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

Create Hub artifact collections lazily (#245)

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

Skip sandbox spaces for artifact metadata (#241)

Add CLI local model support (#228)

Add ML Intern Hub artifact metadata (#225)

Add CI for tests and Ruff (#217)

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

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)

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)

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)

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

Add Slack gateway (#116)

fix(session-uploader): forward user_id and total_cost_usd to dataset row (#153)

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

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)

fix(cli): persist HF user id in saved sessions (#146)

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)

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

feat(observability)

fix: route bedrock/ model ids via LiteLLM Bedrock adapter (#89)

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

feat: enable Anthropic prompt caching on system prompt and tools (#69)

fix /model switcher with effort params

Make X-HF-Bill-To configurable via HF_BILL_TO env (default smolagents) (#57)

Read max context from litellm + compact at 90% (#54)

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

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

Fall back to user HF token for router when INFERENCE_TOKEN is unset (#39)

Refactor approval handling and enhance markdown table styles

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

feat: add headless CLI mode with local filesystem tools and rich terminal rendering

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

feat: LLM-based pruning for complex tool outputs (hf_jobs)

Add deterministic pruning of old tool outputs before LLM compaction

Add per-tool error limits and per-turn request cap

feat: add research sub-agent tool, slim down main agent system prompt

feat: add doom-loop detection for repeated tool call patterns