fix: main.py

main.py

@@ -1,10 +1,10 @@
 import os
 import asyncio
 from typing import TypedDict, Annotated
-
+from langgraph.graph import StateGraph, START, END
+from langgraph.graph.message import add_messages
 from langchain_openai import ChatOpenAI
-from langchain_core.messages import HumanMessage
+from langchain_core.messages import HumanMessage, AIMessage
-from langchain.tools import tool
 from deepagents import create_deep_agent
 from deepagents.backends import CompositeBackend, LocalShellBackend, FilesystemBackend
 
@@ -16,12 +16,6 @@ llm = ChatOpenAI(
     temperature=0.0,
 )
 
-# ---------- Backend ----------
-backend = CompositeBackend([
-    LocalShellBackend(workspace_dir="./workspace"),
-    FilesystemBackend(),
-])
-
 # ---------- State ----------
 class ReflectState(TypedDict):
     question: str
@@ -32,90 +26,75 @@ class ReflectState(TypedDict):
     max_rounds: int
 
 # ---------- Nodes ----------
-from langgraph.graph import StateGraph, START, END
-from langgraph.graph.message import add_messages
-
-# Helper to format the prompt for each node
-DRAFT_PROMPT = """Write a concise answer (5–10 sentences) to the following question:
-
-{question}
-"""
-
-REFLECT_PROMPT = """You are a critic. Given the draft answer below, evaluate its completeness, specificity, and absence of filler. Respond with:
-1. verdict: either "ok" or "needs_revision"
-2. critique: 2–3 bullet points explaining what to improve (if any)
-
-Draft:
-{draft}
-"""
-
-REWRITE_PROMPT = """You are revising the draft answer based on the critique. Produce a new draft that addresses the points. Keep the answer concise (5–10 sentences).
-
-Critique:
-{critique}
-
-Previous draft:
-{draft}
-"""
-
-# Node functions
 async def draft_answer(state: ReflectState) -> ReflectState:
-    response = await llm.ainvoke([HumanMessage(content=DRAFT_PROMPT.format(question=state["question"]))])
+    prompt = f"Write a concise answer (5–10 sentences) to the following question: {state['question']}"
-    state["draft"] = response.content.strip()
+    response = await llm.ainvoke([HumanMessage(content=prompt)])
+    state['draft'] = response.content
     return state
 
 async def reflect(state: ReflectState) -> ReflectState:
-    response = await llm.ainvoke([HumanMessage(content=REFLECT_PROMPT.format(draft=state["draft"]))])
+    prompt = (
-    # Parse verdict and critique
+        f"You are a critic. Evaluate the following draft answer for completeness, specificity, and lack of filler.\n\nDraft: {state['draft']}\n\nProvide a verdict (ok or needs_revision) and 2–3 bullet points of critique."
-    text = response.content.strip()
+    )
-    verdict_line = next((l for l in text.splitlines() if l.lower().startswith("verdict:")), "")
+    response = await llm.ainvoke([HumanMessage(content=prompt)])
-    critique_lines = [l for l in text.splitlines() if l.startswith("-") or l.startswith("•")]
+    # Simple parsing: first line verdict, rest critique
-    verdict = verdict_line.split(":",1)[1].strip().lower() if verdict_line else "needs_revision"
+    lines = response.content.strip().splitlines()
-    critique = "\n".join(critique_lines) if critique_lines else ""
+    verdict_line = lines[0].lower()
-    state["verdict"] = verdict
+    verdict = "ok" if "ok" in verdict_line else "needs_revision"
-    state["critique"] = critique
+    critique = "\n".join(lines[1:]) if len(lines) > 1 else ""
+    state['verdict'] = verdict
+    state['critique'] = critique
     return state
 
 async def rewrite(state: ReflectState) -> ReflectState:
-    response = await llm.ainvoke([HumanMessage(content=REWRITE_PROMPT.format(critique=state["critique"], draft=state["draft"]))])
+    prompt = (
-    state["draft"] = response.content.strip()
+        f"Rewrite the draft answer taking into account the following critique: {state['critique']}\n\nOriginal draft: {state['draft']}"
-    state["round"] += 1
+    )
+    response = await llm.ainvoke([HumanMessage(content=prompt)])
+    state['draft'] = response.content
+    state['round'] += 1
     return state
 
 # ---------- Graph ----------
-graph = StateGraph(ReflectState)
+builder = StateGraph(ReflectState)
-graph.add_node("draft_answer", draft_answer)
+builder.add_node("draft_answer", draft_answer)
-graph.add_node("reflect", reflect)
+builder.add_node("reflect", reflect)
-graph.add_node("rewrite", rewrite)
+builder.add_node("rewrite", rewrite)
 
-# Entry point
+builder.set_entry_point("draft_answer")
-graph.set_entry_point("draft_answer")
 
-# Transitions
+# Transition logic
-# After draft -> reflect
+def should_rewrite(state: ReflectState) -> str:
-graph.add_edge("draft_answer", "reflect")
+    if state['verdict'] == "ok":
-# After reflect
+        return "END"
-# if ok -> END
+    if state['round'] >= state['max_rounds']:
-# if needs_revision and round < max_rounds -> rewrite
-# else -> END
-
-def reflect_conditional(state: ReflectState):
-    if state["verdict"] == "ok":
         return "END"
-    if state["round"] < state["max_rounds"]:
     return "rewrite"
-    return "END"
 
-graph.add_conditional_edges("reflect", reflect_conditional, {"rewrite": "rewrite", "END": "END"})
+builder.add_conditional_edges("reflect", should_rewrite, {
-# After rewrite -> reflect
+    "rewrite": "rewrite",
-graph.add_edge("rewrite", "reflect")
+    "END": "END",
+})
 
-graph.compile()
+builder.add_edge("rewrite", "reflect")
+
+graph = builder.compile()
 
 # ---------- DeepAgent wrapper ----------
-@tool
+backend = CompositeBackend([
-def run_reflect_graph(question: str, max_rounds: int = 2) -> str:
+    LocalShellBackend(workspace_dir="./workspace"),
-    """Run the reflection graph and return the final draft."""
+    FilesystemBackend(),
+])
+
+agent = create_deep_agent(
+    model=llm,
+    tools=[],
+    backend=backend,
+    system_prompt="You are a helper that runs a reflection graph.",
+)
+
+# ---------- CLI ----------
+async def run_graph(question: str, max_rounds: int = 2):
     initial_state: ReflectState = {
         "question": question,
         "draft": "",
@@ -124,23 +103,18 @@ def run_reflect_graph(question: str, max_rounds: int = 2) -> str:
         "round": 0,
         "max_rounds": max_rounds,
     }
-    result = graph.invoke(initial_state)
+    result = await graph.ainvoke(initial_state)
-    return result["draft"]
+    return result
-
-agent = create_deep_agent(
-    model=llm,
-    tools=[run_reflect_graph],
-    backend=backend,
-    system_prompt="You are an assistant that can answer questions and self‑critique using the provided tool.",
-)
 
 async def main():
-    question = "Объясни студенту разницу между tool и resource в MCP."
+    question = "Объясни студенту разницу между tool и resource в MCP"
-    response = await agent.ainvoke(
+    result = await run_graph(question)
-        {"messages": [HumanMessage(content=f"Please answer: {question}")]},
+    print("\n--- Final Draft ---\n")
-        {"configurable": {"thread_id": "session-1"}},
+    print(result["draft"])
-    )
+    print("\n--- Critique ---\n")
-    print("Final answer:\n", response["messages"][-1].content)
+    print(result["critique"])
+    print("\n--- Verdict ---\n")
+    print(result["verdict"])
 
 if __name__ == "__main__":
     asyncio.run(main())