aiagent/backend/app/agent_runtime/core.py

"""
Agent Runtime 核心 —— 自主 ReAct 循环。

流程：
1. 接收用户输入 → 追加到消息列表
2. 调用 LLM（携带 tools schema）
3. 如果 LLM 返回工具调用 → 执行工具 → 结果追加到消息列表 → 回到 2
4. 如果 LLM 返回文本 → 作为最终回答返回
5. 超过 max_iterations → 强制终止
"""
from __future__ import annotations

import hashlib
import json
import logging
import time
from typing import Any, AsyncGenerator, Callable, Dict, List, Optional, Protocol, TypedDict

from app.agent_runtime.schemas import (
    AgentConfig,
    AgentResult,
    AgentStep,
)
from app.agent_runtime.context import AgentContext
from app.agent_runtime.memory import AgentMemory
from app.agent_runtime.tool_manager import AgentToolManager
from app.core.exceptions import WorkflowExecutionError
from app.services.agent_learning_service import (
    extract_pattern_from_result,
    format_pattern_hint,
    load_relevant_patterns,
    save_learning_pattern,
)

logger = logging.getLogger(__name__)


class LLMCallMetrics(TypedDict, total=False):
    """一次 LLM 调用的度量数据"""
    agent_id: Optional[str]
    session_id: str
    user_id: Optional[str]
    model: str
    provider: Optional[str]
    prompt_tokens: int
    completion_tokens: int
    total_tokens: int
    latency_ms: int
    iteration_number: int
    step_type: str  # think / final
    tool_name: Optional[str]
    status: str  # success / error
    error_message: Optional[str]

# 可重试的 API 异常
_RETRYABLE_ERRORS = (
    "timed out",
    "timeout",
    "connection error",
    "temporarily unavailable",
    "server disconnected",
    "rate limit",
    "too many requests",
    "internal server error",
    "service unavailable",
)


class AgentRuntime:
    """
    自主 Agent 运行时。

    用法：
        runtime = AgentRuntime(config)
        result = await runtime.run("帮我写个Python脚本")
    """

    def __init__(
        self,
        config: Optional[AgentConfig] = None,
        context: Optional[AgentContext] = None,
        memory: Optional[AgentMemory] = None,
        tool_manager: Optional[AgentToolManager] = None,
        execution_logger: Optional[Any] = None,
        on_tool_executed: Optional[Callable[[str], Any]] = None,
        on_llm_call: Optional[Callable[[Dict[str, Any]], Any]] = None,
    ):
        self.config = config or AgentConfig()
        self.context = context or AgentContext(
            system_prompt=self.config.system_prompt,
            user_id=self.config.user_id,
        )
        _mem_scope = self.config.memory_scope_id or self.config.user_id or self.config.name
        self.memory = memory or AgentMemory(
            scope_id=_mem_scope,
            max_history=self.config.memory.max_history_messages,
            persist=self.config.memory.persist_to_db,
        )
        self.tool_manager = tool_manager or AgentToolManager(
            include_tools=self.config.tools.include_tools,
            exclude_tools=self.config.tools.exclude_tools,
            cache_enabled=self.config.tools.cache_enabled,
            cache_tool_whitelist=self.config.tools.cache_tool_whitelist,
            cache_ttl_ms=self.config.tools.cache_ttl_ms,
        )
        self.execution_logger = execution_logger
        self.on_tool_executed = on_tool_executed
        self.on_llm_call = on_llm_call
        self._memory_context_loaded = False
        self._llm_invocations = 0
        # 自主学习作用域：bare 聊天用 "bare"，Agent 用 "agent"
        self._learning_scope_kind = "bare" if "bare" in str(_mem_scope) else "agent"

        # 预算回调：供 WorkflowEngine 注入，使 Agent 内部计数计入工作流预算
        # 返回 True 表示预算充足；返回 False 或抛出异常表示超限
        self.on_llm_invocation: Optional[Callable[[], Any]] = None

    async def run(self, user_input: str) -> AgentResult:
        """
        执行 Agent 单轮对话。

        流程：加载记忆 → 追加用户消息 → ReAct 循环 → 保存记忆 → 返回结果。
        """
        max_iter = max(1, self.config.llm.max_iterations)
        self.context.iteration = 0
        self.context.tool_calls_made = 0

        # 1. 首次运行时加载长期记忆到 system prompt
        if not self._memory_context_loaded:
            await self._inject_memory_context(user_input)
            self._memory_context_loaded = True

        # 2. 追加用户消息
        self.context.add_user_message(user_input)

        # 3. ReAct 循环
        llm = _LLMClient(self.config.llm)
        tool_schemas = self.tool_manager.get_tool_schemas()
        has_tools = self.tool_manager.has_tools()
        steps: List[AgentStep] = []
        _self_review_attempted = False  # 防止无限修正循环

        # 构建 LLM 调用回调（包装 on_llm_call，补充上下文）
        llm_callback_ctx = {"step_type": "think", "tool_name": None}

        def _llm_callback(metrics: Dict[str, Any]):
            if self.on_llm_call:
                metrics.update({
                    "session_id": self.context.session_id,
                    "user_id": self.config.user_id,
                    "step_type": llm_callback_ctx["step_type"],
                    "tool_name": llm_callback_ctx["tool_name"],
                })
                self.on_llm_call(metrics)

        while self.context.iteration < max_iter:
            self.context.iteration += 1

            # 裁剪过长历史
            messages = self.memory.trim_messages(self.context.messages)

            # 预算检查：LLM 调用次数（在调用 LLM 之前检查，避免浪费额度）
            budget = self.config.budget
            if self._llm_invocations >= budget.max_llm_invocations:
                err = f"已超过 LLM 调用预算（{budget.max_llm_invocations} 次）"
                logger.warning(err)
                steps.append(AgentStep(iteration=self.context.iteration, type="final", content=err))
                await self.memory.save_context(user_input, err, self.context.messages)
                return AgentResult(success=False, content=err, truncated=True,
                                   iterations_used=self.context.iteration,
                                   tool_calls_made=self.context.tool_calls_made,
                                   steps=steps, error=err)

            # 调用外部 LLM 预算回调（WorkflowEngine 注入，将 Agent 的 LLM 计入工作流预算）
            if self.on_llm_invocation:
                try:
                    self.on_llm_invocation()
                except Exception as e:
                    err = f"LLM 调用超出工作流预算: {e}"
                    logger.warning(err)
                    steps.append(AgentStep(iteration=self.context.iteration, type="final", content=err))
                    await self.memory.save_context(user_input, err, self.context.messages)
                    return AgentResult(success=False, content=err, truncated=True,
                                       iterations_used=self.context.iteration,
                                       tool_calls_made=self.context.tool_calls_made,
                                       steps=steps, error=str(e))

            # 调用 LLM
            try:
                response = await llm.chat(
                    messages=messages,
                    tools=tool_schemas if has_tools and self.context.iteration == 1 else
                               (tool_schemas if has_tools else None),
                    iteration=self.context.iteration,
                    on_completion=_llm_callback,
                )
            except Exception as e:
                err_str = str(e)
                logger.error("LLM 调用失败 (iteration=%s): %s", self.context.iteration, err_str)
                if self.context.iteration < max_iter and self._is_retryable(err_str):
                    steps.append(AgentStep(
                        iteration=self.context.iteration,
                        type="tool_result",
                        content=f"LLM 调用失败（可重试）: {err_str}",
                    ))
                    continue
                return AgentResult(
                    success=False,
                    content=f"LLM 调用失败: {err_str}",
                    iterations_used=self.context.iteration,
                    tool_calls_made=self.context.tool_calls_made,
                    error=err_str,
                )

            # 记录 LLM 调用次数（内部计数）
            self._llm_invocations += 1

            # 解析工具调用
            tool_calls = self._extract_tool_calls(response)
            content = self._extract_content(response)
            reasoning = getattr(response, "reasoning_content", None) or (
                response.get("reasoning_content") if isinstance(response, dict) else None
            )

            if not tool_calls:
                # LLM 直接返回文本 → 结束
                self.context.add_assistant_message(content)
                final_text = content or "（模型未返回有效内容）"

                # 输出质量自检（默认关闭，Agent 节点可开启）
                if self.config.self_review_enabled and not _self_review_attempted:
                    review = await self._self_review(final_text, task_context=user_input)
                    steps.append(AgentStep(
                        iteration=self.context.iteration,
                        type="tool_result",
                        content=f"self_review: score={review['score']:.2f} passed={review['passed']}",
                        tool_name="self_review",
                        tool_input={"content": final_text[:200]},
                        tool_result=json.dumps(review, ensure_ascii=False),
                    ))
                    if review["passed"]:
                        logger.info("self_review 通过 (%.2f >= %.2f)", review["score"], review["threshold"])
                    else:
                        logger.info("self_review 未通过 (%.2f < %.2f)，追加修正", review["score"], review["threshold"])
                        _self_review_attempted = True
                        # 追加修正提示
                        fix_prompt = (
                            f"你的上一个回答未通过质量检查（评分 {review['score']:.1f}/{review['threshold']}）。\n"
                            f"问题：{'；'.join(review['issues'][:3])}\n"
                            f"改进建议：{'；'.join(review['suggestions'][:3])}\n"
                            "请修正你的回答，确保满足上述建议。"
                        )
                        self.context.add_user_message(fix_prompt)
                        continue  # 回到 ReAct 循环，让 LLM 修正

                steps.append(AgentStep(
                    iteration=self.context.iteration,
                    type="final",
                    content=final_text,
                    reasoning=reasoning,
                ))
                # 保存记忆
                await self.memory.save_context(user_input, final_text, self.context.messages)
                # 保存学习模式
                if self.config.memory.learning_enabled:
                    await self._save_learning_pattern(
                        user_input, steps, success=True,
                        iterations_used=self.context.iteration,
                        tool_calls_made=self.context.tool_calls_made,
                    )
                # 提取知识到全局知识池（Agent 间知识共享）
                await self._extract_global_knowledge(user_input, final_text, steps)
                return AgentResult(
                    success=True,
                    content=final_text,
                    iterations_used=self.context.iteration,
                    tool_calls_made=self.context.tool_calls_made,
                    steps=steps,
                )

            # 有工具调用 → 先记录 assistant 消息（含 tool_calls）
            self.context.add_assistant_message(content or "", tool_calls, reasoning)

            # 记录思考步骤（含工具调用意图）
            tc_names = [tc["function"]["name"] for tc in tool_calls]
            tc_args_list = []
            for tc in tool_calls:
                try:
                    tc_args_list.append(json.loads(tc["function"].get("arguments", "{}")))
                except (json.JSONDecodeError, TypeError):
                    tc_args_list.append({})

            steps.append(AgentStep(
                iteration=self.context.iteration,
                type="think",
                content=content or f"调用工具: {', '.join(tc_names)}",
                reasoning=reasoning,
                tool_name=tc_names[0] if len(tc_names) == 1 else None,
                tool_input=tc_args_list[0] if len(tc_args_list) == 1 else None,
            ))

            if self.execution_logger:
                self.execution_logger.info(
                    f"Agent 调用 {len(tool_calls)} 个工具",
                    data={"tool_calls": tc_names,
                          "iteration": self.context.iteration},
                )

            # 逐一执行工具
            for tc in tool_calls:
                tfn = tc.get("function", {})
                tname = tfn.get("name", "unknown")
                tcid = tc.get("id", f"call_{self.context.iteration}_{self.context.tool_calls_made}")

                try:
                    targs = json.loads(tfn.get("arguments", "{}"))
                except (json.JSONDecodeError, TypeError):
                    targs = {}

                # 工具执行前审批检查
                if tname in self.config.tools.require_approval:
                    from app.services.approval_manager import approval_manager as _am
                    logger.info("Agent 工具需审批 [%s]: %s", tname, targs)
                    approval_req = await _am.submit(
                        tool_name=tname, args=targs,
                        timeout_ms=self.config.tools.approval_timeout_ms,
                    )
                    decision = approval_req.decision
                    if decision == "denied":
                        result = f"[审批拒绝] 工具 {tname} 需要人工审批但被拒绝。"
                        self.context.add_tool_result(tcid, tname, result)
                        continue
                    elif decision == "skip":
                        result = f"[审批跳过] 工具 {tname} 被跳过。"
                        self.context.add_tool_result(tcid, tname, result)
                        continue
                    # decision == "approved" → 继续执行

                logger.info("Agent 执行工具 [%s]: %s", tname, targs)
                result = await self.tool_manager.execute(tname, targs)

                steps.append(AgentStep(
                    iteration=self.context.iteration,
                    type="tool_result",
                    content=f"工具 {tname} 返回结果",
                    tool_name=tname,
                    tool_input=targs,
                    tool_result=result[:500] + "..." if len(result) > 500 else result,
                ))

                self.context.add_tool_result(tcid, tname, result)
                self.context.tool_calls_made += 1

                # 预算检查：工具调用次数
                if self.context.tool_calls_made > budget.max_tool_calls:
                    err = f"已超过工具调用预算（{budget.max_tool_calls} 次）"
                    logger.warning(err)
                    steps.append(AgentStep(iteration=self.context.iteration, type="tool_result",
                                           content=err, tool_name=tname))
                    return AgentResult(success=False, content=err, truncated=True,
                                       iterations_used=self.context.iteration,
                                       tool_calls_made=self.context.tool_calls_made,
                                       steps=steps, error=err)

                if self.on_tool_executed:
                    try:
                        await self.on_tool_executed(tname)
                    except WorkflowExecutionError:
                        raise
                    except Exception:
                        pass

                if self.execution_logger:
                    preview = result[:300] + "..." if len(result) > 300 else result
                    self.execution_logger.info(
                        f"工具 {tname} 执行完成",
                        data={"tool_name": tname, "result_preview": preview},
                    )

        # 达到最大迭代次数
        last_content = ""
        for m in reversed(self.context.messages):
            if m.get("role") == "assistant" and m.get("content"):
                last_content = m["content"]
                break

        logger.warning("Agent 达到最大迭代次数 (%s)", max_iter)
        await self.memory.save_context(user_input, last_content or "（已达最大迭代次数）", self.context.messages)
        # 保存学习模式（即便截断，工具调用模式仍有参考价值）
        if self.config.memory.learning_enabled:
            await self._save_learning_pattern(
                user_input, steps, success=True,
                iterations_used=self.context.iteration,
                tool_calls_made=self.context.tool_calls_made,
            )
        if last_content:
            steps.append(AgentStep(
                iteration=self.context.iteration,
                type="final",
                content=last_content,
            ))
        return AgentResult(
            success=True,
            content=last_content or "已达最大迭代次数，但模型未返回最终回答。",
            truncated=True,
            iterations_used=self.context.iteration,
            tool_calls_made=self.context.tool_calls_made,
            steps=steps,
        )

    async def run_stream(self, user_input: str) -> AsyncGenerator[dict, None]:
        """
        流式执行 Agent 单轮对话。

        与 run() 逻辑相同，但在每个关键步骤 yield SSE 事件：
        - think: LLM 思考中，准备调用工具
        - tool_call: 即将执行工具
        - tool_result: 工具执行完毕
        - final: 最终回答
        - error: 出错/预算超限
        """
        max_iter = max(1, self.config.llm.max_iterations)
        self.context.iteration = 0
        self.context.tool_calls_made = 0

        # 1. 首次运行时加载长期记忆到 system prompt
        if not self._memory_context_loaded:
            await self._inject_memory_context(user_input)
            self._memory_context_loaded = True

        # 2. 追加用户消息
        self.context.add_user_message(user_input)

        # 3. ReAct 循环
        llm = _LLMClient(self.config.llm)
        tool_schemas = self.tool_manager.get_tool_schemas()
        has_tools = self.tool_manager.has_tools()
        steps: List[AgentStep] = []
        _self_review_attempted = False

        llm_callback_ctx = {"step_type": "think", "tool_name": None}

        def _llm_callback(metrics: Dict[str, Any]):
            if self.on_llm_call:
                metrics.update({
                    "session_id": self.context.session_id,
                    "user_id": self.config.user_id,
                    "step_type": llm_callback_ctx["step_type"],
                    "tool_name": llm_callback_ctx["tool_name"],
                })
                self.on_llm_call(metrics)

        while self.context.iteration < max_iter:
            self.context.iteration += 1
            messages = self.memory.trim_messages(self.context.messages)

            # 预算检查：LLM 调用次数（在调用 LLM 之前检查，避免浪费额度）
            budget = self.config.budget
            if self._llm_invocations >= budget.max_llm_invocations:
                err = f"已超过 LLM 调用预算（{budget.max_llm_invocations} 次）"
                logger.warning(err)
                yield {"type": "error", "content": err, "iteration": self.context.iteration,
                       "truncated": True}
                await self.memory.save_context(user_input, err, self.context.messages)
                return

            # 调用外部 LLM 预算回调（WorkflowEngine 注入）
            if self.on_llm_invocation:
                try:
                    self.on_llm_invocation()
                except Exception as e:
                    err = f"LLM 调用超出工作流预算: {e}"
                    logger.warning(err)
                    yield {"type": "error", "content": err, "iteration": self.context.iteration,
                           "truncated": True}
                    return

            # think 事件：告知前端 Agent 正在思考（让 UI 即时反馈，避免假死感）
            yield {"type": "think", "content": "", "reasoning": None, "iteration": self.context.iteration}

            # 调用 LLM
            try:
                response = await llm.chat(
                    messages=messages,
                    tools=tool_schemas if has_tools and self.context.iteration == 1 else
                               (tool_schemas if has_tools else None),
                    iteration=self.context.iteration,
                    on_completion=_llm_callback,
                )
            except Exception as e:
                err_str = str(e)
                logger.error("LLM 调用失败 (iteration=%s): %s", self.context.iteration, err_str)
                if self.context.iteration < max_iter and self._is_retryable(err_str):
                    yield {"type": "error", "content": f"LLM 调用失败（可重试）: {err_str}",
                           "iteration": self.context.iteration}
                    continue
                yield {"type": "error", "content": f"LLM 调用失败: {err_str}",
                       "iteration": self.context.iteration}
                return

            # 记录 LLM 调用次数（内部计数）
            self._llm_invocations += 1

            # 解析工具调用
            tool_calls = self._extract_tool_calls(response)
            content = self._extract_content(response)
            reasoning = getattr(response, "reasoning_content", None) or (
                response.get("reasoning_content") if isinstance(response, dict) else None
            )

            if not tool_calls:
                # LLM 直接返回文本 → 结束
                self.context.add_assistant_message(content)
                final_text = content or "（模型未返回有效内容）"

                # 输出质量自检（默认关闭）
                if self.config.self_review_enabled and not _self_review_attempted:
                    review = await self._self_review(final_text, task_context=user_input)
                    yield {
                        "type": "tool_result",
                        "content": f"self_review: score={review['score']:.2f} passed={review['passed']}",
                        "tool_name": "self_review",
                        "iteration": self.context.iteration,
                        "session_id": self.context.session_id,
                    }
                    if review["passed"]:
                        logger.info("self_review 通过 (%.2f >= %.2f)", review["score"], review["threshold"])
                    else:
                        logger.info("self_review 未通过 (%.2f < %.2f)，追加修正", review["score"], review["threshold"])
                        _self_review_attempted = True
                        yield {
                            "type": "think",
                            "content": f"自检未通过（{review['score']:.1f}），正在修正：{'；'.join(review['suggestions'][:2])}",
                            "iteration": self.context.iteration,
                            "session_id": self.context.session_id,
                        }
                        fix_prompt = (
                            f"你的上一个回答未通过质量检查（评分 {review['score']:.1f}/{review['threshold']}）。\n"
                            f"问题：{'；'.join(review['issues'][:3])}\n"
                            f"改进建议：{'；'.join(review['suggestions'][:3])}\n"
                            "请修正你的回答，确保满足上述建议。"
                        )
                        self.context.add_user_message(fix_prompt)
                        continue  # 回到 ReAct 循环，让 LLM 修正

                yield {
                    "type": "final",
                    "content": final_text,
                    "reasoning": reasoning,
                    "iteration": self.context.iteration,
                    "iterations_used": self.context.iteration,
                    "tool_calls_made": self.context.tool_calls_made,
                    "session_id": self.context.session_id,
                }
                await self.memory.save_context(user_input, final_text, self.context.messages)
                # 保存学习模式
                if self.config.memory.learning_enabled:
                    await self._save_learning_pattern(
                        user_input, steps, success=True,
                        iterations_used=self.context.iteration,
                        tool_calls_made=self.context.tool_calls_made,
                    )
                return

            # 有工具调用 → 先记录 assistant 消息
            self.context.add_assistant_message(content or "", tool_calls, reasoning)

            # yield think 事件
            tc_names = [tc["function"]["name"] for tc in tool_calls]
            tc_args_list = []
            for tc in tool_calls:
                try:
                    tc_args_list.append(json.loads(tc["function"].get("arguments", "{}")))
                except (json.JSONDecodeError, TypeError):
                    tc_args_list.append({})

            yield {
                "type": "think",
                "content": content or f"调用工具: {', '.join(tc_names)}",
                "reasoning": reasoning,
                "tool_names": tc_names,
                "iteration": self.context.iteration,
            }

            steps.append(AgentStep(
                iteration=self.context.iteration,
                type="think",
                content=content or f"调用工具: {', '.join(tc_names)}",
                reasoning=reasoning,
                tool_name=tc_names[0] if len(tc_names) == 1 else None,
                tool_input=tc_args_list[0] if len(tc_args_list) == 1 else None,
            ))

            if self.execution_logger:
                self.execution_logger.info(
                    f"Agent 调用 {len(tool_calls)} 个工具",
                    data={"tool_calls": tc_names, "iteration": self.context.iteration},
                )

            # 逐一执行工具
            for tc in tool_calls:
                tfn = tc.get("function", {})
                tname = tfn.get("name", "unknown")
                tcid = tc.get("id", f"call_{self.context.iteration}_{self.context.tool_calls_made}")

                try:
                    targs = json.loads(tfn.get("arguments", "{}"))
                except (json.JSONDecodeError, TypeError):
                    targs = {}

                # yield tool_call 事件
                yield {
                    "type": "tool_call",
                    "name": tname,
                    "input": targs,
                    "iteration": self.context.iteration,
                }

                # 工具执行前审批检查（流式：先 create → yield 事件带 ID → 等待决定）
                if tname in self.config.tools.require_approval:
                    from app.services.approval_manager import approval_manager as _am
                    logger.info("Agent 工具需审批 [%s]: %s", tname, targs)
                    approval_req = _am.create(tool_name=tname, args=targs)
                    yield {
                        "type": "approval_required",
                        "approval_id": approval_req.approval_id,
                        "tool_name": tname,
                        "args": targs,
                        "iteration": self.context.iteration,
                    }
                    decision = await _am.wait_for_decision(
                        approval_req.approval_id,
                        timeout_ms=self.config.tools.approval_timeout_ms,
                    )
                    if decision == "denied":
                        result = f"[审批拒绝] 工具 {tname} 需要人工审批但被拒绝。"
                        yield {"type": "tool_result", "name": tname, "result": result, "iteration": self.context.iteration}
                        self.context.add_tool_result(tcid, tname, result)
                        continue
                    elif decision == "skip":
                        result = f"[审批跳过] 工具 {tname} 被跳过。"
                        yield {"type": "tool_result", "name": tname, "result": result, "iteration": self.context.iteration}
                        self.context.add_tool_result(tcid, tname, result)
                        continue
                    # decision == "approved" → 继续执行

                logger.info("Agent 执行工具 [%s]: %s", tname, targs)
                result = await self.tool_manager.execute(tname, targs)

                # yield tool_result 事件
                yield {
                    "type": "tool_result",
                    "name": tname,
                    "result": result[:500] + "..." if len(result) > 500 else result,
                    "iteration": self.context.iteration,
                }

                steps.append(AgentStep(
                    iteration=self.context.iteration,
                    type="tool_result",
                    content=f"工具 {tname} 返回结果",
                    tool_name=tname,
                    tool_input=targs,
                    tool_result=result[:500] + "..." if len(result) > 500 else result,
                ))

                self.context.add_tool_result(tcid, tname, result)
                self.context.tool_calls_made += 1

                # 预算检查：工具调用次数
                if self.context.tool_calls_made > budget.max_tool_calls:
                    err = f"已超过工具调用预算（{budget.max_tool_calls} 次）"
                    logger.warning(err)
                    yield {"type": "error", "content": err, "iteration": self.context.iteration,
                           "truncated": True}
                    return

                if self.on_tool_executed:
                    try:
                        await self.on_tool_executed(tname)
                    except WorkflowExecutionError:
                        raise
                    except Exception:
                        pass

                if self.execution_logger:
                    preview = result[:300] + "..." if len(result) > 300 else result
                    self.execution_logger.info(
                        f"工具 {tname} 执行完成",
                        data={"tool_name": tname, "result_preview": preview},
                    )

        # 达到最大迭代次数
        last_content = ""
        for m in reversed(self.context.messages):
            if m.get("role") == "assistant" and m.get("content"):
                last_content = m["content"]
                break

        logger.warning("Agent 达到最大迭代次数 (%s)", max_iter)
        await self.memory.save_context(user_input, last_content or "（已达最大迭代次数）", self.context.messages)
        # 保存学习模式（即便截断，工具调用模式仍有参考价值）
        if self.config.memory.learning_enabled:
            await self._save_learning_pattern(
                user_input, steps, success=True,
                iterations_used=self.context.iteration,
                tool_calls_made=self.context.tool_calls_made,
            )
        yield {
            "type": "final",
            "content": last_content or "已达最大迭代次数，但模型未返回最终回答。",
            "iteration": self.context.iteration,
            "iterations_used": self.context.iteration,
            "tool_calls_made": self.context.tool_calls_made,
            "truncated": True,
            "session_id": self.context.session_id,
        }

    async def _inject_memory_context(self, query: str = "") -> None:
        """加载长期记忆并注入 system prompt。"""
        mem_text = await self.memory.initialize(query=query)
        enriched = self.config.system_prompt.rstrip("\n")

        if mem_text:
            enriched += "\n\n" + mem_text

        # 注入学习模式提示（历史工具使用建议）
        if self.config.memory.learning_enabled:
            pattern_hint = await self._inject_learning_patterns(query)
            if pattern_hint:
                enriched += "\n\n" + pattern_hint

        self.context.set_system_prompt(enriched)
        logger.info("Agent 已注入长期记忆上下文")

    async def _inject_learning_patterns(self, query: str) -> str:
        """查询学习模式，返回格式化的提示文本。"""
        from app.core.database import SessionLocal
        db = None
        try:
            db = SessionLocal()
            patterns = load_relevant_patterns(
                db, self._learning_scope_kind, self.memory.scope_id, query
            )
            return format_pattern_hint(patterns, query)
        except Exception as e:
            logger.warning("加载学习模式失败: %s", e)
            return ""
        finally:
            if db:
                db.close()

    async def _save_learning_pattern(
        self, query: str, steps: List[AgentStep],
        success: bool, iterations_used: int, tool_calls_made: int,
    ) -> None:
        """从执行结果中提取模式并保存。"""
        from app.core.database import SessionLocal
        db = None
        try:
            db = SessionLocal()
            pattern_data = extract_pattern_from_result(
                query=query,
                steps=steps,
                success=success,
                iterations_used=iterations_used,
                tool_calls_made=tool_calls_made,
            )
            save_learning_pattern(
                db, self._learning_scope_kind,
                self.memory.scope_id, pattern_data,
            )
        except Exception as e:
            logger.warning("保存学习模式失败: %s", e)
        finally:
            if db:
                db.close()

    async def _extract_global_knowledge(
        self, user_input: str, final_answer: str, steps: List[AgentStep],
    ) -> None:
        """从 Agent 执行结果中提取知识，写入全局知识池（Agent 间共享）。"""
        # 提取工具调用名称作为 tags
        tool_names = list(dict.fromkeys(
            s.tool_name for s in (steps or [])
            if s.tool_name and s.type == "tool_result"
        ))
        tags = tool_names[:5] if tool_names else ["对话"]

        # 提取关键信息：用户问题摘要 + 回答要点（前 500 字）
        content = (
            f"问题: {user_input[:300]}\n"
            f"回答要点: {final_answer[:500]}"
        )
        if tool_names:
            content += f"\n使用工具: {', '.join(tool_names[:5])}"

        source_agent_id = self.config.name if self.config.name != "default_agent" else ""
        source_user_id = self.config.user_id or ""

        await self.memory.save_global_knowledge(
            content=content,
            source_agent_id=source_agent_id,
            source_user_id=source_user_id,
            tags=tags,
        )

    async def _self_review(self, content: str, task_context: str = "") -> dict:
        """输出质量自检：用轻量 LLM 评判输出，返回 {score, passed, issues, suggestions}。"""
        criteria = (
            "回答必须准确、完整、切题。"
            "包含具体可执行的步骤或代码示例。"
            "无明显事实错误或遗漏。"
            "格式清晰，便于阅读。"
        )
        try:
            from app.agent_runtime.core import _LLMClient
            from app.agent_runtime.schemas import AgentLLMConfig

            review_config = AgentLLMConfig(
                provider=getattr(self.config.llm, 'provider', 'deepseek'),
                model="deepseek-v4-flash",
                temperature=0.1,
                max_tokens=800,
                request_timeout=30.0,
            )
            if self.config.llm.api_key:
                review_config.api_key = self.config.llm.api_key
            if self.config.llm.base_url:
                review_config.base_url = self.config.llm.base_url

            client = _LLMClient(review_config)

            judge_prompt = (
                "你是严格的内容质量评审专家。请根据以下标准对内容进行评分。\n\n"
                f"【评判标准】\n{criteria}\n\n"
                f"【待评审内容】\n{content[:8000]}\n"
            )
            if task_context:
                judge_prompt += f"\n【任务背景】\n{task_context[:2000]}\n"

            judge_prompt += (
                "\n请以 JSON 格式返回评审结果（严格只返回 JSON，不要任何其他文字）：\n"
                '{"score": 0.75, "passed": true, "issues": ["问题1"], '
                '"suggestions": ["建议1"], "summary": "一句话总结"}\n\n'
                "评分规则：1.0完美 0.8良好 0.6基本满足 0.4大部分未满足 0.2完全不满足\n"
                "score >= 0.6 时 passed=true，否则 passed=false\n"
            )

            messages = [{"role": "user", "content": judge_prompt}]
            resp = await client.chat(messages=messages, tools=None, iteration=0)
            judge_text = getattr(resp, 'content', '') or (
                resp.get('content', '') if isinstance(resp, dict) else str(resp)
            )

            # 解析 JSON
            try:
                judge_clean = judge_text.strip()
                if judge_clean.startswith("```"):
                    lines = judge_clean.split("\n")
                    judge_clean = "\n".join(lines[1:-1] if lines[-1].strip() == "```" else lines[1:])
                result = json.loads(judge_clean)
            except json.JSONDecodeError:
                import re as _sr_re
                m = _sr_re.search(r'\{[^{}]*"score"\s*:\s*[\d.]+[^{}]*\}', judge_text, _sr_re.DOTALL)
                if m:
                    try:
                        result = json.loads(m.group())
                    except json.JSONDecodeError:
                        result = {"score": 0.5, "passed": False, "issues": ["无法解析评审结果"], "suggestions": [], "summary": ""}
                else:
                    result = {"score": 0.5, "passed": False, "issues": ["无法解析评审结果"], "suggestions": [], "summary": ""}

            score = float(result.get("score", 0.5))
            threshold = self.config.llm.self_review_threshold
            passed = score >= threshold

            return {
                "score": score,
                "passed": passed,
                "threshold": threshold,
                "issues": result.get("issues", []),
                "suggestions": result.get("suggestions", []),
                "summary": result.get("summary", ""),
            }
        except Exception as e:
            logger.warning("self_review 执行失败: %s", e)
            return {"score": 0.5, "passed": True, "issues": [], "suggestions": [], "error": str(e)}

    @staticmethod
    def _extract_tool_calls(response: Any) -> List[Dict[str, Any]]:
        """从 LLM 响应中提取工具调用列表。"""
        if response is None:
            return []
        # OpenAI SDK 格式
        if hasattr(response, "tool_calls") and response.tool_calls:
            result = []
            for tc in response.tool_calls:
                result.append({
                    "id": tc.id,
                    "type": tc.type,
                    "function": {
                        "name": tc.function.name,
                        "arguments": tc.function.arguments,
                    },
                })
            return result
        # 字典格式
        if isinstance(response, dict):
            tc_list = response.get("tool_calls") or []
            if tc_list:
                return tc_list
            # 检查 content 中是否嵌入了 DSML
            content = response.get("content") or ""
            if "invoke" in content or "function_call" in content:
                from app.services.llm_service import _parse_dsml_tool_invocations
                dsml = _parse_dsml_tool_invocations(content)
                if dsml:
                    return [
                        {
                            "id": f"dsml-{i}",
                            "type": "function",
                            "function": {
                                "name": inv["name"],
                                "arguments": json.dumps(inv["arguments"], ensure_ascii=False),
                            },
                        }
                        for i, inv in enumerate(dsml)
                    ]
        return []

    @staticmethod
    def _extract_content(response: Any) -> str:
        """从 LLM 响应中提取文本内容。"""
        if response is None:
            return ""
        if hasattr(response, "content"):
            return response.content or ""
        if isinstance(response, dict):
            return response.get("content") or ""
        return str(response)

    @staticmethod
    def _is_retryable(err_str: str) -> bool:
        """判断错误是否可重试。"""
        err_lower = err_str.lower()
        return any(kw in err_lower for kw in _RETRYABLE_ERRORS)


# LLM 缓存辅助
def _llm_cache_key(messages: list, model: str) -> str:
    import hashlib
    raw = json.dumps({"msgs": messages[-4:], "model": model}, sort_keys=True, ensure_ascii=False)
    return f"llm:{model}:{hashlib.sha256(raw.encode()).hexdigest()[:16]}"

async def _llm_cache_get(key: str) -> Optional[str]:
    try:
        from app.core.redis_client import get_redis_client
        redis = get_redis_client()
        if redis:
            return await redis.get(key)
    except Exception:
        pass
    return None

async def _llm_cache_set(key: str, value: str, ttl_ms: int):
    try:
        from app.core.redis_client import get_redis_client
        redis = get_redis_client()
        if redis:
            await redis.setex(key, max(1, int(ttl_ms / 1000)), value)
    except Exception:
        pass


class _LLMClient:
    """轻量 LLM 客户端包装，复用已有 LLMService 能力。"""

    def __init__(self, config: Any):
        from app.services.llm_service import llm_service
        self._service = llm_service
        self._config = config

    async def chat(
        self,
        messages: List[Dict[str, Any]],
        tools: Optional[List[Dict[str, Any]]] = None,
        iteration: int = 1,
        on_completion: Optional[Callable[[Dict[str, Any]], Any]] = None,
    ) -> Any:
        """调用 LLM，主模型失败时自动切换 fallback_llm 重试。"""
        from openai import AsyncOpenAI
        from app.core.config import settings

        # 优先从配置读取，其次从 settings（.env 加载），最后 os.environ
        api_key = self._config.api_key or settings.OPENAI_API_KEY or ""
        base_url = self._config.base_url or settings.OPENAI_BASE_URL or ""

        if not api_key or api_key == "your-openai-api-key":
            api_key = self._config.api_key or settings.DEEPSEEK_API_KEY or ""
            base_url = self._config.base_url or settings.DEEPSEEK_BASE_URL or "https://api.deepseek.com"

        if not api_key:
            raise ValueError("未配置 API Key")

        return await self._do_chat(
            api_key=api_key, base_url=base_url, model=self._config.model,
            messages=messages, tools=tools, iteration=iteration,
            on_completion=on_completion,
        )

    async def _do_chat(
        self,
        api_key: str,
        base_url: str,
        model: str,
        messages: List[Dict[str, Any]],
        tools: Optional[List[Dict[str, Any]]] = None,
        iteration: int = 1,
        on_completion: Optional[Callable[[Dict[str, Any]], Any]] = None,
        _is_fallback: bool = False,
    ) -> Any:
        from openai import AsyncOpenAI
        from app.core.config import settings

        client = AsyncOpenAI(api_key=api_key, base_url=base_url)

        kwargs: Dict[str, Any] = {
            "model": model,
            "messages": messages,
            "temperature": self._config.temperature,
            "timeout": self._config.request_timeout,
        }
        if self._config.max_tokens:
            kwargs["max_tokens"] = self._config.max_tokens
        if self._config.extra_body:
            kwargs["extra_body"] = self._config.extra_body
        if tools:
            # Normalize tool schemas to OpenAI format: custom tools from the
            # marketplace may be stored as {"name":..., "parameters":...}
            # or {"function":{...}} without the required "type": "function".
            normalized = []
            for t in tools:
                if isinstance(t, dict):
                    if t.get("type") == "function":
                        # Already in correct format: {"type":"function","function":{...}}
                        normalized.append(t)
                    elif "function" in t:
                        # Has function key but missing type: {"function":{...}}
                        normalized.append({"type": "function", "function": t["function"]})
                    else:
                        # Raw schema: {"name":..., "parameters":...}
                        normalized.append({"type": "function", "function": t})
                else:
                    normalized.append(t)
            kwargs["tools"] = normalized
            kwargs["tool_choice"] = "auto"

        # LLM 响应缓存（仅不用工具时缓存，避免复杂序列化）
        if self._config.cache_enabled and not tools and not _is_fallback:
            cache_key = _llm_cache_key(kwargs.get("messages", []), kwargs.get("model", ""))
            cached = await _llm_cache_get(cache_key)
            if cached is not None:
                logger.info("LLM 响应命中缓存: model=%s", kwargs.get("model"))
                class _CachedMsg:
                    content = cached
                    tool_calls = None
                return _CachedMsg()

        start_time = time.perf_counter()
        last_error = None
        try:
            response = await client.chat.completions.create(**kwargs)
        except Exception as e:
            last_error = e
            # 降级回退：主模型失败时尝试 fallback_llm
            fallback = self._config.fallback_llm
            if fallback and isinstance(fallback, dict) and not _is_fallback:
                fb_model = fallback.get("model")
                fb_api_key = fallback.get("api_key")
                fb_base_url = fallback.get("base_url")
                if fb_model and (fb_api_key or fb_base_url):
                    logger.warning(
                        "主模型 %s 调用失败，降级到 %s: %s",
                        model, fb_model, str(e)[:200],
                    )
                    # 先报告主模型失败
                    latency_ms = int((time.perf_counter() - start_time) * 1000)
                    if on_completion:
                        on_completion({
                            "model": model, "provider": self._config.provider,
                            "prompt_tokens": 0, "completion_tokens": 0, "total_tokens": 0,
                            "latency_ms": latency_ms, "iteration_number": iteration,
                            "status": "fallback", "error_message": str(e),
                        })
                    return await self._do_chat(
                        api_key=fb_api_key or api_key,
                        base_url=fb_base_url or base_url,
                        model=fb_model,
                        messages=messages, tools=tools,
                        iteration=iteration, on_completion=on_completion,
                        _is_fallback=True,
                    )
            raise

        latency_ms = int((time.perf_counter() - start_time) * 1000)
        message = response.choices[0].message

        # 缓存写入（仅不用工具时）
        if self._config.cache_enabled and not tools and message.content:
            ck = _llm_cache_key(kwargs.get("messages", []), kwargs.get("model", ""))
            await _llm_cache_set(ck, message.content, self._config.cache_ttl_ms)

        # 提取 token 用量
        usage = getattr(response, "usage", None)
        prompt_tokens = usage.prompt_tokens if usage else 0
        completion_tokens = usage.completion_tokens if usage else 0
        total_tokens = usage.total_tokens if usage else 0

        # 调用完成回调
        if on_completion:
            on_completion({
                "model": model,
                "provider": self._config.provider,
                "prompt_tokens": prompt_tokens or 0,
                "completion_tokens": completion_tokens or 0,
                "total_tokens": total_tokens or 0,
                "latency_ms": latency_ms,
                "iteration_number": iteration,
                "status": "success",
            })

        return message