Resume a Run
Resume a PAUSED run with additional input. The reply in task is delivered to the agent as the answer to its pause request (the trailing pause tool call in the run’s messages), and variables merge over the run’s original variables. Resuming a run that is not paused returns a conflict.
Authorizations
Your Browserbase API Key.
Path Parameters
The run ID.
Body
Additional input for the agent: the reply to its request for input, which is the trailing pause tool call in the run's messages (e.g. an answer or an approval). Delivered to the agent as the result of that pause call.
1Optional named variables the agent can reference as placeholders, i.e. %variable%. Each entry pairs a value the placeholder resolves to with an optional description that hints to the agent when it should be used. Values are not persisted.
Response
The resume has been accepted and the run is RUNNING again. Poll the run for its next state.
One execution of an agent against a task. Created in pending and transitioned through running → completed/failed by the runner.
Unique identifier for the run.
The original task description.
Current status of the run.
PENDING- agent will run soonRUNNING- agent is currently runningCOMPLETED- agent has finished runningFAILED- agent has failed the runSTOPPED- run was stopped by the userTIMED_OUT- run exceeded maximum timePAUSED- run is paused awaiting input from the caller; the agent's request is the trailingpausetool call in the run's messages
PENDING, RUNNING, COMPLETED, FAILED, STOPPED, TIMED_OUT, PAUSED The ID of the agent applied to this run, if any. Omitted for ad-hoc runs.
The Browserbase session ID powering this run.
External sandbox identifier assigned by the runner. Optional.
Per-run JSON Schema override for the result shape. When unset, the agent's default resultSchema applies.
The agent's structured result for the run. Only present when the run has finished and output is available. The result conforms to the provided JSON Schema when one is set.