vodorod/Dorod-Sky
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Add TypeScript SDK reference docs with verified code examples (#4730)

Browse Source
This commit is contained in:
Naman
2026-02-13 06:52:58 +05:30
committed by GitHub
parent 49d281ca63
commit 0959dae9d1
11 changed files with 2540 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

403
docs/ts-sdk-reference/browser-automation.mdx Normal file
View File

@@ -0,0 +1,403 @@
---
title: Browser Automation
subtitle: Control cloud browsers with Playwright + AI
slug: ts-sdk-reference/browser-automation
---
The TypeScript SDK extends Playwright with AI-powered browser automation. Launch a cloud browser, get a page that works like a normal Playwright `Page`, then use `.agent` for full-task AI execution or AI-enhanced versions of `click`, `fill`, and `selectOption` that fall back to natural language when selectors fail.
---
## Launch a cloud browser
### `launchCloudBrowser`
Create a new cloud-hosted browser session and connect to it.
```typescript
const browser = await skyvern.launchCloudBrowser();
const page = await browser.getWorkingPage();
// Use Playwright methods
await page.goto("https://example.com");
// Or use AI
await page.agent.runTask("Fill out the contact form and submit it");
await browser.close();
```
#### Parameters
| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `timeout` | `number` | No | `60` | Session timeout in minutes (5–1440). |
| `proxyLocation` | `ProxyLocation` | No | `undefined` | Geographic proxy location for browser traffic. |
#### Returns `SkyvernBrowser`
<Note>
Cloud browser sessions are only available with `SkyvernEnvironment.Cloud` or `SkyvernEnvironment.Staging`.
</Note>
---
### `useCloudBrowser`
Get or create a cloud browser session. Reuses the most recent available session if one exists, otherwise creates a new one.
```typescript
const browser = await skyvern.useCloudBrowser();
const page = await browser.getWorkingPage();
```
#### Parameters
Same as `launchCloudBrowser`. Options are only used when creating a new session.
#### Returns `SkyvernBrowser`
---
### `connectToCloudBrowserSession`
Connect to an existing cloud browser session by ID.
```typescript
const browser = await skyvern.connectToCloudBrowserSession("pbs_abc123");
const page = await browser.getWorkingPage();
```
#### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `browserSessionId` | `string` | Yes | The ID of the cloud browser session. |
#### Returns `SkyvernBrowser`
---
### `connectToBrowserOverCdp`
Connect to any browser running with Chrome DevTools Protocol (CDP) enabled, whether local or remote.
```typescript
const browser = await skyvern.connectToBrowserOverCdp("http://localhost:9222");
const page = await browser.getWorkingPage();
```
#### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cdpUrl` | `string` | Yes | The CDP WebSocket URL (e.g., `"http://localhost:9222"`). |
#### Returns `SkyvernBrowser`
---
## SkyvernBrowser
A browser context wrapper that provides Skyvern-enabled pages.
### `getWorkingPage()`
Get the most recent page or create a new one if none exists.
```typescript
const page = await browser.getWorkingPage();
```
### `newPage()`
Create a new page (tab) in the browser context.
```typescript
const page = await browser.newPage();
```
### `close()`
Close the browser and release resources. If connected to a cloud session, also closes the session.
```typescript
await browser.close();
```
---
## SkyvernBrowserPage
A `SkyvernBrowserPage` extends Playwright's `Page` with AI capabilities. Every standard Playwright method (`goto`, `click`, `fill`, `waitForSelector`, etc.) works as-is. Additionally, it provides:
- **`page.agent`** — AI-powered task execution (full automations)
- **AI-enhanced `click`, `fill`, `selectOption`** — try selectors first, fall back to AI
- **`page.act`, `page.extract`, `page.validate`, `page.prompt`** — single AI actions
---
### AI-enhanced Playwright methods
These methods extend the standard Playwright API with AI fallback. Pass a CSS selector and it works like normal Playwright. Add a `prompt` option and if the selector fails, AI takes over.
#### `click`
```typescript
// Standard Playwright click
await page.click("#submit-button");
// AI-powered click (no selector needed)
await page.click({ prompt: "Click the 'Submit' button" });
// Selector with AI fallback
await page.click("#submit-button", { prompt: "Click the 'Submit' button" });
```
#### `fill`
```typescript
// Standard Playwright fill
await page.fill("#email", "user@example.com");
// AI-powered fill
await page.fill({ prompt: "Fill 'user@example.com' in the email field" });
// Selector with AI fallback
await page.fill("#email", "user@example.com", {
prompt: "Fill the email address field",
});
```
#### `selectOption`
```typescript
// Standard Playwright select
await page.selectOption("#country", "us");
// AI-powered select
await page.selectOption({ prompt: "Select 'United States' from the country dropdown" });
// Selector with AI fallback
await page.selectOption("#country", "us", {
prompt: "Select United States from country",
});
```
---
### `page.agent` — Full task execution
The `agent` property provides methods for running complete AI-powered automations within the browser page context. These always wait for completion.
#### `agent.runTask`
Run a complete AI task in the context of the current page.
```typescript
const result = await page.agent.runTask("Fill out the contact form and submit it", {
dataExtractionSchema: {
type: "object",
properties: {
confirmation_number: { type: "string" },
},
},
});
console.log(result.output);
```
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `prompt` | `string` | Yes | Natural language task description. |
| `options.engine` | `RunEngine` | No | AI engine to use. |
| `options.url` | `string` | No | URL to navigate to. Defaults to current page URL. |
| `options.dataExtractionSchema` | `Record<string, unknown> \| string` | No | JSON schema for output. |
| `options.maxSteps` | `number` | No | Maximum AI steps. |
| `options.timeout` | `number` | No | Max wait time in seconds. Default: `1800`. |
| `options.webhookUrl` | `string` | No | Webhook URL for notifications. |
| `options.totpIdentifier` | `string` | No | TOTP identifier. |
| `options.totpUrl` | `string` | No | TOTP URL. |
| `options.title` | `string` | No | Run display name. |
| `options.errorCodeMapping` | `Record<string, string>` | No | Custom error code mapping. |
| `options.model` | `Record<string, unknown>` | No | LLM model configuration. |
Returns `TaskRunResponse`.
#### `agent.login`
Run a login workflow in the context of the current page. Supports multiple credential providers via overloaded signatures.
```typescript
// Skyvern credentials
await page.agent.login("skyvern", {
credentialId: "cred_123",
});
// Bitwarden
await page.agent.login("bitwarden", {
bitwardenItemId: "item_id",
bitwardenCollectionId: "collection_id",
});
// 1Password
await page.agent.login("1password", {
onepasswordVaultId: "vault_id",
onepasswordItemId: "item_id",
});
// Azure Vault
await page.agent.login("azure_vault", {
azureVaultName: "vault_name",
azureVaultUsernameKey: "username_key",
azureVaultPasswordKey: "password_key",
});
```
Returns `WorkflowRunResponse`.
#### `agent.downloadFiles`
Download files in the context of the current page.
```typescript
const result = await page.agent.downloadFiles("Download the latest invoice PDF", {
downloadSuffix: ".pdf",
downloadTimeout: 30,
});
```
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `prompt` | `string` | Yes | What to download. |
| `options.url` | `string` | No | URL to navigate to. Defaults to current page URL. |
| `options.downloadSuffix` | `string` | No | Expected file extension. |
| `options.downloadTimeout` | `number` | No | Download timeout in seconds. |
| `options.maxStepsPerRun` | `number` | No | Max AI steps. |
| `options.timeout` | `number` | No | Max wait time in seconds. Default: `1800`. |
Returns `WorkflowRunResponse`.
#### `agent.runWorkflow`
Run a pre-defined workflow in the context of the current page.
```typescript
const result = await page.agent.runWorkflow("wpid_abc123", {
parameters: { company_name: "Acme Corp" },
});
console.log(result.output);
```
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `workflowId` | `string` | Yes | The workflow permanent ID. |
| `options.parameters` | `Record<string, unknown>` | No | Workflow input parameters. |
| `options.template` | `boolean` | No | Whether it's a template. |
| `options.title` | `string` | No | Run display name. |
| `options.timeout` | `number` | No | Max wait time in seconds. Default: `1800`. |
Returns `WorkflowRunResponse`.
---
### Single AI actions
#### `act`
Perform a single AI action on the page.
```typescript
await page.act("Scroll down and click the 'Load More' button");
```
#### `extract`
Extract structured data from the current page.
```typescript
const data = await page.extract({
prompt: "Extract all product names and prices",
schema: {
type: "array",
items: {
type: "object",
properties: {
name: { type: "string" },
price: { type: "string" },
},
},
},
});
console.log(data);
```
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `prompt` | `string` | Yes | What to extract. |
| `schema` | `Record<string, unknown> \| unknown[] \| string` | No | JSON schema for output. |
| `errorCodeMapping` | `Record<string, string>` | No | Custom error codes. |
Returns `Record<string, unknown> | unknown[] | string | null`.
#### `validate`
Validate the current page state with AI.
```typescript
const isLoggedIn = await page.validate("Check if the user is logged in");
console.log(isLoggedIn); // true or false
```
Returns `boolean`.
#### `prompt`
Send a prompt to the LLM and get a structured response.
```typescript
const result = await page.prompt(
"What is the main heading on this page?",
{ heading: { type: "string" } },
);
console.log(result);
```
Returns `Record<string, unknown> | unknown[] | string | null`.
---
## Complete example
```typescript
import { Skyvern } from "@skyvern/client";
const skyvern = new Skyvern({ apiKey: "YOUR_API_KEY" });
const browser = await skyvern.launchCloudBrowser();
const page = await browser.getWorkingPage();
// Navigate with Playwright
await page.goto("https://app.example.com");
// Login with AI
await page.agent.login("skyvern", { credentialId: "cred_abc123" });
// Extract data with AI
const data = await page.extract({
prompt: "Extract all invoice numbers and amounts from the billing page",
schema: {
type: "array",
items: {
type: "object",
properties: {
invoice_number: { type: "string" },
amount: { type: "string" },
},
},
},
});
console.log(data);
// Clean up
await browser.close();
await skyvern.close();
```

133
docs/ts-sdk-reference/browser-profiles.mdx Normal file
View File

@@ -0,0 +1,133 @@
---
title: Browser Profiles
subtitle: Save and reuse browser state across runs
slug: ts-sdk-reference/browser-profiles
---
A browser profile is a snapshot of browser state — cookies, local storage, session data. Create a profile from a completed run, then load it into future workflow runs to skip login and setup steps.
For conceptual background, see [Browser Profiles](/optimization/browser-profiles).
---
## `createBrowserProfile`
Create a profile from a completed workflow run.
```typescript
const profile = await skyvern.createBrowserProfile({
name: "production-login",
workflow_run_id: "wr_abc123",
});
console.log(profile.browser_profile_id); // bpf_abc123
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | `string` | Yes | Display name for the profile. |
| `description` | `string` | No | Optional description. |
| `workflow_run_id` | `string` | No | The workflow run ID to snapshot. The run must have used `persist_browser_session: true`. |
| `browser_session_id` | `string` | No | The browser session ID to snapshot. |
### Returns `BrowserProfile`
| Field | Type | Description |
|-------|------|-------------|
| `browser_profile_id` | `string` | Unique ID. Starts with `bpf_`. |
| `name` | `string` | Profile name. |
| `description` | `string \| undefined` | Profile description. |
| `created_at` | `string` | When the profile was created. |
### Example: Create a profile from a login workflow
```typescript
// Step 1: Run a workflow with persist_browser_session
const run = await skyvern.runWorkflow({
body: {
workflow_id: "wpid_login_flow",
parameters: { username: "demo@example.com" },
},
waitForCompletion: true,
});
// Step 2: Create a profile from the run
const profile = await skyvern.createBrowserProfile({
name: "demo-account-login",
workflow_run_id: run.run_id,
});
// Step 3: Use the profile in future runs (skip login)
const result = await skyvern.runWorkflow({
body: {
workflow_id: "wpid_extract_invoices",
browser_profile_id: profile.browser_profile_id,
},
waitForCompletion: true,
});
```
<Info>
Session archiving is asynchronous. If `createBrowserProfile` fails immediately after a workflow completes, wait a few seconds and retry.
</Info>
---
## `listBrowserProfiles`
List all browser profiles.
```typescript
const profiles = await skyvern.listBrowserProfiles({});
for (const p of profiles) {
console.log(`${p.name} (${p.browser_profile_id})`);
}
```
### Parameters
| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `include_deleted` | `boolean` | No | `undefined` | Include soft-deleted profiles in the results. |
### Returns `BrowserProfile[]`
---
## `getBrowserProfile`
Get a single profile by ID.
```typescript
const profile = await skyvern.getBrowserProfile("bpf_abc123");
console.log(profile.name);
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `profileId` | `string` | Yes | The browser profile ID. |
### Returns `BrowserProfile`
---
## `deleteBrowserProfile`
Delete a browser profile.
```typescript
await skyvern.deleteBrowserProfile("bpf_abc123");
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `profileId` | `string` | Yes | The browser profile ID to delete. |
<Warning>
`browser_profile_id` only works with `runWorkflow`, not `runTask`. If you pass it to `runTask`, it will be silently ignored.
</Warning>

124
docs/ts-sdk-reference/browser-sessions.mdx Normal file
View File

@@ -0,0 +1,124 @@
---
title: Browser Sessions
subtitle: Maintain live browser state between API calls
slug: ts-sdk-reference/browser-sessions
---
A browser session is a persistent browser instance that stays alive between API calls. Use sessions to chain multiple tasks in the same browser without losing cookies, local storage, or login state.
For conceptual background, see [Browser Sessions](/optimization/browser-sessions).
---
## `createBrowserSession`
Spin up a new cloud browser session.
```typescript
const session = await skyvern.createBrowserSession({ timeout: 60 });
console.log(session.browser_session_id); // pbs_abc123
```
### Parameters
| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `timeout` | `number` | No | `60` | Session timeout in minutes (5–1440). Timer starts after the session is ready. |
| `proxy_location` | `ProxyLocation` | No | `undefined` | Route browser traffic through a geographic proxy. |
| `extensions` | `Extensions[]` | No | `undefined` | Browser extensions to install. Options: `"ad-blocker"`, `"captcha-solver"`. |
| `browser_type` | `PersistentBrowserType` | No | `undefined` | Browser type. Options: `"chrome"`, `"msedge"`. |
### Returns `BrowserSessionResponse`
| Field | Type | Description |
|-------|------|-------------|
| `browser_session_id` | `string` | Unique ID. Starts with `pbs_`. |
| `status` | `string \| undefined` | Current session status. |
| `browser_address` | `string \| undefined` | CDP address for connecting to the browser. |
| `app_url` | `string \| undefined` | Link to the live browser view in the Cloud UI. |
| `timeout` | `number \| undefined` | Configured timeout in minutes. |
| `started_at` | `string \| undefined` | When the session became ready. |
| `created_at` | `string` | When the session was requested. |
### Example: Chain multiple tasks in one session
```typescript
const session = await skyvern.createBrowserSession({});
// Step 1: Log in
await skyvern.runTask({
body: {
prompt: "Log in with username demo@example.com",
url: "https://app.example.com/login",
browser_session_id: session.browser_session_id,
},
waitForCompletion: true,
});
// Step 2: Extract data (same browser, already logged in)
const result = await skyvern.runTask({
body: {
prompt: "Go to the invoices page and extract all invoice numbers",
browser_session_id: session.browser_session_id,
},
waitForCompletion: true,
});
console.log(result.output);
// Clean up
await skyvern.closeBrowserSession(session.browser_session_id);
```
---
## `getBrowserSession`
Get the status and details of a session.
```typescript
const session = await skyvern.getBrowserSession("pbs_abc123");
console.log(session.status, session.browser_address);
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `browserSessionId` | `string` | Yes | The session ID. |
### Returns `BrowserSessionResponse`
---
## `getBrowserSessions`
List all active browser sessions.
```typescript
const sessions = await skyvern.getBrowserSessions();
for (const s of sessions) {
console.log(`${s.browser_session_id} — ${s.status}`);
}
```
### Returns `BrowserSessionResponse[]`
---
## `closeBrowserSession`
Close a browser session and release its resources.
```typescript
await skyvern.closeBrowserSession("pbs_abc123");
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `browserSessionId` | `string` | Yes | The session ID to close. |
<Warning>
Closing a session is irreversible. Any unsaved state (cookies, local storage) is lost unless you created a [browser profile](/ts-sdk-reference/browser-profiles) from it.
</Warning>

618
docs/ts-sdk-reference/complete-reference.mdx Normal file
View File

@@ -0,0 +1,618 @@
---
title: Complete Reference (For LLMs)
subtitle: Every method, parameter, and type in one page
slug: ts-sdk-reference/complete-reference
---
## Install and initialize
```bash
npm install @skyvern/client
```
```typescript
import { Skyvern } from "@skyvern/client";
const skyvern = new Skyvern({ apiKey: "YOUR_API_KEY" });
const result = await skyvern.runTask({
body: {
prompt: "Get the title of the top post on Hacker News",
url: "https://news.ycombinator.com",
},
waitForCompletion: true,
});
console.log(result.output);
```
**Constructor:**
```typescript
new Skyvern({
apiKey: string, // Required
baseUrl?: string, // Override for self-hosted deployments
environment?: SkyvernEnvironment | string, // Cloud (default), Staging, or Local
timeoutInSeconds?: number, // HTTP request timeout (default: 60)
maxRetries?: number, // Retry count (default: 2)
headers?: Record<string, string>, // Additional headers
})
```
**Environments:**
```typescript
import { SkyvernEnvironment } from "@skyvern/client";
// SkyvernEnvironment.Cloud → "https://api.skyvern.com"
// SkyvernEnvironment.Staging → "https://api-staging.skyvern.com"
// SkyvernEnvironment.Local → "http://localhost:8000"
```
All methods return promises. Requires Node.js 18+.
---
## Imports
```typescript
import {
Skyvern, // Main client class
SkyvernEnvironment, // Cloud, Staging, Local
SkyvernError, // Base error class
SkyvernTimeoutError, // HTTP timeout error
SkyvernApi, // Namespace for API types and error subclasses
} from "@skyvern/client";
// HTTP error subclasses via SkyvernApi namespace:
// SkyvernApi.BadRequestError — 400
// SkyvernApi.ForbiddenError — 403
// SkyvernApi.NotFoundError — 404
// SkyvernApi.ConflictError — 409
// SkyvernApi.UnprocessableEntityError — 422
```
**Important:** `SkyvernError` and `SkyvernTimeoutError` are top-level exports. The HTTP-specific errors (`BadRequestError`, etc.) extend `SkyvernError` and are accessed via the `SkyvernApi` namespace.
---
## Tasks
### `runTask`
```typescript
const result = await skyvern.runTask({
body: {
prompt: string, // Required. Natural language instructions.
url?: string, // Starting page URL.
engine?: RunEngine, // "skyvern_v2" (default), "skyvern_v1", "openai_cua", "anthropic_cua", "ui_tars"
max_steps?: number, // Cap AI steps to limit cost.
data_extraction_schema?: Record<string, unknown> | string, // JSON Schema for output.
browser_session_id?: string, // Run in existing session.
publish_workflow?: boolean, // Save generated code as reusable workflow.
proxy_location?: ProxyLocation,
webhook_url?: string,
error_code_mapping?: Record<string, string>,
totp_identifier?: string,
totp_url?: string,
title?: string,
model?: Record<string, unknown>,
user_agent?: string,
extra_http_headers?: Record<string, string>,
browser_address?: string,
},
waitForCompletion?: boolean, // Poll until finished. Default: false.
timeout?: number, // Max wait (seconds). Default: 1800.
}): Promise<TaskRunResponse>
```
**`TaskRunResponse` fields:**
| Field | Type | Description |
|-------|------|-------------|
| `run_id` | `string` | Unique ID (`tsk_...`). |
| `status` | `string` | `created` \| `queued` \| `running` \| `completed` \| `failed` \| `terminated` \| `timed_out` \| `canceled` |
| `output` | `Record<string, unknown> \| null` | Extracted data. `null` until completed. |
| `failure_reason` | `string \| undefined` | Error description if failed. |
| `downloaded_files` | `FileInfo[] \| undefined` | Files downloaded during the run. |
| `recording_url` | `string \| undefined` | Session recording video URL. |
| `screenshot_urls` | `string[] \| undefined` | Final screenshots. |
| `app_url` | `string \| undefined` | Link to run in Skyvern UI. |
| `step_count` | `number \| undefined` | Number of AI steps taken. |
| `created_at` | `string` | When the run was created. |
| `finished_at` | `string \| undefined` | When the run finished. |
### `getRun`
```typescript
const run = await skyvern.getRun(runId: string): Promise<GetRunResponse>
```
Returns status and results for any run (task or workflow).
### `cancelRun`
```typescript
await skyvern.cancelRun(runId: string): Promise<void>
```
### `getRunTimeline`
```typescript
const timeline = await skyvern.getRunTimeline(runId: string): Promise<WorkflowRunTimeline[]>
```
### `getRunArtifacts`
```typescript
const artifacts = await skyvern.getRunArtifacts(
runId: string,
request?: { artifact_type?: ArtifactType | ArtifactType[] },
): Promise<Artifact[]>
```
### `getArtifact`
```typescript
const artifact = await skyvern.getArtifact(artifactId: string): Promise<Artifact>
```
### `retryRunWebhook`
```typescript
await skyvern.retryRunWebhook(runId: string): Promise<void>
```
---
## Workflows
### `runWorkflow`
```typescript
const result = await skyvern.runWorkflow({
body: {
workflow_id: string, // Required. Permanent ID (wpid_...).
parameters?: Record<string, unknown>, // Input params matching workflow definition.
browser_session_id?: string,
browser_profile_id?: string, // Load saved browser state.
proxy_location?: ProxyLocation,
webhook_url?: string,
title?: string,
totp_identifier?: string,
totp_url?: string,
user_agent?: string,
extra_http_headers?: Record<string, string>,
browser_address?: string,
},
template?: boolean,
waitForCompletion?: boolean, // Default: false.
timeout?: number, // Default: 1800.
}): Promise<WorkflowRunResponse>
```
**`WorkflowRunResponse` fields:** Same as `TaskRunResponse` plus `run_with`, `ai_fallback`, `script_run`.
### `createWorkflow`
```typescript
const workflow = await skyvern.createWorkflow({
body: { json_definition?: object, yaml_definition?: string },
folder_id?: string,
}): Promise<Workflow>
```
**`Workflow` fields:** `workflow_id`, `workflow_permanent_id`, `version`, `title`, `workflow_definition`, `status`, `created_at`
### `getWorkflows`
```typescript
const workflows = await skyvern.getWorkflows({
page?: number,
page_size?: number,
only_saved_tasks?: boolean,
only_workflows?: boolean,
title?: string,
search_key?: string,
folder_id?: string,
status?: WorkflowStatus | WorkflowStatus[],
}): Promise<Workflow[]>
```
### `getWorkflow`
```typescript
const workflow = await skyvern.getWorkflow(
workflowPermanentId: string,
request?: { version?: number; template?: boolean },
): Promise<Workflow>
```
### `getWorkflowVersions`
```typescript
const versions = await skyvern.getWorkflowVersions(
workflowPermanentId: string,
request?: { template?: boolean },
): Promise<Workflow[]>
```
### `updateWorkflow`
```typescript
const updated = await skyvern.updateWorkflow(
workflowId: string, // The version ID (not permanent ID).
request?: { json_definition?: object; yaml_definition?: string },
): Promise<Workflow>
```
### `deleteWorkflow`
```typescript
await skyvern.deleteWorkflow(workflowId: string): Promise<void>
```
---
## Browser sessions
A persistent browser instance that stays alive between API calls. Use to chain tasks without losing cookies or login state.
### `createBrowserSession`
```typescript
const session = await skyvern.createBrowserSession({
timeout?: number, // Minutes (5-1440). Default: 60.
proxy_location?: ProxyLocation,
extensions?: Extensions[], // "ad-blocker", "captcha-solver"
browser_type?: PersistentBrowserType, // "chrome", "msedge"
}): Promise<BrowserSessionResponse>
```
**`BrowserSessionResponse` fields:** `browser_session_id`, `status`, `browser_address`, `app_url`, `timeout`, `started_at`, `created_at`
### `getBrowserSession`
```typescript
const session = await skyvern.getBrowserSession(browserSessionId: string): Promise<BrowserSessionResponse>
```
### `getBrowserSessions`
```typescript
const sessions = await skyvern.getBrowserSessions(): Promise<BrowserSessionResponse[]>
```
### `closeBrowserSession`
```typescript
await skyvern.closeBrowserSession(browserSessionId: string): Promise<void>
```
### Session chaining example
```typescript
const session = await skyvern.createBrowserSession({});
// Step 1: Log in
await skyvern.runTask({
body: {
prompt: "Log in with username demo@example.com",
url: "https://app.example.com/login",
browser_session_id: session.browser_session_id,
},
waitForCompletion: true,
});
// Step 2: Extract data (same browser, already logged in)
const result = await skyvern.runTask({
body: {
prompt: "Go to the invoices page and extract all invoice numbers",
browser_session_id: session.browser_session_id,
},
waitForCompletion: true,
});
console.log(result.output);
// Clean up
await skyvern.closeBrowserSession(session.browser_session_id);
```
---
## Browser profiles
A saved snapshot of browser state (cookies, local storage). Create from a completed workflow run, then reuse to skip login.
### `createBrowserProfile`
```typescript
const profile = await skyvern.createBrowserProfile({
name: string,
description?: string,
workflow_run_id?: string, // Run must have used persist_browser_session: true.
browser_session_id?: string,
}): Promise<BrowserProfile>
```
**`BrowserProfile` fields:** `browser_profile_id`, `name`, `description`, `created_at`
### `listBrowserProfiles`
```typescript
const profiles = await skyvern.listBrowserProfiles({
include_deleted?: boolean,
}): Promise<BrowserProfile[]>
```
### `getBrowserProfile`
```typescript
const profile = await skyvern.getBrowserProfile(profileId: string): Promise<BrowserProfile>
```
### `deleteBrowserProfile`
```typescript
await skyvern.deleteBrowserProfile(profileId: string): Promise<void>
```
---
## Credentials
Store login information securely. Reference by ID instead of passing secrets in code.
### `createCredential`
```typescript
const credential = await skyvern.createCredential({
name: string,
credential_type: CredentialType, // e.g. "password"
credential: object, // Password: { username: "...", password: "..." }
}): Promise<CredentialResponse>
```
### `getCredentials`
```typescript
const creds = await skyvern.getCredentials({
page?: number,
page_size?: number,
}): Promise<CredentialResponse[]>
```
### `getCredential`
```typescript
const cred = await skyvern.getCredential(credentialId: string): Promise<CredentialResponse>
```
### `deleteCredential`
```typescript
await skyvern.deleteCredential(credentialId: string): Promise<void>
```
### `sendTotpCode`
Send a TOTP code to Skyvern during a run that requires 2FA.
```typescript
await skyvern.sendTotpCode({
totp_identifier: string,
content: string, // The TOTP code value.
task_id?: string,
workflow_id?: string,
workflow_run_id?: string,
source?: string,
expired_at?: string,
}): Promise<TotpCode>
```
---
## Helper methods
### `login`
Automate logging into a website using stored credentials.
```typescript
const result = await skyvern.login({
credential_type: CredentialType, // Required. "skyvern", "bitwarden", "1password", "azure_vault".
url?: string,
credential_id?: string, // When using "skyvern" type.
prompt?: string,
browser_session_id?: string,
browser_address?: string,
proxy_location?: ProxyLocation,
webhook_url?: string,
totp_identifier?: string,
totp_url?: string,
extra_http_headers?: Record<string, string>,
waitForCompletion?: boolean, // Default: false.
timeout?: number, // Default: 1800.
// Bitwarden: bitwarden_collection_id, bitwarden_item_id
// 1Password: onepassword_vault_id, onepassword_item_id
// Azure: azure_vault_name, azure_vault_username_key, azure_vault_password_key, azure_vault_totp_secret_key
}): Promise<WorkflowRunResponse>
```
### `downloadFiles`
```typescript
const result = await skyvern.downloadFiles({
navigation_goal: string, // Required. What to download.
url?: string,
browser_session_id?: string,
browser_profile_id?: string,
download_suffix?: string, // Expected extension, e.g. ".pdf"
download_timeout?: number,
max_steps_per_run?: number,
extra_http_headers?: Record<string, string>,
waitForCompletion?: boolean, // Default: false.
timeout?: number, // Default: 1800.
}): Promise<WorkflowRunResponse>
```
### `uploadFile`
```typescript
const upload = await skyvern.uploadFile({ file }): Promise<UploadFileResponse>
// Returns: { s3_uri: string, presigned_url: string }
```
---
## Browser automation (Playwright + AI)
The TypeScript SDK extends Playwright with AI capabilities via cloud browsers.
### Launch browsers
```typescript
// Launch new cloud browser
const browser = await skyvern.launchCloudBrowser({ timeout?: number, proxyLocation?: ProxyLocation });
// Reuse existing or create new
const browser = await skyvern.useCloudBrowser({ timeout?: number, proxyLocation?: ProxyLocation });
// Connect to existing cloud session
const browser = await skyvern.connectToCloudBrowserSession(browserSessionId: string);
// Connect via CDP
const browser = await skyvern.connectToBrowserOverCdp(cdpUrl: string);
```
### Get pages
```typescript
const page = await browser.getWorkingPage(); // Get or create page
const page = await browser.newPage(); // Always create new page
await browser.close(); // Close browser and session
```
### AI-enhanced page methods
```typescript
// Click with AI fallback
await page.click("#selector"); // Standard Playwright
await page.click({ prompt: "Click the submit button" }); // AI-powered
await page.click("#selector", { prompt: "Click submit" }); // Selector + AI fallback
// Fill with AI fallback
await page.fill("#email", "user@example.com"); // Standard Playwright
await page.fill({ prompt: "Fill email with user@example.com" }); // AI-powered
await page.fill("#email", "user@example.com", { prompt: "..." }); // Selector + AI fallback
// Select with AI fallback
await page.selectOption("#country", "us"); // Standard Playwright
await page.selectOption({ prompt: "Select United States from country" }); // AI-powered
// Single AI actions
await page.act("Click the login button"); // Perform an action
const data = await page.extract({ prompt: "Extract products" }); // Extract data
const ok = await page.validate("User is logged in"); // Validate state (boolean)
const resp = await page.prompt("What is the heading?", schema); // LLM prompt
```
### Full task execution via `page.agent`
```typescript
await page.agent.runTask("Fill out the form", { timeout: 300 });
await page.agent.login("skyvern", { credentialId: "cred_123" });
await page.agent.downloadFiles("Download the PDF", { downloadSuffix: ".pdf" });
await page.agent.runWorkflow("wpid_abc", { parameters: { key: "value" } });
```
---
## Error handling
```typescript
import { SkyvernError, SkyvernTimeoutError, SkyvernApi } from "@skyvern/client";
try {
const run = await skyvern.getRun("tsk_nonexistent");
} catch (e) {
if (e instanceof SkyvernApi.NotFoundError) {
console.log(e.statusCode, e.body); // 404
} else if (e instanceof SkyvernTimeoutError) {
console.log("Request timed out");
} else if (e instanceof SkyvernError) {
console.log(e.statusCode, e.body); // Any other HTTP error
}
}
```
**Error types:** `SkyvernApi.BadRequestError` (400), `SkyvernApi.ForbiddenError` (403), `SkyvernApi.NotFoundError` (404), `SkyvernApi.ConflictError` (409), `SkyvernApi.UnprocessableEntityError` (422). All inherit from `SkyvernError`.
**Completion timeout** throws a standard `Error`:
```typescript
try {
const result = await skyvern.runTask({
body: { prompt: "...", url: "..." },
waitForCompletion: true,
timeout: 300,
});
} catch (e) {
if (e instanceof Error && e.message.includes("Timeout")) {
console.log("Task didn't complete in time");
}
}
```
**Run failure** is not an exception — check `result.status`:
```typescript
if (result.status === "failed") console.log(result.failure_reason);
if (result.status === "completed") console.log(result.output);
```
---
## Request options
Override timeout, retries, or headers per-request (second parameter on all methods):
```typescript
const result = await skyvern.runTask(
{ body: { prompt: "...", url: "..." } },
{
timeoutInSeconds: 120,
maxRetries: 3,
headers: { "x-custom-header": "value" },
abortSignal: controller.signal,
},
);
```
---
## Polling pattern
When not using `waitForCompletion`:
```typescript
const task = await skyvern.runTask({ body: { prompt: "...", url: "..." } });
const terminal = ["completed", "failed", "terminated", "timed_out", "canceled"];
let run;
while (true) {
run = await skyvern.getRun(task.run_id);
if (terminal.includes(run.status)) break;
await new Promise((resolve) => setTimeout(resolve, 5000));
}
console.log(run.output);
```
---
## Key constraints
- `browser_profile_id` works with `runWorkflow` only — silently ignored by `runTask`.
- Only workflow runs with `persist_browser_session: true` produce archives for profile creation.
- Session archiving is async — profile creation may need a short retry delay after a run completes.
- `engine` accepts string values: `"skyvern_v1"`, `"skyvern_v2"`, `"openai_cua"`, `"anthropic_cua"`, `"ui_tars"`.
- Cloud browser methods (`launchCloudBrowser`, `useCloudBrowser`, `connectToCloudBrowserSession`) only work with `Cloud` or `Staging` environments.
- The SDK depends on `playwright` for browser automation features.

120
docs/ts-sdk-reference/credentials.mdx Normal file
View File

@@ -0,0 +1,120 @@
---
title: Credentials
subtitle: Store and manage authentication credentials securely
slug: ts-sdk-reference/credentials
---
Credentials let you store login information (username/password, TOTP secrets) securely in Skyvern's vault. Reference them by ID in tasks and workflows instead of passing secrets in your code.
---
## `createCredential`
Store a new credential.
```typescript
const credential = await skyvern.createCredential({
name: "my-app-login",
credential_type: "password",
credential: {
username: "demo@example.com",
password: "s3cur3-p4ss",
},
});
console.log(credential.credential_id);
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | `string` | Yes | Display name for the credential. |
| `credential_type` | `CredentialType` | Yes | Type of credential. |
| `credential` | `object` | Yes | The credential data. Shape depends on `credential_type`. |
### Returns `CredentialResponse`
---
## `getCredentials`
List all credentials. Credential values are never returned — only metadata.
```typescript
const creds = await skyvern.getCredentials({});
for (const c of creds) {
console.log(`${c.name} (${c.credential_id})`);
}
```
### Parameters
| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `page` | `number` | No | `undefined` | Page number. |
| `page_size` | `number` | No | `undefined` | Results per page. |
### Returns `CredentialResponse[]`
---
## `getCredential`
Get a single credential's metadata by ID.
```typescript
const cred = await skyvern.getCredential("cred_abc123");
console.log(cred.name, cred.credential_type);
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `credentialId` | `string` | Yes | The credential ID. |
### Returns `CredentialResponse`
---
## `deleteCredential`
Delete a credential.
```typescript
await skyvern.deleteCredential("cred_abc123");
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `credentialId` | `string` | Yes | The credential ID to delete. |
---
## `sendTotpCode`
Send a TOTP (time-based one-time password) code to Skyvern during a run that requires 2FA. Call this when your webhook or polling detects that Skyvern is waiting for a TOTP code.
```typescript
await skyvern.sendTotpCode({
totp_identifier: "demo@example.com",
content: "123456",
});
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `totp_identifier` | `string` | Yes | The identifier matching the `totp_identifier` used in the task/workflow. |
| `content` | `string` | Yes | The TOTP code value. |
| `task_id` | `string` | No | Associate with a specific task run. |
| `workflow_id` | `string` | No | Associate with a specific workflow. |
| `workflow_run_id` | `string` | No | Associate with a specific workflow run. |
| `source` | `string` | No | Source of the TOTP code. |
| `expired_at` | `string` | No | When this code expires (ISO 8601 format). |
| `type` | `OtpType` | No | OTP type. |
### Returns `TotpCode`

228
docs/ts-sdk-reference/error-handling.mdx Normal file
View File

@@ -0,0 +1,228 @@
---
title: Error Handling
subtitle: Handle API errors, timeouts, and configure retries
slug: ts-sdk-reference/error-handling
---
The SDK raises typed exceptions for API errors. All errors extend `SkyvernError` and include the HTTP status code, response body, and raw response.
---
## Error types
| Exception | Status Code | When it's raised |
|-----------|-------------|------------------|
| `BadRequestError` | 400 | Invalid request parameters. |
| `ForbiddenError` | 403 | Invalid or missing API key. |
| `NotFoundError` | 404 | Resource (run, workflow, session) not found. |
| `ConflictError` | 409 | Resource conflict (e.g., duplicate creation). |
| `UnprocessableEntityError` | 422 | Request validation failed. |
| `SkyvernError` | Any | Base class for all API errors. Catch this as a fallback. |
| `SkyvernTimeoutError` | — | HTTP request timed out. |
Import errors from the package:
```typescript
import { SkyvernError, SkyvernTimeoutError, SkyvernApi } from "@skyvern/client";
// Base errors are top-level exports:
// SkyvernError — base class for all API errors
// SkyvernTimeoutError — HTTP request timed out
// HTTP status error subclasses are accessed via the SkyvernApi namespace:
// SkyvernApi.BadRequestError — 400
// SkyvernApi.ForbiddenError — 403
// SkyvernApi.NotFoundError — 404
// SkyvernApi.ConflictError — 409
// SkyvernApi.UnprocessableEntityError — 422
```
---
## Catching errors
```typescript
import { Skyvern, SkyvernError, SkyvernApi } from "@skyvern/client";
const skyvern = new Skyvern({ apiKey: "YOUR_API_KEY" });
try {
const run = await skyvern.getRun("tsk_nonexistent");
} catch (e) {
if (e instanceof SkyvernApi.NotFoundError) {
console.log(`Run not found: ${e.body}`);
} else if (e instanceof SkyvernError) {
console.log(`API error ${e.statusCode}: ${e.body}`);
}
}
```
### Error properties
Every error has these attributes:
| Property | Type | Description |
|----------|------|-------------|
| `statusCode` | `number \| undefined` | HTTP status code. |
| `body` | `unknown` | Response body (usually an object with error details). |
| `rawResponse` | `RawResponse \| undefined` | The raw HTTP response. |
| `message` | `string` | Human-readable error message. |
---
## Timeouts
Two different timeouts apply:
### HTTP request timeout
Controls how long the SDK waits for the HTTP response from the Skyvern API. Set it in the constructor or per-request:
```typescript
// Global timeout (applies to all requests)
const skyvern = new Skyvern({
apiKey: "YOUR_API_KEY",
timeoutInSeconds: 30,
});
// Per-request timeout
const result = await skyvern.getRun("tsk_abc123", {
timeoutInSeconds: 10,
});
```
When an HTTP request times out, a `SkyvernTimeoutError` is thrown.
### Completion timeout
Controls how long `waitForCompletion` polls before giving up. This is separate from the HTTP timeout:
```typescript
try {
const result = await skyvern.runTask({
body: {
prompt: "Extract data",
url: "https://example.com",
},
waitForCompletion: true,
timeout: 300, // Give up after 5 minutes
});
} catch (e) {
if (e instanceof Error && e.message.includes("Timeout")) {
console.log("Task didn't complete in time");
}
}
```
The completion timeout throws a standard JavaScript `Error` with a timeout message.
---
## Retries
Configure automatic retries for transient failures. Set it in the constructor or per-request:
```typescript
// Global retries (default: 2)
const skyvern = new Skyvern({
apiKey: "YOUR_API_KEY",
maxRetries: 3,
});
// Per-request retries
const result = await skyvern.runTask(
{
body: {
prompt: "Extract product data",
url: "https://example.com/products",
},
},
{ maxRetries: 5 },
);
```
Retries apply to the HTTP request level (network errors, 5xx responses). They do not retry the entire task if it fails at the AI level — use `getRun` to check the status and re-run if needed.
---
## Abort requests
Cancel in-flight requests using `AbortSignal`:
```typescript
const controller = new AbortController();
// Cancel after 10 seconds
setTimeout(() => controller.abort(), 10000);
try {
const result = await skyvern.runTask(
{
body: {
prompt: "Extract data",
url: "https://example.com",
},
},
{ abortSignal: controller.signal },
);
} catch (e) {
if (e instanceof Error && e.name === "AbortError") {
console.log("Request was aborted");
}
}
```
---
## Run failure vs API errors
There are two distinct failure modes:
**API error** — The HTTP request itself failed. The SDK throws an exception.
```typescript
import { SkyvernError } from "@skyvern/client";
try {
const result = await skyvern.runTask({
body: { prompt: "..." },
});
} catch (e) {
if (e instanceof SkyvernError) {
console.log(`API call failed: ${e.statusCode}`);
}
}
```
**Run failure** — The API call succeeded, but the task/workflow failed during execution. No exception is thrown. Check the `status` field:
```typescript
const result = await skyvern.runTask({
body: {
prompt: "Fill out the form",
url: "https://example.com",
},
waitForCompletion: true,
});
if (result.status === "failed") {
console.log(`Task failed: ${result.failure_reason}`);
} else if (result.status === "timed_out") {
console.log(`Task exceeded step limit after ${result.step_count} steps`);
} else if (result.status === "completed") {
console.log(`Success: ${JSON.stringify(result.output)}`);
}
```
### Run statuses
| Status | Description |
|--------|-------------|
| `created` | Run initialized, not yet queued. |
| `queued` | Waiting for an available browser. |
| `running` | AI is executing. |
| `completed` | Finished successfully. |
| `failed` | Encountered an error during execution. |
| `terminated` | Manually stopped. |
| `timed_out` | Exceeded step limit (`max_steps`). |
| `canceled` | Canceled before starting. |

164
docs/ts-sdk-reference/helpers.mdx Normal file
View File

@@ -0,0 +1,164 @@
---
title: Helper Methods
subtitle: High-level methods for common automation patterns
slug: ts-sdk-reference/helpers
---
These methods wrap common multi-step patterns into single API calls. Under the hood, they create and run specialized workflows.
---
## `login`
Automate logging into a website using stored credentials. This creates a login workflow, executes it, and optionally waits for completion.
```typescript
const result = await skyvern.login({
credential_type: "skyvern",
credential_id: "cred_abc123",
url: "https://app.example.com/login",
waitForCompletion: true,
});
console.log(result.status);
```
### Parameters
| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `credential_type` | `CredentialType` | Yes | — | How credentials are stored. Options: `"skyvern"`, `"bitwarden"`, `"1password"`, `"azure_vault"`. |
| `url` | `string` | No | `undefined` | The login page URL. |
| `credential_id` | `string` | No | `undefined` | The Skyvern credential ID (when using `"skyvern"` type). |
| `prompt` | `string` | No | `undefined` | Additional instructions for the AI during login. |
| `browser_session_id` | `string` | No | `undefined` | Run login inside an existing browser session. |
| `browser_address` | `string` | No | `undefined` | Connect to a browser at this CDP address. |
| `proxy_location` | `ProxyLocation` | No | `undefined` | Route browser traffic through a geographic proxy. |
| `webhook_url` | `string` | No | `undefined` | URL to receive a POST when the login finishes. |
| `totp_identifier` | `string` | No | `undefined` | Identifier for TOTP verification. |
| `totp_url` | `string` | No | `undefined` | URL to receive TOTP codes. |
| `extra_http_headers` | `Record<string, string>` | No | `undefined` | Additional HTTP headers. |
| `max_screenshot_scrolling_times` | `number` | No | `undefined` | Number of screenshot scrolls. |
| `waitForCompletion` | `boolean` | No | `false` | Block until the login finishes. |
| `timeout` | `number` | No | `1800` | Max wait time in seconds. |
**Bitwarden-specific parameters:**
| Parameter | Type | Description |
|-----------|------|-------------|
| `bitwarden_collection_id` | `string` | Bitwarden collection ID. |
| `bitwarden_item_id` | `string` | Bitwarden item ID. |
**1Password-specific parameters:**
| Parameter | Type | Description |
|-----------|------|-------------|
| `onepassword_vault_id` | `string` | 1Password vault ID. |
| `onepassword_item_id` | `string` | 1Password item ID. |
**Azure Key Vault-specific parameters:**
| Parameter | Type | Description |
|-----------|------|-------------|
| `azure_vault_name` | `string` | Azure Key Vault name. |
| `azure_vault_username_key` | `string` | Secret name for the username. |
| `azure_vault_password_key` | `string` | Secret name for the password. |
| `azure_vault_totp_secret_key` | `string` | Secret name for the TOTP secret. |
### Returns `WorkflowRunResponse`
### Example: Login then extract data
```typescript
const session = await skyvern.createBrowserSession({});
// Login
await skyvern.login({
credential_type: "skyvern",
credential_id: "cred_abc123",
url: "https://app.example.com/login",
browser_session_id: session.browser_session_id,
waitForCompletion: true,
});
// Now extract data from the authenticated session
const result = await skyvern.runTask({
body: {
prompt: "Go to the billing page and extract all invoices",
browser_session_id: session.browser_session_id,
},
waitForCompletion: true,
});
console.log(result.output);
```
---
## `downloadFiles`
Navigate to a page and download files.
```typescript
const result = await skyvern.downloadFiles({
navigation_goal: "Download the latest monthly report PDF",
url: "https://app.example.com/reports",
waitForCompletion: true,
});
for (const f of result.downloaded_files ?? []) {
console.log(f.name);
}
```
### Parameters
| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `navigation_goal` | `string` | Yes | — | Natural language description of what to download. |
| `url` | `string` | No | `undefined` | Starting page URL. |
| `browser_session_id` | `string` | No | `undefined` | Run inside an existing browser session. |
| `browser_profile_id` | `string` | No | `undefined` | Load a browser profile. |
| `proxy_location` | `ProxyLocation` | No | `undefined` | Route through a geographic proxy. |
| `webhook_url` | `string` | No | `undefined` | URL to receive a POST when the download finishes. |
| `download_suffix` | `string` | No | `undefined` | Expected file extension to wait for (e.g., `".pdf"`). |
| `download_timeout` | `number` | No | `undefined` | Max time to wait for the download in seconds. |
| `max_steps_per_run` | `number` | No | `undefined` | Cap AI steps. |
| `extra_http_headers` | `Record<string, string>` | No | `undefined` | Additional HTTP headers. |
| `waitForCompletion` | `boolean` | No | `false` | Block until the download finishes. |
| `timeout` | `number` | No | `1800` | Max wait time in seconds. |
### Returns `WorkflowRunResponse`
The `downloaded_files` field contains the list of files that were downloaded.
<Note>
Unlike the Python SDK where `download_files` does not support `wait_for_completion`, the TypeScript SDK supports `waitForCompletion` on all methods including `downloadFiles`.
</Note>
---
## `uploadFile`
Upload a file to Skyvern's storage. Returns a presigned URL and S3 URI you can reference in tasks and workflows.
```typescript
import fs from "fs";
const upload = await skyvern.uploadFile({
file: fs.createReadStream("data.csv"),
});
console.log(upload.s3_uri); // s3://skyvern-uploads/...
console.log(upload.presigned_url); // https://...signed download URL
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file` | `File \| ReadStream \| Blob` | Yes | The file to upload. |
### Returns `UploadFileResponse`
| Field | Type | Description |
|-------|------|-------------|
| `s3_uri` | `string` | S3 URI for the uploaded file. |
| `presigned_url` | `string` | Pre-signed download URL. |

173
docs/ts-sdk-reference/overview.mdx Normal file
View File

@@ -0,0 +1,173 @@
---
title: TypeScript SDK
subtitle: Install, authenticate, and configure the Skyvern TypeScript client
slug: ts-sdk-reference/overview
---
The `@skyvern/client` package wraps the Skyvern REST API in a typed TypeScript client with built-in browser automation via Playwright.
```bash
npm install @skyvern/client
```
<Note>
Requires Node.js 18+. Also compatible with Bun, Deno, and Cloudflare Workers.
</Note>
---
## Initialize the client
The `Skyvern` class provides both API methods and browser automation. All API methods return promises:
```typescript
import { Skyvern } from "@skyvern/client";
const skyvern = new Skyvern({ apiKey: "YOUR_API_KEY" });
const result = await skyvern.runTask({
body: {
prompt: "Get the title of the top post on Hacker News",
url: "https://news.ycombinator.com",
},
waitForCompletion: true,
});
console.log(result.output);
```
### Constructor parameters
| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `apiKey` | `string` | — | **Required.** Your Skyvern API key. Get one at [app.skyvern.com/settings](https://app.skyvern.com/settings/api-keys). |
| `environment` | `SkyvernEnvironment \| string` | `Cloud` | Target environment. Options: `Cloud`, `Staging`, `Local`. |
| `baseUrl` | `string` | `undefined` | Override the API base URL. Use this for self-hosted deployments. |
| `timeoutInSeconds` | `number` | `60` | HTTP request timeout in seconds. |
| `maxRetries` | `number` | `2` | Number of times to retry failed requests. |
| `headers` | `Record<string, string>` | `undefined` | Additional headers included with every request. |
---
## Environments
The SDK ships with three built-in environment URLs:
```typescript
import { SkyvernEnvironment } from "@skyvern/client";
```
| Environment | URL | When to use |
|-------------|-----|-------------|
| `SkyvernEnvironment.Cloud` | `https://api.skyvern.com` | Skyvern Cloud (default) |
| `SkyvernEnvironment.Staging` | `https://api-staging.skyvern.com` | Staging environment |
| `SkyvernEnvironment.Local` | `http://localhost:8000` | Local server started with `skyvern run server` |
For a self-hosted instance at a custom URL, pass `baseUrl` instead:
```typescript
const skyvern = new Skyvern({
apiKey: "YOUR_API_KEY",
baseUrl: "https://skyvern.your-company.com",
});
```
---
## `waitForCompletion`
By default, `runTask` and `runWorkflow` return immediately after the run is queued — you get a `run_id` and need to poll `getRun()` yourself. Pass `waitForCompletion: true` to have the SDK poll automatically until the run reaches a terminal state (`completed`, `failed`, `terminated`, `timed_out`, or `canceled`):
```typescript
// Returns only after the task finishes (up to 30 min by default)
const result = await skyvern.runTask({
body: {
prompt: "Fill out the contact form",
url: "https://example.com/contact",
},
waitForCompletion: true,
timeout: 600, // give up after 10 minutes
});
// Without waitForCompletion — returns immediately
const task = await skyvern.runTask({
body: {
prompt: "Fill out the contact form",
url: "https://example.com/contact",
},
});
console.log(task.run_id); // poll with skyvern.getRun(task.run_id)
```
| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `waitForCompletion` | `boolean` | `false` | Poll until the run finishes. |
| `timeout` | `number` | `1800` | Maximum wait time in seconds. Throws `Error` if exceeded. |
Supported on `runTask`, `runWorkflow`, `login`, and `downloadFiles`.
---
## Request options
Every method accepts an optional second parameter for per-request overrides of timeout, retries, headers, and abort signal:
```typescript
const result = await skyvern.runTask(
{
body: {
prompt: "Extract data",
url: "https://example.com",
},
},
{
timeoutInSeconds: 120,
maxRetries: 3,
headers: { "x-custom-header": "value" },
},
);
```
| Parameter | Type | Description |
|-----------|------|-------------|
| `timeoutInSeconds` | `number` | HTTP timeout for this request. |
| `maxRetries` | `number` | Retry count for this request. |
| `abortSignal` | `AbortSignal` | Signal to abort the request. |
| `apiKey` | `string` | Override the API key for this request. |
| `headers` | `Record<string, string>` | Additional headers for this request. |
These override the client-level defaults for that single call only.
---
## Next steps
<CardGroup cols={2}>
<Card
title="Tasks"
icon="play"
href="/ts-sdk-reference/tasks"
>
Run browser automations with `runTask`
</Card>
<Card
title="Workflows"
icon="diagram-project"
href="/ts-sdk-reference/workflows"
>
Create and run multi-step automations
</Card>
<Card
title="Browser Automation"
icon="robot"
href="/ts-sdk-reference/browser-automation"
>
Control cloud browsers with Playwright + AI
</Card>
<Card
title="Error Handling"
icon="triangle-exclamation"
href="/ts-sdk-reference/error-handling"
>
Handle errors and configure retries
</Card>
</CardGroup>

288
docs/ts-sdk-reference/tasks.mdx Normal file
View File

@@ -0,0 +1,288 @@
---
title: Tasks
subtitle: Run single browser automations with natural language
slug: ts-sdk-reference/tasks
---
A task is a single browser automation. You describe what you want in natural language — Skyvern opens a browser, navigates to the URL, and executes the instructions with AI.
For when to use tasks vs workflows, see [Run a Task](/running-automations/run-a-task).
---
## `runTask`
Start a browser automation. Skyvern opens a cloud browser, navigates to the URL, and executes your prompt with AI.
```typescript
const result = await skyvern.runTask({
body: {
prompt: "Get the title of the top post",
url: "https://news.ycombinator.com",
},
waitForCompletion: true,
});
console.log(result.output);
```
### Parameters
The `runTask` method accepts a single request object with the following shape:
| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `body.prompt` | `string` | Yes | — | Natural language instructions for what the AI should do. |
| `body.url` | `string` | No | `undefined` | Starting page URL. If omitted, the AI navigates from a blank page. |
| `body.engine` | `RunEngine` | No | `"skyvern_v2"` | AI engine. Options: `"skyvern_v2"`, `"skyvern_v1"`, `"openai_cua"`, `"anthropic_cua"`, `"ui_tars"`. |
| `body.max_steps` | `number` | No | `undefined` | Cap the number of AI steps to limit cost. Run terminates with `timed_out` if hit. |
| `body.data_extraction_schema` | `Record<string, unknown> \| string` | No | `undefined` | JSON schema constraining the output shape. |
| `body.proxy_location` | `ProxyLocation` | No | `undefined` | Route the browser through a geographic proxy. |
| `body.browser_session_id` | `string` | No | `undefined` | Run inside an existing [browser session](/optimization/browser-sessions). |
| `body.publish_workflow` | `boolean` | No | `false` | Save the generated code as a reusable workflow. Only works with `skyvern_v2`. |
| `body.webhook_url` | `string` | No | `undefined` | URL to receive a POST when the run finishes. |
| `body.error_code_mapping` | `Record<string, string>` | No | `undefined` | Map custom error codes to failure reasons. |
| `body.totp_identifier` | `string` | No | `undefined` | Identifier for TOTP verification. |
| `body.totp_url` | `string` | No | `undefined` | URL to receive TOTP codes. |
| `body.title` | `string` | No | `undefined` | Display name for this run in the dashboard. |
| `body.model` | `Record<string, unknown>` | No | `undefined` | Override the output model definition. |
| `body.user_agent` | `string` | No | `undefined` | Custom User-Agent header for the browser. |
| `body.extra_http_headers` | `Record<string, string>` | No | `undefined` | Additional HTTP headers injected into every browser request. |
| `body.browser_address` | `string` | No | `undefined` | Connect to a browser at this CDP address instead of spinning up a new one. |
| `waitForCompletion` | `boolean` | No | `false` | Block until the run finishes. |
| `timeout` | `number` | No | `1800` | Max wait time in seconds when `waitForCompletion` is `true`. |
### Returns `TaskRunResponse`
| Field | Type | Description |
|-------|------|-------------|
| `run_id` | `string` | Unique identifier. Starts with `tsk_` for task runs. |
| `status` | `string` | `"created"`, `"queued"`, `"running"`, `"completed"`, `"failed"`, `"terminated"`, `"timed_out"`, or `"canceled"`. |
| `output` | `Record<string, unknown> \| null` | Extracted data from the run. Shape depends on your prompt or `data_extraction_schema`. |
| `downloaded_files` | `FileInfo[] \| undefined` | Files downloaded during the run. |
| `recording_url` | `string \| undefined` | URL to the session recording video. |
| `screenshot_urls` | `string[] \| undefined` | Final screenshots (most recent first). |
| `failure_reason` | `string \| undefined` | Error description if the run failed. |
| `app_url` | `string \| undefined` | Link to view this run in the Cloud UI. |
| `step_count` | `number \| undefined` | Number of AI steps taken. |
| `script_run` | `ScriptRunResponse \| undefined` | Code execution result if the run used generated code. |
| `created_at` | `string` | When the run was created. |
| `finished_at` | `string \| undefined` | When the run finished. |
### Examples
**Extract structured data:**
```typescript
const result = await skyvern.runTask({
body: {
prompt: "Extract the name, price, and rating of the top 3 products",
url: "https://example.com/products",
data_extraction_schema: {
type: "array",
items: {
type: "object",
properties: {
name: { type: "string" },
price: { type: "string" },
rating: { type: "number" },
},
},
},
},
waitForCompletion: true,
});
console.log(result.output);
// [{ name: "Widget A", price: "$29.99", rating: 4.5 }, ...]
```
**Run inside an existing browser session:**
```typescript
const session = await skyvern.createBrowserSession({});
const result = await skyvern.runTask({
body: {
prompt: "Log in and download the latest invoice",
url: "https://app.example.com/login",
browser_session_id: session.browser_session_id,
},
waitForCompletion: true,
});
```
**Limit cost with max_steps:**
```typescript
const result = await skyvern.runTask({
body: {
prompt: "Fill out the contact form",
url: "https://example.com/contact",
max_steps: 10,
},
waitForCompletion: true,
});
```
**Publish as a reusable workflow:**
```typescript
const result = await skyvern.runTask({
body: {
prompt: "Fill out the contact form with the provided data",
url: "https://example.com/contact",
publish_workflow: true,
},
waitForCompletion: true,
});
// The generated workflow is saved and can be re-triggered via runWorkflow
```
---
## `getRun`
Get the current status and results of any run (task or workflow).
```typescript
const run = await skyvern.getRun("tsk_v2_486305187432193504");
console.log(run.status, run.output);
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `runId` | `string` | Yes | The run ID returned by `runTask` or `runWorkflow`. |
### Returns `GetRunResponse`
A discriminated union based on `run_type`. All variants share the same core fields as `TaskRunResponse` above, plus a `run_type` field (`task_v1`, `task_v2`, `openai_cua`, `anthropic_cua`, `ui_tars`, `workflow_run`).
Workflow run responses additionally include `run_with` and `ai_fallback` fields.
---
## `cancelRun`
Cancel a running or queued run.
```typescript
await skyvern.cancelRun("tsk_v2_486305187432193504");
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `runId` | `string` | Yes | The run ID to cancel. |
The run transitions to `canceled` status. If the run has already finished, this is a no-op.
---
## `getRunTimeline`
Get the step-by-step timeline of a run. Each entry represents one AI action with screenshots and reasoning.
```typescript
const timeline = await skyvern.getRunTimeline("tsk_v2_486305187432193504");
for (const step of timeline) {
console.log(`Step ${step.order}: ${step.type} — ${step.status}`);
}
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `runId` | `string` | Yes | The run ID. |
### Returns `WorkflowRunTimeline[]`
Each timeline entry contains step details including type, status, order, and associated artifacts.
---
## `getRunArtifacts`
Get all artifacts (screenshots, recordings, generated code, etc.) for a run.
```typescript
const artifacts = await skyvern.getRunArtifacts("tsk_v2_486305187432193504");
for (const artifact of artifacts) {
console.log(`${artifact.artifact_type}: ${artifact.uri}`);
}
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `runId` | `string` | Yes | The run ID. |
| `artifactType` | `ArtifactType \| ArtifactType[]` | No | Filter by artifact type. |
### Returns `Artifact[]`
---
## `getArtifact`
Get a single artifact by ID.
```typescript
const artifact = await skyvern.getArtifact("art_486305187432193504");
console.log(artifact.uri);
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `artifactId` | `string` | Yes | The artifact ID. |
### Returns `Artifact`
---
## `retryRunWebhook`
Re-send the webhook notification for a completed run. Useful if your webhook endpoint was down when the run finished.
```typescript
await skyvern.retryRunWebhook("tsk_v2_486305187432193504");
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `runId` | `string` | Yes | The run ID. |
---
## Polling pattern
If you don't use `waitForCompletion`, poll `getRun` manually:
```typescript
const task = await skyvern.runTask({
body: {
prompt: "Extract product data",
url: "https://example.com/products",
},
});
const terminalStatuses = ["completed", "failed", "terminated", "timed_out", "canceled"];
let run;
while (true) {
run = await skyvern.getRun(task.run_id);
if (terminalStatuses.includes(run.status)) break;
await new Promise((resolve) => setTimeout(resolve, 5000));
}
console.log(run.output);
```
<Tip>
For production, prefer `waitForCompletion: true` or [webhooks](/going-to-production/webhooks) over manual polling.
</Tip>

273
docs/ts-sdk-reference/workflows.mdx Normal file
View File

@@ -0,0 +1,273 @@
---
title: Workflows
subtitle: Create and run multi-step browser automations
slug: ts-sdk-reference/workflows
---
A workflow chains multiple steps (blocks) into a single automation. Workflows support loops, conditionals, data passing between steps, and code-based re-execution.
For conceptual background, see [Build a Workflow](/multi-step-automations/build-a-workflow).
---
## `runWorkflow`
Execute a workflow by its permanent ID. Skyvern opens a cloud browser and runs each block in sequence.
```typescript
const result = await skyvern.runWorkflow({
body: {
workflow_id: "wpid_abc123",
},
waitForCompletion: true,
});
console.log(result.output);
```
### Parameters
| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `body.workflow_id` | `string` | Yes | — | The workflow's permanent ID (`wpid_...`). |
| `body.parameters` | `Record<string, unknown>` | No | `undefined` | Input parameters defined in the workflow. Keys must match parameter names. |
| `body.browser_session_id` | `string` | No | `undefined` | Run inside an existing [browser session](/optimization/browser-sessions). |
| `body.browser_profile_id` | `string` | No | `undefined` | Load a [browser profile](/optimization/browser-profiles) (cookies, storage) into the session. |
| `body.proxy_location` | `ProxyLocation` | No | `undefined` | Route the browser through a geographic proxy. |
| `body.webhook_url` | `string` | No | `undefined` | URL to receive a POST when the run finishes. |
| `body.title` | `string` | No | `undefined` | Display name for this run in the dashboard. |
| `body.totp_identifier` | `string` | No | `undefined` | Identifier for TOTP verification. |
| `body.totp_url` | `string` | No | `undefined` | URL to receive TOTP codes. |
| `body.user_agent` | `string` | No | `undefined` | Custom User-Agent header for the browser. |
| `body.extra_http_headers` | `Record<string, string>` | No | `undefined` | Additional HTTP headers injected into every browser request. |
| `body.browser_address` | `string` | No | `undefined` | Connect to a browser at this CDP address. |
| `template` | `boolean` | No | `undefined` | Run a template workflow. |
| `waitForCompletion` | `boolean` | No | `false` | Block until the workflow finishes. |
| `timeout` | `number` | No | `1800` | Max wait time in seconds when `waitForCompletion` is `true`. |
### Returns `WorkflowRunResponse`
| Field | Type | Description |
|-------|------|-------------|
| `run_id` | `string` | Unique identifier. Starts with `wr_` for workflow runs. |
| `status` | `string` | `"created"`, `"queued"`, `"running"`, `"completed"`, `"failed"`, `"terminated"`, `"timed_out"`, or `"canceled"`. |
| `output` | `Record<string, unknown> \| null` | Extracted data from the workflow's output block. |
| `downloaded_files` | `FileInfo[] \| undefined` | Files downloaded during the run. |
| `recording_url` | `string \| undefined` | URL to the session recording. |
| `failure_reason` | `string \| undefined` | Error description if the run failed. |
| `app_url` | `string \| undefined` | Link to view this run in the Cloud UI. |
| `step_count` | `number \| undefined` | Total AI steps taken across all blocks. |
| `run_with` | `string \| undefined` | Whether the run used `"code"` or `"agent"`. |
| `ai_fallback` | `boolean \| undefined` | Whether AI fallback was configured. |
| `script_run` | `ScriptRunResponse \| undefined` | Code execution result. Contains `ai_fallback_triggered` if code was used. |
### Examples
**Pass parameters to a workflow:**
```typescript
const result = await skyvern.runWorkflow({
body: {
workflow_id: "wpid_invoice_extraction",
parameters: {
company_name: "Acme Corp",
date_range: "2025-01-01 to 2025-12-31",
},
},
waitForCompletion: true,
});
```
**Run with a browser profile (skip login):**
```typescript
const result = await skyvern.runWorkflow({
body: {
workflow_id: "wpid_daily_report",
browser_profile_id: "bpf_abc123",
},
waitForCompletion: true,
});
```
---
## `createWorkflow`
Create a new workflow from a JSON or YAML definition.
```typescript
const workflow = await skyvern.createWorkflow({
body: {
json_definition: {
title: "Extract Products",
workflow_definition: {
parameters: [
{
key: "target_url",
parameter_type: "workflow",
workflow_parameter_type: "string",
description: "URL to scrape",
},
],
blocks: [
{
block_type: "task",
label: "extract",
prompt: "Extract the top 3 products with name and price",
url: "{{ target_url }}",
},
],
},
},
},
});
console.log(workflow.workflow_permanent_id);
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `body.json_definition` | `object` | No | Workflow definition as a JSON object. |
| `body.yaml_definition` | `string` | No | Workflow definition as a YAML string. |
| `folder_id` | `string` | No | Folder to organize the workflow in. |
You must provide either `body.json_definition` or `body.yaml_definition`.
### Returns `Workflow`
| Field | Type | Description |
|-------|------|-------------|
| `workflow_id` | `string` | Unique ID for this version. |
| `workflow_permanent_id` | `string` | Stable ID across all versions. Use this to run workflows. |
| `version` | `number` | Version number. |
| `title` | `string` | Workflow title. |
| `workflow_definition` | `WorkflowDefinition` | The full definition including blocks and parameters. |
| `status` | `string \| undefined` | Workflow status. |
| `created_at` | `string` | When the workflow was created. |
---
## `getWorkflows`
List all workflows. Supports filtering and pagination.
```typescript
const workflows = await skyvern.getWorkflows({});
for (const wf of workflows) {
console.log(`${wf.title} (${wf.workflow_permanent_id})`);
}
```
### Parameters
| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `page` | `number` | No | `undefined` | Page number for pagination. |
| `page_size` | `number` | No | `undefined` | Number of results per page. |
| `only_saved_tasks` | `boolean` | No | `undefined` | Only return saved tasks. |
| `only_workflows` | `boolean` | No | `undefined` | Only return workflows (not saved tasks). |
| `only_templates` | `boolean` | No | `undefined` | Only return templates. |
| `title` | `string` | No | `undefined` | Filter by exact title. |
| `search_key` | `string` | No | `undefined` | Search by title. |
| `folder_id` | `string` | No | `undefined` | Filter by folder. |
| `status` | `WorkflowStatus \| WorkflowStatus[]` | No | `undefined` | Filter by status. |
### Returns `Workflow[]`
---
## `getWorkflow`
Get a specific workflow by its permanent ID.
```typescript
const workflow = await skyvern.getWorkflow("wpid_abc123");
console.log(workflow.title, `v${workflow.version}`);
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `workflowPermanentId` | `string` | Yes | The workflow's permanent ID. |
| `version` | `number` | No | Specific version to retrieve. Defaults to latest. |
| `template` | `boolean` | No | Whether to fetch a template workflow. |
### Returns `Workflow`
---
## `getWorkflowVersions`
List all versions of a workflow.
```typescript
const versions = await skyvern.getWorkflowVersions("wpid_abc123");
for (const v of versions) {
console.log(`v${v.version} — ${v.modified_at}`);
}
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `workflowPermanentId` | `string` | Yes | The workflow's permanent ID. |
| `template` | `boolean` | No | Whether to fetch template versions. |
### Returns `Workflow[]`
---
## `updateWorkflow`
Update an existing workflow's definition.
```typescript
const updated = await skyvern.updateWorkflow("wpid_abc123", {
json_definition: {
title: "Extract Products Updated",
workflow_definition: {
blocks: [
{
block_type: "task",
label: "extract_data",
prompt: "Extract the top 5 products",
url: "https://example.com/products",
},
],
parameters: [],
},
},
});
console.log(`Updated to v${updated.version}`);
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `workflowId` | `string` | Yes | The workflow's permanent ID (`wpid_...`). |
| `json_definition` | `object` | No | Updated workflow definition as JSON. |
| `yaml_definition` | `string` | No | Updated workflow definition as YAML. |
### Returns `Workflow`
Creates a new version of the workflow.
---
## `deleteWorkflow`
Delete a workflow.
```typescript
await skyvern.deleteWorkflow("wf_abc123");
```
### Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `workflowId` | `string` | Yes | The workflow version ID to delete. |