README: add validator canonical tags (track + achievements).

README: add demo video + X post links; drop off-the-grid badge.

UI: clean EHR-style clinical theme; remove Peitho branding.

ZeroGPU: disable moshi torch.compile + CUDA graphs.

ZeroGPU: load on CPU, place on GPU inside @spaces.GPU, fresh ChatState per turn.

Pin python_version 3.12: liquid-audio requires >=3.12, ZeroGPU image was 3.10.

ZeroGPU attempt: boot-safe loader + @spaces.GPU realtime handler.

Hackathon: full tags, Field Notes report, custom UI for Off-Brand.

Rewrite README as the hackathon story: German fine-tune + physician value.

Redesign UI: dark teal theme, hero, schedule cards, question chips.

Cover all four patients in few-shot examples (Yilmaz + Weber).

Add few-shot example Q&A turns to coax v6 into plan-grounded answers.

Ground each question with the plan in the user turn; assertive prompt.

Shorten briefing prompt so v6 answers from the plan instead of parroting.

Make it the Praxis-Briefing medical demo on the working v6 realtime stack.

v6 TURN: use own Cloudflare Calls keys (free fastrtc/HF TURN is down).

Fix v6 demo TURN: use live HF Hub endpoint, lazy fetch, STUN fallback.

Roll back Space to Peitho v6 demo (state of 8360af0).

Route TURN through HF Hub API when turn.fastrtc.org DNS is down.

Trigger rebuild after WebRTC inputs fix (webrtc must be first).

Align Space S2S with official liquid-audio-demo WebRTC stack.

Fix mic audio shape and add realtime WebRTC S2S tab.

Pivot to Praxis-Briefing: GP voice schedule lookup, no WebRTC.

Use HF API for TURN credentials instead of dead fastrtc.org DNS.

Fetch TURN lazily when mic connects instead of at boot.

Fix Space startup crash when TURN DNS is not ready.

Pivot to Nachsorge-Stimme medical discharge voice check-in.

Tag README for Build Small hackathon validation.

Add Morgenruf morning check-in for Oma.

README: document English-only base, why fine-tune is required

chat: restore v6 routing, document why base-only failed

Revert to v6 overlay: base model is English-only per model card

README: document base-model A/B variant

chat: route through base_model, drop transcribe pre-pass, new persona prompt

A/B: drop v6 overlay, run stock base model as Peitho

README: document dual-model setup (base for ASR, v6 for chat)

chat: route transcribe pass to base_model, chat to v6_model

Use base model for transcribe pre-pass (v6 cannot follow transcribe prompts)

Upload chat.py with huggingface_hub

Upload app.py with huggingface_hub

Try short persona prompt + temp=0.3 topk=10 to combat verbosity

Upload folder using huggingface_hub

initial commit