feat: 添加swarms团队编排功能并优化agent委派系统

- 引入AgentTeamOrchestrator支持多agent协同任务执行
- 增加第三方swarms库依赖并配置git协议替换以改善包管理
- 扩展DelegationManager支持团队任务调度和进度跟踪
- 实现中文bigram分词算法提升中文任务检索准确性
- 调整A2AClient和DelegationManager超时时间从30秒增至600秒
- 优化AgentRunResult状态判断逻辑增加有意义摘要检测
- 修改Dockerfile配置npm仓库镜像地址和git协议映射
- 更新CLI命令行接口支持网关端口配置传递
- 调整提供者超时配置机制增强请求稳定性
- 移除过时的support_group字段简化agent描述符结构
- 增强错误处理和进度事件报告机制改进用户体验

app-instance/backend/nanobot/providers/custom_provider.py

@@ -12,10 +12,20 @@ from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
 
 class CustomProvider(LLMProvider):
 
-    def __init__(self, api_key: str = "no-key", api_base: str = "http://localhost:8000/v1", default_model: str = "default"):
-        super().__init__(api_key, api_base)
+    def __init__(
+        self,
+        api_key: str = "no-key",
+        api_base: str = "http://localhost:8000/v1",
+        default_model: str = "default",
+        request_timeout_seconds: float | None = None,
+    ):
+        super().__init__(api_key, api_base, request_timeout_seconds=request_timeout_seconds)
         self.default_model = default_model
-        self._client = AsyncOpenAI(api_key=api_key, base_url=api_base)
+        self._client = AsyncOpenAI(
+            api_key=api_key,
+            base_url=api_base,
+            timeout=self.request_timeout_seconds,
+        )
 
     async def chat(self, messages: list[dict[str, Any]], tools: list[dict[str, Any]] | None = None,
                    model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7) -> LLMResponse:
@@ -49,4 +59,3 @@ class CustomProvider(LLMProvider):
 
     def get_default_model(self) -> str:
         return self.default_model
-