changed llm

agent.py

@@ -23,6 +23,7 @@ from langgraph.prebuilt import ToolNode, tools_condition
 # load environment variables
 load_dotenv()
 HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+print(f"DEBUG: HUGGINGFACEHUB_API_TOKEN = {HUGGINGFACEHUB_API_TOKEN}")
 
 
 # maths tool
@@ -150,24 +151,35 @@ tools = [
 def build_graph():
     # llm
     llm = HuggingFaceEndpoint(
-        repo_id = "microsoft/Phi-4-reasoning-plus",
+        repo_id="deepseek-ai/DeepSeek-R1",
         huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN,
     )
+    print(f"DEBUG: llm object = {llm}")
 
     chat = ChatHuggingFace(llm=llm, verbose=False)
+    print(f"DEBUG: chat object = {chat}")
 
     # bind tools to llm
     chat_with_tools = chat.bind_tools(tools)
+    print(f"DEBUG: chat_with_tools object = {chat_with_tools}")
 
     # generate AgentState and Agent graph
     class AgentState(TypedDict):
         messages: Annotated[list[AnyMessage], add_messages]
 
     def assistant(state: AgentState):
+        result = chat_with_tools.invoke(state["messages"])
+        # Ensure the result is always wrapped in a list, even if invoke returns a single message
+        # Add usage information if it's not already present
+        if isinstance(result, AIMessage) and result.usage_metadata is None:
+             # Add dummy usage metadata if none exists
+            result.usage_metadata = {"input_tokens": 0, "output_tokens": 0, "total_tokens": 0}
+
         return {
-            "messages": [chat_with_tools.invoke(state["messages"])],
+            "messages": [result]
         }
 
+
     # build graph
     builder = StateGraph(AgentState)
 
@@ -188,3 +200,14 @@ def build_graph():
         }
     )
     builder.add_edge("tools", "assistant")
+
+    return builder.compile()
+
+
+if __name__ == "__main__":
+    question = "When was a picture of St. Thomas Aquinas first added to the Wikipedia page on the Principle of double effect?"
+    graph = build_graph()
+    messages = [HumanMessage(content=question)]
+    messages = graph.invoke({"messages": messages})
+    for m in messages["messages"]:
+        m.pretty_print()