This repository was archived by the owner on Mar 9, 2026. It is now read-only.
Repository navigation
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Context
Hi Team,
I realized that there was no way to specify the
ThinkingBudgetparameter when making requests to Gemini models. This limited the ability to control model reasoning steps. For Flash and Flash-Lite, this means I can't enable it either.Referencing the Gemini API and looking at the curl example, we should an additional optional alongside specifying token size, temp etc. Below is the example:
This is a bit longer but the link shows an example of how we can include the IncludeThoughts flag as well: https://ai.google.dev/gemini-api/docs/thinking#go_1
Proposal
ThinkingBudget: Add support in the codebase to allow users to specifyThinkingBudgetfor Gemini models via configuration or CLI.IncludeThoughts:* Add support for the theIncludeThoughtsflag to make troubleshooting if thinking is working as intended.Rationale
These changes will enable advanced configuration for Gemini users.
Request for Feedback
Is there interest or concern in supporting the Gemini
ThinkingBudgetparameter? Is this functionality already available and I've somehow missed it? If so apologies for the hassle.I've also submitted a PR with some proposed changes.
Would love to hear your feedback :)
All reactions