fix(cli): shorten the restored thinking budget comment

This commit is contained in:
Miguel Angel Simon Sierra
2026-11-04 17:25:29 -05:00
parent 3f4ecb60d0
commit e2903264fc
+2 -5
View File
@@ -412,11 +412,8 @@ export async function captionImagesWithGemini(
],
config: {
maxOutputTokens: maxTokens,
// A one-line factual caption needs no reasoning, and leaving thinking on is
// not merely wasteful: thinking tokens are drawn from maxOutputTokens, so the
// model can spend the whole budget and return empty text. That surfaces as a
// successful request with no caption — the capture then logs "Captioned N/N
// images" followed by "0 images captioned", which is what production shows.
// Thinking tokens are drawn from maxOutputTokens, so the model can spend the
// whole budget and return a successful request with no caption text.
thinkingConfig: { thinkingBudget: 0 },
abortSignal: signal,
httpOptions: { timeout: timeoutMs },