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

Use hyphenated ml-intern Trackio prefixes (#250)

Skip sandbox spaces for artifact metadata (#241)

Add ML Intern Hub artifact metadata (#225)

Add CI for tests and Ruff (#217)

Retry sandbox hardware requests (#210)

Auto-start CPU sandboxes for sessions (#200)

Make sandboxes private (#195)

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

Embed trackio dashboard in chat for jobs and sandboxes (#161)

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

feat(observability)

Rename CLI entry and Space assets from ml-agent to ml-intern

Fix sandbox HF_TOKEN not available inside container

Use sandbox read endpoint for script resolution to avoid bash truncation

Improve agent loop, tools, and research subagent for long-running autonomous tasks

Deduplicate file re-reads via content hashing for local and sandbox tools

feat: cancel sandbox creation on user interrupt

feat: kill sandbox processes and cancel HF jobs on user interrupt

chore: increase sandbox sleep_time to 45 min

stream sandbox creation logs to tool output, fix hf_jobs final status race

fix: increase sandbox sleep_time to 1500s

feat: resolve sandbox file paths and show tool description in status

fix: route all HF token usage through session.hf_token from OAuth

feat: inject OAuth token as HF_TOKEN secret into sandbox Space

feat: require sandbox_create approval before sandbox operations

fix: use OAuth token for sandbox creation instead of env HF_TOKEN

feat: restore sandbox tools and proactive compaction

feat: merge HF Space improvements

v3 prompt and tool desc rework

sandbox working and agent can use it

add create sandbox tool

sandbox start