feat(glm): max_tokens 可选透传（site-import 前置）

max_tokens 探针结论: 8192 可用（glm-4-flash 实测 max_tokens=8192 调用成功返回，finish_reason=stop；Task 5 可按 8192 取值）

Co-Authored-By: Claude Code <noreply@anthropic.com>

app/engine/providers/glm.py

@@ -13,9 +13,16 @@ DEFAULT_MODEL = "glm-4-flash"
 
 
 class GLMProvider(AIProvider):
-    def __init__(self, api_key: str, model: str = "glm-4-flash", base_url: str = ""):
+    def __init__(
+        self,
+        api_key: str,
+        model: str = "glm-4-flash",
+        base_url: str = "",
+        max_tokens: int | None = None,
+    ):
         self.client = ZhipuAI(api_key=api_key, base_url=base_url or None)
         self.model = model
+        self.max_tokens = max_tokens
 
     async def chat(self, messages: list[dict], system_prompt: str) -> str:
         full_messages = [{"role": "system", "content": system_prompt}] + messages
@@ -74,6 +81,7 @@ class GLMProvider(AIProvider):
                 model=self.model,
                 messages=messages,
                 temperature=temperature,
+                **({"max_tokens": self.max_tokens} if self.max_tokens is not None else {}),
             )
             return resp.choices[0].message.content