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 dataset uploads to Hub (#255)

Create Hub artifact collections lazily (#245)

Fix Pro entitlement checks (#239)

Force OAuth refresh after scope changes (#227)

quick wins, after internal audit (#229)

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)

Retry sandbox hardware requests (#210)

Fallback to free model for gated defaults (#208)

Auto-start CPU sandboxes for sessions (#200)

Add session YOLO auto-approval budget (#201)

Use HF username for personal trace uploads (#199)

Auto-share session traces to a private HF dataset (#193)

Add DeepSeek V4 Pro model option (#189)

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

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

Track Pro conversions + credits top-up; emit user_id + new KPIs (#174)

Fix _fetch_user_plan after JobsAccess.plan removal (#173)

Bill HF Jobs by namespace credits, drop Pro and org-join gating (#172)

Persist Space sessions in MongoDB (#170)

fix(sandbox): retry cleanup on transient failures + add backstop sweeper (#163)

Remember the chosen jobs namespace and clean up the picker dialog (#162)

Add Slack gateway (#116)

Use `huggingface_hub.get_token()` for auth fallback (#126)

feat(session): include user_id and total_cost_usd in trajectory dump (#136)

Run jobs under user or org accounts with upgrade / org-pick UX (#132)

Fix CLI rendering corruption and split CLI/frontend model defaults (#121)

feat(observability)

feat: route Claude via Bedrock inference profile (#82)

feat(quota): daily Opus cap + HF-org gate + cap dialog (#72)

Title gen: swap Llama-3.1-8B for gpt-oss-120b via Cerebras (#58)

Title generation: pin to Llama-3.1-8B-Instruct via Cerebras, plain-text output (#53)

Restore expired sessions via summary-based catch-up (#52)

Scope model selection per session instead of globally

Route HF inference through /v1 auto-router + add reasoning_effort knob

Raise MAX_SESSIONS to 200 for 8 vCPU / 32 GB Space

Replace multi-screen onboarding with single checklist view

Add message edit and regenerate from any point in conversation

Fall back to HF_TOKEN env var for local dev sessions

Fix tool errors not persisting (#3)

fix: exit gracefully on port conflict in dev mode

fix: prevent port conflict in HF Spaces dev mode