Enforce YOLO cap across session usage (#313)

Use session billing endpoint for inference usage (#314)

Implement user-billed model policy (#289)

Route LLM inference through HF Router (#282)

Enable FAL endpoint to lift limits (#278)

Add CI for tests and Ruff (#217)

feat(telemetry): track 5 untracked Bedrock call sites for full cost attribution (#179)

Switch from Bedrock to Anthropic endpoint as default. Include support for gpt-5.5 (#118)

fix /model switcher with effort params