Add Claude Fable 5 eval results#87
Merged
Merged
Conversation
Adds claude-fable-5 and claude-fable-5--agents-md experiments and their cached run results (24 evals each, default effort, timeout=1200). Without AGENTS.md: 22/24 (92%). With AGENTS.md: 23/24 (96%). Runs through the Vercel AI Gateway (agent: vercel-ai-gateway/claude-code) since Fable 5 requires a data-retention-enabled workspace. Updates scripts/export-results.ts so agent-results.json labels the model and merges the --agents-md variant into the base row with docsImpact.
The dry-run gate ran `pnpm sync-evals` against bare `canary`, so any upstream eval change red-lined the check for every PR until all models were re-run. Next.js canary just renamed agent-040 (unstable_instant -> instant, #94578), orphaning all 38 models' results. Pin the CI sync to the parent commit (9e4d718) so the eval suite is stable. Also teach sync-evals to accept a commit SHA (fetch + checkout FETCH_HEAD instead of clone --branch, which rejects raw SHAs). Bump the pin in the same PR that re-runs a changed eval across all models.
cramforce
approved these changes
Jun 10, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds Claude Fable 5 to the Next.js coding-agent eval suite, both with and without
AGENTS.md.Details
claude-fable-5.tsandclaude-fable-5--agents-md.ts(default effort,timeout: 1200).agent: vercel-ai-gateway/claude-code) because Fable 5 requires a data-retention-enabled workspace; the direct keychain key 400s on Fable.scripts/export-results.tslabels the model and merges the--agents-mdvariant into the base row withdocsImpact(base 92% → docs 96%).Notes
agent-040;agent-043additionally fails without AGENTS.md. AGENTS.md helps (22→23).