refactor: use a single agent model path

agent_platform/runtime/app.py

@@ -10,7 +10,7 @@ from typing import Annotated, Any
 
 import httpx
 import uvicorn
-from fastapi import FastAPI, Header, HTTPException, status
+from fastapi import FastAPI, Header, HTTPException
 from fastapi.responses import JSONResponse, StreamingResponse
 
 from agent_platform.auth import UserIdentity, decode_openwebui_identity, verify_service_bearer
@@ -198,16 +198,6 @@ def create_app(
             return await forward_direct()
 
         stable_chat_id = (chat_id or message_id or f"ephemeral-{uuid.uuid4().hex}").strip()
-        selected_mode = await app.state.store.select_mode(identity.user_id, chat_id or "", spec.mode)
-        if selected_mode == "work" and spec.mode == "chat":
-            raise HTTPException(
-                status_code=status.HTTP_409_CONFLICT,
-                detail="This conversation has been upgraded to Work and cannot return to Chat.",
-            )
-
-        if spec.mode == "chat":
-            return await forward_direct()
-
         messages = [message.model_dump(exclude_none=True) for message in body.messages]
         if not body.stream:
 
@@ -224,7 +214,7 @@ def create_app(
             )
             return _completion(body.model, answer)
 
-        async def work_stream() -> AsyncIterator[bytes]:
+        async def agent_stream() -> AsyncIterator[bytes]:
             queue: asyncio.Queue[tuple[str, Any]] = asyncio.Queue()
 
             async def publish(event_type: str, payload: dict[str, Any]) -> None:
@@ -255,7 +245,7 @@ def create_app(
                     if kind == "done":
                         break
                     if kind == "error":
-                        yield _sse_chunk(body.model, f"\n\nWork 运行失败：{value}")
+                        yield _sse_chunk(body.model, f"\n\nAgent 运行失败：{value}")
                         continue
                     if kind == "answer":
                         text = str(value)
@@ -271,7 +261,7 @@ def create_app(
                 await asyncio.gather(task, return_exceptions=True)
 
         return StreamingResponse(
-            work_stream(),
+            agent_stream(),
             media_type="text/event-stream",
             headers={"Cache-Control": "no-cache", "X-Accel-Buffering": "no"},
         )