Timer-driven reveal and spinner ticks (streaming reveal, tool-args reveal,
tool-execution spinner, todo strike animation) now hand the changed
component to `TUI.requestComponentRender(component)` instead of forcing a
full-tree render at 30fps. Every other root subtree reuses its previous
frame rows, cutting the Box/Container tree walk out of the compose
pipeline while the transcript grows.
Shimmer:
- Intern the working-message palette per accent (WeakMap-keyed) so the
Symbol-slot compiled-ANSI cache in `shimmerSegments.compile` actually
hits between frames — the fresh palette literal in `renderWorkingMessage`
guaranteed a per-tick miss.
- Add an `activeBand` fast-path: outside the sweep window the intensity
is guaranteed zero, so those code points coalesce into a single low-tier
run without running `intensityFn` or `tierFor`. On the typical ~60-char
working message the classic band is 12 cells wide, so ~80% of the per-char
loop disappears.
Widen `ToolExecutionHandle` to extend `Component` (matches every
concrete impl — `ToolExecutionComponent`, `ReadToolGroupComponent` —
which already extend `Container`) so the reveal controller callback
sites are type-checked.
Fixes#4377
Each 30fps streaming-reveal tick re-segmented the whole revealed prefix via sliceGraphemes (per-tick slice cost grew with the prefix). BlockUnitCounter already memoized per-block grapheme counts; apply the same idea to slicing: cache the slice boundary per block index and re-segment only the per-step delta from the boundary cluster, so per-update cost grows with the delta instead of the rendered prefix.
buildDisplayMessage gains an optional sliceOf seam (default = sliceGraphemes, so existing callers are unchanged); the controller wires its BlockUnitCounter.slice through it via a #build helper that also de-duplicates six previously-repeated buildDisplayMessage call sites.
Only an exact (text, units) hit skips segmentation; the incremental guard (text === cached.text || text.startsWith(cached.text)) && units >= cached.units re-segments from the boundary cluster, so an append that extends the final cluster (e.g. a -> a combining acute, ZWJ family merge) is never stale.
Benchmark (bench/streaming-throughput.bench.ts, 30520-grapheme message, 61 ticks/episode): 23.78ms -> 2.27ms per episode (~10x). Regression tests vs a pure Intl.Segmenter reference cover fixed-text growing units, append growth, boundary-cluster extension, multi-block indices, shrink/regrow, full replace, and a 400-step seeded fuzz.
- Added a `proseOnlyThinking` configuration setting to suppress raw code blocks in AI thinking traces.
- Implemented `formatThinkingForDisplay` utility to replace code blocks with ellipses in the UI.
- Integrated runtime toggling and live refreshing of message components via streaming reveal controllers.
- Added a live tokens-per-second indicator to the assistant thinking pulse.
- Verified logic with new unit and integration tests for thinking block presentation.
- Added a setup-system-deps action with preloaded-runner guards and apt fallbacks.
- Updated CI workflows to download Linux x64 native artifacts and gate on native job success.
- Renamed coding-agent fast mode to singleton in scripts and test partitioning logic.
- Added settings test-state begin/restore helpers with recursive cleanup in affected tests.
- Filtered dot-only or blank thinking blocks so they no longer render as assistant thought.
- Adjusted assistant-message and streaming-reveal logic to use visible-thinking helpers for consistency.
per-block grapheme counts cached (blocks only grow) and in-flight partials bypass the markdown render LRU, removing repeated full Intl.Segmenter walks per 33ms tick and retained stale partial snapshots on long replies.
- Added `display.smoothStreaming` to settings schema.
- Updated streaming-reveal behavior to produce smooth 30 FPS reveals.
- Updated event-controller flow to support smooth streaming reveal mode.
- Expanded streaming-reveal tests for the new smooth streaming behavior.
roboomp