Files
zhenxun_bot/zhenxun/services/ai/flow/team/runner.py
T
922d092650 ♻️ refactor(core): 重构 AI 能力与定时任务调度系统 (#2148)
* ♻️ refactor(core): 重构 AI 能力与定时任务调度系统

- 【AI 能力与工具】重构 Capability 注册与管理机制,引入 CapabilityManager 统一管理
- 移除全局能力注册表,改用声明式装饰器 `@capability` 进行解耦注册
- 重构工具解析器链,使用统一的 BaseToolResolver 代替原有的多个特定解析器
- 增强工具查询过滤,支持通配符匹配、工具箱过滤和排除标签
- 【定时任务调度】重构定时任务管理器,引入 SchedulerRegistry 统一管理任务元数据
- 引入 JobConfig 聚合定时任务配置,支持用户维度的定时任务调度
- 重构执行分发器,支持并发限制、串行间隔和随机延迟打散
- 【运行上下文】引入 ScheduledDeps 以支持后台和定时任务环境下的依赖注入
- 优化 RunContext,支持从定时任务上下文快速构造,并提供 emit 辅助方法
- 【日志与监控】引入 AILoggerProxy,实现 AI 各模块的专属日志输出
- 将各模块的全局 logger 替换为对应的模块专属日志代理
- 【其他优化】修复 Pydantic V1 兼容层中 model_validator 的装饰器兼容性问题
- 在非交互式环境(如定时任务)中自动隐藏 HITL 交互工具以节省 Token

* ♻️ refactor(core): 优化内部导入路径并提升 Pydantic 兼容性

- 【重构】将 `services/ai` 模块内的绝对导入重构为相对导入,优化包结构
- 【重构】移除不必要的 `if TYPE_CHECKING` 保护,通过 `from __future__ import annotations` 直接导入类型
- 【清理】清理 `core/messages/types.py` 中未使用的 `AssistantContentUnion` 等联合类型定义
- 【优化】在 `utils/pydantic_compat.py` 中新增 `model_rebuild` 兼容函数,统一 Pydantic V1/V2 的模型重建逻辑
- 【优化】将部分函数内部的延迟导入提升至模块顶部,规范代码结构

* ♻️ refactor(imports): 优化导入路径为相对导入并清理冗余导入

- 【重构】将 AI 服务相关模块中的绝对导入路径修改为相对导入,提升模块内聚性与可移植性
- 【清理】移除多处函数内部或类方法中未使用的冗余导入,避免循环引用和资源浪费
- 【格式化】微调部分工具装饰器和返回语句的格式与尾随逗号

* 🚨 auto fix by pre-commit hooks

---------

Co-authored-by: webjoin111 <455457521@qq.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2026-07-10 09:14:06 +08:00

238 lines
8.9 KiB
Python

import asyncio
from collections.abc import AsyncGenerator
from typing import Any
from zhenxun.services.ai.core.exceptions import (
AbortException,
ControlFlowExit,
LLMException,
)
from zhenxun.services.ai.core.messages import UsageInfo
from zhenxun.services.ai.flow.agent.models import AgentConfig
from zhenxun.services.ai.run import AgentRunResult, RunContext
from zhenxun.services.ai.run.models import AgentRunEnd
from zhenxun.services.ai.utils.logger import log_team as logger
from zhenxun.utils.pydantic_compat import model_construct
from .capabilities import TeamRoutingCapability
from .models import (
CallAction,
ConcurrentCallAction,
FinishAction,
)
from .strategy import BaseTeamStrategy, RouteStrategy
class TeamRunner:
"""
多智能体团队核心执行引擎。
"""
def __init__(self, team: Any, strategy: BaseTeamStrategy):
self.team = team
self.strategy = strategy
async def _execute_call_action_to_queue(
self,
index: int,
action: CallAction,
context: RunContext,
session_id: str,
queue: asyncio.Queue,
):
"""
辅助方法:执行单一 Agent 任务,
并将内部产生的 UI 事件与最终结果通过队列透传回主线程
"""
if isinstance(action.agent, str):
target_agent = next(
(m for m in self.team.members if m.name == action.agent), None
)
if not target_agent:
logger.error(f"❌ 找不到团队成员: {action.agent}")
await queue.put(
(
"result",
(
action.agent,
AgentRunResult(
output=f"Error: {action.agent} not found",
usage=UsageInfo(),
),
),
)
)
return
else:
target_agent = action.agent
sub_context = context.clone_for_member(target_agent.name)
sub_context.capabilities = list(sub_context.capabilities)
if isinstance(self.strategy, RouteStrategy):
routing_cap = TeamRoutingCapability(
team_name=self.team.name,
members=self.team.members,
state_flow=getattr(self.strategy, "state_flow", None),
max_handoffs=getattr(self.strategy, "max_handoffs", 3),
)
sub_context.capabilities.append(routing_cap)
logger.debug(f"🚀 **专员 👨💼`{target_agent.name}`** 开始执行子任务...")
agent_res = None
try:
async with target_agent.run_stream(
prompt=action.task,
context=sub_context,
config=AgentConfig(message_history=action.history),
**(action.kwargs or {}),
) as stream_result:
async for event in stream_result.stream_events():
if isinstance(event, AgentRunEnd):
agent_res = event.result
else:
await queue.put(("yield_event", event))
except ControlFlowExit as cfe:
if isinstance(cfe, AbortException):
await queue.put(("control_flow_error", cfe))
return
else:
logger.debug(
f"Agent {target_agent.name} 触发局部控制流: "
f"{type(cfe).__name__} - {cfe}"
)
agent_res = AgentRunResult(output=str(cfe), usage=UsageInfo())
except Exception as e:
logger.error(f"Agent {target_agent.name} 执行崩溃: {e}")
if isinstance(e, LLMException):
abort_msg = getattr(e, "user_friendly_message", str(e))
display_msg = (
f"❌ 智能体 {target_agent.name} 执行发生致命故障: {abort_msg}"
)
abort_err = AbortException(
reason=str(e),
display=display_msg,
)
await queue.put(("control_flow_error", abort_err))
return
agent_res = AgentRunResult(output=f"Error: {e}", usage=UsageInfo())
if agent_res and agent_res.handoff:
target_name = agent_res.handoff.target
reason = agent_res.handoff.reason
logger.info(
f"🛣️ **路由决策**: 委派给专员 👨💼`{target_name}` (理由: {reason})"
)
if not agent_res:
agent_res = AgentRunResult(
output="Error: No result returned", usage=UsageInfo()
)
logger.debug(f"✅ **专员 👨💼`{target_agent.name}`** 完成任务!")
await queue.put(("result", index, target_agent.name, agent_res))
async def run_stream(
self, prompt: Any, context: RunContext, **kwargs: Any
) -> AsyncGenerator[Any, None]:
session_id = context.session_id or "default_team_session"
task_desc = getattr(prompt, "description", str(prompt))
logger.info(f"🤝 **团队 [{self.team.name}] 开始协作**: `{task_desc}`")
plan_gen = self.strategy.generate_plan(self.team, prompt, context, **kwargs)
send_value = None
final_result = None
cumulative_usage = UsageInfo()
try:
while True:
try:
action = await plan_gen.asend(send_value)
except StopAsyncIteration:
break
if isinstance(action, CallAction):
queue = asyncio.Queue()
task = asyncio.create_task(
self._execute_call_action_to_queue(
0, action, context, session_id, queue
)
)
try:
while True:
msg_type, *payload = await queue.get()
if msg_type == "yield_event":
yield payload[0]
elif msg_type == "control_flow_error":
raise payload[0]
elif msg_type == "result":
idx, agent_name, agent_res = payload
send_value = agent_res
cumulative_usage += agent_res.usage
break
finally:
if not task.done():
task.cancel()
elif isinstance(action, ConcurrentCallAction):
queue = asyncio.Queue()
tasks = []
for i, act in enumerate(action.actions):
tasks.append(
asyncio.create_task(
self._execute_call_action_to_queue(
i, act, context, session_id, queue
)
)
)
results_dict = {}
try:
while len(results_dict) < len(action.actions):
msg_type, *payload = await queue.get()
if msg_type == "yield_event":
yield payload[0]
elif msg_type == "control_flow_error":
for t in tasks:
t.cancel()
raise payload[0]
elif msg_type == "result":
idx, agent_name, agent_res = payload
results_dict[idx] = (agent_name, agent_res)
cumulative_usage += agent_res.usage
send_value = [
results_dict[i] for i in range(len(action.actions))
]
finally:
for task in tasks:
if not task.done():
task.cancel()
elif isinstance(action, FinishAction):
final_result = action.result
break
else:
raise ValueError(f"TeamRunner 遇到了未知的动作类型: {type(action)}")
except Exception as e:
raise e
logger.info(f"🏁 **团队 [{self.team.name}]** 协作圆满结束!")
if not isinstance(final_result, AgentRunResult):
final_result = model_construct(
AgentRunResult, output=final_result, usage=cumulative_usage
)
else:
final_result.usage += cumulative_usage
yield AgentRunEnd(result=final_result)