---
title: "Resume a Run"
method: POST
path: "/v1/agents/runs/{runId}/resume"
---

# Resume a Run

`POST /v1/agents/runs/{runId}/resume`

## Request

- Base URL: `https://api.browserbase.com`
- URL: `https://api.browserbase.com/v1/agents/runs/{runId}/resume`
- Auth: API key in header `X-BB-API-Key`

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.

## Path parameters

- `runId` string, required

## Request body

- object
  - `task` string: 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.
  - `variables` object: Optional 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 `202`

The resume has been accepted and the run is `RUNNING` again. Poll the run for its next state.

- AgentRun: One execution of an agent against a task. Created in `pending` and transitioned through `running` → `completed`/`failed` by the runner.
  - `runId` string, required: Unique identifier for the run.
  - `agentId` string: The ID of the agent applied to this run, if any. Omitted for ad-hoc runs.
  - `task` string, required: The original task description.
  - `status` 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'STOPPED' | 'TIMED_OUT' | 'PAUSED', required: Current status of the run. - `PENDING` - agent will run soon - `RUNNING` - agent is currently running - `COMPLETED` - agent has finished running - `FAILED` - agent has failed the run - `STOPPED` - run was stopped by the user - `TIMED_OUT` - run exceeded maximum time - `PAUSED` - run is paused awaiting input from the caller; the agent's request is the trailing `pause` tool call in the run's messages
  - `sessionId` string: The Browserbase session ID powering this run.
  - `sandboxId` string: External sandbox identifier assigned by the runner. Optional.
  - `resultSchema` object: Per-run [JSON Schema](https://json-schema.org/specification) override for the result shape. When unset, the agent's default `resultSchema` applies.
  - `result` object: 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](https://json-schema.org/specification) when one is set.
  - `cause` object
    - `code` string, required: Structured failure code (e.g., RUNNER_HEARTBEAT_LOST).
    - `message` string: Human-readable failure detail.
  - `startedAt` string, date-time
  - `endedAt` string, date-time
  - `createdAt` string, date-time, required
  - `updatedAt` string, date-time, required

## Changes

- **2026-10-16** `266d5199a560`: 1 info
  - endpoint added

[Operation history](https://skmtc.dev/browserbase/apis/browserbase-api/changes/v1/agents/runs/:runId/resume/post.md)

---

[API](https://skmtc.dev/browserbase/apis/browserbase-api.md) - [All operations](https://skmtc.dev/browserbase/apis/browserbase-api/llms.txt) - [OpenAPI document](https://skmtc.dev/browserbase/apis/browserbase-api/revisions/106c5f72c742?raw)