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

feat: emit tool_log events from research sub-agent for UI liveness

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

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

Improve tool output quality: ANSI stripping, tail-biased truncation, noise suppression

feat: render cancelled tool state in UI after user interrupt

feat: cancel sandbox creation on user interrupt

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

fix: auto-retry on truncated tool calls + correct activity status on refresh

fix: retry sandbox API calls on transient failures

fix: live event streaming after reconnection + LiteLLM timeout

chore: double sandbox command timeouts

chore: increase sandbox sleep_time to 45 min

fix: clear pending_approval before tool execution starts

fix: gracefully handle MCP and OpenAPI failures during startup

refactor: simplify tool call validation and make interrupts cancel tool execution

feat: prompt for HF token interactively when not found

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

fix: correct context_length init and emit tool_call events for malformed calls

fix: handle interrupt during streaming tool calls without corrupting context

fix: recover malformed tool calls instead of crashing session

feat: add data audit section to system prompt

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

fix: protect system prompt in undo, scan backwards for dangling tool calls, gate input on SDK status

fix: patch dangling tool calls on error, move undo to context manager

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

fix: improve compaction summary prompt, remove sidebar status bar

fix: increase sandbox sleep_time to 1500s

sync: org onboarding, model updates, sandbox cleanup, prompt fixes

fix: buffer websocket events during disconnects and replay on reconnect

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