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)

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)

Make sandboxes private (#195)

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

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

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

Persist Space sessions in MongoDB (#170)

Recognize Pro OAuth users via isPro flag (#164)

feat(kpis): per-tool counts, research engagement, surface split (#160)

Add web search so the agent can cite current sources (#159)

Add Slack gateway (#116)

Honor interactive model override after current CLI changes (#111)

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

Protect sandbox control-plane routes (#142)

Preserve streamed thinking metadata with live model tests (#150)

Preserve thinking state across tool turns (#143)

Keep repetition guard internal (#144)

fix(doom_loop): normalize tool-call args before hashing (#119)

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

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

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

feat(observability)

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

Remove stale tests directory

fix: use correct HF API filter param and improve integration tests

feat: add hf_papers tool for paper discovery and reading