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

Migrate inference backend from Hugging Face to Groq

Code quality and polish pass for launch

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

Add inference module with HF API wrapper

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