Controls committed on blur, which turned leaving a field into a durable,
revision-fenced document write the user could neither preview nor undo, and
silently discarded a draft the field did not accept.
A card's form now owns the staged text every control renders, and Save is the
only point where drafts become writes. Reset stages the composed default the
same way; an invalid draft blocks the save with its reason instead of being
dropped; Discard drops the drafts; a collapsed card marks that it holds some.
The Host stays the only authority on whether a value was accepted, so the save
reads the section back and keeps the drafts of a save that did not land.
Three things the page got wrong.
The web-search provider's defaults lived only at their use site, so the
served section carried no value for them and the card fell back to a zero it
invented — a number the schema itself rejects. Declaring them on the schema
makes the settings service the one authority: `maxUses` now reads 5 because
that is what the Host resolves, not because the page guessed. `baseURL` keeps
its code-side default, which exists so `$DEEPSEEK_SEARCH_BASE_URL` can win.
A field the Host serves no value for now renders empty rather than as zero.
The cards were rows in a settings page of cards: name and description ran
together on one line because the shared disclosure row lays them side by side.
Each card now draws its own header, stacking the two, and the section follows
the idiom the Agent Preset page established.
Three scenarios over the real wire: the cards this deployment's exposed
namespaces produce, one field edited down to the settings document with the
override badge that layering produces, and the reset that clears it back to
the composed default.
Every other settings golden gains the same nav entry and nothing else.
The assembled Web snapshot lane selected its locale with a `dsh.locale`
localStorage key. That key stopped selecting anything once the locale
preference moved to the Host settings document, so the image-display
scenario's Chinese expectations met the English default and failed.
Pin the navigator languages the boot env already documents, and state the
image-display expectations in the lane's English copy — the fixture session
title stays Chinese because it is fixture data, not product copy.
The frame carried `agentPreset` for surfaces that label the session, but
nothing consumed it: `noteAgentPreset` ran only in the switching tab's RPC
callback, so a second connected client refetched its catalogs while its
session row — the header label's source, and the hero chip's no-op input —
kept the composition the session had replaced.
`SessionManager.handleHostEnvelope` now folds the frame like the other
session frames. Re-applying the switching tab's own frame is a no-op: the
merge lowers `blank` only and keeps the row's `updatedAt`.
Presets own the rows that decide what a session's `/` menu contains, but
both browser catalogs cache per session and had no invalidation edge for a
recompose: `commands/changed` is registry-wide and recomposing registers
nothing, so the menu kept serving the composition the session no longer ran.
The host stream now frames the logged `agent-preset/selected` commit as
`host/session-preset-changed`; the runtime bridges it to the typed
`session/preset-changed` event, `ui-command` soft-refreshes that session's
directory key and `ui-skill` invalidates its catalog entry.
Reaching the host on a second switch was a separate defect: the list-row
identity guard compared every summary field except `agentPreset`, and the
merge keeps the row's `updatedAt`, so a switched row looked unchanged and
served its cached instance forever. The hero chip compares the pick against
that row, so switching back to the creation-time preset sent no RPC at all.
`tool-bash` resolves the background-task registry with `ctx.get('tasks')`,
and it sits at the preset's top level. The registry sat inside an
entry-local `isolate: { tasks: true }` realm, which is invisible to every
sibling row outside it, while the Web surface disabled the host row — so
both lookups missed and every `run_in_background` call answered
"background tasks unavailable" with `task_output`, `task_list`, and
`task_kill` still listed in the catalog. `task_list` returning
"(no background tasks)" is what made the outage read as an empty queue
rather than a severed producer.
That is the `goals` criterion read from inside the preset: a Service a row
outside its realm READS belongs to the plane both can see. `tasks` already
keys access by owning agent (`assertAccess` compares `task.owner.id`) and
mints an independent token per `attachSurface` call, so one host instance
serves every session exactly as before presets — the per-preset-standing-mounts
note records that sharing `tasks-local` is a return to its design.
`minimal` mounts no `tool-tasks`, and the `start()` control-surface gate is
a service-wide set that another preset's controls would open for it, so its
`tool-bash` disables `run_in_background` and drops the parameter from the
schema.
Fixes#2141
The mid golden was racing the reasoning block's stream: captureStableAria
could freeze on the pre-render gap between steering acceptance and the
assistant step, pinning a snapshot without the Think row. Wait for the
[data-variant=think] row so the golden captures the complete assistant step.
Steering bubbles render as plain user bubbles; a mid-turn steer is
recognizable by its position in the flow. The runtime SteeringMessageNode
projection and pending-steering lifecycle are unchanged.
Partially supersedes the 2026-08-04 context-source and steer marks note;
the new simplification note owns the removal rationale.
The persistence catalog recognizes SessionEventMap augmentations of
'@deepseek-ai/dsh-session/types' alone, so the selected event's old
root-specifier declaration compiled but silently vanished from the
generated catalog. The hermetic scaffold e2e still addressed the skill
registry as a preset-realm service; under the layered host registry the
composed agent's view is a scope read, and the ambient-root isolation it
proves is unchanged.
