feat:修改投顾agent和nl2sql的功能

tool/llm.py

@@ -169,21 +169,40 @@ class LLMClient:
         temperature: float | None,
         max_tokens: int | None,
     ) -> str:
-        payload = {
-            "model": model,
-            "messages": messages,
-            "temperature": self.cfg.temperature if temperature is None else temperature,
-            "max_tokens": self.cfg.max_tokens if max_tokens is None else max_tokens,
-            "stream": False,
-        }
+        request_max_tokens = self.cfg.max_tokens if max_tokens is None else max_tokens
         url = f"{backend.base_url}/chat/completions"
         # 指数退避：retry_backoff_sec → 翻倍 → …，最多 max_retries 次
         for attempt in range(self.cfg.max_retries):
+            payload = {
+                "model": model,
+                "messages": messages,
+                "temperature": self.cfg.temperature if temperature is None else temperature,
+                "max_tokens": request_max_tokens,
+                "stream": False,
+            }
             try:
                 async with backend.client(self.cfg.timeout) as client:
                     r = await client.post(url, headers=backend.headers, json=payload)
                     r.raise_for_status()
-                return r.json()["choices"][0]["message"]["content"]
+                choice = r.json()["choices"][0]
+                message = choice["message"]
+                content = message.get("content")
+                if isinstance(content, str) and content.strip():
+                    return content
+
+                # DeepSeek reasoning models may consume the entire small token budget
+                # in reasoning_content, leaving content empty and finish_reason=length.
+                if choice.get("finish_reason") == "length" and attempt < self.cfg.max_retries - 1:
+                    request_max_tokens = max(request_max_tokens * 4, 256)
+                    logger.warning(
+                        "chat backend=%s model=%r returned empty content after token limit; "
+                        "retrying with max_tokens=%d",
+                        backend.name,
+                        model,
+                        request_max_tokens,
+                    )
+                    continue
+                raise ValueError("LLM 返回空内容")
             except Exception:
                 if attempt == self.cfg.max_retries - 1:
                     raise