[Feature]Optimization of Thinking Pattern Framework (#4302)

* add model status in vl

* add x1 parser

* add model_status

* fix parser

* fix parser

* fix parser

* fix parser

* Revert "fix parser"

This reverts commit 300f446d8a.

* fix parser

* fix

* fix

* fix

* fix

* fix parser

* fix unit test

* fix unit test

* add unit test

* fix

* fix

* add unit test

* fix unit test

* add unit test

* add unit test

* fix unit test

* fix unit test

* fix bug

* fix unit test

* x1 tool parser

* fix unit test

* fix unit test

* fix unit test

* fix n

* fix unit test

* add unit test

* add unit test

* remove pring

fastdeploy/input/qwen_vl_processor/qwen_vl_processor.py

@@ -267,6 +267,18 @@ class QwenVLProcessor(TextProcessor):
         # Set default max_tokens if not specified
         if request.get("max_tokens") is None:
             request["max_tokens"] = max(1, max_model_len - len(request["prompt_token_ids"]))  # Ensure at least 1 token
+        if self.reasoning_parser:
+            model_status = self.reasoning_parser.get_model_status(request["prompt_token_ids"])
+            parts = request["request_id"].split("_")
+            if len(parts) > 1:
+                real_req_id = parts[0]
+                index = int(parts[1])
+                n = request.get("n", 1)
+                for idx in range(index * n, (index + 1) * n):
+                    self.model_status_dict[f"{real_req_id}_{idx}"] = model_status
+            else:
+                self.model_status_dict[request["request_id"]] = model_status
+            request["enable_thinking"] = model_status == "think_start"
         data_processor_logger.info(f"Processed request {request}")
 
         return request