> ## Documentation Index
> Fetch the complete documentation index at: https://docs.base44.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Clear message queue

> <Info>This API is in beta. Endpoints, fields, and behavior may still change, so avoid depending on it in production.</Info>

Removes every queued message and lifts any pause, so the next message you send runs as soon as the AI is free. With `keep_pr_watch=true`, queued PR Watch runs stay in the queue, and if any remain the queue keeps its pause. The turn that's already running isn't affected. Stop it with [Stop generation](/api-reference/stop-generation).

A message that was just taken off the queue to run is cancelled too, if its turn hasn't started yet.

A collaborator in the editor can send a queued message into the turn that's running. While that's happening the message can't be changed or removed. Clearing the queue is refused until it finishes, unless you pass `keep_sent=true`.

With `keep_sent=true`, messages already sent into the chat stay in the queue and still run, even after the turn they were sent into ends, and the request is never refused for a message being sent. Until that behavior reaches your account, `keep_sent` has no effect and the clear works as without it.

This is limited to 60 requests per minute per app for each workspace's personal API keys, so every personal API key in a workspace shares one allowance, and each workspace API key has its own. Every endpoint that changes the queue shares it. Some workspaces have a different limit.

<Note>This endpoint accepts a personal API key belonging to a user with editor access to the app, or a workspace API key, which acts as the workspace owner. A read-only key is refused.</Note>

<Warning>The response includes fields beyond the ones documented here. Don't rely on undocumented response fields, as they can change at any time.</Warning>



## OpenAPI

````yaml /developers/references/app-management/app-management-openapi.json delete /api/apps/{app_id}/chat/queue
openapi: 3.1.0
info:
  title: Base44 App Management API
  version: 1.0.0
servers:
  - url: https://app.base44.com
security:
  - PersonalAccessTokenAuth: []
paths:
  /api/apps/{app_id}/chat/queue:
    delete:
      summary: Clear message queue
      description: >-
        <Info>This API is in beta. Endpoints, fields, and behavior may still
        change, so avoid depending on it in production.</Info>


        Removes every queued message and lifts any pause, so the next message
        you send runs as soon as the AI is free. With `keep_pr_watch=true`,
        queued PR Watch runs stay in the queue, and if any remain the queue
        keeps its pause. The turn that's already running isn't affected. Stop it
        with [Stop generation](/api-reference/stop-generation).


        A message that was just taken off the queue to run is cancelled too, if
        its turn hasn't started yet.


        A collaborator in the editor can send a queued message into the turn
        that's running. While that's happening the message can't be changed or
        removed. Clearing the queue is refused until it finishes, unless you
        pass `keep_sent=true`.


        With `keep_sent=true`, messages already sent into the chat stay in the
        queue and still run, even after the turn they were sent into ends, and
        the request is never refused for a message being sent. Until that
        behavior reaches your account, `keep_sent` has no effect and the clear
        works as without it.


        This is limited to 60 requests per minute per app for each workspace's
        personal API keys, so every personal API key in a workspace shares one
        allowance, and each workspace API key has its own. Every endpoint that
        changes the queue shares it. Some workspaces have a different limit.


        <Note>This endpoint accepts a personal API key belonging to a user with
        editor access to the app, or a workspace API key, which acts as the
        workspace owner. A read-only key is refused.</Note>


        <Warning>The response includes fields beyond the ones documented here.
        Don't rely on undocumented response fields, as they can change at any
        time.</Warning>
      operationId: clear_queue_api_api_apps__app_id__chat_queue_delete
      parameters:
        - name: app_id
          in: path
          required: true
          schema:
            type: string
            description: ID of the app whose message queue this request acts on.
            title: App Id
          description: ID of the app whose message queue this request acts on.
          example: 6820f3a4e7b91d003c45a1f2
        - name: keep_pr_watch
          in: query
          required: false
          schema:
            type: string
            description: >-
              `true` keeps queued PR Watch runs. If any remain, the queue keeps
              its pause.
            default: 'false'
            title: Keep Pr Watch
          description: >-
            `true` keeps queued PR Watch runs. If any remain, the queue keeps
            its pause.
        - name: keep_sent
          in: query
          required: false
          schema:
            type: string
            description: >-
              `true` keeps messages already sent into the chat, which still run,
              and never refuses the clear with a 409. The response can then
              include them.
            default: 'false'
            title: Keep Sent
          description: >-
            `true` keeps messages already sent into the chat, which still run,
            and never refuses the clear with a 409. The response can then
            include them.
        - name: branch_id
          in: query
          required: false
          schema:
            type: string
            description: >-
              ID of the branch to work on, as returned by [List
              branches](/api-reference/list-branches). Omit it to work on the
              app's main branch.
            title: Branch Id
          description: >-
            ID of the branch to work on, as returned by [List
            branches](/api-reference/list-branches). Omit it to work on the
            app's main branch.
          example: 68f1a2b3c4d5e6f708192a3b
      responses:
        '200':
          description: >-
            The emptied, unpaused queue. With `keep_pr_watch=true`, any kept PR
            Watch runs remain and the queue keeps its pause. With
            `keep_sent=true`, messages already sent into the chat remain too.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/MessageQueue'
        '401':
          description: Missing or invalid credentials.
        '403':
          description: >-
            You don't have editor access to this app, the app is blocked, you're
            a viewer in the app's workspace, or your API key is read-only.
        '404':
          description: App not found, or no branch you can see has this `branch_id`.
        '409':
          description: >-
            A collaborator is sending a queued message into the turn that's
            running. Try again once it finishes. Not returned with
            `keep_sent=true`.
        '422':
          description: '`keep_pr_watch` or `keep_sent` is not `true` or `false`.'
        '429':
          description: >-
            Rate limit exceeded. The base limit is 60 requests per minute. See
            [Rate
            limits](/developers/references/apps-api/get-started/rate-limits) for
            the multiplier your plan gets.
        '503':
          description: >-
            Database temporarily unavailable (`database_unavailable`): the data
            cluster did not answer in time. Retry after the `Retry-After`
            seconds.
          headers:
            Retry-After:
              description: Seconds to wait before retrying.
              schema:
                type: integer
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StandardErrorEnvelope'
              examples:
                database_unavailable:
                  summary: database_unavailable
                  value:
                    error:
                      code: database_unavailable
                      message: Database temporarily unavailable, please retry
                      details: {}
      security:
        - PersonalAccessTokenAuth:
            - full_access
        - WorkspaceApiKeyAuth:
            - full_access
        - WorkspaceApiKeyBearerAuth:
            - full_access
components:
  schemas:
    MessageQueue:
      properties:
        items:
          items:
            $ref: '#/components/schemas/QueuedMessage'
          type: array
          title: Items
          description: >-
            The queued messages, next to run first. Holds at most 7 independent
            requests; an internal session continuation does not use a slot.
          example:
            - branch_id: 68f1a2b3c4d5e6f708192a3b
              content: Add a contact form to the home page
              created_at: '2026-10-05T14:30:00.123456+00:00'
              id: 3b9d2f6e-8c41-4a7e-9f05-1d2c3b4a5e6f
        is_paused:
          type: boolean
          title: Is Paused
          description: Whether the queue is paused. While it is, queued messages don't run.
          example: false
        session_id:
          anyOf:
            - type: string
            - type: 'null'
          title: Session Id
          description: >-
            Present only on enrolled Base Code apps: the session owning this
            queue.
          example: 68f1a2b3c4d5e6f708192a4
      type: object
      required:
        - items
        - is_paused
      title: MessageQueue
      description: The messages waiting to run, in the order they run.
    StandardErrorEnvelope:
      properties:
        error:
          $ref: '#/components/schemas/StandardError'
          description: What went wrong.
      type: object
      required:
        - error
      title: StandardErrorEnvelope
      description: The error body returned in the standard envelope.
    QueuedMessage:
      properties:
        id:
          type: string
          title: Id
          description: ID of the queued message.
          example: 3b9d2f6e-8c41-4a7e-9f05-1d2c3b4a5e6f
        content:
          type: string
          title: Content
          description: Text of the message, as it will be sent to the AI.
          example: Add a contact form to the home page
        branch_id:
          anyOf:
            - type: string
            - type: 'null'
          title: Branch Id
          description: >-
            Target branch ID. Null means main on branch queues, or a branch
            chosen when execution starts for session_current requests.
          example: 68f1a2b3c4d5e6f708192a3b
        target_mode:
          anyOf:
            - type: string
            - type: 'null'
          title: Target Mode
          description: >-
            Present on enrolled session queues: fixed uses branch_id;
            session_current resolves the session's current branch when execution
            starts.
          example: session_current
        is_continuation:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Is Continuation
          description: >-
            Present on enrolled session queues. True means remaining work of the
            active request, ahead of later independent requests.
          example: false
        created_at:
          type: string
          title: Created At
          description: When the message was queued, as a UTC timestamp in ISO 8601 format.
          example: '2026-10-05T14:30:00.123456+00:00'
      type: object
      required:
        - id
        - content
        - branch_id
        - created_at
      title: QueuedMessage
      description: A message waiting for the AI to finish its current turn.
    StandardError:
      properties:
        code:
          type: string
          title: Code
          description: >-
            Stable machine-readable cause of the failure. Match on this, not on
            `message`.
          example: not_found
        message:
          type: string
          title: Message
          description: Human-readable explanation. It isn't a stable contract.
          example: App not found
        details:
          additionalProperties: true
          type: object
          title: Details
          description: >-
            Structured context for the failure, or an empty object when there's
            none.
          example: {}
      type: object
      required:
        - code
        - message
      title: StandardError
  securitySchemes:
    PersonalAccessTokenAuth:
      type: http
      scheme: bearer
      description: >-
        Personal access token, sent as `Authorization: Bearer <token>`. Each
        operation lists the permission it needs: `read_only` or `full_access`. A
        full-access token can call every operation. A read-only token can call
        only the operations that list `read_only`; anything else returns 403
        `read_only_credential_route_not_allowed`.
    WorkspaceApiKeyAuth:
      type: apiKey
      in: header
      name: api_key
      description: >-
        Workspace API key, sent as `api_key: <key>`. Each operation that accepts
        one lists what the key needs: a permission, `read_only` or
        `full_access`, like a personal access token, or a scope. A key without
        the scope gets 403 `workspace_api_key_scope_required`.
    WorkspaceApiKeyBearerAuth:
      type: http
      scheme: bearer
      description: >-
        Workspace API key, sent as `Authorization: Bearer <key>`. Accepted
        wherever `api_key` is, with the same permission.

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.