mirror of
https://github.com/zhenxun-org/zhenxun_bot.git
synced 2026-10-20 03:30:11 +08:00
✨ feat!(llm): 重构并升级大语言模型服务为全新 AI 智能体框架 (#2146)
* ✨ feat!(llm): 重构并升级大语言模型服务为全新 AI 智能体框架 - 【重构】将原 services/llm 重构并迁移至全新的 services/ai 架构，提供向下兼容垫片 - 【新增】引入 Agent、Team、Workflow 三大智能体与工作流编排范式 - 【新增】引入基于 RAG 的长期向量记忆与中期槽位记忆系统 - 【新增】引入基于 Docker 的安全代码执行沙箱环境 - 【新增】支持 MCP 协议，允许动态管理和调用 MCP 服务 - 【新增】引入输入输出安全合规护栏与自愈反思机制 - 【优化】重构并优化多厂商 API 适配器 (Gemini, OpenAI, DeepSeek, GLM 等) - 【优化】优化日志脱敏与 Token 预估机制 - 【移除】移除旧版 llm default 和 llm reset-key 命令，新增 llm mcp 管理命令 * 🔧 chore(deps): 更新项目依赖与配置 - 添加 mcp、jieba 和 aiodocker 依赖到配置文件及 requirements.txt - 在 pyright 配置中设置 reportMissingImports 为 none - 调整 .gitignore 中 resources 目录的忽略规则 * ♻️ refactor(tools): 重构工具终止机制并清理知识库日志输出 - 统一使用 `context.state["__end_run__"]` 替代 `EndRunResult` 控制任务结束 - 移除文件系统和向量知识库检索工具中 `ToolResult` 的 `.with_log` 调用 - 调整指令处理器（Directive）的返回值为 `tool_res.output` - 修复部分类型检查警告并优化联合类型判断语法 * ♻️ refactor(tools): 重构工具副作用指令与控制流熔断机制 - 引入 `DirectivePayload` 及 `ToolResult` 的子类以结构化表达工具副作用 - 移除通过 `context.state` 传递魔术变量的隐式控制流设计 - 重构 `DirectiveManager` 处理器接口，直接在处理器中修改 `AgentState` 并构建 `AgentRunResult` - 在 `StandardAgentExecutor` 中统一通过 `directive_manager` 调度工具返回的副作用指令 - 补全 `MessageBuilder` 中部分核心方法的文档注释 * 🐛 fix(sandbox): 修复 Docker 沙箱容器状态检测与会话清理逻辑 -【修复】修正 `is_alive` 中直接读取私有属性的问题，改用 `show()` 返回值 -【修复】解决 `execute_code` 中缓存的执行器与当前会话不一致的问题 -【优化】在清理工作区前增加容器存活检测，避免向已死容器发送请求 -【优化】创建容器时增加运行状态校验，若已停止则自动从缓存中移除并重建 -【优化】优化容器销毁和清理逻辑，静默处理容器不存在 (404) 的异常 * 📝 docs(core): 补充核心模块初始化方法的文档注释 * 🚨 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>
This commit is contained in:
Rumio
co-authored by
webjoin111
pre-commit-ci[bot]
webjoin111
pre-commit-ci[bot]
parent
bdc1374848
commit
80fc5b86a7
@@ -0,0 +1,162 @@
|
||||
from abc import ABC, abstractmethod
|
||||
from typing import Any
|
||||
|
||||
from zhenxun.services.ai.core.exceptions import (
|
||||
ConfigurationException,
|
||||
LLMException,
|
||||
UpstreamServerException,
|
||||
)
|
||||
from zhenxun.services.ai.core.options import GenerationConfig
|
||||
from zhenxun.services.ai.llm.manager import (
|
||||
_get_group_name,
|
||||
_resolve_model_group,
|
||||
get_default_model,
|
||||
get_model_instance,
|
||||
list_available_models,
|
||||
)
|
||||
from zhenxun.services.ai.llm.system.capabilities import get_model_capabilities
|
||||
from zhenxun.services.ai.llm.system.network import health_manager
|
||||
from zhenxun.services.log import logger
|
||||
|
||||
|
||||
class BaseModelRouter(ABC):
|
||||
@abstractmethod
|
||||
async def route(
|
||||
self,
|
||||
request: Any,
|
||||
model_names: list[str],
|
||||
task: str,
|
||||
override_config: GenerationConfig | dict | None,
|
||||
cancellation_token: Any | None,
|
||||
) -> Any:
|
||||
pass
|
||||
|
||||
|
||||
class FallbackRouter(BaseModelRouter):
|
||||
"""主备故障转移路由器"""
|
||||
|
||||
async def route(
|
||||
self,
|
||||
request: Any,
|
||||
model_names: list[str],
|
||||
task: str,
|
||||
override_config: GenerationConfig | dict | None,
|
||||
cancellation_token: Any | None,
|
||||
) -> Any:
|
||||
errors = []
|
||||
all_nodes_bypassed = True
|
||||
|
||||
is_routed_call = len(model_names) > 1
|
||||
request.extra["_is_routed_call"] = is_routed_call
|
||||
start_idx = request.extra.get("_working_route_index", 0)
|
||||
indices_to_try = list(range(start_idx, len(model_names))) + list(
|
||||
range(0, start_idx)
|
||||
)
|
||||
|
||||
for idx in indices_to_try:
|
||||
m_name = model_names[idx]
|
||||
|
||||
if not health_manager.is_route_healthy(m_name, strict_mode=is_routed_call):
|
||||
logger.debug(f"👉 [Orchestrator] 节点 '{m_name}' 熔断中，已跳过")
|
||||
errors.append(f"{m_name}(熔断中)")
|
||||
continue
|
||||
|
||||
caps = get_model_capabilities(m_name)
|
||||
if not caps.supports_task(task):
|
||||
errors.append(f"{m_name}(Unsupported Task: {task})")
|
||||
continue
|
||||
|
||||
all_nodes_bypassed = False
|
||||
try:
|
||||
if len(model_names) > 1:
|
||||
if idx != start_idx:
|
||||
logger.debug(f"🔄 [Orchestrator] 切换至备用节点: '{m_name}'...")
|
||||
|
||||
async with await get_model_instance(
|
||||
m_name, override_config, task=task
|
||||
) as instance:
|
||||
response = await instance.invoke(request, cancellation_token)
|
||||
request.extra["_working_route_index"] = idx
|
||||
if run_ctx := request.extra.get("run_context"):
|
||||
run_ctx.state["_working_route_index"] = idx
|
||||
return response
|
||||
except LLMException as e:
|
||||
if not e.should_failover:
|
||||
logger.warning(
|
||||
f"🚫 [Orchestrator] 节点 '{m_name}' "
|
||||
f"返回不可恢复错误 ({e.__class__.__name__})，停止故障转移。"
|
||||
)
|
||||
raise e
|
||||
logger.warning(
|
||||
f"⚠️ [Orchestrator] 节点 '{m_name}' "
|
||||
f"错误 ({e.__class__.__name__})，触发故障转移..."
|
||||
)
|
||||
errors.append(f"{m_name}({e.__class__.__name__})")
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
f"⚠️ [Orchestrator] 节点 '{m_name}' 发生未知异常，触发故障转移: {e}"
|
||||
)
|
||||
errors.append(f"{m_name}(Error)")
|
||||
|
||||
if all_nodes_bypassed and len(model_names) > 1:
|
||||
fallback_model = health_manager.get_best_fallback_route(model_names)
|
||||
logger.warning(
|
||||
f"⚠️ [Orchestrator] 路由组所有节点均已宕机！"
|
||||
f"强制放行 '{fallback_model}' 探活..."
|
||||
)
|
||||
try:
|
||||
async with await get_model_instance(
|
||||
fallback_model, override_config, task=task
|
||||
) as instance:
|
||||
return await instance.invoke(request, cancellation_token)
|
||||
except Exception as e:
|
||||
errors.append(f"{fallback_model}(保底探活彻底失败:{e})")
|
||||
|
||||
err_msg = f"所有路由尝试均已失败: {', '.join(errors)}"
|
||||
raise UpstreamServerException(err_msg)
|
||||
|
||||
|
||||
class BaseOrchestrator:
|
||||
"""顶层大模型请求编排器，负责组解析与路由策略委派。"""
|
||||
|
||||
def __init__(self, router: BaseModelRouter | None = None):
|
||||
self.router = router or FallbackRouter()
|
||||
|
||||
async def invoke(
|
||||
self,
|
||||
request: Any,
|
||||
model_name: str | None = None,
|
||||
task: str = "chat",
|
||||
override_config: GenerationConfig | dict | None = None,
|
||||
cancellation_token: Any | None = None,
|
||||
) -> Any:
|
||||
resolved_model_name = model_name
|
||||
if resolved_model_name is None:
|
||||
resolved_model_name = get_default_model(task)
|
||||
if resolved_model_name is None:
|
||||
available_models = list_available_models()
|
||||
if not available_models:
|
||||
raise ConfigurationException("未配置任何AI模型")
|
||||
resolved_model_name = available_models[0]["full_name"]
|
||||
logger.warning(f"未指定模型，使用第一个可用模型: {resolved_model_name}")
|
||||
|
||||
group_name = _get_group_name(resolved_model_name)
|
||||
if group_name is not None:
|
||||
model_names = _resolve_model_group(group_name)
|
||||
if not model_names:
|
||||
raise ConfigurationException(
|
||||
f"模型路由组 '{group_name}' 解析失败或为空，请检查配置。"
|
||||
)
|
||||
else:
|
||||
model_names = [resolved_model_name]
|
||||
|
||||
return await self.router.route(
|
||||
request=request,
|
||||
model_names=model_names,
|
||||
task=task,
|
||||
override_config=override_config,
|
||||
cancellation_token=cancellation_token,
|
||||
)
|
||||
|
||||
|
||||
LLMOrchestrator = BaseOrchestrator()
|
||||
Reference in New Issue
Block a user