fix(harness): change _runs INSERT OR IGNORE to ON CONFLICT DO UPDATE for incremental infer

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

app/harness/log.py

@@ -1,8 +1,9 @@
 """HarnessLog：SQLite 薄包装 + RunLogImpl 只读查询端口。
 
 HarnessLog 提供统一的结构化日志接口，从 TRM4 直搬，保留全部线程安全与幂等语义。
+同 run_id 重复创建时通过 ON CONFLICT DO UPDATE 更新 started_at/config/status。
 RunLogImpl 实现 core/evolution/protocols.py::RunLog Protocol，用独立连接做只读 SELECT，
-不经 HarnessLog 生命周期（不触发 _runs INSERT OR IGNORE），避免污染运行状态。
+不经 HarnessLog 生命周期（不触发 _runs upsert），避免污染运行状态。
 """
 
 from __future__ import annotations
@@ -41,7 +42,7 @@ class HarnessLog:
 
     关键设计：
     - WAL 模式 + threading.Lock 保证共享连接下并发安全。
-    - INSERT OR IGNORE INTO _runs 保证幂等（同 run_id 多次创建不报错）。
+    - ON CONFLICT DO UPDATE 保证幂等（同 run_id 多次创建不报错）并更新 started_at/config/status。
     - query 也持锁：共享连接（check_same_thread=False）下并发 SELECT + INSERT
       在同一连接上 execute 会损坏游标状态，故读也须串行化。
     - context manager 语义：正常退出 completed，异常退出 failed。
@@ -70,9 +71,13 @@ class HarnessLog:
         resolved_sha = git_sha or _get_git_sha()
         config_json = json.dumps(config_snapshot, ensure_ascii=False) if config_snapshot else None
         self._conn.execute(
-            "INSERT OR IGNORE INTO _runs"
+            "INSERT INTO _runs"
             " (run_id, git_sha, started_at, config, status)"
-            " VALUES (?, ?, ?, ?, ?)",
+            " VALUES (?, ?, ?, ?, ?)"
+            " ON CONFLICT(run_id) DO UPDATE SET"
+            " started_at=excluded.started_at,"
+            " config=excluded.config,"
+            " status=excluded.status",
             (run_id, resolved_sha, _now_iso(), config_json, "running"),
         )
         self._conn.commit()

tests/unit/test_harness_log.py

@@ -8,6 +8,7 @@ from __future__ import annotations
 
 import sqlite3
 import threading
+import time
 from typing import TYPE_CHECKING
 
 import pytest
@@ -118,8 +119,8 @@ class TestHarnessLog:
 
         assert row["status"] == "failed"
 
-    def test_insert_or_ignore_idempotent(self, db_path: str, run_id: str) -> None:
+    def test_upsert_idempotent(self, db_path: str, run_id: str) -> None:
-        """同一 run_id 多次创建 HarnessLog 不报错（INSERT OR IGNORE 幂等）。"""
+        """同一 run_id 多次创建 HarnessLog 不报错（ON CONFLICT DO UPDATE 幂等）。"""
         with HarnessLog(db_path, run_id):
             pass
 
@@ -134,7 +135,7 @@ class TestHarnessLog:
         ).fetchone()[0]
         conn.close()
 
-        assert count == 1, "INSERT OR IGNORE 应保证 _runs 只有一行"
+        assert count == 1, "ON CONFLICT DO UPDATE 应保证 _runs 只有一行"
 
     def test_wal_mode(self, db_path: str, run_id: str) -> None:
         """连接初始化后 journal_mode 应为 WAL。"""
@@ -195,6 +196,34 @@ class TestHarnessLog:
         assert rows[0]["val"] == "2"
 
 
+# ===========================================================================
+# HarnessLog upsert 行为测试
+# ===========================================================================
+
+
+class TestHarnessLogUpsert:
+    """_runs 表 upsert 行为。"""
+
+    def test_same_run_id_updates_started_at(self, tmp_path: Path) -> None:
+        """同 run_id 第二次创建 HarnessLog 应更新 started_at。"""
+        db = str(tmp_path / "test.db")
+        with HarnessLog(db, "run_1", git_sha="abc") as log1:
+            rows = log1.query("SELECT started_at FROM _runs WHERE run_id='run_1'")
+            first_time = rows[0]["started_at"]
+
+        time.sleep(0.05)
+
+        with HarnessLog(db, "run_1", git_sha="abc") as log2:
+            rows = log2.query("SELECT started_at FROM _runs WHERE run_id='run_1'")
+            second_time = rows[0]["started_at"]
+
+        assert second_time > first_time
+
+        with HarnessLog(db, "run_1") as log3:
+            rows = log3.query("SELECT COUNT(*) as cnt FROM _runs WHERE run_id='run_1'")
+            assert rows[0]["cnt"] == 1
+
+
 # ===========================================================================
 # RunLogImpl 测试
 # ===========================================================================