feat: add deep think feature (#311)

* feat: implement backend logic

* feat: implement api/config endpoint

* rename the symbol

* feat: re-implement configuration at client-side

* feat: add client-side of deep thinking

* fix backend bug

* feat: add reasoning block

* docs: update readme

* fix: translate into English

* fix: change icon to lightbulb

* feat: ignore more bad cases

* feat: adjust thinking layout, and implement auto scrolling

* docs: add comments

---------

Co-authored-by: Henry Li <henry1943@163.com>

src/server/app.py

@@ -24,7 +24,6 @@ from src.prompt_enhancer.graph.builder import build_graph as build_prompt_enhanc
 from src.rag.builder import build_retriever
 from src.rag.retriever import Resource
 from src.server.chat_request import (
-    ChatMessage,
     ChatRequest,
     EnhancePromptRequest,
     GeneratePodcastRequest,
@@ -39,6 +38,8 @@ from src.server.rag_request import (
     RAGResourceRequest,
     RAGResourcesResponse,
 )
+from src.server.config_request import ConfigResponse
+from src.llms.llm import get_configured_llm_models
 from src.tools import VolcengineTTS
 
 logger = logging.getLogger(__name__)
@@ -81,6 +82,7 @@ async def chat_stream(request: ChatRequest):
             request.mcp_settings,
             request.enable_background_investigation,
             request.report_style,
+            request.enable_deep_thinking,
         ),
         media_type="text/event-stream",
     )
@@ -98,6 +100,7 @@ async def _astream_workflow_generator(
     mcp_settings: dict,
     enable_background_investigation: bool,
     report_style: ReportStyle,
+    enable_deep_thinking: bool,
 ):
     input_ = {
         "messages": messages,
@@ -125,6 +128,7 @@ async def _astream_workflow_generator(
             "max_search_results": max_search_results,
             "mcp_settings": mcp_settings,
             "report_style": report_style.value,
+            "enable_deep_thinking": enable_deep_thinking,
         },
         stream_mode=["messages", "updates"],
         subgraphs=True,
@@ -156,6 +160,10 @@ async def _astream_workflow_generator(
             "role": "assistant",
             "content": message_chunk.content,
         }
+        if message_chunk.additional_kwargs.get("reasoning_content"):
+            event_stream_message["reasoning_content"] = message_chunk.additional_kwargs[
+                "reasoning_content"
+            ]
         if message_chunk.response_metadata.get("finish_reason"):
             event_stream_message["finish_reason"] = message_chunk.response_metadata.get(
                 "finish_reason"
@@ -399,3 +407,12 @@ async def rag_resources(request: Annotated[RAGResourceRequest, Query()]):
     if retriever:
         return RAGResourcesResponse(resources=retriever.list_resources(request.query))
     return RAGResourcesResponse(resources=[])
+
+
+@app.get("/api/config", response_model=ConfigResponse)
+async def config():
+    """Get the config of the server."""
+    return ConfigResponse(
+        rag=RAGConfigResponse(provider=SELECTED_RAG_PROVIDER),
+        models=get_configured_llm_models(),
+    )

src/server/chat_request.py

@@ -62,6 +62,9 @@ class ChatRequest(BaseModel):
     report_style: Optional[ReportStyle] = Field(
         ReportStyle.ACADEMIC, description="The style of the report"
     )
+    enable_deep_thinking: Optional[bool] = Field(
+        False, description="Whether to enable deep thinking"
+    )
 
 
 class TTSRequest(BaseModel):

src/server/config_request.py

@@ -0,0 +1,13 @@
+# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
+# SPDX-License-Identifier: MIT
+
+from pydantic import BaseModel, Field
+
+from src.server.rag_request import RAGConfigResponse
+
+
+class ConfigResponse(BaseModel):
+    """Response model for server config."""
+
+    rag: RAGConfigResponse = Field(..., description="The config of the RAG")
+    models: dict[str, list[str]] = Field(..., description="The configured models")