feat(app-instance): 集成Beaver后端并更新配置管理

集成新的Beaver后端服务到应用实例中，替换原有的nanobot实现。

主要变更包括：
- 在Dockerfile和环境配置中添加Beaver相关路径和配置变量
- 更新工作目录结构从.nanobot到.beaver
- 实现Beaver引擎加载器，支持配置文件加载和工具组装
- 添加内置工具如ListDirectoryTool、ReadFileTool、SearchFilesTool
- 更新消息处理流程，支持通道适配器和网关模式
- 重构技能系统，支持显式工具提示和嵌入式检索
- 改进错误处理和生命周期管理

此变更使应用实例能够使用统一的Beaver后端进行AI代理运行时管理。

app-instance/backend/beaver/engine/providers/litellm.py

@@ -8,7 +8,7 @@ import os
 from typing import Any
 
 from .base import LLMProvider, LLMResponse, ToolCallRequest
-from .registry import find_by_model, find_gateway
+from .registry import find_by_model, find_by_name, find_gateway
 from .runtime import ProviderRoutingConfig
 
 try:  # pragma: no cover - optional dependency
@@ -58,7 +58,11 @@ class LiteLLMProvider(LLMProvider):
 
         if not api_key:
             return {}
-        spec = self._gateway or find_by_model(model)
+        spec = self._gateway
+        if spec is None and self.provider_name:
+            spec = find_by_name(self.provider_name)
+        if spec is None:
+            spec = find_by_model(model)
         if spec is None or not spec.env_key:
             return {}
         overrides: dict[str, str] = {spec.env_key: api_key}
@@ -97,6 +101,15 @@ class LiteLLMProvider(LLMProvider):
             if prefix and not resolved.startswith(f"{prefix}/"):
                 resolved = f"{prefix}/{resolved}"
             return resolved
+        if self.provider_name:
+            spec = find_by_name(self.provider_name)
+            if spec is not None and not spec.is_gateway and not spec.is_local:
+                resolved = model
+                if spec.litellm_prefix and not any(resolved.startswith(prefix) for prefix in spec.skip_prefixes):
+                    resolved = f"{spec.litellm_prefix}/{resolved}"
+                elif spec.name == "openai" and "/" not in resolved:
+                    resolved = f"openai/{resolved}"
+                return resolved
         spec = find_by_model(model)
         if spec and spec.litellm_prefix:
             if not any(model.startswith(prefix) for prefix in spec.skip_prefixes):