The `+N` active count rides ToolRow's non-shrinking `summarySuffix` slot,
but only jsdom package suites covered it: the ACP snapshots render no web
surface and the built-boot smoke asserts no todo row. Add
`apps/web/tests/todo-row.snapshot.ts`, which boots the built client bundles
against the keyless fixture transport and records `summary`, `suffix`, and
the plan strip's header as separate fields, so folding the count back into
the summary string changes the expected output.
The three assembled-jsdom files now share `apps/web/tests/assembled-boot.ts`
instead of each carrying its own copy of the boot entry list, bundle map,
jsdom stubs, and mount call.
Also: name the policy branch in each `allowParallelInProgress` test title so
no case asserting `true` sits under a `false` describe, reword the stale cap
comment in todo-panel.spec.tsx, and record the plan strip's real header
format in the Agent Note (per-status counts, not `<done>/<total> tasks`).
Rebuild the todo row's parallel summary on the shared ToolRow that master
introduced: planSummary still returns the active name and the remaining
count separately, and the row hands the count to a new non-shrinking
summarySuffix slot so a narrow row clips the summary text before the count.
An error row drops the suffix, whose collapsed summary is the failure line.
Re-record the ACP todo-write transcript for the parallel prompt, regenerate
the config catalog for the required allowParallelInProgress field, and
re-record the bilingual pairing hashes.
The TTFT and tok/s readings divide by measured wall time, so they are not
reproducible: the same replayed scenario yielded 69 and 70 tok/s on
consecutive local runs, and a 3 ms replayed stream reads 26333 tok/s. Baking
those into committed goldens made the Web lane flaky by construction, and the
goldens for the readings themselves were never refreshed.
Three fixes, then a refresh:
The footer's decorative dots are `aria-hidden`, so the readings concatenated
into one accessible string — `Ran for 13sTTFT 0.2s12 tok/s`. That is a real
defect on its own (a reader hears one run-on instead of three facts) and it
also denied `{{duration}}` the word boundary it matches on, so even the
previously-stable `Ran for` duration started leaking raw. The separators now
carry flanking spaces.
`normalizeAria` gains `{{throughput}}` beside `{{duration}}`, and its duration
alternation accepts the stats line's compact `2m42s` as well as the
message-chrome template's `2m 42s` — the compact form had no pattern at all,
which is why `LLM 382m39s` survived the first refresh.
Refreshed 17 goldens. They also record that the stats line's `LLM` group now
renders at all: it folds assistant `timing`, which the live transcript adapter
only began attaching in this branch, so the group was previously dead in Chat.
Verified by running the lane in replay three times after the refresh: 41/41
files green each time, goldens untouched. Before this change two consecutive
runs disagreed on both the values and the failure count.
The merge staged the `--ours` consistency records before the merged prose was
re-recorded, so the committed hashes still describe the pre-merge content and
`verify-translation-pairing` rejects the pair. Re-record all three against
what actually merged.
The composer ring, percentage, and `~used / capacity` header read
`contextPressure.pressureTokens`, which moves only when a request reports
usage. Compaction reports none — compact-basic summarizes through a direct
`ctx.llm.stream()` call and appends only its own `compact/*` records plus the
replacement `user/message` — so the meter was frozen across the one action
taken to change it. Driving a real `compactNow` through the agent loop:
BEFORE compact: ring=4% header=~4227/100000 rows=[18, 0, 4365]
AFTER compact: ring=4% header=~4227/100000 rows=[18, 0, 286]
The composition rows fell 93%; the ring did not move, and would not until an
entire further turn completed. The panel then contradicted itself by more than
an order of magnitude at exactly the moment a reader opens it.
`contextPressure` now also publishes `projectedTokens`: the provider sample
plus the heuristic repricing of everything the surface gained or lost since
that sample, clamped at zero, folded through the shared `surface-fold.ts`. The
sample is stamped before the same event joins the surface, so an
`assistant/message` anchors against the surface its own request carried. Only
the delta is estimated, so the figure stays provider-anchored — the estimator's
CJK and JSON-schema underpricing stays out of the occupancy number — while
reacting the moment content lands or a span is shadowed. Same run after:
BEFORE compact: ring=4% header=~4323/100000 (pressure=4227, projected=4323)
AFTER compact: ring=0% header=~ 244/100000 (pressure=4227, projected= 244)
`contextOccupancy` prefers the projected figure and falls back to the bare
sample, so a projection restored from a pre-field checkpoint degrades to the
old behavior rather than disappearing. `stateVersion` moves to 3.
The panel header concatenated a `45%` span with a `context.used` fragment, so
Chinese rendered "45% 上下文已用" against the ring's own "上下文已用 45%". The
header now renders the one localized `context.aria` sentence split around its
`{percent}` slot: each locale owns the reading's position while the reading
keeps its primary tone, and the side a locale leaves empty collapses through
`.headline:empty` instead of spending a header gap.
The bar mapped every composition row to a segment unconditionally, and
`.segment`'s 2px min-width kept each one visible, so a 0% occupancy panel
painted an ~8px filled bar over an empty context. Parts are now computed with
their widths and zero-width parts are filtered out, which also collapses the
plain and segmented branches into one map.
Assistant footers and the stats line gain TTFT/tok-per-second readings
folded from step timings; context occupancy moves off the stats line onto
a composer ring whose panel shows a heuristic system/tools/messages
breakdown from the new token-meter contextBreakdown session projection.
core-data-structures/bash.md now names dsh-bash as owner of the shared
exit-status contract parseExitStatus/ParsedExitStatus provide to both
shell tools' presentResult (mirroring the README seam paragraph); the
windows-pwsh-default roadmap no longer claims composition-first ordering
while the rendering stage ships first; the terminal-card-model JSDoc
covers the shell tools, not just bash. Re-record both bilingual pairs.
A completed pwsh foreground call now presents as the bash tool's terminal
card with the parsed exit-status pill instead of a generic console fence,
and the collapsed row classifies as the shell family (Pwsh title). The
marker-to-exit-status parse moves from dsh-tool-bash's private render
module into the @deepseek-ai/dsh-bash seam so both shell tools share one
inverse of the marker contract (the bash-env precedent). The Web UI needs
no per-tool code: the terminal-card bridge maps any card:'terminal' view.
Coverage: dsh-bash owns the parse edge cases; the tool-pwsh presenter
suite mirrors tool-bash's; the client row-model suite pins the Pwsh shell
row; the new keyless pwsh-terminal web lane seeds an authored session,
presents it through the real tool on replay, and pins the card golden.
TUI is out of scope: the TUI package was removed (ed30088adb), so the Web
surface is the only UI the gap affected; the roadmap proposal's stage 2
is updated accordingly.
The composer seat is one node laid out against two different edges: in Chat it
is a sticky child of the column's scroller and rides its content box, which a
space-consuming scrollbar shortens, while a view declaring a composer overlay
gets an absolutely positioned seat against the padding box, which no bar
reduces. With the transcript scrolling the two tabs disagreed by the bar's
width, so the centred input card moved 4px sideways on every switch — and the
same 4px inside Chat when a growing transcript began to scroll.
The column now reserves its scrollbar gutter unconditionally and states the
overlay branch a scroll container on the same axes, so both states measure
against the same width.
