chore(release): v0.15.0#368
Merged
Merged
Conversation
Token-savings metric honesty (PRs #363-#365): exact full-file baseline, realistic targeted-read baseline, two-baseline reporting with the whole-repo line demoted to an upper bound. Cross-tool efficiency benchmark (PRs #366-#367): offline `archex benchmark cross-tool` and the checked-in per-corpus reference artifact. Bumps version to 0.15.0 and documents both in the README and CHANGELOG.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Release prep for v0.15.0. Bumps the version, relocks, and documents the two landed stacks from the token-savings-metric-honesty plan in the README and CHANGELOG. No source changes.
What v0.15.0 contains (already merged to main)
Token-savings metric honesty (metrics-only, PRs #363–#365)
imports_context(index schema 4 → 5, forward migration; legacy index omits the baseline non-fatally).returned <= targeted_read <= full_file(ledger schema 1 → 2).archex metrics summaryreports both labeled savings numbers and demotes the whole-repo line to an explicit upper bound.Cross-tool efficiency benchmark (offline, benchmark-only, PRs #366–#367)
archex benchmark cross-tool: tokens-at-fixed-recall vs a naive grep/read agent, recall held equal, not inDEFAULT_STRATEGIES.docs/LOCAL_METRICS.mdnumbers.Files
pyproject.toml,uv.lock— version 0.14.0 → 0.15.0CHANGELOG.md— new[0.15.0]sectionREADME.md— two-baseline metrics paragraph + cross-tool benchmark entry under Measured results