fix(gemini-cli): raise output floor for thinking and add validated toolConfig (#2486)

Gemini CLI requests with small max_tokens spend the whole output budget on
thoughts after reasoning_effort maps to thinkingConfig, returning blank
content or finish=length. Raise maxOutputTokens floors per thinking level/
budget (clamped to caps.maxOutput). Also emit toolConfig
functionCallingConfig.mode=VALIDATED for Gemini CLI tool requests to avoid
MALFORMED_FUNCTION_CALL.

Co-authored-by: Cursor <cursoragent@cursor.com>

open-sse/translator/request/openai-to-gemini.js

@@ -281,18 +281,17 @@ function wrapInCloudCodeEnvelope(model, geminiCLI, credentials = null, isAntigra
   // Antigravity specific fields
   if (isAntigravity) {
     envelope.requestType = "agent";
-
-    // Add toolConfig for Antigravity
-    if (geminiCLI.tools?.length > 0) {
-      envelope.request.toolConfig = {
-        functionCallingConfig: { mode: "VALIDATED" }
-      };
-    }
   } else {
     // Keep safetySettings for Gemini CLI
     envelope.request.safetySettings = geminiCLI.safetySettings;
   }
 
+  if (geminiCLI.tools?.length > 0) {
+    envelope.request.toolConfig = {
+      functionCallingConfig: { mode: "VALIDATED" }
+    };
+  }
+
   return envelope;
 }