Repository navigation
fix(agent): never rewrite a crew-bound spec Crew does not own (0.11.0 backport of #25325) - #25913
Conversation
UX Review (Opus 5.5) — ⏭️ skippedRevision |
First Principles Review (Opus 5.5) — ✅ human override accepted@bolichen97 overrode this lane for |
Design Review (Opus 5.5) — ✅ PASSDesign-level review of Design-Verdict: PASS Nothing blocks: this is a faithful backport of the merged #25325 fix. The ceiling still holds, because a kiro-cli start on an over-ceiling unowned spec is refused instead of the file being rewritten. Notes
[DESIGN-REVIEWED] 6b61b1a Description read[DESCRIPTION-READ] 5f3d81cd1fabc4acc3994af558b83efa4b0c35629a51bd8a868f7c48559a3b9f 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 |
5565b77 to
3e9dc6a
Compare
GPT 6.1 Review — ✅ human override acceptedHuman judgment by @bolichen97 overrides the GPT 6.1 finding for [GPT-OVERRIDE] 6b61b1a 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: |
Opus 5.5 Review — ✅ no blocking findingsReviewed Verdict parsed from the review's SHA-scoped output markers for commit False positive or not applicable? A repository writer can comment: |
The shared-template governance pass rewrote every crew-bound spec Crew does not own to filter its allowedTools/autoApprove, writing the user's own file in ~/.kiro/agents. kiro-cli loads that same file outside Crew, so the user's own sessions lost those grants, and a package manager reinstalling the spec fought the rewrite on every restart. Per the owner decision superseding the 2026-10-27 migration entry: - The pass never writes such a spec. KAS filters both lists against the live ceiling in its projection; a kiro-cli start on such a file is refused while the governance passes would narrow it (or it cannot be read), so no Crew session auto-approves a ceiling-denied tool. - The startup migration moves the rows that still reach such a file onto the conductor and their own crewmate file. A hooks/permissions/ toolsSettings restriction the file cannot carry no longer keeps a crewmate in place: it moves as is and its one notice names each dropped restriction. A gain is still only offered through the capability card. - A crewmate shadowed by its own private copy (a fork) moves after the copy is retired to ~/.kiro/mates/retired/; one shadowed by a spec Crew does not own stays, is told once, and that spec is never written. - A used row with no member_id (person- or package-written, DM thread holds a turn) is given an id and its own V2 store first, allocated as the upgrade allocates it so it keeps its slug. Closes #25289 (cherry picked from commit e778f71) Backport note: the HARNESS_EXEMPT_SETS row #25325 adds is dropped; that table is not on release/0.11.0 (same as the #25154 backport).
|
AI-review override not recorded: class |
3e9dc6a to
6b61b1a
Compare
|
AI-review override not recorded: class |
|
/ai-review override gpt 6b61b1a owner-decision: Ray (@buluoray, owner) confirmed the superseding 2026-10-28 decision at #25332 (comment) ; this backport carries #25332 and #25325 unchanged to release/0.11.0. |
Human judgment recorded@bolichen97 recorded a owner-decision release (class
This decision applies only to this commit. A new push requires a new judgment. |
|
/ai-review override first-principles 6b61b1a owner-decision: Ray (@buluoray, owner) confirmed this migration shape, including identity and store provisioning for used rows, at #25332 (comment) ; it shipped on main in #25325 and this backport is the same code. |
Human judgment recorded@bolichen97 recorded a owner-decision release (class
This decision applies only to this commit. A new push requires a new judgment. |
Problem / Motivation
Goal: Ship the #25325 bug fix on the 0.11.0 insider line.
#25325 (fixes #25289): Crew rewrote a crew-bound agent spec it does not own. This backports it to
release/0.11.0.Why it matters
The 0.11.0 insider (crewmate launch) users hit this bug. The fix is on its way into
main, not yet on the release branch.Not a goal
What changed (motivation → approach → change)
Two commits:
docs(decisions): docs(decisions): every crewmate on a user-level agent moves to the conductor #25332, the 2026-10-28 owner decision (Ray, @buluoray) that supersedes2026-10-27-every-used-crewmate-moves-to-the-conductor.md. fix(agent): never rewrite a crew-bound spec Crew does not own #25325's migration change (a crewmate whose hooks orpermissions/toolsSettingsrestrictions its worker drops now moves, with those named in its notice) rests on it, so it ships first.git cherry-pickof e778f71, the fix(agent): never rewrite a crew-bound spec Crew does not own #25325 head commit (merged on main as 99fd8a2, same change).Conflicts resolved by hand:
src/kiro_crew/agent_sdk/backends.pykeeps only #25325's ownACP_BACKENDS_SPEC_FILE_GRANTSlines; the neighbouringACP_BACKENDS_TEMPLATE_ADDITIONS_AT_SPAWNlines come from #25172, which is not on release. #25325'sHARNESS_EXEMPT_SETSrow inscripts/check_harness_parity.pyis dropped: that table is not on release/0.11.0 (same as the #25154 backport), so the script is unchanged.Backwards compatibility
Compatible: same change as #25325 on main.
Reader: src/kiro_crew/mate_config_migration.py:_candidates -- release -- the superseding decision (commit 1) records that a restriction now moves with the crewmate and is named in its notice; pinned by #25325's test_mate_config_migration.py and test_mate_upgrade_notice.py
Tests
test_harness_parity.pyandtest_backend_cards.py: 737 passed on this branch.mypy src/kiro_crewclean; flake8 clean on the changed files; harness gate passes againstorigin/release/0.11.0.Manual verification
N/A — verified on #25325 itself.
Related Issues
Backport of #25325 and #25332. Fixes #25289 on release/0.11.0.
Sibling sweep
Siblings: none -- a backport of one main fix; its sibling sweep is on #25325
Pattern harvest
Not generalizable: backport of #25325; its harvest is recorded on that PR.
Checklist
Contribution License Agreement
Contributed under the project's Apache-2.0 license.