mirror of
https://github.com/zhenxun-org/zhenxun_bot.git
synced 2026-10-05 03:39:59 +08:00
* ♻️ refactor(ai): 重构 AI 服务模块并完善文档注释 - 【重构】统一清理并优化所有 AI 服务模块文件的导入语句,将其移至文件顶部 - 【重构】重构 `hooks.py` 中的 `Hooks` 派发逻辑,使用通用管道函数消除重复代码,并引入 `HookPoint` 描述符 - 【重构】重构工具装饰器实现,新增 `toolkit` 类装饰器,优化 `BaseToolkit` 配置合并与前缀处理 - 【功能】Docker 沙箱容器创建时支持自动注入系统代理环境变量并配置 `ExtraHosts` - 【功能】Jupyter 服务启动前自动清理旧进程并初始化临时目录权限 - 【修复】优化 Pydantic 结构化输出校验失败时的错误信息提取,提供更详细的字段级错误反馈 - 【修复】在 `api.py` 中避免将 `ModelRetry` 和 `ControlFlowExit` 异常错误地包装为 `LLMException` - 【文档】为 AI 服务、沙箱、工具链、工作流等核心模块补充完整的 Docstring 和类型注释 * 📝 docs(ai): 补全核心模块文档注释并清理冗余代码 - 补全 `run/context`、`run/hooks` 和 `tools/engine/registry` 中类与方法的中文文档注释 - 清理 `tools/providers/builtin/sandbox` 中未使用的 `PythonPluginProtocol` 协议及相关导入 - 规范化部分代码的格式与尾随逗号 * ♻️ refactor!(flow): 重构 Task 为 AgentTask 并优化工作流元数据定义 - 【Breaking Change】将 `Task` 重命名为 `AgentTask` 以避免命名冲突 - 更新 Agent、Team、Workflow 等模块中的类型声明与相关逻辑 - 引入 `AutoNodeMeta` 强类型元数据,替换工作流装饰器中的裸字典定义 - 将 `StepMeta`、`ConditionMeta` 和 `RouterMeta` 统一移动至 `types.py` - 优化 `RunnableNode` 对上游 `AgentTask` 的处理与拼接逻辑 - 调整团队协作策略中 `FinishAction` 的返回值为完整结果对象 * ♻️ refactor(workflow): 移除人工确认机制并重构错误策略 - 移除工作流节点的人工确认(HITL)与挂起继续机制 - 删除 `auto` 自动化工作流及相关装饰器文件 - 将错误处理策略类从 `types.py` 拆分并移动到新文件 `policies.py` - 优化节点执行失败时的异常信息格式化输出 - 移除 `WorkflowRunResult` 和 `StepOutput` 中与挂起相关的状态字段 * 🚨 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>
225 lines
7.9 KiB
Python
225 lines
7.9 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.flow.workflow.policies import (
|
|
AbortPolicy,
|
|
BaseFailurePolicy,
|
|
PolicyAction,
|
|
)
|
|
from zhenxun.services.ai.flow.workflow.types import (
|
|
StepInput,
|
|
StepOutput,
|
|
StepType,
|
|
)
|
|
from zhenxun.services.ai.run import RunContext
|
|
from zhenxun.services.log import logger
|
|
|
|
|
|
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
|