feat: Implement AI Agent with enhanced tool processing capabilities (#89)

* feat: Implement AI Agent with tool processing capabilities

- Added tools for listing and running processors in the agent.
- Created data models for agent chat requests and tool calls.
- Developed API integration for agent chat and streaming responses.
- Built the AI Agent widget with a user interface for interaction.
- Styled the agent components for better user experience.

* feat: 增强 AI 助手工具功能，添加文件操作和搜索功能，更新界面显示

* feat: 更新 AI 助手组件

* feat: 更新 AiAgentWidget 组件样式，调整背景和边距以提升界面一致性

domain/agent/api.py

@@ -0,0 +1,39 @@
+from typing import Annotated
+
+from fastapi import APIRouter, Depends, Request
+from fastapi.responses import StreamingResponse
+
+from api.response import success
+from domain.agent.service import AgentService
+from domain.agent.types import AgentChatRequest
+from domain.audit import AuditAction, audit
+from domain.auth.service import get_current_active_user
+from domain.auth.types import User
+
+
+router = APIRouter(prefix="/api/agent", tags=["agent"])
+
+
+@router.post("/chat")
+@audit(action=AuditAction.CREATE, description="Agent 对话", body_fields=["auto_execute"])
+async def chat(
+    request: Request,
+    payload: AgentChatRequest,
+    current_user: Annotated[User, Depends(get_current_active_user)],
+):
+    data = await AgentService.chat(payload, current_user)
+    return success(data)
+
+
+@router.post("/chat/stream")
+@audit(action=AuditAction.CREATE, description="Agent 对话（SSE）", body_fields=["auto_execute"])
+async def chat_stream(
+    request: Request,
+    payload: AgentChatRequest,
+    current_user: Annotated[User, Depends(get_current_active_user)],
+):
+    return StreamingResponse(
+        AgentService.chat_stream(payload, current_user),
+        media_type="text/event-stream",
+        headers={"Cache-Control": "no-cache"},
+    )