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/providers/base.py

@@ -0,0 +1,30 @@
+from collections.abc import AsyncIterator
+from dataclasses import dataclass, field
+from typing import Protocol
+
+from app.contracts import ModelEvent, ModelInfo, ModelRequest
+
+
+@dataclass(slots=True)
+class ProviderToolCall:
+    tool_call_id: str
+    name: str
+    arguments: dict[str, object] = field(default_factory=dict)
+
+
+@dataclass(slots=True)
+class ProviderTurn:
+    text: str | None = None
+    tool_calls: list[ProviderToolCall] = field(default_factory=list)
+    input_tokens: int = 0
+    output_tokens: int = 0
+
+
+class ModelProvider(Protocol):
+    async def complete(self, request: ModelRequest) -> ProviderTurn: ...
+
+    def stream(self, request: ModelRequest) -> AsyncIterator[ModelEvent]: ...
+
+    async def list_models(self) -> list[ModelInfo]: ...
+
+    async def test_connection(self, model: str | None = None) -> tuple[bool, str]: ...