Add round-robin provider rotation across 9 API keys

Batch emotion + profile extraction into single LLM call per coaching turn

Remove LLM status badge from frontend

Add automatic provider fallback on rate limiting

Support GROQ_API_KEY env var and strip whitespace from config

Make LLM provider configurable via env vars (switch to Groq)

Fix emotion detection: center arousal in backend, fix LLM classifier fallback, add 57 emotion accuracy tests

Add SSE streaming for token-by-token LLM responses and fix circumplex display

Add companion gate to planning/update phases and improve profile extraction

Fix emotional detection, eliminate duplicate cognitive load calls, and add Bayes net visualization

Add user profile visualization panel with Plotly charts

Fix double LLM call at calibration-to-visualization transition and add behavioral test suite

Fix double LLM call in visualization-to-planning transition

Fix double cognitive load assessment causing LLM repetition

Integrate emotional inference into EFE action selection

Improve conversation naturalness and reduce number recitation

Fix choice buttons showing without proposal, fix duplicate message history

Fix duplicate user message bug causing LLM repetition, add debug logging

Fix LLM response rambling and topic hijacking

Add companion mode and LLM status indicator

Add HF Spaces metadata to README

Merge HF Space initial commit

Add EFE-driven action selection, learning feedback loop, and Docker deployment

initial commit

Add README with install instructions and architecture overview

Merge branch 'main' of https://github.com/mahault/mindsphere-coach

Initial commit: MindSphere Coach — ToM-powered coaching agent

Initial commit