Repository navigation
Conversation
Design Review (Fable 5) — ✅ PASSDesign-level review of Design-Verdict: PASS Verify Suggestions
[DESIGN-REVIEWED] 4d2206e Description read[DESCRIPTION-READ] dd5e2da51f6f41ed2c8b94dd340874892acbe772de865381482f2208e2f477b1 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 |
First Principles Review (Fable 5) — ✅ PASSPremise-level review of First-Principles-Verdict: PASS Nothing to check. What this change shipsInventory (4 items) — 4 justifiedIntent: FIX — the startup crewmate prune must never delete the row the loader would select as the default crew, including one made the default between the scan and the delete.
[FIRST-PRINCIPLES-REVIEWED] 4d2206e Description read[DESCRIPTION-READ] c28fa1b299be96d80e28c630fa20896990aaa0863d671d6a92e478effba04009 That sha256 names the PR description this verdict read. Recompute it with |
GPT 5.6 Review — 🔴 changes requested (blocking)GPT 5.6 found at least one blocking issue that must be resolved before merging This comment is updated in place on each push. BLOCKING -- src/kiro_crew/crewmate_prune_migration.py:322 -- Invalid agent records distort default resolution Adjudication (Opus 5) — is blocking on each finding proportionate?Harm: UNBOUNDED-class (silent rebinding of the default crew's workspace/memory store plus loss of its [ADJUDICATION] 4d2206e total=0 uphold=0 downgrade=0 False positive or not applicable? A repository writer can comment: |
Opus 5 Review — ✅ no blocking findingsReviewed Review detailsNo findings. FINDING — src/kiro_crew/crewmate_prune_migration.py:657 — [OPUS-REVIEWED] 4d2206e Verdict parsed from the review's SHA-scoped output markers for commit False positive or not applicable? A repository writer can comment: |
636c76a to
ceef710
Compare
|
Review dispositions for GPT 5.6 BLOCKING ( Opus 5 FINDING (feature-map:119, "the roster hides those") — fixed. Confirmed First Principles BLOCK (RFC §03 amendment ships in this diff) — needs a maintainer. The fix above narrows the reversal ( Design CONCERNS (edited rows with |
ceef710 to
cfed64d
Compare
|
Review dispositions for First Principles BLOCK (§03 amendment reversed accepted keep rules): fixed. The §03 amendment, the feature-map edit and the widened rule are gone; the keep rule, its docs and its marker are main's. Disabling the edited-row keep ( Hiding kept-but-never-chatted rows is #15363's: its roster lists a row unasked only when its DM thread holds a message, it was created on the dashboard, or it is the default crew, so a kept sync row nobody chatted with is hidden there. |
|
Review dispositions for GPT 5.6 F2 (edited sync rows deleted with their workspace): fixed by the same revert: a row whose shape differs from a fresh sync row is not a candidate. GPT 5.6 F1 (overlay Hiding kept-but-never-chatted rows is #15363's: its roster lists a row unasked only when its DM thread holds a message, it was created on the dashboard, or it is the default crew, so a kept sync row nobody chatted with is hidden there. |
|
Review dispositions for Opus 5 BLOCKING (private-fork row deleted, orphaning the fork): fixed. Private copies are excluded from candidates and re-checked under the spec lock, as on main. Opus 5 FINDINGs (RFC launch criterion; docstrings naming Hiding kept-but-never-chatted rows is #15363's: its roster lists a row unasked only when its DM thread holds a message, it was created on the dashboard, or it is the default crew, so a kept sync row nobody chatted with is hidden there. |
cfed64d to
bfaac01
Compare
|
Dispositions for Design CONCERNS and First Principles CONCERNS (base GPT 5.6 and Opus 5 reported no blocking findings on |
bfaac01 to
d5617ce
Compare
d5617ce to
27f0f64
Compare
|
GPT 5.6 disposition for BLOCKING ( |
|
First Principles disposition for CONCERNS (early base-default guard at |
The scan skips the default row as the merged config reads it, but the delete's in-lock re-check read neither document's default_agent. A name made the default between the scan and the delete -- `kirocrew config set default_agent <name>` in config.json, or `--local` in config.local.json -- was removed. The re-check now resolves the default from the two documents read under their locks exactly as the loader merges them -- the overlay's default_agent key when it carries one, else the base's, falling back to `default`, else the first row, when that names no row -- and refuses that row. The keep rule is RFC crewmates-launch section 03 as accepted: a generated row the owner edited (a model, avatar, triggers, colour, star, workspace, store), a row bound to a runtime-owned spec, a private copy or an uninstalled spec, and any kirocrew or app-stamped row stay.
27f0f64 to
4d2206e
Compare
|
Dispositions for GPT 5.6 BLOCKING ( First Principles CONCERNS (duplicate early guard): fixed in the same commit. |
|
Thanks for this, @buluoray! Closing because this draft has had no activity for over two weeks and main has moved on since. You are welcome to reopen it or open a fresh PR whenever you are ready. |
Problem / Motivation
Goal: The startup crewmate prune never deletes the default crew.
The scan skips the default row as the merged config reads it, but the delete's in-lock re-check read neither document's
default_agent. A row made the default between the scan and the delete --kirocrew config set default_agent <name>inconfig.json, or--localinconfig.local.json-- was removed.Why it matters
Deleting the default crew's row leaves the default pointing at a name with no record, so every surface that falls back to the default crew lands on nothing.
Not a goal
crewmates-launch§03 as accepted: a generated row the owner edited (model, avatar, triggers, colour, star, workspace, store), a row bound to a runtime-owned spec, a private copy or an uninstalled spec, and everykirocrewor app-stamped row are kept.What changed
remove_never_chattedresolves the default from the fresh base document (held under the base lock) and the overlay (read under its sidecar lock) as the loader merges them: the overlay'sdefault_agentkey when present, else the base's, falling back todefault, else the first row, when that names no row. That row is refused.crew-mode.mdstates the locked re-check covers both documents'default_agent.Backwards compatibility
Compatible: the pass refuses one more case and removes nothing it did not remove before. The marker name is unchanged.
Tests
TestCandidates::test_a_base_default_selected_under_the_lock_refuses_the_deleteand::test_an_overlay_default_selected_under_the_lock_refuses_the_delete: and::test_a_fallback_default_under_the_lock_refuses_the_delete: dropping each check fails its test (1 failure each)._is_fresh_sync_shapeanswering true) fails 34 tests, so the §03 keep rule stays pinned.test/test_crewmate_prune_migration.py.Manual verification
N/A: the pass runs once at startup against
config.json, and the unit test drives it against real temp config and overlay files.Related Issues
Follows #14897 and #15103. Hiding is #15363.
Pattern harvest
Not generalizable: a default-row check missing from one migration's locked re-check.
Checklist
feat|fix|docs|style|refactor|perf|test|chore|ci|build|revert: ...)Contribution License Agreement