feat: record the reasoning verdict in telemetry

This issue surfaced only because someone ran a slow suite that is
excluded by default and had not been run for eighteen days. As a column
it becomes a query: which model stopped being observable, and when.

The emitter unwraps the enum to a plain str at the single _record exit.
asyncpg makes no promise about encoding a str subclass, and a telemetry
write that fails is downgraded to one warning — it would not crash, it
would just quietly cost the Postgres path a column. Normalising at the
emitter follows what tenant_id, meta and sampling already do.

The column is appended last in COLUMNS and in both DDLs. An existing
table can only take ALTER at the end, so putting it anywhere else
forks the physical column order between a freshly built database and a
backfilled one.
This commit is contained in:
2026-08-26 00:29:26 -04:00
parent ab1c47ebcc
commit 56acb8f3ac
7 changed files with 146 additions and 30 deletions
+1 -1
View File
@@ -143,7 +143,7 @@ class SQLiteRecorder:
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 24 字段冻结签名(ports.TelemetryRecorder)。
"""写一行遥测;字段集合即 25 字段冻结签名(ports.TelemetryRecorder)。
取值按 `self._columns`(manual 档可能已被裁剪),与 `self._insert` 的
占位符同序——两者必须一起改,分开改就是把值写进错位的列。