fix: keep the postgres backfill from disabling telemetry or locking the table

tests/unit/test_telemetry.py

@@ -219,6 +219,78 @@ class TestSQLiteColumnBackfill:
         recorder.close()
 
 
+class _FakePgConn:
+    """记录执行过的语句;可让 ALTER 抛错以模拟权限不足。"""
+
+    def __init__(self, existing: list[str], *, fail_alter: bool = False):
+        self.existing = existing
+        self.fail_alter = fail_alter
+        self.statements: list[str] = []
+
+    async def execute(self, sql, *args):
+        self.statements.append(sql)
+        if sql.startswith("ALTER TABLE") and self.fail_alter:
+            raise RuntimeError("must be owner of table llm_calls")
+
+    async def fetch(self, sql, *args):
+        self.statements.append(sql)
+        return [{"attname": name} for name in self.existing]
+
+
+class _FakePgPool:
+    def __init__(self, conn):
+        self._conn = conn
+
+    def acquire(self):
+        conn = self._conn
+
+        class _Ctx:
+            async def __aenter__(self):
+                return conn
+
+            async def __aexit__(self, *exc):
+                return False
+
+        return _Ctx()
+
+
+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"]
+
+    def _recorder(self, conn):
+        from polygateway.telemetry.postgres import PostgresRecorder
+
+        return PostgresRecorder("postgresql://u:p@h:5432/polygateway", pool=_FakePgPool(conn))
+
+    async def test_alter_failure_does_not_disable_the_recorder(self):
+        """ALTER 失败(如账号只有 INSERT 权限)不得置 _failed —— 那会让遥测全灭。"""
+        conn = _FakePgConn(self._LEGACY, fail_alter=True)
+        recorder = self._recorder(conn)
+        await _record_minimal(recorder)  # 不得抛
+        assert recorder._failed is False
+        assert any(s.startswith("INSERT INTO llm_calls") for s in conn.statements)
+
+    async def test_no_alter_when_columns_already_exist(self):
+        """ADD COLUMN IF NOT EXISTS 即使列已存在也会先抢 ACCESS EXCLUSIVE 锁,
+
+        而遥测是内联 await——稳态下必须一条 ALTER 都不发,否则每个进程的首次
+        写入都会去锁共享审计表。
+        """
+        conn = _FakePgConn(self._CURRENT)
+        await _record_minimal(self._recorder(conn))
+        assert not [s for s in conn.statements if s.startswith("ALTER TABLE")]
+
+    async def test_missing_columns_are_added_once(self):
+        conn = _FakePgConn(self._LEGACY)
+        await _record_minimal(self._recorder(conn))
+        altered = [s for s in conn.statements if s.startswith("ALTER TABLE")]
+        assert len(altered) == 2
+        assert all("IF NOT EXISTS" not in s for s in altered)  # 探测已确认缺列,无需再判
+
+
 class _MemoryRecorder:
     def __init__(self):
         self.rows = []