SHIPPED · v1.21.0
AI Agent Orchestrator
New
AI Agent Orchestrator — Let Your AI Delegate To Other AIs: Mention any AI agent and your current agent will delegate the task — type @Codex write jokes in a Claude terminal and Claude calls Codex headlessly, captures the output, and reasons over it
AI Agent Orchestrator — Let Your AI Delegate To Other AIs: Works with every coding CLI — Claude, Codex, Gemini, Amp, OpenCode, Qwen, and Aider can all be called or do the calling
AI Agent Orchestrator — Let Your AI Delegate To Other AIs: Multi-agent workflows in natural language — ask "have Codex write jokes and score them until 8/10" and the orchestrating agent handles the loop automatically
AI Agent Orchestrator — Let Your AI Delegate To Other AIs: Run agents in parallel — mention multiple agents and the AI decides whether to run them simultaneously or sequentially based on your prompt
AI Agent Orchestrator — Let Your AI Delegate To Other AIs: New MCP tools available to every AI terminal — run_agent delegates a prompt to another agent, list_agents shows which agents are installed on your system
AI Agent Orchestrator — Let Your AI Delegate To Other AIs: Manage from Settings → MCP — toggle the Orchestrator feature on/off, see both tools with their descriptions and status
Mission Control — Bird's-Eye View Of All Your Projects: Press the grid icon in the toolbar — to open Mission Control — a full-screen overlay showing every project as a card
Mission Control — Bird's-Eye View Of All Your Projects: Each card shows what's running — terminal count by agent type (3 Claude, 1 Codex), browser tabs, HTTP requests, and database connections at a glance
Mission Control — Bird's-Eye View Of All Your Projects: Custom commands are parsed and badged — if a terminal runs claude --model opus, the card shows a colored Claude badge with the flags
Mission Control — Bird's-Eye View Of All Your Projects: Active projects float to the top — , inactive projects are grouped below with a subtle divider
Mission Control — Bird's-Eye View Of All Your Projects: Keyboard navigation — arrow keys to move between cards, Enter to switch, Escape to close
Mission Control — Bird's-Eye View Of All Your Projects: Spring-animated transitions — cards shrink in from full size on open, the selected card zooms back out on close
MCP Tool Activity Badges — See Tool Calls In Real Time: Live badges appear in the terminal area — when an AI agent calls an MCP tool — database queries, HTTP requests, or agent orchestration calls
MCP Tool Activity Badges — See Tool Calls In Real Time: Animated status indicators — a pulsing dot while running, a checkmark or error icon when done, with elapsed time counter
MCP Tool Activity Badges — See Tool Calls In Real Time: Click any badge to open a detail panel — showing the full result — query output as a formatted table, HTTP response with status/headers/body, or the delegated agent's response
MCP Tool Activity Badges — See Tool Calls In Real Time: Color-coded by category — green for database, blue for HTTP, amber for orchestrator
MCP Tool Activity Badges — See Tool Calls In Real Time: Auto-dismiss or clear all — badges stay visible until dismissed so you can review results at your pace
Improved
Smarter Session Resume: Session names appear in the Resume panel — Claude sessions show the AI-generated title, Codex sessions show the thread name, OpenCode sessions show the session title
Smarter Session Resume: Model info displayed — see which model (Opus, Sonnet, GPT-4o) was used in each session
Smarter Session Resume: Git branch shown — know which branch a session was on before resuming
Smarter Session Resume: Card-style layout — sessions now show as cards with a colored accent bar matching the agent, replacing the flat row layout
Smarter Session Resume: Search by session name — find sessions by their AI-generated title, not just the first prompt
MCP Settings Redesign: Tools tab shows every registered MCP tool — grouped by feature — see tool names, descriptions, and whether they're read-only or mutating
MCP Settings Redesign: Feature toggle immediately changes tool visibility — no restart required
MCP Settings Redesign: Bridge health card shows enabled tool count — and registry version
Fixed
Fixed macOS build failing during notarization step
Fixed MCP server failing to start when the bridge wasn't fully initialized
Fixed Agent Input overlay not recognizing built-in AI agents for chip display — Claude Code, Codex, Gemini, and all others now show as chips when mentioned
AI Agent Orchestrator settings panel showing MCP tools for agent delegation Mission Control overlay showing all projects with terminal badges and activity indicators