Simplify requirements: pin only gradio and pydantic range

Fix pydantic version conflict with gradio[mcp] extra

Pin dependency versions to match working local venv

Update Goatcounter to dedicated PRISMA site; add Milestone 4c

Add Goatcounter analytics to page head

Restore per-IP daily session cap default to 10 (production)

Reduce per-IP daily session cap default to 2 for test phase

Migrate to gpt-oss-120b, strict JSON schema, per-IP rate limiting

Increase parse-retry budget from 1 to 4 (5 total attempts)

Retry once on EvaluationParseError to mask stochastic JSON drift

Remove type kwarg from gr.Chatbot (not supported in Gradio 6.x)

Migrate inference backend from Hugging Face to Groq

Separate live-demo and research-paper lines in README

Let impressions panel match chat width on mobile

Stack footer columns vertically on mobile viewports

Code quality and polish pass for launch

Finalize README, ROADMAP, and env template for launch

Rewrite ARCHITECTURE.md as finished v1 document

Add footer figure and fix SVG sizing

Surface errors as toasts instead of fake assistant messages

Disable SSR on launch to fix HF Space startup hang

Add HF Spaces YAML frontmatter to README

Add HF Spaces .gitattributes (LFS config)

UI tweaks: rainbow PRISMA title, dark inputs/bubbles, selected-turn highlight, plot jitter

Drop unused EvaluationParseError import in inference module

Remove debug parse-failure print from inference client

UI polish pass: dark theme, embedded figure, bar-cell impressions, trajectory plot

ROADMAP.md update

Add inference module with HF API wrapper

Force JSON mode in inference call

Add evaluation module with parsing, validation, and formatting

Refresh README with hero figure and finalize v1 attribute set

Add system prompt and test harness (M2)

Initial project scaffolding

Initial commit