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/openai_codex_provider.py

@@ -20,8 +20,12 @@ DEFAULT_ORIGINATOR = "nanobot"
 class OpenAICodexProvider(LLMProvider):
     """Use Codex OAuth to call the Responses API."""
 
-    def __init__(self, default_model: str = "openai-codex/gpt-5.1-codex"):
-        super().__init__(api_key=None, api_base=None)
+    def __init__(
+        self,
+        default_model: str = "openai-codex/gpt-5.1-codex",
+        request_timeout_seconds: float | None = None,
+    ):
+        super().__init__(api_key=None, api_base=None, request_timeout_seconds=request_timeout_seconds)
         self.default_model = default_model
 
     async def chat(
@@ -58,12 +62,24 @@ class OpenAICodexProvider(LLMProvider):
 
         try:
             try:
-                content, tool_calls, finish_reason = await _request_codex(url, headers, body, verify=True)
+                content, tool_calls, finish_reason = await _request_codex(
+                    url,
+                    headers,
+                    body,
+                    verify=True,
+                    timeout_seconds=self.request_timeout_seconds or 600.0,
+                )
             except Exception as e:
                 if "CERTIFICATE_VERIFY_FAILED" not in str(e):
                     raise
                 logger.warning("SSL certificate verification failed for Codex API; retrying with verify=False")
-                content, tool_calls, finish_reason = await _request_codex(url, headers, body, verify=False)
+                content, tool_calls, finish_reason = await _request_codex(
+                    url,
+                    headers,
+                    body,
+                    verify=False,
+                    timeout_seconds=self.request_timeout_seconds or 600.0,
+                )
             return LLMResponse(
                 content=content,
                 tool_calls=tool_calls,
@@ -102,8 +118,9 @@ async def _request_codex(
     headers: dict[str, str],
     body: dict[str, Any],
     verify: bool,
+    timeout_seconds: float,
 ) -> tuple[str, list[ToolCallRequest], str]:
-    async with httpx.AsyncClient(timeout=60.0, verify=verify) as client:
+    async with httpx.AsyncClient(timeout=timeout_seconds, verify=verify) as client:
         async with client.stream("POST", url, headers=headers, json=body) as response:
             if response.status_code != 200:
                 text = await response.aread()