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 ca3cc56
Browse filesBrowse the repository at this point in the historyBrowse files
feat(cli,metadata-protocol): `os migrate packageless-overlays` moves package-less Setup customizations of a package's view, dashboard, report, translation or email template into its paired `.custom` package as declared overrides
7
+
8
+
Clause-②: yes (widening)
9
+
Metadata-protocol: added
10
+
Skills-docs: none — the one taught line this touches, `skills/objectstack-platform/SKILL.md`'s "a package-unbound Setup row still wins over the base's until D11", stays true: the ceremony moves such rows when an operator runs it, and the package-less write that makes new ones stays open until #28576, which is the change that retires that line. No file under `skills/**` teaches the `os migrate` operator ceremonies (a `git grep` of `skills/` for `packageless` and `security-catalog-overlays` names nothing).
11
+
12
+
**The one operator step of this release.** After upgrading, run `os migrate packageless-overlays` once (preview), then `os migrate packageless-overlays --apply`, on each deployment that has Setup customizations. Until it runs, those customizations are still served, but they stay rows of no package: they are not exported and do not reach another environment.
13
+
14
+
-**What moves.** Every `sys_metadata` row bound to no package, of the five overlay types (`view`, `dashboard`, `report`, `translation`, `email_template`, active or draft), over a name exactly one installed read-only package ships. It moves into that package's paired `<base>.custom` — created through the ensure door when absent and persisted to `sys_packages` — with `overrides: { package: <base>, basedOn: <the base's installed version> }` in its body, saved through the metadata save door in its own state. The new row is read back as the served override, and only then is the package-less row deleted (with its history tombstone). Every read of the name serves the same content as before. A second run moves nothing.
15
+
-**What is left alone, and listed.** A name several packages ship; a row whose body already declares an override of another package; and a row the pair already overrides, active or draft (a customization made in Studio first — the report names the two ways out: delete the package-less row, or "Restore package original" in Studio and re-run). A name no package ships is environment metadata and is not touched. Permission sets and positions are not overlay types; `os migrate security-catalog-overlays` is theirs.
16
+
-**Declarations missing `basedOn`.** A row of a pair, of any type a declared override applies to, that declares `overrides: { package }` with no `basedOn` is read as an override but refused on its next save. The same command records `basedOn` (the base's installed version) on it.
17
+
-**Setup keeps working on a moved item.** Until the package-less write closes, a save that names no package and lands on a moved row (Setup's form save and reset) keeps that row's `overrides` block when the body carries none, and is judged as the write into the pair when the body carries one — so it is no longer refused `403 NOT_OVERRIDABLE`. A package-less delete removes the pair's row, and the package's own document is served again.
18
+
-**Flags.**`--apply` (with `--yes` or the prompt), `--json`, `--force` past a busy SQLite file, `--database-url`, and `serve`'s `--preset` / `--dev`. The command is the operator's; the HTTP door that creates a pair keeps its walled refusal.
19
+
20
+
`ObjectStackProtocolImplementation` gains `listPackagelessOverlays()` and `migratePackagelessOverlays({ actor })`.
fix(objectql,formula): a formula field whose `date()` / `datetime()` is handed text it cannot parse is a reported evaluation fault, not a silent null
7
+
8
+
Clause-②: no
9
+
Metadata-protocol: none
10
+
11
+
A formula field such as `date(record.first)` on a row whose `first` holds text that is not a date (`"grace"`) read `null`, the same bytes an empty `first` gives, and nothing was logged. `date()` / `datetime()` answer an invalid Date for such text, the evaluator reports that as a success, and the invalid Date serializes to `null`, so the once-per-field formula fault line never fired.
12
+
13
+
-**The field now reports it.** The read path (`find`, `findOne` and a write's response) treats that invalid Date as an evaluation fault: the field reads `null` exactly as before, and the engine's logger gets the one `warn` line per object and field per engine instance that every other formula fault gets. The line says that `date()` / `datetime()` take ISO text, a timestamp or epoch milliseconds. The record's text is not quoted in the log. A date function over the bad value (`addDays(date(record.first), 1)`) reports the same way.
14
+
-**An empty source is not a fault.**`null`, empty or blank text still reads `null` with no line.
15
+
-**Predicates are unchanged.**`date()` still answers the same invalid Date, so `date(record.d) == today()` over non-date text is still `false`, and `visibleWhen`, validation rules and filters answer as before. `isoDate()` and `daysBetween()` over it still refuse at evaluation.
16
+
-**`@objectstack/formula` gains `isUnparseableDate(value)`**: `true` for the invalid Date `date()` / `datetime()` (or `addDays` / `addMonths` over it) answered for non-empty text they could not parse, `false` for everything else, including an invalid Date from an empty source. It reads a weakly held mark and never changes what any function returns.
17
+
-**What a read returns over the wire does not move.** In process, `ObjectQL#find` now hands back `null` for such a field where it handed back an invalid `Date`; serialized, both are `null`.
0 commit comments