Repository navigation
Commit e8a9387
<!-- claude-projects-attribution: {"github_login":"marchtian"} -->
_Requested by **田騏** · [project
thread](https://claude.ai/code/project/chan_01VmuUhXU9SSUzqJYyXSmYSi?thread=cmsg_01VmuUhXU9SSUzqJYyXSmYSiNjyvCdXYygFqntMNR7S2dW)_
Fixes #30590
Ruling-ref: 6663894403
Clause-②: no
Metadata-protocol: none
## 维护者速读
- **改了什么**:只改一个文件
`docs/adr/0125-release-approval-gate-replaces-the-typed-version.md`:末尾新增一节「Amendment
(2026-11-05, #29466)」,状态行加一条修订记录,D1 与 D4 下各加一条指向该节的「⚠️
Amended」提示(2026-09-29 修订的既有写法),D1–D6 正文一字未改。它把您裁决的 B 方案写进规范:稳定版发布照旧(QA
清单、Version Packages PR、您在 `release` 环境批准、发到
`latest`);另加一条只能手工触发、每天提议一次、仍由您批准的 `next` 快照发布通道,快照不打 tag、不建 Release、不碰
Version Packages PR、永不移动 `latest`,也不首发任何包(首发会写 `latest`,首发归稳定版通道)。
- **为什么改**:ADR-0125 D1 原本读作「版本提交是唯一的发布」,不先修订它,#30591 的 release.yml
快照通道就不能动工。修订后 D1 读作「版本提交是唯一的**稳定版**发布」。第二轮按独立复核的裁定补了四条对 #30591
的硬要求:不首发包、快照派发不跑任何稳定版作业、pre 模式下拒绝、只快照「全量测试恰在该提交通过」的提交。
- **风险与回滚**:纯文档,不改任何
workflow、脚本或代码,不新增任何裁决没有做的决定(本记录自己的两处解读已标明;三件未决事项在文内「Not decided
here」列出)。回滚 = revert 本 PR。
- **先看**:该文件末尾「What the lane must satisfy」七条(其中「The guard, and the debut
rule」是复核发现的必修项:`@objectstack/service-push` 在树里却从未发布过)和「What the ruling
binds」八条(与裁决评论 6663894403 逐条对应);其次是 D1、D4 下新增的两条提示。
- **两分钟验证**:打开文件末尾,把八条与裁决评论「What the ruling
binds」逐条对读;预期:每条都能在裁决里找到原句,标为「this record's reading」的只有两处,`latest`
永不被快照移动,每次快照仍需您批准。
- **需要您做的**:ADR 属 Tier H 受管面:独立复核通过后,由您合并(或入队)本 PR。
## What changes
One file, docs only. Round 2 (independent full review, round 1 FAIL,
record 6672362721) is folded in; the diff against `origin/main` is now
four hunks:
- the `**Status**:` line gains one `· **Amended** (2026-11-05, #29466
…)` entry, in the shape the 2026-09-29 entry set, pointing at the new
section;
- a `⚠️ Amended 2026-11-05` blockquote callout under **D1** and another
under **D4**, in the 2026-09-29 house shape — pointers to the new
section; D1 to D6 text is not rewritten;
- a new terminal section `## Amendment (2026-11-05, #29466): a
maintainer-approved next snapshot lane beside D1`, with: *Status of this
amendment* · *Why* · *What the ruling binds* (the eight bound lines of
ruling record 6663894403, numbered; two sentences marked as this
record's own readings — the trial start, citing seat note 6664069140,
and the D3 "removed in the same change" consequence) · *How D1 to D6
read with it* (D1 as amended is the only **stable** publish; D2 and D3
gate the snapshot job identically; D4's repair lane and `force`
untouched; D5's no-displacement property gains a third lane; D6 gains
nothing) · *What the lane must satisfy — requirements on #30591, not
workflow text*: the dist-tag guard **and the debut rule** (a fixed-group
member with no version on npm is refused, because a first publish takes
`latest` whatever tag it carries; `@objectstack/service-push` is that
case today), **dispatch-only and exclusive** (a snapshot dispatch runs
none of the stable lane's jobs, read like `refresh_version_pr`; the
snapshot job runs on no other dispatch; the un-sweepable stale-prompt
hazard named), **the commit** (the head of the newest green full-battery
run, distance zero under `scripts/ci/scheduled-full-run.mjs
--release-gate`, so the ruling's "at that commit" holds literally),
**not during a major's RC cycle** (`.changeset/pre.json` `mode: pre`
refuses; the release-channels table in `docs/releases-maintenance.md` is
a consumer #30591 updates), **workspace only** (bare `changeset version
--snapshot next`, never `pnpm run version`; consumed changesets and
rendered CHANGELOGs stay uncommitted), **the approval screen** (the name
must not match the stable prompt shape `release-pending-publish.mjs`
reads), **the dry run** (109-package fixed group, not 69; packed
manifests, since changesets leaves `workspace:*` ranges alone) · *What
stays forbidden* · *What does not change*, with a "Not decided here"
list.
Not touched, on purpose: the TL;DR (the ADR's own convention keeps
amendments out of it — the 2026-09-29 amendment did not touch it
either), the text of D1 to D6, the 2026-09-29 amendment,
`.github/workflows/release.yml`, and `docs/adr/README.md` (the index row
keys on the first status keyword, `Accepted`, so it is unchanged; `node
scripts/adr-index.mjs --report` answers "current").
## Tests
Docs only: no package moved, so local verification scope ① (dependency
closure) and ② (package tests and typecheck) are empty by rule. The
gates that read `docs/adr/**` are under Verification.
## Acceptance notes
- Governed surface (`docs/adr/**`, Tier H): this PR stays a draft with
no reviewers and no assignees. The seat orders the independent full
review and does the hand-off; landing is the maintainer's hand.
- Round 1 of the independent full review (record 6672362721 on this PR)
failed on M1 (the debut rule) and asked S1 to S5; every finding is
applied on this head as the seat ruled, and the review's observations
for #30591 now live in the amendment's requirements list. A re-render of
the review is owed on this head.
- No decision the ruling did not make is taken. The amendment lists
three items as "Not decided here", for the lane card and the maintainer:
whether a snapshot builds the runtime image (the ruling names npm
alone); the form the daily proposal takes; what becomes of the `next`
channel when the trial ends.
- Registry readings behind the text (read-only `npm view`):
`@objectstack/service-push` answers 404 while the tree carries it at
18.2.0 in the fixed group — the live debut case; `next` resolves to
18.2.0 (a stable version, which `scripts/release-dist-tags.mjs` leaves
alone by its own rule) and `latest` to 18.3.0. `.changeset/config.json`
carries no `snapshot` block, so `changeset version --snapshot next`
composes its default `0.0.0-next-` timestamp version shape — the dry run
the ruling asks for will show it; no `.changeset/pre.json` exists at
`origin/main`.
- Observation, not filed: the pre-existing `#10150` link on the Status
line (cited as a pull) answers 404 through the issues API; left as is.
## Verification
- Gate derivation for the final diff: `node
scripts/pm/dispatch-gates.mjs --commands --repo
objectstack-ai/objectstack` at head `8adeb7793e` (after the merge of
`origin/main` `ab44ec94b0`) derived 21 commands (13 matched by path, 8
whole-tree). All 21 ran at that head with each exit code captured before
any pipe; every one exited 0 on the first pass. Reconciliation
`dispatch-gates --ran`: 21 derived families accounted for, 21 run, 0 NOT
MEASURED. (Round 1 at `28c6fc09b8`: the same 21 green after one
prerequisite build of `@objectstack/formula` and `@objectstack/lint`
under the verify lock.)
- The 21, every one exit 0: check-adr-links (+ self-test),
check-closing-keyword-parity (+ self-test), check-comment-mask-corpus,
plan-test-core-shards self-test, lint check:doc-formula-expressions,
check:adr-anchors, check:adr-index, check:adr-symbol-anchors,
check:ci-filter-parity, check:closed-ceremony-text,
check:cross-package-test-inputs, check:doc-authoring,
check:driver-memory-census, check:gitlink-declared, check:nul-bytes,
check:pm-governed-merges, check:pm-prior-rulings,
check:refd-timer-probe, check:watch-hint-literal.
- `node scripts/adr-index.mjs --report`: exit 0 — "docs/adr/README.md is
current, every record parsed, self-test 46 assertions green".
- Control-character scan of the edited file: none. `git diff --stat
origin/main...HEAD`: 1 file, +69 / −1 — exactly one removed line (the
Status line); D1 and D4 gain appended callouts, no decision text is
rewritten.
- CI's own, not rerun locally: the whole-tree and wide-population
families, `check-issue-citations` (the citations this diff adds —
#29466, #30590, #30591, #24528, #25581 — resolve on the board), `Lint &
Repo Gates` and the other PR check-runs; their verdicts are read from
the PR, and this report does not wait for them.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
<!-- signed: domain:devx#2 · marchtian ·
session_017ihL2ebbZkr2QAEG1x7UC8 -->
---------
Co-authored-by: Claude <noreply@anthropic.com>
1 parent 6a983a1 commit e8a9387
1 file changed
Lines changed: 69 additions & 1 deletion
0 commit comments