# AskUI Integration (`sovanza.inc/askui-integration`) Actor

AskUI Integration runs UI automation tasks through AskUI-compatible environments using natural language or structured steps. It returns task status, screenshots, logs, action traces, timing, and session metadata for QA, RPA, DevOps, and automation workflows.

- **URL**: https://apify.com/sovanza.inc/askui-integration.md
- **Developed by:** [Sovanza](https://apify.com/sovanza.inc) (community)
- **Categories:** Automation, Developer tools, Integrations
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, NaN bookmarks
- **User rating**: No ratings yet

## Pricing

from $20.00 / 1,000 task results

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event

## What's an Apify Actor?

Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md):

```bash
npm install apify-client
```

In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md):

```bash
pip install apify-client
```

In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md):

````bash
# MacOS / Linux
curl -fsSL https://apify.com/install-cli.sh | bash
# Windows
irm https://apify.com/install-cli.ps1 | iex
```bash

In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md).

If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).


# README

### AskUI Integration – UI Automation Orchestrator & Task Execution Engine

A powerful integration actor that connects Apify workflows with AskUI to execute UI automation tasks across desktop, browser, and mobile environments.
This is not a scraper — it is a UI automation orchestration layer designed for running, managing, and scaling automation workflows using natural language or structured steps.

### 🚀 Start Automating UI Workflows

Run automation tasks across platforms with full control and visibility.

👉 Execute UI automation using natural language  
👉 Run structured task workflows across systems  
👉 Collect screenshots, logs, and action traces  
👉 Integrate automation into CI/CD and pipelines  

Click “Run” to execute your first automation task.

### 🧠 What This Actor Actually Solves

UI automation is hard to scale because:

- Tools are platform-specific (desktop, web, mobile)
- Automation scripts require maintenance
- No unified orchestration layer
- Difficult to integrate into pipelines

This actor solves that by acting as a central orchestration engine:

- Accepts tasks from Apify
- Sends them to AskUI environments
- Monitors execution
- Returns structured results

### 🔄 How It Works

1. Define tasks (natural language or structured steps)
2. Actor validates and prepares execution payload
3. Tasks are dispatched to AskUI-compatible environment
4. Execution is monitored and polled
5. Results are normalized and returned

### ⚙️ Task Definition Modes

**🔹 Natural Language Automation**

Describe actions like:

- “Open browser and search for product”
- “Login and submit form”

**🔹 Structured Steps**

Define precise actions (examples):

- click
- type
- navigate
- extract

**🔹 Hybrid Mode**

Combine both for flexibility and precision.

### ⚡ Core Features

- AskUI integration for UI automation
- Cross-platform automation (desktop, web, mobile)
- Natural language task execution
- Structured workflow automation
- Batch task processing
- Artifact collection (screenshots, logs, traces)
- Execution monitoring & status tracking
- Normalized output for pipelines

### 📊 Execution Artifacts

Each task can return:

- Screenshots (UI state capture)
- Execution logs (step-by-step logs)
- Action traces (detailed workflow steps)
- Timing data (execution duration)
- Session metadata

### 🎯 Real-World Use Cases

- **🧪 QA Automation & Testing:** run UI tests across multiple platforms and environments.
- **🤖 RPA (Robotic Process Automation):** automate repetitive UI tasks across applications.
- **⚙️ DevOps & CI/CD:** integrate UI-level checks into deployment pipelines.
- **🖥️ Cross-Platform Automation:** control desktop apps, browsers, and mobile interfaces.
- **📊 Business Workflow Automation:** automate data entry, form submissions, and system interactions.

### 🛠️ How to Use

- Define tasks in input (natural language or steps)
- Choose run mode (`dry_run`, `execute`, `validate_only`)
- Configure AskUI environment (optional)
- Run the actor
- Review results (logs, screenshots, status)

### 🛠️ How to Use AskUI Integration on Apify (aligned to this implementation)

At a high level:

1. Add one or more automation tasks in `tasks` (natural language, structured steps, or hybrid).
2. Choose `runMode` (`dry_run`, `execute`, or `validate_only`).
3. Choose `targetEnvironment`:
   - `adapter_mock` (default) for out-of-the-box testing
   - `askui_remote` to dispatch to a remote AskUI-compatible API (requires credentials)
4. Run the actor and review results in the **default dataset** (and optionally a combined export via KV store).

#### Input example

Full schema: `INPUT_SCHEMA.json`. Example:

```json
{
  "tasks": [
    {
      "taskId": "demo-001",
      "title": "Open calculator and add two numbers",
      "instruction": "Open the calculator app, type 42 + 18, and press equals.",
      "taskMode": "natural_language",
      "platformHint": "windows",
      "applicationHint": "calculator",
      "expectedOutcome": "Calculator displays 60"
    }
  ],
  "runMode": "dry_run",
  "taskDefinitionStyle": "hybrid",
  "targetEnvironment": "adapter_mock",
  "maxConcurrency": 3,
  "outputMode": "dataset"
}
````

- **`tasks`** (required): Array of task objects. Each task must include at least a `title` or `instruction`.
- **`runMode`** (optional): `dry_run` (default), `execute`, or `validate_only`.
- **`targetEnvironment`** (optional): `adapter_mock` (default), `askui_remote`, or `askui_local_agent` (placeholder).
- **`askUiBaseUrl`** (required for `askui_remote`): Base URL to your AskUI-compatible gateway.
- **`askUiAccessToken`** (required for `askui_remote`): Secret token for the remote gateway.
- **`maxConcurrency`** (optional): Parallel task processing limit.
- **`outputMode`** (optional): `dataset`, `kv_store`, or `both` (default `dataset`).
- **`outputKvStoreKey`** (optional): KV key name for combined output (default `ASKUI_OUTPUT`).

### Output

Results are stored in the Actor’s **default dataset**. Each item is a compact JSON object and typically includes:

- **Identity:** `taskId`, `inputTitle`
- **Modes:** `runMode`, `targetEnvironment`
- **Status:** `executionStatus`, `normalizedResult`
- **Artifacts (optional):** `artifacts.screenshots`, `artifacts.logs`, `artifacts.actionTrace`
- **Meta:** `sessionId`, `durationSecs`, `timestamp`

Example result row (illustrative):

```json
{
  "type": "task_result",
  "taskId": "demo-001",
  "inputTitle": "Open calculator and add two numbers",
  "runMode": "dry_run",
  "targetEnvironment": "adapter_mock",
  "executionStatus": "validated",
  "normalizedResult": "ready",
  "builtPayloadPreview": {
    "taskId": "demo-001",
    "title": "Open calculator and add two numbers",
    "taskMode": "natural_language",
    "platform": "windows"
  },
  "timestamp": "2026-04-29T12:00:00.000Z"
}
```

### 🔌 Integration Options

This actor can be used with:

- Apify API
- Webhooks and schedules
- Zapier / Make
- Internal automation systems

### 🔐 Execution Modes Explained

- `dry_run` → Validate tasks and preview execution
- `execute` → Run tasks on AskUI environment
- `validate_only` → Check task structure only

### FAQ

#### What is AskUI integration used for?

This tool connects AskUI with the Apify platform to enable UI automation workflows, task orchestration, and cross-platform automation.

#### Is this a web scraping tool?

No. This is a UI automation and RPA orchestration tool, not a scraper.

#### Can I automate tasks using natural language?

Yes. You can describe tasks in plain English, and the actor will process and execute them using AskUI.

#### What platforms does this support?

It supports desktop applications, web browsers, and mobile interfaces through AskUI environments.

#### Can I use this for QA automation testing?

Yes. It is ideal for UI testing, regression testing, and cross-platform QA automation.

#### Does this work as an RPA tool?

Yes. It can be used for robotic process automation (RPA), including repetitive UI workflows and business automation tasks.

#### What is dry\_run mode?

Dry run validates tasks and builds execution payloads without actually executing them — useful for testing.

#### Can I run multiple automation tasks at once?

Yes. The actor supports batch execution with configurable concurrency.

#### What kind of output do I get?

You get structured results including:

- Execution status
- Logs
- Screenshots
- Action traces

#### Do I need AskUI credentials?

Only if you want to run real executions. Mock mode works without any external setup.

#### Can I integrate this into CI/CD pipelines?

Yes. This is one of the primary use cases for automation and DevOps workflows.

#### What makes this different from traditional automation tools?

This actor provides:

- Central orchestration
- Cross-platform support
- Natural language automation
- Structured output for pipelines

### 📈 Why Use This Actor?

Instead of managing multiple automation tools, this gives you:

- Unified automation layer
- Scalable task execution
- Structured output
- Easy integration into workflows

### 🚀 Get Started

Run your first UI automation task and streamline your workflows instantly.

# Actor input Schema

## `tasks` (type: `array`):

List of AskUI automation task requests. Each item defines a UI automation job to validate, dispatch, or execute.

## `runMode` (type: `string`):

Execution mode. 'dry\_run' validates and previews payloads without executing. 'execute' dispatches to the target adapter. 'validate\_only' checks task validity.

## `taskDefinitionStyle` (type: `string`):

Default task definition style. Individual tasks can override via taskMode.

## `targetEnvironment` (type: `string`):

Where tasks are dispatched. 'adapter\_mock' runs locally with deterministic fake outputs. 'askui\_remote' dispatches to an AskUI-compatible API. 'askui\_local\_agent' is a placeholder for local AskUI Agent OS.

## `askUiBaseUrl` (type: `string`):

Base URL for the AskUI-compatible execution API or gateway. Required for askui\_remote mode.

## `askUiWorkspaceId` (type: `string`):

Workspace identifier for the AskUI environment.

## `askUiAccessToken` (type: `string`):

Secret access token for authenticating with the AskUI API. Never logged or included in output.

## `sessionId` (type: `string`):

Optional existing AskUI or agent session identifier to reuse.

## `createNewSession` (type: `boolean`):

Whether to create a new AskUI session if no sessionId is provided.

## `platform` (type: `string`):

Default target platform for automation tasks.

## `applicationType` (type: `string`):

Default application type for automation tasks.

## `includeScreenshots` (type: `boolean`):

Collect screenshot artifacts from task execution.

## `includeExecutionLogs` (type: `boolean`):

Collect execution log entries from task runs.

## `includeActionTrace` (type: `boolean`):

Collect step-by-step action trace from execution.

## `includeArtifacts` (type: `boolean`):

Collect all execution artifacts (screenshots, logs, traces).

## `maxTasks` (type: `integer`):

Maximum number of tasks to process in a single run.

## `maxConcurrency` (type: `integer`):

Maximum number of tasks to execute concurrently.

## `requestTimeoutSecs` (type: `integer`):

Timeout in seconds for individual HTTP requests to the AskUI adapter.

## `pollIntervalSecs` (type: `integer`):

Seconds between status polling attempts during task execution.

## `maxExecutionWaitSecs` (type: `integer`):

Maximum seconds to wait for a single task to complete before timing out.

## `failFast` (type: `boolean`):

Stop the entire run on the first task failure instead of continuing.

## `includeDebugFields` (type: `boolean`):

Add diagnostic fields (adapter info, polling stats, normalization reasons) to output. Never includes secrets.

## `outputMode` (type: `string`):

Where to write results. 'dataset' writes individual rows, 'kv\_store' writes a combined export, 'both' does both.

## `outputKvStoreKey` (type: `string`):

Key name used when writing the combined export to the key-value store.

## Actor input object example

```json
{
  "tasks": [
    {
      "taskId": "demo-001",
      "title": "Open calculator and add two numbers",
      "instruction": "Open the calculator app, type 42 + 18, and press equals.",
      "taskMode": "natural_language",
      "platformHint": "windows",
      "applicationHint": "calculator",
      "expectedOutcome": "Calculator displays 60"
    }
  ],
  "runMode": "dry_run",
  "taskDefinitionStyle": "hybrid",
  "targetEnvironment": "adapter_mock",
  "askUiBaseUrl": "",
  "askUiWorkspaceId": "",
  "sessionId": "",
  "createNewSession": true,
  "platform": "auto",
  "applicationType": "unknown",
  "includeScreenshots": true,
  "includeExecutionLogs": true,
  "includeActionTrace": true,
  "includeArtifacts": true,
  "maxTasks": 50,
  "maxConcurrency": 3,
  "requestTimeoutSecs": 60,
  "pollIntervalSecs": 3,
  "maxExecutionWaitSecs": 300,
  "failFast": false,
  "includeDebugFields": false,
  "outputMode": "dataset",
  "outputKvStoreKey": "ASKUI_OUTPUT"
}
```

# Actor output Schema

## `results` (type: `string`):

Validated or executed automation tasks in the default dataset.

## `export` (type: `string`):

Full JSON export with results and summary when outputMode is kv\_store or both.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "tasks": [
        {
            "taskId": "demo-001",
            "title": "Open calculator and add two numbers",
            "instruction": "Open the calculator app, type 42 + 18, and press equals.",
            "taskMode": "natural_language",
            "platformHint": "windows",
            "applicationHint": "calculator",
            "expectedOutcome": "Calculator displays 60"
        }
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("sovanza.inc/askui-integration").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "tasks": [{
            "taskId": "demo-001",
            "title": "Open calculator and add two numbers",
            "instruction": "Open the calculator app, type 42 + 18, and press equals.",
            "taskMode": "natural_language",
            "platformHint": "windows",
            "applicationHint": "calculator",
            "expectedOutcome": "Calculator displays 60",
        }] }

# Run the Actor and wait for it to finish
run = client.actor("sovanza.inc/askui-integration").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "tasks": [
    {
      "taskId": "demo-001",
      "title": "Open calculator and add two numbers",
      "instruction": "Open the calculator app, type 42 + 18, and press equals.",
      "taskMode": "natural_language",
      "platformHint": "windows",
      "applicationHint": "calculator",
      "expectedOutcome": "Calculator displays 60"
    }
  ]
}' |
apify call sovanza.inc/askui-integration --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://mcp.apify.com/?tools=sovanza.inc/askui-integration",
                "--header",
                "Authorization: Bearer <YOUR_API_TOKEN>"
            ]
        }
    }
}

```

## OpenAPI specification

```json
{
    "openapi": "3.0.1",
    "info": {
        "title": "AskUI Integration",
        "description": "AskUI Integration runs UI automation tasks through AskUI-compatible environments using natural language or structured steps. It returns task status, screenshots, logs, action traces, timing, and session metadata for QA, RPA, DevOps, and automation workflows.",
        "version": "0.0",
        "x-build-id": "9hb4GIufEoVP4Bprb"
    },
    "servers": [
        {
            "url": "https://api.apify.com/v2"
        }
    ],
    "paths": {
        "/acts/sovanza.inc~askui-integration/run-sync-get-dataset-items": {
            "post": {
                "operationId": "run-sync-get-dataset-items-sovanza.inc-askui-integration",
                "x-openai-isConsequential": false,
                "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
                "tags": [
                    "Run Actor"
                ],
                "requestBody": {
                    "required": true,
                    "content": {
                        "application/json": {
                            "schema": {
                                "$ref": "#/components/schemas/inputSchema"
                            }
                        }
                    }
                },
                "parameters": [
                    {
                        "name": "token",
                        "in": "query",
                        "required": true,
                        "schema": {
                            "type": "string"
                        },
                        "description": "Enter your Apify token here"
                    }
                ],
                "responses": {
                    "200": {
                        "description": "OK"
                    }
                }
            }
        },
        "/acts/sovanza.inc~askui-integration/runs": {
            "post": {
                "operationId": "runs-sync-sovanza.inc-askui-integration",
                "x-openai-isConsequential": false,
                "summary": "Executes an Actor and returns information about the initiated run in response.",
                "tags": [
                    "Run Actor"
                ],
                "requestBody": {
                    "required": true,
                    "content": {
                        "application/json": {
                            "schema": {
                                "$ref": "#/components/schemas/inputSchema"
                            }
                        }
                    }
                },
                "parameters": [
                    {
                        "name": "token",
                        "in": "query",
                        "required": true,
                        "schema": {
                            "type": "string"
                        },
                        "description": "Enter your Apify token here"
                    }
                ],
                "responses": {
                    "200": {
                        "description": "OK",
                        "content": {
                            "application/json": {
                                "schema": {
                                    "$ref": "#/components/schemas/runsResponseSchema"
                                }
                            }
                        }
                    }
                }
            }
        },
        "/acts/sovanza.inc~askui-integration/run-sync": {
            "post": {
                "operationId": "run-sync-sovanza.inc-askui-integration",
                "x-openai-isConsequential": false,
                "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
                "tags": [
                    "Run Actor"
                ],
                "requestBody": {
                    "required": true,
                    "content": {
                        "application/json": {
                            "schema": {
                                "$ref": "#/components/schemas/inputSchema"
                            }
                        }
                    }
                },
                "parameters": [
                    {
                        "name": "token",
                        "in": "query",
                        "required": true,
                        "schema": {
                            "type": "string"
                        },
                        "description": "Enter your Apify token here"
                    }
                ],
                "responses": {
                    "200": {
                        "description": "OK"
                    }
                }
            }
        }
    },
    "components": {
        "schemas": {
            "inputSchema": {
                "type": "object",
                "required": [
                    "tasks"
                ],
                "properties": {
                    "tasks": {
                        "title": "Automation Tasks",
                        "type": "array",
                        "description": "List of AskUI automation task requests. Each item defines a UI automation job to validate, dispatch, or execute.",
                        "items": {
                            "type": "object",
                            "properties": {
                                "taskId": {
                                    "title": "Task ID",
                                    "type": "string",
                                    "description": "Unique identifier for this task. Auto-generated if omitted.",
                                    "editor": "textfield"
                                },
                                "title": {
                                    "title": "Task Title",
                                    "type": "string",
                                    "description": "Short descriptive name for the automation task.",
                                    "editor": "textfield"
                                },
                                "instruction": {
                                    "title": "Instruction",
                                    "type": "string",
                                    "description": "Natural language instruction describing what the automation should do.",
                                    "editor": "textarea"
                                },
                                "taskMode": {
                                    "title": "Task Mode",
                                    "type": "string",
                                    "description": "How this task is defined: natural_language, structured_steps, or hybrid.",
                                    "editor": "textfield"
                                },
                                "platformHint": {
                                    "title": "Platform Hint",
                                    "type": "string",
                                    "description": "Hint for the target platform: windows, macos, linux, android, ios, browser.",
                                    "editor": "textfield"
                                },
                                "applicationHint": {
                                    "title": "Application Hint",
                                    "type": "string",
                                    "description": "Hint for the target application (e.g. chrome, excel, calculator).",
                                    "editor": "textfield"
                                },
                                "deviceTarget": {
                                    "title": "Device Target",
                                    "type": "string",
                                    "description": "Specific device or VM identifier to target.",
                                    "editor": "textfield"
                                },
                                "context": {
                                    "title": "Context",
                                    "type": "string",
                                    "description": "Additional context or notes for the automation task.",
                                    "editor": "textarea"
                                },
                                "variables": {
                                    "title": "Variables",
                                    "type": "object",
                                    "description": "Key-value variables to inject into the task (e.g. URLs, search terms).",
                                    "editor": "json"
                                },
                                "steps": {
                                    "title": "Structured Steps",
                                    "type": "array",
                                    "description": "Ordered list of structured automation steps (for structured_steps or hybrid mode).",
                                    "editor": "json"
                                },
                                "expectedOutcome": {
                                    "title": "Expected Outcome",
                                    "type": "string",
                                    "description": "What the successful completion of this task looks like.",
                                    "editor": "textfield"
                                }
                            }
                        }
                    },
                    "runMode": {
                        "title": "Run Mode",
                        "enum": [
                            "dry_run",
                            "execute",
                            "validate_only"
                        ],
                        "type": "string",
                        "description": "Execution mode. 'dry_run' validates and previews payloads without executing. 'execute' dispatches to the target adapter. 'validate_only' checks task validity.",
                        "default": "dry_run"
                    },
                    "taskDefinitionStyle": {
                        "title": "Task Definition Style",
                        "enum": [
                            "natural_language",
                            "structured_steps",
                            "hybrid"
                        ],
                        "type": "string",
                        "description": "Default task definition style. Individual tasks can override via taskMode.",
                        "default": "hybrid"
                    },
                    "targetEnvironment": {
                        "title": "Target Environment",
                        "enum": [
                            "askui_remote",
                            "askui_local_agent",
                            "adapter_mock"
                        ],
                        "type": "string",
                        "description": "Where tasks are dispatched. 'adapter_mock' runs locally with deterministic fake outputs. 'askui_remote' dispatches to an AskUI-compatible API. 'askui_local_agent' is a placeholder for local AskUI Agent OS.",
                        "default": "adapter_mock"
                    },
                    "askUiBaseUrl": {
                        "title": "AskUI Base URL",
                        "type": "string",
                        "description": "Base URL for the AskUI-compatible execution API or gateway. Required for askui_remote mode.",
                        "default": ""
                    },
                    "askUiWorkspaceId": {
                        "title": "AskUI Workspace ID",
                        "type": "string",
                        "description": "Workspace identifier for the AskUI environment.",
                        "default": ""
                    },
                    "askUiAccessToken": {
                        "title": "AskUI Access Token",
                        "type": "string",
                        "description": "Secret access token for authenticating with the AskUI API. Never logged or included in output."
                    },
                    "sessionId": {
                        "title": "Session ID",
                        "type": "string",
                        "description": "Optional existing AskUI or agent session identifier to reuse.",
                        "default": ""
                    },
                    "createNewSession": {
                        "title": "Create New Session",
                        "type": "boolean",
                        "description": "Whether to create a new AskUI session if no sessionId is provided.",
                        "default": true
                    },
                    "platform": {
                        "title": "Platform",
                        "enum": [
                            "windows",
                            "macos",
                            "linux",
                            "android",
                            "ios",
                            "browser",
                            "auto"
                        ],
                        "type": "string",
                        "description": "Default target platform for automation tasks.",
                        "default": "auto"
                    },
                    "applicationType": {
                        "title": "Application Type",
                        "enum": [
                            "desktop_app",
                            "web_app",
                            "mobile_app",
                            "citrix",
                            "terminal",
                            "unknown"
                        ],
                        "type": "string",
                        "description": "Default application type for automation tasks.",
                        "default": "unknown"
                    },
                    "includeScreenshots": {
                        "title": "Include Screenshots",
                        "type": "boolean",
                        "description": "Collect screenshot artifacts from task execution.",
                        "default": true
                    },
                    "includeExecutionLogs": {
                        "title": "Include Execution Logs",
                        "type": "boolean",
                        "description": "Collect execution log entries from task runs.",
                        "default": true
                    },
                    "includeActionTrace": {
                        "title": "Include Action Trace",
                        "type": "boolean",
                        "description": "Collect step-by-step action trace from execution.",
                        "default": true
                    },
                    "includeArtifacts": {
                        "title": "Include Artifacts",
                        "type": "boolean",
                        "description": "Collect all execution artifacts (screenshots, logs, traces).",
                        "default": true
                    },
                    "maxTasks": {
                        "title": "Max Tasks",
                        "minimum": 1,
                        "maximum": 500,
                        "type": "integer",
                        "description": "Maximum number of tasks to process in a single run.",
                        "default": 50
                    },
                    "maxConcurrency": {
                        "title": "Max Concurrency",
                        "minimum": 1,
                        "maximum": 20,
                        "type": "integer",
                        "description": "Maximum number of tasks to execute concurrently.",
                        "default": 3
                    },
                    "requestTimeoutSecs": {
                        "title": "Request Timeout (seconds)",
                        "minimum": 5,
                        "maximum": 600,
                        "type": "integer",
                        "description": "Timeout in seconds for individual HTTP requests to the AskUI adapter.",
                        "default": 60
                    },
                    "pollIntervalSecs": {
                        "title": "Poll Interval (seconds)",
                        "minimum": 1,
                        "maximum": 60,
                        "type": "integer",
                        "description": "Seconds between status polling attempts during task execution.",
                        "default": 3
                    },
                    "maxExecutionWaitSecs": {
                        "title": "Max Execution Wait (seconds)",
                        "minimum": 10,
                        "maximum": 3600,
                        "type": "integer",
                        "description": "Maximum seconds to wait for a single task to complete before timing out.",
                        "default": 300
                    },
                    "failFast": {
                        "title": "Fail Fast",
                        "type": "boolean",
                        "description": "Stop the entire run on the first task failure instead of continuing.",
                        "default": false
                    },
                    "includeDebugFields": {
                        "title": "Include Debug Fields",
                        "type": "boolean",
                        "description": "Add diagnostic fields (adapter info, polling stats, normalization reasons) to output. Never includes secrets.",
                        "default": false
                    },
                    "outputMode": {
                        "title": "Output Mode",
                        "enum": [
                            "dataset",
                            "kv_store",
                            "both"
                        ],
                        "type": "string",
                        "description": "Where to write results. 'dataset' writes individual rows, 'kv_store' writes a combined export, 'both' does both.",
                        "default": "dataset"
                    },
                    "outputKvStoreKey": {
                        "title": "Output KV Store Key",
                        "type": "string",
                        "description": "Key name used when writing the combined export to the key-value store.",
                        "default": "ASKUI_OUTPUT"
                    }
                }
            },
            "runsResponseSchema": {
                "type": "object",
                "properties": {
                    "data": {
                        "type": "object",
                        "properties": {
                            "id": {
                                "type": "string"
                            },
                            "actId": {
                                "type": "string"
                            },
                            "userId": {
                                "type": "string"
                            },
                            "startedAt": {
                                "type": "string",
                                "format": "date-time",
                                "example": "2025-01-08T00:00:00.000Z"
                            },
                            "finishedAt": {
                                "type": "string",
                                "format": "date-time",
                                "example": "2025-01-08T00:00:00.000Z"
                            },
                            "status": {
                                "type": "string",
                                "example": "READY"
                            },
                            "meta": {
                                "type": "object",
                                "properties": {
                                    "origin": {
                                        "type": "string",
                                        "example": "API"
                                    },
                                    "userAgent": {
                                        "type": "string"
                                    }
                                }
                            },
                            "stats": {
                                "type": "object",
                                "properties": {
                                    "inputBodyLen": {
                                        "type": "integer",
                                        "example": 2000
                                    },
                                    "rebootCount": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "restartCount": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "resurrectCount": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "computeUnits": {
                                        "type": "integer",
                                        "example": 0
                                    }
                                }
                            },
                            "options": {
                                "type": "object",
                                "properties": {
                                    "build": {
                                        "type": "string",
                                        "example": "latest"
                                    },
                                    "timeoutSecs": {
                                        "type": "integer",
                                        "example": 300
                                    },
                                    "memoryMbytes": {
                                        "type": "integer",
                                        "example": 1024
                                    },
                                    "diskMbytes": {
                                        "type": "integer",
                                        "example": 2048
                                    }
                                }
                            },
                            "buildId": {
                                "type": "string"
                            },
                            "defaultKeyValueStoreId": {
                                "type": "string"
                            },
                            "defaultDatasetId": {
                                "type": "string"
                            },
                            "defaultRequestQueueId": {
                                "type": "string"
                            },
                            "buildNumber": {
                                "type": "string",
                                "example": "1.0.0"
                            },
                            "containerUrl": {
                                "type": "string"
                            },
                            "usage": {
                                "type": "object",
                                "properties": {
                                    "ACTOR_COMPUTE_UNITS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATASET_READS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATASET_WRITES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "KEY_VALUE_STORE_READS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "KEY_VALUE_STORE_WRITES": {
                                        "type": "integer",
                                        "example": 1
                                    },
                                    "KEY_VALUE_STORE_LISTS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "REQUEST_QUEUE_READS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "REQUEST_QUEUE_WRITES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATA_TRANSFER_INTERNAL_GBYTES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATA_TRANSFER_EXTERNAL_GBYTES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "PROXY_SERPS": {
                                        "type": "integer",
                                        "example": 0
                                    }
                                }
                            },
                            "usageTotalUsd": {
                                "type": "number",
                                "example": 0.00005
                            },
                            "usageUsd": {
                                "type": "object",
                                "properties": {
                                    "ACTOR_COMPUTE_UNITS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATASET_READS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATASET_WRITES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "KEY_VALUE_STORE_READS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "KEY_VALUE_STORE_WRITES": {
                                        "type": "number",
                                        "example": 0.00005
                                    },
                                    "KEY_VALUE_STORE_LISTS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "REQUEST_QUEUE_READS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "REQUEST_QUEUE_WRITES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATA_TRANSFER_INTERNAL_GBYTES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATA_TRANSFER_EXTERNAL_GBYTES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "PROXY_SERPS": {
                                        "type": "integer",
                                        "example": 0
                                    }
                                }
                            }
                        }
                    }
                }
            }
        }
    }
}
```