Add prompt improvement button in drawer

backend/services/test_runs/evaluator.py

@@ -15,7 +15,6 @@ from services.test_runs.text_runner import RawToolCall, RawTurnResult, TextCaseR
 from test_schemas import (
     BatchEvaluationResult,
     BatchTurnResult,
-    FixedInputTurn,
     OverallCriterion,
     ReplyExpectedBehavior,
     TestCaseDefinition,
@@ -32,9 +31,7 @@ class EvaluatedCase:
     @property
     def passed(self) -> bool:
         evaluations = [
-            item
-            for turn in self.turns
-            for item in turn.evaluations
+            item for turn in self.turns for item in turn.evaluations
         ] + self.overall_criteria
         return all(item.status == "pass" for item in evaluations)
 
@@ -93,29 +90,47 @@ class LLMJudge:
             )
         try:
             async with httpx.AsyncClient(timeout=self._timeout_seconds) as client:
-                response = await client.post(
-                    f"{base_url}/chat/completions",
-                    headers={
-                        "Authorization": f"Bearer {api_key}",
-                        "Content-Type": "application/json",
-                    },
-                    json=payload,
-                )
-            response.raise_for_status()
-            body = response.json()
-            content = body["choices"][0]["message"]["content"]
-            if isinstance(content, list):
-                content = "".join(
-                    str(part.get("text") or "")
-                    for part in content
-                    if isinstance(part, dict)
-                )
-            parsed = self._parse_json(str(content or ""))
-            return (
-                bool(parsed.get("passed")),
-                str(parsed.get("reason") or "LLM 未提供判断理由"),
-                str(parsed.get("actual") or ""),
-            )
+                for attempt in range(2):
+                    request_payload = dict(payload)
+                    if attempt:
+                        request_payload["messages"] = [
+                            {
+                                "role": "user",
+                                "content": (
+                                    f"{prompt}\n\n格式修正：上一次响应无法解析。"
+                                    "请只返回一个完整 JSON 对象，不要重复输出、"
+                                    "不要添加解释或 Markdown。"
+                                ),
+                            }
+                        ]
+                    response = await client.post(
+                        f"{base_url}/chat/completions",
+                        headers={
+                            "Authorization": f"Bearer {api_key}",
+                            "Content-Type": "application/json",
+                        },
+                        json=request_payload,
+                    )
+                    response.raise_for_status()
+                    try:
+                        body = response.json()
+                        content = body["choices"][0]["message"]["content"]
+                        if isinstance(content, list):
+                            content = "".join(
+                                str(part.get("text") or "")
+                                for part in content
+                                if isinstance(part, dict)
+                            )
+                        parsed = self._parse_json(str(content or ""))
+                    except (KeyError, IndexError, TypeError, ValueError):
+                        if attempt == 0:
+                            continue
+                        raise
+                    return (
+                        bool(parsed.get("passed")),
+                        str(parsed.get("reason") or "LLM 未提供判断理由"),
+                        str(parsed.get("actual") or ""),
+                    )
         except TestExecutionError:
             raise
         except (httpx.HTTPError, KeyError, IndexError, TypeError, ValueError) as exc:
@@ -133,14 +148,10 @@ class LLMJudge:
             text = re.sub(r"^```(?:json)?\s*", "", text)
             text = re.sub(r"\s*```$", "", text)
         start = text.find("{")
-        end = text.rfind("}")
-        if start < 0 or end < start:
+        if start < 0:
             raise ValueError("评估模型没有返回 JSON")
-        parsed = json.loads(text[start : end + 1])
-        if (
-            not isinstance(parsed, dict)
-            or not isinstance(parsed.get("passed"), bool)
-        ):
+        parsed, _end = json.JSONDecoder().raw_decode(text[start:])
+        if not isinstance(parsed, dict) or not isinstance(parsed.get("passed"), bool):
             raise ValueError("评估模型返回格式不正确")
         return parsed
 
@@ -221,7 +232,9 @@ class EvaluationEngine:
             )
 
         normalized_reply = reply.casefold()
-        matches = [keyword.casefold() in normalized_reply for keyword in behavior.keywords]
+        matches = [
+            keyword.casefold() in normalized_reply for keyword in behavior.keywords
+        ]
         matched = all(matches) if behavior.keyword_match_mode == "all" else any(matches)
         passed = not matched if behavior.negate_keywords else matched
         relation = (