"""
Main entry point for the Planning Agent assignment.

The program demonstrates a LangGraph agent that:
1. Plans a task into discrete steps using an LLM.
2. Executes each step sequentially, collecting results.
3. Returns a final summary of all results.

Three example tasks are executed when run as a script.
"""

import os
from typing import TypedDict, List
from langgraph.graph import StateGraph, START, END
from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage, SystemMessage
from rich.console import Console

# ---------------------------------------------------------------------------
# 1. State definition
# ---------------------------------------------------------------------------
class PlanningState(TypedDict):
    task: str
    plan: List[str] | None
    current_step: int
    results: List[str]

# ---------------------------------------------------------------------------
# 2. LLM configuration – BroJS provider
# ---------------------------------------------------------------------------
llm = ChatOpenAI(
    model="openai/gpt-oss-20b:free",
    base_url="https://platform.brojs.ru/jrnl-bh/api/inference/v1",
    api_key=os.getenv("JOURNAL_MCP_PAT"),
    temperature=0.2,
)

# ---------------------------------------------------------------------------
# 3. Planning node – split the task into steps
# ---------------------------------------------------------------------------
def planning(state: PlanningState) -> PlanningState:
    """Ask LLM to produce a numbered list of steps.

    The prompt asks for JSON output with a single key ``steps`` containing an array
    of strings.  This guarantees deterministic parsing.
    """
    task = state["task"]
    system_prompt = (
        "You are a helpful assistant that breaks down a user request into a list of concrete, actionable steps."
    )
    user_prompt = (
        f"Task: {task}\n\nReturn a JSON object with a single key 'steps' containing an array of strings.  Each string should be a concise step.  Provide between 3 and 6 steps.")

    response = llm.invoke([SystemMessage(content=system_prompt), HumanMessage(content=user_prompt)])
    # Parse JSON safely
    import json, re
    try:
        data = json.loads(response.content)
        steps = data.get("steps", [])
    except Exception:
        # Fallback: extract numbered list via regex
        pattern = r"\d+\.\s*(.+)"
        steps = [m.group(1).strip() for m in re.finditer(pattern, response.content)]
    return {
        "task": task,
        "plan": steps,
        "current_step": 0,
        "results": [],
    }

# ---------------------------------------------------------------------------
# 4. Execution node – run one step and record result
# ---------------------------------------------------------------------------
def execution(state: PlanningState) -> PlanningState:
    idx = state["current_step"]
    plan = state["plan"] or []
    if idx >= len(plan):
        return state
    step_text = plan[idx]
    # For demonstration, we simply echo the step as result.
    # In a real scenario this could invoke tools or perform computation.
    result = f"Result of step {idx+1}: {step_text}"
    new_results = state["results"] + [result]
    return {
        "task": state["task"],
        "plan": plan,
        "current_step": idx + 1,
        "results": new_results,
    }

# ---------------------------------------------------------------------------
# 5. Decision node – continue or finish
# ---------------------------------------------------------------------------
def should_continue(state: PlanningState) -> str:
    if state["current_step"] >= len(state.get("plan", [])):
        return "finish"
    return "execute"

# ---------------------------------------------------------------------------
# 6. Build graph
# ---------------------------------------------------------------------------
graph = StateGraph(PlanningState)
graph.add_node("planning", planning)
graph.add_node("execution", execution)
graph.add_conditional_edges(
    "planning",
    lambda _: "execute" if _["plan"] else "finish",
)
graph.add_edge("execution", "should_continue")
graph.add_conditional_edges(
    "should_continue",
    should_continue,
    {"execute": "execution", "finish": END},
)
# Start from planning
graph.set_entry_point("planning")
agent = graph.compile()

# ---------------------------------------------------------------------------
# 7. Helper to run a task and print results
# ---------------------------------------------------------------------------
def run_task(task: str) -> None:
    console = Console()
    console.print(f"\n[bold cyan]Running task:[/bold cyan] {task}")
    result_state = agent.invoke({"task": task})
    plan = result_state.get("plan", [])
    results = result_state.get("results", [])
    console.print("\n[green]Plan:\n[/green]")
    for i, step in enumerate(plan, 1):
        console.print(f"{i}. {step}")
    console.print("\n[blue]Execution results:\n[/blue]")
    for r in results:
        console.print(r)
    console.print("\n[bold magenta]Final summary:[/bold magenta]\n")
    # Final LLM summarization
    summary_prompt = (
        "You have executed the following steps: \n" + "\n".join(results) + "\nProvide a concise final answer.")
    summary_response = llm.invoke([HumanMessage(content=summary_prompt)])
    console.print(summary_response.content)

# ---------------------------------------------------------------------------
# 8. Main – three example tasks
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    examples = [
        "Compare Python and JavaScript in terms of performance, syntax simplicity, and ecosystem support.",
        "Explain how to set up a basic Flask application with a single route.",
        "Outline the steps required to deploy a Dockerized Node.js app to AWS Elastic Beanstalk.",
    ]
    for ex in examples:
        run_task(ex)
"""