Skip to content

Commit 7913854

Browse files
committed
Merge origin/main into claude/project-thread-1kqwvu
Resolves packages/spec/liveness/action.json by hand: main's in-repo evidence, evidenceScope and producer for onSuccess.navigate, with this branch's #25800 note sentence (already pointing at in-repo ui/ paths) kept on main's note. Claude-Session: https://claude.ai/code/session_013w86pS2SMm6BU2PfGQ3vJ7 Co-authored-by: Claude <noreply@anthropic.com>
2 parents 5dc4881 + 7111e14 commit 7913854

130 files changed

Lines changed: 6299 additions & 1409 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.
Lines changed: 24 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
---
2+
'@objectstack/spec': minor
3+
'@objectstack/service-automation': minor
4+
'@object-ui/app-shell': minor
5+
---
6+
7+
feat(spec,automation,app-shell): a flow screen field typed `file` collects an upload, and the run resumes with the uploaded file's id
8+
9+
Clause-②: yes (narrowing)
10+
Metadata-protocol: semantic
11+
12+
<!-- adr-0087: not-required (no-migration-prescription) No metadata moves: no spec key, authorable spelling, object definition, stored row or stored shape is added, removed, renamed or re-shaped. `ScreenFieldConfigSchema.type` stays an open string, so every flow that parsed before still parses, and nothing exported is removed or narrowed. What changes is what a screen field already declared `type: 'file'` means: the console renders the upload widget for it, and the resume door refuses a value that is not a file id. The remedy is a change in what a caller posts to `resume` (the uploaded file's id), never a rewrite of a package source or a stored row, so there is nothing for `objectstack migrate meta` to rewrite. The other categories are closed on facts: the three packages publish (not unpublished); no ADR-0087 id is named or touched (not registered or already-registered); and no runtime interface, type or export is removed or narrowed (not runtime-interface-only, type-surface-only or runtime-export-retired). -->
13+
14+
A wizard can now ask for a file before the record that will own it exists, and write everything after its last screen.
15+
16+
- **`@objectstack/spec`**: `ScreenFieldConfigSchema.type` (and the `ScreenFieldSpec` contract) documents `'file'` as the second value domain beside `'number'`. A `type: 'file'` field renders the platform upload widget. The upload goes through the file service and lands as a `sys_file` that no record owns yet. The resume carries that file's id, which is ADR-0104 D3's stored form, and nothing else. A later `create_record` or `update_record` node writes the id into an object's `file` field, and that write claims the file for the record. Under the default `runAs: 'user'`, the claim first makes the download door's read check as the run's user; a `runAs: 'system'` run's write is not checked, as no system write is.
17+
- **`@objectstack/service-automation`**: the resume re-checks a `type: 'file'` field as a value domain. A value that is not a file id, judged by the spec's `isFileIdToken` (the same predicate the claim path reads), is refused with `400 INVALID_SCREEN_INPUT` and the field code `invalid_type` ("must be the id of an uploaded file"). That covers a URL, the expanded `{ id, name, url, … }` read form, a list and a number. The value is never reduced to an id. The refusal writes nothing and keeps the pause, so a corrected resume still lands. An empty optional field and a hidden field are not judged. `image`, `avatar`, `video` and `audio` stay open widget hints.
18+
- **`@object-ui/app-shell`**: the flow screen dialog renders the object form's `FileField` for a `type: 'file'` field and uploads through the console's `UploadProvider`. While an upload is in flight, Submit is disabled and reads "Uploading…". The resume posts each file field as its bare id, and a prefilled expanded value is reduced to its id first.
19+
20+
**BREAKING** (a resume-acceptance narrowing) for a flow whose `screen` node already declares a field `type: 'file'`. None was found in this repository's examples or packages.
21+
22+
- **Before.** `type: 'file'` was an open widget hint the console did not know, so the field rendered a plain text input, and `POST /automation/:name/runs/:runId/resume` accepted any value for it.
23+
- **Now.** The field renders the upload widget, and the resume refuses any value that is not a file id with `400 INVALID_SCREEN_INPUT` (`invalid_type`). The refusal keeps the pause.
24+
- **Fix.** A caller that resumes the run itself, without the console, uploads the file through the file service first and posts the minted `sys_file` id for the field: FROM `{ "contract_file": "https://…/nda.pdf" }` TO `{ "contract_file": "FILE_ID" }`. A field that was never meant to collect an upload takes another `type`, such as `text`.
Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,14 @@
1+
---
2+
'@object-ui/fields': patch
3+
---
4+
5+
fix(fields): a lookup's option subtitle no longer repeats the record name when the referenced object's name field is not `name`
6+
7+
Clause-②: no
8+
Metadata-protocol: none
9+
10+
The quick-picker shows each candidate as its title over a subtitle of the referenced object's other columns. A lookup that declares no `displayField` titles the option through the referenced object's name field (`nameField`, else the derived title field), but the subtitle skipped only a field literally called `name`. On an object whose name field is `title`, `customer_name` or any other name (every AI-built object), the subtitle's first and widest slot repeated the title and pushed the column that tells two records apart, such as a phone number, into truncation.
11+
12+
The subtitle now also skips the referenced object's resolved name field when the lookup declares no `displayField`. Unchanged: a declared `displayField` is the field skipped, so the object's name field stays in the subtitle; an object titled by a `titleFormat` template keeps every field in the subtitle; an explicitly authored `descriptionField` still leads the subtitle.
13+
14+
What to do: nothing.
Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
---
2+
'@object-ui/app-shell': patch
3+
---
4+
5+
feat(ui): the Studio permission-set form offers the field permission `when` (row condition on the edit vote)
6+
7+
Clause-②: yes (widening)
8+
Metadata-protocol: none
9+
10+
Part of #25866 — the Studio clause of ruling 6408558941 (part ①, item 4), after #25980 landed the key itself.
11+
12+
- **Before.** The permission matrix's field rows carried two checkboxes, `readable` and `editable`: no way to offer or see a `when`. The Read-off cascade could leave `readable: false` beside an authored `when` (the shape the spec refuses at publish), and the Read all / Write all shortcuts dropped the condition.
13+
- **Now.** Each field row carries **When (edit)**: an authored condition shows as a chip, and the row opens the same CEL editor the row-level-security clauses use, linted the same way; a finding the publish gate would refuse holds the save. Read off clears the condition, Read all / Write all keep it, Clear drops the entry, blank text removes the key. `FieldPerm` gains `when`, carried verbatim by the package-door slice merge.
Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
1+
---
2+
'@object-ui/i18n': patch
3+
---
4+
5+
fix(i18n): the Chinese account menu's sign-out item reads 「退出登录」, not 「注销」
6+
7+
Clause-②: no
8+
Metadata-protocol: none
9+
10+
In the `zh` pack, `user.logout` read 「注销」, which a Chinese reader takes as "delete my account", on the menu every signed-in user opens. It now reads 「退出登录」, the wording the same pack already uses for signing out elsewhere. No key is added or removed; other locales are unchanged.
Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
---
2+
'@object-ui/plugin-detail': patch
3+
---
4+
5+
fix(plugin-detail): the record page's read mode wraps a text value instead of cutting it to one line, and a highlighted date keeps its day
6+
7+
Clause-②: no
8+
Metadata-protocol: none
9+
10+
- **Details body.** A `text` field in a `record:details` section, read mode, was drawn with the grid's one-line cell (one line, an ellipsis), so a case subject read "Data export timing out for large…" in a two-column section with room to spare. It now reads through the text field's own read display and wraps, as a `textarea` already did. The same holds for every type that used the grid's text cell (`code`, `time`, `auto_number`, …). A host that registered its own cell renderer for one of those types keeps it. Grid cells are unchanged and still truncate, with the whole value on hover.
11+
- **Highlights strip.** A `date` or `datetime` chip now takes the wide column (16rem floor) that email, phone and URL chips take. On the 9rem column the compact datetime face, and a date in Chinese or Japanese, overran the value box, so the ellipsis landed inside the day ("2026/10/2…"). A chip whose line runs out still truncates, with the whole value as its hover title.
12+
13+
What to do: nothing.
Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,14 @@
1+
---
2+
'@object-ui/plugin-grid': patch
3+
---
4+
5+
fix(plugin-grid): a bulk action's `confirmText` fills its `{{ count }}` hole with the number of records the run covers
6+
7+
Clause-②: no
8+
Metadata-protocol: none
9+
10+
A bulk action's `confirmText` is a `template` slot, and its declared scope names `count`, the number of records the run will cover. The bulk dialog printed the sentence as written, so a person confirming `Archive {{ count }} account(s)?` read the braces instead of the number. The confirm step now fills `{{ count }}` through the same template engine the flow notifications and the single-record `confirmText` render with, so the whitelisted formatters apply (`{{ count | number }}`) and a hole holds no logic. A sentence without a `{{ }}` hole is shown as written, the default sentence is unchanged, and a source the engine refuses is shown as written.
11+
12+
A hole naming one of the action's params prints empty for now; filling the params with their display values is the next change.
13+
14+
What to do: nothing.
Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
---
2+
'@object-ui/plugin-form': patch
3+
---
4+
5+
fix(plugin-form): a `{ group }` form section no longer warns that it "also declares `collapsible`, `collapsed`" when its author wrote neither
6+
7+
Clause-②: no
8+
Metadata-protocol: none
9+
10+
`@objectstack/spec` gives a form section's `collapsible` and `collapsed` a default of `false`, so every parsed section carries both, and it refuses them beside `group` only when they are `true`. The console's form renderer reported any value at all, so every `{ group }` section of a parsed form logged the group-owned-key warning once per page and told the author to move keys they never wrote to the object's `fieldGroups`. The renderer now reads those two keys the way the spec does: `true` beside `group` is still reported (a programmatic caller that skips the spec's parse), while `false` or absent is not. `name`, `label`, `description` and `visibleWhen` are still reported on any value.
11+
12+
What to do: nothing. If you moved `collapsible` / `collapsed` off a `{ group }` section because of this warning, no metadata change was needed.
Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
---
2+
'@object-ui/plugin-dashboard': patch
3+
---
4+
5+
fix(plugin-dashboard): a `compareTo` KPI tile shows its number when the reader picks All time, instead of the executor's "compareTo needs a dated window to shift" error
6+
7+
Clause-②: no
8+
Metadata-protocol: none
9+
10+
- **Before.** A dataset-bound widget with `compareTo` always sent `compareTo` to the dataset executor, but lowered a `timeDimensions` window only when its resolved filter held a closed `{ $gte, $lte }` date pair. Picking **All time** on the dashboard's date-range filter removes that pair, so the executor refused the query and the tile showed a 400 error where its number belonged. The same tile without `compareTo` showed its number.
11+
- **Now.** When the resolved filter carries no date condition at all on the compared field (on any field when `compareTo.dimension` is omitted), the widget asks for no comparison: the query is the one a widget without `compareTo` sends, and the tile shows its number with no comparison badge.
12+
- **Unchanged: an author-written window that is not closed stays an error.** A one-bound window (`{ $gte: '{current_year_start}' }`, a YTD tile), an exclusive bound or a single day is still sent with `compareTo`, and the executor still refuses it and names the fix. The executor and the spec define a comparison only against a two-bound window. Two dated fields with no `compareTo.dimension` stay the executor's ambiguity error.
Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
---
2+
'@object-ui/app-shell': patch
3+
---
4+
5+
refactor(app-shell): the Console `ObjectView`'s module-level helpers move into sibling modules
6+
7+
Clause-②: no
8+
Metadata-protocol: none
9+
10+
Module-level helpers, types and constants of `views/ObjectView.tsx` (the record links the list publishes, the saved-view tab, override and column helpers, and the small toolbar and filter helpers) move verbatim into `objectViewRecordLinks.ts`, `objectViewTabs.ts` and `objectViewHelpers.ts` beside it. No logic, name or rendered output changes. `ObjectView.tsx` keeps the component and re-exports every name it exported before, and the package entry is unchanged.
11+
12+
What to do: nothing.
Lines changed: 26 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,26 @@
1+
---
2+
'@objectstack/cloud-connection': patch
3+
'@objectstack/cli': patch
4+
---
5+
6+
feat: `OS_CONSOLE_MAP_STYLE_URL` names a deployment's default map style, served on runtime-config and allowed by the Console's content-security-policy
7+
8+
Clause-②: no
9+
Metadata-protocol: none
10+
11+
A map view that names no `mapStyle` falls back to a built-in style on a public demo host, so a deployment without public internet, or one whose policy forbids a third-party tile host, shows a grey map. An operator can now name the deployment's own style document once:
12+
13+
```sh
14+
OS_CONSOLE_MAP_STYLE_URL=https://tiles.example.com/styles/basic/style.json
15+
```
16+
17+
That one value does two things, both read at boot:
18+
19+
- `GET /api/v1/runtime/config` serves it verbatim as the top-level `mapStyleUrl`, the deployment's default map style. Unset, the key is absent and every other key is unchanged.
20+
- The Console document's `connect-src` gains the URL's origin. The default demo host stays allowed beside it.
21+
22+
The value must be an absolute `https:` URL on a host name, with no user name, password or whitespace. Anything else stops the server at boot with a message naming the variable, the same way a malformed `OS_CONSOLE_CSP_CONNECT_SRC` entry does. The runtime-config door is anonymous, so the URL is public once set.
23+
24+
It is an operator setting only: there is no Setup setting and no metadata key for it, so only the person who runs the deployment can widen the Console's content-security-policy. A style whose tiles, sprites or glyphs live on other hosts still needs those hosts in `OS_CONSOLE_CSP_CONNECT_SRC`.
25+
26+
The Console's map renderer reads `mapStyleUrl` in a separate change; until then the served value and the policy are in place, and map views keep the built-in style.

0 commit comments

Comments
 (0)