x

app/config.py

@@ -19,6 +19,7 @@ class Settings(BaseModel):
     openai_port: int = 8001
     vllm_openai_internal_url: str = "http://127.0.0.1:8001/v1"
     public_model_name: str = "Qwen_local_model"
+    default_enable_thinking: bool = False
     reasoning_enabled: bool = False
     model_root: str = "/opt/model"
     offline_mode: bool = True
@@ -49,6 +50,7 @@ def get_settings() -> Settings:
         openai_port=runtime["openai_port"],
         vllm_openai_internal_url=runtime["vllm_openai_internal_url"],
         public_model_name=runtime["public_model_name"],
+        default_enable_thinking=runtime["default_enable_thinking"],
         reasoning_enabled=runtime["reasoning_enabled"],
         model_root=runtime["model_root"],
         offline_mode=runtime["offline_mode"],

app/model_catalog.py

@@ -74,6 +74,7 @@ def resolve_runtime_settings(content: dict[str, Any]) -> dict[str, Any]:
         "openai_port": openai_port,
         "vllm_openai_internal_url": internal_url.rstrip("/"),
         "public_model_name": _to_str(content.get("public_model_name"), "Qwen_local_model"),
+        "default_enable_thinking": _to_bool(content.get("default_enable_thinking"), False),
         "api_key": str(content.get("api_key", "")).strip() or None,
         "reasoning_enabled": _to_bool(content.get("reasoning_enabled"), False),
         "tensor_parallel_size": _to_int(content.get("tensor_parallel_size"), 2),

app/start_openai.py

@@ -1,3 +1,4 @@
+import json
 import os
 import subprocess
 import sys
@@ -19,6 +20,7 @@ def build_command() -> list[str]:
     host = str(runtime["openai_host"])
     port = str(runtime["openai_port"])
     public_model_name = str(runtime["public_model_name"]).strip()
+    default_enable_thinking = bool(runtime["default_enable_thinking"])
     reasoning_enabled = bool(runtime["reasoning_enabled"])
     api_key = runtime["api_key"] or ""
     dtype = str(updates["dtype"] or runtime["dtype"])
@@ -56,6 +58,12 @@ def build_command() -> list[str]:
         cmd.append("--enable-auto-tool-choice")
     if updates["tool_call_parser"]:
         cmd.extend(["--tool-call-parser", str(updates["tool_call_parser"])])
+    cmd.extend(
+        [
+            "--default-chat-template-kwargs",
+            json.dumps({"enable_thinking": default_enable_thinking}),
+        ]
+    )
     if reasoning_enabled and reasoning_parser:
         cmd.extend(["--reasoning-parser", reasoning_parser])
     if quantization: