Repository navigation
bench: token count and next-action replay of 1.2.2 - #28
Merged
Merged
Conversation
tokens-20261105-122.json counts the 1.2.2 release views on the 26 cases: 521,703 tokens raw, 38,471 in views, 92.6% fewer, identical to 1.0 case by case. nap-20261105-122.json replays the 48 off sessions of the 1.2.1 campaign: 17 steps, NAP 0.59 for the view against 0.92 for raw, the view costing one verifying call where it leaves the answer out.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
bench/results/tokens-20261105-122.json: the 1.2.2 release views on the 26 cases, counted bycount_tokensfor Opus 5.5 and Haiku 5.5: 521,703 tokens raw, 38,471 in views (92.6% fewer), no case worse, identical to 1.0 case by case.bench/results/nap-20261105-122.json: the 48offsessions of the 1.2.1 live campaign replayed with raw output and the 1.2.2 view (Haiku 5.5, 3 draws, 17 steps, no failed call): NAP 0.59 against raw's 0.92. The view keeps the next action where the failure or location is in it; ongrep_contextanddiff_mediumthe agent makes one verifying call first.bench/README.mdandREADME.mdsummarize both.No code change.