Skip to main content
Agent View: event log on the left, live browser screenshot with the agent's current action on the right

Agent View: watch a session live, or replay it afterward

Every session shows up in Agent View on the H Platform, and its agent_view_url links straight there. Watch it live to debug a detour or tune a prompt, or replay every observation, action, and message once it ends. Agent View reads the same events stream as your code. Everything below targets the session id and works the same for a single agent or a manager with subagents.

Watch a run

A blocking run-and-wait call (run_session / runSession) never surfaces the session mid-run. To read or intervene while it works, start the session and keep its handle.

Stream events as they arrive

The SDK handle’s stream() runs the changes long-poll loop for you and yields each event in order.
  • It resumes from_index and skips 204 no-change responses.
  • It stops when the session settles: a terminal state, or idle. Pass until="terminal" to keep it open across the idle turns of an interactive session.
  • It is read-only and does not answer tool calls. For custom tools, use wait_for_completion / run_session, which run them for you.

Steer a running agent

Until the session reaches a terminal state, you can:

Hold an interactive conversation

By default a session ends when the agent answers. Set idle_timeout_s at create time to keep it open: after each answer it goes idle and waits that long for your next message, keeping its context and environment across turns. It terminates once a turn goes unanswered for idle_timeout_s.
A settled session reports the agent’s outcome and, on failure, an error_code: see Session failures. At your concurrency limit, new sessions wait in queued: see Queued sessions.