Skip to content

docs(rfc): re-audit kas, jev and early-l RFC status - #39830

Merged
bolichen97 merged 1 commit into
mainfrom
docs/sweep-rfc-2-3
Nov 20, 2026
Merged

bolichen97 merged 1 commit into
mainfrom
docs/sweep-rfc-2-3

Conversation

@bolichen97

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: RFC status fields match what main implements.

Why it matters

The First Principles review lane and readers trust each RFC's status; a status behind main misleads both.

Not a goal

  • Rewriting RFC design bodies, deleting RFCs, or editing the index in docs/request-for-change/README.md (handled by a separate finisher PR).

What changed (motivation → approach → change)

Re-audited each RFC's status, last-audited and audited-at against main.

  • rfc-kas-session-head-in-agent-prompt: accepted -> implemented. perf(kas): send a new chat's session-stable blocks as the agent prompt #37108 shipped session_head.py, read by acp/harness/kas.py and context_assembly/turn_message.py.
  • rfc-jev-task-executor: accepted -> partial. Rollout step 2 is on main (Noul and Score in decisions/types.py, feat(decisions): add noul and score question types #16014); jev_executor/, jev_computer_task and dispatch_structured are not.
  • rfc-issue-radar-dispatch, rfc-kas-own-engine-route, rfc-kiro-sign-in-card-extension, rfc-large-session-bounded-restore, rfc-leaked-runtime-reclaim, rfc-living-ui, rfc-local-notification-bus, rfc-main-spec-start-recovery: status still matches main; audit keys bumped.

Backwards compatibility

Compatible: documentation front matter and status prose only.
Removes nothing: no RFC body, key or file is removed.

Tests

Proof: not provable -- docs or config only. ./scripts/docs-lint.sh exits 0.

Manual verification

Each status was checked by grepping the named deliverables (definition and caller) on main and reading the listed PRs with gh pr view.

Real-machine verification

N/A -- docs only, the diff runs nothing.

Related Issues

N/A -- periodic docs sweep.

Checklist

  • A Conventional Commits title (feat|fix|docs|style|refactor|perf|test|chore|ci|build|revert: ...); PR Hygiene does not count commits
  • Existing tests pass and new tests added for new functionality
  • Self-review completed; code follows project style guidelines
  • Documentation updated (if applicable)
  • No secrets, credentials, or internal references in the diff

Contribution License Agreement

@bolichen97
bolichen97 requested review from a team and KiroCrewCaptain as code owners November 20, 2026 08:07
@bolichen97
bolichen97 requested a review from buluoray November 20, 2026 08:07
@bolichen97
bolichen97 enabled auto-merge (squash) November 20, 2026 08:07
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Nov 20, 2026
@github-actions

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ⏭️ skipped

Revision a7e693aadd5844ea49ddee7f5783ac66082403a3 ships no reviewable capability (docs, tests or generated files only), so there is nothing to inventory. Does not block merge.

@github-actions

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision a7e693aadd5844ea49ddee7f5783ac66082403a3 touches no user-facing surface (no changes under website/ or committed screenshots), so the UX review was skipped. Does not block merge.

@github-actions

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of a7e693aadd5844ea49ddee7f5783ac66082403a3 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

This is a docs-only status sweep, so nothing blocks. Both status changes match the tree: session_head.py exists and the KAS harness and turn-message code use it, and jev_executor/ is absent.

[DESIGN-REVIEWED] a7e693a

Description read

[DESCRIPTION-READ] 048b05b0d0b91304e94c8fb8d5caea807afc9be384e59015852db86cb4ec3728

That sha256 names everything this verdict read: the PR description, plus the 1 evidence file(s) the workflow collected from it and handed this review. It covers that evidence because the media strip replaces every attachment URL with the same placeholder, so an edit swapping one attachment for another would leave the description's captured text identical while what this review judged changed. Recompute it with .github/scripts/pr-description-capture.sh over the same inputs; if it differs, the description or that evidence changed after this verdict was formed and any finding drawn from either is unproven.

@github-actions

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of a7e693aadd5844ea49ddee7f5783ac66082403a3 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] a7e693a

False positive or not applicable? A repository writer can comment:
/ai-review override gpt a7e693aadd5844ea49ddee7f5783ac66082403a3 false-positive: <reason, 20 to 500 characters>

@github-actions

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — 🔴 changes requested (blocking)

Reviewed a7e693aadd5844ea49ddee7f5783ac66082403a3 — this comment is updated in place on each push.

The RFC index in docs/request-for-change/README.md still shows the old statuses, so it now contradicts the documents this audit re-marked. The index rows for the session-head RFC and the jev RFC were not updated.

BLOCKING — docs/request-for-change/README.md:45
| [rfc-kas-session-head-in-agent-prompt.md](...) | accepted | ... Nothing built; it changes no code. (and README.md:131: | [rfc-jev-task-executor.md](...) | accepted | ...)
Trigger: The diff changes rfc-kas-session-head-in-agent-prompt.md from status: accepted to status: implemented, citing #37108. That work is on main: src/kiro_crew/session_head.py exists and acp/harness/kas.py:1582 calls session_head.head_blocks. The diff also changes rfc-jev-task-executor.md to status: partial. Neither index row was edited, and no docs lint checks the index against the front matter.
Outcome: Anyone reading the directory index sees the session-head RFC listed as accepted with "Nothing built", and the jev RFC listed as accepted. The documents now say implemented and partial, so the index and the documents disagree.
Anchor: defect
Fix: In the same PR, update the status cell, the summary and the verified-at commit in README rows 45 and 131. Also refresh the open-#27535 wording in row 59 so it matches the re-audited document.

[BLOCK-MERGE] a7e693a
[OPUS-REVIEWED] a7e693a

Verdict parsed from the review's SHA-scoped output markers for commit a7e693aadd5844ea49ddee7f5783ac66082403a3.

False positive or not applicable? A repository writer can comment:
/ai-review override fable a7e693aadd5844ea49ddee7f5783ac66082403a3 false-positive: <reason, 20 to 500 characters>

@bolichen97
bolichen97 merged commit 49111b9 into main Nov 20, 2026
73 of 77 checks passed
@bolichen97
bolichen97 deleted the docs/sweep-rfc-2-3 branch November 20, 2026 08:31
@github-actions github-actions Bot removed the readiness: checking Automated validation is still running label Nov 20, 2026
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