add: main.py

main.py

@@ -1,22 +1,16 @@
-"""
-# main.py
-# Implementation of the LangGraph reflective agent using deepagents
-# Author: Auto-generated for the assignment
-# Requires: deepagents, langchain-openai, langgraph, langchain
-"""
 import os
 import asyncio
 from typing import TypedDict, Annotated
 
 from langchain_openai import ChatOpenAI
-from langchain_core.messages import HumanMessage, SystemMessage
+from langchain_core.messages import HumanMessage
 from langchain.tools import tool
 from deepagents import create_deep_agent
-from deepagents.backends import CompositeBackend, LocalShellBackend, FilesystemBackend
+from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
 from langgraph.graph import StateGraph, START, END
 from langgraph.graph.message import add_messages
 
-# ---------- LLM configuration (OpenRouter) ----------
+# ---------- LLM ----------
 llm = ChatOpenAI(
     model="openai/gpt-oss-20b:free",
     base_url="https://openrouter.ai/api/v1",
@@ -24,130 +18,107 @@ llm = ChatOpenAI(
     temperature=0.0,
 )
 
-# ---------- State definition ----------
+# ---------- Backend for deepagents ----------
-class ReflectState(TypedDict):
-    question: str
-    draft: str
-    critique: str
-    verdict: str  # "ok" | "needs_revision"
-    round: int
-    max_rounds: int
-
-# ---------- Node implementations ----------
-async def draft_answer(state: ReflectState) -> ReflectState:
-    """Generate an initial draft answer (5–10 sentences)."""
-    prompt = (
-        "You are an expert tutor. Answer the following question in 5–10 concise sentences. "
-        "Avoid filler and keep it clear.
-"
-        f"Question: {state['question']}"
-    )
-    response = await llm.ainvoke([SystemMessage(content="You are a helpful tutor."), HumanMessage(content=prompt)])
-    state["draft"] = response.content.strip()
-    state["round"] = 1
-    return state
-
-async def reflect(state: ReflectState) -> ReflectState:
-    """Critique the draft and decide if revision is needed."""
-    prompt = (
-        "You are a critical reviewer. Evaluate the following answer for completeness, specificity, and lack of filler. "
-        "Respond with a verdict of either "ok" or "needs_revision", followed by 2–3 bullet points of constructive feedback.
-"
-        f"Answer draft:\n{state['draft']}"
-    )
-    response = await llm.ainvoke([SystemMessage(content="You are a critical reviewer."), HumanMessage(content=prompt)])
-    text = response.content.strip()
-    # Parse verdict and critique
-    if "needs_revision" in text.lower():
-        verdict = "needs_revision"
-    else:
-        verdict = "ok"
-    # Extract critique lines after the verdict
-    lines = text.splitlines()
-    critique_lines = [line for line in lines if line.strip() and line.strip().lower() not in {"ok", "needs_revision"}]
-    critique = "\n".join(critique_lines).strip()
-    state["critique"] = critique
-    state["verdict"] = verdict
-    return state
-
-async def rewrite(state: ReflectState) -> ReflectState:
-    """Rewrite the draft incorporating the critique."""
-    prompt = (
-        "You are revising an answer based on the following critique. Produce a new version that addresses the points and remains 5–10 sentences.
-"
-        f"Original draft:\n{state['draft']}\n\nCritique:\n{state['critique']}"
-    )
-    response = await llm.ainvoke([SystemMessage(content="You are a revising tutor."), HumanMessage(content=prompt)])
-    state["draft"] = response.content.strip()
-    state["round"] += 1
-    return state
-
-# ---------- Graph construction ----------
-def build_graph() -> StateGraph[ReflectState]:
-    graph = StateGraph(ReflectState)
-    graph.add_node("draft_answer", draft_answer)
-    graph.add_node("reflect", reflect)
-    graph.add_node("rewrite", rewrite)
-
-    # Entry point
-    graph.set_entry_point("draft_answer")
-
-    # Transitions
-    graph.add_conditional_edges(
-        "draft_answer",
-        lambda _: "reflect",
-    )
-    graph.add_conditional_edges(
-        "reflect",
-        lambda state: "END" if state["verdict"] == "ok" else "rewrite",
-    )
-    graph.add_conditional_edges(
-        "rewrite",
-        lambda state: "END" if state["round"] > state["max_rounds"] else "reflect",
-    )
-
-    return graph
-
-# ---------- Tool that runs the graph ----------
-@tool
-async def answer_question(query: str) -> str:
-    """Run the reflective LangGraph to answer a question."""
-    graph = build_graph()
-    # Initialize state
-    state: ReflectState = {
-        "question": query,
-        "draft": "",
-        "critique": "",
-        "verdict": "",
-        "round": 0,
-        "max_rounds": 2,
-    }
-    # Run graph
-    final_state = await graph.ainvoke(state)
-    return final_state["draft"]
-
-# ---------- DeepAgent setup ----------
 backend = CompositeBackend([
     LocalShellBackend(workspace_dir="./workspace"),
     FilesystemBackend(),
 ])
 
+# ---------- State definition ----------
+class ReflectState(TypedDict):
+    question: str
+    draft: str
+    critique: str
+    verdict: str  # ok | needs_revision
+    round: int
+    max_rounds: int
+
+# ---------- LangGraph nodes ----------
+async def draft_answer(state: ReflectState) -> ReflectState:
+    prompt = f"Write a concise answer (5–10 sentences) to the following question:\n\n{state['question']}"
+    response = await llm.ainvoke([HumanMessage(content=prompt)])
+    state["draft"] = response.content.strip()
+    return state
+
+async def reflect(state: ReflectState) -> ReflectState:
+    prompt = (
+        "You are a critic. Evaluate the draft answer for completeness, specificity, and lack of filler.\n"
+        "Return a verdict ('ok' or 'needs_revision') and 2–3 bullet points of critique.\n"
+        f"Draft: {state['draft']}"
+    )
+    response = await llm.ainvoke([HumanMessage(content=prompt)])
+    # Simple parsing: first line verdict, rest critique
+    lines = response.content.strip().splitlines()
+    verdict = lines[0].strip().lower()
+    critique = "\n".join(lines[1:]).strip()
+    state["verdict"] = verdict
+    state["critique"] = critique
+    return state
+
+async def rewrite(state: ReflectState) -> ReflectState:
+    prompt = (
+        "Rewrite the draft answer incorporating the following critique. Keep the answer concise (5–10 sentences).\n"
+        f"Critique: {state['critique']}\n"
+        f"Original draft: {state['draft']}"
+    )
+    response = await llm.ainvoke([HumanMessage(content=prompt)])
+    state["draft"] = response.content.strip()
+    state["round"] += 1
+    return state
+
+# ---------- Graph construction ----------
+graph = StateGraph(ReflectState)
+graph.add_node("draft_answer", draft_answer)
+graph.add_node("reflect", reflect)
+graph.add_node("rewrite", rewrite)
+
+# Entry point
+graph.set_entry_point("draft_answer")
+
+# Transitions
+graph.add_edge("draft_answer", "reflect")
+# From reflect: if ok -> END, else if needs_revision and round < max_rounds -> rewrite
+graph.add_conditional_edges(
+    "reflect",
+    lambda state: (
+        "END" if state["verdict"] == "ok" else (
+            "rewrite" if state["round"] < state["max_rounds"] else "END"
+        )
+    ),
+)
+graph.add_edge("rewrite", "reflect")
+
+app = graph.compile()
+
+# ---------- DeepAgent wrapper ----------
+@tool
+def run_graph(question: str, max_rounds: int = 2) -> str:
+    """Run the reflection graph for a given question."""
+    initial_state: ReflectState = {
+        "question": question,
+        "draft": "",
+        "critique": "",
+        "verdict": "",
+        "round": 0,
+        "max_rounds": max_rounds,
+    }
+    result = app.invoke(initial_state)
+    return result["draft"]
+
 agent = create_deep_agent(
     model=llm,
-    tools=[answer_question],
+    tools=[run_graph],
     backend=backend,
-    system_prompt="You are a helpful educational agent. Use the provided tools to answer questions.",
+    system_prompt="You are an assistant that can generate and improve answers using reflection. Use the provided tool to get a refined answer.",
 )
 
-# ---------- CLI entry point ----------
 async def main():
     question = "Объясни студенту разницу между tool и resource в MCP"
-    result = await agent.ainvoke(
+    response = await agent.ainvoke(
         {"messages": [HumanMessage(content=question)]},
         {"configurable": {"thread_id": "session-1"}},
     )
-    # The tool returns the final answer as the last message content
+    print("Final answer:\n", response["messages"][-1].content)
-    print("\nFinal answer:\n", result["messages"][-1].content)
 
 if __name__ == "__main__":
     asyncio.run(main())