relevance + diversity evals, batched scoring, math tooltips

sensing calibration + ink via ollama

air-writing

-

refactored and added synthetic data

Add voice + air-writing conflict resolution

Stop blocking /chat on evals; let the UI poll for them

Streaming candidate picker + side-index feedback loops

Session priors (P(bucket) + P(type)) + inline eval UI

Add faithfulness + authenticity evals; run scoring off the response path

Add PRESENT_STATE intent + head-shake turnaround

added deeper memories and new users.

dropped more bloat

Remove library bloat

Added scaffolding for evals

Code refactor for extensibility