feat: add emulated tool-calling bridge for Lingma

Add a proxy-side tool emulation layer so Lingma requests can surface stable OpenAI tool_calls and Anthropic tool_use blocks even when upstream tool events are missing or inconsistent.

Constraint: Keep native Lingma tool event bridging as the first path and layer emulation as a fallback

Rejected: Depend exclusively on Lingma native tool/invoke events | tool visibility remains inconsistent across models and transports

Confidence: high

Scope-risk: moderate

README.md

@@ -6,6 +6,7 @@
 - Anthropic：`/v1/messages`、`/v1/messages/count_tokens`（含 stream）
 - 内置：多实例池、会话复用、Prometheus 指标、登录态 bundle 注入
 - 工具事件桥接：Lingma 上游返回 `tool` 事件时，网关会输出为 OpenAI `tool_calls`（stream/non-stream）和 Anthropic `tool_use` / `tool_result`（stream/non-stream）；请求侧 `tools` / `tool_choice` 仅在 `TOOL_FORWARD_ENABLED=true` 时透传（默认开启，可显式关闭）
+- 工具模拟回退：当 Lingma 未稳定外显原生 `tool/*` 事件时，网关会把注入后的 `json action` / `#Tool Call` 等动作文本归一化为 OpenAI `tool_calls`，并支持 tool result continuation
 - 多模态降级：OpenAI `image_url` / `input_image` 转 `[image]`，`input_audio` 转 `[audio]`；Anthropic `image` 转 `[image]`
 
 > 架构设计与二开细节请看 [`DESIGN.md`](./DESIGN.md)。
@@ -85,6 +86,9 @@ python3 -m unittest tests/test_tool_call_bridge.py
 
 # 全量 unittest
 python3 -m unittest discover -s tests -p "test_*.py"
+
+# Docker 端到端工具调用冒烟
+bash scripts/smoke_tool_calls.sh
 ```
 
 ---
@@ -201,6 +205,7 @@ curl -s "http://127.0.0.1:${PORT}/healthz"
 | `healthz` 正常但请求失败 | 用错端口 | 以 `.env` 的 `PORT` 为准，`docker compose ps` 再确认 |
 | `git pull` 提示 not on a branch | 处于 detached HEAD | 执行 `git checkout -B main origin/main` |
 | 自动登录不稳定 | 浏览器流程波动 | 优先使用 `LINGMA_SESSION_BUNDLE(_FILE)` |
+| 日志出现 `extension main js path not found` / `ExtensionApi executor not inited` | Lingma 扩展运行时未完整提取，MCP/工具执行器未初始化 | 重启容器触发 bootstrap 自愈；确认 `data/bin/<version>/extension/main.js` 已存在 |
 | 工具调用未触发 | 模型未选择工具或当前协议路径不支持合成回退 | OpenAI 可配合 `tool_choice` 强制并约束输出 JSON；Anthropic 当前仅 non-stream 支持合成 `tool_use` / `tool_result` 回退 |
 
 ---