feat: record the observability fields end to end through telemetry

src/polygateway/telemetry/postgres.py

@@ -6,7 +6,7 @@
 ① 结构性失败(建池/建表)→ warning 一次后永久降级(池置 None 短路);
 ② 运行时单条写失败 → 逐条 warning 丢弃,不降级不重试(连接抖动由
 asyncpg 池自恢复;避免浸泡开头一次抖动导致后续全程失遥测)。
-构造不连库(lazy),18 列 schema 与 SQLite 版同名同序。
+构造不连库(lazy),20 列 schema 与 SQLite 版同名同序。
 """
 
 from __future__ import annotations
@@ -39,10 +39,18 @@ CREATE TABLE IF NOT EXISTS llm_calls (
     cache_hit          BOOLEAN NOT NULL DEFAULT FALSE,
     error              TEXT,
     cost               DOUBLE PRECISION,
-    created_at         TIMESTAMPTZ NOT NULL DEFAULT now()
+    created_at         TIMESTAMPTZ NOT NULL DEFAULT now(),
+    cached_prompt_tokens INTEGER,
+    model_reported       TEXT
 );
 """
 
+# 新列排在 created_at 之后: 与旧表 ALTER 追加的位置一致(见 sqlite.py 同款注释)
+_BACKFILL = (
+    "ALTER TABLE llm_calls ADD COLUMN IF NOT EXISTS cached_prompt_tokens INTEGER",
+    "ALTER TABLE llm_calls ADD COLUMN IF NOT EXISTS model_reported TEXT",
+)
+
 _COLUMNS = (
     "call_id",
     "parent_call_id",
@@ -62,6 +70,8 @@ _COLUMNS = (
     "cache_hit",
     "error",
     "cost",
+    "cached_prompt_tokens",
+    "model_reported",
 )
 
 _INSERT = (
@@ -104,6 +114,9 @@ class PostgresRecorder:
                     self._pool = await asyncpg.create_pool(self._dsn, timeout=10)
                 async with self._pool.acquire() as conn:
                     await conn.execute(_DDL)
+                    for statement in _BACKFILL:
+                        # 已存在的旧表补新列(issue #3);ADD COLUMN IF NOT EXISTS 原生幂等
+                        await conn.execute(statement)
                 self._schema_ready = True
                 return self._pool
             except asyncio.CancelledError:

src/polygateway/telemetry/sqlite.py

@@ -34,10 +34,16 @@ CREATE TABLE IF NOT EXISTS llm_calls (
     cache_hit          INTEGER NOT NULL DEFAULT 0,
     error              TEXT,
     cost               REAL,
-    created_at         TEXT    NOT NULL DEFAULT (datetime('now'))
+    created_at         TEXT    NOT NULL DEFAULT (datetime('now')),
+    cached_prompt_tokens INTEGER,
+    model_reported       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"))
+
 _COLUMNS = (
     "call_id",
     "parent_call_id",
@@ -57,6 +63,8 @@ _COLUMNS = (
     "cache_hit",
     "error",
     "cost",
+    "cached_prompt_tokens",
+    "model_reported",
 )
 
 _INSERT = (
@@ -82,9 +90,32 @@ class SQLiteRecorder:
             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)")}
+            for column, decl in _BACKFILL_COLUMNS:
+                if column in existing:
+                    continue
+                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 18 字段冻结签名(ports.TelemetryRecorder)。"""
+        """写一行遥测;字段集合即 20 字段冻结签名(ports.TelemetryRecorder)。"""
         if self._conn is None:
             return
         row = tuple(fields[col] for col in _COLUMNS)