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

app/lingma_client.py

@@ -419,6 +419,17 @@ class LspWsRpcClient:
         method = msg.get("method")
         params = msg.get("params") or {}
 
+        if method and (
+            method.startswith("tool/")
+            or method.startswith("mcp/")
+            or method in {"chat/answer", "chat/finish"}
+        ):
+            logger.info(
+                "lingma server message method=%s params=%s",
+                method,
+                params,
+            )
+
         if method == "chat/answer":
             req_id = params.get("requestId")
             stream = self._chat_streams.get(req_id)