Game: diagonal 2x map + half-size heroes; hidden overlay sidebar; persona-select state

Game: free-roam overworld with biome-themed enemy spawning

Game page: directly-controlled Forgotten Plains battle; rename to "Game"

Add World Map sandbox tab; fix ported-component styling on the Space

Add Classes + Enemies sandbox tabs (synced from auto-battler)

Skill Forge: optional "show thinking" for coding models

Add BLS Mini-Code 1.0 (Cohere 30B MoE) coding sidecar

Coding model in presets + Mellum2→Nemotron NIM fallback

Add Coding Model setting + Skill Forge sandbox

Move Nemotron text generation to WebGPU

Add Nemotron text generation option

Add MiniCPM5 text generation option

Stream Tiny Aya deltas through text route

Add Tiny Aya text generation option

Retry transient VoxCPM accelerator errors

Add VoxCPM reference audio cloning

Add VoxCPM ZeroGPU voice provider

Add Klein ZeroGPU portrait option

Portraits: set correct Content-Type for cloud images (NIM returns JPEG)

Portraits step 2: /portrait engine routing + imagen facade + Settings picker

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

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

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

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

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

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

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

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

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

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

Space: render the FULL Sprite Animations chrome via shared playground

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

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

Space: drop the Gradio tab bar, navigate solely via sidebar (fixes mobile nav)

Space: send upgrade-insecure-requests as response header (meta too late for Gradio's early theme.css link)

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

Space: link shared sidebar.css unscoped via head (Gradio css_paths scopes selectors)

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

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

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