Files
PolyGateway/src/polygateway/telemetry/sqlite.py
T
iomgaa 4516761dbe feat: record sampling parameters in telemetry (port 20 to 21 fields)
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.
2026-07-31 21:30:45 -04:00

150 lines
5.2 KiB
Python

"""SQLite 遥测后端(默认): WAL + 单持久连接 + to_thread 桥接。
蓝本 VT `adapters/telemetry.py`: 构造期建连接与表,失败降级为 no-op
(记录基础设施不得拖垮业务调用);`INSERT OR IGNORE` 幂等(call_id 主键);
写入经 threading.Lock 串行化后由 `asyncio.to_thread` 执行,不阻塞事件循环。
"""
from __future__ import annotations
import asyncio
import sqlite3
import threading
from pathlib import Path
from loguru import logger
_DDL = """
CREATE TABLE IF NOT EXISTS llm_calls (
call_id TEXT PRIMARY KEY,
parent_call_id TEXT,
session_id TEXT,
model TEXT NOT NULL,
provider TEXT NOT NULL,
source_name TEXT NOT NULL,
messages TEXT NOT NULL,
response TEXT NOT NULL,
thinking TEXT NOT NULL DEFAULT '',
prompt_tokens INTEGER NOT NULL,
completion_tokens INTEGER NOT NULL,
usage_source TEXT NOT NULL,
latency_ms INTEGER NOT NULL,
ttft_ms REAL,
max_inter_token_ms REAL,
cache_hit INTEGER NOT NULL DEFAULT 0,
error TEXT,
cost REAL,
created_at TEXT NOT NULL DEFAULT (datetime('now')),
cached_prompt_tokens INTEGER,
model_reported TEXT,
sampling TEXT
);
"""
# 新列必须排在 created_at 之后: 旧表只能经 ALTER 追加到末尾,新建库若把它们
# 插在前面,两条路径的物理列序会分叉(列序断言测试无合规修法)。
_BACKFILL_COLUMNS = (
("cached_prompt_tokens", "INTEGER"),
("model_reported", "TEXT"),
("sampling", "TEXT"),
)
_COLUMNS = (
"call_id",
"parent_call_id",
"session_id",
"model",
"provider",
"source_name",
"messages",
"response",
"thinking",
"prompt_tokens",
"completion_tokens",
"usage_source",
"latency_ms",
"ttft_ms",
"max_inter_token_ms",
"cache_hit",
"error",
"cost",
"cached_prompt_tokens",
"model_reported",
"sampling",
)
_INSERT = (
f"INSERT OR IGNORE INTO llm_calls ({', '.join(_COLUMNS)}) "
f"VALUES ({', '.join('?' for _ in _COLUMNS)})"
)
class SQLiteRecorder:
"""TelemetryRecorder 端口的 SQLite 实现;初始化/写入失败全降级 warning。"""
def __init__(self, db_path: Path | str) -> None:
self._lock = threading.Lock()
self._conn: sqlite3.Connection | None = None
try:
path = Path(db_path)
path.parent.mkdir(parents=True, exist_ok=True)
conn = sqlite3.connect(path, check_same_thread=False, timeout=10.0)
conn.execute("PRAGMA journal_mode=WAL")
conn.execute("PRAGMA busy_timeout=5000")
conn.execute(_DDL)
conn.commit()
self._conn = conn
except (OSError, sqlite3.Error) as exc:
logger.warning("SQLite 遥测初始化失败,后续记录降级为 no-op: {}", exc)
self._backfill_columns()
def _backfill_columns(self) -> None:
"""给已存在的旧表补新列(issue #3);独立 try,失败只降级为逐行丢弃。
必须放在 `self._conn` 赋值**之后**并先判空: 初始化失败时连接为 None,
无守卫的补列会抛 AttributeError 逃出 `__init__`,把"静默降级"变成崩溃。
补列失败也绝不清空 `self._conn`——那会让整个 recorder 永久 no-op,
比逐行丢弃严重得多。
"""
if self._conn is None:
return
try:
existing = {row[1] for row in self._conn.execute("PRAGMA table_info(llm_calls)")}
except sqlite3.Error as exc:
logger.warning("SQLite 遥测列探测失败(写入将逐行降级): {}", exc)
return
for column, decl in _BACKFILL_COLUMNS:
if column in existing:
continue
# 逐列独立 try: 一列撞上 duplicate 不得让后面的列漏补
try:
self._conn.execute(f"ALTER TABLE llm_calls ADD COLUMN {column} {decl}")
self._conn.commit()
except sqlite3.Error as exc:
# duplicate column: 多进程共库时后到者必然撞上,属预期竞态,视为成功
if "duplicate column" not in str(exc).lower():
logger.warning("SQLite 遥测补列失败(写入将逐行降级): {}", exc)
async def record_llm_call(self, **fields: object) -> None:
"""写一行遥测;字段集合即 21 字段冻结签名(ports.TelemetryRecorder)。"""
if self._conn is None:
return
row = tuple(fields[col] for col in _COLUMNS)
try:
await asyncio.to_thread(self._write, row)
except (OSError, sqlite3.Error) as exc:
logger.warning("SQLite 遥测写入失败(降级不冒泡): {}", exc)
def _write(self, row: tuple) -> None:
assert self._conn is not None # 内部不变量: 调用方已判空
with self._lock:
self._conn.execute(_INSERT, row)
self._conn.commit()
def close(self) -> None:
"""幂等关闭持久连接。"""
conn, self._conn = self._conn, None
if conn is not None:
with self._lock:
conn.close()