"""Evolution Engine — 从历史轨迹中学习, 反哺各智能体 prompt, 实现自进化。

闭环(自进化):
  轨迹采集 → 奖励打分 → 归纳成功/失败模式 → 生成进化建议 →
  反哺/追加到各 agent 的系统提示词(可选启用)

Level 1 实现:
  - analyze: 从已保存轨迹中总结高分/低分模式(常见工具序列、步骤分布)
  - generate_insights: 生成可读的进化洞察(markdown)
  - evolve_prompt: 将洞察追加到对应 agent 的 system prompt(可选)

轻量自进化的核心: 不编造"强化学习训练", 而是做"基于经验的 prompt 增强"
——把历史中高奖励轨迹用过的工具调用序列、成功策略, 有选择地注入
未来 agent 的提示词, 让系统越用越聪明。
"""

from __future__ import annotations

import json
from collections import Counter
from pathlib import Path
from typing import Any

from .reward import compute_reward_v1
from .trajectory import TrajectoryRecorder


class EvolutionEngine:
    """自进化引擎(Level 1 轻量版)。"""

    def __init__(
        self,
        base_dir: Path,
        recorder: TrajectoryRecorder,
        enabled: bool = True,
    ):
        self._base_dir = Path(base_dir)
        self._recorder = recorder
        self.enabled = enabled
        self._insights_dir = self._base_dir / "xingbang_evolution" / "insights"
        self._insights_dir.mkdir(parents=True, exist_ok=True)

    # ── 分析历史轨迹 ────────────────────────────────────
    def _load_all_trajectories(self) -> list[dict[str, Any]]:
        trajs = []
        for p in self._recorder.list_trajectories():
            try:
                trajs.append(json.loads(p.read_text(encoding="utf-8")))
            except Exception:
                continue
        return trajs

    def analyze(self) -> dict[str, Any]:
        """分析全部历史轨迹, 返回统计与模式。"""
        trajectories = self._load_all_trajectories()
        if not trajectories:
            return {"count": 0, "message": "尚无轨迹样本,先积累数据"}

        # 计算每条奖励
        scored = []
        for t in trajectories:
            r = compute_reward_v1(t)
            t["_reward"] = r
            scored.append(t)

        scored.sort(key=lambda x: x["_reward"], reverse=True)
        high = scored[: max(1, len(scored) // 4)]  # 前 25%
        low = scored[-max(1, len(scored) // 4):]   # 后 25%

        # 归纳高频工具序列
        def agent_tool_sequences(trajs):
            counter = Counter()
            for t in trajs:
                for s in t.get("steps", []):
                    seq = tuple(s.get("tools", []))
                    if seq:
                        counter[seq] += 1
            return counter.most_common(5)

        high_patterns = {
            "seqs": agent_tool_sequences(high),
            "avg_steps": sum(len(t["steps"]) for t in high) / max(1, len(high)),
            "success_rate": sum(1 for t in high if t["final_result"].get("success"))
                              / max(1, len(high)),
        }
        return {
            "count": len(trajectories),
            "avg_reward": round(sum(t["_reward"] for t in scored) / len(scored), 2),
            "high": {"samples": len(high), "patterns": high_patterns},
            "low": {
                "samples": len(low),
                "avg_steps": sum(len(t["steps"]) for t in low) / max(1, len(low)),
            },
            "top_agents_used": self._agent_usage(scored),
        }

    def _agent_usage(self, trajs) -> dict:
        counter = Counter()
        for t in trajs:
            for s in t.get("steps", []):
                counter[s.get("agent", "?")] += 1
        return dict(counter.most_common())

    # ── 生成进化洞察 ────────────────────────────────────
    def generate_insights(self) -> str:
        """生成可读的 markdown 进化洞察报告。"""
        analysis = self.analyze()
        if analysis.get("count", 0) == 0:
            return "# 自进化洞察\n\n尚无轨迹样本。运行审批流水线积累数据后,系统将自动进化。"
        lines = [
            f"# 兴邦 AI 评审·自进化洞察",
            f"\n**样本数**: {analysis['count']} 条轨迹  |  **平均奖励**: {analysis['avg_reward']}",
            "",
            "## ✅ 高分轨迹模式 (前 25%)",
        ]
        hp = analysis["high"]
        lines.append(f"- 平均步骤数: {hp['patterns']['avg_steps']:.1f}")
        lines.append(f"- 成功率: {hp['patterns']['success_rate']*100:.0f}%")
        lines.append("- 高频工具序列:")
        for seq, n in hp["patterns"]["seqs"]:
            lines.append(f"  - {' → '.join(seq)} (出现 {n} 次)")
        lines += ["", "## ⚠️ 低分轨迹 (后 25%)", f"- 平均步骤数: {analysis['low']['avg_steps']:.1f}"]
        lines += ["", "## 🧠 智能体使用分布", ""]
        for agent, count in analysis.get("top_agents_used", {}).items():
            lines.append(f"- {agent}: {count} 次")
        lines += [
            "",
            "## 进化建议",
            "1. 高分轨迹的工具序列可在各 agent 的 system prompt 中作为'推荐工作流'注入",
            "2. 步骤数偏多(>5)的 agent 提示词应强调'一次到位,减少反复读取'",
            "3. 持续积累轨迹 → 达到一定量后启动更高阶优化(LoRA 微调)",
        ]
        return "\n".join(lines)

    def save_insights(self) -> Path:
        """保存洞察报告到 insights 目录。"""
        report = self.generate_insights()
        path = self._insights_dir / "evolution_insights.md"
        path.write_text(report, encoding="utf-8")
        return path

    # ── 反哺 prompt (自进化闭环) ────────────────────────
    def evolve_prompt_suggestion(self, agent_key: str) -> str | None:
        """为指定 agent 生成可注入的 prompt 增强建议(基于历史高分轨迹)。

        返回一段可追加到该 agent system_prompt 的文本, 若无历史则 None。
        """
        analysis = self.analyze()
        if analysis.get("count", 0) == 0:
            return None
        hp = analysis["high"]
        seqs = hp["patterns"]["seqs"]
        if not seqs:
            return None
        top_seq_text = " → ".join(seqs[0][0]) if seqs else ""
        suggestion = (
            f"\n\n[自进化推荐 · 基于 {analysis['count']} 条历史轨迹] "
            f"高分任务常用工具序列: {top_seq_text}。"
            f"请优先复用该模式,减少无效工具往返,一次到位完成任务。"
        )
        return suggestion