Update README.md

Update README.md

Update README.md

Add ml-agent CLI entry point and update README

4 steps shown

Fix sandbox HF_TOKEN not available inside container

removing extra agent tag

Enhance terminal display with new markdown emphasis styles

Refactor approval handling and enhance markdown table styles

Enhance user experience by clearing 'Waiting for approval' status immediately upon approval and refining markdown table styles for better readability and aesthetics.

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

Remove eval/ from tracking and add to gitignore

Bump dependency minimum versions to fix security vulnerabilities

Fix build: remove unused isRunning variable

Show fun running messages for all tools including research

Cherry-picked today's changes from HF Space development:

Remove unused create-pr.sh

Add SOTA research guidance to main agent system prompt

Fix missing detail in research step labels for truncated args

Persist research subtool steps across page refresh

Minimize S2 API calls: drop paper_details enrichment, add response cache, rate limit only with API key

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

Better deletion flow (#12)

Show 4 rolling subtool steps in research display

Latest ui fixes (#11)

Add delete confirmation dialog and sidebar spacing tweaks

Fix stale approval dialog reappearing after page refresh

Show fun placeholder instead of raw args for running tools

Fix message disappearing and duplicate rendering bugs (#10)

Restore localStorage org detection for iframe onboarding

Replace multi-screen onboarding with single checklist view

Use sandbox read endpoint for script resolution to avoid bash truncation

Add message edit and regenerate from any point in conversation

Redesign research subagent display with live stats and rolling steps

Fix session title only updating on the very first user message

Remove outdated-API flagging line from research prompt

Add SOTA-awareness to research sub-agent system prompt

Fall back to HF_TOKEN env var for local dev sessions

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

Fix tool errors not persisting (#3)

Merge pull request #31 from huggingface/agent-improvements

Update system_prompt_v3.yaml

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

Sync main.py: markdown stream buffer, shimmer timing fixes

Only show plan_tool output in CLI, hide all other tool outputs

Use Haiku 4.5 for research sub-agent

Use Haiku for research sub-agent when main model is Anthropic

Research stats tick every second via background timer

Live research stats: tool count, tokens, elapsed time in header

Show full sub-agent tool call lines, no truncation