Skip to content

test(conductor): map the shared goal_plan rule to its Ultra Mode anchor - #36652

Merged
buluoray merged 1 commit into
mainfrom
test/parity-goal-plan-anchor
Nov 13, 2026
Merged

buluoray merged 1 commit into
mainfrom
test/parity-goal-plan-anchor

Conversation

@iamwhatever

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: Put main's conductor parity test back to green.

On main, test/test_mate_conductor_parity.py::test_every_shared_rule_has_an_ultra_counterpart_or_a_named_gap fails with shared rules with no Ultra Mode counterpart: ['goal_plan']. #36529 added that check; #36540 added the shared goal_plan rule. Each passed alone, and together the new key has no anchor.

Why it matters

Every PR whose Backend Tests run this file is red until it lands.

Not a goal

  • No prompt or skill text change.

What changed (motivation → approach → change)

The rule already has its Ultra Mode counterpart: goal-conductor/SKILL.md Patrol says "A finding rewrites the plan at once ... rewrite the goal text's Plan and ...". This maps goal_plan to those two phrases in ULTRA_SKILL_ANCHORS.

Backwards compatibility

Compatible: test-only.

Removes nothing: it adds one map entry.

Tests

Proof: not provable -- test-only change

test/test_mate_conductor_parity.py: 24 passed with this change; 1 failed, 23 passed on main.

Manual verification

N/A — test-only.

Related Issues

Closes #36651

Sibling sweep

Siblings: none -- every other _LEDGER_CONDUCTOR_RULES key is already mapped or gapped; the test checks all keys.

Pattern harvest

Not generalizable: a one-off merge-order clash between two PRs that each passed alone.

Checklist

  • At most two commits (one is the norm), with a Conventional Commits title (feat|fix|docs|style|refactor|perf|test|chore|ci|build|revert: ...)
  • 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

@iamwhatever
iamwhatever requested review from a team and KiroCrewCaptain as code owners November 13, 2026 14:17
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Nov 13, 2026
@github-actions

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ⏭️ skipped

Revision e706659adfdbecc35b0f45f38dd923e4a2bded96 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 e706659adfdbecc35b0f45f38dd923e4a2bded96 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 e706659adfdbecc35b0f45f38dd923e4a2bded96 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing to check. This is a test-only change that adds one map entry. Both anchor phrases appear in goal-conductor/SKILL.md:334-335, and that text matches the shared goal_plan rule.

[DESIGN-REVIEWED] e706659

Description read

[DESCRIPTION-READ] ccd5c87ee77694b61bc623cbf8c7c45b67c2a64df604bcb4df45823658dcf18b

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

Opus 5.5 Review — ✅ no blocking findings

Reviewed e706659adfdbecc35b0f45f38dd923e4a2bded96 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] e706659

Verdict parsed from the review's SHA-scoped output markers for commit e706659adfdbecc35b0f45f38dd923e4a2bded96.

False positive or not applicable? A repository writer can comment:
/ai-review override fable e706659adfdbecc35b0f45f38dd923e4a2bded96 false-positive: <reason, 20 to 500 characters>

@github-actions

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of e706659adfdbecc35b0f45f38dd923e4a2bded96 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] e706659

False positive or not applicable? A repository writer can comment:
/ai-review override gpt e706659adfdbecc35b0f45f38dd923e4a2bded96 false-positive: <reason, 20 to 500 characters>

@KiroCrewCaptain

Copy link
Copy Markdown
Collaborator

Code change approver recommendation: Approve

Why: the decider estimates a 3% chance that this change introduces a defect, within the 12% limit for approving on its own, and every check passes.

Test-only, one-line fix. It adds a goal_plan entry to ULTRA_SKILL_ANCHORS, so the parity test's check that every shared rule is mapped or gapped passes again on main. Both anchor phrases are in goal-conductor/SKILL.md:334-335 once the test's _words helper strips emphasis marks, joins lines and lowercases. That paragraph is the Ultra Mode counterpart of the shared rule: rewrite the goal's Plan/Changed lines when a finding comes in. The key isn't in ULTRA_GAPS, so the mapped/gapped overlap and stale-entry checks still hold. Every other rule key is already covered. Tests weren't run here; some CI checks were still pending at review time.

An automated recommendation, not a review: a maintainer still decides. It approves on its own only when the estimated chance of a defect is at most 12% and the change has at most 400 changed lines. Decider v3c (217fe607) · commit e706659adf · 1 changed lines. If this recommendation is wrong, reply here: replies are how the approver is evaluated.

@buluoray buluoray left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🤖 Kiro Crew Auto-Pipeline [operator: buluoray]:

Approve. This fixes the red on main.

#36540 added the shared conductor rule goal_plan, and #36529 added the guard that every shared rule must map to an Ultra Mode anchor or a named gap. Together they left goal_plan unmapped, so test_every_shared_rule_has_an_ultra_counterpart_or_a_named_gap fails on main (Linux shard 3 and Windows shard 3 of the latest main run).

The two anchors are real text in the chain the team lead reads: src/kiro_crew/builtin_skills/goal-conductor/SKILL.md:334-335 ("A finding rewrites the plan at once", "rewrite the goal text's Plan and"). So this is a mapping, not a gap, and it does not weaken the guard.

Checked on current main with this diff applied: test/test_mate_conductor_parity.py 24 passed.

@buluoray
buluoray enabled auto-merge (squash) November 13, 2026 15:17
@github-actions github-actions Bot removed the readiness: checking Automated validation is still running label Nov 13, 2026
@buluoray
buluoray merged commit da73b69 into main Nov 13, 2026
97 checks passed
@github-actions github-actions Bot added the readiness: passed Eligible automated validation passed for the current revision label Nov 13, 2026
@buluoray
buluoray deleted the test/parity-goal-plan-anchor branch November 13, 2026 15:17
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Nov 13, 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.

main red: test_every_shared_rule_has_an_ultra_counterpart_or_a_named_gap fails on goal_plan

3 participants