You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 001b617
Browse filesBrowse the repository at this point in the historyBrowse files
fix(spec): the liveness ledger's `query.searchFields` row cites `engine-find.ts#expandSearchOnAst`, where the hand-off lives, so `check:liveness` is green again
6
+
7
+
Clause-②: no
8
+
Metadata-protocol: none
9
+
10
+
- The row cited `engine.ts#expandSearchOnAst`. The body has lived in `engine-find.ts` since the `engine.ts` codemod split, and the last mention of `searchFields` in `engine.ts`, a private docblock, moved out with the first slice of the hand-series docblock move, so the check found no mention of the key in the cited file.
11
+
- Nothing to do on upgrade: only the shipped `liveness/query.json` evidence text changes.
fix(metadata-protocol,rest): a `.custom` pair's declared override of a page, dataset, app, book, dashboard, view or report is labelled in the ruled order on every `/meta` read — the pair's own translation, then the override's own label, then the base's translation (#30062)
7
+
8
+
Clause-②: yes (widening) — `ObjectStackProtocolImplementation` gains six public methods: `getPackagedPageBase`, `getPackagedDatasetBase`, `getPackagedAppBase`, `getPackagedBookBase`, `servedOverrideBaseOf` and `getPairTranslationBundle` (measured on `packages/metadata-protocol/dist/index.d.ts`); `@objectstack/rest`'s exported `MetaBookTreeSources` accepts one more optional key, `resolveProtocol` (measured on `packages/rest/dist/index.d.ts`). No accepted key, value or answer is taken away.
9
+
Metadata-protocol: semantic
10
+
11
+
-**Now.** A changed label on a declared override reads the pair's own translation of that key when the pair ships one, else the override's own text, in every locale, on `GET /meta/:type/:name`, `GET /meta/:type` and `GET /meta/book/:name/tree`. An unchanged label still reads the base's translation. Before, a page, dataset, app or book override read the base's translation over its own changed label, and no type read the pair's translation first.
12
+
-**The pair's translations.** They are the pair's own active `translation` rows (`package_id` = the pair). A `.custom` package has no code bundle, so it has no code translation source. A package-less authored row is in the deployment catalog but is not the pair's, so it does not rank first.
13
+
-**Object.** An object is extended, never replaced (ADR-0146 D10), so it has no declared override and no pair bundle: seven types take one.
14
+
-**The book tree.**`GET /meta/book/:name/tree` now judges a book against its packaged base as the list does, so the docs sidebar and the book list serve the same label (#26690).
fix(plugin-auth)!: saving the auth settings refuses to turn off the last way to sign in (#30202)
7
+
8
+
Clause-②: yes (narrowing) — a save an administrator could make before is now refused at the settings save door with the existing `SETTINGS_VALIDATION` / `invalid_value` field error: a save after which email and password is off and nothing else signs anyone in, judged on the whole save, including the Google change that removes the last provider while email and password is off. No new error code or settings key. The widening half: `SettingsWritePredicateInput`, exported from `@objectstack/service-settings`, gains an optional `batch` field, the whole write a predicate is asked about.
9
+
Metadata-protocol: none
10
+
Skills-docs: none — no file under `skills/**` teaches `auth.email_password_enabled` or the settings write predicate; `content/docs/deployment/environment-variables.mdx` already names the `OS_AUTH_EMAIL_PASSWORD_ENABLED` override used for recovery below.
11
+
12
+
<!-- adr-0087: not-required (no-migration-prescription) No key of any schema is added, removed, renamed or re-shaped: auth.email_password_enabled and the auth.google_* keys keep their declarations, and the save door now refuses only the save that leaves no way to sign in. The predicate input's new batch field is optional and additive. A value stored before is not rewritten (the existing OS_AUTH_EMAIL_PASSWORD_ENABLED override recovers it), so there is nothing at rest for a migration to rewrite. -->
13
+
14
+
**BREAKING** accept-set narrowing at the auth settings save door (`PUT /api/settings/auth`, `SettingsService.setMany('auth', …)`): a save that would leave no way to sign in is refused, where it was saved before.
15
+
16
+
-**Before.** Setup → Settings → Authentication, "Enable email/password login" off, save: "Settings saved", with no social provider and SSO off. After the next sign-out nobody could sign in, the administrator included.
17
+
-**Now.** A save after which email and password is off and no other way in is in force answers `400 SETTINGS_VALIDATION`. The field error sits at `email_password_enabled` (`code: invalid_value`, `constraint.lastSignInMethod: email_password`), and its message, in the caller's language (en, zh-CN, ja-JP, es-ES), says to keep or set up another sign-in method before or in that save. Nothing in that batch is written, and email and password stays on.
18
+
-**The whole save is judged.**`{ email_password_enabled: false, google_enabled: false }` (or with `google_client_secret` cleared) on a deployment signing in with email and password plus Google is refused, with a field error at each of the two keys. Google filled in (switch, client ID and secret) in the same save that turns email and password off is accepted, and so is the switch alone over a client ID and secret already stored.
19
+
-**What counts as another way in.** A social or OIDC provider in force whose client ID and client secret are both set; enterprise SSO switched on with at least one identity provider registered (the switch alone does not count); phone-number sign-in; a host sign-in handoff the host declared. `ssoOnlyMode` alone, magic link, passkeys, and a provider listed without its credentials do not count.
20
+
-**The other direction.** While email and password is off, `google_enabled: false`, or clearing `google_client_id` / `google_client_secret` when no environment variable or stack config supplies it, is refused (`constraint.lastSignInMethod: google`) if Google is the last way in.
21
+
-**Already locked out.** Set `OS_AUTH_EMAIL_PASSWORD_ENABLED=true` and restart: the environment override wins over the stored `false`, and email and password sign-in comes back. Then set up another method before turning it off again.
22
+
-**For a write predicate's author (`@objectstack/service-settings`).**`SettingsWritePredicateInput.batch` holds every key the write sets in the namespace, the asked key among them, with the value it would store (`null` clears). `setMany` always passes it, frozen. A rule over several keys judges the state after the whole write from it instead of one key against the rest as they stand. Existing predicates need no change.
fix(cloud-connection,cli): the install-local ledger follows `OS_HOME`, so `os dev --fresh` and a second instance under another `OS_HOME` start without an earlier run's installs
7
+
8
+
Clause-②: yes (widening)
9
+
Metadata-protocol: none
10
+
11
+
-**Now.** With no `storageDir`, the install-local ledger (`LocalManifestSource`, and so `MarketplaceInstallLocalPlugin`) lives at `$OS_HOME/installed-packages` when `OS_HOME` is set, and at `CWD/.objectstack/installed-packages` when it is not. Before, it was always the working directory, so `os dev --fresh` (a fresh `OS_HOME` and database) rehydrated a package an earlier run installed, and so did a second instance under another `OS_HOME`.
12
+
-**Unchanged.**`os dev` without `OS_HOME` keeps the ledger in the project, beside its database. `os start` in project mode sets `OS_HOME` to `CWD/.objectstack`, which is the same directory as before. An explicit `storageDir` is used as given.
13
+
-**Existing installs.** When the ledger moved (an `OS_HOME` other than `CWD/.objectstack`) and its new directory does not exist yet, the boot copies the `.json` files of the working-directory ledger into it once, and logs a warning naming both directories. The old files are left in place and are not read again; remove them. A copy that fails is logged as an error, and the next boot tries again. Under `os dev --fresh` nothing is copied.
14
+
-**`os doctor`** reads the same directory the runtime does, `OS_HOME` included.
15
+
-**The widening.**`@objectstack/cloud-connection` exports `resolveInstalledPackagesDir({ env?, cwd? })` (returns `{ dir, legacyDir }`), `INSTALLED_PACKAGES_HOME_SUBDIR`, and `LocalManifestSource.legacyDir` / `adoptLegacyEntries()`. `os doctor` takes the ledger directory from `resolveInstalledPackagesDir`; a `@objectstack/cloud-connection` without it is reported as a reader that does not declare the ledger directory. Align the two packages' versions.
0 commit comments