mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-07-09 16:08:31 +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.
86 lines
3.4 KiB
Python
86 lines
3.4 KiB
Python
"""Unit tests for ``deerflow.trace_context`` validation helpers.
|
|
|
|
The middleware-level end-to-end coverage lives in ``test_trace_middleware.py``;
|
|
this file pins the character-set invariants of ``normalize_trace_id`` directly
|
|
so that a future relaxation of the check trips a targeted failure.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from deerflow.trace_context import _MAX_TRACE_ID_LENGTH, normalize_trace_id
|
|
|
|
|
|
class TestNormalizeTraceIdAcceptsPrintableAscii:
|
|
def test_accepts_uuid_hex(self) -> None:
|
|
assert normalize_trace_id("0123456789abcdef0123456789abcdef") == "0123456789abcdef0123456789abcdef"
|
|
|
|
def test_accepts_alphanumerics_and_punctuation(self) -> None:
|
|
assert normalize_trace_id("abc-123_XYZ.foo:bar/baz") == "abc-123_XYZ.foo:bar/baz"
|
|
|
|
def test_strips_surrounding_whitespace(self) -> None:
|
|
assert normalize_trace_id(" trace-1 ") == "trace-1"
|
|
|
|
def test_accepts_boundary_low(self) -> None:
|
|
assert normalize_trace_id("\x20abc") == "abc"
|
|
|
|
def test_accepts_boundary_high(self) -> None:
|
|
assert normalize_trace_id("abc\x7e") == "abc\x7e"
|
|
|
|
def test_accepts_maximum_length(self) -> None:
|
|
value = "a" * _MAX_TRACE_ID_LENGTH
|
|
assert normalize_trace_id(value) == value
|
|
|
|
|
|
class TestNormalizeTraceIdRejectsUnsafeInput:
|
|
def test_rejects_non_string(self) -> None:
|
|
assert normalize_trace_id(None) is None
|
|
assert normalize_trace_id(12345) is None
|
|
assert normalize_trace_id(b"abc") is None
|
|
|
|
def test_rejects_empty_and_whitespace_only(self) -> None:
|
|
assert normalize_trace_id("") is None
|
|
assert normalize_trace_id(" \t ") is None
|
|
|
|
def test_rejects_over_max_length(self) -> None:
|
|
assert normalize_trace_id("a" * (_MAX_TRACE_ID_LENGTH + 1)) is None
|
|
|
|
@pytest.mark.parametrize(
|
|
"value",
|
|
[
|
|
"trace\x00id", # NUL
|
|
"trace\x1fid", # last C0 control
|
|
"trace\tid", # embedded tab
|
|
"trace\nid", # LF — the classic log-injection / CRLF pivot
|
|
"trace\rid", # CR
|
|
],
|
|
)
|
|
def test_rejects_c0_controls(self, value: str) -> None:
|
|
assert normalize_trace_id(value) is None
|
|
|
|
def test_rejects_del(self) -> None:
|
|
assert normalize_trace_id("trace\x7fid") is None
|
|
|
|
@pytest.mark.parametrize("value", ["trace\x80id", "trace\x9fid"])
|
|
def test_rejects_c1_controls_in_latin1_range(self, value: str) -> None:
|
|
"""C1 controls latin-1-encode successfully but are stripped or
|
|
rejected by hardened intermediaries (nginx / envoy / cloudfront),
|
|
silently breaking the response. Reject at validation time."""
|
|
assert normalize_trace_id(value) is None
|
|
|
|
def test_rejects_latin1_supplement_characters(self) -> None:
|
|
assert normalize_trace_id("caf\xe9") is None # é = 0xE9
|
|
|
|
def test_rejects_cjk_characters(self) -> None:
|
|
"""Codepoints > 0xFF raise UnicodeEncodeError inside
|
|
``MutableHeaders.__setitem__`` before ``send`` is dispatched, forcing
|
|
a 500 on any endpoint. This is the exact case from the review."""
|
|
assert normalize_trace_id("请求-1") is None
|
|
assert normalize_trace_id("トレース") is None
|
|
|
|
def test_rejects_emoji(self) -> None:
|
|
assert normalize_trace_id("trace-\U0001f680") is None # 🚀
|
|
|
|
def test_rejects_surrogate_pair_pieces(self) -> None:
|
|
assert normalize_trace_id("trace-\ud83d") is None
|