mirror of
https://github.com/Skyvern-AI/skyvern.git
synced 2026-04-28 19:50:42 +00:00
Add workflow runs links from scheduler pages (#SKY-8468) (#5162)
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
This commit is contained in:
Shuchang Zheng
GitHub
parent
7ed9cfebac
commit
1d2a398cbf
26 changed files with 645 additions and 421 deletions
|
|
@ -47,6 +47,264 @@ All methods are async. Use `await` inside `async def`, with `asyncio.run()` as e
|
|||
|
||||
---
|
||||
|
||||
## Browser control
|
||||
|
||||
The SDK can launch and connect to browsers directly, giving you a Playwright-compatible page with AI capabilities layered on top. This is separate from the API-level browser session methods — here you get a live `SkyvernBrowser` and `SkyvernBrowserPage` you can script against.
|
||||
|
||||
### `launch_local_browser`
|
||||
|
||||
Launch a local Chromium browser with CDP enabled. Requires local mode (`Skyvern.local()`).
|
||||
|
||||
```python
|
||||
browser = await client.launch_local_browser(
|
||||
headless: bool = False, # Run headless or with a visible window.
|
||||
port: int = 9222, # CDP port.
|
||||
args: list[str] | None = None, # Extra Chromium flags.
|
||||
user_data_dir: str | None = None,# Persistent profile directory.
|
||||
) -> SkyvernBrowser
|
||||
```
|
||||
|
||||
### `connect_to_browser_over_cdp`
|
||||
|
||||
Connect to any running browser via Chrome DevTools Protocol.
|
||||
|
||||
```python
|
||||
browser = await client.connect_to_browser_over_cdp(
|
||||
cdp_url: str, # e.g. "http://localhost:9222"
|
||||
) -> SkyvernBrowser
|
||||
```
|
||||
|
||||
### `connect_to_cloud_browser_session`
|
||||
|
||||
Connect to an existing cloud browser session by ID.
|
||||
|
||||
```python
|
||||
browser = await client.connect_to_cloud_browser_session(
|
||||
browser_session_id: str,
|
||||
) -> SkyvernBrowser
|
||||
```
|
||||
|
||||
### `launch_cloud_browser`
|
||||
|
||||
Create a new cloud browser session and connect to it.
|
||||
|
||||
```python
|
||||
browser = await client.launch_cloud_browser(
|
||||
timeout: int | None = None, # Minutes (5-1440). Default 60.
|
||||
proxy_location: ProxyLocation | None = None,
|
||||
) -> SkyvernBrowser
|
||||
```
|
||||
|
||||
### `use_cloud_browser`
|
||||
|
||||
Reuse the most recent available cloud session, or create a new one if none exists.
|
||||
|
||||
```python
|
||||
browser = await client.use_cloud_browser(
|
||||
timeout: int | None = None,
|
||||
proxy_location: ProxyLocation | None = None,
|
||||
) -> SkyvernBrowser
|
||||
```
|
||||
|
||||
### Getting a page
|
||||
|
||||
```python
|
||||
page = await browser.get_working_page() # Most recent page, or creates one
|
||||
page = await browser.new_page() # Always creates a new tab
|
||||
```
|
||||
|
||||
Both return a `SkyvernBrowserPage` — a Playwright `Page` with AI methods added.
|
||||
|
||||
---
|
||||
|
||||
## Page-level AI methods
|
||||
|
||||
`SkyvernBrowserPage` extends Playwright's `Page`. You can use all standard Playwright methods (`goto`, `fill`, `locator`, `screenshot`, etc.) plus these AI-powered methods.
|
||||
|
||||
### `page.act`
|
||||
|
||||
Perform an action described in natural language.
|
||||
|
||||
```python
|
||||
await page.act(prompt: str) -> None
|
||||
```
|
||||
|
||||
```python
|
||||
await page.act("Click the login button")
|
||||
await page.act("Select 'United States' from the country dropdown")
|
||||
```
|
||||
|
||||
### `page.click` (AI-enhanced)
|
||||
|
||||
Click an element using a CSS selector, an AI prompt, or both with fallback.
|
||||
|
||||
```python
|
||||
await page.click(
|
||||
selector: str | None = None, # CSS selector.
|
||||
prompt: str | None = None, # Natural language target description.
|
||||
ai: str | None = "fallback", # "fallback" (try selector, then AI) or None.
|
||||
**kwargs, # Standard Playwright click options.
|
||||
) -> str | None
|
||||
```
|
||||
|
||||
```python
|
||||
# Selector only
|
||||
await page.click("#submit-btn")
|
||||
|
||||
# AI only
|
||||
await page.click(prompt="Click the 'Submit Order' button")
|
||||
|
||||
# Selector with AI fallback
|
||||
await page.click("#submit-btn", prompt="Click the submit button")
|
||||
```
|
||||
|
||||
### `page.extract`
|
||||
|
||||
Extract structured data from the current page using AI.
|
||||
|
||||
```python
|
||||
result = await page.extract(
|
||||
prompt: str, # What to extract.
|
||||
schema: dict | list | str | None = None, # JSON Schema for the output.
|
||||
error_code_mapping: dict[str, str] | None = None,
|
||||
) -> dict | list | str | None
|
||||
```
|
||||
|
||||
```python
|
||||
products = await page.extract(
|
||||
prompt="Extract all products with name and price",
|
||||
schema={
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"name": {"type": "string"},
|
||||
"price": {"type": "number"},
|
||||
},
|
||||
},
|
||||
},
|
||||
)
|
||||
```
|
||||
|
||||
### `page.agent.run_task`
|
||||
|
||||
Run an AI task in the context of the current page. Always waits for completion.
|
||||
|
||||
```python
|
||||
result = await page.agent.run_task(
|
||||
prompt: str,
|
||||
engine: RunEngine = RunEngine.skyvern_v2,
|
||||
url: str | None = None, # Defaults to current page URL.
|
||||
data_extraction_schema: dict | str | None = None,
|
||||
max_steps: int | None = None,
|
||||
timeout: float = 1800,
|
||||
# Plus: model, webhook_url, totp_identifier, totp_url, title, error_code_mapping, user_agent
|
||||
) -> TaskRunResponse
|
||||
```
|
||||
|
||||
### `page.agent.login`
|
||||
|
||||
Run a login workflow in the context of the current page. Supports all credential types.
|
||||
|
||||
```python
|
||||
# Skyvern credentials
|
||||
await page.agent.login(
|
||||
credential_type=CredentialType.skyvern,
|
||||
credential_id="cred_123",
|
||||
)
|
||||
|
||||
# Bitwarden
|
||||
await page.agent.login(
|
||||
credential_type=CredentialType.bitwarden,
|
||||
bitwarden_item_id="item_id",
|
||||
)
|
||||
|
||||
# 1Password
|
||||
await page.agent.login(
|
||||
credential_type=CredentialType.onepassword,
|
||||
onepassword_vault_id="vault_id",
|
||||
onepassword_item_id="item_id",
|
||||
)
|
||||
|
||||
# Azure Key Vault
|
||||
await page.agent.login(
|
||||
credential_type=CredentialType.azure_vault,
|
||||
azure_vault_name="vault_name",
|
||||
azure_vault_username_key="username_key",
|
||||
azure_vault_password_key="password_key",
|
||||
)
|
||||
```
|
||||
|
||||
### `page.agent.download_files`
|
||||
|
||||
Download files using AI navigation, in the context of the current page.
|
||||
|
||||
```python
|
||||
result = await page.agent.download_files(
|
||||
prompt: str,
|
||||
url: str | None = None,
|
||||
download_suffix: str | None = None,
|
||||
download_timeout: float | None = None,
|
||||
max_steps_per_run: int | None = None,
|
||||
timeout: float = 1800,
|
||||
) -> WorkflowRunResponse
|
||||
```
|
||||
|
||||
### `page.agent.run_workflow`
|
||||
|
||||
Run a workflow in the context of the current page.
|
||||
|
||||
```python
|
||||
result = await page.agent.run_workflow(
|
||||
workflow_id: str,
|
||||
parameters: dict | None = None,
|
||||
timeout: float = 1800,
|
||||
) -> WorkflowRunResponse
|
||||
```
|
||||
|
||||
### Full example
|
||||
|
||||
```python
|
||||
from skyvern import Skyvern
|
||||
from skyvern.schemas.run_blocks import CredentialType
|
||||
|
||||
async def main():
|
||||
client = Skyvern(api_key="YOUR_API_KEY")
|
||||
browser = await client.launch_cloud_browser()
|
||||
page = await browser.get_working_page()
|
||||
|
||||
# Navigate and log in with AI
|
||||
await page.goto("https://app.example.com")
|
||||
await page.agent.login(
|
||||
credential_type=CredentialType.skyvern,
|
||||
credential_id="cred_123",
|
||||
)
|
||||
|
||||
# Mix Playwright and AI
|
||||
await page.click("#invoices-tab")
|
||||
data = await page.extract(
|
||||
prompt="Extract all invoice numbers and amounts",
|
||||
schema={
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"invoice_number": {"type": "string"},
|
||||
"amount": {"type": "number"},
|
||||
},
|
||||
},
|
||||
},
|
||||
)
|
||||
print(data)
|
||||
|
||||
await browser.close()
|
||||
|
||||
import asyncio
|
||||
asyncio.run(main())
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Imports
|
||||
|
||||
```python
|
||||
|
|
@ -591,3 +849,6 @@ print(run.output)
|
|||
- 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 `RunEngine` enum values: `skyvern_v1`, `skyvern_v2`, `openai_cua`, `anthropic_cua`, `ui_tars`.
|
||||
- `launch_local_browser` only works in local mode (`Skyvern.local()`). Cloud browser methods (`launch_cloud_browser`, `use_cloud_browser`, `connect_to_cloud_browser_session`) require cloud environment.
|
||||
- `page.agent` methods always wait for completion — they don't support `wait_for_completion=False`.
|
||||
- TypeScript SDK does not support browser control (local or cloud) — use the Python SDK for browser automation.
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue