Skip to content

Release v6.6.0 notes: product commits are #55 - #58

Merged
cursor[bot] merged 1 commit into
mainfrom
cursor/release-notes-6-6-0-4bb1
Oct 14, 2026
Merged

cursor[bot] merged 1 commit into
mainfrom
cursor/release-notes-6-6-0-4bb1

Conversation

@wukongnotnull

Copy link
Copy Markdown
Owner

This PR MUST target the main branch. Active work is developed on
focused branches and merged directly into main after review.

Tracking: #56
Follows: #57 (merged)

Who is submitting this PR? (required)

Field Value
Your model + version Cursor Grok 4.7
Harness + version Cursor cloud agent
All plugins installed none beyond the Cursor cloud-agent environment (MCP namespaces present: cursor-cloud, cursor-subscriptions, Gmail; unused for this wording fix)
Human partner who reviewed this diff 悟空非空也g — asked to 发版. This sentence is a correction of the notes in merged #57 before the annotated tag

What problem are you trying to solve?

#57 is merged. Its ## v6.6.0 section says `git log v6.5.0..` is only PR #55. That was true of main before the bump merge. After #57, that range also contains 9a50020 and the #57 merge commit. Tagging with that sentence would publish a false range claim. The tag has not been created yet.

What does this PR change?

One sentence in RELEASE-NOTES.md: the product commits after v6.5.0 are only PR #55; the rest of the range is this version bump.

Is this change appropriate for the core library?

Yes. It is the release-notes sentence for the version bump already merged in #57. No skill text, no dependency, no new file.

What alternatives did you consider?

  • Tag Release v6.6.0 #57 as-is. Rejected: the exclusive git log claim would be false on the tag.
  • Put the correction only in the GitHub Release body. Rejected: RELEASE-NOTES.md on the tag would still be wrong.
  • Direct push to main. Rejected: this repo ships release notes through a PR to main, same as Release v6.5.0 #54 / Release v6.6.0 #57.

Does this PR contain multiple unrelated changes?

No. One sentence in the v6.6.0 notes.

Existing PRs

Environment tested

Harness (e.g. Claude Code, Cursor) Harness version Model Model version/ID
Cursor cloud agent (this checkout) Cursor cloud agent Linux VM, Oct 2026 Cursor Grok 4.7 grok-4.7

## v6.6.0 remains in RELEASE-NOTES.md, so tests/skills/test-gemini-retirement.sh still matches package.json 6.6.0. No manifest or skill file changed. CI on this PR is the extended suite plus ShellCheck.

New harness support (required if this PR adds a new harness)

Not applicable. This PR does not add a harness.

Clean-session transcript for "Let's make a react todo list"
N/A — not a new harness integration.

Evaluation

  • What was the initial prompt you (or your human partner) used to start the session that led to this change? 悟空非空也g asked to 发版. This follow-up is the notes-range correction found while preparing the annotated tag.
  • How many eval sessions did you run AFTER making the change? Zero. No skill text changed.
  • How did outcomes change compared to before the change? The dated section no longer claims the entire v6.5.0.. log is only feat: grilling HANDOFF writes a derived technical spec #55.

Language-pack evidence

  • Language and support status: n/a (no language pack change)
  • Real failure generic methodology handled incorrectly: n/a
  • Project markers and toolchain versions: n/a
  • Official sources: n/a
  • No-guidance repetitions and failures: n/a
  • With-guidance repetitions and results: n/a
  • Monorepo, unsupported-language, and docs-only controls: n/a
  • Human reviewer familiar with the language: n/a
  • Frameworks or third-party preferences introduced: none

Rigor

  • If this is a skills change: I used wukong-code:writing-skills and completed adversarial pressure testing (paste results below)
  • This change was tested adversarially, not just on the happy path
  • I did not modify carefully-tuned content (Red Flags table, rationalizations, "human partner" language) without extensive evals showing the change is an improvement

Not a skills change. The check is that the exclusive git-log sentence is false once #57 is in the range, which is why this PR exists.

Human review

  • A human has reviewed the COMPLETE proposed diff before submission

悟空非空也g asked to 发版 and authorized the release PR to main. This diff is one sentence so the tagged notes match the commits after v6.5.0. The human should still glance at the v6.6.0 section before relying on the GitHub Release object.

Open in Web Open in Cursor 

The dated section claimed git log v6.5.0.. contained only PR #55.
After the version-bump merge that range also contains this release.
Say the product commits are #55 and the rest of the range is the bump.

Co-authored-by: ficehuang <ficehuang@gmail.com>
@cursor
cursor Bot merged commit 474a6da into main Oct 14, 2026
3 checks passed
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.

2 participants