Skip to content

Commit c658320

Browse files
docs(qa): wave-3 held checklist items — scope notes leave negative[], Studio save status, initialStates gap, capped bulk banner, locked settings row (#28551)
<!-- claude-projects-attribution: {"github_login":"marchtian"} --> _Requested by **田騏** · [project thread](https://claude.ai/code/project/chan_01VmuUhXU9SSUzqJYyXSmYSi?thread=cmsg_01VmuUhXU9SSUzqJYyXSmYSi9paTx1Lu8ENYwwssthfK3h)_ Fixes #28345 Clause-②: no Metadata-protocol: none ## 维护者速读 - 改了什么:按你对 5 处遗留项的裁决(全部 A)改了测试清单:28 条只写范围说明、无法判定的否定项挪进 `source[]`;Studio 顶栏「已保存」不算写入反馈;Studio 不能填 `initialStates`,该判据移出验收;批量全选超过 5000 条时横幅必须写明上限;组织管理员保存已锁定的设置应被拒。 - 为什么改:这些条目要么让测试员只能记「跳过」,要么判据和产品实际能力不符,要么缺一条权限边界的判据;不改,每轮巡检都会给出假的通过或假的失败。 - 风险与回滚:只动 5 个清单 JSON 文件,不碰产品代码、不进任何发布包;每个改动的条目 revision +1 并追加一行 history。回滚就是 revert 本 PR。 - 先看:`docs/qa/platform-checklist/areas/records-forms.json` 的 `records-forms.bulk-select-all-matching` 新增 acceptance[5];`platform-core.json` 的 `platform-core.settings-organization-isolation-and-platform-rung` 新增 negative[0];`studio-authoring.json` 的 `validation-rules-authoring`。 - 两分钟验证:在仓库根运行 `pnpm check:platform-checklist`,预期最后一行是 `check-platform-checklist: OK — 16 areas, 352 items`。 - 需要你做的:无,席位落地。 ## What changes Ruling-ref: 6545938831 Five checklist area files, no product code. Every edited item bumps `revision` by one and appends exactly one `history` row, dated 2026-11-01, `ref` #28345, naming wave anchor #27377. Main's history stays an exact prefix of each item's history. This was checked structurally: each file was re-parsed and compared with the original object plus the intended edit. **① Scope-note negatives move out of `negative[]` (28 items).** Each moved entry was its item's last negative, so no other negative index shifts. Each lands as the item's new last `source[]` row, the field sibling items already use for cross-refs (the #27651 precedent). A leading `SCOPE:` label now reads `cross-ref:`. The rest of each text is unchanged. - `studio-authoring.json`: all 24 active items whose last negative began `SCOPE:`. - `platform-core.notification-center` negative[3] (`cross-ref:`). - `access-security.permission-matrix-edit-loop` negative[2] (`cross-ref:`). - Same shape, different spelling: `access-security.record-view-read-audit` negative[2] (`cross-ref access-security.audit-log-browser …`). Its `automated.ref` called negative[2] a cross-reference, so that note now points at source[4]. - Same shape, different spelling: `records-forms.import-transform-matrix` negative[3] (`cross-ref guard: …`). **② `ux-conventions.write-feedback` acceptance[1].verify.** The Studio top bar's save status ('Saved' / 「已保存」) names no item, so it is not write feedback. A Studio row passes only on a toast or inline text naming the item or package. A row whose only feedback is that status scores FAIL. The clause wording is unchanged. **③ `studio-authoring.validation-rules-authoring`.** acceptance[3] no longer names `invalid_initial_state`, and steps[2] no longer asks for an initial state. A new `fixtures.knownGaps[0]` says why: Studio's Validations tab has no `initialStates` input, so the state can only be written through the API. `ObjectValidationsPanel.tsx` carries no `initialStates` at base 3718424. The insert-time code is still covered by `records-forms.validation-rule-type-matrix` variants[0]. This item's history merges its ① and ③ edits into one row. **④ `records-forms.bulk-select-all-matching`.** Adds acceptance[5] (dom oracle), steps[7] (a cap leg of more than 5000 scratch rows through `createMany`, at most 200 per call) and `fixtures.knownGaps[1]`. The new clause: past HARD_CAP 5000, the cross-page offer, the all-selected line and the selected count name the cap, for example 「将处理前 5000 条」. They must never present the uncapped total as the set the action processes. The clause is an expected FAIL today. The product defect card is owed, and the seat files it. No existing clause changed. **⑤ `platform-core.settings-organization-isolation-and-platform-rung`.** Adds the item's first `negative[]`. LOCKED means platform-locked. After steps[2]'s lock, A's organization administrator saving the same key again must be refused, with the value unchanged and the row still locked on re-read. A 2xx is a security FAIL. It is a walled leg, `blocked(fixture)` when unprovisioned, like acceptance[2] and [3]. steps[2] now drives it. The live measure the ruling asks for was run, and its result went to the seat thread. ## Tests Docs only: no package changed, so no build closure is owed and no package tests run. Local gates on head `5e7c1c9e`, with each exit code captured before any pipe: <details><summary>dispatch-gates --commands (16 families), every one run</summary> ```text 0 node scripts/check-adr-links.mjs 0 node scripts/check-adr-links.mjs --self-test 0 node scripts/check-closing-keyword-parity.mjs 0 node scripts/check-closing-keyword-parity.mjs --self-test 0 node scripts/check-comment-mask-corpus.mjs 0 node scripts/ci/plan-test-core-shards.mjs --self-test 0 pnpm --filter @objectstack/lint run check:doc-formula-expressions 0 pnpm check:ci-filter-parity 0 pnpm check:cross-package-test-inputs 0 pnpm check:doc-authoring 0 pnpm check:driver-memory-census 0 pnpm check:gitlink-declared 0 pnpm check:nul-bytes 0 pnpm check:platform-checklist 0 pnpm check:refd-timer-probe 0 pnpm check:watch-hint-literal ``` `--ran` reconciliation: `✓ dispatch-gates --ran: 16 derived famil(ies) accounted for — 16 run, 0 NOT-MEASURED (a DERIVED zero — all 16 recorded an exit code and none of them is 3).` `check-platform-checklist: OK — 16 areas, 352 items (347 active, 1 planned); coverage: 40 kinds mapped, 3 waived; traps: 19 documented, 19 in use; …` `check-platform-checklist --changed-from origin/main: OK — 1 anchored file(s) in the change set, 1 anchor(s) judged, 0 lost.` </details> ## Acceptance notes - Left in `negative[]` on purpose, for the seat to rule on: - `access-security.platform-owner-email-anchor` negative[3] ("out of scope here …"). Its `automated.ref` cites it by index. - `approvals.pending-count-surfaces` negative[1]. It carries a tracked product defect, objectui#4074, which fits `knownGaps` rather than a cross-ref. - `ux-conventions.disabled-control-reason` negative[1] and `ux-conventions.labels-over-machine-names` negative[1]. These are carve-outs of their own criterion rather than pointers to a sibling item. - Two retired items: `dashboards.report-schedule-dispatch-delivery` negative[3] and `access-security.packaged-permission-set-lifecycle` negative[3]. A retired item never runs. - The PM census figure of 38 counted every `SCOPE:` / `cross-ref:` string in the six files. The records-forms 7 and automation 3, and one of the dashboards 2, are already `source[]` rows, so there was nothing to move there. - ② edits acceptance[1].verify only. acceptance[0] ("visible feedback") still lists "an inline status" without excluding the top bar. - The `studio-authoring.expression-editors` mechanical fixes (vitest cwd, card refs, `record.FORMULA_FIELD` binding) are not taken. The census comment does not quote the exact text of its rows, so they stay with the seat's follow-up batch. ## Verification Each moved entry was diffed against its new `source[]` row: the same bytes apart from the `SCOPE:` → `cross-ref:` label. Every history row was checked: one `#28345` row per item, equal to `revision`, citing #27377. --- 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude <noreply@anthropic.com>
1 parent 0bf7aaf commit c658320

6 files changed

Lines changed: 320 additions & 138 deletions

File tree

‎docs/qa/platform-checklist/areas/access-security.json‎

Lines changed: 32 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -2307,7 +2307,7 @@
23072307
"title": "Editing the permission matrix and publishing flips an affected persona's live API access; revoke flips it back; assign/unassign moves access",
23082308
"since": "v16",
23092309
"status": "active",
2310-
"revision": 5,
2310+
"revision": 6,
23112311
"priority": "P1",
23122312
"surface": "mixed",
23132313
"personas": [
@@ -2372,8 +2372,7 @@
23722372
],
23732373
"negative": [
23742374
"an edit that repaints the matrix but whose PUT/publish never lands (M's access unchanged) is a FAIL — the network + M's live access are the oracles, not the checkbox paint",
2375-
"enforcement flipping on the DRAFT alone (before publish) is wrong: access must key on the PUBLISHED set",
2376-
"cross-ref: enforcement correctness is access-security.crud-permission-matrix and the read-only-package lock is access-security.readonly-package-locks-studio — this item is the WRITE/edit loop only"
2375+
"enforcement flipping on the DRAFT alone (before publish) is wrong: access must key on the PUBLISHED set"
23772376
],
23782377
"variants": [
23792378
"object-verb flip (CRUD)",
@@ -2391,7 +2390,8 @@
23912390
"packages/rest/src/rest-route-ledger.ts#REST_ROUTE_LEDGER (PUT /api/v1/meta/:type/:name saveItem; POST .../publish publishItem — re-pointed #18104: saveItem is a CLIENT METHOD name, carried in this file only inside a string value)",
23922391
"packages/metadata-protocol/src/sys-metadata-repository.ts#promoteDraft (the publish-with-nothing-pending refusal: status 404, code NO_DRAFT)",
23932392
"examples/app-showcase/src/security/permission-sets.ts",
2394-
"cross-ref access-security.crud-permission-matrix + access-security.readonly-package-locks-studio, ADR-0090 D1/D5, ADR-0033"
2393+
"cross-ref access-security.crud-permission-matrix + access-security.readonly-package-locks-studio, ADR-0090 D1/D5, ADR-0033",
2394+
"cross-ref: enforcement correctness is access-security.crud-permission-matrix and the read-only-package lock is access-security.readonly-package-locks-studio — this item is the WRITE/edit loop only"
23952395
],
23962396
"history": [
23972397
{
@@ -2413,6 +2413,12 @@
24132413
"date": "2026-10-31",
24142414
"change": "steps[2], [4] and [5] said 'save (draft) then publish'. The console Save on the Setup door lands active, as QA run #27441 measured. Source agrees: PermissionMatrixEditor.tsx's saveVersioned call adds mode 'draft' only when the editor is mounted with a packageId (Studio's Access pillar), and Setup's metadata-admin door mounts it with none, so its Save is a plain PUT that writes state 'active'. The steps now say Save, and that the publish call then answers 404 NO_DRAFT. acceptance[1] already scored both paths and is unchanged. Read from source at base efdddc9060. Wave anchor #27377, wave-3 accuracy slice S3; finding parked in anchor comment 6490438726",
24152415
"ref": "#27441"
2416+
},
2417+
{
2418+
"revision": 6,
2419+
"date": "2026-11-01",
2420+
"change": "negative[2] moved to source[6]: it was a scope note naming the items that own the neighbouring surfaces, which no run can decide, so it could only score skipped. Its text is unchanged. Ruling 6545938831 item ① on #28345 (scope notes leave negative[], which keeps only decidable entries; the #27651 precedent). No clause changed. Wave anchor #27377",
2421+
"ref": "#28345"
24162422
}
24172423
]
24182424
},
@@ -3087,7 +3093,7 @@
30873093
"title": "OS_PLATFORM_OWNER_EMAIL platform-admin anchor: only a VERIFIED stored-email match confers PLATFORM_ADMIN — unset, unverified match, non-match and malformed lists each confer nothing, fail closed",
30883094
"since": "v17",
30893095
"status": "active",
3090-
"revision": 12,
3096+
"revision": 13,
30913097
"priority": "P1",
30923098
"surface": "api",
30933099
"personas": [
@@ -3153,8 +3159,7 @@
31533159
"negative": [
31543160
"no runtime write reaches the anchor: OS_PLATFORM_OWNER_EMAIL is declared a NON-TABLE derivation input (admin-standing-surface.ts) — revocation is a configuration change plus a process roll, by design. Any in-product surface found mutating who is a platform administrator is an authorization finding: record it under RUNNER rule 2's carve-out (no card; one run-record row `area.item · clause · security finding — detail withheld, reported to PM`), never with a reproduction",
31553161
"the derivation reads the caller's OWN STORED sys_user row, never the session-seeded grants.email — the ⭐ P1 pin of the leg. That property is asserted by the unit pin (the '⭐ … reads the STORED row, never the seeded email' describe); do not attempt to re-prove it against a live server",
3156-
"run every refused probe as the seeded admin too: a 200 proves each refusal keyed on the member's standing, not on a broken route (wrong-persona, both sides)",
3157-
"out of scope here: the WALLED-posture boot refusal when the variable is unset (#11184) is plugin-auth's separate door — do not score it on this item"
3162+
"run every refused probe as the seeded admin too: a 200 proves each refusal keyed on the member's standing, not on a broken route (wrong-persona, both sides)"
31583163
],
31593164
"variants": [
31603165
"unset (zero config-derived admins)",
@@ -3171,7 +3176,7 @@
31713176
],
31723177
"automated": {
31733178
"kind": "dogfood",
3174-
"ref": "packages/qa/dogfood/test/platform-owner-email-anchor.dogfood.test.ts (#26571) restarts one showcase deployment per variable value on one database file, in the steps' order, with the datasource admin routes mounted as serve mounts them; probes are GET /datasources and GET /auth/me/permissions as member M and as the seeded admin. acceptance[0] — unset: M 403 PERMISSION_DENIED and no manage_platform_settings, the admin 200 on the grant anchor; acceptance[1] — the variable names unverified M: the same refusal; acceptance[2] — it names an address no row holds: the same, the admin still 200; acceptance[4]'s live leg — it names M after a system-context email_verified stamp (the knownGaps doorway): M 200 and every ADMIN_FULL_ACCESS_CAPABILITIES systemPermission; acceptance[3] — 'M, not an address' with M still verified and holding no admin_full_access grant: the [authz] refusal is printed once, naming the entry verbatim and the zero-administrator consequence, M is refused and the admin served; negative[0] — ADMIN_STANDING_NON_TABLE_INPUTS (@objectstack/core) declares {kind:'env', name:'OS_PLATFORM_OWNER_EMAIL'}; negative[2] — every refused probe has the admin's 200 beside it. A fresh database booted with a well-formed variable promotes only the declared owner (bootstrap-platform-admin.ts), so the variants run on one database first booted unset, as the steps restart one deployment. Unit pins beneath: packages/core/src/security/resolve-authz-context.platform-admin-config.test.ts (the acceptance criterion, all four fail-closed arms, the ⭐ stored-row-not-seed pin, the #11663 L5 posture split of the legacy grant anchor, the '[ADR-0131 D5] under `single` the Default Organization's admin_full_access grant is the anchor' describe) + packages/core/src/security/platform-admin.test.ts (parse/refusal/memo) + packages/core/src/security/admin-standing-surface.test.ts. acceptance[5] and negative[1] are test-scored; negative[3] is out of scope"
3179+
"ref": "packages/qa/dogfood/test/platform-owner-email-anchor.dogfood.test.ts (#26571) restarts one showcase deployment per variable value on one database file, in the steps' order, with the datasource admin routes mounted as serve mounts them; probes are GET /datasources and GET /auth/me/permissions as member M and as the seeded admin. acceptance[0] — unset: M 403 PERMISSION_DENIED and no manage_platform_settings, the admin 200 on the grant anchor; acceptance[1] — the variable names unverified M: the same refusal; acceptance[2] — it names an address no row holds: the same, the admin still 200; acceptance[4]'s live leg — it names M after a system-context email_verified stamp (the knownGaps doorway): M 200 and every ADMIN_FULL_ACCESS_CAPABILITIES systemPermission; acceptance[3] — 'M, not an address' with M still verified and holding no admin_full_access grant: the [authz] refusal is printed once, naming the entry verbatim and the zero-administrator consequence, M is refused and the admin served; negative[0] — ADMIN_STANDING_NON_TABLE_INPUTS (@objectstack/core) declares {kind:'env', name:'OS_PLATFORM_OWNER_EMAIL'}; negative[2] — every refused probe has the admin's 200 beside it. A fresh database booted with a well-formed variable promotes only the declared owner (bootstrap-platform-admin.ts), so the variants run on one database first booted unset, as the steps restart one deployment. Unit pins beneath: packages/core/src/security/resolve-authz-context.platform-admin-config.test.ts (the acceptance criterion, all four fail-closed arms, the ⭐ stored-row-not-seed pin, the #11663 L5 posture split of the legacy grant anchor, the '[ADR-0131 D5] under `single` the Default Organization's admin_full_access grant is the anchor' describe) + packages/core/src/security/platform-admin.test.ts (parse/refusal/memo) + packages/core/src/security/admin-standing-surface.test.ts. acceptance[5] and negative[1] are test-scored; the out-of-scope note that was negative[3] is source[10]"
31753180
},
31763181
"source": [
31773182
"packages/core/src/security/resolve-authz-context.ts#hasPlatformAdminStanding (§6b-config — the config anchor inside the ONE derivation site; additive, never subtractive) + (hasPlatformAdminStanding, the id-shaped projection)",
@@ -3183,7 +3188,8 @@
31833188
"packages/types/src/env.ts#PLATFORM_OWNER_EMAIL_ENV + packages/types/src/env.ts#resolvePlatformOwnerEmail (the variable's name, and its live per-call read)",
31843189
"packages/plugins/plugin-auth/src/auth-plugin.ts (#11343 — the dev seed stamps its admin's address verified)",
31853190
"packages/services/service-datasource/src/admin-routes.ts#DATASOURCE_ADMIN_CAPABILITY (the manage_platform_settings-floor probe)",
3186-
"#11663 L2 (the design and ruled bundle), #13146 (landed 2026-08-29), ADR-0068 D2 (the stored-grant anchor beside it)"
3191+
"#11663 L2 (the design and ruled bundle), #13146 (landed 2026-08-29), ADR-0068 D2 (the stored-grant anchor beside it)",
3192+
"out of scope here: the WALLED-posture boot refusal when the variable is unset (#11184) is plugin-auth's separate door — do not score it on this item"
31873193
],
31883194
"history": [
31893195
{
@@ -3257,6 +3263,12 @@
32573263
"date": "2026-10-29",
32583264
"change": "RUNNER rule 2's security-finding carve-out re-worded (#27382; maintainer rulings of 2026-10-29, recorded on #27377): a security finding gets no GitHub card at all, the run record carries the one row `area.item · clause · security finding — detail withheld, reported to PM`, and the reproduction goes privately to the dispatching PM session. negative[0] quoted the retired 'detail withheld pending maintainer' row and now names the new one. The same PR re-words every item string that quoted the retired row. No clause, oracle or status changed",
32593265
"ref": "#27642"
3266+
},
3267+
{
3268+
"revision": 13,
3269+
"date": "2026-11-01",
3270+
"change": "negative[3] moved to source[10]: it was a scope note (the walled-posture boot refusal is plugin-auth's door, not scored here), which no run can decide, so it could only score skipped. Its text is unchanged; automated.ref's closing note, which called negative[3] out of scope, now points at source[10]. Ruling 6545938831 item ① on #28345 (scope notes leave negative[], which keeps only decidable entries; the #27651 precedent). No clause changed. Wave anchor #27377",
3271+
"ref": "#28345"
32603272
}
32613273
]
32623274
},
@@ -3402,7 +3414,7 @@
34023414
"title": "Opt-in record-view auditing writes `read` rows for exactly the opted-in objects' detail reads, batched off the request path — stock boot audits nothing, excluded names refuse loudly, values never copied",
34033415
"since": "v17",
34043416
"status": "active",
3405-
"revision": 6,
3417+
"revision": 7,
34063418
"priority": "P2",
34073419
"surface": "api",
34083420
"personas": [
@@ -3467,8 +3479,7 @@
34673479
],
34683480
"negative": [
34693481
"an audit write must never break the read: reads answer 200 even when the ledger write fails — the failure is reported once per CAUSE with the durability text (read-audit.ts; #18247): a second, different cause reports again at error, and a repeat of a cause already reported degrades to debug. Rows are LOST, not retried. Observing that needs a broken ledger and is out of scope for a stock run; do not fabricate it",
3470-
"a read with no principal (no userId and no actor) lands no row — noise in the WHO ledger is refused by design (read-audit.ts)",
3471-
"cross-ref access-security.audit-log-browser — WRITE auditing, the browser UI, and the append-only guard belong there; this item owes only the read-writer's contract (one ledger, two items, no double-scoring). The append-only negative there covers action:'read' rows too: user-context POSTs to sys_audit_log are refused regardless of action"
3482+
"a read with no principal (no userId and no actor) lands no row — noise in the WHO ledger is refused by design (read-audit.ts)"
34723483
],
34733484
"variants": [
34743485
"stock boot (nothing audited)",
@@ -3485,13 +3496,14 @@
34853496
],
34863497
"automated": {
34873498
"kind": "dogfood",
3488-
"ref": "packages/qa/dogfood/test/record-view-read-audit.dogfood.test.ts (#26571) boots the showcase twice with the AuditPlugin serve would end up running (bootStack constructs none), reads rows through GET /data/sys_audit_log as the admin and keeps the 2 s flush. Stock (new AuditPlugin()): acceptance[0] — the boot log carries INFO lines and AuditPlugin lines (the positive control) and no 'record-view auditing installed' line; a member's GET /data/showcase_account/:id answers 200 and past the flush window the ledger holds no action 'read' row. Configured (readAudit.objects ['showcase_account', 'sys_job'], the docs' opt-in): acceptance[1] and [4] — one install line, 'on 1 object(s) — showcase_account', without sys_job, and the exclusion warning naming sys_job; acceptance[1] and [2] — one detail read lands exactly one row with action 'read', user_id = M, object_name, record_id, old_value and new_value null, and created_at inside the read's wall-clock window (before the flush could have run); acceptance[3] — a filtered LIST read that serves the record leaves the ledger count unchanged; acceptance[1] — an un-opted showcase_project detail read (200) lands no row. Unit pins beneath: packages/plugins/plugin-audit/src/read-audit.test.ts (discriminator, batching/flush, isSystem + no-principal skips, exclusion filter) + audit-plugin.test.ts. acceptance[5] stays test-scored; negative[0] needs a broken ledger and is out of scope for a stock run; negative[1] is the unit pin's no-principal skip; negative[2] is a cross-reference"
3499+
"ref": "packages/qa/dogfood/test/record-view-read-audit.dogfood.test.ts (#26571) boots the showcase twice with the AuditPlugin serve would end up running (bootStack constructs none), reads rows through GET /data/sys_audit_log as the admin and keeps the 2 s flush. Stock (new AuditPlugin()): acceptance[0] — the boot log carries INFO lines and AuditPlugin lines (the positive control) and no 'record-view auditing installed' line; a member's GET /data/showcase_account/:id answers 200 and past the flush window the ledger holds no action 'read' row. Configured (readAudit.objects ['showcase_account', 'sys_job'], the docs' opt-in): acceptance[1] and [4] — one install line, 'on 1 object(s) — showcase_account', without sys_job, and the exclusion warning naming sys_job; acceptance[1] and [2] — one detail read lands exactly one row with action 'read', user_id = M, object_name, record_id, old_value and new_value null, and created_at inside the read's wall-clock window (before the flush could have run); acceptance[3] — a filtered LIST read that serves the record leaves the ledger count unchanged; acceptance[1] — an un-opted showcase_project detail read (200) lands no row. Unit pins beneath: packages/plugins/plugin-audit/src/read-audit.test.ts (discriminator, batching/flush, isSystem + no-principal skips, exclusion filter) + audit-plugin.test.ts. acceptance[5] stays test-scored; negative[0] needs a broken ledger and is out of scope for a stock run; negative[1] is the unit pin's no-principal skip; the cross-reference that was negative[2] is source[4]"
34893500
},
34903501
"source": [
34913502
"packages/plugins/plugin-audit/src/read-audit.ts#READ_AUDIT_ACTION (READ_AUDIT_ACTION, installReadAuditWriter opt-in + exclusion filter, extractDetailReadId, buildRow nulls + view instant, isSystem/no-principal skips, batcher)",
34923503
"packages/plugins/plugin-audit/src/audit-plugin.ts#writer (wiring readAudit options into the writer; the install log line)",
34933504
"content/docs/permissions/record-view-auditing.mdx ('Under os serve' — the option-less auto-instance audits no views; last-one-wins supersession is the opt-in path; no metadata key / stack key / env flag by design)",
3494-
"#8992 (the card and the 2026-08-16 maintainer ruling: Option A scoped MVP — detail views only, per-object closed opt-in, async batched writes)"
3505+
"#8992 (the card and the 2026-08-16 maintainer ruling: Option A scoped MVP — detail views only, per-object closed opt-in, async batched writes)",
3506+
"cross-ref access-security.audit-log-browser — WRITE auditing, the browser UI, and the append-only guard belong there; this item owes only the read-writer's contract (one ledger, two items, no double-scoring). The append-only negative there covers action:'read' rows too: user-context POSTs to sys_audit_log are refused regardless of action"
34953507
],
34963508
"history": [
34973509
{
@@ -3529,6 +3541,12 @@
35293541
"date": "2026-10-27",
35303542
"change": "automated.kind unit -> dogfood (#26571 slice 3; the slice-2 ACCEPT noted it): revision 5's ref already leads with a dogfood pin over the in-process HTTP stack, with the unit pins beneath. No ref, clause or status changed",
35313543
"ref": "#26571"
3544+
},
3545+
{
3546+
"revision": 7,
3547+
"date": "2026-11-01",
3548+
"change": "negative[2] moved to source[4]: it was a scope note naming the items that own the neighbouring surfaces, which no run can decide, so it could only score skipped. Its text is unchanged, and automated.ref's closing note, which called negative[2] a cross-reference, now points at source[4]. Ruling 6545938831 item ① on #28345 (scope notes leave negative[], which keeps only decidable entries; the #27651 precedent). No clause changed. Wave anchor #27377",
3549+
"ref": "#28345"
35323550
}
35333551
]
35343552
},

0 commit comments

Comments
 (0)