docs(changeset): retire two present-tense "in-flight PR" claims before they publish (objectui#9706) (#9714)

Fixes #9706

Clause-②: no

Two unconsumed `.changeset/8478-*.md` bodies asserted, **in the present
tense**, that part
of their remaining scope was "held by in-flight PR ...". A changeset
body publishes
**verbatim** into the CHANGELOG, so at the next `@object-ui/types`
release these become
permanently published false statements about repo state. The window is
live: release pull
request objectui#5400 is open and its branch already carries both
sentences verbatim in
`packages/types/CHANGELOG.md`. Repairing the bodies on `main`
regenerates that branch.
⛔ Nothing here touches objectui#5400 or `changeset-release/main`.

## The two PR states, read live from the REST API before writing

Read at 2026-09-17, `GET /repos/objectstack-ai/objectui/pulls/NUMBER`,
not taken from the
card's restatement:

| PR | reading |
|---|---|
| objectui#8763 | `state=closed merged=true
merged_at=2026-09-09T08:11:20Z` |
| objectui#8799 | `state=closed merged=true
merged_at=2026-09-09T11:40:18Z` |
| objectui#8766 (control, cited in past tense already) | `state=closed
merged=true merged_at=2026-09-09T05:33:13Z` |

## What changed — one sentence per file, prose only

`.changeset/8478-describe-line-addresses.md`, before:

> The remaining 15 addresses (`form.zod.ts`, `layout.zod.ts`,
`complex.zod.ts`) are out of
> scope for this PR — held by in-flight PR #8763
(`form.zod.ts` /
> `layout.zod.ts`); `complex.zod.ts`'s hold (PR
#8766) cleared when
> that PR merged during this round, so its 6 addresses return to the
queue rather than
> riding this PR's scope.

after:

> The remaining 15 addresses (`form.zod.ts`, `layout.zod.ts`,
`complex.zod.ts`) were out
> of scope for this PR — `form.zod.ts` / `layout.zod.ts` were held while
PR
> #8763 was open; `complex.zod.ts`'s hold (PR
> #8766) cleared when that PR merged during this
round, so its 6
> addresses returned to the queue rather than riding this PR's scope.

`.changeset/8478-zod-pins-form-layout.md`, before:

> The remaining 6 addresses (`zod/complex.zod.ts`) stay out of scope for
this PR — held by
> in-flight PR #8799 — and the card does not
close here.

after:

> The remaining 6 addresses (`zod/complex.zod.ts`) stayed out of scope
for this PR and
> returned to the queue rather than riding this PR's scope — the card
did not close here.

Neither replacement contains a present-tense assertion about any other
PR, branch or card
— that is the defect class itself, and a repair that reintroduced it
would rot the same
way. The `objectui#8766` clause in the first file was left **verbatim**:
it was already
past tense and accurate, and it is not this card's target.

## The six `complex.zod.ts` addresses — the contradiction, settled

The two bodies disagreed about the same six addresses: the first said
the hold cleared and
the six returned to the queue; the second (written later) said those six
were held by
in-flight objectui#8799. **The first is the true one**, and both now say
the same thing.
Evidence, in order of decisiveness:

1. **The second claim was already false when it landed.** objectui#8799
merged
`2026-09-09T11:40:18Z`. The pull request that introduced that body,
objectui#8822,
merged `2026-09-09T12:52:14Z` — 72 minutes later. The sentence was born
describing a
   state that had already ended.
2. **A separate PR carried the six.** objectui#8835 (`fix(types): drop
stale source-line
citations from 6 published describe() strings`) merged
`2026-09-09T13:31:48Z`; its file
   list is exactly `.changeset/8478-zod-pins-complex.md` (added) and
`packages/types/src/zod/complex.zod.ts` (modified). The six went back to
the queue and
were picked up on their own, which is precisely what the first body said
would happen
   and the opposite of "riding objectui#8799's scope".
3. **objectui#8478 reached `state=closed`** at `2026-09-09T13:31:50Z`,
two seconds after
   objectui#8835 merged.
4. **The tree agrees today.** A paren-matching scan of every
`.describe()` argument on
`396a1c198` finds **0** `NAME.ext:NNN` addresses in `complex.zod.ts`
(167 `.describe()`
calls), `form.zod.ts` (203) and `layout.zod.ts` (91). Lit control on the
same corpus:
the bare address matcher still fires 7 times in `complex.zod.ts` — in
`//` and JSDoc
   comments, which were never in objectui#8478's population.

⚠️ Also checked: objectui#8799 **did** modify `complex.zod.ts`, so it
was a genuine hold
while it was open. The defect is the tense, not the attribution.

## Scope — exactly two files

```
 .changeset/8478-describe-line-addresses.md | 10 +++++-----
 .changeset/8478-zod-pins-form-layout.md    |  4 ++--
```

Frontmatter untouched, and that is measured rather than asserted:
`check-changeset-overwrite` prints `declared at base: @object-ui/types:
patch` /
`declares now: @object-ui/types: patch` for both files.

## Gates — exit code captured to disk before any pipe

| gate | exit | printed verdict |
|---|---|---|
| `pnpm check:changeset-claims` | 0 | `No pending changeset names a file
this change touches.` (report-only) |
| `node scripts/check-changeset-overwrite.mjs` | 0 | 2 modified, both
`@object-ui/types: patch` at base and now — the gate's own case 2,
"CORRECTING a declaration on purpose ... prose that no longer matches"
(report-only) |
| `node scripts/check-changeset-presence.mjs` | 0 | `No source or
published contract of a released package changed in this range, so no
changeset is owed.` |
| `node scripts/check-changeset-fixed.mjs` | 0 | `All workspace packages
are in the changeset fixed group.` |
| `node scripts/check-changeset-no-major.mjs` | 0 | `No changeset
declares a major bump.` |
| `pnpm check:control-bytes` | 0 | `OK (scanned 7814 tracked text
file(s); skipped 85 binary)` |
| `pnpm check:new-line-citations` | 0 | `0 new citation(s), enforcement
report-only`, with its own four synthetic controls PASSing |
| `pnpm check:pending-changeset-literals` | 0 | `No test source names a
pending changeset.` |
| `node scripts/check-governed-queue-guard.mjs --test` on both paths | 0
| `NOT GOVERNED — 2 path(s) checked against 5 governed surface(s)` |

Controls, because a zero on an unlit instrument is not a reading:

- Governed guard, lit: the same script on `AGENTS.md` exits **3**,
`GOVERNED`.
- Control-byte scan of the two files: `grep -naP` exits **1** (no hits);
the same
  expression on a file holding one BEL byte exits **0**.
- The in-flight scan below reads **0** on a corpus where the lit control
reads **1327**.

⚠️ The census is deliberately **not** a `git grep`: these bodies wrap at
about 80
columns and the offending sentence wraps mid-phrase, so a line-anchored
matcher cannot see
it. The scan collapses whitespace per file first. Before: 2 hits. After:
0, lit control
1327 files of 1637, absent control 0.

No source file moved, no released package moved, no other changeset
touched. Nothing owed
in `pnpm test` / `pnpm lint`: the diff is markdown prose in
`.changeset/`, and no package
source changed. Repository-wide scans belong to CI.

## Deliberately not done

- Other pending changesets of the same shape are **reported, not
repaired** —
objectui#9713 already tracks that wider class and the routing is the
PM's. The
whitespace-tolerant census over all 1637 pending declarations found no
other "in-flight
PR" claim; the one adjacent observation is recorded in the report rather
than acted on.
- objectui#5400 and `changeset-release/main`: untouched, unread beyond
what the card
  already recorded, not commented on.

---
_Generated by [Claude
Code](https://claude.ai/code/session_01UanLVj6xvbS6puBCewLr8L)_

Co-authored-by: Claude <noreply@anthropic.com>

Author: os-sales

.changeset/8478-describe-line-addresses.md

@@ -18,8 +18,8 @@ description) was measured to have already drifted — the cited line is now unre
 permissions code; the real read site is `ObjectKanban.tsx:365`. Filed back on
 objectstack-ai/objectui#8478 as the drift evidence its own re-grade trigger asked for.
 
-The remaining 15 addresses (`form.zod.ts`, `layout.zod.ts`, `complex.zod.ts`) are out of
-scope for this PR — held by in-flight PR objectstack-ai/objectui#8763 (`form.zod.ts` /
-`layout.zod.ts`); `complex.zod.ts`'s hold (PR objectstack-ai/objectui#8766) cleared when
-that PR merged during this round, so its 6 addresses return to the queue rather than
-riding this PR's scope.
+The remaining 15 addresses (`form.zod.ts`, `layout.zod.ts`, `complex.zod.ts`) were out
+of scope for this PR — `form.zod.ts` / `layout.zod.ts` were held while PR
+objectstack-ai/objectui#8763 was open; `complex.zod.ts`'s hold (PR
+objectstack-ai/objectui#8766) cleared when that PR merged during this round, so its 6
+addresses returned to the queue rather than riding this PR's scope.

.changeset/8478-zod-pins-form-layout.md

@@ -20,5 +20,5 @@ marker site now `:52`) and `text.tsx:162,167` (actual `{schema.content}` sites n
 `:165`/`:170`). Filed back on objectstack-ai/objectui#8478 as further drift evidence for
 its own pre-committed p3-to-p2 re-grade trigger.
 
-The remaining 6 addresses (`zod/complex.zod.ts`) stay out of scope for this PR — held by
-in-flight PR objectstack-ai/objectui#8799 — and the card does not close here.
+The remaining 6 addresses (`zod/complex.zod.ts`) stayed out of scope for this PR and
+returned to the queue rather than riding this PR's scope — the card did not close here.