Add Qwen3-TTS Voice Design (DashScope) + persona voice descriptions

Cap persona + diary at 100 tokens; shorten prompts; stream the diary

Fix empty-JSON: keep the answer when a model leaves <think> unclosed

Model bar: show params once (avoid '0.6B · 0.6B' for byte-less engines)

Settings: model section to top; default WebLLM + Qwen3 0.6B; copyable debug

Put the model picker in Gradio's OWN settings page (not a custom tab)

Move engine/model settings to a Settings page; share one model across both pages

Cache status + delete for WebLLM and Transformers.js (like wllama)

Transformers.js: pre-flight WebGPU device, else WASM (fixes load + caching)

Fix stale JS (no-cache on /web) + Transformers.js WebGPU→WASM fallback

Fix Qwen3 on WebLLM: budget for thinking + capture reasoning_content

Fix Qwen3 parsing (/no_think) + WebLLM double-load guard & progress clarity

Mobile: collapse model/voice control bars behind tap-to-expand

Mobile: give persona/diary content real space on phones

Add in-browser TTS: read war diaries aloud (Kokoro / Kitten / Web Speech)

Fix model re-downloads (persistent storage) + WebLLM shader-f16 crash

Multi-engine benchmark: wllama vs Transformers.js vs WebLLM (engine selector)

Add Qwen3-0.6B; surface WebGPU backend; strip <think> from answers

In-browser models: catalog + picker + cache delete, live tok/s stats, raw 'thinking' stream

Personas + War Diary now run llama.cpp IN THE BROWSER via wllama (local-first)

Personas + war-diary via llama.cpp (reusing woid's persona SSE protocol)

Space: brand title in Fraunces w/ red dot + 'small minds, big dreams' subtitle; CHARACTERS title small+red; stage fixed-fills full height like main sidebar

Chrome: left-align picker rows (Gradio was centering them)

Space: fix Carnival assets (URL-decode), red section headers w/ line, square selections, kill Gradio list bullets/margins, stage fills page

Shell/chrome: force label spans to inherit link colour (Gradio --body-text-color hid active-item + compass text on dark fills)

Space: theme-independent parchment (no theme redirect), full 47-char roster, fonts via Gradio vars

Space: mirror auto-battler styling — parchment theme, fonts, paper sidebar

Shell: defend movement chrome link/key/extra colors with !important vs Gradio .prose

Space: render the FULL Sprite Animations chrome via shared playground

Space: close drift — curate full asset set, unified nav IR, sync via build.sh

Shared: also bind click (not just pointerdown) for tap-to-move on touch devices

Space: auto-load a default character on scene mount (demo.load races the module)

Shared: load sprite sheets resiliently (curated Space subset may 404 some shadows)

Space: add read-only window.tinySnap accessor (scene getSnapshot) for verification

Space: Sprite tab uses the shared spriteScene render core + click/tap-to-move

Space: fix mixed-content fonts (upgrade-insecure-requests + proxy_headers) and self-style collapse/reopen buttons

Shell: !important link-reset on nav items so host link themes can't leak in

Shell: scope nav-item link styles under .tac-sidebar (beats host .prose a)

Space: shared app-shell sidebar (nav.json IR + sidebar.css/js) wired into Gradio

Battle tab: real sprites (shared slicer/facing/anim); fix die animation (idle-cell)

Re-render sprite on tab show (first draw happens at 0x0 while hidden)

Fix leftover cell ref — use shared cellOf for sprite scale

Share the sprite-sheet slicer with auto-battler (web/sheet.js from src/render/spriteSheet.js)

Serve sprites at /sprites (not /assets — collided with Gradio's UI bundle)

Resize Pixi canvases on tab select (tabs start hidden at 0x0)

Gradio-native UI: gr.Blocks tabs (Battle | Sprite Animations | Barracks)

Built on Gradio: gr.Server custom frontend (Pixi + barracks via @app .api)

Gradio app at root with Pixi battlefield embedded via iframe (/battle)

Pixi battlefield: real deterministic engine running in-browser