mirror of
https://github.com/zhenxun-org/zhenxun_bot.git
synced 2026-09-29 00:32:06 +08:00
* ♻️ 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>
226 lines
7.8 KiB
Python
226 lines
7.8 KiB
Python
from abc import ABC, abstractmethod
|
|
import asyncio
|
|
from collections.abc import AsyncIterator
|
|
from typing import Any
|
|
|
|
from zhenxun.services.ai.core.exceptions import (
|
|
AbortException,
|
|
ControlFlowExit,
|
|
ToolFatalError,
|
|
)
|
|
from zhenxun.services.ai.run import RunContext
|
|
from zhenxun.services.ai.utils.logger import log_flow as logger
|
|
|
|
from .policies import (
|
|
AbortPolicy,
|
|
BaseFailurePolicy,
|
|
PolicyAction,
|
|
)
|
|
from .types import (
|
|
StepInput,
|
|
StepOutput,
|
|
StepType,
|
|
)
|
|
|
|
|
|
class BaseNode(ABC):
|
|
"""工作流节点统一抽象基类"""
|
|
|
|
def __init__(
|
|
self,
|
|
name: str,
|
|
failure_policy: BaseFailurePolicy | None = None,
|
|
):
|
|
"""
|
|
初始化工作流节点基类。
|
|
|
|
参数:
|
|
name: 节点的唯一名称标识。
|
|
failure_policy: 该节点执行失败时的错误恢复与自愈策略,
|
|
默认使用中断策略 (AbortPolicy)。
|
|
"""
|
|
self.name = name
|
|
self.failure_policy = failure_policy or AbortPolicy()
|
|
|
|
@property
|
|
@abstractmethod
|
|
def node_type(self) -> StepType:
|
|
"""节点类型标识 (供子类实现)"""
|
|
pass
|
|
|
|
async def _handle_execution_failure(
|
|
self, e: BaseException, step_input: StepInput, context: RunContext, attempt: int
|
|
) -> tuple[str, StepOutput | None, StepInput | None, Any]:
|
|
"""
|
|
解析执行异常并应用容错策略
|
|
"""
|
|
if isinstance(e, asyncio.CancelledError):
|
|
raise e
|
|
|
|
if isinstance(e, ControlFlowExit):
|
|
logger.info(
|
|
f"⏭️ [控制流拦截] Node '{self.name}' 触发中断信号: "
|
|
f"{type(e).__name__} - {e}"
|
|
)
|
|
content = str(e)
|
|
if getattr(e, "display_content", None):
|
|
content = str(getattr(e, "display_content"))
|
|
elif getattr(e, "display", None):
|
|
content = str(getattr(e, "display"))
|
|
elif getattr(e, "result_output", None):
|
|
content = str(getattr(e, "result_output"))
|
|
|
|
output = StepOutput(
|
|
step_name=self.name,
|
|
step_type=self.node_type,
|
|
content=content,
|
|
success=False,
|
|
stop=True,
|
|
error=f"{type(e).__name__}: {e}"
|
|
if isinstance(e, AbortException | ToolFatalError)
|
|
else None,
|
|
)
|
|
return "break", output, None, None
|
|
|
|
logger.warning(f"Node '{self.name}' 执行发生异常: {e}")
|
|
policy_result = await self.failure_policy.handle_failure(
|
|
self, e, step_input, context
|
|
)
|
|
|
|
if policy_result.action == PolicyAction.RETRY:
|
|
if policy_result.delay > 0:
|
|
await asyncio.sleep(policy_result.delay)
|
|
new_input = policy_result.new_input or step_input
|
|
logger.debug(f" 🔄 [节点重试] `{self.name}` 进行第 {attempt} 次重试...")
|
|
return "continue", None, new_input, None
|
|
|
|
elif policy_result.action == PolicyAction.FALLBACK:
|
|
fallback_node = policy_result.fallback_node
|
|
fallback_name = getattr(fallback_node, "name", "FallbackNode")
|
|
logger.info(
|
|
f"🔀 节点 {self.name} 执行失败,触发降级路由至: {fallback_name}"
|
|
)
|
|
return "fallback", None, None, fallback_node
|
|
|
|
elif policy_result.action == PolicyAction.CONTINUE:
|
|
logger.warning(f"Node '{self.name}' 执行异常,已被策略自动跳过: {e}")
|
|
output = StepOutput(
|
|
step_name=self.name,
|
|
step_type=self.node_type,
|
|
content=f"节点执行失败,已通过策略自动跳过: {type(e).__name__} - {e}",
|
|
success=False,
|
|
stop=False,
|
|
error=f"{type(e).__name__}: {e}",
|
|
)
|
|
return "break", output, None, None
|
|
else:
|
|
logger.error(f"Node '{self.name}' 执行崩溃,已被策略中断执行流: {e}")
|
|
output = StepOutput(
|
|
step_name=self.name,
|
|
step_type=self.node_type,
|
|
content=f"执行崩溃: {type(e).__name__} - {e}",
|
|
success=False,
|
|
stop=True,
|
|
error=f"{type(e).__name__}: {e}",
|
|
)
|
|
return "break", output, None, None
|
|
|
|
@abstractmethod
|
|
async def run_stream(
|
|
self, step_input: StepInput, context: RunContext
|
|
) -> AsyncIterator[Any]:
|
|
"""子类必须实现的核心流式执行逻辑"""
|
|
yield None
|
|
|
|
async def _forward_stream(
|
|
self, stream: AsyncIterator[Any], output_box: list[StepOutput]
|
|
) -> AsyncIterator[Any]:
|
|
"""辅助方法:转发内部流事件,并将最终的 StepOutput 拦截放入 output_box 列表中"""
|
|
async for event in stream:
|
|
if isinstance(event, StepOutput):
|
|
output_box.append(event)
|
|
else:
|
|
yield event
|
|
|
|
async def aexecute(self, step_input: StepInput, context: RunContext) -> StepOutput:
|
|
"""非流式执行(聚合流并返回最终结果),子类无需重写"""
|
|
output = None
|
|
async for event in self.aexecute_stream(step_input, context):
|
|
if isinstance(event, StepOutput):
|
|
output = event
|
|
|
|
if output is None:
|
|
output = StepOutput(
|
|
step_name=self.name,
|
|
step_type=self.node_type,
|
|
content="节点未产生有效输出",
|
|
success=False,
|
|
)
|
|
return output
|
|
|
|
async def aexecute_stream(
|
|
self, step_input: StepInput, context: RunContext
|
|
) -> AsyncIterator[Any]:
|
|
"""标准化模板方法:处理缓存快进、授权挂起、异常熔断与生命周期事件分发"""
|
|
logger.debug(f" ⚙️ [节点] `{self.name}` 开始执行...")
|
|
|
|
cached_out = context.state.get("__completed_steps__", {}).get(self.name)
|
|
if cached_out and cached_out.success:
|
|
logger.debug(f"⏭️ 快进跳过已完成节点: {self.name}")
|
|
|
|
yield cached_out
|
|
return
|
|
|
|
current_input = step_input
|
|
attempt = 1
|
|
|
|
while True:
|
|
output = None
|
|
try:
|
|
async for event in self.run_stream(current_input, context):
|
|
if isinstance(event, StepOutput):
|
|
output = event
|
|
output.step_name = self.name
|
|
output.step_type = self.node_type
|
|
else:
|
|
yield event
|
|
|
|
if output is None:
|
|
output = StepOutput(
|
|
step_name=self.name,
|
|
step_type=self.node_type,
|
|
content="执行完毕,无数据返回",
|
|
success=True,
|
|
)
|
|
|
|
context.upstream_results[self.name] = output.content
|
|
|
|
break
|
|
|
|
except BaseException as e:
|
|
(
|
|
action_cmd,
|
|
output,
|
|
new_input,
|
|
fallback_node,
|
|
) = await self._handle_execution_failure(
|
|
e, current_input, context, attempt
|
|
)
|
|
if action_cmd == "continue":
|
|
current_input = (
|
|
new_input if new_input is not None else current_input
|
|
)
|
|
attempt += 1
|
|
continue
|
|
elif action_cmd == "fallback" and fallback_node:
|
|
async for evt in fallback_node.aexecute_stream(
|
|
current_input, context
|
|
):
|
|
if isinstance(evt, StepOutput):
|
|
output = evt
|
|
else:
|
|
yield evt
|
|
break
|
|
|
|
yield output
|