实现 AI Core 与 Agent Core 基础功能

- 更新 README 描述从后端壳子到 AI Core/Agent Core
- 添加 ToolCall 和 ToolResult 数据结构定义
- 扩展 AgentRun 模型增加输出、错误码、工具调用结果等字段
- 添加 mock 提供商类型支持
- 实现聊天、代理运行、工具调用和提供商管理的核心路由逻辑
- 集成容器化依赖注入和错误处理机制
- 更新 API 接口契约和文档说明

backend/app/container.py

@@ -0,0 +1,49 @@
+from dataclasses import dataclass
+
+from app.agent import AgentRuntime, PermissionManager, PermissionPolicy, ToolRegistry
+from app.agent.builtin_tools import register_builtin_tools
+from app.contracts import ModelCapability, ProviderConfig, ProviderType
+from app.providers import MockProvider, ProviderRegistry
+
+
+@dataclass(frozen=True)
+class ApplicationContainer:
+    providers: ProviderRegistry
+    tools: ToolRegistry
+    permissions: PermissionManager
+    agent: AgentRuntime
+
+
+def build_container() -> ApplicationContainer:
+    providers = ProviderRegistry()
+    providers.register(
+        ProviderConfig(
+            provider_id="mock",
+            provider_type=ProviderType.mock,
+            name="Mock Provider",
+            default_model="mock-1",
+            enabled=True,
+            capabilities=[
+                ModelCapability.chat,
+                ModelCapability.tool_calling,
+                ModelCapability.streaming,
+            ],
+        ),
+        MockProvider(),
+    )
+
+    tools = ToolRegistry()
+    register_builtin_tools(tools)
+
+    policy = PermissionPolicy()
+    permissions = PermissionManager(policy)
+    agent = AgentRuntime(providers=providers, tools=tools, permissions=permissions)
+    return ApplicationContainer(
+        providers=providers,
+        tools=tools,
+        permissions=permissions,
+        agent=agent,
+    )
+
+
+container = build_container()