Guides/Agent Chat

Agent Chat

The Chat tab in Agent Detail provides a bubble UI for conversing with agents, with persistent history and real-time status updates.

Watch

All videos

I Gave My AI Three Years of My Notes — Then Interviewed It

May 2026

Stateless Chat

This tab is stateless: each message starts fresh, replaying the visible transcript as text. It is labelled as such, with a Continue in Workspace → link beside it.

For a conversation where the agent keeps its working memory between turns — tool results, mid-task state, reasoning — use the Workspace instead. The Session-mode toggle that used to live here has been retired in its favour, and ?tab=session links now redirect there.

Concepts

•Chat Session — A conversation thread stored in the database. Each agent can have multiple sessions.

•Dynamic Thinking Status — Real-time labels showing what the agent is doing (replaces static “Thinking...”). Maps tool names to human-readable labels with 500ms anti-flicker.

•Playbook Autocomplete — Type / in the chat input to trigger a dropdown of available playbooks. Ghost text shows command syntax with argument hints.

•Continue as Chat — Resume a completed or failed execution as an interactive chat, preserving the full context (150K+ tokens) via Claude Code's --resume flag.

How It Works

Open an agent's detail page and click the Chat tab.

Select an existing session from the dropdown or click New Chat.

Type a message and press Enter.

The agent processes the message — the status label updates in real-time (e.g., “Reading files...”, “Running tests...”).

The response appears as a chat bubble with cost and token tracking.

Type / to autocomplete playbook commands.

File Attachments

Attach files using the paperclip button or drag-and-drop onto the chat input.

Supported types

•Images (JPEG, PNG, GIF, WebP) — passed as vision content blocks

•Plain text, CSV, JSON — written to /home/developer/uploads/ inside the agent container

•Unsupported: PDF, ZIP, archives, video, audio

Limits per message

Max files	3
Max size per file	5 MB
Max total image size	10 MB

Oversized files are rejected client-side. Files exceeding limits are skipped with a note appended to the message context. File uploads work in both authenticated and public chat.

Voice Chat

Voice chat is available directly from the Chat tab.

•Click the microphone button to start a voice session.

•Audio streams bidirectionally through the backend WebSocket proxy to Gemini 2.5 Flash Native Audio (~280ms latency).

•Transcripts are auto-saved to the chat session with source="voice" markers.

•Requires GEMINI_API_KEY configured on the platform.

•Controls: mute, end session, status indicator.

•Tool calling: during a voice session, Gemini can invoke run_task to delegate complex work to the Claude agent. The orb shows an amber badge while the task runs (up to 30 seconds) and returns to listening state when done.

Continue as Chat

•From the Execution Detail page, click Continue as Chat.

•This opens the Chat tab with a resume banner showing execution context.

•Uses --resume {session_id} for native session continuity.

Session Management

•Sessions persist across container restarts.

•Context window tracking: token usage display (e.g., “45.5K / 200K”).

•Session cost tracking: cumulative cost across the conversation.

•Close a session: POST /api/agents/{name}/chat/sessions/{id}/close

API Endpoints

Endpoint	Method	Description
/api/agents/{name}/chat	POST	Send chat message (stream-json output)
/api/agents/{name}/chat/sessions	GET	List all sessions
/api/agents/{name}/chat/sessions/{id}	GET	Get session with messages
/api/agents/{name}/chat/sessions/{id}/close	POST	Close session
/api/agents/{name}/chat/history/persistent	GET	Get persistent history
/api/agents/{name}/chat/history	DELETE	Reset session

MCP Tools

•chat_with_agent(agent_name, message) — Send a message to an agent.

•get_chat_history(agent_name) — Retrieve chat history for an agent.