Skip to content

docs(decisions): every crewmate on a user-level agent moves to the conductor - #25332

Merged
buluoray merged 2 commits into
mainfrom
docs/decision-every-bound-crewmate-moves
Oct 28, 2026
Merged

buluoray merged 2 commits into
mainfrom
docs/decision-every-bound-crewmate-moves

Conversation

@buluoray

@buluoray buluoray commented Oct 28, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: Record the owner's decision that every crewmate still bound to a user-level agent moves onto its conductor, with a restriction its file cannot carry moving with it and named in its notice, superseding the 2026-10-27 crewmate-migration entry.

The 2026-10-27 entry keeps a crewmate on its old agent when that agent states a hooks, permissions or toolsSettings restriction the crewmate file cannot carry. Such a row, like any row still bound to a spec in the user-level agents folder, keeps the shared-template governance pass rewriting the user's own file (#25289).

Why it matters

Implementation PR #25325 changes that behaviour; docs/decisions/README.md rule 3 requires the superseding entry to ship in its own pull request, and rule 4 requires the deciding maintainer to restate it here.

Not a goal

What changed (motivation → approach → change)

  • New entry docs/decisions/2026-10-28-every-crewmate-on-a-user-level-agent-moves-to-the-conductor.md, Supersedes: the 2026-10-27 entry, Decided by: Ray.
  • One index row in docs/decisions/README.md.

The decision was given by the owner to the pipeline that is fixing #25289; per README rule 4 it needs the owner to restate it as a comment on this pull request, which the entry's Evidence will then cite.

Backwards compatibility

Compatible: documentation only.

Tests

N/A: documentation only; the decision-ledger-history gate checks that no existing entry changed.

Manual verification

N/A.

Screenshots / video

N/A: no UI change.

Related Issues

Refs #25289. Implemented by #25325.

Checklist

  • At most two commits (one is the norm), with a Conventional Commits title
  • Existing tests pass and new tests added for new functionality (N/A: docs only)
  • Self-review completed; code follows project style guidelines
  • Documentation updated (if applicable)
  • No secrets, credentials, or internal references in the diff

Contribution License Agreement

Contributed under the project's Apache-2.0 license (see CONTRIBUTING.md).

@buluoray
buluoray requested review from a team and KiroCrewCaptain as code owners October 28, 2026 17:18
@buluoray
buluoray requested a review from dodgeblaster October 28, 2026 17:18
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Oct 28, 2026
@github-actions

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 0cf023cd30f518c2f66f0c12dc25b3520c179914 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Docs-only decision entry; the owner's call is recorded with its supersession, so nothing in the design blocks.

Notes

[DESIGN-REVIEWED] 0cf023c

Description read

[DESCRIPTION-READ] a6db7072a69f33be81995a8d26ceb68e0fa9a4c97abf924db5e43be650166c70

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

github-actions Bot commented Oct 28, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ human override accepted

Reviewed 0cf023cd30f518c2f66f0c12dc25b3520c179914 — this comment is updated in place on each push.

Human judgment by @buluoray overrides the Opus 5.5 finding for 0cf023cd30f518c2f66f0c12dc25b3520c179914; the recorded reason is authoritative for this commit.

[OPUS-OVERRIDE] 0cf023c

Verdict recorded from an authorized human decision for commit 0cf023cd30f518c2f66f0c12dc25b3520c179914.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 0cf023cd30f518c2f66f0c12dc25b3520c179914 false-positive: <reason, 20 to 500 characters>

@github-actions

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ✅ PASS

UX-level review of 0cf023cd30f518c2f66f0c12dc25b3520c179914 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

UX-Verdict: PASS

Nothing to check. The diff only adds a decision record and one index row in docs/decisions/, and changes no user-visible control, so having no screenshots leaves no evidence gap.

[UX-REVIEWED] 0cf023c

Description read

[DESCRIPTION-READ] 84ad03f9aa174aef74340615670426a6c583c08a9b815a44bd140eda429cafd5

That sha256 names everything this verdict read: the PR description, plus the 3 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

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of 0cf023cd30f518c2f66f0c12dc25b3520c179914 — why this exists and whether the shipped surface is the smallest honest version. Updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

First-Principles-Verdict: PASS

This PR only adds a ledger entry. It changes no behaviour, and the Supersedes: and owner-restatement steps follow README rules 3–4.

What this change ships

Inventory (2 items) — 2 justified

Intent: record the owner's decision that every crewmate still bound to a user-level agent moves onto its conductor, superseding the 2026-10-27 entry. This is a FIX (docs only). The MCP routed hunks in the patch belong to #24925, which is already on base fe317a66; they are not part of this PR's commit.

  1. New decision entry: crewmates on user-level agents move to the conductor, and restrictions the crewmate file cannot carry are named in the notice (supersedes 2026-10-27) — justified
  2. One new index row for that entry in docs/decisions/README.md — justified

[FIRST-PRINCIPLES-REVIEWED] 0cf023c

Description read

[DESCRIPTION-READ] 535e97aba2bf14ecad9eb19d3e357e719eae97176d7c215f922b87d9ec70ba35

That sha256 names the PR description this verdict read. Recompute it with .github/scripts/pr-description-capture.sh; if it differs, the description changed after this verdict was formed and any finding drawn from the description is unproven.

@github-actions

github-actions Bot commented Oct 28, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ human override accepted

Human judgment by @buluoray overrides the GPT 6.1 finding for 0cf023cd30f518c2f66f0c12dc25b3520c179914; the recorded reason is authoritative for this commit.

[GPT-OVERRIDE] 0cf023c

This comment is updated in place on each push.

The model was not re-run because an authorized human decision supersedes it.

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 0cf023cd30f518c2f66f0c12dc25b3520c179914 false-positive: <reason, 20 to 500 characters>

@github-actions github-actions Bot added readiness: action required A blocking check or review needs attention and removed readiness: checking Automated validation is still running labels Oct 28, 2026
@buluoray

Copy link
Copy Markdown
Contributor Author

🤖 Kiro Crew Auto-Pipeline [operator: buluoray#ce473fca]: Owner decision, posted at @buluoray's direction.

I confirm this decision. Every crewmate still bound to a user-level agent under ~/.kiro/agents moves to kirocrew-mate-conductor plus its mate file. kiro-cli retires v2 at the end of November, so rewriting a spec Crew does not own is no longer an option.

  • A restriction the mate file cannot carry (hooks, permissions, toolsSettings) no longer applies. It is NOT made up for by withholding tools. The one-time notice names each restriction that no longer applies.
  • The governance ceiling (POLICY ∩ PROFILE) still governs the merged worker spec. Capability gains still come only through the capability card.
  • If a third-party spec already uses the id, the row stays as is, gets a one-time notice, and is never renamed. The pass never writes the third-party file.
  • A member_id and V2 store are minted only for rows the mate prune would keep.

This supersedes the earlier entry. The GPT and Opus blocks on this PR are the recorded-decisions rule doing its job; I am releasing them as the owner.

@buluoray

Copy link
Copy Markdown
Contributor Author

/ai-review override fable 0cf023c owner-decision: This PR is the superseding decision entry itself; the recorded-decisions rule blocks it by design. Owner decision: #25332 (comment)

@buluoray

Copy link
Copy Markdown
Contributor Author

/ai-review override gpt 0cf023c owner-decision: This PR is the superseding decision entry itself; the recorded-decisions rule blocks it by design. Owner decision: #25332 (comment)

@github-actions

Copy link
Copy Markdown
Contributor

Human judgment recorded

@buluoray recorded a owner-decision release (class owner-decision) for the fable AI finding on 0cf023cd30f518c2f66f0c12dc25b3520c179914.

This PR is the superseding decision entry itself; the recorded-decisions rule blocks it by design. Owner decision: #25332 (comment)

This decision applies only to this commit. A new push requires a new judgment.

@github-actions

Copy link
Copy Markdown
Contributor

Human judgment recorded

@buluoray recorded a owner-decision release (class owner-decision) for the gpt AI finding on 0cf023cd30f518c2f66f0c12dc25b3520c179914.

This PR is the superseding decision entry itself; the recorded-decisions rule blocks it by design. Owner decision: #25332 (comment)

This decision applies only to this commit. A new push requires a new judgment.

@buluoray
buluoray enabled auto-merge (squash) October 28, 2026 22:34
@github-actions github-actions Bot added readiness: passed Eligible automated validation passed for the current revision and removed readiness: action required A blocking check or review needs attention labels Oct 28, 2026
@buluoray

Copy link
Copy Markdown
Contributor Author

@bolichen97 could you approve this one? It is the superseding decision entry for #25289; checks are green and the AI-review overrides are recorded. #25325 waits on it before the 11/2 KAS switch.

@KiroCrewCaptain KiroCrewCaptain left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Approved on behalf of the watch holder (bolichen). Design and First Principles pass on this head, UX skipped or pass, all checks green, no conflict, no open change request.

@buluoray
buluoray merged commit 6512997 into main Oct 28, 2026
146 of 156 checks passed
@buluoray
buluoray deleted the docs/decision-every-bound-crewmate-moves branch October 28, 2026 22:54
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Oct 28, 2026
bolichen97 pushed a commit that referenced this pull request Oct 29, 2026
…nductor (#25332)

* docs(decisions): every crewmate on a user-level agent moves to the conductor

* docs(decisions): a restriction the crewmate file cannot carry moves with it

(cherry picked from commit 6512997)
bolichen97 added a commit that referenced this pull request Oct 29, 2026
… backport of #25325) (#25913)

Backports #25332 and #25325 to release/0.11.0.

- fix(agent): never rewrite a crew-bound spec Crew does not own
- docs(decisions): every crewmate on a user-level agent moves to the conductor (#25332)
  (#25325 cherry picked from commit e778f71, merged on main as 99fd8a2)

Backport notes: backends.py keeps only #25325's own ACP_BACKENDS_SPEC_FILE_GRANTS lines; the HARNESS_EXEMPT_SETS row is dropped because that table is not on release/0.11.0.
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