feat: Phase 5 — AI Research Agent（受控工具白名单 + LLM 编排 + API）

- agent/tools.py：Tool 元数据（JSON Schema）+ 白名单调用（异常转可读反馈，不中断对话）
- agent/tools_impl.py：6 个受控工具 search_stocks / get_market_data / test_factor / run_backtest / get_experiment / compare_experiments —— 全部只读经 Job/Experiment 链路，研究自动归档；无 shell/任意执行/写删数据能力
- agent/llm.py：LLMClient 抽象 + OpenAI 兼容客户端（LLM_API_KEY/LLM_BASE_URL/LLM_MODEL 走 .env，未配置给出引导提示）+ 研究纪律 system prompt（反过拟合/样本外/成本）
- agent/service.py：编排循环（tool/final JSON 决策 → 执行 → 回喂 → 结论），轮次上限兜底，未知工具拒绝
- /api/agent/chat；httpx 移至主依赖；Job 默认工厂抽取（api/agent/executor 复用）
- 测试 6 项（白名单无 shell、完整研究循环产出、未知工具拒绝、轮次兜底），全量 79 passed / ruff clean

backend/uv.lock

@@ -911,6 +911,7 @@ source = { virtual = "." }
 dependencies = [
     { name = "alembic" },
     { name = "fastapi" },
+    { name = "httpx" },
     { name = "pyyaml" },
     { name = "sqlalchemy" },
     { name = "uvicorn", extra = ["standard"] },
@@ -932,6 +933,7 @@ dev = [
 requires-dist = [
     { name = "alembic", specifier = ">=1.13" },
     { name = "fastapi", specifier = ">=0.115" },
+    { name = "httpx", specifier = ">=0.28.1" },
     { name = "pyyaml", specifier = ">=6.0" },
     { name = "sqlalchemy", specifier = ">=2.0" },
     { name = "tushare", marker = "extra == 'datasource-tushare'", specifier = ">=1.4" },