[codex] Switch defaults to GLM 5.2 (#333)

Remove unused model provider metadata (#330)

[codex] Update hosted web model defaults (#328)

Enforce YOLO cap across session usage (#313)

Use session billing endpoint for inference usage (#314)

Add plan-aware CLI billing CTA (#309)

Make LLM health check use request token (#290)

Implement user-billed model policy (#289)

Enforce premium quota across sessions daily (#287)

Set Sonnet as default premium model (#284)

Remove old Claude model support (#283)

Route LLM inference through HF Router (#282)

Add Opus 4.8 as premium model (#281)

Fix endpoint for free calls (#279)

Enable FAL endpoint to lift limits (#278)

Fix Pro entitlement checks (#239)

Add CI for tests and Ruff (#217)

Retry sandbox hardware requests (#210)

Fallback to free model for gated defaults (#208)

Add session YOLO auto-approval budget (#201)

Expose OpenAI models in the UI & make Claude model picker configurable (#183)