---
title: "Submit tool-call input"
method: POST
path: "/api/apps/{app_id}/chat/submit-tool-call-input"
---

# Submit tool-call input

`POST /api/apps/{app_id}/chat/submit-tool-call-input`

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

Approves or rejects one tool call the AI builder is waiting on, then resumes the turn.

Some steps pause for you before they run. The turn stops with an `assistant` message whose tool call has no result yet, and the builder waits. Answer it here to let the turn continue. Use [Read conversation messages](/api-reference/read-conversation-messages) to find the tool call that is waiting and take its ID.

The request stays open until the resumed turn settles, so it can take several minutes. Resuming a turn consumes credits. To answer several waiting tool calls at once, use [Submit tool-call input (batch)](/api-reference/submit-tool-call-input-batch).

<Warning>A turn that fails still returns `200`. Check `status.state`: `error` means the turn failed, and `status.error_source` says where. `paywall` there means you ran out of credits.</Warning>

<Warning>The response includes fields beyond the ones documented here. Don't rely on undocumented response fields, as they can change at any time. Send only the fields documented here. Other request fields are not supported and their behavior can change.</Warning>

## Path parameters

- `app_id` string, required — ID of the app whose builder chat this request acts on.

## Request body

- object
  - `tool_call_id` string, required — ID of the tool call to answer. Read it off the waiting `assistant` message returned by [Read conversation messages](/api-reference/read-conversation-messages).
  - `action` 'approved' | 'rejected', required — Whether to let the tool call run or turn it down. Rejecting tells the builder to continue without doing that step.
  - `message_id` string — ID of the message the tool call belongs to. Some tools use it to report progress.

## Response `200`

The app once the resumed turn finished.

- ChatTurnResponse — The app document the chat endpoints return once a turn settles. The real payload is the whole app document, so this is a strict subset: the fields a caller needs to see what the turn did and whether it succeeded.
  - `id` string, nullable — ID of the app.
  - `name` string, nullable — Display name of the app.
  - `status` AppStatusResponse
    - `state` 'ready' | 'processing' | 'error', required — Where the app is in its build lifecycle. Ready means idle with no build in progress, processing means the app is being generated or modified, and error means the last build failed. This tracks building, not publishing.
    - `details` string, nullable — Human readable note about the current state, such as what is being processed or why it failed, or `null` when there is nothing to report.
    - `request_id` string, nullable — ID of the request that last changed the status, or `null` if the status has never changed. Useful when reporting an issue.
    - `last_updated_date` string, date-time, nullable — Time the status was last updated.
    - `error_source` string, nullable — Where the failure originated when the state is error, or `null` otherwise.
    - `paywall_context` PaywallStatusContextResponse
      - `billing_organization_id` string, required — ID of the billing organization the paywall was evaluated against.
      - `user_id` string, required — ID of the user the paywall was evaluated for.
      - `evaluated_at` string, date-time, required — Time the paywall condition was evaluated.
  - `conversation` ChatTurnConversation
    - `id` string, nullable — ID of the conversation.
    - `messages` ConversationMessageSummary[], nullable — The conversation's messages once the request finished, oldest first.
      - `id` string, nullable — ID of the message.
      - `role` 'user' | 'assistant' | 'system', nullable — Who produced the message. `user` is a prompt sent to the AI builder, `assistant` is the builder's reply, and `system` is a platform generated note.
      - `content` string, nullable — Text of the message. Empty on assistant turns whose work is carried entirely by tool calls, and on internal diff messages.
      - `file_urls` string[], nullable — URLs of the files attached to the message, or `null` if it has none.
      - `hidden` boolean, nullable — Whether the message is internal and hidden from the chat in the app editor.
      - `checkpoint_id` string, nullable — ID of the [checkpoint](/developers/references/app-management/get-started/overview#checkpoints) this message produced, or `null` if it produced none. Pass it as `checkpoint_id` to [Deploy an app](/api-reference/deploy-an-app) to deploy that version.
      - `tool_calls` ConversationToolCallSummary[], nullable — Tool calls the builder made on this message, or `null` on messages that made none. A call with `status` set to `waiting_for_user_input` is holding the turn open until you answer it.
        - `id` string, nullable — ID of the tool call. Pass it as `tool_call_id` to [Submit tool-call input](/api-reference/submit-tool-call-input) when `status` is `waiting_for_user_input`.
        - `name` string, nullable — Name of the tool the builder is calling.
        - `status` 'running' | 'success' | 'error' | 'stopped' | 'waiting_for_user_input', nullable — Where the tool call is. `waiting_for_user_input` means the turn is paused until you answer it.
        - `requires_user_input` boolean, nullable — Whether this tool call needs you to approve or reject it before the turn can continue.
      - `usage` MessageUsageSummary
        - `prompt_tokens` integer, nullable — Tokens the model read for this message, including the conversation history it was given.
        - `completion_tokens` integer, nullable — Tokens the model generated for this message.
        - `credits_charged` number, nullable — Credits charged for this message, or `null` if it was not billed.
      - `metadata` MessageMetadataSummary
        - `created_date` string, date-time, nullable — Time the message was created.
        - `created_by_email` string, nullable — Email of the user whose turn produced the message.

## Other responses

- `400` — The app has unsaved sandbox changes that could not be committed first. Retry the request.
- `401` — Missing or invalid credentials.
- `403` — You don't have access to this app.
- `404` — App not found, or no such tool call is waiting.
- `409` — The app is busy with another operation that blocks this resume.
- `422` — Validation Error
- `503` — The server is shutting down. Retry the request.

---

[API](https://skmtc.dev/idealspot/apis/base44-app-management-api.md) · [All operations](https://skmtc.dev/idealspot/apis/base44-app-management-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/idealspot/base44-app-management-api/revisions/31ef75eb64ab/schema)