Repository navigation
chore: default Gemini Flash model to gemini-3.8-flash - #5364
Merged
Merged
Conversation
Google is retiring Gemini 3.6 Flash (2026-11-19) and 3.7 Flash (2027-01-28); after those dates requests to them return 404. 3.8 Flash is the generally available successor at the same price. - hermes integration: default model for the gemini provider - system evals: default HINDSIGHT_EVAL_LLM_MODEL in replay_delta_ops and the README example Pricing entries for 3.6/3.7 stay in refresh_cost.py so historical runs still cost out.
nicoloboschi
approved these changes
Oct 7, 2026
This was referenced Oct 8, 2026
Merged
This was referenced Oct 16, 2026
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
Google is retiring Gemini 3.6 Flash (2026-11-19) and 3.7 Flash (2027-01-28). After those dates, requests to them return 404. Anyone relying on these defaults would start failing.
Gemini 3.8 Flash is the generally available successor, at the same per-token price.
Change
geminiprovider goes fromgemini-3.6-flashtogemini-3.8-flash.HINDSIGHT_EVAL_LLM_MODELinreplay_delta_ops.pyand the README example go fromgemini-3.7-flashtogemini-3.8-flash.refresh_cost.pyare kept, so cost reports on historical runs still work.Testing
replay_delta_ops.pycompiles.gemini-3.8-flashanswersgenerateContentand makes the same tool call as 3.6 Flash on a function-calling probe. It has the same 1M input / 65K output limits.