fix: drop the conflict target so partitioned tables can accept writes

PG requires a partitioned table's unique constraints to include the
partition key, so issue #12's RANGE partitioning on created_at forces
the primary key to (call_id, created_at). The old
`ON CONFLICT (call_id) DO NOTHING` then matches no constraint and PG
rejects every row with

    there is no unique or exclusion constraint matching the
    ON CONFLICT specification

which the recorder swallows as a per-row warning: telemetry would go
silently dark under a partitioned deployment. The target-free form is
valid on both table shapes and is literally equivalent on a plain table
(the primary key is its only unique constraint). SQLite's
`INSERT OR IGNORE` already carries no target and is untouched.

Integration coverage on the real PG instance, both inside self-created
temp schemas: a plain table still keeps one row per call_id, and a
table partitioned by created_at now accepts writes and reads them back.
The second case was red before this change with the error above.
This commit is contained in:
2026-08-19 11:34:13 -04:00
parent d4b40b0e64
commit ecc22b34fc
3 changed files with 136 additions and 5 deletions
@@ -14,6 +14,7 @@ import asyncio
import json
import os
import re
from datetime import UTC, datetime, timedelta
from uuid import uuid4
import pytest
@@ -628,3 +629,123 @@ class TestCallerDimensionsAcceptance:
assert any("写入失败" in m for m in captured_warnings)
finally:
await recorder.aclose()
# issue #12 的目标表形态: 按 created_at 做 RANGE 分区(过期清理 DROP PARTITION 而非 DELETE)。
# PG 强制分区表的唯一约束必须包含分区键,故主键只能是 (call_id, created_at) ——
# 这正是带目标的 `ON CONFLICT (call_id)` 再也匹配不到约束的现场。
_PARTITIONED_DDL = """
CREATE TABLE {schema}.llm_calls (
call_id TEXT NOT NULL,
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 DOUBLE PRECISION,
max_inter_token_ms DOUBLE PRECISION,
cache_hit BOOLEAN NOT NULL DEFAULT FALSE,
error TEXT,
cost DOUBLE PRECISION,
created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
cached_prompt_tokens INTEGER,
model_reported TEXT,
sampling TEXT,
reasoning_tokens INTEGER,
tenant_id TEXT NOT NULL DEFAULT '',
meta JSONB NOT NULL DEFAULT '{{}}'::jsonb,
PRIMARY KEY (call_id, created_at)
) PARTITION BY RANGE (created_at)
"""
_PARTITION_DDL = (
"CREATE TABLE {schema}.llm_calls_current PARTITION OF {schema}.llm_calls "
"FOR VALUES FROM ('{start}') TO ('{end}')"
)
def _current_month_bounds() -> tuple[str, str]:
"""当前月的 [月初, 下月初) 边界字面量;分区键落在区间外会因找不到分区而写失败。"""
now = datetime.now(UTC)
start = now.replace(day=1, hour=0, minute=0, second=0, microsecond=0)
end = (start + timedelta(days=32)).replace(day=1)
fmt = "%Y-%m-%d %H:%M:%S%z"
return start.strftime(fmt), end.strftime(fmt)
@pytest.fixture
async def partitioned_schema(dsn):
"""自建临时 schema 里造一张按 created_at RANGE 分区的表 + 覆盖当前月的分区。
与 legacy_schema 同款隔离: 绝不碰共享的 public.llm_calls,teardown 只 DROP
自己建的 schema(CASCADE 连分区一并删)。
"""
import asyncpg
name = f"pgwtest_part_{uuid4().hex[:8]}"
start, end = _current_month_bounds()
conn = await asyncpg.connect(dsn, timeout=10)
try:
await conn.execute(f"CREATE SCHEMA {name}")
await conn.execute(_PARTITIONED_DDL.format(schema=name))
await conn.execute(_PARTITION_DDL.format(schema=name, start=start, end=end))
finally:
await conn.close()
yield _search_path_dsn(dsn, name), name
conn = await asyncpg.connect(dsn, timeout=10)
try:
await conn.execute(f"DROP SCHEMA {name} CASCADE")
finally:
await conn.close()
class TestConflictTargetFreeInsert:
"""issue #13: INSERT 不绑定冲突目标,普通表与分区表两种形态都写得进去。"""
async def test_plain_table_still_dedupes_by_call_id(self, fresh_schema, captured_warnings):
"""普通表上语义不变: 重复 call_id 仍只落一行,且不是被拒后丢弃。
表上只有主键这一个唯一约束,故无目标的 DO NOTHING 与 `(call_id)` 逐字等价;
断言"无写入失败 warning"是为了区分"冲突被忽略""整条被 PG 拒收"
"""
fresh_dsn, _ = fresh_schema
recorder = PostgresRecorder(fresh_dsn)
try:
await _record_minimal(recorder, call_id=_cid("nodup"))
await _record_minimal(recorder, call_id=_cid("nodup"), response="second")
assert [m for m in captured_warnings if "写入失败" in m] == []
rows = await _fetch(
fresh_dsn, "SELECT response FROM llm_calls WHERE call_id = $1", _cid("nodup")
)
assert [r["response"] for r in rows] == ["ok"] # 首行胜出,写入幂等
finally:
await recorder.aclose()
async def test_partitioned_table_accepts_writes(self, partitioned_schema, captured_warnings):
"""分区表上写入成功且能读回——改动前这里必红。
带目标的 `ON CONFLICT (call_id)` 在主键为 `(call_id, created_at)` 的表上
匹配不到任何约束,PG 报 "there is no unique or exclusion constraint matching
the ON CONFLICT specification";该错误被逐行降级吞成 warning,于是分区部署下
遥测全线写不进去却一声不吭,只能靠"读不回来"暴露。
"""
part_dsn, _ = partitioned_schema
recorder = PostgresRecorder(part_dsn)
try:
await _record_minimal(recorder, call_id=_cid("part"), tenant_id="tenant-p")
assert [m for m in captured_warnings if "写入失败" in m] == []
rows = await _fetch(
part_dsn,
"SELECT call_id, tenant_id FROM llm_calls WHERE call_id = $1",
_cid("part"),
)
assert [(r["call_id"], r["tenant_id"]) for r in rows] == [(_cid("part"), "tenant-p")]
finally:
await recorder.aclose()