Add model settings for Gemini 3.1 Pro Preview and Flash-Lite#5166
Open
Cyberfilo wants to merge 1 commit into
Open
Add model settings for Gemini 3.1 Pro Preview and Flash-Lite#5166Cyberfilo wants to merge 1 commit into
Cyberfilo wants to merge 1 commit into
Conversation
Adds entries to aider/resources/model-settings.yml for the gemini-3.1-pro-preview and gemini-3.1-flash-lite models across the gemini/, vertex_ai/, and openrouter/google/ providers. These models already have pricing/context-window metadata in litellm's model cost map (the upstream that aider pulls from) but were missing the project-side settings (edit_format, weak_model_name, etc.), so aider falls back to defaults that are wrong for the diff-fenced edit format the 3.x line expects. The configuration mirrors the existing gemini-3-pro-preview / gemini-3-flash-preview entries: diff-fenced edit format, repo map enabled, thinking_tokens accepted, with the pro variant routed through flash-lite for weak/editor model duties. Also adds a HISTORY.md entry under the main branch section.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds entries to
aider/resources/model-settings.ymlfor the recently released Gemini 3.1 Pro Preview and Gemini 3.1 Flash-Lite models across three providers: nativegemini/,vertex_ai/, andopenrouter/google/.These models already have pricing and context-window metadata in litellm's
model_prices_and_context_window.json(the upstream aider pulls from atModelInfoManager.MODEL_INFO_URL), but were missing the project-side settings (edit_format,weak_model_name,accepts_settings, etc.). Without explicit settings, aider falls back to defaults that don't match the diff-fenced edit format the 3.x Gemini line expects, so users have to override per-model on the CLI.Models added
gemini/gemini-3.1-pro-previewgemini/gemini-3.1-flash-litevertex_ai/gemini-3.1-pro-previewvertex_ai/gemini-3.1-flash-liteopenrouter/google/gemini-3.1-pro-previewopenrouter/google/gemini-3.1-flash-liteSettings shape
Mirrors the existing
gemini-3-pro-preview/gemini-3-flash-previewblock:edit_format: diff-fenced(the 3.x line's preferred edit grammar)use_repo_map: trueovereager: trueaccepts_settings: [\"thinking_tokens\"]flash-liteforweak_model_name(andeditor_model_nameon Vertex), matching the cost-tiered weak-model pattern used elsewhere in the file.Test plan
Notes
I considered also adding the
-customtoolsand-image-previewvariants ofgemini-3.1-pro-previewthat litellm tracks, but skipped them — they're niche variants without a clear edit-flow use case in aider. Happy to add if a maintainer wants them in.