chore(bench): self-describing verdict tables — models + config in every banner and artifact#251
Merged
Merged
Conversation
…ry banner and artifact A pasted verdict table must carry its own provenance: every verdict banner now prints worker/analyst/author/compressor models + domain/n/budget (and objective where set), and every artifact (grid, steering-modes, evolve, compression-gate) carries a models + config block. Tables become shareable without the surrounding session.
tangletools
approved these changes
Jun 10, 2026
tangletools
left a comment
tangletools
left a comment
Contributor
There was a problem hiding this comment.
✅ Auto-approved PR — b345abe4
Blanket team auto-approval is enabled for this reviewer service.
The full PR reviewer audit still runs separately and will publish findings if it detects issues.
tangletools · auto-approval · reason: blanket_auto_approve · 2026-06-10T23:18:47Z
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
A pasted verdict table must carry its own provenance. Every verdict banner now prints the model identities (worker / analyst / author+fallback / compressor) plus domain, n, budget, and objective; every artifact (ablation-grid, steering-modes, flywheel-evolve, prompt-compression-gate) carries a
models+configblock.The standing model map (cheap router models only — never CC models): EOPS runs = deepseek-v4-pro worker/author with flash fallback; AIME/math grid + steering modes = deepseek-v4-flash worker; compressor = deepseek-v4-flash; analyst defaults to the worker (the
analystModelknob exists).Bench-only; the running cost experiment is unaffected (tsx loaded its sources at start). Typecheck deltas beyond the known stale-dist class: none.