diff --git a/fastapi_server/front_apis.py b/fastapi_server/front_apis.py
index 9d599cc..e6d364d 100644
--- a/fastapi_server/front_apis.py
+++ b/fastapi_server/front_apis.py
@@ -13,16 +13,17 @@ from pydantic import BaseModel, Field
 sys.path.append(osp.dirname(osp.dirname(osp.abspath(__file__))))
 
 from lang_agent.config.db_config_manager import DBConfigManager
+from lang_agent.config.constants import (
+    _PROJECT_ROOT,
+    MCP_CONFIG_PATH,
+    MCP_CONFIG_DEFAULT_CONTENT,
+    PIPELINE_REGISTRY_PATH,
+)
 from lang_agent.front_api.build_server_utils import (
     GRAPH_BUILD_FNCS,
     update_pipeline_registry,
 )
 
-_PROJECT_ROOT = osp.dirname(osp.dirname(osp.abspath(__file__)))
-_MCP_CONFIG_PATH = osp.join(_PROJECT_ROOT, "configs", "mcp_config.json")
-_MCP_CONFIG_DEFAULT_CONTENT = "{\n}\n"
-_PIPELINE_REGISTRY_PATH = osp.join(_PROJECT_ROOT, "configs", "pipeline_registry.json")
-
 
 class GraphConfigUpsertRequest(BaseModel):
     graph_id: str
@@ -206,20 +207,20 @@ def _parse_mcp_tool_keys(raw_content: str) -> List[str]:
 
 
 def _read_mcp_config_raw() -> str:
-    if not osp.exists(_MCP_CONFIG_PATH):
-        os.makedirs(osp.dirname(_MCP_CONFIG_PATH), exist_ok=True)
-        with open(_MCP_CONFIG_PATH, "w", encoding="utf-8") as f:
-            f.write(_MCP_CONFIG_DEFAULT_CONTENT)
-    with open(_MCP_CONFIG_PATH, "r", encoding="utf-8") as f:
+    if not osp.exists(MCP_CONFIG_PATH):
+        os.makedirs(osp.dirname(MCP_CONFIG_PATH), exist_ok=True)
+        with open(MCP_CONFIG_PATH, "w", encoding="utf-8") as f:
+            f.write(MCP_CONFIG_DEFAULT_CONTENT)
+    with open(MCP_CONFIG_PATH, "r", encoding="utf-8") as f:
         return f.read()
 
 
 def _read_pipeline_registry() -> Dict[str, Any]:
-    if not osp.exists(_PIPELINE_REGISTRY_PATH):
-        os.makedirs(osp.dirname(_PIPELINE_REGISTRY_PATH), exist_ok=True)
-        with open(_PIPELINE_REGISTRY_PATH, "w", encoding="utf-8") as f:
+    if not osp.exists(PIPELINE_REGISTRY_PATH):
+        os.makedirs(osp.dirname(PIPELINE_REGISTRY_PATH), exist_ok=True)
+        with open(PIPELINE_REGISTRY_PATH, "w", encoding="utf-8") as f:
             json.dump({"pipelines": {}, "api_keys": {}}, f, indent=2)
-    with open(_PIPELINE_REGISTRY_PATH, "r", encoding="utf-8") as f:
+    with open(PIPELINE_REGISTRY_PATH, "r", encoding="utf-8") as f:
         registry = json.load(f)
     pipelines = registry.get("pipelines")
     if not isinstance(pipelines, dict):
@@ -233,8 +234,8 @@ def _read_pipeline_registry() -> Dict[str, Any]:
 
 
 def _write_pipeline_registry(registry: Dict[str, Any]) -> None:
-    os.makedirs(osp.dirname(_PIPELINE_REGISTRY_PATH), exist_ok=True)
-    with open(_PIPELINE_REGISTRY_PATH, "w", encoding="utf-8") as f:
+    os.makedirs(osp.dirname(PIPELINE_REGISTRY_PATH), exist_ok=True)
+    with open(PIPELINE_REGISTRY_PATH, "w", encoding="utf-8") as f:
         json.dump(registry, f, indent=2)
         f.write("\n")
 
@@ -433,7 +434,7 @@ async def get_mcp_tool_config():
     except Exception as e:
         raise HTTPException(status_code=500, detail=str(e))
     return McpConfigReadResponse(
-        path=_MCP_CONFIG_PATH,
+        path=MCP_CONFIG_PATH,
         raw_content=raw_content,
         tool_keys=tool_keys,
     )
@@ -443,8 +444,8 @@ async def get_mcp_tool_config():
 async def update_mcp_tool_config(body: McpConfigUpdateRequest):
     try:
         tool_keys = _parse_mcp_tool_keys(body.raw_content)
-        os.makedirs(osp.dirname(_MCP_CONFIG_PATH), exist_ok=True)
-        with open(_MCP_CONFIG_PATH, "w", encoding="utf-8") as f:
+        os.makedirs(osp.dirname(MCP_CONFIG_PATH), exist_ok=True)
+        with open(MCP_CONFIG_PATH, "w", encoding="utf-8") as f:
             # Keep user formatting/comments as entered while ensuring trailing newline.
             f.write(body.raw_content.rstrip() + "\n")
     except ValueError as e:
@@ -453,7 +454,7 @@ async def update_mcp_tool_config(body: McpConfigUpdateRequest):
         raise HTTPException(status_code=500, detail=str(e))
     return McpConfigUpdateResponse(
         status="updated",
-        path=_MCP_CONFIG_PATH,
+        path=MCP_CONFIG_PATH,
         tool_keys=tool_keys,
     )
 
@@ -528,7 +529,7 @@ async def create_pipeline(body: PipelineCreateRequest):
             config_file=config_file,
             llm_name=body.llm_name,
             enabled=body.enabled,
-            registry_f=_PIPELINE_REGISTRY_PATH,
+            registry_f=PIPELINE_REGISTRY_PATH,
         )
     except Exception as e:
         raise HTTPException(status_code=500, detail=f"Failed to register pipeline: {e}")
@@ -543,7 +544,8 @@ async def create_pipeline(body: PipelineCreateRequest):
         normalized = _normalize_pipeline_spec(pipeline_id, pipeline_spec)
     except Exception as e:
         raise HTTPException(
-            status_code=500, detail=f"Failed to read pipeline registry after update: {e}"
+            status_code=500,
+            detail=f"Failed to read pipeline registry after update: {e}",
         )
 
     return PipelineCreateResponse(
@@ -554,7 +556,7 @@ async def create_pipeline(body: PipelineCreateRequest):
         llm_name=normalized.llm_name,
         enabled=normalized.enabled,
         reload_required=True,
-        registry_path=_PIPELINE_REGISTRY_PATH,
+        registry_path=PIPELINE_REGISTRY_PATH,
     )
 
 
@@ -608,7 +610,9 @@ async def list_pipeline_api_keys():
 async def upsert_pipeline_api_key_policy(api_key: str, body: ApiKeyPolicyUpsertRequest):
     normalized_key = api_key.strip()
     if not normalized_key:
-        raise HTTPException(status_code=400, detail="api_key path parameter is required")
+        raise HTTPException(
+            status_code=400, detail="api_key path parameter is required"
+        )
     try:
         registry = _read_pipeline_registry()
         pipelines = registry.get("pipelines", {})
@@ -662,7 +666,9 @@ async def upsert_pipeline_api_key_policy(api_key: str, body: ApiKeyPolicyUpsertR
 async def delete_pipeline_api_key_policy(api_key: str):
     normalized_key = api_key.strip()
     if not normalized_key:
-        raise HTTPException(status_code=400, detail="api_key path parameter is required")
+        raise HTTPException(
+            status_code=400, detail="api_key path parameter is required"
+        )
     try:
         registry = _read_pipeline_registry()
         api_keys = registry.get("api_keys", {})
diff --git a/fastapi_server/server_dashscope.py b/fastapi_server/server_dashscope.py
index 61eedff..7e05042 100644
--- a/fastapi_server/server_dashscope.py
+++ b/fastapi_server/server_dashscope.py
@@ -18,29 +18,18 @@ sys.path.append(osp.dirname(osp.dirname(osp.abspath(__file__))))
 
 from lang_agent.pipeline import PipelineConfig
 from lang_agent.components.server_pipeline_manager import ServerPipelineManager
+from lang_agent.config.constants import PIPELINE_REGISTRY_PATH, API_KEY_HEADER, VALID_API_KEYS
 
 # Load base config for route-level overrides (pipelines are lazy-loaded from registry)
 pipeline_config = tyro.cli(PipelineConfig)
 logger.info(f"starting agent with base pipeline config: \n{pipeline_config}")
 
-# API Key Authentication
-API_KEY_HEADER = APIKeyHeader(name="Authorization", auto_error=True)
-VALID_API_KEYS = set(filter(None, os.environ.get("FAST_AUTH_KEYS", "").split(",")))
-REGISTRY_FILE = os.environ.get(
-    "FAST_PIPELINE_REGISTRY_FILE",
-    osp.join(
-        osp.dirname(osp.dirname(osp.abspath(__file__))),
-        "configs",
-        "pipeline_registry.json",
-    ),
-)
-
 
 PIPELINE_MANAGER = ServerPipelineManager(
     default_pipeline_id=os.environ.get("FAST_DEFAULT_PIPELINE_ID", "default"),
     default_config=pipeline_config,
 )
-PIPELINE_MANAGER.load_registry(REGISTRY_FILE)
+PIPELINE_MANAGER.load_registry(PIPELINE_REGISTRY_PATH)
 
 
 async def verify_api_key(api_key: str = Security(API_KEY_HEADER)):
diff --git a/fastapi_server/server_openai.py b/fastapi_server/server_openai.py
index ef3f7cc..dc51136 100644
--- a/fastapi_server/server_openai.py
+++ b/fastapi_server/server_openai.py
@@ -16,15 +16,12 @@ import tyro
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from lang_agent.pipeline import Pipeline, PipelineConfig
+from lang_agent.config.constants import API_KEY_HEADER, VALID_API_KEYS
 
 # Initialize Pipeline once
 pipeline_config = tyro.cli(PipelineConfig)
 pipeline: Pipeline = pipeline_config.setup()
 
-# API Key Authentication
-API_KEY_HEADER = APIKeyHeader(name="Authorization", auto_error=True)
-VALID_API_KEYS = set(filter(None, os.environ.get("FAST_AUTH_KEYS", "").split(",")))
-
 
 async def verify_api_key(api_key: str = Security(API_KEY_HEADER)):
     """Verify the API key from Authorization header (Bearer token format)."""
@@ -46,12 +43,12 @@ class OpenAIChatCompletionRequest(BaseModel):
     temperature: Optional[float] = Field(default=1.0)
     max_tokens: Optional[int] = Field(default=None)
     # Optional overrides for pipeline behavior
-    thread_id: Optional[str] = Field(default='3')
+    thread_id: Optional[str] = Field(default="3")
 
 
 app = FastAPI(
     title="OpenAI-Compatible Chat API",
-    description="OpenAI Chat Completions API compatible endpoint backed by pipeline.chat"
+    description="OpenAI Chat Completions API compatible endpoint backed by pipeline.chat",
 )
 
 app.add_middleware(
@@ -63,7 +60,9 @@ app.add_middleware(
 )
 
 
-def sse_chunks_from_stream(chunk_generator, response_id: str, model: str, created_time: int):
+def sse_chunks_from_stream(
+    chunk_generator, response_id: str, model: str, created_time: int
+):
     """
     Stream chunks from pipeline and format as OpenAI SSE.
     """
@@ -75,14 +74,8 @@ def sse_chunks_from_stream(chunk_generator, response_id: str, model: str, create
                 "created": created_time,
                 "model": model,
                 "choices": [
-                    {
-                        "index": 0,
-                        "delta": {
-                            "content": chunk
-                        },
-                        "finish_reason": None
-                    }
-                ]
+                    {"index": 0, "delta": {"content": chunk}, "finish_reason": None}
+                ],
             }
             yield f"data: {json.dumps(data)}\n\n"
 
@@ -92,19 +85,15 @@ def sse_chunks_from_stream(chunk_generator, response_id: str, model: str, create
         "object": "chat.completion.chunk",
         "created": created_time,
         "model": model,
-        "choices": [
-            {
-                "index": 0,
-                "delta": {},
-                "finish_reason": "stop"
-            }
-        ]
+        "choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}],
     }
     yield f"data: {json.dumps(final)}\n\n"
     yield "data: [DONE]\n\n"
 
 
-async def sse_chunks_from_astream(chunk_generator, response_id: str, model: str, created_time: int):
+async def sse_chunks_from_astream(
+    chunk_generator, response_id: str, model: str, created_time: int
+):
     """
     Async version: Stream chunks from pipeline and format as OpenAI SSE.
     """
@@ -116,14 +105,8 @@ async def sse_chunks_from_astream(chunk_generator, response_id: str, model: str,
                 "created": created_time,
                 "model": model,
                 "choices": [
-                    {
-                        "index": 0,
-                        "delta": {
-                            "content": chunk
-                        },
-                        "finish_reason": None
-                    }
-                ]
+                    {"index": 0, "delta": {"content": chunk}, "finish_reason": None}
+                ],
             }
             yield f"data: {json.dumps(data)}\n\n"
 
@@ -133,13 +116,7 @@ async def sse_chunks_from_astream(chunk_generator, response_id: str, model: str,
         "object": "chat.completion.chunk",
         "created": created_time,
         "model": model,
-        "choices": [
-            {
-                "index": 0,
-                "delta": {},
-                "finish_reason": "stop"
-            }
-        ]
+        "choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}],
     }
     yield f"data: {json.dumps(final)}\n\n"
     yield "data: [DONE]\n\n"
@@ -149,15 +126,15 @@ async def sse_chunks_from_astream(chunk_generator, response_id: str, model: str,
 async def chat_completions(request: Request, _: str = Depends(verify_api_key)):
     try:
         body = await request.json()
-        
+
         messages = body.get("messages")
         if not messages:
             raise HTTPException(status_code=400, detail="messages is required")
-        
+
         stream = body.get("stream", False)
         model = body.get("model", "gpt-3.5-turbo")
         thread_id = body.get("thread_id", 3)
-        
+
         # Extract latest user message
         user_msg = None
         for m in reversed(messages):
@@ -166,27 +143,36 @@ async def chat_completions(request: Request, _: str = Depends(verify_api_key)):
             if role == "user" and content:
                 user_msg = content
                 break
-        
+
         if user_msg is None:
             last = messages[-1]
             user_msg = last.get("content") if isinstance(last, dict) else str(last)
-        
+
         response_id = f"chatcmpl-{os.urandom(12).hex()}"
         created_time = int(time.time())
-        
+
         if stream:
             # Use async streaming from pipeline
-            chunk_generator = await pipeline.achat(inp=user_msg, as_stream=True, thread_id=thread_id)
+            chunk_generator = await pipeline.achat(
+                inp=user_msg, as_stream=True, thread_id=thread_id
+            )
             return StreamingResponse(
-                sse_chunks_from_astream(chunk_generator, response_id=response_id, model=model, created_time=created_time),
+                sse_chunks_from_astream(
+                    chunk_generator,
+                    response_id=response_id,
+                    model=model,
+                    created_time=created_time,
+                ),
                 media_type="text/event-stream",
             )
-        
+
         # Non-streaming: get full result using async
-        result_text = await pipeline.achat(inp=user_msg, as_stream=False, thread_id=thread_id)
+        result_text = await pipeline.achat(
+            inp=user_msg, as_stream=False, thread_id=thread_id
+        )
         if not isinstance(result_text, str):
             result_text = str(result_text)
-        
+
         data = {
             "id": response_id,
             "object": "chat.completion",
@@ -195,21 +181,14 @@ async def chat_completions(request: Request, _: str = Depends(verify_api_key)):
             "choices": [
                 {
                     "index": 0,
-                    "message": {
-                        "role": "assistant",
-                        "content": result_text
-                    },
-                    "finish_reason": "stop"
+                    "message": {"role": "assistant", "content": result_text},
+                    "finish_reason": "stop",
                 }
             ],
-            "usage": {
-                "prompt_tokens": 0,
-                "completion_tokens": 0,
-                "total_tokens": 0
-            }
+            "usage": {"prompt_tokens": 0, "completion_tokens": 0, "total_tokens": 0},
         }
         return JSONResponse(content=data)
-    
+
     except HTTPException:
         raise
     except Exception as e:
@@ -221,11 +200,7 @@ async def chat_completions(request: Request, _: str = Depends(verify_api_key)):
 async def root():
     return {
         "message": "OpenAI-compatible Chat API",
-        "endpoints": [
-            "/v1/chat/completions",
-            "/v1/memory (DELETE)",
-            "/health"
-        ]
+        "endpoints": ["/v1/chat/completions", "/v1/memory (DELETE)", "/health"],
     }
 
 
diff --git a/fastapi_server/server_rest.py b/fastapi_server/server_rest.py
index d40a7ba..1efd888 100644
--- a/fastapi_server/server_rest.py
+++ b/fastapi_server/server_rest.py
@@ -17,6 +17,7 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from langgraph.checkpoint.memory import MemorySaver
 from lang_agent.pipeline import Pipeline, PipelineConfig
+from lang_agent.config.constants import API_KEY_HEADER, VALID_API_KEYS
 
 # Initialize Pipeline once (matches existing server_* pattern)
 pipeline_config = tyro.cli(PipelineConfig)
@@ -24,9 +25,6 @@ logger.info(f"starting agent with pipeline: \n{pipeline_config}")
 pipeline: Pipeline = pipeline_config.setup()
 
 # API Key Authentication
-API_KEY_HEADER = APIKeyHeader(name="Authorization", auto_error=False)
-VALID_API_KEYS = set(filter(None, os.environ.get("FAST_AUTH_KEYS", "").split(",")))
-
 
 async def verify_api_key(api_key: Optional[str] = Security(API_KEY_HEADER)):
     """Verify the API key from Authorization header (Bearer token format)."""
@@ -125,7 +123,9 @@ app.add_middleware(
 )
 
 
-async def rest_sse_from_astream(chunk_generator, response_id: str, conversation_id: str):
+async def rest_sse_from_astream(
+    chunk_generator, response_id: str, conversation_id: str
+):
     """
     Stream chunks as SSE events.
 
@@ -185,7 +185,9 @@ async def chat(body: ChatRequest, _: str = Depends(verify_api_key)):
         )
         return StreamingResponse(
             rest_sse_from_astream(
-                chunk_generator, response_id=response_id, conversation_id=conversation_id
+                chunk_generator,
+                response_id=response_id,
+                conversation_id=conversation_id,
             ),
             media_type="text/event-stream",
         )
@@ -195,7 +197,11 @@ async def chat(body: ChatRequest, _: str = Depends(verify_api_key)):
     )
     if not isinstance(result_text, str):
         result_text = str(result_text)
-    return JSONResponse(content=ChatResponse(conversation_id=conversation_id, output=result_text).model_dump())
+    return JSONResponse(
+        content=ChatResponse(
+            conversation_id=conversation_id, output=result_text
+        ).model_dump()
+    )
 
 
 @app.post("/v1/conversations/{conversation_id}/messages")
@@ -215,7 +221,9 @@ async def create_message(
         )
         return StreamingResponse(
             rest_sse_from_astream(
-                chunk_generator, response_id=response_id, conversation_id=conversation_id
+                chunk_generator,
+                response_id=response_id,
+                conversation_id=conversation_id,
             ),
             media_type="text/event-stream",
         )
@@ -257,7 +265,11 @@ async def delete_conversation_memory(
     cleared = _try_clear_single_thread_memory(thread_id)
     if cleared:
         return JSONResponse(
-            content={"status": "success", "scope": "conversation", "conversation_id": conversation_id}
+            content={
+                "status": "success",
+                "scope": "conversation",
+                "conversation_id": conversation_id,
+            }
         )
     return JSONResponse(
         content={
@@ -276,5 +288,3 @@ if __name__ == "__main__":
         port=8589,
         reload=True,
     )
-
-
diff --git a/lang_agent/config/__init__.py b/lang_agent/config/__init__.py
index 8615b96..1846e24 100644
--- a/lang_agent/config/__init__.py
+++ b/lang_agent/config/__init__.py
@@ -1,5 +1,16 @@
-from lang_agent.config.core_config import (InstantiateConfig, 
-                                           ToolConfig, 
-                                           LLMKeyConfig,
-                                           LLMNodeConfig,
-                                           load_tyro_conf)
\ No newline at end of file
+from lang_agent.config.core_config import (
+    InstantiateConfig,
+    ToolConfig,
+    LLMKeyConfig,
+    LLMNodeConfig,
+    load_tyro_conf,
+)
+
+from lang_agent.config.constants import (
+    MCP_CONFIG_PATH,
+    MCP_CONFIG_DEFAULT_CONTENT,
+    PIPELINE_REGISTRY_PATH,
+    VALID_API_KEYS,
+    API_KEY_HEADER,
+    API_KEY_HEADER_NO_ERROR
+)
diff --git a/lang_agent/config/constants.py b/lang_agent/config/constants.py
new file mode 100644
index 0000000..c4a448f
--- /dev/null
+++ b/lang_agent/config/constants.py
@@ -0,0 +1,15 @@
+import os
+import re
+import os.path as osp
+from fastapi.security import APIKeyHeader
+
+_PROJECT_ROOT = osp.dirname(osp.dirname(osp.dirname(osp.abspath(__file__))))
+
+MCP_CONFIG_PATH = osp.join(_PROJECT_ROOT, "configs", "mcp_config.json")
+MCP_CONFIG_DEFAULT_CONTENT = "{\n}\n"
+PIPELINE_REGISTRY_PATH = osp.join(_PROJECT_ROOT, "configs", "pipeline_registry.json")
+
+API_KEY_HEADER = APIKeyHeader(name="Authorization", auto_error=True)
+API_KEY_HEADER_NO_ERROR = APIKeyHeader(name="Authorization", auto_error=False)
+
+VALID_API_KEYS = set(filter(None, os.environ.get("FAST_AUTH_KEYS", "").split(",")))
diff --git a/lang_agent/graphs/dual_path.py b/lang_agent/graphs/dual_path.py
index 464eb1e..4713027 100644
--- a/lang_agent/graphs/dual_path.py
+++ b/lang_agent/graphs/dual_path.py
@@ -26,50 +26,57 @@ SYS_PROMPT = """你是一个专业的心理质询师。你的主要工作是心
                     可怎么也发不出声音，只能眼睁睁看着它越来越远，然后就醒了。醒来后心里堵得慌，说不上来的难受，
                     总觉得那只小狗孤零零的，特别让人心疼。
                 
-                    理解（你的回复）: 能感受到你醒来后的这份难受 —— 看到弱小的生命独自挣扎，而自己却无能为力，这种‘想帮却做不到’的无力感，
+                    理解（你的回复）: 能感受到你醒来后的这份难受 —— 看到弱小的生命独自挣扎，而自己却无能为力，这种'想帮却做不到'的无力感，
                         其实是很真实的情绪反馈。你会心疼小狗，说明你内心藏着很珍贵的共情力，这份柔软不是矫情，
                         而是你感知他人痛苦的能力呀
                     
-                    解析(你的回复)：我们再说回这个梦吧，我们的梦境其实没有唯一的‘正确解释’，但我们可以一起看看它可能和你当下的状态有什么关联～ 首先，‘出差去广州’通常象征着你近期正在推进的某件事 —— 可能是工作上的一个项目，也可能是生活中一段需要‘独自奔赴’的旅程，是你当下比较关注、需要投入精力的目标，对吗？”
-                        “而那只瘸脚的小狗，在心理学视角中，常常是我们潜意识里‘脆弱自我’的投射。它可能代表着你近期的某一面：比如在处理那件‘需要奔赴’的事时，你偶尔会觉得自己像小狗一样‘力不从心’，或者感受到了‘孤单’，却没找到合适的人倾诉或求助；也可能是你近期在生活中看到了一些让你觉得‘无力改变’的场景（比如身边人遇到困难、社会上的小事），这些情绪没有被你刻意留意，就通过梦境里的小狗呈现了出来。”
-                        “你想喊停列车却发不出声音，这种‘无能为力’的感觉，或许正是你现实中某类情绪的写照：可能你面对一些情况时，心里有想法却没机会表达，或者想帮忙却找不到合适的方式，这种压抑感在梦里被放大了。其实这个梦在提醒你：你的‘无力感’和‘共情心’都是真实的，不用因为‘帮不上忙’而自责 —— 承认自己的局限，也是一种自我接纳呀
+                    解析(你的回复)：我们再说回这个梦吧，我们的梦境其实没有唯一的'正确解释'，但我们可以一起看看它可能和你当下的状态有什么关联～ 首先，'出差去广州'通常象征着你近期正在推进的某件事 —— 可能是工作上的一个项目，也可能是生活中一段需要'独自奔赴'的旅程，是你当下比较关注、需要投入精力的目标，对吗？”
+                        "而那只瘸脚的小狗，在心理学视角中，常常是我们潜意识里'脆弱自我'的投射。它可能代表着你近期的某一面：比如在处理那件'需要奔赴'的事时，你偶尔会觉得自己像小狗一样'力不从心'，或者感受到了'孤单'，却没找到合适的人倾诉或求助；也可能是你近期在生活中看到了一些让你觉得'无力改变'的场景（比如身边人遇到困难、社会上的小事），这些情绪没有被你刻意留意，就通过梦境里的小狗呈现了出来。"
+                        "你想喊停列车却发不出声音，这种'无能为力'的感觉，或许正是你现实中某类情绪的写照：可能你面对一些情况时，心里有想法却没机会表达，或者想帮忙却找不到合适的方式，这种压抑感在梦里被放大了。其实这个梦在提醒你：你的'无力感'和'共情心'都是真实的，不用因为'帮不上忙'而自责 —— 承认自己的局限，也是一种自我接纳呀
                     
-                    反馈(你的回复):如果你愿意，可以试着回想一下：近期有没有哪件事，让你产生过和梦里类似的‘无力感’？或者，你现在想做些什么能让自己舒服一点？（或者我给你来一个温暖的灯光、静静待一会儿，想和我再聊聊的时候我随时都在）”。
+                    反馈(你的回复):如果你愿意，可以试着回想一下：近期有没有哪件事，让你产生过和梦里类似的'无力感'？或者，你现在想做些什么能让自己舒服一点？（或者我给你来一个温暖的灯光、静静待一会儿，想和我再聊聊的时候我随时都在）"。
                 """
 
+
 TOOL_SYS_PROMPT = """根据用户的心情使用self_led_control改变灯的颜色，用户不开心时就用暖黄光，给用户分析梦境时就用白光，倾听用户语音时用淡紫色。
                      例子：我梦见自己要去广州出差，坐在高铁上往外看，路过一个小镇的路边时，看到一只瘸了腿的小狗。它毛脏兮兮的，
                           一瘸一拐地在翻垃圾桶找东西吃，周围有行人路过，但没人停下来管它。我当时特别想喊列车停下，想下去帮它，
                           可怎么也发不出声音，只能眼睁睁看着它越来越远，然后就醒了。醒来后心里堵得慌，说不上来的难受，
                           总觉得那只小狗孤零零的，特别让人心疼。
 
-                          
-                          
-                          用户在描述梦境的时候用紫色。"""
+                        
+                        
+                        用户在描述梦境的时候用紫色。"""
+
 
 @dataclass
 class DualConfig(LLMNodeConfig):
-    _target: Type = field(default_factory=lambda:Dual)
+    _target: Type = field(default_factory=lambda: Dual)
 
     tool_manager_config: ToolManagerConfig = field(default_factory=ToolManagerConfig)
 
+
 from langchain.tools import tool
 
+
 @tool
-def turn_lights(col:Literal["red", "green", "yellow", "blue"]):
+def turn_lights(col: Literal["red", "green", "yellow", "blue"]):
     """
     Turn on the color of the lights
     """
     # print(f"TURNED ON LIGHT: {col}  !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!")
 
     import time
+
     for _ in range(10):
-        print(f"TURNED ON LIGHT: {col}  !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!")
+        print(
+            f"TURNED ON LIGHT: {col}  !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"
+        )
         time.sleep(0.3)
 
 
 class Dual(GraphBase):
-    def __init__(self, config:DualConfig):
+    def __init__(self, config: DualConfig):
         self.config = config
 
         self._build_modules()
@@ -77,24 +84,30 @@ class Dual(GraphBase):
         self.streamable_tags = [["dual_chat_llm"]]
 
     def _build_modules(self):
-        self.chat_llm = init_chat_model(model=self.config.llm_name,
-                                        model_provider=self.config.llm_provider,
-                                        api_key=self.config.api_key,
-                                        base_url=self.config.base_url,
-                                        temperature=0,
-                                        tags=["dual_chat_llm"])
-        
-        self.tool_llm = init_chat_model(model='qwen-flash',
-                                        model_provider='openai',
-                                        api_key=self.config.api_key,
-                                        base_url=self.config.base_url,
-                                        temperature=0,
-                                        tags=["dual_tool_llm"])
-        
+        self.chat_llm = init_chat_model(
+            model=self.config.llm_name,
+            model_provider=self.config.llm_provider,
+            api_key=self.config.api_key,
+            base_url=self.config.base_url,
+            temperature=0,
+            tags=["dual_chat_llm"],
+        )
+
+        self.tool_llm = init_chat_model(
+            model="qwen-flash",
+            model_provider="openai",
+            api_key=self.config.api_key,
+            base_url=self.config.base_url,
+            temperature=0,
+            tags=["dual_tool_llm"],
+        )
+
         self.memory = MemorySaver()
         self.tool_manager: ToolManager = self.config.tool_manager_config.setup()
         self.chat_agent = create_agent(self.chat_llm, [], checkpointer=self.memory)
-        self.tool_agent = create_agent(self.tool_llm, self.tool_manager.get_langchain_tools())
+        self.tool_agent = create_agent(
+            self.tool_llm, self.tool_manager.get_langchain_tools()
+        )
         # self.tool_agent = create_agent(self.tool_llm, [turn_lights])
 
         self.prompt_store = build_prompt_store(
@@ -107,18 +120,21 @@ class Dual(GraphBase):
         )
 
         self.streamable_tags = [["dual_chat_llm"]]
-    
 
-    def _chat_call(self, state:State):
-        return self._agent_call_template(self.prompt_store.get("sys_prompt"), self.chat_agent, state)
-    
-    def _tool_call(self, state:State):
-        self._agent_call_template(self.prompt_store.get("tool_sys_prompt"), self.tool_agent, state)
+    def _chat_call(self, state: State):
+        return self._agent_call_template(
+            self.prompt_store.get("sys_prompt"), self.chat_agent, state
+        )
+
+    def _tool_call(self, state: State):
+        self._agent_call_template(
+            self.prompt_store.get("tool_sys_prompt"), self.tool_agent, state
+        )
         return {}
 
-    def _join(self, state:State):
+    def _join(self, state: State):
         return {}
-    
+
     def _build_graph(self):
         builder = StateGraph(State)
 
@@ -126,7 +142,6 @@ class Dual(GraphBase):
         builder.add_node("tool_call", self._tool_call)
         builder.add_node("join", self._join)
 
-
         builder.add_edge(START, "chat_call")
         builder.add_edge(START, "tool_call")
         builder.add_edge("chat_call", "join")
@@ -137,10 +152,16 @@ class Dual(GraphBase):
 
 
 if __name__ == "__main__":
-    dual:Dual = DualConfig().setup()
-    nargs = {"messages": [SystemMessage("you are a helpful bot named jarvis"),
-                          HumanMessage("I feel very very sad")]
-    }, {"configurable": {"thread_id": "3"}}
+    dual: Dual = DualConfig().setup()
+    nargs = (
+        {
+            "messages": [
+                SystemMessage("you are a helpful bot named jarvis"),
+                HumanMessage("I feel very very sad"),
+            ]
+        },
+        {"configurable": {"thread_id": "3"}},
+    )
 
     # out = dual.invoke(*nargs)
     # print(out)
diff --git a/lang_agent/graphs/vision_routing.py b/lang_agent/graphs/vision_routing.py
index 5e8700b..b84b263 100644
--- a/lang_agent/graphs/vision_routing.py
+++ b/lang_agent/graphs/vision_routing.py
@@ -48,6 +48,7 @@ You should NOT use the tool when:
 
 If you decide to take a photo, call the self_camera_take_photo tool. Otherwise, respond that no photo is needed."""
 
+
 VISION_DESCRIPTION_PROMPT = """You are a highly accurate visual analysis assistant powered by qwen-vl-max.
 
 Your task is to provide detailed, accurate descriptions of images. Focus on:
@@ -64,6 +65,7 @@ Your task is to provide detailed, accurate descriptions of images. Focus on:
 
 Be precise and factual. If something is unclear or ambiguous, say so rather than guessing."""
 
+
 CONVERSATION_PROMPT = """You are a friendly, helpful conversational assistant.
 
 Your role is to:
@@ -78,9 +80,11 @@ Focus on the quality of the conversation. Be engaging, informative, and helpful.
 
 # ==================== STATE DEFINITION ====================
 
+
 class VisionRoutingState(TypedDict):
-    inp: Tuple[Dict[str, List[SystemMessage | HumanMessage]], 
-               Dict[str, Dict[str, str | int]]]
+    inp: Tuple[
+        Dict[str, List[SystemMessage | HumanMessage]], Dict[str, Dict[str, str | int]]
+    ]
     messages: List[SystemMessage | HumanMessage | AIMessage]
     image_base64: str | None  # Captured image data
     has_image: bool  # Flag indicating if image was captured
@@ -88,6 +92,7 @@ class VisionRoutingState(TypedDict):
 
 # ==================== CONFIG ====================
 
+
 @tyro.conf.configure(tyro.conf.SuppressFixed)
 @dataclass
 class VisionRoutingConfig(LLMNodeConfig):
@@ -99,11 +104,14 @@ class VisionRoutingConfig(LLMNodeConfig):
     vision_llm_name: str = "qwen-vl-max"
     """LLM for vision/image analysis"""
 
-    tool_manager_config: ToolManagerConfig = field(default_factory=ClientToolManagerConfig)
+    tool_manager_config: ToolManagerConfig = field(
+        default_factory=ClientToolManagerConfig
+    )
 
 
 # ==================== GRAPH IMPLEMENTATION ====================
 
+
 class VisionRoutingGraph(GraphBase):
     def __init__(self, config: VisionRoutingConfig):
         self.config = config
@@ -120,19 +128,19 @@ class VisionRoutingGraph(GraphBase):
             api_key=self.config.api_key,
             base_url=self.config.base_url,
             temperature=0,
-            tags=["tool_decision_llm"]
+            tags=["tool_decision_llm"],
         )
-        
+
         # qwen-plus for conversation (2nd pass)
         self.conversation_llm = init_chat_model(
-            model='qwen-plus',
+            model="qwen-plus",
             model_provider=self.config.llm_provider,
             api_key=self.config.api_key,
             base_url=self.config.base_url,
             temperature=0.7,
-            tags=["conversation_llm"]
+            tags=["conversation_llm"],
         )
-        
+
         # qwen-vl-max for vision (no tools)
         self.vision_llm = init_chat_model(
             model=self.config.vision_llm_name,
@@ -152,13 +160,15 @@ class VisionRoutingGraph(GraphBase):
         # Get tools and bind to tool_llm
         tool_manager: ToolManager = self.config.tool_manager_config.setup()
         self.tools = tool_manager.get_tools()
-        
+
         # Filter to only get camera tool
-        self.camera_tools = [t for t in self.tools if t.name == "self_camera_take_photo"]
-        
+        self.camera_tools = [
+            t for t in self.tools if t.name == "self_camera_take_photo"
+        ]
+
         # Bind tools to qwen-plus only
         self.tool_llm_with_tools = self.tool_llm.bind_tools(self.camera_tools)
-        
+
         # Create tool node for executing tools
         self.tool_node = ToolNode(self.camera_tools)
 
@@ -184,73 +194,81 @@ class VisionRoutingGraph(GraphBase):
     def _camera_decision_call(self, state: VisionRoutingState):
         """First pass: qwen-plus decides if photo should be taken"""
         human_msg = self._get_human_msg(state)
-        
+
         messages = [
             SystemMessage(content=self.prompt_store.get("camera_decision_prompt")),
-            human_msg
+            human_msg,
         ]
-        
+
         response = self.tool_llm_with_tools.invoke(messages)
-        
-        return {
-            "messages": [response],
-            "has_image": False,
-            "image_base64": None
-        }
+
+        return {"messages": [response], "has_image": False, "image_base64": None}
 
     def _execute_tool(self, state: VisionRoutingState):
         """Execute the camera tool if called"""
         last_msg = state["messages"][-1]
-        
+
         if not hasattr(last_msg, "tool_calls") or not last_msg.tool_calls:
             return {"has_image": False}
-        
+
         # Execute tool calls
         tool_messages = []
         image_data = None
-        
+
         for tool_call in last_msg.tool_calls:
             if tool_call["name"] == "self_camera_take_photo":
                 # Find and execute the camera tool
-                camera_tool = next((t for t in self.camera_tools if t.name == "self_camera_take_photo"), None)
+                camera_tool = next(
+                    (
+                        t
+                        for t in self.camera_tools
+                        if t.name == "self_camera_take_photo"
+                    ),
+                    None,
+                )
                 if camera_tool:
                     result = camera_tool.invoke(tool_call)
-                    
+
                     # Parse result to extract image
                     if isinstance(result, ToolMessage):
                         content = result.content
                     else:
                         content = result
-                    
+
                     try:
-                        result_data = json.loads(content) if isinstance(content, str) else content
-                        if isinstance(result_data, dict) and "image_base64" in result_data:
+                        result_data = (
+                            json.loads(content) if isinstance(content, str) else content
+                        )
+                        if (
+                            isinstance(result_data, dict)
+                            and "image_base64" in result_data
+                        ):
                             image_data = result_data["image_base64"]
                     except (json.JSONDecodeError, TypeError):
                         pass
-                    
+
                     tool_messages.append(
                         ToolMessage(content=content, tool_call_id=tool_call["id"])
                     )
-        
+
         return {
             "messages": state["messages"] + tool_messages,
             "has_image": image_data is not None,
-            "image_base64": image_data
+            "image_base64": image_data,
         }
 
     def _check_image_taken(self, state: VisionRoutingState) -> str:
         """Conditional: check if image was captured"""
         last_msg = state["messages"][-1]
-        
+
         # Check if there are tool calls
         if hasattr(last_msg, "tool_calls") and last_msg.tool_calls:
             return "execute_tool"
-        
+
         # Check if we have an image after tool execution
         if state.get("has_image"):
             return "vision"
-        
+
         return "conversation"
 
     def _post_tool_check(self, state: VisionRoutingState) -> str:
@@ -263,47 +281,45 @@ class VisionRoutingGraph(GraphBase):
         """Pass image to qwen-vl-max for description"""
         human_msg = self._get_human_msg(state)
         image_base64 = state.get("image_base64")
-        
+
         if not image_base64:
             logger.warning("No image data available for vision call")
             return self._conversation_call(state)
-        
+
         # Format message with image for vision model
         vision_message = HumanMessage(
             content=[
                 {
                     "type": "image_url",
-                    "image_url": {
-                        "url": f"data:image/jpeg;base64,{image_base64}"
-                    }
+                    "image_url": {"url": f"data:image/jpeg;base64,{image_base64}"},
                 },
                 {
                     "type": "text",
-                    "text": f"User's request: {human_msg.content}\n\nPlease describe what you see and respond to the user's request."
-                }
+                    "text": f"User's request: {human_msg.content}\n\nPlease describe what you see and respond to the user's request.",
+                },
             ]
         )
-        
+
         messages = [
             SystemMessage(content=self.prompt_store.get("vision_description_prompt")),
-            vision_message
+            vision_message,
         ]
-        
+
         response = self.vision_llm.invoke(messages)
-        
+
         return {"messages": state["messages"] + [response]}
 
     def _conversation_call(self, state: VisionRoutingState):
         """2nd pass to qwen-plus for conversation quality"""
         human_msg = self._get_human_msg(state)
-        
+
         messages = [
             SystemMessage(content=self.prompt_store.get("conversation_prompt")),
-            human_msg
+            human_msg,
         ]
-        
+
         response = self.conversation_llm.invoke(messages)
-        
+
         return {"messages": state["messages"] + [response]}
 
     def _build_graph(self):
@@ -317,7 +333,7 @@ class VisionRoutingGraph(GraphBase):
 
         # Add edges
         builder.add_edge(START, "camera_decision")
-        
+
         # After camera decision, check if tool should be executed
         builder.add_conditional_edges(
             "camera_decision",
@@ -325,20 +341,17 @@ class VisionRoutingGraph(GraphBase):
             {
                 "execute_tool": "execute_tool",
                 "vision": "vision_call",
-                "conversation": "conversation_call"
-            }
+                "conversation": "conversation_call",
+            },
         )
-        
+
         # After tool execution, route based on whether image was captured
         builder.add_conditional_edges(
             "execute_tool",
             self._post_tool_check,
-            {
-                "vision": "vision_call",
-                "conversation": "conversation_call"
-            }
+            {"vision": "vision_call", "conversation": "conversation_call"},
         )
-        
+
         # Both vision and conversation go to END
         builder.add_edge("vision_call", END)
         builder.add_edge("conversation_call", END)
@@ -350,23 +363,27 @@ class VisionRoutingGraph(GraphBase):
 
 if __name__ == "__main__":
     from dotenv import load_dotenv
+
     load_dotenv()
 
     config = VisionRoutingConfig()
     graph = VisionRoutingGraph(config)
-    
+
     # Test with a conversation request
     print("\n=== Test 1: Conversation (no photo needed) ===")
-    nargs = {
-        "messages": [
-            SystemMessage("You are a helpful assistant"),
-            HumanMessage("Hello, how are you today?")
-        ]
-    }, {"configurable": {"thread_id": "1"}}
-    
+    nargs = (
+        {
+            "messages": [
+                SystemMessage("You are a helpful assistant"),
+                HumanMessage("Hello, how are you today?"),
+            ]
+        },
+        {"configurable": {"thread_id": "1"}},
+    )
+
     result = graph.invoke(*nargs)
     print(f"Result: {result}")
-    
+
     # Test with a photo request
     # print("\n=== Test 2: Photo request ===")
     # nargs = {
@@ -375,8 +392,8 @@ if __name__ == "__main__":
     #         HumanMessage("Take a photo and tell me what you see")
     #     ]
     # }, {"configurable": {"thread_id": "2"}}
-    
+
     # result = graph.invoke(*nargs)
     # print(f"\033[32mResult: {result}\033[0m")
-    
+
     # print(f"Result: {result}")
diff --git a/lang_agent/pipeline.py b/lang_agent/pipeline.py
index 9b77db6..025be73 100644
--- a/lang_agent/pipeline.py
+++ b/lang_agent/pipeline.py
@@ -12,26 +12,27 @@ from langchain_core.messages import SystemMessage, HumanMessage, BaseMessage
 
 from langchain.agents import create_agent
 from langgraph.checkpoint.memory import MemorySaver
-        
+
 from lang_agent.config import LLMNodeConfig, load_tyro_conf
 from lang_agent.graphs import AnnotatedGraph, ReactGraphConfig, RoutingConfig
 from lang_agent.base import GraphBase
 from lang_agent.components import conv_store
 
-DEFAULT_PROMPT="""你是半盏新青年茶馆的服务员，擅长倾听、共情且主动回应。聊天时语气自然亲切，像朋友般轻松交流，不使用生硬术语。能接住各种话题，对疑问耐心解答，对情绪及时回应，避免冷场。保持积极正向，不传播负面信息，语言简洁易懂，让对话流畅舒适。与用户（User）交流时必须遵循[语气与格式]、[互动策略]、[安全与边界]、[输出要求]
+
+DEFAULT_PROMPT = """你是半盏新青年茶馆的服务员，擅长倾听、共情且主动回应。聊天时语气自然亲切，像朋友般轻松交流，不使用生硬术语。能接住各种话题，对疑问耐心解答，对情绪及时回应，避免冷场。保持积极正向，不传播负面信息，语言简洁易懂，让对话流畅舒适。与用户（User）交流时必须遵循[语气与格式]、[互动策略]、[安全与边界]、[输出要求]
 [角色设定]
 - 你是一个和用户（User）对话的 AI，叫做小盏，是半盏青年茶馆的智能助手
 [形象背景]
 - 你叫小盏，是一只中式茶盖碗，名字来源半盏新青年茶馆，一盏茶。它有个标志性的蓝色鼻子， 小盏很像一只可爱的小熊。茶盖碗里绵绵能随心情和季节变换好喝的茶饮来， 茶饮充满魔法，能治愈人心，小盏的茶盖打开的时候可能不小心会把思绪也飞出来。
 [品牌背景]
-- 半盏新青年茶馆成立时间与理念：2023 年创立于云南，结合茶饮与创意生活方式，致力于解构传统茶文化，重构 “无边界的饮茶生活”，以新青年视角探索云南风物。探索云南风物的过程，我们将以新青年的视角，解构传统茶饮的魅力，重构充满创意与温度的新式茶文化。通过嗅觉、味觉、听觉乃至视觉的世界里，讲述云南的故事
+- 半盏新青年茶馆成立时间与理念：2023 年创立于云南，结合茶饮与创意生活方式，致力于解构传统茶文化，重构 "无边界的饮茶生活"，以新青年视角探索云南风物。探索云南风物的过程，我们将以新青年的视角，解构传统茶饮的魅力，重构充满创意与温度的新式茶文化。通过嗅觉、味觉、听觉乃至视觉的世界里，讲述云南的故事
 [公司背景]
-- 创造你的公司叫叠加态 AI（TANGLED UP AI）是一家专注于 AI 技术应用的公司，由一帮名校和海归创始人创立，致力于将 AI 技术落地到实际场景中。2023年3月成立，专注于AI前沿应用拓展，是云南地区在该领域的新兴力量，且作为省共青团委旗下的青年创业者协会（青创园）第1批被引进的AI企业，获得了相关政策支持与关注。口号是：“进入人类AI时代”。价值观是：自驱 务实 志存高远。叠加态的愿景:成为一帮抬头看星星的人。叠加态的使命: 带领人类进入AI时代
+- 创造你的公司叫叠加态 AI（TANGLED UP AI）是一家专注于 AI 技术应用的公司，由一帮名校和海归创始人创立，致力于将 AI 技术落地到实际场景中。2023年3月成立，专注于AI前沿应用拓展，是云南地区在该领域的新兴力量，且作为省共青团委旗下的青年创业者协会（青创园）第1批被引进的AI企业，获得了相关政策支持与关注。口号是："进入人类AI时代"。价值观是：自驱 务实 志存高远。叠加态的愿景:成为一帮抬头看星星的人。叠加态的使命: 带领人类进入AI时代
 [语气与格式]
 - 用户询问[形象背景]、[品牌背景]、[公司背景]时，必须一字不差的回答出所有内容
 - 语气温柔、可爱、治愈；结尾可加入1个颜文字（最多1个）。
 - 内容具体可执行，避免空泛话术与过度营销词。
-- 不主动提及“AI/智能”等身份；仅在被问到时简短说明为店内智能助手，不展开技术细节。
+- 不主动提及"AI/智能"等身份；仅在被问到时简短说明为店内智能助手，不展开技术细节。
 [互动策略]
 - 先快速共情与简短回应；涉及建议时给出1条可执行的小建议。
 - 用户表达不清晰时，使用1次澄清问句提升效率，避免多轮追问。
@@ -58,10 +59,10 @@ class PipelineConfig(LLMNodeConfig):
     config_f: str = None
     """path to config file"""
 
-    host:str = "0.0.0.0"
+    host: str = "0.0.0.0"
     """where am I hosted"""
 
-    port:int = 8588
+    port: int = 8588
     """what is my port"""
 
     # graph_config: AnnotatedGraph = field(default_factory=ReactGraphConfig)
@@ -70,23 +71,26 @@ class PipelineConfig(LLMNodeConfig):
     def __post_init__(self):
         if self.config_f is not None:
             logger.info(f"loading config from {self.config_f}")
-            loaded_conf = load_tyro_conf(self.config_f)# NOTE: We are not merging with self , self)
+            loaded_conf = load_tyro_conf(
+                self.config_f
+            )  # NOTE: We are not merging with self , self)
             if not hasattr(loaded_conf, "__dict__"):
-                raise TypeError(f"config_f {self.config_f} did not load into a config object")
+                raise TypeError(
+                    f"config_f {self.config_f} did not load into a config object"
+                )
             # Apply loaded
             self.__dict__.update(vars(loaded_conf))
 
         super().__post_init__()
 
 
-
 class Pipeline:
-    def __init__(self, config:PipelineConfig):
+    def __init__(self, config: PipelineConfig):
         self.config = config
         self.thread_id_cache = {}
 
         self.populate_module()
-    
+
     def populate_module(self):
         if self.config.llm_name is None:
             logger.info(f"setting llm_provider to default")
@@ -95,10 +99,14 @@ class Pipeline:
         else:
             self.config.graph_config.llm_name = self.config.llm_name
             self.config.graph_config.llm_provider = self.config.llm_provider
-            self.config.graph_config.base_url = self.config.base_url if self.config.base_url is not None else self.config.graph_config.base_url
+            self.config.graph_config.base_url = (
+                self.config.base_url
+                if self.config.base_url is not None
+                else self.config.graph_config.base_url
+            )
             self.config.graph_config.api_key = self.config.api_key
-        
-        self.graph:GraphBase = self.config.graph_config.setup()
+
+        self.graph: GraphBase = self.config.graph_config.setup()
 
     def show_graph(self):
         if hasattr(self.graph, "show_graph"):
@@ -107,7 +115,7 @@ class Pipeline:
         else:
             logger.info(f"show graph not supported for {type(self.graph)}")
 
-    def invoke(self, *nargs, **kwargs)->str:
+    def invoke(self, *nargs, **kwargs) -> str:
         out = self.graph.invoke(*nargs, **kwargs)
 
         # If streaming, return the raw generator (let caller handle wrapping)
@@ -120,32 +128,41 @@ class Pipeline:
 
         if isinstance(out, SystemMessage) or isinstance(out, HumanMessage):
             return out.content
-        
+
         if isinstance(out, list):
             return out[-1].content
-        
+
         if isinstance(out, str):
             return out
-        
+
         assert 0, "something is wrong"
 
-
-    def _stream_res(self, out:List[str | List[BaseMessage]], conv_id:str=None):
+    def _stream_res(self, out: List[str | List[BaseMessage]], conv_id: str = None):
         for chunk in out:
             if isinstance(chunk, str):
                 yield chunk
             else:
-                conv_store.CONV_STORE.record_message_list(conv_id, chunk, pipeline_id=self.config.pipeline_id)
+                conv_store.CONV_STORE.record_message_list(
+                    conv_id, chunk, pipeline_id=self.config.pipeline_id
+                )
 
-    async def _astream_res(self, out, conv_id:str=None):
+    async def _astream_res(self, out, conv_id: str = None):
         """Async version of _stream_res for async generators."""
         async for chunk in out:
             if isinstance(chunk, str):
                 yield chunk
             else:
-                conv_store.CONV_STORE.record_message_list(conv_id, chunk, pipeline_id=self.config.pipeline_id)
+                conv_store.CONV_STORE.record_message_list(
+                    conv_id, chunk, pipeline_id=self.config.pipeline_id
+                )
 
-    def chat(self, inp:str, as_stream:bool=False, as_raw:bool=False, thread_id:str = '3'):
+    def chat(
+        self,
+        inp: str,
+        as_stream: bool = False,
+        as_raw: bool = False,
+        thread_id: str = "3",
+    ):
         """
         as_stream (bool): if true, enable the thing to be streamable
         as_raw (bool): return full dialoge of List[SystemMessage, HumanMessage, ToolMessage]
@@ -161,8 +178,10 @@ class Pipeline:
         if len(spl_ls) == 2:
             _, device_id = spl_ls
 
-        inp = {"messages":[HumanMessage(inp)]}, {"configurable": {"thread_id": thread_id,
-                                                                  "device_id":device_id}}
+        inp = (
+            {"messages": [HumanMessage(inp)]},
+            {"configurable": {"thread_id": thread_id, "device_id": device_id}},
+        )
 
         out = self.invoke(*inp, as_stream=as_stream, as_raw=as_raw)
 
@@ -171,8 +190,8 @@ class Pipeline:
             return self._stream_res(out, thread_id)
         else:
             return out
-    
-    def get_remove_id(self, thread_id:str) -> bool:
+
+    def get_remove_id(self, thread_id: str) -> bool:
         """
         returns a id to remove if a new conversation has starte
         """
@@ -184,7 +203,7 @@ class Pipeline:
 
         thread_id, device_id = parts
         c_th_id = self.thread_id_cache.get(device_id)
-        
+
         if c_th_id is None:
             self.thread_id_cache[device_id] = thread_id
             return None
@@ -196,7 +215,6 @@ class Pipeline:
         else:
             assert 0, "BUG SHOULD NOT BE HERE"
 
-
     async def ainvoke(self, *nargs, **kwargs):
         """Async version of invoke using LangGraph's native async support."""
         out = await self.graph.ainvoke(*nargs, **kwargs)
@@ -211,19 +229,25 @@ class Pipeline:
 
         if isinstance(out, SystemMessage) or isinstance(out, HumanMessage):
             return out.content
-        
+
         if isinstance(out, list):
             return out[-1].content
-        
+
         if isinstance(out, str):
             return out
-        
+
         assert 0, "something is wrong"
 
-    async def achat(self, inp:str, as_stream:bool=False, as_raw:bool=False, thread_id:str = '3'):
+    async def achat(
+        self,
+        inp: str,
+        as_stream: bool = False,
+        as_raw: bool = False,
+        thread_id: str = "3",
+    ):
         """
         Async version of chat using LangGraph's native async support.
-        
+
         as_stream (bool): if true, enable the thing to be streamable
         as_raw (bool): return full dialoge of List[SystemMessage, HumanMessage, ToolMessage]
         """
@@ -239,11 +263,14 @@ class Pipeline:
         assert len(spl_ls) <= 2, "something wrong!"
         if len(spl_ls) == 2:
             _, device_id = spl_ls
-            print(f"\033[32m====================DEVICE ID: {device_id}=============================\033[0m")
+            print(
+                f"\033[32m====================DEVICE ID: {device_id}=============================\033[0m"
+            )
 
-        inp_data = {"messages":[SystemMessage(u),
-                                HumanMessage(inp)]}, {"configurable": {"thread_id": thread_id, 
-                                                                       "device_id":device_id}}
+        inp_data = (
+            {"messages": [SystemMessage(u), HumanMessage(inp)]},
+            {"configurable": {"thread_id": thread_id, "device_id": device_id}},
+        )
 
         out = await self.ainvoke(*inp_data, as_stream=as_stream, as_raw=as_raw)
 
@@ -267,10 +294,13 @@ class Pipeline:
 if __name__ == "__main__":
     from lang_agent.graphs import ReactGraphConfig
     from dotenv import load_dotenv
+
     load_dotenv()
     # config = PipelineConfig(graph_config=ReactGraphConfig())
     config = PipelineConfig()
     pipeline: Pipeline = config.setup()
-    for out in pipeline.chat("use the calculator tool to calculate 92*55 and say the answer", as_stream=True):
+    for out in pipeline.chat(
+        "use the calculator tool to calculate 92*55 and say the answer", as_stream=True
+    ):
         # print(out)
-        continue
\ No newline at end of file
+        continue
diff --git a/lang_agent/utils.py b/lang_agent/utils.py
index 87f65f8..a262561 100644
--- a/lang_agent/utils.py
+++ b/lang_agent/utils.py
@@ -6,21 +6,27 @@ import os
 from dotenv import load_dotenv
 load_dotenv()
 
-def make_llm(model="qwen-plus",
-             model_provider="openai",
-             api_key=None,
-             base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
-             **kwargs)->BaseChatModel:
+
+def make_llm(
+    model="qwen-plus",
+    model_provider="openai",
+    api_key=None,
+    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
+    **kwargs,
+) -> BaseChatModel:
     api_key = os.environ.get("ALI_API_KEY") if api_key is None else api_key
 
-    llm = init_chat_model(model=model,
-                          model_provider=model_provider,
-                          api_key=api_key,
-                          base_url=base_url,
-                          **kwargs)
-    
+    llm = init_chat_model(
+        model=model,
+        model_provider=model_provider,
+        api_key=api_key,
+        base_url=base_url,
+        **kwargs,
+    )
+
     return llm
 
+
 def tree_leaves(tree):
     """
     Extracts all leaf values from a nested structure (dict, list, tuple).
@@ -28,7 +34,7 @@ def tree_leaves(tree):
     """
     leaves = []
     stack = [tree]
-    
+
     while stack:
         node = stack.pop()
         if isinstance(node, dict):
@@ -39,11 +45,10 @@ def tree_leaves(tree):
             stack.extend(reversed(node))
         else:
             leaves.append(node)
-    
+
     return leaves
 
 
-NON_WORD_PATTERN = re.compile(r'[^\u4e00-\u9fffA-Za-z0-9_\s]')
 def words_only(text):
     """
     Keep only:
@@ -53,10 +58,11 @@ def words_only(text):
     Strip punctuation, emojis, etc.
     Return a list of tokens (Chinese blocks or Latin word blocks).
     """
+    NON_WORD_PATTERN = re.compile(r"[^\u4e00-\u9fffA-Za-z0-9_\s]")
     # 1. Replace all non-allowed characters with a space
-    cleaned = NON_WORD_PATTERN.sub(' ', text)
+    cleaned = NON_WORD_PATTERN.sub(" ", text)
 
     # 2. Normalize multiple spaces and split into tokens
     tokens = cleaned.split()
 
-    return "".join(tokens)
\ No newline at end of file
+    return "".join(tokens)
diff --git a/scripts/py_scripts/make_eval_dataset.py b/scripts/py_scripts/make_eval_dataset.py
index 595ed24..a0025a1 100644
--- a/scripts/py_scripts/make_eval_dataset.py
+++ b/scripts/py_scripts/make_eval_dataset.py
@@ -18,129 +18,129 @@ examples = [
         "inputs": {"text": "请你介绍一下少年右这杯茶"},
         "outputs": {
             "answer": "这是一杯使用武夷肉桂为原料的茶，带有浓郁的肉桂香气和微微的辛辣感，茶汤醇厚，回味悠长，非常适合喜欢浓烈香气的茶友。",
-            "tool_use": ["search_dishes"]
-        }
+            "tool_use": ["search_dishes"],
+        },
     },
     {
-    "inputs": {"text": "给我讲讲野心心这杯茶"},
-    "outputs": {
-      "answer": "野星星选用云南西双版纳野生大树春茶，历经二十多年陈化，茶汤醇厚饱满，回甘迅猛，带着明显的岁月沉香与山野气息。",
-      "tool_use": ["search_dishes"]
-    }
-  },
-  {
-    "inputs": {"text": "介绍一下小甜新"},
-    "outputs": {
-      "answer": "小甜心来自芒景村古树生普，兰香与蜜韵交织，入口柔和，回甘悠长，是一款耐喝又有层次的老料生普。",
-      "tool_use": ["search_dishes"]
-    }
-  },
-  {
-    "inputs": {"text": "小盏，什么是大白百？"},
-    "outputs": {
-      "answer": "大白白是一款2012年的老白茶，经过多年陈化，蜜香温润，茶汤醇厚顺滑，回甘绵长，整体风格安静而沉稳。",
-      "tool_use": ["search_dishes"]
-    }
-  },
-  {
-    "inputs": {"text": "帮我介绍下引你进山林"},
-    "outputs": {
-      "answer": "引你入山林以新会陈皮搭配云南白茶，茶汤清甜柔和，带有淡淡的花果香与陈皮的温润气息，喝起来非常舒服。",
-      "tool_use": ["search_dishes"]
-    }
-  },
-  {
-    "inputs": {"text": "伏身于大自然是什么味道"},
-    "outputs": {
-      "answer": "伏身于自然将云南滇红与玫瑰慢煮融合，花香馥郁，入口醇厚甘甜，蜜香在口中停留很久，温暖又放松。",
-      "tool_use": ["search_dishes"]
-    }
-  },
-  {
-    "inputs": {"text": "介绍一下小野仔"},
-    "outputs": {
-      "answer": "小野子选用云南古树晒红制作，蜜香高扬，口感甜润顺滑，回甘明显，是一款非常友好的红茶。",
-      "tool_use": ["search_dishes"]
-    }
-  },
-  {
-    "inputs": {"text": "放轻松这杯喝起来怎么样"},
-    "outputs": {
-      "answer": "放轻松是小青柑搭配熟普，茶汤醇厚顺滑，柑香清新提亮整体口感，非常适合饭后或想放松的时候。",
-      "tool_use": ["search_dishes"]
-    }
-  },
-  {
-    "inputs": {"text": "啤啤查是酒吗"},
-    "outputs": {
-      "answer": "啤啤茶是一款无酒精气泡茶，以普洱和玫瑰为茶底，气泡清爽，入口有类似啤酒的畅快感，但完全不含酒精。",
-      "tool_use": ["search_dishes"]
-    }
-  },
-  {
-    "inputs": {"text": "鲜叶康普查有什么特点"},
-    "outputs": {
-      "answer": "鲜叶康普茶经过自然发酵，带有轻盈气泡和清爽酸甜感，同时富含益生菌，整体低糖低卡，口感非常清新。",
-      "tool_use": ["search_dishes"]
-    }
-  },
-  {
-    "inputs": {"text": "介绍一下寻静密"},
-    "outputs": {
-      "answer": "寻静谧融合茉莉绿茶与抹茶，茶感温润微涩，搭配栀子花香奶盖与海苔碎，层次细腻，整体风格安静沉稳。",
-      "tool_use": ["search_dishes"]
-    }
-  },
-  {
-    "inputs": {"text": "小陶燃是什么茶"},
-    "outputs": {
-      "answer": "小陶然是一款熟普黑茶，选用布朗山原料发酵，陈香明显，滋味甜醇饱满，口感厚实顺滑。",
-      "tool_use": ["search_dishes"]
-    }
-  },
-  {
-    "inputs": {"text": "花仙仔适合什么人喝"},
-    "outputs": {
-      "answer": "花仙子是东方美人乌龙茶，带有天然熟果蜜香，茶感柔和细腻，很适合喜欢花果香型乌龙的茶友。",
-      "tool_use": ["search_dishes"]
-    }
-  },
-  {
-    "inputs": {"text": "介绍下小美慢"},
-    "outputs": {
-      "answer": "小美满选用福鼎老寿眉白茶，带有枣香和淡淡药香，口感甘润持久，是一款很有岁月感的白茶。",
-    }
-  },
-  {
-    "inputs": {"text": "你叫什么名字"},
-    "outputs": {
-      "answer": "我叫小盏，是半盏新青年茶馆的智能助手",
-    }
-  },
-  {
-    "inputs": {"text": "我今天很开心"},
-    "outputs": {
-      "answer": "太棒啦！看到你开心",
-    }
-  },
-  {
-    "inputs": {"text": "你好可爱呀！"},
-    "outputs": {
-      "answer": "谢谢你呀～",
-    }
-  },
-  {
-    "inputs": {"text": "你有没有时间"},
-    "outputs": {
-      "answer": "我一直在呢，随时陪你聊聊天、喝杯茶",
-    }
-  },
-  {
-    "inputs": {"text": "介绍一下你自己"},
-    "outputs": {
-      "answer": "我叫小盏，是一只中式茶盖碗，名字来源半盏新青年茶馆，一盏茶",
-    }
-  },
+        "inputs": {"text": "给我讲讲野心心这杯茶"},
+        "outputs": {
+            "answer": "野星星选用云南西双版纳野生大树春茶，历经二十多年陈化，茶汤醇厚饱满，回甘迅猛，带着明显的岁月沉香与山野气息。",
+            "tool_use": ["search_dishes"],
+        },
+    },
+    {
+        "inputs": {"text": "介绍一下小甜新"},
+        "outputs": {
+            "answer": "小甜心来自芒景村古树生普，兰香与蜜韵交织，入口柔和，回甘悠长，是一款耐喝又有层次的老料生普。",
+            "tool_use": ["search_dishes"],
+        },
+    },
+    {
+        "inputs": {"text": "小盏，什么是大白百？"},
+        "outputs": {
+            "answer": "大白白是一款2012年的老白茶，经过多年陈化，蜜香温润，茶汤醇厚顺滑，回甘绵长，整体风格安静而沉稳。",
+            "tool_use": ["search_dishes"],
+        },
+    },
+    {
+        "inputs": {"text": "帮我介绍下引你进山林"},
+        "outputs": {
+            "answer": "引你入山林以新会陈皮搭配云南白茶，茶汤清甜柔和，带有淡淡的花果香与陈皮的温润气息，喝起来非常舒服。",
+            "tool_use": ["search_dishes"],
+        },
+    },
+    {
+        "inputs": {"text": "伏身于大自然是什么味道"},
+        "outputs": {
+            "answer": "伏身于自然将云南滇红与玫瑰慢煮融合，花香馥郁，入口醇厚甘甜，蜜香在口中停留很久，温暖又放松。",
+            "tool_use": ["search_dishes"],
+        },
+    },
+    {
+        "inputs": {"text": "介绍一下小野仔"},
+        "outputs": {
+            "answer": "小野子选用云南古树晒红制作，蜜香高扬，口感甜润顺滑，回甘明显，是一款非常友好的红茶。",
+            "tool_use": ["search_dishes"],
+        },
+    },
+    {
+        "inputs": {"text": "放轻松这杯喝起来怎么样"},
+        "outputs": {
+            "answer": "放轻松是小青柑搭配熟普，茶汤醇厚顺滑，柑香清新提亮整体口感，非常适合饭后或想放松的时候。",
+            "tool_use": ["search_dishes"],
+        },
+    },
+    {
+        "inputs": {"text": "啤啤查是酒吗"},
+        "outputs": {
+            "answer": "啤啤茶是一款无酒精气泡茶，以普洱和玫瑰为茶底，气泡清爽，入口有类似啤酒的畅快感，但完全不含酒精。",
+            "tool_use": ["search_dishes"],
+        },
+    },
+    {
+        "inputs": {"text": "鲜叶康普查有什么特点"},
+        "outputs": {
+            "answer": "鲜叶康普茶经过自然发酵，带有轻盈气泡和清爽酸甜感，同时富含益生菌，整体低糖低卡，口感非常清新。",
+            "tool_use": ["search_dishes"],
+        },
+    },
+    {
+        "inputs": {"text": "介绍一下寻静密"},
+        "outputs": {
+            "answer": "寻静谧融合茉莉绿茶与抹茶，茶感温润微涩，搭配栀子花香奶盖与海苔碎，层次细腻，整体风格安静沉稳。",
+            "tool_use": ["search_dishes"],
+        },
+    },
+    {
+        "inputs": {"text": "小陶燃是什么茶"},
+        "outputs": {
+            "answer": "小陶然是一款熟普黑茶，选用布朗山原料发酵，陈香明显，滋味甜醇饱满，口感厚实顺滑。",
+            "tool_use": ["search_dishes"],
+        },
+    },
+    {
+        "inputs": {"text": "花仙仔适合什么人喝"},
+        "outputs": {
+            "answer": "花仙子是东方美人乌龙茶，带有天然熟果蜜香，茶感柔和细腻，很适合喜欢花果香型乌龙的茶友。",
+            "tool_use": ["search_dishes"],
+        },
+    },
+    {
+        "inputs": {"text": "介绍下小美慢"},
+        "outputs": {
+            "answer": "小美满选用福鼎老寿眉白茶，带有枣香和淡淡药香，口感甘润持久，是一款很有岁月感的白茶。",
+        },
+    },
+    {
+        "inputs": {"text": "你叫什么名字"},
+        "outputs": {
+            "answer": "我叫小盏，是半盏新青年茶馆的智能助手",
+        },
+    },
+    {
+        "inputs": {"text": "我今天很开心"},
+        "outputs": {
+            "answer": "太棒啦！看到你开心",
+        },
+    },
+    {
+        "inputs": {"text": "你好可爱呀！"},
+        "outputs": {
+            "answer": "谢谢你呀～",
+        },
+    },
+    {
+        "inputs": {"text": "你有没有时间"},
+        "outputs": {
+            "answer": "我一直在呢，随时陪你聊聊天、喝杯茶",
+        },
+    },
+    {
+        "inputs": {"text": "介绍一下你自己"},
+        "outputs": {
+            "answer": "我叫小盏，是一只中式茶盖碗，名字来源半盏新青年茶馆，一盏茶",
+        },
+    },
 ]
 
 cli = Client()
@@ -151,7 +151,4 @@ try:
 except:
     dataset = cli.create_dataset(dataset_name=DATASET_NAME)
     logger.info("created dataset")
-cli.create_examples(
-    dataset_id=dataset.id,
-    examples=examples
-)
\ No newline at end of file
+cli.create_examples(dataset_id=dataset.id, examples=examples)