add main.py

main.py

@@ -1,16 +1,22 @@
+"""
+# 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
+from langchain_core.messages import HumanMessage, SystemMessage
 from langchain.tools import tool
 from deepagents import create_deep_agent
-from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
+from deepagents.backends import CompositeBackend, LocalShellBackend, FilesystemBackend
 from langgraph.graph import StateGraph, START, END
 from langgraph.graph.message import add_messages
 
-# ---------- LLM ----------
+# ---------- LLM configuration (OpenRouter) ----------
 llm = ChatOpenAI(
     model="openai/gpt-oss-20b:free",
     base_url="https://openrouter.ai/api/v1",
@@ -18,108 +24,130 @@ llm = ChatOpenAI(
     temperature=0.0,
 )
 
-# ---------- Backend ----------
+# ---------- State definition ----------
-backend = CompositeBackend([
-    LocalShellBackend(workspace_dir="./workspace"),
-    FilesystemBackend(),
-])
-
-# ---------- State ----------
 class ReflectState(TypedDict):
     question: str
     draft: str
     critique: str
-    verdict: str  # ok | needs_revision
+    verdict: str  # "ok" | "needs_revision"
     round: int
     max_rounds: int
 
-# ---------- Nodes ----------
+# ---------- Node implementations ----------
 async def draft_answer(state: ReflectState) -> ReflectState:
-    prompt = f"Write a concise answer (5–10 sentences) to the following question: {state['question']}"
+    """Generate an initial draft answer (5–10 sentences)."""
-    response = await llm.ainvoke([HumanMessage(content=prompt)])
+    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"] = 0
+    state["round"] = 1
-    state["max_rounds"] = state.get("max_rounds", 2)
     return state
 
 async def reflect(state: ReflectState) -> ReflectState:
+    """Critique the draft and decide if revision is needed."""
     prompt = (
-        "You are a critic. Evaluate the following draft answer for completeness, specificity, and lack of filler.\n"
+        "You are a critical reviewer. Evaluate the following answer for completeness, specificity, and lack of filler. "
-        f"Draft: {state['draft']}\n"
+        "Respond with a verdict of either "ok" or "needs_revision", followed by 2–3 bullet points of constructive feedback.
-        "Return a JSON object with fields: verdict (ok or needs_revision) and critique (2–3 bullet points)."
+"
+        f"Answer draft:\n{state['draft']}"
     )
-    response = await llm.ainvoke([HumanMessage(content=prompt)])
+    response = await llm.ainvoke([SystemMessage(content="You are a critical reviewer."), HumanMessage(content=prompt)])
-    # Simple extraction of JSON
+    text = response.content.strip()
-    import json, re
+    # Parse verdict and critique
-    try:
+    if "needs_revision" in text.lower():
-        data = json.loads(re.search(r"\{.*\}", response.content, re.S).group(0))
+        verdict = "needs_revision"
-    except Exception:
+    else:
-        data = {"verdict": "needs_revision", "critique": "Could not parse critique."}
+        verdict = "ok"
-    state["critique"] = data.get("critique", "")
+    # Extract critique lines after the verdict
-    state["verdict"] = data.get("verdict", "needs_revision")
+    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 = (
-        "Rewrite the draft answer incorporating the following critique. Keep the answer concise (5–10 sentences).\n"
+        "You are revising an answer based on the following critique. Produce a new version that addresses the points and remains 5–10 sentences.
-        f"Critique: {state['critique']}\n"
+"
-        f"Original draft: {state['draft']}"
+        f"Original draft:\n{state['draft']}\n\nCritique:\n{state['critique']}"
     )
-    response = await llm.ainvoke([HumanMessage(content=prompt)])
+    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 ----------
+# ---------- Graph construction ----------
-graph = StateGraph(ReflectState)
+def build_graph() -> StateGraph[ReflectState]:
-graph.add_node("draft_answer", draft_answer)
+    graph = StateGraph(ReflectState)
-graph.add_node("reflect", reflect)
+    graph.add_node("draft_answer", draft_answer)
-graph.add_node("rewrite", rewrite)
+    graph.add_node("reflect", reflect)
+    graph.add_node("rewrite", rewrite)
 
-# Entry point
+    # Entry point
-graph.set_entry_point("draft_answer")
+    graph.set_entry_point("draft_answer")
 
-# Transitions
+    # Transitions
-graph.add_edge("draft_answer", "reflect")
+    graph.add_conditional_edges(
-# If ok -> END
+        "draft_answer",
-graph.add_conditional_edges(
+        lambda _: "reflect",
-    "reflect",
+    )
-    lambda state: "rewrite" if state["verdict"] == "needs_revision" and state["round"] < state["max_rounds"] else "END",
+    graph.add_conditional_edges(
-)
+        "reflect",
-# rewrite -> reflect
+        lambda state: "END" if state["verdict"] == "ok" else "rewrite",
-graph.add_edge("rewrite", "reflect")
+    )
+    graph.add_conditional_edges(
+        "rewrite",
+        lambda state: "END" if state["round"] > state["max_rounds"] else "reflect",
+    )
 
-app = graph.compile()
+    return graph
 
-# ---------- DeepAgent wrapper ----------
+# ---------- Tool that runs the graph ----------
 @tool
-def run_graph(question: str) -> str:
+async def answer_question(query: str) -> str:
-    """Run the reflection graph for a given question."""
+    """Run the reflective LangGraph to answer a question."""
+    graph = build_graph()
+    # Initialize state
     state: ReflectState = {
-        "question": question,
+        "question": query,
         "draft": "",
         "critique": "",
         "verdict": "",
         "round": 0,
         "max_rounds": 2,
     }
-    result = app.invoke(state)
+    # Run graph
-    return result["draft"]
+    final_state = await graph.ainvoke(state)
+    return final_state["draft"]
+
+# ---------- DeepAgent setup ----------
+backend = CompositeBackend([
+    LocalShellBackend(workspace_dir="./workspace"),
+    FilesystemBackend(),
+])
 
 agent = create_deep_agent(
     model=llm,
-    tools=[run_graph],
+    tools=[answer_question],
     backend=backend,
-    system_prompt="You are a helpful agent that can answer questions and self‑critique using the provided tool.",
+    system_prompt="You are a helpful educational agent. Use the provided tools to answer questions.",
 )
 
+# ---------- CLI entry point ----------
 async def main():
     question = "Объясни студенту разницу между tool и resource в MCP"
     result = await agent.ainvoke(
         {"messages": [HumanMessage(content=question)]},
         {"configurable": {"thread_id": "session-1"}},
     )
-    print("Final answer:\n", result["messages"][-1].content)
+    # The tool returns the final answer as the last message content
+    print("\nFinal answer:\n", result["messages"][-1].content)
 
 if __name__ == "__main__":
     asyncio.run(main())