Add MBG keracunan pangan example to Surat Konstituen tab

Stream live per-agent activity in the Gradio UI

Improve hackathon polish and use 9B models

chore: remove upload instruction, video already on YouTube

chore: set YouTube video ID jgYXyij1P9Q

chore: update final video (44s, 720p30, audio)

chore: update video ref to manim version (33s, 720p)

docs: add @ilhamfputra credit for pasal.id API on Kredit tab

docs: add YouTube guide video section to Beranda tab

feat: add ethics guardrails, verifier, beranda + kredit tabs

feat: add token setup guide in Settings tab for new users

fix: don't embed HF_TOKEN/PASAL_API_TOKEN in frontend HTML/JS

fix: enable Gradio queue for progress reporting

fix: detect model IDs (no ://) as HF InferenceClient, not OpenAI

fix: add Settings import in _pasal_settings

fix: add missing LLMConfig/Settings import in custom endpoint branch

SMALL→Qwen3.5-9B, add extra_body(enable_thinking=False) to HFLLM

Fix: use huggingface_hub InferenceClient as default backend

Switch to Qwen3-32B (BIG) and Qwen3-8B (SMALL) — confirmed working on HF API

Fix build_pool: don't call load_settings(), use env vars/HF defaults directly

Swap defaults: BIG→Qwen3.6-27B, SMALL→Qwen3.6-35B-A3B

Add HF Space for Build Small Hackathon