Repository navigation
fix(cli): update model presets that point at unavailable models - #635
Merged
Merged
Conversation
`--model free`/`free-fast` resolved to google/gemini-2.0-flash-exp:free and `free-smart` to deepseek/deepseek-r1:free. Neither is in the OpenRouter model catalog any more, so every request made with these presets fails. Use nvidia/nemotron-3-super-120b-a12b:free, the free model the auto-labeling workflow already moved to because it supports structured outputs, for free/free-fast, and nvidia/nemotron-3.5-super-vl:free for free-smart. Both are free, support tools and structured outputs, which the `--format` options rely on. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
OpenAI shuts down o4-mini on 2026-10-23 and names gpt-5.6-terra as its replacement. The CLI fell back to o4-mini when no model is given and used it for `latest-fast`. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
OpenAI shuts down o3-mini on 2026-10-23 and names gpt-5.6-sol as its replacement. It is the default of the `--model` option, so every command run without `--model` would start failing. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Some CLI model presets point at models that are gone or about to be:
--model free/free-fastresolved togoogle/gemini-2.0-flash-exp:freeandfree-smarttodeepseek/deepseek-r1:free. Neither is in the OpenRouter catalog any more (GET https://openrouter.ai/api/v1/models), so commands using these presets fail.--modeldefault iso3-mini, and the fallback when no model is given andlatest-fastresolved too4-mini. OpenAI shuts both down on 2026-10-23 (deprecations).This PR maps:
free/free-fast→nvidia/nemotron-3-super-120b-a12b:free, the model the auto-labeling workflow already switched to because it supports structured outputs.free-smart→nvidia/nemotron-3.5-super-vl:free. Both free models support tool calling and the structured outputs that the--formatoptions use.--modeldefault →gpt-5.6-sol, the replacement OpenAI names foro3-mini.latest-fast→gpt-5.6-terra, the replacement OpenAI names foro4-mini.o3(latest-smart) is not part of that shutdown and is unchanged. The CLI sends no sampling parameters, so the reasoning models accept the same requests.The CLI project builds, and
dotnet format --verify-no-changespasses onHelpers.cs(the other change is a one-string default inCommonOptions.cs).This change was made with Claude Code.
🤖 Generated with Claude Code