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 8664400
Browse filesBrowse the repository at this point in the historyBrowse files
fix: no shipped text says the SQL driver reads organization-less rows, and the in-memory HTTP outbox no longer does
15
+
16
+
Clause-②: no (one fix and texts: the in-memory HTTP outbox's `redeliver()` now answers as `SqlHttpOutbox` already did; no accept set, served body or error code of a shipped composition moves)
17
+
18
+
ADR-0131 D8 retired the driver's `OR organization_id IS NULL` arm. Several shipped texts still described it as the live tenant predicate. They now state the current rule: the tenant term is `organization_id = :tenant`, or `IN (:tenants)` under the `group` posture, and nothing else. No tenant-scoped read reaches an organization-less row on a tenant table.
19
+
20
+
-**`@objectstack/service-messaging` — fix.**`MemoryHttpOutbox.redeliver()` no longer lets a tenant-scoped caller replay a row with no organization. It answers `RESOURCE_NOT_FOUND`, as `SqlHttpOutbox` does through the driver's tenant scope (ADR-0131 D8: no layer has a NULL arm). A caller with no tenant is still unscoped. No shipped composition constructs the in-memory outbox; the messaging plugin always builds `SqlHttpOutbox`. Code that embeds `MemoryHttpOutbox` directly sees the change.
21
+
-**`@objectstack/service-automation`.** The `[http]` node's warning for a durable callout with no organization no longer says the `sys_http_delivery` row is "a global row every organization's redeliver door can reach". It now says no organization's redeliver door reaches that row.
22
+
-**`@objectstack/objectql`.** The `sys_record_share` entry of the platform-object tenancy inventory carries an updated `evidence` text.
23
+
-**`@objectstack/lint`.**`os explain unique/legacy-organization-composite` now says that a new row carries its organization wherever the organization object is registered. A composition that registers no organization object still writes rows whose organization column is NULL.
24
+
-**`@objectstack/spec`.** The TSDoc of `SharingRuleRow` no longer calls it a 1-to-1 stored shape: `deploymentWide` has no `sys_sharing_rule` column. The TSDoc of `DriverOptions.tenantIds` and of the events `organizationId` member describe the predicate without a NULL arm.
fix(platform-objects): the password an administrator or user types into an action dialog is masked, no longer shown in clear text
6
+
7
+
Clause-②: no (an input's presentation: the param still accepts the same string, and no accept set or served shape moves)
8
+
9
+
Twelve credential params on the identity objects were declared `type: 'text'`, so the console's action dialog drew each as a plain text input and the typed password was readable on screen and in screenshots. Each now declares `type: 'password'`, which the dialog draws as a masked input:
10
+
11
+
-`sys_user`: `create_user`'s `password` and `set_user_password`'s `newPassword` (Setup › Users), `change_my_password`'s `currentPassword` and `newPassword`, and the `password` of `delete_my_account`, `enable_two_factor`, `disable_two_factor` and `generate_backup_codes`.
12
+
-`sys_two_factor`: the `password` of `enable_two_factor`, `disable_two_factor` and `regenerate_backup_codes`.
fix(plugin-auth): an administrator's impersonation session is not held by the target's forced password reset or password expiry (#24762)
6
+
7
+
Clause-②: no
8
+
9
+
Impersonating a user who must change their password used to strand the administrator: the impersonation session was refused `403 PASSWORD_RESET_REQUIRED` on every protected route, and the console showed the target's change-password screen. An impersonation session is minted from the administrator's own session, which has passed its own posture check, so it is not the user's password sign-in, and a `credential`-scope posture holds the password sign-in alone (`AUTH_GATE_SCOPES`).
10
+
11
+
-**What moves.** On a session that carries `impersonatedBy`, the session gate (`user.authGate`, stamped in `customSession`) now shows only the first `account`-scope posture the user holds. `PASSWORD_RESET_REQUIRED` and `PASSWORD_EXPIRED` no longer hold it. `MFA_REQUIRED` still does, so an impersonation session of a user who owes MFA enrolment is still refused `403 MFA_REQUIRED`, including when the user also owes a password change.
12
+
-**Unchanged.** The user's own sign-in stays held until they change the password. The forced reset's revocation (`revokeSessionsAndKeys`, on by default) still ends every session of the user, impersonation sessions included. API keys, the print door's refusal of an impersonation session, and the impersonation door's own check of the administrator's posture are unchanged.
fix(platform-objects): a team record no longer lists Sessions with "Sign out other devices" (#24765)
6
+
7
+
Clause-②: no (narrowing)
8
+
9
+
<!-- adr-0087: not-required (no-migration-prescription) One shipped object field gains `relatedList: false`, a key it was always free to set. No spec key, authorable spelling, export, type or stored shape is added, removed or renamed, and no stored row or column is read or rewritten, so `objectstack migrate meta` has nothing to rewrite. What narrows is one derived related list on a team's served detail page. The other categories are closed on facts: the package publishes (not unpublished); no ADR-0087 id covers this field (not already-registered); and the change is metadata on a shipped object, not an interface, a type or an export (not runtime-interface-only, type-surface-only or runtime-export-retired). -->
10
+
11
+
**BREAKING** for a reader of a team's derived related lists only: Setup → Teams → a team → Related no longer lists *Sessions*. Shipped as `minor` under the launch-window convention for accept-set narrowings.
12
+
13
+
-**Before.**`sys_session.active_team_id` is a lookup to `sys_team` that did not set `relatedList: false`, so every team record derived a Sessions related list. That list carried the session list's only toolbar action, "Sign out other devices", whose confirmation reads "Sign out of every other device where you're currently logged in?". The action signs out the administrator's own other sessions, not the team's.
14
+
-**Now.**`active_team_id` sets `relatedList: false`, so a team record derives no Sessions list. A team's Members and Invitations lists are unchanged.
15
+
-**Unchanged.** The `active_team_id` field, its lookup to `sys_team`, its label and its column: better-auth still writes `activeTeamId` there. A user record's Sessions tab (keyed on `user_id`), where "Sign out other devices" belongs, and the action itself.
16
+
17
+
**What to do.** Nothing. No team-scoped session action existed to lose.
fix(platform-objects): Rotate Client Secret's result dialog states the immediate cut-off its confirmation states
6
+
7
+
Clause-②: no (text only: no accept set, served shape or behaviour moves)
8
+
9
+
-**Before.** On `sys_oauth_application`, the Rotate Client Secret confirmation said the previous secret "will stop working immediately". The result dialog then told the admin to "update every integration before the previous secret's grace period ends". Only the first is true.
10
+
-**What rotation does.**`POST /api/v1/auth/oauth2/client/rotate-secret` is better-auth's own route. It overwrites the client's one stored secret, and client authentication checks a presented secret against that value only. No previous secret is kept, so there is no grace period: the old secret is refused from the moment the rotation completes.
11
+
-**Now.** The result dialog reads "Save the new secret now — it is shown only once. The previous secret has already stopped working: update every integration with the new secret." The zh-CN, ja-JP and es-ES translations of that sentence are updated to match. The confirmation, the dialog's title, acknowledgement and secret field are unchanged.
fix(plugin-auth): the vendored auth library records and keys on the client address the server established (#24799)
6
+
7
+
Clause-②: no
8
+
9
+
better-auth reads a request's client address with its own reader, and three things are keyed on what it reads: a session's `ip_address` (and the `login` / `logout` audit rows copied from it), the address on the `login_failed` / `account_locked` audit rows, and the key of better-auth's own per-address rate limiter. That reader did not follow `server.trustProxy`. It now follows the same rule as the `allowed_ip_ranges` allow-list and `last_login_ip`: `X-Forwarded-For` (its first entry), then `X-Real-IP`, count only when the stack declares `server.trustProxy`. Otherwise the address is the connection's peer address. When neither is available, better-auth is handed no address.
10
+
11
+
**For operators:**
12
+
13
+
- Behind a reverse proxy or load balancer, declare `server: { trustProxy: true }` in the stack. Without it, sessions and audit rows record the proxy's own address, and better-auth's per-address rate limit counts every client behind the proxy as one client.
14
+
- With `server.trustProxy` declared, a forwarded chain (`client, proxy`) now resolves to its first entry. Before, better-auth read a multi-entry header as no address.
15
+
- A request whose client address cannot be established records no address, and better-auth's rate limiter counts it in one shared bucket.
16
+
17
+
**For hosts:**`AuthManager.handleRequest` now drops any `x-objectstack-client-address` request header a caller sends. The platform writes that header itself, from the address it established, and better-auth reads no other header for the client address. A programmatic `auth.api.*` call is handed whatever headers its caller passes. Route a client's request through `handleRequest` instead.
fix(plugin-security): a platform operator's tenant-scoped insert from a session with no active organization is refused 403 naming the missing organization, as a member's is, instead of a 500
6
+
7
+
Clause-②: no (no accept set moves: the insert was refused before and is refused now, with the ADR-0123 D2 answer in place of an internal error)
8
+
9
+
-**Before.** Under `group` or `isolated`, a platform operator (`admin_full_access`) whose session had no active organization got `500 ERR_SYSTEM_WRITE_ORGANIZATION_REQUIRED` for a create on a tenant object whose posture lets it cross the organization wall (`access.default: 'private'`). The operator crosses the wall there, so the wall let the insert through, and the engine then refused the row as a system write with no organization.
10
+
-**After.** That create gets `403 PERMISSION_DENIED` with the message a member gets in the same state. The message names the missing active organization and tells the user to join or select one.
11
+
-**Unchanged.** Nothing was written before and nothing is written now. The refusal judges the row as it is about to be stored, the same row the engine's own organization check reads, so it covers exactly the inserts that answered 500 and no insert that was admitted. These are as before:
12
+
- a row a `beforeInsert` hook places in an organization;
13
+
- the operator's reads and updates across organizations;
14
+
- inserts from an operator with an active organization;
15
+
- inserts into objects that opted out of tenancy;
16
+
- system contexts (which still meet the engine's own refusal);
fix(service-settings): Setup → Authentication saves "Enable Google login" ON when the Google credentials come from the server (#24844)
6
+
7
+
Clause-②: no
8
+
9
+
On a deployment that sets `GOOGLE_CLIENT_ID` and `GOOGLE_CLIENT_SECRET` and leaves the two credential fields empty, saving `auth.google_enabled: true` was refused with `SETTINGS_VALIDATION` (`google_client_id` / `google_client_secret`: `required`). An admin who switched Google off on the page could not switch it back on there, although the server held valid credentials. The settings service reads only `OS_*` names, so it cannot see that pair.
10
+
11
+
`auth.google_client_id` and `auth.google_client_secret` are no longer `required`. Google sign-in needs the two credentials to resolve, saved on the page or set on the server; it never needed them stored. The `google_enabled` help already says so: Google is offered once both resolve, and the server's pair wins over saved values.
12
+
13
+
Who may sign in, and which providers the login page offers, do not change for any deployment. Saving the toggle ON while neither pair resolves is now accepted; the login page then shows no Google button, as it does with the toggle left at its default.
0 commit comments