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

[codex] Harden agent prompt guidance (#331)

Remove unused model provider metadata (#330)

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

Remove ~900 lines of dead code across agent, backend, and frontend (#318)

Instrument dataset usage and billing analytics (#316)

Enforce YOLO cap across session usage (#313)

Use session billing endpoint for inference usage (#314)

Add sandbox costs to usage meter (#311)

Add session usage threshold approvals (#310)

Add plan-aware CLI billing CTA (#309)

Rename idle reaper timeout to minutes (#305)

Enable FAL prompt cache validation (#301)

Reset usage billing window on session activation (#296)

Fix billing usage visibility (#294)

Add app-attributed usage display (#292)

Make LLM health check use request token (#290)

Implement user-billed model policy (#289)

Enforce premium quota across sessions daily (#287)

Restore prompt caching for FAL router models (#286)

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)

Reclaim idle sessions to fix session-capacity overshoot (#277)

Add `/clear` and `/new` commands (#256)

Add dataset uploads to Hub (#255)

Add CLI sandbox runtime and fix HF Jobs script paths (#237)

Use hyphenated ml-intern Trackio prefixes (#250)

Use duplicate_repo for sandbox Spaces (#249)

Align CLI help output (#248)

Fix GPU sandbox hardware OAuth failure (#246)

Create Hub artifact collections lazily (#245)

Implement `/resume` command for CLI (#233)

Fix Pro entitlement checks (#239)

Skip sandbox spaces for artifact metadata (#241)

Add CLI local model support (#228)

Add backlog prioritization report tooling (#222)

Force OAuth refresh after scope changes (#227)

Add collection OAuth scope (#226)

Add ML Intern Hub artifact metadata (#225)

Add CI for tests and Ruff (#217)

Preserve HF token across restored sessions (#218)

Skip redundant CPU sandbox hardware request (#216)

Retry sandbox hardware requests (#210)

Stop attaching timestamps to LLM messages (#209)

fix(compaction): break infinite loop + truncate oversized messages (#213)

Fallback to free model for gated defaults (#208)