Skip to content

Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors

fix(antigravity): don't inject default maxOutputTokens when client omits max_tokens

ivan_yakimkineeb836d62a16
diff --git a/open-sse/translator/request/openai-to-gemini.ts b/open-sse/translator/request/openai-to-gemini.ts
index e79f0653fb..2f362ddb73 100644
--- a/open-sse/translator/request/openai-to-gemini.ts
+++ b/open-sse/translator/request/openai-to-gemini.ts
@@ -567,7 +567,17 @@ export function openaiToAntigravityRequest(model, body, stream, credentials = nu
}
const geminiCLI = openaiToGeminiCLIRequest(model, body, stream);
- return wrapInCloudCodeEnvelope(model, geminiCLI, credentials, true);
+ const envelope = wrapInCloudCodeEnvelope(model, geminiCLI, credentials, true);
+
+ // Match real Antigravity client: don't send maxOutputTokens when the user
+ // hasn't explicitly specified max_tokens / max_completion_tokens.
+ // The Cloud Code server decides the output limit on its own.
+ const clientRequestedMaxTokens = body.max_tokens ?? body.max_completion_tokens;
+ if (clientRequestedMaxTokens === undefined && envelope.request?.generationConfig) {
+ delete envelope.request.generationConfig.maxOutputTokens;
+ }
+
+ return envelope;
}
// Register