Agent ready
What happens between powering on a desktop and the AI agent being available.
Why the agent is not ready instantly
When you start a Le Bureau desktop, the AI agent does not become available the moment the VM powers on. Several boot phases need to complete first. Knowing the sequence helps you understand why chat may not work immediately.
Boot phases
Phase 1: VM boot (0-15 seconds)
The virtual machine powers on, loads the OS, and starts core services. By the end of this phase, the VM has an IP address and basic network connectivity.
What works: VNC viewer shows the boot screen.
What does not work yet: terminal, chat, file transfers.
Phase 2: System initialization (15-45 seconds)
The initialization process runs the desktop's setup scripts:
- Configures the
agentuser - Writes the agent configuration
- Installs enabled plugins
- Sets up the workspace (soul file, agents file, memory directory)
- Starts background services (terminal server, AI agent)
What works: VNC viewer shows the desktop loading. Terminal becomes available toward the end.
What does not work yet: chat, because the AI agent is still starting.
Phase 3: Agent startup (45-90 seconds)
The AI agent starts, loads its configuration, and begins accepting connections. Le Bureau checks the agent to confirm it is ready.
What works: everything. VNC, terminal, file transfers, and chat.
agentReady = true
The desktop is marked agentReady only after Le Bureau confirms that the AI agent is running and accepting connections. This means the agent is fully initialized and ready to accept messages.
In the dashboard, the chat panel becomes active when agentReady is true.
Why chat fails before agentReady
If you try to send a message before the agent is ready, you will get a 503 error or a "not ready" message. This is by design. Sending messages to a gateway that has not started would either fail silently or produce confusing errors.
The dashboard blocks message sending until agentReady is confirmed.
Typical boot timeline
| Time | Phase | What happens |
|---|---|---|
| 0-15s | VM boot | OS starts, network comes up, IP assigned |
| 15-45s | Initialization | User config, plugins, workspace setup |
| 45-90s | Agent startup | AI agent starts and accepts connections |
| ~90s | Ready | agentReady=true, chat available |
These times are approximate. They depend on how many plugins are enabled and the current infrastructure load.
Checking agent status
The dashboard shows the agent status on each desktop card. When the chat panel becomes active, the agent is ready. You can also check the desktop detail view for the agentReady indicator.
What if the agent never becomes ready?
If the desktop reaches running status but agentReady stays false for more than 3 minutes:
- Make sure you entered a valid API key during desktop creation.
- Verify the API key is active and has credits on your provider's dashboard.
- Try restarting the desktop from the dashboard.
- If the problem persists, delete the desktop and create a new one with a confirmed working API key.
If the issue continues, see the troubleshooting guide or contact support at contact@talentai.fr.