feat(factor): 批量评估断点续跑——run_id复用+已落库因子跳过+空续跑免load直收尾;跨session CI容器重启只损失在途1因子,重挂即续 [vps]

sanguo_factor/batch_eval.py

@@ -43,6 +43,7 @@ def run_batch_eval(
     cfg=None,
     progress_cb=None,
     vnpy_db_override: str | None = None,
+    run_id: str | None = None,
 ) -> dict:
     """跑一轮批量评估,结果增量写入 eval_db,返回摘要."""
     from vnpy.alpha.dataset.utility import calculate_by_expression
@@ -82,11 +83,29 @@ def run_batch_eval(
 
     universe_label = universe if symbols is None else "custom"
     eval_store.init_db(eval_db)
-    run_id = eval_store.create_run(
-        eval_db, label=label, universe=universe_label,
-        symbols_count=bars["vt_symbol"].n_unique(), factors_total=len(factor_names),
-        start=start, end=end, params={"limit": limit, "symbols": symbols[:20] if symbols else None},  # 截断防 4400 只全量塞 JSON
-    )
+    if run_id is None:
+        run_id = eval_store.create_run(
+            eval_db, label=label, universe=universe_label,
+            symbols_count=bars["vt_symbol"].n_unique(), factors_total=len(factor_names),
+            start=start, end=end, params={"limit": limit, "symbols": symbols[:20] if symbols else None},  # 截断防 4400 只全量塞 JSON
+        )
+        done_before = set()
+    else:
+        # 断点续跑:复用既有 run 行,跳过已落库因子(容器被 CI 重启后无损接续)
+        from sanguo_factor.eval_store import get_rows as _get_rows
+        done_before = {r["factor"] for r in _get_rows(eval_db, run_id)}
+        factor_names = [f for f in factor_names if f not in done_before]
+        if not factor_names:
+            # 空续跑:全部已完成时直接收尾不炸
+            eval_store.finish_run(eval_db, run_id, "done", factors_done=len(done_before))
+            return {
+                "run_id": run_id,
+                "factors_total": len(done_before),
+                "factors_done": len(done_before),
+                "errors": [],
+                "elapsed_sec": round(time.time() - t0, 1),
+                "symbols_count": int(bars["vt_symbol"].n_unique()),
+            }
 
     errors: list[str] = []
     done = 0
@@ -103,11 +122,11 @@ def run_batch_eval(
         if progress_cb:
             progress_cb(done, len(factor_names), name)
 
-    eval_store.finish_run(eval_db, run_id, "done", factors_done=done)
+    eval_store.finish_run(eval_db, run_id, "done", factors_done=len(done_before) + done)
     return {
         "run_id": run_id,
-        "factors_total": len(factor_names),
-        "factors_done": done,
+        "factors_total": len(done_before) + len(factor_names),
+        "factors_done": len(done_before) + done,
         "errors": errors,
         "elapsed_sec": round(time.time() - t0, 1),
         "symbols_count": int(bars["vt_symbol"].n_unique()),