (#4998 )

2026-08-25 07:49:38 +08:00

test_codex_provider.py

chroe(2585): keep polishing the code of codex token usage (#2689 )

2026-05-02 15:04:11 +08:00

test_compose_default_bind_host.py

fix(docker): don't abort Docker startup when .env is missing (#4956 )

2026-08-24 21:48:37 +08:00

test_compose_default_workers.py

fix(docker): default Gateway to a single worker to prevent multi-worker breakage (#3475 )

2026-06-10 21:36:25 +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_config_version.py

feat(harness): deterministic tool receipts with model-visible ledger (RFC #4651 , layer 1) (#4659 )

2026-08-23 15:43:37 +08:00

test_console_router.py

fix(console): disable cost reporting when model pricing mixes currencies (#4564 )

2026-07-29 22:24:04 +08:00

test_context_compaction_observation.py

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

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

test_context_compaction.py

fix(summarization): summarize with the run model, fall back on summary-provider failure (#4361 )

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

test_converters.py

feat(persistence): add unified persistence layer with event store, token tracking, and feedback (#1930 )

2026-04-26 11:05:47 +08:00

test_crawl4ai_tools.py

fix(web_fetch): add SSRF guard for self-hosted providers (#3942 )

2026-07-05 09:54:55 +08:00

test_create_deerflow_agent_live.py

feat: add create_deerflow_agent SDK entry point (Phase 1) (#1203 )

2026-03-29 15:31:18 +08:00

test_create_deerflow_agent.py

feat(subagents): add unified capacity and durable batch execution (#4998 )

2026-08-25 07:49:38 +08:00

test_credential_loader.py

feat(loop-detection): make loop detection configurable with per-tool frequency overrides (#2711 )

2026-05-07 16:15:15 +08:00

test_csrf_middleware.py

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

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

test_custom_agent.py

fix(tests): isolate custom agent test from local config.yaml (#4645 )

2026-08-03 08:28:15 +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_ddg_search_tools.py

fix(search): fix DDGS Wikipedia region handling (#3423 )

2026-06-08 07:59:50 +08:00

test_deermem_self_contained.py

feat(memory): add hybrid fact eviction policy (#4789 )

2026-08-17 08:20:42 +08:00

test_deferred_catalog.py

fix(tool_search): remove MAX_RESULTS cap on select: exact-name lookups (#4086 )

2026-07-13 17:57:34 +08:00

test_deferred_filter_middleware.py

fix(tool-search): reliably hide deferred MCP schemas by removing the ContextVar (closures + graph state) (#3342 )

2026-06-02 22:43:22 +08:00

test_deferred_promotion_integration.py

refactor(tool-search): consolidate MCP metadata tag and harden deferred-tool setup (#3370 )

2026-06-05 15:21:41 +08:00

test_deferred_setup.py

fix(tools): stop capping tool_search's select: at MAX_RESULTS (#4054 )

2026-07-12 00:17:11 +08:00

test_deferred_tool_crosscontext.py

feat(skills): deferred skill discovery via describe_skill tool (#3775 )

2026-07-04 23:09:29 +08:00

test_deferred_tool_promotion_real_llm.py

fix(tool-search): reliably hide deferred MCP schemas by removing the ContextVar (closures + graph state) (#3342 )

2026-06-02 22:43:22 +08:00

test_delegation_ledger_live.py

feat: preserve durable context across summarization (#3887 )

2026-07-01 22:49:17 +08:00

test_delegation_ledger.py

feat(harness): subagent receipt citation verification (#5076 )

2026-08-29 16:56:56 +08:00

test_delta_channel_checkpointers.py

feat(checkpoint): dual-mode checkpoint storage with LangGraph DeltaChannel (#4292 )

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

test_delta_channel_state.py

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

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

test_deploy_uv_extras.py

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

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

test_detect_blocking_io_static.py

fix(blocking-io): trace self/cls attribute chains and local aliases in the call graph (#4200 )

2026-07-22 13:55:40 +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

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

2026-08-05 08:29:22 +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

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

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

test_dingtalk_channel.py

fix(feishu): preserve inbound attachment files (#4903 )

2026-08-23 10:45:30 +08:00

test_discord_channel_connections.py

feat(im): Add user-owned IM channel connections (#3487 )

2026-06-12 15:24:58 +08:00

test_discord_channel.py

fix(channels): retain strong reference to Discord ack-reaction tasks (#5049 )

2026-08-27 17:56:56 +08:00

test_docker_sandbox_mode_detection.py

fix(docker): don't abort Docker startup when .env is missing (#4956 )

2026-08-24 21:48:37 +08:00

test_dockerignore_excludes_runtime_data.py

fix(docker): keep runtime data out of the build context (#4853 )

2026-08-18 23:14:17 +08:00

test_doctor.py

feat(community): add Serply web search tool (#5023 )

2026-08-28 10:30:30 +08:00

test_durable_context_middleware.py

fix(summarization): summarize with the run model, fall back on summary-provider failure (#4361 )

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

test_dynamic_context_middleware.py

fix(middleware): target the latest user message on first-turn fallback injection (#4667 )

2026-08-16 11:53:21 +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

feat(sandbox): make E2B mount upload deadline configurable (#4876 )

2026-08-30 11:31:53 +08:00

test_ensure_admin.py

refactor: Remove init_token handling from admin initialization logic and related tests

2026-04-26 11:09:56 +08:00

test_ensure_sandbox_initialized.py

fix(sandbox): unwrap Overwrite-wrapped state in ensure_sandbox_initialized (#4429 )

2026-07-29 07:04:26 +08:00

test_exa_tools.py

feat(community): add Exa search as community tool provider (#1357 )

2026-04-08 17:13:39 +08:00

test_extension_api_contracts.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_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): let an out-of-tree extension observe what the agent did (#4863 )

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

test_extension_app_loading.py

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

2026-08-13 23:55:30 +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

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

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

test_extension_gateway_wiring.py

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

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

test(extensions): isolate temporary Git hooks (#4813 )

2026-08-14 23:30:03 +08:00

test_extension_ordering.py

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

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

test_extension_placement_guarantees.py

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

2026-08-04 22:33:26 +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_route_principal.py

feat(auth): add personal access tokens for programmatic API access (#5041 )

2026-08-29 23:50:45 +08:00

test_extension_stack_wiring.py

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

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

test_extension_subagent_lifecycle.py

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

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

test_extension_system_model_calls.py

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

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

test_extension_task_lifecycle.py

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

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

test_extension_task_store_runtime.py

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

2026-08-12 09:25:05 +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_fastcrw_tools.py

fix(web_fetch): add SSRF guard for self-hosted providers (#3942 )

2026-07-05 09:54:55 +08:00

test_features_router.py

feat(subagents): add unified capacity and durable batch execution (#4998 )

2026-08-25 07:49:38 +08:00

test_feedback.py

fix(context): resolve context compress bug (#4065 )

2026-07-14 10:43:13 +08:00

test_feishu_parser.py

fix(feishu): preserve inbound attachment files (#4903 )

2026-08-23 10:45:30 +08:00

test_file_conversion.py

fix: don't flag outline as truncated at exactly MAX_OUTLINE_ENTRIES headings (#3856 )

2026-07-02 08:24:15 +08:00

test_file_io.py

fix(gateway): offload gateway upload file IO (#3935 )

2026-07-04 21:31:01 +08:00

test_file_signature.py

fix(config): close out #4124 review follow-ups (shared signature helper, resolve_config_path None contract) (#4275 )

2026-07-19 22:12:30 +08:00

test_firecrawl_tools.py

Revert "fix(firecrawl): align tools with installed firecrawl-py v2 SDK surfac…" (#4165 )

2026-07-14 11:57:48 +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

feat(checkpoint): dual-mode checkpoint storage with LangGraph DeltaChannel (#4292 )

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

test_gateway_docs_toggle.py

fix(gateway): expose the run metadata header to split-origin clients (#4535 )

2026-07-29 00:09:02 +08:00

test_gateway_extension_service_lifecycle.py

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

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

test_gateway_imports.py

feat: add Lark CLI integration (#3971 )

2026-07-26 08:09:17 +08:00

test_gateway_lifespan_shutdown.py

feat(mcp): add ordinary durable task driver (#4690 )

2026-08-15 14:26:38 +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_shutdown.py

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

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

test_gateway_run_recovery.py

fix(scheduler): support safe multi-instance scheduler recovery (#4713 )

2026-08-14 23:50:40 +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_services.py

feat(harness): subagent receipt citation verification (#5076 )

2026-08-29 16:56:56 +08:00

test_gateway_startup.py

chore: Extend frontend startup timeout from 120s to 300s. (#4899 )

2026-08-19 22:06:16 +08:00

test_github_agents_config.py

feat(channels): add GitHub as a webhook-driven channel (#3754 )

2026-07-04 22:56:24 +08:00

test_github_app_auth.py

feat(channels): add GitHub as a webhook-driven channel (#3754 )

2026-07-04 22:56:24 +08:00

test_github_channel.py

feat(channels): add GitHub as a webhook-driven channel (#3754 )

2026-07-04 22:56:24 +08:00

test_github_dispatcher.py

fix(channels): bound inbound intake and worker lifecycle (#4800 )

2026-08-14 12:35:24 +08:00

test_github_identity.py

feat(channels): add GitHub as a webhook-driven channel (#3754 )

2026-07-04 22:56:24 +08:00

test_github_prompts.py

fix(channels): drop redundant GitHub review-comment webhook fan-out (#4131 )

2026-07-14 22:56:50 +08:00

test_github_registry.py

feat(channels): add GitHub as a webhook-driven channel (#3754 )

2026-07-04 22:56:24 +08:00

test_github_token_plumbing.py

feat(channels): add GitHub as a webhook-driven channel (#3754 )

2026-07-04 22:56:24 +08:00

test_github_triggers.py

fix(github): match allow_authors logins case-insensitively (#4218 )

2026-07-16 09:12:29 +08:00

test_github_webhooks.py

fix(gateway): stop implying 200 webhook deliveries are unrecoverable (#4307 )

2026-07-23 14:32:49 +08:00

test_goal_runtime.py

fix(tracing): attach Langfuse trace metadata to the goal evaluator (#4202 )

2026-07-15 22:30:34 +08:00

test_goal_worker.py

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

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

test_groundroute_tools.py

feat(community): add GroundRoute web search + fetch engine (#3675 )

2026-06-21 15:55:10 +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

refactor: split backend into harness (deerflow.*) and app (app.*) (#1131 )

2026-03-14 22:55:52 +08:00

test_harness_packaging.py

feat(sandbox): add OpenSandbox provider (#4877 )

2026-08-23 15:46:10 +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_history_batch_queries.py

feat(chat): edit and rerun latest user turn (#4377 )

2026-07-27 22:46:51 +08:00

test_honcho_memory_backend.py

fix(memory): validate Honcho timeout and character limits (#4783 )

2026-08-17 08:22:11 +08:00

test_human_input.py

feat(clarification): structured form fields for human-input cards (#4400 Phase 1) (#4406 )

2026-07-27 14:05:31 +08:00

test_image_search.py

Return the full-resolution image URL from image_search (#3990 )

2026-07-10 11:08:30 +08:00

test_inbound_dedupe.py

feat(channels): share inbound webhook dedupe across pods via Postgres (#4210 )

2026-07-27 23:07:40 +08:00

test_infoquest_client.py

feat(harness): integration ACP agent tool (#1344 )

2026-03-26 14:20:18 +08:00

test_initialize_admin.py

fix auth setup redirects (#3844 )

2026-06-28 16:10:44 +08:00

test_input_polish_router.py

feat: add composer input polishing (#3986 )

2026-07-08 17:10:27 +08:00

test_input_sanitization_middleware.py

feat(harness): subagent report contract and delegation acceptance criteria (#5090 )

2026-08-30 11:39:25 +08:00

test_internal_auth.py

feat(skills): per-user custom skill isolation with sandbox mounting (#3889 )

2026-07-04 13:54:04 +08:00

test_interrupt_serialization.py

fix(serialization): stop stripping __interrupt__ from channel values (#3595 ) (#3605 )

2026-06-17 15:29:22 +08:00

test_invoke_acp_agent_tool.py

feat: integrate MiniMax Code as a native ACP agent (#4846 )

2026-08-17 08:16:14 +08:00

test_jina_client.py

fix(web_fetch): support proxy for Jina reader in restricted networks (#3418 ) (#3430 )

2026-06-08 23:25:29 +08:00

test_jsonl_event_store_async_io.py

fix(runtime): preserve per-run files in JSONL batch writes (#4938 )

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

test_langgraph_auth.py

fix: restore standalone LangGraph Studio compatibility (#4760 )

2026-08-15 21:20:34 +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

fix: restore standalone LangGraph Studio compatibility (#4760 )

2026-08-15 21:20:34 +08:00

test_lark_broker.py

feat(lark): sidecar credential broker for sandbox lark-cli (Pattern B) (#4501 )

2026-07-28 22:54:44 +08:00

test_lark_cli_integration.py

fix(lark): keep CLI lock directory writable in sandboxes (#4701 )

2026-08-10 11:01:14 +08:00

test_lead_agent_model_resolution.py

feat(subagents): add unified capacity and durable batch execution (#4998 )

2026-08-25 07:49:38 +08:00

test_lead_agent_prompt.py

feat(subagents): add unified capacity and durable batch execution (#4998 )

2026-08-25 07:49:38 +08:00

test_lead_agent_skills.py

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

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

test_list_uploaded_files_tool.py

fix(tools): exclude injected runtime from list_uploaded_files schema (#4375 ) (#4376 )

2026-07-23 08:22:15 +08:00

test_llm_error_handling_middleware.py

test(llm-error): rename a stand-in, not the shared FakeError (#4744 )

2026-08-12 08:47:42 +08:00

test_local_bash_tool_loading.py

fix(sandbox): improve sandbox security and preserve multimodal content (#2114 )

2026-04-11 16:52:10 +08:00

test_local_registration_gate.py

fix(auth): let deployments close local self-registration (#4311 )

2026-07-20 23:33:09 +08:00

test_local_sandbox_command_timeout.py

perf(boxlite): add benchmark-driven warm-pool reclaim tuning (#4001 )

2026-07-09 17:21:25 +08:00

test_local_sandbox_encoding.py

fix(sandbox): scope MSYS path conversion exclusions (#5003 )

2026-08-25 15:20:31 +08:00

test_local_sandbox_path_regex_cache.py

fix(sandbox): use os.sep in reverse-resolve containment check on Windows (#4058 )

2026-07-13 00:01:22 +08:00

test_local_sandbox_provider_mounts.py

fix(skills): copy projected skill files instead of hardlinking (#4825 )

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

test_local_sandbox_virtual_path_contract.py

fix(sandbox): use os.sep in reverse-resolve containment check on Windows (#4058 )

2026-07-13 00:01:22 +08:00

test_local_skill_storage_write.py

feat(skills): per-user custom skill isolation with sandbox mounting (#3889 )

2026-07-04 13:54:04 +08:00

test_logging_config.py

feat(observability): add trace-id correlation and enhanced logging (#3902 )

2026-07-03 08:01:46 +08:00

test_logging_level_from_config.py

fix(config): unify log_level from config.yaml across Gateway and debug entry points (#2601 )

2026-04-30 22:27:14 +08:00

test_loop_detection_config.py

feat(loop-detection): make loop detection configurable with per-tool frequency overrides (#2711 )

2026-05-07 16:15:15 +08:00

test_loop_detection_middleware.py

fix(loop-detection): clear the per-tool frequency counter on evict/reset (#4295 )

2026-07-19 17:13:44 +08:00

test_loop_detection_stop_reason.py

fix: surface length-capped model responses (#4309 )

2026-07-26 14:43:08 +08:00

test_makefile_shell_script_invocation.py

fix(scripts): invoke repo shell scripts through an explicit interpreter (#5031 )

2026-08-29 14:54:02 +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

feat: add managed subagents and delegation scopes (#4887 )

2026-08-24 11:04:23 +08:00

test_mcp_cache.py

fix(config): close out #4124 review follow-ups (shared signature helper, resolve_config_path None contract) (#4275 )

2026-07-19 22:12:30 +08:00

test_mcp_client_config.py

feat(mcp): add per-server tool_call_timeout for MCP tool calls (#3843 )

2026-07-03 15:39:12 +08:00

test_mcp_config_secrets.py

fix(mcp): constrain stdio launcher args and env at the config API (#4617 )

2026-08-01 22:01:45 +08:00

test_mcp_context_headers.py

feat(mcp): map request-scoped secrets to MCP HTTP/SSE headers (#5010 )

2026-08-27 10:42:42 +08:00

test_mcp_custom_interceptors.py

feat(mcp): support custom tool interceptors via extensions_config.json (#2451 )

2026-04-25 09:18:13 +08:00

test_mcp_file_migration.py

fix(mcp): exclude internal temp files from workspace changes (#4898 )

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

test_mcp_header_names.py

feat(mcp): map request-scoped secrets to MCP HTTP/SSE headers (#5010 )

2026-08-27 10:42:42 +08:00

test_mcp_oauth.py

fix(mcp): keep grant_type authoritative over extra_token_params (#4860 )

2026-08-22 17:01:38 +08:00

test_mcp_routing_auto_promote.py

feat(mcp): auto-promote deferred MCP tools from routing hints (#4019 )

2026-07-10 07:54:36 +08:00

test_mcp_routing_config.py

feat(mcp): add MCP routing hints (#4004 )

2026-07-09 16:26:31 +08:00

test_mcp_routing_metadata.py

feat(mcp): add MCP routing hints (#4004 )

2026-07-09 16:26:31 +08:00

test_mcp_routing_prompt.py

fix(runtime): honor LangGraph Server identity for user-scoped data (#4538 )

2026-07-28 22:59:14 +08:00

test_mcp_session_pool.py

fix(mcp): tear down the in-flight owner when get_session is cancelled mid-eviction (#5008 )

2026-08-30 11:36:26 +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

feat: support per-server MCP tool name prefixes (#4624 )

2026-08-01 22:33:11 +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_models.py

feat(mcp): add ordinary durable task driver (#4690 )

2026-08-15 14:26:38 +08:00

test_mcp_task_ordinary_driver.py

feat(mcp): map request-scoped secrets to MCP HTTP/SSE headers (#5010 )

2026-08-27 10:42:42 +08:00

test_mcp_task_ordinary_e2e.py

feat(mcp): add ordinary durable task driver (#4690 )

2026-08-15 14:26:38 +08:00

test_mcp_task_repository.py

feat(mcp): complete durable task notifications and chat UI (#4833 )

2026-08-22 16:53:32 +08:00

test_mcp_task_runtime_config.py

feat(mcp): add ordinary durable task driver (#4690 )

2026-08-15 14:26:38 +08:00

test_mcp_task_service.py

fix(mcp): compensate cancelled task submissions (#4933 )

2026-08-23 15:30:21 +08:00

test_mcp_task_tool_caller.py

fix(mcp): preserve pooled stdio sessions after task timeouts (#5027 )

2026-08-28 10:37:01 +08:00

test_mcp_task_tool_wrapping.py

feat(mcp): add ordinary durable task driver (#4690 )

2026-08-15 14:26:38 +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

fix(gateway): reject MCP task cancellation when the worker is stopped (#4963 )

2026-08-24 06:57:55 +08:00

test_mcp_tool_name_prefix.py

feat(mcp): add ordinary durable task driver (#4690 )

2026-08-15 14:26:38 +08:00

test_mcp_tool_name_validation.py

fix(mcp): validate MCP tool names at load so deferred prompts stay inert (#4154 )

2026-07-14 09:49:43 +08:00

test_mcp_user_scoped_auth.py

feat(mcp): per-user credential injection for shared MCP servers (#4868 )

2026-08-23 15:16:04 +08:00

test_mem0_memory_backend.py

fix(memory): reject non-finite mem0 timeout_seconds (#4823 )

2026-08-15 15:40:43 +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_eviction.py

feat(memory): add hybrid fact eviction policy (#4789 )

2026-08-17 08:20:42 +08:00

test_memory_manager_interface.py

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

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

test_memory_manager_pluggable.py

feat(memory): memory message processing (#4447 )

2026-07-26 21:16:36 +08:00

test_memory_markdown_migration_cli.py

feat(memory): add incremental agent-scoped Markdown fact storage (#4279 )

2026-07-22 07:46:03 +08:00

test_memory_middleware.py

fix(runtime): honor LangGraph Server identity for user-scoped data (#4538 )

2026-07-28 22:59:14 +08:00

test_memory_prompt_injection.py

feat(memory): pluggable memory abstraction with self-contained DeerMem backend (#4122 )

2026-07-15 11:21:04 +08:00

test_memory_queue_user_isolation.py

feat(memory): memory message processing (#4447 )

2026-07-26 21:16:36 +08:00

test_memory_queue.py

feat(memory): memory message processing (#4447 )

2026-07-26 21:16:36 +08:00

test_memory_retrieval_adapter.py

feat(memory): built-in FTS5/BM25 retrieval adapter (#4360 )

2026-07-27 23:17:18 +08:00

test_memory_router.py

fix(memory): reject duplicate facts inside the create critical section (#4599 )

2026-07-31 18:06:45 +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

feat(memory): pluggable memory abstraction with self-contained DeerMem backend (#4122 )

2026-07-15 11:21:04 +08:00

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

feat(memory): add incremental agent-scoped Markdown fact storage (#4279 )

2026-07-22 07:46:03 +08:00

test_memory_storage_user_isolation.py

feat(memory): add incremental agent-scoped Markdown fact storage (#4279 )

2026-07-22 07:46:03 +08:00

test_memory_storage.py

feat(memory): add incremental agent-scoped Markdown fact storage (#4279 )

2026-07-22 07:46:03 +08:00

test_memory_thread_meta_isolation.py

feat(threads): distinguish branched conversations (#4983 )

2026-08-25 08:29:18 +08:00

test_memory_tools.py

feat(memory): add hybrid fact eviction policy (#4789 )

2026-08-17 08:20:42 +08:00

test_memory_updater_user_isolation.py

feat(memory): pluggable memory abstraction with self-contained DeerMem backend (#4122 )

2026-07-15 11:21:04 +08:00

test_memory_updater.py

feat(memory): add hybrid fact eviction policy (#4789 )

2026-08-17 08:20:42 +08:00

test_memory_upload_filtering.py

feat(uploads): lazy-load historical files via list_uploaded_files tool (#4174 )

2026-07-22 14:02:56 +08:00

test_message_processing_signals.py

feat(memory): memory message processing (#4447 )

2026-07-26 21:16:36 +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

feat(harness): subagent receipt citation verification (#5076 )

2026-08-29 16:56:56 +08:00

test_middleware_release_policy.py

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

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

test_migration_0004_run_ownership_dedupe.py

feat(auth): add personal access tokens for programmatic API access (#5041 )

2026-08-29 23:50:45 +08:00

test_migration_0007_scheduled_run_active_dedupe.py

feat(auth): add personal access tokens for programmatic API access (#5041 )

2026-08-29 23:50:45 +08:00

test_migration_0009_webhook_dedupe.py

feat(channels): share inbound webhook dedupe across pods via Postgres (#4210 )

2026-07-27 23:07:40 +08:00

test_migration_0015_scheduled_task_enqueue.py

feat(auth): add personal access tokens for programmatic API access (#5041 )

2026-08-29 23:50:45 +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_user_isolation.py

feat(skills): per-user custom skill isolation with sandbox mounting (#3889 )

2026-07-04 13:54:04 +08:00

test_mindie_provider.py

fix(security): escape MindIE tool-response content against </tool_response> breakout (#4253 )

2026-07-17 14:23:44 +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_factory.py

feat(models): add GLM-5.3-Flash thinking workaround (#5074 )

2026-08-28 22:24:10 +08:00

test_model_length_finish_reason_middleware.py

fix: surface length-capped model responses (#4309 )

2026-07-26 14:43:08 +08:00

test_model_length_termination_detectors.py

fix: surface length-capped model responses (#4309 )

2026-07-26 14:43:08 +08:00

test_models_authorization.py

feat(authz): enforce model authorization at Gateway routes and runtime (#4063 Phase 3) (#4540 )

2026-08-01 22:34:11 +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

feat(channels): share inbound webhook dedupe across pods via Postgres (#4210 )

2026-07-27 23:07:40 +08:00

test_multi_worker_postgres_gate.py

fix(scheduler): support safe multi-instance scheduler recovery (#4713 )

2026-08-14 23:50:40 +08:00

test_multi_worker_run_ownership.py

fix(runtime): cancel runs across live gateway workers (#4500 )

2026-07-28 21:45:20 +08:00

test_multiturn_message_stream_graph_integration.py

test(agents): multi-turn message-stream invariants (graph integration) (#3708 )

2026-06-22 18:55:20 +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(nginx): allow long chat prompts through /api/langgraph/ without a raw 500 (#4277 )

2026-07-18 17:48:42 +08:00

test_oidc_auth.py

feat(auth): add OIDC SSO support (#3506 )

2026-06-21 15:47:53 +08:00

test_openapi_operation_ids.py

fix(gateway): split stream_existing_run into per-method routes for unique OpenAPI operationIds (#3228 )

2026-05-28 08:20:52 +08:00

test_opensandbox_provider.py

feat(sandbox): share sandbox identity derivation and acquire serialization (#4741 ) (#5089 )

2026-08-30 10:30:34 +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

refactor(memory): use official OpenViking adapter (#4707 )

2026-08-07 11:22:00 +08:00

test_owner_isolation.py

fix(runs): close multi-worker ownership gaps in run atomicity (#3948 ) (#4003 )

2026-07-11 16:05:30 +08:00

test_pat_auth.py

feat(auth): add personal access tokens for programmatic API access (#5041 )

2026-08-29 23:50:45 +08:00

test_patched_deepseek.py

fix(wizard): update DeepSeek provider models to v4 (#3939 )

2026-07-04 21:44:22 +08:00

test_patched_mimo.py

feat(provider) Add patched MiMo reasoning content support (#3298 )

2026-05-28 18:24:32 +08:00

test_patched_minimax.py

feat: MiniMax provider for image/video/podcast skills + new music-generation skill (#3437 )

2026-06-08 22:04:38 +08:00

test_patched_openai.py

fix(LLM): fixing Gemini thinking + tool calls via OpenAI gateway (#1180 ) (#1205 )

2026-03-26 15:07:05 +08:00

test_patched_stepfun.py

feat(models): add StepFun reasoning model adapter (#3461 )

2026-06-09 18:01:43 +08:00

test_paths_user_isolation.py

feat: add Lark CLI integration (#3971 )

2026-07-26 08:09:17 +08:00

test_persistence_autogen_script.py

feat(persistence): wire alembic migrations, bootstrap schema on startup (#3706 )

2026-06-24 13:57:12 +08:00

test_persistence_bootstrap_concurrency.py

feat(auth): add personal access tokens for programmatic API access (#5041 )

2026-08-29 23:50:45 +08:00

test_persistence_bootstrap_pg_lock.py

feat(persistence): wire alembic migrations, bootstrap schema on startup (#3706 )

2026-06-24 13:57:12 +08:00

test_persistence_bootstrap_regression.py

feat(auth): add personal access tokens for programmatic API access (#5041 )

2026-08-29 23:50:45 +08:00

test_persistence_bootstrap_sqlite_lock.py

feat(persistence): wire alembic migrations, bootstrap schema on startup (#3706 )

2026-06-24 13:57:12 +08:00

test_persistence_bootstrap_url.py

feat(persistence): support custom postgres schema (#3442 )

2026-07-30 13:51:17 +08:00

test_persistence_bootstrap.py

feat(auth): add personal access tokens for programmatic API access (#5041 )

2026-08-29 23:50:45 +08:00

test_persistence_engine_postgres_config.py

feat(persistence): support custom postgres schema (#3442 )

2026-07-30 13:51:17 +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_scaffold.py

feat(persistence): support custom postgres schema (#3442 )

2026-07-30 13:51:17 +08:00

test_persistence_timezone.py

fix(persistence): emit tz-aware timestamps from SQLite-backed stores (#3130 )

2026-05-21 16:22:09 +08:00

test_personal_access_tokens_repository.py

feat(auth): add personal access tokens for programmatic API access (#5041 )

2026-08-29 23:50:45 +08:00

test_pg_schema_integration.py

feat(persistence): support custom postgres schema (#3442 )

2026-07-30 13:51:17 +08:00

test_pnpm_script.py

fix(docker): wait for gateway readiness (#4806 )

2026-08-14 11:07:23 +08:00

test_postgres_schema_helper.py

feat(persistence): support custom postgres schema (#3442 )

2026-07-30 13:51:17 +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_prompt_external.py

feat(memory): memory template externalization (#4286 )

2026-07-20 07:24:34 +08:00

test_provisioner_kubeconfig.py

feat(provisioner): add optional PVC support for sandbox volumes (#2020 )

2026-04-10 20:40:30 +08:00

test_provisioner_mount_contract.py

fix(lark): keep CLI lock directory writable in sandboxes (#4701 )

2026-08-10 11:01:14 +08:00

test_provisioner_pvc_volumes.py

fix(lark): keep CLI lock directory writable in sandboxes (#4701 )

2026-08-10 11:01:14 +08:00

test_provisioner_request_threading.py

fix(gateway):unify thread id validation (#4589 )

2026-08-01 19:42:44 +08:00

test_ragflow_client.py

feat(knowledge): add read-only RAGFlow retrieval (#4955 )

2026-08-25 16:57:55 +08:00

test_ragflow_tools.py

feat(knowledge): add read-only RAGFlow retrieval (#4955 )

2026-08-25 16:57:55 +08:00

test_rbac_authorization_provider.py

feat(authz): add built-in RBAC provider and provider factory (#4260 )

2026-07-21 09:23:14 +08:00

test_read_before_write_middleware.py

feat(middleware): add structured tool result meta and tool-progress state machine (#3601 )

2026-07-06 20:57:41 +08:00

test_read_file_line_range.py

fix(sandbox): push read_file ranges into sandbox reads (#3824 )

2026-07-30 07:53:10 +08:00

test_read_file_tool_binary.py

fix(sandbox): keep skill reads on provider mappings (#4792 )

2026-08-13 21:20:49 +08:00

test_readability.py

refactor: split backend into harness (deerflow.*) and app (app.*) (#1131 )

2026-03-14 22:55:52 +08:00

test_receipt_verification.py

feat(harness): subagent receipt citation verification (#5076 )

2026-08-29 16:56:56 +08:00

test_reflection_resolvers.py

refactor: split backend into harness (deerflow.*) and app (app.*) (#1131 )

2026-03-14 22:55:52 +08:00

test_reload_boundary.py

feat(observability): add trace-id correlation and enhanced logging (#3902 )

2026-07-03 08:01:46 +08:00

test_remote_sandbox_backend.py

feat(lark): sidecar credential broker for sandbox lark-cli (Pattern B) (#4501 )

2026-07-28 22:54:44 +08:00

test_replay_golden.py

fix(replay-e2e): match by conversation, not the living system prompt (#3436 )

2026-06-08 17:32:41 +08:00

test_replay_provider.py

fix(replay-e2e): key fixtures by caller and conversation (#3453 )

2026-06-09 21:58:31 +08:00

test_review_changed_public_skills.py

fix(skills): recognize fully deleted public skill packages in review CI (#4169 )

2026-07-14 23:08:33 +08:00

test_review_skill_package_tool.py

feat(skills): add skill review quality gate (#4037 )

2026-07-11 15:58:07 +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

perf(runtime): index MemoryRunEventStore events by run_id to avoid O(n) scans (#3686 )

2026-06-24 17:47:04 +08:00

test_run_event_store_filter.py

feat(subagents): persist and display subagent step history (#3779 ) (#3845 )

2026-07-02 07:43:09 +08:00

test_run_event_store_pagination.py

fix the lint error in backend

2026-04-26 15:09:25 +08:00

test_run_event_store.py

fix(gateway): preserve exact history attribution beyond event page limits (#4953 )

2026-08-25 08:22:57 +08:00

test_run_event_stream_contract.py

fix(run): add run event stream contract (#4342 )

2026-07-23 21:33:57 +08:00

test_run_events_endpoint.py

fix(security): reject legacy MCP credentials in run metadata (#4448 )

2026-07-28 21:31:23 +08:00

test_run_journal.py

fix(subagents): isolate callbacks and activate skills lazily (#4497 )

2026-07-28 23:29:14 +08:00

test_run_manager.py

feat(mcp): complete durable task notifications and chat UI (#4833 )

2026-08-22 16:53:32 +08:00

test_run_metadata_secret_safety.py

fix(security): reject legacy MCP credentials in run metadata (#4448 )

2026-07-28 21:31:23 +08:00

test_run_naming.py

feat(trace):LangGraph -> lead_agent and set custom agent_name to run_name (#3101 )

2026-05-21 14:48:28 +08:00

test_run_repository.py

feat(mcp): complete durable task notifications and chat UI (#4833 )

2026-08-22 16:53:32 +08:00

test_run_request_validation.py

feat(runtime): enforce artifact delivery from workspace snapshots (#4494 )

2026-07-27 22:27:16 +08:00

test_run_worker_delivery.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_run_worker_delta_resume.py

fix(runtime): resume original title when regenerating (#4480 )

2026-07-27 11:32:10 +08:00

test_run_worker_mcp_tasks.py

feat(mcp): complete durable task notifications and chat UI (#4833 )

2026-08-22 16:53:32 +08:00

test_run_worker_rollback.py

fix(runtime): cancel runs across live gateway workers (#4500 )

2026-07-28 21:45:20 +08:00

test_runs_api_endpoints.py

fix(gateway):unify thread id validation (#4589 )

2026-08-01 19:42:44 +08:00

test_runtime_channel_config_merge.py

fix(channels): let UI runtime channel config win over config.yaml (#3674 )

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

test_runtime_lifecycle_e2e.py

feat(checkpoint): dual-mode checkpoint storage with LangGraph DeltaChannel (#4292 )

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

test_runtime_paths.py

fix(config): close out #4124 review follow-ups (shared signature helper, resolve_config_path None contract) (#4275 )

2026-07-19 22:12:30 +08:00

test_safety_finish_reason_graph_integration.py

fix(streaming): expose custom events to astream_events (#4403 )

2026-07-23 22:56:12 +08:00

test_safety_finish_reason_middleware.py

fix(streaming): expose custom events to astream_events (#4403 )

2026-07-23 22:56:12 +08:00

test_safety_termination_detectors.py

fix(runtime): suppress tool execution when provider safety-terminates with tool_calls (#3035 )

2026-05-22 21:20:28 +08:00

test_sandbox_audit_middleware.py

fix(sandbox): judge command substitution by position in audit middleware (#4623 )

2026-08-01 21:44:34 +08:00

test_sandbox_authorization.py

feat(authz): enforce sandbox:execute authorization at sandbox acquisition (#4063 Phase 3) (#4911 )

2026-08-24 16:32:06 +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_memory_profile_script.py

chore: add sandbox memory profiling tools (#3249 )

2026-06-03 22:02:27 +08:00

test_sandbox_middleware.py

fix(sandbox): push read_file ranges into sandbox reads (#3824 )

2026-07-30 07:53:10 +08:00

test_sandbox_orphan_reconciliation_e2e.py

fix(sandbox): add startup reconciliation to prevent orphaned container leaks (#1976 )

2026-04-09 17:21:23 +08:00

test_sandbox_orphan_reconciliation.py

feat(sandbox): share sandbox identity derivation and acquire serialization (#4741 ) (#5089 )

2026-08-30 10:30:34 +08:00

test_sandbox_ownership_store.py

fix(sandbox): reject non-finite ownership timings (#4960 )

2026-08-24 15:27:33 +08:00

test_sandbox_path_patterns.py

refactor(sandbox): give the host→virtual output-mask regex a single owner (#4108 )

2026-07-13 18:34:41 +08:00

test_sandbox_provider_lifecycle.py

fix(sandbox): synchronize sandbox provider singleton lifecycle (+ concurrency regression tests) (#3730 )

2026-06-25 08:06:17 +08:00

test_sandbox_search_tools.py

fix(sandbox): allow grep to search a single file (#4512 )

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

test_sandbox_tools_security.py

fix(sandbox): push read_file ranges into sandbox reads (#3824 )

2026-07-30 07:53:10 +08:00

test_sandbox_windows_path_normalization.py

feat(skills): per-user custom skill isolation with sandbox mounting (#3889 )

2026-07-04 13:54:04 +08:00

test_scan_changed_blocking_io.py

feat(skill): add blocking-io-guard — SOP skill for blocking-IO triage and runtime anchors (#3503 )

2026-06-12 10:20:38 +08:00

test_scheduled_task_claims.py

feat: add scheduled tasks MVP (#3898 )

2026-07-04 21:51:57 +08:00

test_scheduled_task_dispatch_race.py

fix(scheduler): enqueue busy scheduled task runs (#4918 )

2026-08-24 15:38:32 +08:00

test_scheduled_task_lifecycle.py

feat: add scheduled tasks MVP (#3898 )

2026-07-04 21:51:57 +08:00

test_scheduled_task_models.py

fix(scheduler): enqueue busy scheduled task runs (#4918 )

2026-08-24 15:38:32 +08:00

test_scheduled_task_postgres.py

fix(scheduler): enqueue busy scheduled task runs (#4918 )

2026-08-24 15:38:32 +08:00

test_scheduled_task_queue.py

fix(scheduler): enqueue busy scheduled task runs (#4918 )

2026-08-24 15:38:32 +08:00

test_scheduled_task_repository.py

fix(scheduler): enqueue busy scheduled task runs (#4918 )

2026-08-24 15:38:32 +08:00

test_scheduled_task_router_behavior.py

fix(gateway): enforce run-create authorization on stateless endpoints (#5030 )

2026-08-27 14:59:31 +08:00

test_scheduled_task_router.py

feat: add scheduled tasks MVP (#3898 )

2026-07-04 21:51:57 +08:00

test_scheduled_task_schedules.py

fix(scheduler): normalize once-schedule next_run_at to UTC (#4607 )

2026-07-31 17:27:51 +08:00

test_scheduled_task_service.py

fix(scheduler): enqueue busy scheduled task runs (#4918 )

2026-08-24 15:38:32 +08:00

test_scheduler_config.py

feat(scheduler): make scheduled-run recursion_limit configurable (#4848 )

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

test_searxng_client.py

feat(community): add SearXNG and Browserless web search/fetch tools (#3451 )

2026-06-12 09:45:26 +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(serialization): strip base64 image data from streamed values events (#3631 )

2026-06-19 11:23:07 +08:00

test_serialize_message_content.py

feat(harness): integration ACP agent tool (#1344 )

2026-03-26 14:20:18 +08:00

test_serper_tools.py

fix(serper): ignore malformed image URLs (#4319 )

2026-07-21 08:15:33 +08:00

test_serply_tools.py

feat(community): add Serply web search tool (#5023 )

2026-08-28 10:30:30 +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_nginx_stop.py

fix: reap macOS nginx processes on stop (#3828 )

2026-06-27 23:30:54 +08:00

test_session_pool_singleton_lifecycle.py

fix(mcp): synchronize session pool singleton lifecycle (#3797 )

2026-07-07 23:09:06 +08:00

test_setup_agent_e2e_user_isolation.py

feat(agents): database-backed storage for custom agent definitions (#4359 )

2026-07-23 08:03:21 +08:00

test_setup_agent_http_e2e_real_server.py

fix(agents): make update_agent honor runtime.context user_id like setup_agent (#2867 )

2026-05-12 23:18:54 +08:00

test_setup_agent_tool.py

feat(agents): database-backed storage for custom agent definitions (#4359 )

2026-07-23 08:03:21 +08:00

test_setup_wizard.py

feat(models): add GLM-5.3-Flash thinking workaround (#5074 )

2026-08-28 22:24:10 +08:00

test_should_ignore_name.py

perf(sandbox): speed up should_ignore_name in glob/grep walks (#3657 )

2026-06-19 21:57:03 +08:00

test_skill_catalog.py

feat(skills): deferred skill discovery via describe_skill tool (#3775 )

2026-07-04 23:09:29 +08:00

test_skill_container_path_defaults.py

feat: emit structured runtime metadata (follow-up#3887) (#3906 )

2026-07-04 11:27:19 +08:00

test_skill_context.py

feat: emit structured runtime metadata (follow-up#3887) (#3906 )

2026-07-04 11:27:19 +08:00

test_skill_describe.py

feat(skills): deferred skill discovery via describe_skill tool (#3775 )

2026-07-04 23:09:29 +08:00

test_skill_manage_tool.py

fix(sandbox): enforce disabled skills in filesystem views (#4178 )

2026-07-31 17:55:24 +08:00

test_skill_metadata_prompt_injection.py

fix(skills): escape untrusted skill metadata before it enters the model prompt (#4128 )

2026-07-13 10:40:22 +08:00

test_skill_permissions.py

Fix custom skill install permissions (#3241 )

2026-05-28 15:48:32 +08:00

test_skill_policy_deferred_discovery.py

test(mcp): cover passive skill tool visibility (#4247 )

2026-07-17 14:39:35 +08:00

test_skill_projection.py

fix(skills): parse Responses API content blocks in moderation scanner (#4936 )

2026-08-24 21:27:43 +08:00

test_skill_request_scoped_secrets.py

fix(security): reject legacy MCP credentials in run metadata (#4448 )

2026-07-28 21:31:23 +08:00

test_skill_review_core.py

fix(skills): handle non-string frontmatter keys (#4167 )

2026-07-24 21:25:53 +08:00

test_skill_reviewer_public_skill.py

feat(skills): add skill review quality gate (#4037 )

2026-07-11 15:58:07 +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_tool_policy_middleware.py

fix(skills): safely tokenize portable allowed-tools patterns (#4984 )

2026-08-28 08:58:59 +08:00

test_skills_archive_root.py

refactor: extract shared skill installer and upload manager to harness (#1202 )

2026-03-25 16:28:33 +08:00

test_skills_bundled.py

fix(skills): apply allowed-tools only to active skills (#4098 )

2026-07-16 14:12:02 +08:00

test_skills_custom_router.py

fix(sandbox): enforce disabled skills in filesystem views (#4178 )

2026-07-31 17:55:24 +08:00

test_skills_installer.py

fix(skills): reject colon in zip member names to close NTFS ADS smuggling gap (#4236 )

2026-07-19 22:36:15 +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): safely tokenize portable allowed-tools patterns (#4984 )

2026-08-28 08:58:59 +08:00

test_skills_reload.py

fix(skills): reload mounted skills without restarting Gateway (#4264 )

2026-07-17 23:22:16 +08:00

test_skills_router_authz.py

fix(sandbox): enforce disabled skills in filesystem views (#4178 )

2026-07-31 17:55:24 +08:00

test_skills_validation.py

fix(skills): safely tokenize portable allowed-tools patterns (#4984 )

2026-08-28 08:58:59 +08:00

test_skillscan_native.py

test(skillscan): document known instance-client false negatives from #4296 (#4644 )

2026-08-03 17:17:01 +08:00

test_slack_channel_connections.py

fix(channels): add operational guardrails (#3584 )

2026-06-18 10:09:46 +08:00

test_slash_skill_contract.py

feat(frontend): render slash-skill activations as inline chips (#3981 )

2026-07-08 21:58:33 +08:00

test_slash_skills.py

fix(skills): parse Responses API content blocks in moderation scanner (#4936 )

2026-08-24 21:27:43 +08:00

test_soul_prompt_injection.py

fix(runtime): honor LangGraph Server identity for user-scoped data (#4538 )

2026-07-28 22:59:14 +08:00

test_sse_format.py

feat(gateway): implement LangGraph Platform API in Gateway, replace langgraph-cli (#1403 )

2026-03-30 16:02:23 +08:00

test_sse_observer_disconnect.py

feat(auth): add personal access tokens for programmatic API access (#5041 )

2026-08-29 23:50:45 +08:00

test_stateless_runs_owner_isolation.py

feat(gateway): seed checkpoint history (#4590 )

2026-07-31 17:25:07 +08:00

test_str_replace_empty_file.py

fix(sandbox): make an empty old_str a no-op in str_replace on any file (#4256 )

2026-07-22 09:20:54 +08:00

test_stream_bridge.py

feat(streaming): make heartbeat interval configurable (#5017 )

2026-08-30 10:46:01 +08:00

test_subagent_batch_repository.py

feat(subagents): add unified capacity and durable batch execution (#4998 )

2026-08-25 07:49:38 +08:00

test_subagent_batch_service.py

feat(subagents): add unified capacity and durable batch execution (#4998 )

2026-08-25 07:49:38 +08:00

test_subagent_batches_router.py

feat(subagents): add unified capacity and durable batch execution (#4998 )

2026-08-25 07:49:38 +08:00

test_subagent_capacity_config.py

feat(subagents): add unified capacity and durable batch execution (#4998 )

2026-08-25 07:49:38 +08:00

test_subagent_capacity.py

fix(subagents): harden background-task registry and capacity snapshot edge cases (#5086 )

2026-08-30 10:43:58 +08:00

test_subagent_checkpointer_isolation.py

fix(subagent): isolate subagent from parent run checkpointer (#3559 )

2026-06-14 10:30:45 +08:00

test_subagent_deferred_promotion_integration.py

feat(subagents): extend deferred MCP tool loading to subagents (#3432 )

2026-06-08 23:17:22 +08:00

test_subagent_description_injection.py

fix(security): html-escape subagent descriptions before the <subagent_system> block (#4157 )

2026-07-14 08:14:21 +08:00

test_subagent_execution_capacity.py

feat(subagents): add unified capacity and durable batch execution (#4998 )

2026-08-25 07:49:38 +08:00

test_subagent_executor.py

feat(harness): subagent report contract and delegation acceptance criteria (#5090 )

2026-08-30 11:39:25 +08:00

test_subagent_limit_middleware.py

feat(subagents): add unified capacity and durable batch execution (#4998 )

2026-08-25 07:49:38 +08:00

test_subagent_prompt_security.py

feat: add managed subagents and delegation scopes (#4887 )

2026-08-24 11:04:23 +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

fix(agent): route subagents by net benefit (#4384 )

2026-07-30 07:21:55 +08:00

test_subagent_runtime.py

feat(subagents): add unified capacity and durable batch execution (#4998 )

2026-08-25 07:49:38 +08:00

test_subagent_skills_config.py

refactor: thread app_config through lead and subagent task path (#2666 )

2026-05-02 06:37:49 +08:00

test_subagent_status_contract.py

feat(harness): subagent receipt citation verification (#5076 )

2026-08-29 16:56:56 +08:00

test_subagent_step_events.py

feat(subagents): show effective model and token usage on task cards (#4049 )

2026-07-11 15:41:57 +08:00

test_subagent_timeout_config.py

feat(agent): Add subagent total delegation cap (#4115 )

2026-07-13 19:26:07 +08:00

test_subagent_token_collector.py

fix(gateway): attribute token usage to actual models (#3658 )

2026-06-19 21:42:42 +08:00

test_subagents_router.py

feat: add managed subagents and delegation scopes (#4887 )

2026-08-24 11:04:23 +08:00

test_suggestions_router.py

feat(suggestions): configure follow-up suggestion count (#4533 )

2026-07-28 19:35:21 +08:00

test_summarization_middleware.py

fix(middleware): Fix the issue where summarization compressed away the user message of the current request (#4882 )

2026-08-22 16:47:11 +08:00

test_summarization_summary_text.py

feat: add manual context compaction (#3969 )

2026-07-07 19:55:33 +08:00

test_summarize_checkpoint_channels.py

bench(checkpoint): production-shaped full/delta benchmark with configurable snapshot frequency (#4467 )

2026-07-27 11:47:49 +08:00

test_summarize_checkpoint_production.py

bench(checkpoint): production-shaped full/delta benchmark with configurable snapshot frequency (#4467 )

2026-07-27 11:47:49 +08:00

test_support_bundle.py

fix(gateway):unify thread id validation (#4589 )

2026-08-01 19:42:44 +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_tool_core_logic.py

feat(harness): subagent report contract and delegation acceptance criteria (#5090 )

2026-08-30 11:39:25 +08:00

test_task_tool_usage_recorder.py

fix(stability): resolve P0 blockers from v2.0-m1-rc1 stability audit (#3107 ) (#3131 )

2026-05-21 21:18:10 +08:00

test_telegram_channel_connections.py

fix(channels): move Telegram _attach_connection_identity to main event loop (#4815 )

2026-08-23 10:27:19 +08:00

test_tencent_wsa_tools.py

feat(search): add Tencent Cloud WSA provider (#5057 )

2026-08-27 18:12:05 +08:00

test_tenki_provider.py

fix(deps): depend on renamed tenki package instead of tenki-sandbox (#5087 )

2026-08-30 10:37:58 +08:00

test_terminal_response_middleware.py

fix: ensure visible response after tool runs (#4033 )

2026-07-11 15:53:14 +08:00

test_thread_data_middleware.py

fix(runtime): honor LangGraph Server identity for user-scoped data (#4538 )

2026-07-28 22:59:14 +08:00

test_thread_id_route_contract.py

fix(gateway):unify thread id validation (#4589 )

2026-08-01 19:42:44 +08:00

test_thread_id_validation.py

fix(gateway):unify thread id validation (#4589 )

2026-08-01 19:42:44 +08:00

test_thread_messages_feedback.py

feat(chat): edit and rerun latest user turn (#4377 )

2026-07-27 22:46:51 +08:00

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

feat(threads): distinguish branched conversations (#4983 )

2026-08-25 08:29:18 +08:00

test_thread_regenerate_prepare.py

fix(gateway): enforce run-create authorization on stateless endpoints (#5030 )

2026-08-27 14:59:31 +08:00

test_thread_run_messages_pagination.py

fix(runs): stamp elapsed duration once per run across message APIs (#4163 )

2026-07-29 12:47:30 +08:00

test_thread_run_query_validation.py

feat(chat): edit and rerun latest user turn (#4377 )

2026-07-27 22:46:51 +08:00

test_thread_state_promoted.py

fix(tool-search): reliably hide deferred MCP schemas by removing the ContextVar (closures + graph state) (#3342 )

2026-06-02 22:43:22 +08:00

test_thread_state_reducers.py

feat(checkpoint): dual-mode checkpoint storage with LangGraph DeltaChannel (#4292 )

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

test_thread_token_usage.py

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

2026-07-31 21:57:22 +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

feat(auth): add personal access tokens for programmatic API access (#5041 )

2026-08-29 23:50:45 +08:00

test_three_way_skills_mount_e2e.py

fix(sandbox): keep skill reads on provider mappings (#4792 )

2026-08-13 21:20:49 +08:00

test_tiktoken_cache_and_count_tokens.py

feat(memory): pluggable memory abstraction with self-contained DeerMem backend (#4122 )

2026-07-15 11:21:04 +08:00

test_title_generation.py

refactor: split backend into harness (deerflow.*) and app (app.*) (#1131 )

2026-03-14 22:55:52 +08:00

test_title_middleware_core_logic.py

fix(agent): reserve ellipsis room so the local title respects max_chars (#4052 )

2026-07-11 23:15:03 +08:00

test_todo_middleware.py

fix(todo-middleware): call super in wrap_model_call to restore write_todos prompt injection (#4714 ) (#4735 )

2026-08-11 11:41:31 +08:00

test_token_budget_middleware.py

fix(subagents): unify guardrail caps on additive stop_reason + add token_budget (#3875 Phase 2) (#3980 )

2026-07-08 22:26:06 +08:00

test_token_usage_by_model.py

feat(gateway): cache-aware cost accounting (#3920 )

2026-07-04 23:14:46 +08:00

test_token_usage_config.py

enable token usage by default (#2841 )

2026-05-10 22:00:57 +08:00

test_token_usage_middleware.py

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

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

test_token_usage.py

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

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

test_tool_args_schema_no_pydantic_warning.py

feat(chat): edit and rerun latest user turn (#4377 )

2026-07-27 22:46:51 +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_error_handling_middleware.py

feat(harness): deterministic tool receipts with model-visible ledger (RFC #4651 , layer 1) (#4659 )

2026-08-23 15:43:37 +08:00

test_tool_error_handling_subagent_stamp.py

feat: emit structured runtime metadata (follow-up#3887) (#3906 )

2026-07-04 11:27:19 +08:00

test_tool_output_budget_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_tool_output_truncation.py

fix: add output truncation to ls_tool to prevent context window overflow (#1896 )

2026-04-06 15:09:57 +08:00

test_tool_progress_middleware.py

feat(middleware): add structured tool result meta and tool-progress state machine (#3601 )

2026-07-06 20:57:41 +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_meta.py

feat(middleware): add structured tool result meta and tool-progress state machine (#3601 )

2026-07-06 20:57:41 +08:00

test_tool_result_sanitization_middleware.py

fix(security): neutralize prompt-injection tags in web_capture results (#4099 )

2026-07-12 11:24:24 +08:00

test_tool_search.py

fix(mcp): validate MCP tool names at load so deferred prompts stay inert (#4154 )

2026-07-14 09:49:43 +08:00

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

fix(gateway): prefer X-Trace-Id over metadata.deerflow_trace_id when header is set (#4283 )

2026-07-19 09:13:51 +08:00

test_trace_middleware.py

fix(gateway): prefer X-Trace-Id over metadata.deerflow_trace_id when header is set (#4283 )

2026-07-19 09:13:51 +08:00

test_tracing_config.py

feat(trace): add agent observability with Monocle (#4024 )

2026-07-14 08:58:06 +08:00

test_tracing_factory.py

feat(trace): add agent observability with Monocle (#4024 )

2026-07-14 08:58:06 +08:00

test_tracing_metadata.py

feat(observability): add trace-id correlation and enhanced logging (#3902 )

2026-07-03 08:01:46 +08:00

test_tui_app.py

fix(tui): preserve transcript scroll position (#4975 )

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

test_tui_cli_main.py

fix(cli): allow overriding agent recursion limit (#4615 )

2026-08-04 08:33:10 +08:00

test_tui_cli.py

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

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

test_tui_command_registry.py

fix(tui): derive /help text from the command registry (#4327 )

2026-07-22 07:53:50 +08:00

test_tui_composer.py

feat(tui): Hermes-like terminal workbench (deerflow) backed by DeerFlowClient (#3760 )

2026-06-25 20:10:49 +08:00

test_tui_input_history.py

feat(tui): Hermes-like terminal workbench (deerflow) backed by DeerFlowClient (#3760 )

2026-06-25 20:10:49 +08:00

test_tui_message_format.py

feat(tui): Hermes-like terminal workbench (deerflow) backed by DeerFlowClient (#3760 )

2026-06-25 20:10:49 +08:00

test_tui_overlays.py

feat(tui): Hermes-like terminal workbench (deerflow) backed by DeerFlowClient (#3760 )

2026-06-25 20:10:49 +08:00

test_tui_palette_render.py

feat(tui): Hermes-like terminal workbench (deerflow) backed by DeerFlowClient (#3760 )

2026-06-25 20:10:49 +08:00

test_tui_palette.py

feat(tui): Hermes-like terminal workbench (deerflow) backed by DeerFlowClient (#3760 )

2026-06-25 20:10:49 +08:00

test_tui_persistence.py

feat(tui): Hermes-like terminal workbench (deerflow) backed by DeerFlowClient (#3760 )

2026-06-25 20:10:49 +08:00

test_tui_render.py

feat(tui): Hermes-like terminal workbench (deerflow) backed by DeerFlowClient (#3760 )

2026-06-25 20:10:49 +08:00

test_tui_runtime.py

fix(tui): stop empty-id assistant deltas from merging across turns (#4201 )

2026-07-15 22:27:00 +08:00

test_tui_session.py

feat(tui): Hermes-like terminal workbench (deerflow) backed by DeerFlowClient (#3760 )

2026-06-25 20:10:49 +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

feat(tui): add clear command (#4306 )

2026-07-20 23:56:37 +08:00

test_update_agent_e2e_user_isolation.py

fix(agents): make update_agent honor runtime.context user_id like setup_agent (#2867 )

2026-05-12 23:18:54 +08:00

test_update_agent_tool.py

feat: add managed subagents and delegation scopes (#4887 )

2026-08-24 11:04:23 +08:00

test_updater_truncation.py

feat(memory): memory message processing (#4447 )

2026-07-26 21:16:36 +08:00

test_updater_watermark.py

feat(memory): memory message processing (#4447 )

2026-07-26 21:16:36 +08:00

test_uploads_manager.py

fix(uploads): keep deduplicated filenames within the 255-byte limit (#5059 )

2026-08-28 09:16:51 +08:00

test_uploads_middleware_core_logic.py

fix(runtime): honor LangGraph Server identity for user-scoped data (#4538 )

2026-07-28 22:59:14 +08:00

test_uploads_router.py

fix(uploads): keep deduplicated filenames within the 255-byte limit (#5059 )

2026-08-28 09:16:51 +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_scoped_skill_storage.py

fix(skills): parse Responses API content blocks in moderation scanner (#4936 )

2026-08-24 21:27:43 +08:00

test_utils_llm_text.py

test: add unit tests for deerflow.utils.llm_text (#4046 )

2026-07-11 09:18:12 +08:00

test_utils_messages.py

fix(context): resolve context compress bug (#4065 )

2026-07-14 10:43:13 +08:00

test_utils_time.py

fix(gateway): return ISO 8601 timestamps from threads endpoints (#2599 )

2026-05-02 15:16:16 +08:00

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_view_image_middleware.py

perf(middleware): stop checkpointing view_image base64 payloads (#5014 )

2026-08-27 09:12:37 +08:00

test_view_image_tool.py

feat(tools): support GIF images in view_image (#4438 )

2026-07-24 13:12:43 +08:00

test_vllm_provider.py

feat(models): support cumulative vLLM stream usage (#4537 )

2026-07-28 19:56:40 +08:00

test_wait_disconnect_handling.py

fix(streaming): signal replay history gaps (#4426 )

2026-07-27 07:13:06 +08:00

test_warm_pool_lifecycle.py

feat(sandbox): warm pool for boxlite (#3951 )

2026-07-06 07:21:12 +08:00

test_web_fetch_error_shell_meta.py

fix(agents): classify web_fetch error pages as errors, not successful evidence (#4314 )

2026-07-20 23:05:47 +08:00

test_wechat_channel.py

fix(wechat): validate timing configuration (#4280 )

2026-07-18 17:53:30 +08:00

test_wecom_ws_text.py

fix(wecom): guard null quote fields in _on_ws_text to prevent AttributeError (#4069 )

2026-07-12 07:52:45 +08:00

test_worker_langfuse_metadata.py

fix(runtime): cancel runs across live gateway workers (#4500 )

2026-07-28 21:45:20 +08:00

test_worker_stream_subgraph_namespace.py

fix(runtime): cancel runs across live gateway workers (#4500 )

2026-07-28 21:45:20 +08:00

test_worker_subagent_persistence.py

fix(runs): re-buffer subagent event batch on flush failure instead of dropping (#4082 )

2026-07-12 11:51:31 +08:00

test_workspace_changes.py

fix(mcp): exclude internal temp files from workspace changes (#4898 )

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

test_write_file_tool_size_guard.py

fix(#3189 ): prevent write_file streaming timeout on long reports (#3195 )

2026-06-07 17:47:11 +08:00