Rules read from the main model decide who it is offered as a crowd member,
a friend and on its roster; any-to-any with denies by default, or
none-to-none with allows. The crowd picker names what it holds back and
why, and a model held back only by a person's own rule -- or by anything,
with the new rules.override -- can still be added by hand. Another data
group is now a deny that an explicit rule opens. Admin -> Model rules and
a card in Settings, each with a matrix drawn by the enforcing function.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every connection is in a data group. Its models are handed, and can find,
only that group's memories, notes, skills, knowledge, reports and
personality -- by search and by id. A chat stays in the group it was
started in: switching its model, the endpoint fallback, the crowd, friends,
bases and the @ menu all stay inside it, and a chat whose model has moved
is refused rather than sent. A group may name its own embedder and image
reviewer. data.manage lets a person make personal groups, remap
connections for themselves and move their own records.
Also: a search no longer mixes two embedders of the same width.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The model menu asks each connection's /v1/models for the load state
llama-swap reports there and marks the loaded model; endpoints that state
nothing (a hosted API) get no dot. The new-chat screen offered the generic
three efforts whatever the model took, so Bonsai's xhigh default showed as
off. The composer was as wide as its widest hint. And the Doors of Durin are
a riddle: Speak friend and enter.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The chat's model picker shows name, context window (CTX 131K) and an eye
for vision, on shared column tracks; the capability tags are gone from it.
Settings -> Models gives the name its own row and wraps the tags beneath.
The picker's tick now follows an in-place choice.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Three fixes to how a round behaves, found by reading one real round on the live
instance rather than by testing it.
A member asked "what would you have done differently" answered the person's
original question again instead of critiquing what was already there. Fine on a
question with one answer; on a request to *make* something it is an invitation.
`crowd.turn` now says to respond to what is above and not to re-answer.
The model that opened the round, told to write the final answer and take what
the others got right, abandoned its own good answer and adopted the newcomer's
position with no argument anywhere for why. Both closing fragments now say that
an answer is not the worse one for having been written first, and that agreement
with no argument behind it is not a reason to change.
That second one is not cosmetic: all three answers from the observed round were
compiled. The original and the critic's alternative both build; the merged
answer that was actually delivered does not. A crowd's failure mode is not
looping -- the caps handle that -- it is converging on the last thing said.
Third, the reply that opens a round now carries a chip like every other one. It
is the single contribution the crowd does not start, so there was nothing to
stamp it with until the round began, and a two-model round rendered as an
unmarked reply followed by one saying "2 of 2". The stamp is display state and
never scheduling state: `crowd.scheduling_state` hides it from everything that
decides what happens next, because fed to the scheduler it would inherit the
round's clock -- regenerating the opening an hour later would end the round with
"out of time" before anybody spoke -- and would hand that reply a member's tools
and a member's instruction.
And the chip was never translated. It is now, with the count as placeholders
rather than three t() calls around one sentence.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Two reports against 1.6.0 and 1.7.0, both correct.
The crowd worked end to end and was, in practice, not there: the picker was
behind the ⋯ menu of a chat that already existed, and the switch was a card on
the Agents page, which made it read as an agent-chat feature. The picker is now
a button in the composer toolbar on both screens that include it, and on the
new-chat screen the choice rides along with the first message, so a chat can
start as a crowd instead of having to be converted into one. The instance
switch has its own page.
The width bug was the suggestion cards, exactly as reported. `.suggestions`
rendered 455px inside a 366px column, and the tree's standing rule applied on
its own made it worse -- 428px to 455px. A grid item carries `min-width: auto`,
which is a min-content floor, and a floor beats `width: 100%`; the floor is
measured while the percentage is indefinite, so `min(100%, …)` alone sends the
track to a card's max-content. Both halves now go on all four auto-fit grids,
and a test refuses either alone.
It survived four releases of narrow-width checking because the harness never
rendered that screen: `TestClient(app)` runs no lifespan outside a `with` block,
so the startup-seeded cards were missing from every shot ever taken of it. And
its overflow check skipped anything inside a scroller -- right for a table in
its own scroller, blind to the scroller itself, which `overflow-y: auto` makes
scroll sideways too. Both fixed; it now names the box and the child to blame.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
969 strings, an instance default and a per-person choice, and no half-done corner:
the admin prose is translated too. Design and reasoning: LLeMbas.wiki/Translations.
KEYED BY THE ENGLISH SENTENCE
A missing entry renders the key, which is the English -- so an untranslated string
looks as it always did, an English instance is byte-for-byte 1.6.0, and a
half-finished catalogue is a half-translated page rather than a page of dotted key
names. The cost is that editing an English sentence orphans its translation
silently, which is what tests/test_translations.py asserts in both directions.
No gettext: .po -> .mo is a build step and this project does not have one.
A JINJA GLOBAL, AND THEREFORE A CONTEXTVAR
`t()` is a global for the reason `brand` already documents -- render() is bypassed
by 25 TemplateResponse calls and 8 get_template().render() calls, the latter being
the SSE frames, which have no Request at all. A global is bound once at import and
the language is per person, so the active language is a ContextVar set per request.
🚨 `get_current_user` had to become `async def`. FastAPI runs a sync dependency in a
threadpool, and anyio copies the context in and discards it on the way out -- so
the language was set where nothing could see it and every page rendered in the
instance's language whatever anybody had chosen, with no error anywhere.
NOT TRANSLATED, ON PURPOSE
Everything a model reads: the 60 prompt fragments, and the dates in harness.py,
schedule/runner.py and schedule/compile.py. Only `i18n.stamp` is localised, and
only where a person reads it -- with the *format* translatable as well as the
words, because "26. septembra 2026" is a different pattern rather than the same one
with different words in it. A process locale is not an option: global, not
thread-safe, two people's pages at once.
A second fragment telling models to answer in the reader's language was written
during this work and removed: `core.style` has said it since long before, and
test_an_empty_override_turns_a_fragment_off caught the duplicate.
THE BULK PASS
1213 sites wrapped by a one-off script that only touched patterns it could not
misread. It got three wrong in a way that mattered -- `t('…')` inside `attr="…"`
where the sentence held an apostrophe, closing the Jinja string and 500ing two
pages whose partials no test renders. tests/test_translations.py now compiles all
110 templates. It also wrapped the product's own name, an SSH key header, a
keystroke hint and an example URL, all taken back out: a string is not
translatable just because it is a string.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
HomerandClaude Opus 5.5