Persona voice: cloud voice-clone, varied voice designs, animated class picker

Personas → heroes: shield icon, hero terminology, empty state, active highlight

Fix: red headings, voice-edit badge, and voices persisting across refresh

Persona voice: one pulsing play button, sidebar-style headings, live badge

Persona: red section headings, icon buttons, edit-aware voice + clone-on-play

Persona: editable fields (auto-save), quote after about, Create/Replay voice

Personas-as-agents: spoken quote + save to a local-first barracks roster

Voice: cloud Qwen3-TTS is the default engine in prod (was Kokoro)

Voice settings: add "Qwen3-TTS local" engine — localhost-only, default on localhost

app.py: PORT env (default 7860) so it runs locally next to a service on 7860

Add Qwen3-TTS local bridge: ?tts= override + tts_server.py

Move Voice settings into the Settings page; add a sidebar ⚙ Settings button

Qwen3-TTS: use DashScope international endpoint (our key is sk-ws- intl)

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)

Add /persona/selftest to measure pure generation tok/s inside the Space

Persona: cap n_threads=2 (cpu_count over-reports host cores in a container → llama.cpp thrashing/50x slowdown); smaller ctx; /persona/status diag; lower token cap

Persona: load model under its own lock + prewarm in background (cold-start download no longer makes requests 'busy')

Persona endpoint: stop generation on client disconnect, fail-fast lock, lower token cap (prevents abandoned-gen lock pile-up)

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: force light theme (dark-mode text was white on parchment), remove per-page brand text, picker as sidebar + framed canvas stage

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)