ui: model name as a byline, not a chip

ui: breathing dot instead of the blinking block on the status line

ui: put the blinking cursor back on the status line

ui: drawn icons for pipeline stages, brain for general, hover-only tab chips

toggles: topic icons, nudged right, contents centred

ui: darken the composer to match ChatGPT's contrast, not its hex

ui: icon copy buttons, orange confirmation, ChatGPT composer grey

pipeline: give the hedge the web, instead of skipping it

chat: stop, regenerate, inline prompt editing, copy answer

chat tips: friendlier copy with GAVL as the actor

answer formatting + UI: rich-answer format prompt, gpt-oss labels, input polish

router: GPT-OSS 120B generalist + Llama 4 Scout verifier; greeting fix; input UI

user message bubbles: rounded-full to match the input pill

input typed text stone-200 -> stone-100 (closer to white)

toggles up (mt-3->mt-1), bigger gap to input box (mt-2->mt-4)

nudge topic toggles right (pl-4)

remove 'topic' label next to the toggle buttons

input box: rounded-3xl -> rounded-full (pill), more side padding

brighten input placeholder text stone-600 -> stone-400

remove borders from topic toggles and chat/metrics tabs

remove input box border; subtle bg fill (rounded, borderless)

richer /explain, new copy: splash tagline, greeting, bot animation

tips as rotating input placeholder; boss opener holds longer; pixel tagline

chat empty state: drop NEW GAME + box, keep only the (bigger) tagline

tips linger ~10s into a query instead of vanishing at first token

rebrand to GAVL

loading tips + /explain command

narrow answer bubbles further 68% -> 58%

web search: GPT-style rotating ticker instead of status-line-only

web search: tell verifier answer is web-grounded; add 'searching' stage

move copy button from whole-message to per-code-block (top-right)

input box: rounder corners (rounded-xl -> rounded-3xl)

bid_timeout 20->30s; narrow AI bubbles to 68%; round the input box

tier-1 lineup: Gemma 4 (general), Qwen3 Coder (coding), DeepSeek V4 Flash (logic/math)

tier-1: DeepSeek V4 Flash (general), Qwen (coding), Skyfall 36B V2 (creative)

narrow assistant/live bubbles to 80% width

mobile responsiveness

bump tiny pixel-font UI text: toggles/badges 7-8px -> 10px, tabs/send 9-10px -> 12px

assistant bubbles on pure black; selection shown by orange left accent

hint in input placeholder: phd level stem questions trigger frontier

boss fights always open with 'someone called the boss??'

wider chat: sidebar 440->360px, assistant bubbles full-width, user 90%

widen assistant bubbles to 97%, narrow user bubbles to 65%

hard gate: GPT-5 reserved exclusively for hard STEM/reasoning queries

borderless chat bubbles; selection shown via background shade

reasoning ticker: one condensed headline every ~7.5s

tame the reasoning ticker: reading-pace drain, two-line clamp

syntax highlighting for code blocks in finalized messages

stream the hedge draft live from t=0; slow the typewriter to reading pace

slow the typewriter drain; TTFT unchanged