mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-09-11 06:28:58 +00:00
9146bfa03d
* refactor(gateway): issue request trace ids unconditionally The request trace id was gated behind logging.enhance.enabled at every entry point, so downstream code had to keep asking whether one existed: a header-provenance flag in its own ContextVar, a precedence resolver, and three-level carrier fallbacks at each consumer. Bind one unconditionally instead. TraceMiddleware covers Gateway HTTP; ensure_trace_context covers the entry points that never touch ASGI -- scheduled occurrences, MCP task notification runs, IM channel messages, and the embedded client -- each scoped to one unit of work so a long-lived worker task cannot leak one occurrence's id into the next. The ContextVar becomes the only source; the response header, runtime context, run metadata and log records are derived outputs. Consumers now use ensure_trace_id() or resolve_trace_id(*carriers) and drop their presence guards. Removed: resolve_deerflow_trace_id, the header-provenance flag and its three helpers, set/reset_current_trace_id, is_trace_correlation_enabled and its gateway alias. BREAKING CHANGE: every Gateway HTTP response now carries X-Trace-Id and it cannot be turned off; logging.enhance.enabled controls log output only. Installations on the default enabled: false will start seeing the header. No config keys were added or removed. * fix(gateway): stop persisting a caller-supplied trace id on the run record body.metadata forks two ways: through build_run_config into the live run config, which the run worker restamps, and through create_or_reject into the run record that the runs API echoes verbatim. Only the first was covered, so a client sending metadata.deerflow_trace_id made the most durable and most visible surface of a run disagree with the X-Trace-Id and the log lines the same request produced -- a correlation id that does not match the logs is worse than none. Stamp the server-issued id once at the trust boundary so both forks receive it, preserving the caller's own metadata keys. Close the same gap on config.context, which reaches the runtime context by a separate path: _build_runtime_context no longer merges server-owned keys from the caller, and _install_runtime_context assigns rather than setdefaults. A thread's metadata is no longer seeded with the run-scoped id of whichever run created it -- one thread spans many runs and as many trace ids. Found by driving a real run through the Gateway and reading the run back from the runs API; every unit test built its metadata by hand and so could not see it. * fix(gateway): expose X-Trace-Id to split-origin browser clients X-Trace-Id is not on the CORS safelist, so a browser client served from a separate origin could not read it -- and those are exactly the clients that cannot read the Gateway's logs either, leaving them with nothing to quote in a bug report. Same-origin nginx deployments were unaffected, which is why this stayed hidden. Add it to CORS_EXPOSED_HEADERS beside Content-Location, referencing TRACE_ID_HEADER rather than repeating the literal. * fix(gateway): keep X-Trace-Id on unhandled-exception 500s Starlette's ServerErrorMiddleware sits outside every user middleware and emits unhandled-exception 500s through the raw send, so those responses never pass TraceMiddleware's header-writing wrapper. The 500 for a server bug is exactly the response a user most needs to correlate with a log line, and it was the one response that shipped without the id. TraceMiddleware now tracks whether http.response.start has been sent. On an exception with no response started it emits its own plain 500 carrying the header, then re-raises: the outer ServerErrorMiddleware sees the response already started and only re-raises too, so the server's exception logging is untouched. An exception mid-stream keeps propagating unchanged — a second response start cannot be sent, and the already-written header stands. The trace id is printable ASCII by construction (normalize_trace_id / generate_trace_id), which is what makes the raw latin-1 header encoding safe. * fix(gateway): strip the forged trace id from the persisted request echo The run-record fix stopped a forged metadata.deerflow_trace_id on the authoritative metadata surface, but the raw request echo still carried one: create_or_reject persists body.config verbatim as runs.kwargs_json, which the runs API serves back. A client posting config.context.deerflow_trace_id therefore still got its forged value stored and echoed on one API surface while the header, logs, run metadata, and checkpoint all carried the real id — the id is ignored as input there, so echoing it back only manufactures disagreement. Two changes close it. redact_config_secrets — already the shared scrub for that echo, applied at admission and again at serve time, so historical records are covered too — now also drops deerflow_trace_id from config.metadata and config.context. And build_run_config now merges run metadata onto a copy of the caller's config["metadata"] instead of updating it in place: the nested values of the request config are reference copies, so the in-place merge was writing the server-stamped key through into body.config, contaminating the "what the client sent" record before it was persisted (and incidentally masking the forged-value echo on the metadata container). The regression test posts a forged id through body.metadata, config.metadata, and config.context at once and reads the kwargs echo back off the run record, failing if either leak returns. * docs(harness): record the trace-echo scrub, 500 fallback, and accepted retry divergence The trace section of the harness AGENTS.md now covers the two fixes that close the derived-output rule (the kwargs-echo scrub in redact_config_secrets plus build_run_config's copy merge, and TraceMiddleware's own 500 for unhandled exceptions), and CHANGELOG gains their Fixed entries. It also writes down the one accepted divergence: a crash-recovered scheduled launch reuses the durable run through its idempotency key, and start_run returns early on idempotency_reused without restamping — so the run record keeps the first attempt's deerflow_trace_id while the retry's own log lines carry the freshly minted id of its ensure_trace_context binding. The divergence is confined to the crash-recovery window and is accepted rather than fixed: restamping on reuse would rewrite a persisted record for a run that already exists, which is worse than two ids that each correlate their own attempt's logs. Written down so the next reader of the scheduler recovery path does not diagnose it as a bug. * docs(config): align the logging.enhance schema note with the unconditional trace id The config-module AGENTS.md still described logging.enhance as the gate for the Gateway X-Trace-Id header and Langfuse deerflow_trace_id. That model is gone: ids are issued unconditionally and this block decides log output only. Left as-is, the stale wording invites an agent to "restore" a header gate it believes was lost. Reworded to match the sibling AGENTS.md files and config.example.yaml, with a pointer to the Request Trace Context section that owns the full model. * docs(changelog): link the trace entries to #5119 The five new entries pointed at the ([#XXXX]) placeholder with no reference definition, rendering as literal text instead of a link — and RELEASING.md step 2 relies on those references when the section becomes release notes. All five now point at #5119, with the definition appended to the reference block. * refactor(harness): rename _stream_without_trace_context to _stream_turn The name asserted the opposite of what the method now does. It was accurate while logging.enhance.enabled could route stream() around the trace scope; with the gate gone it is the only stream implementation left, and it binds the id itself via ensure_trace_id(). Private, so the rename touches only the definition and the one stream() call site. * docs(harness): fit the trace-context guidance inside the AGENTS.md chain budget The expanded Request Trace Context section pushed the effective AGENTS.md chain for agents/middlewares to 99,815 bytes, past the 98,304 hard limit scripts/check_agent_guidance.py enforces in CI (AG002). Compressed the section from 7,359 to 4592 bytes with no facts removed: the entry-point table, the derived-output rule and its enforcement points, the accepted scheduled-retry divergence, the two resolution helpers, the stream() binding rationale, the log-output-only gate, the CORS listing, the 500 fallback, and the test map all remain. Sized against the merge, not just the branch: current main grew the same chain by ~724 bytes, so the check was verified on the merged tree as well (97,772 bytes; branch tree 97,048). * fix(gateway): declare content-length on the fallback 500 The pre-response 500 declared content-type but no content-length, leaving the framing to the ASGI server: chunked on HTTP/1.1, close-delimited on HTTP/1.0 — the one wire difference from the ServerErrorMiddleware response it replaces, which sends content-length: 21. The explicit header keeps the fallback byte-identical to what clients saw before. * docs(readme): drop the trace-correlation condition from the translations The zh/ja/fr/ru Langfuse sections still said metadata.deerflow_trace_id matches X-Trace-Id "when request trace correlation is enabled". The id now always matches and that condition no longer exists, so each bullet states the unconditional match and that logging.enhance.enabled only controls whether the id is printed into logs — the one piece of the feature a user can still configure. * test(gateway): pin TraceMiddleware wiring through create_app() Every X-Trace-Id test exercised a hand-built four-route app, so the real stack's add_middleware(TraceMiddleware) line was pinned by nothing: deleting it — or short-circuiting above it — passed CI while silently dropping both the response header and the ambient id the run-record stamp and enhanced log records derive from. One case now drives /health through create_app() and asserts the inbound id round-trips; mutation-checked by removing the wiring line, which fails exactly this test. * docs(gateway): note the fallback 500 is CORS-opaque The pre-response 500 is emitted outside CORSMiddleware — the exception has already unwound past it — so it carries no Access-Control-Allow-Origin and a split-origin browser client cannot read the id on this one response, unchanged from the ServerErrorMiddleware 500 it replaces. Documented on the class and in the CHANGELOG entry rather than fixed: replicating the origin allowlist outside CORSMiddleware would let the two policies drift. * fix(harness): keep abandoned-stream cleanup inside the trace binding stream() binds the turn's id around each next(inner) and resets it before yielding, but the finally's inner.close() ran after that binding was gone. Abandoning the stream therefore drove the inner LangGraph generator's GeneratorExit/finally path with no trace id — or an unrelated ambient one from whichever context ran the close — so cancellation and finalization logs and callbacks did not correlate with the turn they belong to. inner.close() is now wrapped in a local bind/reset of the same turn id. The token is set and reset in the same frame, never across a yield, so the per-step cross-context safety is preserved even when GC closes the generator from another Context — pinned by the existing copy_context close test, which now exercises this path. The regression test records the id from the inner generator's finally and fails without the binding. * test(harness): teach the worker-trace fake about RunManager.cleanup Upstream #5112 (bound gateway memory after terminal runs) added a run_manager.cleanup(run_id) call to run_agent's finalization, so the merge-commit CI run failed all five worker-trace-binding tests with AttributeError on this PR's _FakeRunManager. The fake gains the same no-op shape as its other methods. * docs(gateway): bring the gateway AGENTS.md back under its soft budget Upstream #5092 grew backend/app/gateway/AGENTS.md to 40,966 bytes, 6 over the 40,960 soft budget that test_agent_guidance_check.py::test_repository_guidance_stays_below_soft_budgets_and_avoids_doc_indexes enforces — its Unit Tests run on main was cancelled by push concurrency, so main is currently red on that test and every PR merge-run inherits the failure. Two whitespace/wording trims in the row #5092 touched (a doubled space, and "its configured `context_window`" → "its `context_window`") bring the file to 40,953 with no content change. --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
5.6 KiB
5.6 KiB
Tracing System (packages/harness/deerflow/tracing/)
LangSmith and Langfuse are both supported. The wiring lives in two layers:
factory.py::build_tracing_callbacks()— returns the LangChainCallbackHandlerlist for the providers currently enabled via env vars (LANGSMITH_TRACING,LANGFUSE_TRACING, etc.). The handlers are attached at the graph invocation root for in-graph runs (make_lead_agentandDeerFlowClient.streamboth append them toconfig["callbacks"]before invoking the graph) so a single run produces one trace with all node / LLM / tool calls as child spans. Standalone callers — anything that invokes a model outside such a graph (e.g.MemoryUpdater) — keepcreate_chat_model's defaultattach_tracing=True, which falls back to model-level callback attachment.metadata.py::build_langfuse_trace_metadata()— builds the Langfuse-reserved trace attributes forRunnableConfig.metadata. The Langfuse v4langchain.CallbackHandlerlifts these onto the root trace (see its_parse_langfuse_trace_attributes), but only when it seeson_chain_start(parent_run_id=None)— which is why the callbacks have to live at the graph root, not the model.
Trace-attribute injection points: both runtime/runs/worker.py::run_agent (gateway path) and client.py::DeerFlowClient.stream (embedded path) merge the metadata into config["metadata"] right before constructing the graph. subagents/executor.py::_aexecute does the same for every subagent run so subagent traces group under the parent thread's session card (carrying the parent thread_id → langfuse_session_id, the user_id captured at task_tool → langfuse_user_id, and a subagent:<normalized-name> trace name). Caller-supplied keys win via setdefault, so an external session_id override is preserved. Field mapping:
| Langfuse field | Source |
|---|---|
langfuse_session_id |
LangGraph thread_id |
langfuse_user_id |
get_effective_user_id() (default in no-auth); for subagents, captured from runtime.context at task_tool time via resolve_runtime_user_id() |
langfuse_trace_name |
RunRecord.assistant_id / client agent_name (defaults to lead-agent); for subagents, subagent:<name> (lowercased, _ → -) |
langfuse_tags |
env:<DEER_FLOW_ENV> + model:<model_name> |
deerflow_trace_id |
Current entry trace id from deerflow.trace_context; always written, and always equal to the X-Trace-Id the same Gateway request returned. Not gated by config — see packages/harness/deerflow/AGENTS.md |
Returns {} when Langfuse is not in the enabled providers — LangSmith-only deployments are unaffected. Set DEER_FLOW_ENV (or ENVIRONMENT) to tag traces by deployment environment. Tests live in tests/test_tracing_factory.py, tests/test_tracing_metadata.py, tests/test_worker_langfuse_metadata.py, tests/test_client_langfuse_metadata.py, and tests/test_subagent_executor.py::TestSubagentTracingWiring.
Monocle telemetry is a third provider, structurally unlike LangSmith/Langfuse. It is not a LangChain callback: tracing/monocle.py::setup_monocle_tracing_if_enabled() calls monocle_apptrace.setup_monocle_telemetry() once, which installs a process-global OTel TracerProvider, patches span serialization, and auto-instruments the openai/langchain/langgraph clients. Because that is a one-time, process-global side effect (not a per-run callback), it is initialized from the Gateway lifespan (app/gateway/app.py) — never from build_tracing_callbacks() — and it is off by default. The setup call was deliberately moved out of agents/__init__.py, so import deerflow.agents must never start tracing (pinned by tests/test_monocle_tracing.py::test_no_import_time_setup). The Gateway lifespan is the sole call site (pinned by test_gateway_lifespan_initializes_monocle), so unlike LangSmith/Langfuse — which attach at the graph roots and cover every path — the embedded DeerFlowClient and the TUI are not instrumented; embedded users who want Monocle traces call setup_monocle_tracing_if_enabled() themselves before running the agent.
Unlike the Langfuse metadata above, DeerFlow injects no per-run fields into Monocle traces — the only attribute it sets is workflow_name="deer-flow"; every span attribute (span.type, entity.*, token usage, span inputs/outputs, scope.agentic.session) is produced by Monocle's own metamodel and auto-instrumentation, so there is no DeerFlow trace-attribute layer to maintain here.
Config is env-driven like the others — MonocleTracingConfig, built in get_tracing_config() and gated by is_monocle_tracing_enabled(). MONOCLE_TRACING enables it; MONOCLE_EXPORTERS selects exporters (default file → trace JSON in .monocle/; also console, okahu, s3, blob, gcs, where okahu requires OKAHU_API_KEY). setup_monocle_tracing_if_enabled() stays a thin wrapper on purpose: monocle_apptrace already guards duplicate setup (instrumentor.py::check_duplicate_setup) and never force-overrides an existing global provider, so the wrapper only gates on config. Coexistence with Langfuse (v4, also OTel-based) is verified: whichever library initializes second reuses the existing global TracerProvider and attaches its own span processor, so neither side loses spans (pinned by test_coexists_with_langfuse). Both processors see all spans, so Monocle's exporters also capture Langfuse's spans when both are enabled. (LangSmith is a plain callback and coexists trivially.) Tests: tests/test_monocle_tracing.py.