fix(setup): Remove model selection constraint from setup command#142
Merged
fix(setup): Remove model selection constraint from setup command#142
Conversation
moisgobg
added
bug
hminooei
approved these changes
Mar 4, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Removes a hardcoded critical instruction from the setup command that previously forced the agent to always select the "flash" model regardless of task complexity.
We need to remove this constraint for a couple of reasons:
1. Not always working: Forcing the "flash" model selection for every task leads to unpredictable results, and causes the agent to hallucinate more.
2. Quota management belongs in Gemini CLI: This constraint was originally added as a workaround for quota limitations. We should address quota issues and model tiering robustly within the core Gemini CLI logic, rather than through hardcoded prompt LLM instructions.
Related Issue:
Fixes #141