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/agent/builtin_tools.py

@@ -0,0 +1,46 @@
+from pydantic import BaseModel, ConfigDict
+
+from app.agent.tools import ToolExecutionContext, ToolRegistry
+from app.contracts import ToolDefinition
+
+
+class ToolArguments(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
+
+class EchoArguments(ToolArguments):
+    text: str
+
+
+class AddArguments(ToolArguments):
+    left: float
+    right: float
+
+
+async def echo(arguments: EchoArguments, _: ToolExecutionContext) -> dict[str, str]:
+    return {"text": arguments.text}
+
+
+async def add(arguments: AddArguments, _: ToolExecutionContext) -> dict[str, float]:
+    return {"value": arguments.left + arguments.right}
+
+
+def register_builtin_tools(registry: ToolRegistry) -> None:
+    registry.register(
+        ToolDefinition(
+            name="system.echo",
+            description="Echo text for local Agent integration testing.",
+            parameters=EchoArguments.model_json_schema(),
+        ),
+        EchoArguments,
+        echo,
+    )
+    registry.register(
+        ToolDefinition(
+            name="math.add",
+            description="Add two numbers without external side effects.",
+            parameters=AddArguments.model_json_schema(),
+        ),
+        AddArguments,
+        add,
+    )