fix: normalize non-scalar prediction; harden predictions insert

app/harness/inference.py

@@ -14,6 +14,7 @@ from __future__ import annotations
 
 import asyncio
 import json
+import sqlite3
 from collections import defaultdict
 from dataclasses import dataclass
 from typing import TYPE_CHECKING, Any
@@ -162,6 +163,24 @@ def _to_text_field(value: Any) -> str:
     return json.dumps(value, ensure_ascii=False)
 
 
+def _normalize_prediction(answer: object) -> str | None:
+    """归一化 prediction 落库值。
+
+    LLM 提交的 answer 有时是 list/dict（如 {'answer': ['B']}），sqlite 无法绑定
+    非标量类型直接入库会抛 ProgrammingError 击穿整轮 gather。None 保留（INFRA 空
+    预测语义，供正确率判定天然计错）；str 原样；其余 JSON 序列化为文本。
+
+    参数:
+        answer: LoopResult.result 中的 answer 原始值（可能是 None/str/list/dict）。
+
+    返回:
+        None（保留空预测语义）或可直接入库的字符串。
+    """
+    if answer is None or isinstance(answer, str):
+        return answer
+    return _to_text_field(answer)
+
+
 def _zero_result(run_id: str) -> InferenceResult:
     """空记录时的零值 InferenceResult。
 
@@ -419,7 +438,7 @@ async def _run_single_question(
         reasoning = _to_text_field(result_dict.get("reasoning", ""))
         record.update(
             {
-                "prediction": result_dict.get("answer"),
+                "prediction": _normalize_prediction(result_dict.get("answer")),
                 "evidence": evidence,
                 "reasoning": reasoning,
                 "steps_used": loop_result.steps_used,
@@ -442,8 +461,18 @@ async def _run_single_question(
     except Exception:
         logger.exception("[{}] QA {} 执行异常", qa.video_id, qa.question_id)
 
-    # prediction 必落库（try 外，无论成败）
-    await asyncio.to_thread(log.insert, "predictions", record)
+    # prediction 必落库（try 外，无论成败）；绑定异常降级为最小 error 行，不击穿 gather
+    try:
+        await asyncio.to_thread(log.insert, "predictions", record)
+    except (sqlite3.InterfaceError, sqlite3.ProgrammingError):
+        logger.exception("[{}] QA {} 落库绑定异常，降级为 error 行", qa.video_id, qa.question_id)
+        record["prediction"] = None
+        record["stop_reason"] = "error"
+        await asyncio.to_thread(
+            log.insert,
+            "predictions",
+            {k: v for k, v in record.items() if isinstance(v, (str, int, float, type(None)))},
+        )
     return record