Move model whitelist to config file, expand to 16 models#248
Merged
Conversation
This was referenced Jun 3, 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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
The model whitelist was hardcoded in both workflows as a GitHub Actions variable fallback (
vars.FORGE_MODEL_WHITELIST), limiting miners to 3 models (claude-haiku, claude-3-5-haiku, gpt-4o-mini). This moves it to a committed file and expands it to 16 models across all major providers.Changes
config/model-whitelist.txt— one model per line, commented by providerscore.yml: load whitelist from file infind-agentjob, pass via job output toscore-roundandhidden-evaleval.yml: load whitelist from file before the eval stepCONTRIBUTING.md: reference the config file instead of listing 3 hardcoded modelsOperator action required
Delete the
FORGE_MODEL_WHITELISTGitHub Actions variable from repo Settings → Secrets and variables → Actions → Variables. It is no longer referenced by CI.Models added
DeepSeek-R1, DeepSeek-R1-distill-70B, DeepSeek-chat-v3, Claude-3.5-Sonnet, Claude-Sonnet-4.5, GPT-4o, Llama-3.1-70B, Llama-3.1-405B, Gemini-2.0-Flash, Gemini-Flash-1.5, Mixtral-8x7B, Qwen-2.5-72B