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Remove outdated-API flagging line from research prompt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

Revert "Sub-agent log: tool_name → output_preview on one line"

Sub-agent log: tool_name → output_preview on one line

Log 20-char output preview for sub-agent tool calls

Sub-agent display: 2 lines, gray, 20 char truncation

Indent ASCII banner to match all other output

Indent all agent output, remove turn separator line

Render streamed responses as markdown, indent agent output for alignment

Hide research sub-agent tool_call and tool_output from CLI display

Tool output: last 10 lines for main agent, rolling 3-line display for sub-agents

Fix Ctrl+C at idle prompt: no false interrupt, no stuck state

Full HF-yellow ASCII art banner for CLI

Fix streaming: line-buffered output instead of per-token Live re-render

Overhaul CLI visual design with rich-powered formatting

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

refactor: append dynamic session context after static system prompt for cache stability

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

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

fix: also skip plan_tool from deterministic pruning

fix: skip research tool outputs in deterministic pruning

Add deterministic pruning of old tool outputs before LLM compaction

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

fix: move import/signature validation to sandbox, keep host-side lightweight

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

fix: update system_prompt_v3.yaml (the actual active prompt) to use research tool

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