Files
deer-flow/backend/tests/test_worker_langfuse_metadata.py
T
Xinmin Zeng df95154282 fix(tracing): propagate session_id and user_id into Langfuse traces (#2944)
* fix(tracing): propagate session_id and user_id into Langfuse traces

Adds Langfuse v4 reserved trace attributes (langfuse_session_id,
langfuse_user_id, langfuse_trace_name, langfuse_tags) to
RunnableConfig.metadata inside the run worker, so the langchain
CallbackHandler can lift them onto the root trace.

- New deerflow.tracing.metadata.build_langfuse_trace_metadata() returns
  the reserved keys when Langfuse is in the enabled providers, else {}.
- worker.run_agent merges them with setdefault so caller-supplied keys
  win, allowing per-request overrides from upstream metadata.
- session_id mirrors the LangGraph thread_id; user_id reads
  get_effective_user_id() (falls back to "default" in no-auth mode).
- trace_name defaults to "lead-agent"; tags carry env and model name
  when DEER_FLOW_ENV (or ENVIRONMENT) and a model name are present.

Closes #2930

* fix(tracing): attach Langfuse callback at graph root so metadata propagates

The first commit injected ``langfuse_session_id`` / ``langfuse_user_id`` /
``langfuse_trace_name`` / ``langfuse_tags`` into ``RunnableConfig.metadata``,
but on ``main`` the Langfuse callback is attached at *model* level
(``models/factory.py``). LangChain still threads ``parent_run_id`` through
the contextvar, so the handler sees the model as a nested observation and
``__on_llm_action`` strips the ``langfuse_*`` keys
(``keep_langfuse_trace_attributes=False``). The trace's top-level
``sessionId`` / ``userId`` therefore stayed empty in deer-flow's LangGraph
runtime — confirmed live against a real Langfuse instance.

This commit moves the callback to the **graph invocation root** so the
handler fires ``on_chain_start(parent_run_id=None)`` and runs the
``propagate_attributes`` path that actually lifts ``session_id`` /
``user_id`` onto the trace:

- ``models/factory.py``: add ``attach_tracing`` keyword (default ``True``)
  so standalone callers (``MemoryUpdater``, etc.) keep their direct
  model-level tracing.
- ``agents/lead_agent/agent.py``: call ``build_tracing_callbacks()`` once
  inside ``_make_lead_agent`` and append the result to
  ``config["callbacks"]``; the four in-graph ``create_chat_model`` sites
  (bootstrap, default agent, sync + async summarization) pass
  ``attach_tracing=False`` to avoid duplicate spans.
- ``agents/middlewares/title_middleware.py``: same ``attach_tracing=False``
  for the title-generation model, since it inherits the graph's
  RunnableConfig via ``_get_runnable_config``.

Test updates:

- ``tests/test_lead_agent_model_resolution.py`` and
  ``tests/test_title_middleware_core_logic.py``: extend the fake
  ``create_chat_model`` signatures / mock assertions to accept the new
  ``attach_tracing`` kwarg.
- ``tests/test_worker_langfuse_metadata.py``: switch the no-user fallback
  test from direct ContextVar mutation to ``monkeypatch.setattr`` on
  ``get_effective_user_id`` to avoid pollution across the langfuse OTel
  global tracer provider.
- ``tests/conftest.py``: add an autouse fixture that resets
  ``deerflow.config.title_config._title_config`` to its pristine default
  after every test. Any test that loads the real ``config.yaml`` (via
  ``get_app_config()``) calls ``load_title_config_from_dict`` and mutates
  the module-level singleton, which previously poisoned the
  title-middleware suite when run after, e.g., the new
  ``test_worker_langfuse_metadata.py`` cases. The fixture is independent
  of this PR's main change but unblocks the cross-file test run.

Live verification (same Langfuse instance as before):

- Drove ``worker.run_agent`` against the real ``make_lead_agent`` +
  ``gpt-4o-mini`` for three distinct ``user_context`` identities
  (``fancy-engineer``, ``alice-pm``, ``bob-designer``).
- Each run produced one ``lead-agent`` trace whose top-level
  ``sessionId`` / ``userId`` / ``tags`` carry the expected values, e.g.
  ``session=e2e-2930-8f347c-alice-pm user=alice-pm name='lead-agent'
  tags=['model:gpt-4o-mini']``.

Refs #2930.

* fix(tracing): extend root-callback + metadata injection to the embedded client

Addresses Copilot review on PR #2944.

Commit 2 disabled model-level tracing for ``TitleMiddleware`` and
``_create_summarization_middleware`` because ``_make_lead_agent`` now
attaches the tracing callbacks at the graph invocation root. But the
embedded ``DeerFlowClient`` does not call ``_make_lead_agent`` — it
calls ``_build_middlewares`` directly and never appends the tracing
handlers to its ``RunnableConfig``. So under the embedded path,
title-generation and summarization LLM calls were left untraced —
a regression introduced by this PR.

This commit mirrors the gateway worker's injection in
``DeerFlowClient.stream``:

- Append ``build_tracing_callbacks()`` to ``config["callbacks"]`` so
  the Langfuse handler sees ``on_chain_start(parent_run_id=None)`` at
  the graph root and runs the ``propagate_attributes`` path.
- Merge ``build_langfuse_trace_metadata(...)`` into
  ``config["metadata"]`` with ``setdefault`` so caller-supplied keys
  still win.
- ``_ensure_agent`` now creates its main model with
  ``attach_tracing=False`` to avoid duplicate spans now that the
  callback lives at the graph root.

Docs:
- ``backend/CLAUDE.md`` Tracing section rewritten to describe the
  graph-root attachment model (replacing the inaccurate
  "at model-creation time" wording).
- ``README.md`` Langfuse section now lists both injection points
  (worker + client) instead of only the worker path.

Tests:
- ``tests/test_client_langfuse_metadata.py`` (new, 3 cases):
  callbacks + metadata are injected when Langfuse is enabled,
  caller-supplied metadata overrides win via ``setdefault``, and the
  injection is inert when Langfuse is disabled.

Live verification on the real Langfuse instance:

  === user=fancy-client ===
    id=cbd22847..  session=client-2930-6b9491-fancy-client  user=fancy-client  name='lead-agent'
  === user=alice-client ===
    id=b4f6f576..  session=client-2930-6b9491-alice-client  user=alice-client  name='lead-agent'

Refs #2930.

* refactor(tracing): address maintainer review on PR #2944

Addresses @WillemJiang's 5 comments.

1. Duplicated metadata-injection code between worker.py and client.py
   New ``deerflow.tracing.inject_langfuse_metadata(config, ...)`` helper
   takes the 10-line build + merge + setdefault logic that was duplicated
   in ``runtime/runs/worker.py`` and ``client.py``. Both callers now share
   a single source of truth, so the two paths cannot drift.

2. Direct private-attribute mutation in conftest.py and tests
   Added public ``reset_tracing_config()`` / ``reset_title_config()``
   functions. ``tests/conftest.py`` and every test that previously did
   ``tracing_module._tracing_config = None`` or
   ``title_module._title_config = TitleConfig()`` now goes through the
   public API. A future internal rename will surface as an ImportError
   instead of a silent no-op.

3. client.py reading os.environ directly
   ``DeerFlowClient.__init__`` grows an optional ``environment`` parameter
   so programmatic callers can pass the deployment label explicitly.
   ``stream()`` consults ``self._environment`` first and only falls back
   to ``DEER_FLOW_ENV`` / ``ENVIRONMENT`` env vars when nothing was
   passed in. Backwards compatible — env-var behaviour preserved for
   callers that opt to keep using it.

4. build_tracing_callbacks() cached on hot path
   Not implemented. Inspected the langfuse v4 ``langchain.CallbackHandler``
   constructor: it only resolves the module-level singleton client via
   ``get_client()`` and initialises a few dicts (no I/O, no env parsing
   at construction time). The build is essentially free. Caching would
   trade a non-measurable speedup for two real risks: handler instances
   carry per-run state internally (``_run_states``, ``_root_run_states``,
   ``last_trace_id``), and tracing config can be reloaded by env-var
   changes between runs. Will revisit if profiling ever shows it as
   a hot spot.

5. attach_tracing=False easy to forget at new in-graph call sites
   - Module docstring at the top of ``lead_agent/agent.py`` documents
     the invariant ("every in-graph ``create_chat_model`` MUST pass
     ``attach_tracing=False``") and enumerates the current sites.
   - New regression test
     ``test_make_lead_agent_attaches_tracing_callbacks_at_graph_root`` in
     ``tests/test_lead_agent_model_resolution.py`` locks both halves of
     the invariant: ``config["callbacks"]`` carries the tracing handler
     after ``_make_lead_agent``, AND every ``create_chat_model`` call
     captured by the test passes ``attach_tracing=False``. A future
     in-graph site that forgets the flag will fail this test.

Lint clean. Full touched-suite bundle: 246 passed.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-05-21 16:49:31 +08:00

249 lines
8.0 KiB
Python

"""Integration test: worker.run_agent injects Langfuse trace metadata.
Verifies that the agent factory's resulting graph receives a
``RunnableConfig`` whose ``metadata`` carries the Langfuse reserved keys
(``langfuse_session_id`` / ``langfuse_user_id`` / ``langfuse_trace_name``).
"""
from __future__ import annotations
import asyncio
import pytest
from deerflow.runtime.runs.manager import RunRecord
from deerflow.runtime.runs.schemas import DisconnectMode, RunStatus
from deerflow.runtime.runs.worker import RunContext, run_agent
class _FakeAgent:
"""Minimal LangGraph-like graph that captures the runnable config."""
def __init__(self) -> None:
self.captured_config: dict | None = None
self.metadata: dict = {}
# Worker may assign these attributes; need them to exist.
self.checkpointer = None
self.store = None
self.interrupt_before_nodes: list[str] = []
self.interrupt_after_nodes: list[str] = []
async def astream(self, graph_input, *, config, stream_mode, **kwargs):
self.captured_config = config
# Empty async generator — no chunks produced.
return
yield # pragma: no cover (makes this an async generator)
class _FakeRunManager:
async def set_status(self, *_args, **_kwargs) -> None:
return None
async def update_model_name(self, *_args, **_kwargs) -> None:
return None
async def update_run_completion(self, *_args, **_kwargs) -> None:
return None
class _FakeBridge:
def __init__(self) -> None:
self.events: list[tuple[str, object]] = []
async def publish(self, _run_id, event, payload) -> None:
self.events.append((event, payload))
async def publish_end(self, _run_id) -> None:
self.events.append(("end", None))
async def cleanup(self, _run_id, *, delay: int = 0) -> None:
return None
@pytest.fixture(autouse=True)
def _clear_tracing_env(monkeypatch):
from deerflow.config.tracing_config import reset_tracing_config
for name in ("LANGFUSE_TRACING", "LANGFUSE_PUBLIC_KEY", "LANGFUSE_SECRET_KEY", "LANGFUSE_BASE_URL"):
monkeypatch.delenv(name, raising=False)
reset_tracing_config()
yield
reset_tracing_config()
@pytest.mark.asyncio
async def test_run_agent_injects_langfuse_metadata(monkeypatch):
monkeypatch.setenv("LANGFUSE_TRACING", "true")
monkeypatch.setenv("LANGFUSE_PUBLIC_KEY", "pk-lf-test")
monkeypatch.setenv("LANGFUSE_SECRET_KEY", "sk-lf-test")
from deerflow.config.tracing_config import reset_tracing_config
reset_tracing_config()
fake_agent = _FakeAgent()
def agent_factory(config):
return fake_agent
record = RunRecord(
run_id="run-1",
thread_id="thread-xyz",
assistant_id="lead-agent",
status=RunStatus.pending,
on_disconnect=DisconnectMode.cancel,
model_name="gpt-4o",
)
record.abort_event = asyncio.Event()
ctx = RunContext(checkpointer=None)
await run_agent(
_FakeBridge(),
_FakeRunManager(),
record,
ctx=ctx,
agent_factory=agent_factory,
graph_input={"messages": []},
config={"configurable": {"thread_id": "thread-xyz"}},
)
assert fake_agent.captured_config is not None, "astream was not invoked"
metadata = fake_agent.captured_config.get("metadata") or {}
assert metadata.get("langfuse_session_id") == "thread-xyz"
# conftest.py autouse fixture injects ``test-user-autouse`` into the
# contextvar — the worker should read it via ``get_effective_user_id``.
user_id = metadata.get("langfuse_user_id")
assert user_id == "test-user-autouse", f"expected test-user-autouse, got {user_id}"
assert metadata.get("langfuse_trace_name") == "lead-agent"
tags = metadata.get("langfuse_tags") or []
assert "model:gpt-4o" in tags
@pytest.mark.asyncio
async def test_run_agent_falls_back_to_default_user_when_unset(monkeypatch):
"""When no user is in the contextvar, langfuse_user_id falls back to 'default'.
Uses ``monkeypatch.setattr`` to redirect ``get_effective_user_id`` to return
``"default"`` rather than directly mutating the contextvar — direct contextvar
operations across pytest test boundaries have produced spooky cross-file
pollution when combined with the langfuse OTel global tracer provider.
"""
monkeypatch.setenv("LANGFUSE_TRACING", "true")
monkeypatch.setenv("LANGFUSE_PUBLIC_KEY", "pk-lf-test")
monkeypatch.setenv("LANGFUSE_SECRET_KEY", "sk-lf-test")
from deerflow.config.tracing_config import reset_tracing_config
from deerflow.runtime.runs import worker as worker_module
from deerflow.runtime.user_context import DEFAULT_USER_ID
reset_tracing_config()
monkeypatch.setattr(worker_module, "get_effective_user_id", lambda: DEFAULT_USER_ID)
fake_agent = _FakeAgent()
def agent_factory(config):
return fake_agent
record = RunRecord(
run_id="run-fallback",
thread_id="thread-fb",
assistant_id="lead-agent",
status=RunStatus.pending,
on_disconnect=DisconnectMode.cancel,
)
record.abort_event = asyncio.Event()
ctx = RunContext(checkpointer=None)
await run_agent(
_FakeBridge(),
_FakeRunManager(),
record,
ctx=ctx,
agent_factory=agent_factory,
graph_input={"messages": []},
config={"configurable": {"thread_id": "thread-fb"}},
)
metadata = fake_agent.captured_config.get("metadata") or {}
assert metadata.get("langfuse_user_id") == "default"
@pytest.mark.asyncio
async def test_run_agent_preserves_caller_metadata_overrides(monkeypatch):
"""Caller-provided langfuse_* keys must NOT be overridden by the default injection."""
monkeypatch.setenv("LANGFUSE_TRACING", "true")
monkeypatch.setenv("LANGFUSE_PUBLIC_KEY", "pk-lf-test")
monkeypatch.setenv("LANGFUSE_SECRET_KEY", "sk-lf-test")
from deerflow.config.tracing_config import reset_tracing_config
reset_tracing_config()
fake_agent = _FakeAgent()
def agent_factory(config):
return fake_agent
record = RunRecord(
run_id="run-2",
thread_id="thread-default",
assistant_id="lead-agent",
status=RunStatus.pending,
on_disconnect=DisconnectMode.cancel,
)
record.abort_event = asyncio.Event()
ctx = RunContext(checkpointer=None)
await run_agent(
_FakeBridge(),
_FakeRunManager(),
record,
ctx=ctx,
agent_factory=agent_factory,
graph_input={"messages": []},
config={
"configurable": {"thread_id": "thread-default"},
"metadata": {
"langfuse_session_id": "custom-session-id",
"langfuse_user_id": "explicit-user",
},
},
)
metadata = fake_agent.captured_config.get("metadata") or {}
# Caller-supplied keys win.
assert metadata["langfuse_session_id"] == "custom-session-id"
assert metadata["langfuse_user_id"] == "explicit-user"
# Worker still fills in keys that the caller didn't set.
assert metadata["langfuse_trace_name"] == "lead-agent"
@pytest.mark.asyncio
async def test_run_agent_skips_metadata_when_langfuse_disabled(monkeypatch):
fake_agent = _FakeAgent()
def agent_factory(config):
return fake_agent
record = RunRecord(
run_id="run-3",
thread_id="thread-noop",
assistant_id="lead-agent",
status=RunStatus.pending,
on_disconnect=DisconnectMode.cancel,
)
record.abort_event = asyncio.Event()
ctx = RunContext(checkpointer=None)
await run_agent(
_FakeBridge(),
_FakeRunManager(),
record,
ctx=ctx,
agent_factory=agent_factory,
graph_input={"messages": []},
config={"configurable": {"thread_id": "thread-noop"}},
)
metadata = fake_agent.captured_config.get("metadata") or {}
assert "langfuse_session_id" not in metadata
assert "langfuse_user_id" not in metadata
assert "langfuse_trace_name" not in metadata