mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-07-22 14:08:28 +00:00
e3e5c73b03
* feat(observability): add trace-id correlation and enhanced logging - add opt-in gateway request trace correlation via X-Trace-Id - enhance logging with configurable trace_id-aware formatting - propagate deerflow_trace_id into runtime context and Langfuse metadata - keep enhanced logging disabled by default to preserve existing behavior * fix: harden trace correlation wiring - Make logging enhancement a restart-required startup snapshot and remove per-request config reads from TraceMiddleware - Restrict trace ids to printable ASCII before writing them to response headers, logs, and Langfuse metadata - Gate implicit DeerFlowClient trace-id creation behind logging.enhance.enabled while preserving explicit caller opt-in - Bind embedded client trace context per stream step to avoid generator ContextVar leaks and cross-context reset errors - Rebind memory update trace ids in Timer/executor worker paths so enhanced logs keep the captured correlation id - Remove unrelated __run_journal context overwrite from the trace-correlation change set * fix(gateway): avoid eager app construction on package import * fix(gateway): avoid config load during app import Keep Gateway app construction import-safe when config.yaml is absent by disabling TraceMiddleware only for that construction-time fallback path. Startup lifespan still performs strict config loading before serving.
64 lines
2.5 KiB
Python
64 lines
2.5 KiB
Python
"""Gateway request trace middleware."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from typing import Any
|
|
|
|
from starlette.datastructures import Headers, MutableHeaders
|
|
from starlette.types import ASGIApp, Message, Receive, Scope, Send
|
|
|
|
from deerflow.config.app_config import is_trace_correlation_enabled
|
|
from deerflow.trace_context import TRACE_ID_HEADER, request_trace_context
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class TraceMiddleware:
|
|
"""Bind a request-level trace id and write it to HTTP response headers.
|
|
|
|
The ``enabled`` flag is a **startup snapshot** rather than a per-request
|
|
live read: ``logging`` is registered as restart-required in
|
|
``deerflow.config.reload_boundary.STARTUP_ONLY_FIELDS`` because
|
|
``configure_logging()`` only installs the trace-context filter and
|
|
formatter during app.py lifespan startup. Reading ``logging.enhance.enabled``
|
|
live here would let a runtime config edit surface the response
|
|
``X-Trace-Id`` header and Langfuse ``deerflow_trace_id`` immediately while
|
|
the log formatter stays on its startup value, contradicting the
|
|
restart-required contract IDE hover surfaces on ``AppConfig.logging``.
|
|
"""
|
|
|
|
def __init__(self, app: ASGIApp, *, enabled: bool):
|
|
self.app = app
|
|
self.enabled = bool(enabled)
|
|
|
|
async def __call__(self, scope: Scope, receive: Receive, send: Send) -> None:
|
|
if scope["type"] != "http" or not self.enabled:
|
|
await self.app(scope, receive, send)
|
|
return
|
|
|
|
headers = Headers(scope=scope)
|
|
incoming_trace_id = headers.get(TRACE_ID_HEADER)
|
|
|
|
with request_trace_context(incoming_trace_id) as trace_id:
|
|
|
|
async def send_with_trace(message: Message) -> None:
|
|
if message["type"] == "http.response.start":
|
|
response_headers = MutableHeaders(scope=message)
|
|
response_headers[TRACE_ID_HEADER] = trace_id
|
|
await send(message)
|
|
|
|
await self.app(scope, receive, send_with_trace)
|
|
|
|
|
|
def resolve_trace_enabled(config: Any) -> bool:
|
|
"""Read ``logging.enhance.enabled`` from an ``AppConfig``-like object.
|
|
|
|
Thin backwards-compatible alias around
|
|
:func:`deerflow.config.app_config.is_trace_correlation_enabled`, kept so
|
|
existing gateway callers and tests do not have to switch imports. Both
|
|
the Gateway middleware and the embedded ``DeerFlowClient`` resolve the
|
|
gate through the same harness helper so their behaviour cannot drift.
|
|
"""
|
|
return is_trace_correlation_enabled(config)
|