Skip to content

chore: release v0.6.0 - #83

Merged
szjanikowski merged 2 commits into
mainfrom
chore/release-v0.6.0
Sep 12, 2026
Merged

szjanikowski merged 2 commits into
mainfrom
chore/release-v0.6.0

Conversation

@szjanikowski

Copy link
Copy Markdown
Contributor

Summary

Why 0.6.0, not 0.5.1

cost_usd semantics changed (cache-aware, ADR-014), Harbor 0.13 → 0.19, new judge inputs and CLI flags — a 0.x minor.

Test plan

  • [#NN] link-refs: every cited PR is defined at the bottom (script-checked, no dangling refs)
  • Unit tests also pass against Harbor 0.22 (462 passed in a scratch venv) — a follow-up bump to >=0.22,<0.23 is planned as 0.6.1 after a smoke run, deliberately not coupled with this release
  • CI green
  • After merge: git tag v0.6.0 && git push origin v0.6.0 (publish.yml handles TestPyPI → smoke → PyPI → GitHub Release, per docs/RELEASING.md)

🤖 Generated with Claude Code

https://claude.ai/code/session_01UwjBNRxR1vkNGBcETRzdf2

Move [Unreleased] under 0.6.0 (2026-09-11), add the missing CHANGELOG entry
for the calibration round 2 engine changes (#75: agent diff as judge input,
per-task dimensions, precheck.sh hook, eval --eval-model/--eval-backend) and
the [#76] link-ref on the Harbor 0.19 entry.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UwjBNRxR1vkNGBcETRzdf2
Trim the 0.6.0 section to concise, user-facing entries: one bullet per
feature with the value it brings, no implementation history or internal
verification notes. Same facts, 76 lines -> 47.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UwjBNRxR1vkNGBcETRzdf2
@szjanikowski
szjanikowski merged commit 742c4eb into main Sep 12, 2026
9 checks passed
@szjanikowski
szjanikowski deleted the chore/release-v0.6.0 branch September 12, 2026 09:57
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant