release: merge develop into release/0.1 (one confirmation for a set, compact answers, file reading, links) #117

Merged
james.maes merged 34 commits from rc/develop-into-release-0.1-one-card-files into release/0.1 2026-11-18 17:25:42 +00:00
34 Commits
Author SHA1 Message Date
james.maesandClaude Fable 5.2 55bcf1a509 release: merge develop into release/0.1 (one confirmation for a set, compact answers, no silent stop at the output ceiling, widgets follow data access, file reading where a host turns it on, links the application gave)
maven / build (push) Successful in 9m18s
build / maven (push) Successful in 9m18s
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-18 11:15:05 -06:00
james.maes 5ffe50f898 Merge pull request 'feat(tools): the assistant can read the files of records, where a host turns that on; an answer keeps no address the application did not give' (#116) from feat/read-file-contents into develop
maven / build (push) Successful in 9m42s
build / maven (push) Successful in 9m42s
2026-11-18 17:12:30 +00:00
james.maesandClaude Fable 5.2 3f93119b4b fix(attachments): the glyphs taken of a PDF are bounded; read_file takes a bounded text out of a document
maven / build (push) Successful in 10m18s
build / maven (push) Successful in 10m18s
A one-page PDF of six million glyphs is 17 KB, and PDFBox keeps the
position of every glyph of a page until the page ends: reading it through
read_file, or as a file attached to a question, exhausted a heap of 1 GB
whatever the caps on pages and characters (found by an independent review).

PdfText counts glyphs as they are taken and stops past a bound: twice the
characters asked for, never more than 200,000. What was taken of the page
is written, and the text is reported as truncated. read_file takes at most
100,000 characters out of one document instead of all of it.

PdfGlyphBoundTest reads that file through both routes. Before the bound
read_file handed over all 6,000,000 characters and the attachment route
allocated 3,992 MB; with it, 94 MB.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-18 09:33:07 -06:00
james.maesandClaude Fable 5.2 d994be923e Merge remote-tracking branch 'origin/develop' into feat/read-file-contents
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-18 09:28:17 -06:00
james.maes dac309ccc2 Merge pull request 'feat(engine): compact answers; a reply cut off at the output ceiling drops no work and never ends COMPLETE' (#114) from feat/compact-answers-and-output-ceiling into develop
maven / build (push) Successful in 9m51s
build / maven (push) Successful in 9m51s
2026-11-18 15:01:05 +00:00
james.maes c390c15948 Merge pull request 'feat(process): one confirmation runs a set to its end, within what its card showed; no card for a change the person may not make' (#113) from feat/one-card-for-a-set into develop
maven / build (push) Successful in 11m27s
build / maven (push) Successful in 11m27s
2026-11-18 15:00:49 +00:00
james.maesandClaude Fable 5.2 6e812014c3 Merge branch 'feat/compact-answers-and-output-ceiling' into feat/read-file-contents
maven / build (push) Successful in 9m14s
build / maven (push) Successful in 9m14s
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-17 16:09:21 -06:00
james.maesandClaude Fable 5.2 7da70de9ba fix(tools): file reading is off until a host turns it on; a file is read only with the record it is attached to; one deadline for an outside fetch
After a second independent review of reading files and of the link rule:

- Reading files is off by default. A host turns it on per table
  (withFileSource) or for every table (withFileReading); until then the
  tool is not offered and a call reads nothing.
- A file is read only when the record it is attached to may be read: where
  the host declared it (withAttachedTo, withAttachedToRecordOf), the
  assistant must be allowed that record's table and the person that record.
  An attachment-style table with no declaration is refused, and the refusal
  says what to declare.
- A file kept outside the application is fetched only from an allowed
  origin (scheme, host and port; https unless an http origin is listed),
  with one deadline for the whole fetch, body included. The client is shut
  down after each fetch. A refusal names neither the address nor its host.
- Taking the text out of a document is bounded: what a workbook inflates
  to, the rows and cells walked, and time.
- The link rule judges every way a path of the application can be written
  (angle brackets, an HTML anchor, relative forms), and a path that is only
  written in the content of a file or a record no longer counts as given.
  The design note says plainly that the panel is the control for addresses
  of other sites and for images.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-17 16:09:21 -06:00
james.maesandClaude Fable 5.2 97ee750c26 Merge branch 'feat/one-card-for-a-set' into feat/compact-answers-and-output-ceiling
maven / build (push) Successful in 8m57s
build / maven (push) Successful in 8m57s
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-17 16:02:39 -06:00
james.maesandClaude Fable 5.2 ce9a1323bb Merge remote-tracking branch 'origin/develop' into feat/one-card-for-a-set
maven / build (push) Successful in 10m2s
build / maven (push) Successful in 10m2s
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-17 15:53:05 -06:00
james.maesandClaude Fable 5.2 efe161a94d fix(process): a review's own inputs and values are held to what the card showed
A review was passed on its count and its lines alone. A review with an
option whose value the process had changed after the card was made, or with
a value to read, went on to store with what the card never showed (proved
by a second independent review).

A review is a screen too: before it is passed, and before it is answered
with "validate", what it has of its own is held to the record of what the
card displayed (screenDiffers), like any other screen. Such a run stops
with nothing stored, and the card to go on with shows the review's inputs
with the values the process holds now and its values to read. The values
the card gave for a review's own inputs are sent with its answer.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-17 15:53:05 -06:00
james.maes 31b18767a5 Merge pull request 'fix(tools): render_widget follows the assistant's data access; no widget is rendered until a host allows it' (#112) from fix/render-widget-follows-data-access into develop
maven / build (push) Successful in 12m3s
build / maven (push) Successful in 12m3s
2026-11-17 21:46:15 +00:00
james.maes c3ffc97445 Merge pull request 'fix(tools): a tool call does not hold a monitor while it waits for another thread (one and two processors)' (#115) from fix/tool-call-admission-does-not-pin into develop
maven / build (push) Successful in 9m15s
build / maven (push) Successful in 9m15s
2026-11-17 21:43:14 +00:00
james.maesandClaude Fable 5.2 77f2b7595c feat(tools): the assistant reads the files of records, and an answer keeps no address the application did not give
maven / build (push) Successful in 12m36s
build / maven (push) Successful in 12m35s
A person asked what was in a file attached to a record. The assistant found
the row of the file, said it cannot read files, and wrote an address it had
composed as plain text.

read_file returns the content of a file a record holds, for a person who
may open it. Which fields are files is read from the metadata (a BLOB, a
field with a file-download adornment); no table of another QBit is named.
The record is read as the person, a BLOB is downloaded with the
application's own operation as the person (UiApiGateway.download), and a
file kept outside the application is fetched only from a host the code
allowed (withFileUrlHosts; no credentials, no redirect). Data access and
field exposure narrow it as for every read: a masked field is not read.
Text comes back as text, a PDF or a workbook as its text, bounded, and a
part says it is a part; an image and any other binary is described, never
dumped. The content is untrusted data inside the envelope, and the
tool-call log does not keep it.

A file is shown as a chip that opens the record it is attached to (when the
host said which, and the application lists that table for the person), or
its own record. An address of the application in an answer is kept only
when a tool result, the conversation or the page gave it (AnswerLinks): a
composed path is removed from the streamed and the stored text.

Design: docs/file-contents-and-links.md.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-17 15:15:51 -06:00
james.maes 8bf9a557ab Merge branch 'feat/one-card-for-a-set' into feat/compact-answers-and-output-ceiling
maven / build (push) Successful in 10m12s
build / maven (push) Successful in 10m12s
2026-11-17 13:52:55 -06:00
james.maesandClaude Fable 5.2 479be0408b fix(engine): the model row's output limit follows the same floor as the provider row's; the panel and INCOMPLETE in the upgrade notes
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-17 13:46:57 -06:00
james.maesandClaude Fable 5.2 a5b5f8cc4a test: the tool-set file follows the description of get_run_status
maven / build (push) Successful in 10m8s
build / maven (push) Successful in 10m8s
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-17 13:43:34 -06:00
james.maes c6ef837d0a Merge branch 'feat/one-card-for-a-set' into feat/compact-answers-and-output-ceiling 2026-11-17 13:43:11 -06:00
james.maes df24de71fe Merge branch 'fix/render-widget-follows-data-access' into feat/one-card-for-a-set
# Conflicts:
#	CHANGELOG.md
2026-11-17 13:41:14 -06:00
james.maesandClaude Fable 5.2 7485fa010f docs: remove a conflict marker line left in the changelog by the merge below
maven / build (push) Successful in 8m20s
build / maven (push) Successful in 8m20s
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-17 13:41:07 -06:00
james.maesandClaude Fable 5.2 647a8eadfb fix(process): a screen is passed only against the record of its card; a review is judged before any step; an unread job is not described
Three cases an independent review proved against the first version, each
with a test that fails without its fix:

- a review with a warning and an error was answered with 'validate first'
  before its lines were read, and a process that is not core's streamed one
  went on to store. The lines are now judged first, for every process, and
  'validate first' is only answered for core's own streamed process; a
  review with no lines is not passed.
- a screen outside the process's list of steps (an optional step), with a
  defaulted option, was passed although the card never displayed it. The
  stored proposal now keeps a record of what the card displayed, and a screen
  is passed only against it; a screen the process changed while it ran and
  every screen of a state-machine process stop.
- a job the person may not read was reported as running. A job that was not
  read is reported as exactly that, and the action fails.

Also: a status check cancels nothing; a run still working is 'started and
has not finished'; the names on a card are in the application's order;
every input is on the card, also one left empty.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-17 13:40:24 -06:00
james.maes 2f615879ba Merge branch 'fix/tool-call-admission-does-not-pin' into fix/render-widget-follows-data-access
maven / build (push) Successful in 11m20s
build / maven (push) Successful in 11m20s
# Conflicts:
#	CHANGELOG.md
2026-11-17 13:27:56 -06:00
james.maesandClaude Fable 5.2 1b7e92897e fix(tools): an allowed widget whose tables are not declared is not rendered; the person must be able to read them
render_widget rendered a widget that was allowed by name and had no
withWidgetTables entry without any check of what it reads. It now fails
closed: a widget is rendered only when it is allowed, its tables are
declared, and every one of them may be read by the assistant and by the
signed-in person (asked of the application as them).

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-17 13:27:49 -06:00
james.maesandClaude Fable 5.2 f4b279b95d fix(tools): a tool call does not hold a monitor while it waits for another thread
maven / build (push) Successful in 9m40s
build / maven (push) Successful in 9m40s
A tool call is a virtual thread, and the first call of a turn works out what
the person is offered by waiting for another one. ToolCallService did that
inside synchronized(admission), which keeps the carrier thread: with two
processors a batch of tool calls, and with one processor every first tool
call of a turn, waited out toolCallTimeoutSeconds, and the person was then
offered no write and no process tool for that turn.

An admission is now guarded by a ReentrantLock. FewProcessorsTest runs in
JVMs with one and with two processors (two surefire executions) and fails
there without the fix.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-17 13:26:08 -06:00
james.maes 4bf102cd4a Merge branch 'feat/one-card-for-a-set' into feat/compact-answers-and-output-ceiling
maven / build (push) Successful in 8m32s
build / maven (push) Successful in 8m32s
2026-11-15 05:42:34 -06:00
james.maesandClaude Fable 5.2 298b75c5ff test: a provider row's output cap is read with the floor in code
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-15 05:42:34 -06:00
james.maesandClaude Fable 5.2 18e893b835 fix(process): a card shows all a screen says; a screen that says more than a card shows is not passed
maven / build (push) Successful in 9m20s
build / maven (push) Successful in 9m20s
The first card showed the first 300 characters of a screen's text and then
passed the screen. It now shows the whole text (up to 2,000 characters), and
a screen whose text is longer is one the card did not show in full: the run
stops there.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-15 05:42:27 -06:00
james.maes 540ad0371d Merge branch 'feat/one-card-for-a-set' into feat/compact-answers-and-output-ceiling 2026-11-15 05:31:49 -06:00
james.maes d6bfe77c78 Merge branch 'fix/render-widget-follows-data-access' into feat/one-card-for-a-set
# Conflicts:
#	CHANGELOG.md
#	UPGRADE.md
2026-11-15 05:31:32 -06:00
james.maesandClaude Fable 5.2 50845aa99b fix(tools): render_widget follows the assistant's data access; no widget is rendered until a host allows it
maven / build (push) Successful in 8m50s
build / maven (push) Successful in 8m56s
A widget is code of the application and can show rows of any table, so
render_widget could hand a model the rows of a table the assistant may not
read. The tool now refuses, before the application is asked, every widget
the host did not allow by name (withAllowedWidgetNames, empty by default),
one it hid, and one that reads a table the assistant may not read
(new: withWidgetTables).

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-15 05:30:57 -06:00
james.maesandClaude Fable 5.2 15de0db565 feat(engine): compact answers; a reply cut off at the output ceiling drops no work and never ends COMPLETE
A reply that stopped at the output ceiling is read like any other: the tool
calls it had completely formed run, the one it was still writing (its last
part) and any whose input a provider could not read never do and get an
error result that says so. The answer goes on by itself at most
maxOutputContinuations times, each a model call under every limit of any
other; after that it ends INCOMPLETE, never COMPLETE, says what was done and
what was not, and stays in the conversation so that 'continue' goes on.

A provider row lowers the output ceiling of one reply only down to
minOutputTokensPerRequest; it never raises the ceiling the code configured.

An answer shows a record once and at most maxRecordCardsPerTurn record cards
and maxRecordChipsPerTurn record links; a confirmation card is never left
out. The system prompt asks for one proposal for a set and compact answers.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-15 05:29:56 -06:00
james.maesandClaude Fable 5.2 47d3e34f8c docs(process): the design of one confirmation for a set; the card's records and what they were, in the API
docs/one-card-for-a-set.md is the design and the safety argument for parts A
to D; README, UPGRADE, CHANGELOG and the agent notes follow it. UI API
extension assistant 1.11.0 (additive): AssistantActionV1.recordCount,
records and recordsBefore for a run over a set.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-15 05:28:55 -06:00
james.maesandClaude Fable 5.2 583f8f1f9d test: the existing security tests follow 'no card for what cannot happen'
A person the application refuses is refused before a card where the
application says so beforehand; the confirm-time refusal (a permission that
goes between the card and the confirmation) keeps its tests, with the UI's
own status and message. The tool-set file changes in one description
(run_process), replaced as text.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-15 05:23:13 -06:00
james.maesandClaude Fable 5.2 11fc143e6d feat(process): one confirmation runs a set to its end, within what its card showed; no card for a change the person may not make
A confirmed run_process goes through the process's own init and step
operations as the person and passes a screen for them only when it shows
nothing their card did not: its text and inputs were on the card with the
values the process has now, and a review counts exactly the records of the
card and, with every record validated first, has no warning and no error.
Anything else comes back to the person with a new card and nothing stored.

The set is frozen by primary key and by one digest over its records as the
person read them; a set that changed is not run. The card keeps what the
records were (how many, a sample of 20) and lists the whole set by name.

The assistant no longer creates a job: when the application itself hands the
work to a background job, the job is the person's, it is waited for, and its
outcome (rows done, failed and why) is the card's. A job the application
created waiting is cancelled and the run reported as not done.

A change to records of a table is proposed only to a person the application
lets make it (what it tells their own screens); otherwise they are told so
and there is no card.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-15 05:09:34 -06:00