mirror of
https://github.com/heygen-com/hyperframes.git
synced 2026-11-19 19:36:04 +00:00
fix(cli): shorten the restored thinking budget comment
This commit is contained in:
@@ -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 },
|
||||
|
||||
Reference in New Issue
Block a user