Remove old Claude model support (#283)

Route LLM inference through HF Router (#282)

Add Opus 4.8 as premium model (#281)

Improve premium quota label in model selector (#280)

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)

Fix stale tool error badges (#247)

Fix Pro entitlement checks (#239)

Fallback to free model for gated defaults (#208)

Add session YOLO auto-approval budget (#201)

Add DeepSeek V4 Pro model option (#189)

Make sandboxes private (#195)

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

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

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

feat: add support to open links in new tab (#76)

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

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

Fix parallel-research display: per-call stats in CLI and web UI (#49)

Scope model selection per session instead of globally

Drop 'Via' prefix from provider subtitles

Show default provider under each HF-routed model in selector

Use model maker as subtitle in selector, not routing mechanic

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

Fix stuck 'Waiting for approval' spinner and improve table rendering

Fix build: remove unused isRunning variable

Show fun running messages for all tools including research

Fix missing detail in research step labels for truncated args

Persist research subtool steps across page refresh

Add Semantic Scholar integration: citation graph, filtered search, snippet search, recommendations

Show 4 rolling subtool steps in research display

Latest ui fixes (#11)

Show fun placeholder instead of raw args for running tools

Add message edit and regenerate from any point in conversation

Redesign research subagent display with live stats and rolling steps

Show cancelled prompt in shimmer status bar instead of chat input placeholder

Fix tool errors not persisting (#3)

fix: infinite re-render loop from Zustand selector returning new []

feat: beautiful research sub-agent UI with inline progress steps

feat: render cancelled tool state in UI after user interrupt

feat: CLI local mode, slash commands, interrupt support; remove lmnr; frontend fixes

feat: improve bash tool status labels in activity bar

fix: reset approval UI state when new approval round arrives

fix: properly close SDK message on error, show tool errorText

Revert "fix: show errorText for failed tools, bump eval max_iterations to 300"