fix: clear gate-derived rows on step rerun (idempotency)

app/harness/runner.py

@@ -602,6 +602,52 @@ def _write_skip_report(
     )
 
 
+def _clear_step_rows(db_path: str, *, baseline_run_id: str, epoch: int, step: int) -> None:
+    """清空一个 step 的全部旧行（rollout + gate 派生），保证崩溃重跑幂等。
+
+    修复前序潜伏 bug：旧实现只清 rollout run_id，gate 派生 run_id
+    （`{step_run_id}_gate_%`）从不清理，重跑会累积重复 predictions（HarnessLog
+    无主键去重），_load_run_rows 的 dict 覆盖使结果依赖 SELECT 顺序。
+    gate_evidence / quadrant_pair 以 (run_id, epoch, step) 过滤删除；
+    表不存在（首个 step）时跳过。step_report 为按文件名覆盖写的 JSON，天然幂等。
+
+    参数:
+        db_path: harness.db 路径。
+        baseline_run_id: 基线 run（gate_evidence/quadrant_pair 的 run_id 维度）。
+        epoch: 轮次（1-based）。
+        step: epoch 内 step 序号（0-based）。
+
+    返回:
+        无。
+
+    关键实现细节:
+        predictions/traces 的 gate 行按 LIKE 前缀删除，'_' 通配显式转义
+        （ESCAPE）钉死字面匹配，避免 `..._s1` 误匹配 `..._s10` 类前缀陷阱。
+    """
+    from app.harness.inference import PREDICTIONS_SCHEMA, TRACES_SCHEMA
+    from app.harness.log import HarnessLog
+
+    step_run_id = f"{baseline_run_id}_e{epoch}_s{step}"
+    with HarnessLog(db_path, step_run_id, register_run=False) as log:
+        log.create_table("predictions", PREDICTIONS_SCHEMA)
+        log.create_table("traces", TRACES_SCHEMA)
+        for table in ("predictions", "traces"):
+            log.execute(f"DELETE FROM {table} WHERE run_id=?", (step_run_id,))
+            log.execute(
+                f"DELETE FROM {table} WHERE run_id LIKE ? ESCAPE '\\'",
+                (step_run_id.replace("_", r"\_") + r"\_gate\_%",),
+            )
+        for table in ("gate_evidence", "quadrant_pair"):
+            exists = log.query(
+                "SELECT name FROM sqlite_master WHERE type='table' AND name=?", (table,)
+            )
+            if exists:
+                log.execute(
+                    f"DELETE FROM {table} WHERE run_id=? AND epoch=? AND step=?",
+                    (baseline_run_id, epoch, step),
+                )
+
+
 # ---------------------------------------------------------------------------
 # Runner 主类
 # ---------------------------------------------------------------------------
@@ -1096,17 +1142,16 @@ class Runner:
         """单 step：rollout → correctness 增量 → 诊断 → 累加 system/tool → 按类 gate。"""
         run_id = f"{pools.baseline_run_id}_e{epoch}_s{step}"
 
-        from app.harness.inference import PREDICTIONS_SCHEMA, TRACES_SCHEMA
         from app.harness.log import HarnessLog
 
-        # 幂等：重跑同一 step 前先清旧行，避免断点续跑重复累计双计。
-        # 先 CREATE TABLE IF NOT EXISTS（fresh workspace 首跑时表尚未由 run_inference 建），
-        # register_run=False 避免只读清理污染 _runs 运行状态。
-        with HarnessLog(str(self._paths.db_path), run_id, register_run=False) as log:
-            log.create_table("predictions", PREDICTIONS_SCHEMA)
-            log.create_table("traces", TRACES_SCHEMA)
-            log.execute("DELETE FROM predictions WHERE run_id=?", (run_id,))
-            log.execute("DELETE FROM traces WHERE run_id=?", (run_id,))
+        # 幂等：重跑同一 step 前清 rollout + 全部 gate 派生旧行（修复潜伏 bug：
+        # 旧实现只清 rollout，gate 行崩溃重跑会累积重复）。
+        _clear_step_rows(
+            str(self._paths.db_path),
+            baseline_run_id=pools.baseline_run_id,
+            epoch=epoch,
+            step=step,
+        )
 
         await self._rollout_batch(batch, run_id)