iomgaa/PolyGateway
1
0
Fork 0
Code Issues 3 Pull Requests Actions Packages Projects Releases 9 Wiki Activity

feat: record sampling parameters in telemetry (port 20 to 21 fields)

Browse Source 
Each of the three emitter entry points has a pinned meaning: only the
attempt path has an effective source, so only it merges extra_body.
This commit is contained in:
iomgaa
2026-07-31 21:30:45 -04:00
parent b6e4cc3f3b
commit 4516761dbe
6 changed files with 141 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/integration/test_postgres_telemetry.py
+2
View File
@@ -41,6 +41,7 @@ _EXPECTED_COLUMNS = [
"created_at",
"cached_prompt_tokens",
"model_reported",
"sampling",
]
# run 级前缀: 同库并存的其他运行(迁移批跑/另一开发机)互不可见
@@ -104,6 +105,7 @@ async def _record_minimal(
"cost": None,
"cached_prompt_tokens": None,
"model_reported": None,
"sampling": None,
}
fields.update(overrides)
await recorder.record_llm_call(**fields)
tests/unit/test_telemetry.py
+113 -12
View File
@@ -1,6 +1,7 @@
"""遥测子系统测试: SQLiteRecorder(20 列)+ TelemetryEmitter 单一 helper + TelemetryMW。"""
"""遥测子系统测试: SQLiteRecorder(21 列)+ TelemetryEmitter 单一 helper + TelemetryMW。"""
import asyncio
import json
import sqlite3
import subprocess
from pathlib import Path
@@ -37,6 +38,7 @@ _EXPECTED_COLUMNS = [
"created_at",
"cached_prompt_tokens",
"model_reported",
"sampling",
]
@@ -60,15 +62,17 @@ def _resp(**overrides):
return LLMResponse(**base)
def _source():
return SourceConfig(
name="s1",
provider="p",
base_url="https://gw.example/v1",
api_key="sk",
model="m",
timeout_s=10.0,
)
def _source(**overrides):
base = {
"name": "s1",
"provider": "p",
"base_url": "https://gw.example/v1",
"api_key": "sk",
"model": "m",
"timeout_s": 10.0,
}
base.update(overrides)
return SourceConfig(**base)
# 输出单价 8 元/百万: 改前 `unavailable` 行按兜底的 0/4000 换算恰好是 0.032
@@ -97,6 +101,7 @@ async def _record_minimal(recorder, call_id="c1", **overrides):
"cost": None,
"cached_prompt_tokens": None,
"model_reported": None,
"sampling": None,
}
fields.update(overrides)
await recorder.record_llm_call(**fields)
@@ -153,6 +158,20 @@ class TestSQLiteRecorder:
assert rows["c-zero"] == 0 # 真实零命中,读回仍是 0 而非 NULL
assert rows["c-none"] is None
async def test_sampling_column_round_trips(self, tmp_path):
"""issue #4: 采样参数落库,否则事后无法证明某批数据跑在什么温度下。"""
recorder = SQLiteRecorder(tmp_path / "t.db")
await _record_minimal(recorder, call_id="c-s", sampling='{"seed": 42, "temperature": 0}')
await _record_minimal(recorder, call_id="c-plain")
recorder.close()
rows = dict(
sqlite3.connect(tmp_path / "t.db")
.execute("SELECT call_id, sampling FROM llm_calls")
.fetchall()
)
assert json.loads(rows["c-s"]) == {"seed": 42, "temperature": 0}
assert rows["c-plain"] is None # 无采样参数为 NULL,便于 SQL 过滤
class TestSQLiteColumnBackfill:
"""issue #3: 已存在的 18 列旧表必须自动补列,否则每行写入都被丢弃。"""
@@ -258,7 +277,14 @@ class TestPostgresBackfillDiscipline:
"""PG 补列必须与 SQLite 侧对称: 失败只逐行降级,且稳态不抢排他锁(issue #3)。"""
_LEGACY = ["call_id", "cost", "created_at"]
_CURRENT = ["call_id", "cost", "created_at", "cached_prompt_tokens", "model_reported"]
_CURRENT = [
"call_id",
"cost",
"created_at",
"cached_prompt_tokens",
"model_reported",
"sampling",
]
def _recorder(self, conn):
from polygateway.telemetry.postgres import PostgresRecorder
@@ -286,8 +312,10 @@ class TestPostgresBackfillDiscipline:
async def test_missing_columns_are_added_once(self):
conn = _FakePgConn(self._LEGACY)
await _record_minimal(self._recorder(conn))
from polygateway.telemetry.postgres import _BACKFILL
altered = [s for s in conn.statements if s.startswith("ALTER TABLE")]
assert len(altered) == 2
assert len(altered) == len(_BACKFILL) # 旧表缺全部补列,故一列一条 ALTER
assert all("IF NOT EXISTS" not in s for s in altered) # 探测已确认缺列,无需再判
@@ -394,6 +422,79 @@ class TestEmitterObservabilityFields:
assert rec.rows[0]["model_reported"] is None
class TestEmitterSamplingColumn:
"""issue #4: sampling 列在三个入口的口径(设计决策 D 表格)。
列语义 = 「调用方采样意图 ⊎ 生效源 extra_body」,**不含**结构化注入的
response_format(列名是采样参数,schema 不是;且数 KB schema 逐行落库会让
审计表无谓膨胀)。三入口若各读各的层,同一列在不同行含义就不同。
"""
_SAMPLED = ChatRequest(
messages=[{"role": "user", "content": "hi"}],
sampling={"seed": 42},
overlay={"seed": 42, "response_format": {"type": "json_object"}},
)
async def test_attempt_merges_source_extra_body(self):
rec = _MemoryRecorder()
await TelemetryEmitter(rec).emit_attempt(
request=self._SAMPLED,
source=_source(extra_body={"temperature": 0}),
call_id="c",
latency_ms=1,
response=_resp(),
error=None,
)
assert json.loads(rec.rows[0]["sampling"]) == {"seed": 42, "temperature": 0}
async def test_response_format_never_leaks_into_the_column(self):
"""三行都不得出现 response_format——它不是采样参数。"""
rec = _MemoryRecorder()
emitter = TelemetryEmitter(rec)
await emitter.emit_attempt(
request=self._SAMPLED,
source=_source(),
call_id="c",
latency_ms=1,
response=_resp(),
error=None,
)
await emitter.emit_cache_hit(request=self._SAMPLED, response=_resp())
await emitter.emit_terminal_failure(
request=self._SAMPLED, call_id="c", latency_ms=1, error="dead"
)
assert len(rec.rows) == 3
for row in rec.rows:
assert "response_format" not in row["sampling"]
@pytest.mark.parametrize("emit", ["cache_hit", "terminal_failure"])
async def test_sourceless_entries_record_call_level_only(self, emit):
"""两个最外层入口没有"生效源"可言,与 model/source_name 置空同一先例。"""
rec = _MemoryRecorder()
emitter = TelemetryEmitter(rec)
if emit == "cache_hit":
await emitter.emit_cache_hit(request=self._SAMPLED, response=_resp())
else:
await emitter.emit_terminal_failure(
request=self._SAMPLED, call_id="c", latency_ms=1, error="dead"
)
assert json.loads(rec.rows[0]["sampling"]) == {"seed": 42}
async def test_absent_sampling_is_null(self):
"""无采样参数时为 NULL,而非空字符串或 "{}"——便于 SQL 过滤。"""
rec = _MemoryRecorder()
await TelemetryEmitter(rec).emit_attempt(
request=_REQ,
source=_source(),
call_id="c",
latency_ms=1,
response=_resp(),
error=None,
)
assert rec.rows[0]["sampling"] is None
class TestCostWithCachedTier:
"""issue #3: 命中部分按缓存单价计费,避免 cost 系统性高估。"""