What It Does
An agent can:- create a child agent
- send another agent instructions
- ask for a reply or send a fire-and-forget message
- read another agent’s transcript
- coordinate from the originating chat or agent session
Lineage And Sessions
The agent that starts another agent is the parent. The new agent is the child. The child agent has its own session, model, mode, transcript, and run state. It does not merge into the parent chat. The parent can read the result, continue the conversation, or use the child agent’s work as context for the next step. This is why agent-to-agent work shows up as hierarchy in Chats instead of as one flat transcript. Communication can still happen between multiple visible agent sessions when the selected agent paths support it.Agent Selection
Traycer uses agent-selection instructions to choose the right child agent for delegated work. Configure those defaults in Settings > Agents.Agent-To-Agent Support
Terminal-agent support is narrower than chat support today. Codex and OpenCode Terminal Agents can run terminal-style work, but they do not receive agent-to-agent messages.
Plain Terminals do not participate. They are shell sessions, not agent sessions.
For the broader distinction, see Terminal Agents VS Terminals.
Related Pages
- Chats explains where parent and child agent sessions appear.
- Agents & Models lists supported coding-agent paths.
- Settings > Agents explains global and workspace-specific agent-selection instructions.