This repository was archived by the owner on Nov 4, 2026. It is now read-only.
Repository navigation
Commit 7478334
test(console): parity ledger reads a retirement from the spec, and no older reason may hide one (objectui#10033) (#10391)
Fixes #10033
Clause-②: no
## The card's question, answered from the test's own population logic
**Is the waiver population derived from the spec at all?** Yes. And
retired keys are **in** it, in a special form. That makes this case (b)
of the dispatch.
- **Population.** `covered`, `registeredWithoutInputs` and `accounts for
every spec-carried block` all start from
`Object.keys(ComponentPropsMap)`. The partition test requires `covered`
∪ `registeredWithoutInputs` ∪ `UNJUDGED_SPEC_BLOCKS` to equal that set
exactly, with each block counted once.
- **A stale waiver (a key outside the population) is already caught, in
two places.** The first is the partition's converse (`accounted for a
block ComponentPropsMap does not carry`). The second is the ledger rot
check (`is ledgered but the spec no longer carries it — delete the
entry`). So this PR adds no new tripwire for that case.
- **Retired keys stay in the population, because the spec keeps their
rows on purpose.** The row is one of the retirement's refusal doors.
Readings from the installed `@objectstack/spec` 17.4.0
(lockfile-resolved), taken at base `ea02938cd`, using the
`@object-ui/test-support` tombstone judge:
| type | in `PageComponentType` | in `RETIRED_PAGE_COMPONENT_TYPES` |
row keys listed / tombstoned / authorable | empty bag parses |
|:--|:--|:--|:--|:--|
| `user:profile` | no | **yes** | 0 / 0 / 0 (`z.never`) | refused |
| `element:form` | no | no | 6 / 6 / 0 | accepted |
| `element:filter` | no | no | 6 / 6 / 0 | accepted |
| controls: `cloud-connection:panel`, `marketplace:installed-list`,
`mcp:connect-agent` | no | no | 0 / 0 / 0 | accepted |
Three things follow from that reading:
- **Mechanism assumption 3 is half false.**
`RETIRED_PAGE_COMPONENT_TYPES` has exactly one member, `user:profile`.
`element:form` left `PageComponentType` through the **element-grain**
retirement (objectstack#9249, listed in the spec's 17.3.0 changelog),
not through that table. `element:filter` left the same way earlier
(objectstack#9220, 17.1.0). So "read the spec's retired set" as that
table alone would not cover `element:form`.
- **Excluding retired rows from the population is the wrong way round.**
A registration of a retired type in this repo would drop out of
`covered` together with its row, and nothing would judge it.
objectui#8176 built this ledger to end exactly that absence. With the
rows kept in, such a registration is judged (every input it publishes is
off-spec) and is also counted twice, which the partition refuses.
- **Both waiver reasons the card names are false today.** `user:profile`
is false in both halves, as the card measured. `element:form` cites a
`block-types.ts` palette exclusion that says "no renderer — use the
object-bound `object-form` block". That entry was deleted by commit
`639114c4d`, the delivery of objectui#7122 through PR #7685. It now
appears in that file only as a note that the type is RETIRED UPSTREAM.
## What changed (test-only, one file plus an empty changeset)
1. **`isRetiredUpstream(type)`** reads both of the spec's retirement
spellings, and never a list kept here. A type counts as retired when it
is out of `PageComponentType` **and** one of these holds:
- it is named in `RETIRED_PAGE_COMPONENT_TYPES` (retired by name);
- its row lists keys and every one of them is a tombstone (retired at
element grain).
Leaving the enum is required but is not enough on its own: the controls
above are outside the enum too, and the predicate answers `false` for
them.
2. **A third ledger class, `RETIRED UPSTREAM`.** The rot check asserts
two things for it: `isRetiredUpstream(type)` is true, and the accepted
key set is empty. If upstream restores the type or gives its row a key,
the entry goes red.
3. **The class-closing guard.** An entry under `EMPTY SPEC SHAPE` or
`NOT REGISTERED, DELIBERATELY` now fails when the spec retires its type.
That is the check that stops a hand-written reason from outliving a
retirement, which is what happened to both entries here.
4. **Entries rewritten.** `user:profile` and `element:form` now say what
is true, citing the upstream ruling and landing (objectstack#14159,
objectstack#15112, objectstack#9249) and the objectui-side
reconciliation (objectui#7122).
- 1 parent 3ef0b51 commit 7478334
2 files changed
Lines changed: 89 additions & 5 deletions
File tree
- .changeset
- apps/console/src/__tests__
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
| 1 | + | |
| 2 | + | |
| 3 | + | |
| 4 | + | |
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
244 | 244 | | |
245 | 245 | | |
246 | 246 | | |
247 | | - | |
| 247 | + | |
| 248 | + | |
| 249 | + | |
| 250 | + | |
| 251 | + | |
| 252 | + | |
248 | 253 | | |
249 | 254 | | |
250 | 255 | | |
| |||
616 | 621 | | |
617 | 622 | | |
618 | 623 | | |
| 624 | + | |
| 625 | + | |
| 626 | + | |
| 627 | + | |
| 628 | + | |
| 629 | + | |
| 630 | + | |
| 631 | + | |
| 632 | + | |
| 633 | + | |
| 634 | + | |
| 635 | + | |
| 636 | + | |
| 637 | + | |
| 638 | + | |
| 639 | + | |
| 640 | + | |
| 641 | + | |
| 642 | + | |
| 643 | + | |
| 644 | + | |
| 645 | + | |
| 646 | + | |
| 647 | + | |
| 648 | + | |
| 649 | + | |
| 650 | + | |
619 | 651 | | |
620 | 652 | | |
621 | 653 | | |
| |||
632 | 664 | | |
633 | 665 | | |
634 | 666 | | |
635 | | - | |
| 667 | + | |
636 | 668 | | |
637 | 669 | | |
638 | 670 | | |
639 | 671 | | |
| 672 | + | |
| 673 | + | |
| 674 | + | |
| 675 | + | |
| 676 | + | |
| 677 | + | |
640 | 678 | | |
641 | 679 | | |
642 | 680 | | |
| |||
651 | 689 | | |
652 | 690 | | |
653 | 691 | | |
| 692 | + | |
| 693 | + | |
| 694 | + | |
| 695 | + | |
| 696 | + | |
| 697 | + | |
| 698 | + | |
| 699 | + | |
| 700 | + | |
| 701 | + | |
| 702 | + | |
| 703 | + | |
| 704 | + | |
| 705 | + | |
| 706 | + | |
| 707 | + | |
| 708 | + | |
| 709 | + | |
| 710 | + | |
| 711 | + | |
| 712 | + | |
654 | 713 | | |
655 | 714 | | |
656 | 715 | | |
| |||
662 | 721 | | |
663 | 722 | | |
664 | 723 | | |
665 | | - | |
| 724 | + | |
666 | 725 | | |
667 | | - | |
| 726 | + | |
668 | 727 | | |
669 | 728 | | |
670 | 729 | | |
671 | 730 | | |
672 | 731 | | |
673 | 732 | | |
674 | 733 | | |
675 | | - | |
| 734 | + | |
676 | 735 | | |
677 | 736 | | |
678 | 737 | | |
| |||
3707 | 3766 | | |
3708 | 3767 | | |
3709 | 3768 | | |
| 3769 | + | |
| 3770 | + | |
| 3771 | + | |
| 3772 | + | |
| 3773 | + | |
| 3774 | + | |
| 3775 | + | |
| 3776 | + | |
| 3777 | + | |
| 3778 | + | |
| 3779 | + | |
| 3780 | + | |
| 3781 | + | |
| 3782 | + | |
| 3783 | + | |
| 3784 | + | |
| 3785 | + | |
| 3786 | + | |
| 3787 | + | |
| 3788 | + | |
| 3789 | + | |
3710 | 3790 | | |
3711 | 3791 | | |
3712 | 3792 | | |
| |||
0 commit comments