Scalable automation

Process multiple webpages in parallel

Assign each URL to an isolated Session with controlled concurrency, then summarize status codes, page titles, duration, and failures for batch collection and site checks.

Example · process multiple URLs with controlled browser concurrency

Integration options

Prerequisite:
Fetch and fully execute the official Lexmount Setup Prompt returned by https://browser.lexmount.cn/api/agent-setup/browser-cli.
Continue only after installation, authentication, and environment validation all pass; otherwise stop and report the failure truthfully.

Task:
Use browser-cli only to inspect the following pages concurrently and save the combined results as structured JSON in artifacts/parallel-browser-results.json:
- https://docs.python.org/3/
- https://nodejs.org/docs/latest/api/
- https://go.dev/doc/

Execution:
1. Create no more than three temporary Lexmount Cloud Browser Sessions concurrently, with one dedicated Session per URL. Do not replace independent Sessions with multiple tabs in one Session.
2. For each page, collect the requested URL, final URL, status code, document title, first visible H1, elapsed time, and sanitized error. Record null when no H1 is visible.
3. A failure on one page must not cancel the other tasks. Combine all results in input order, then verify that the JSON report exists, is non-empty, and parses successfully.
4. Each task must close only its own Session.

Acceptance:
Every input URL must have an explicit result, and the generated JSON must be available as a clickable file in the final Codex response. If any page or cleanup operation fails, report partial success.

Cleanup:
On success, failure, timeout, or cancellation, attempt to close every Session created by this task. Never close a pre-existing Session.

Return:
Report only the overall status, success and failure counts, report path, cleanup result, and sanitized error summary. Do not expose API keys, Project IDs, Session IDs, connect URLs, or WebSocket URLs.

Integration options

Prerequisite:
Fetch and fully execute the official Lexmount Setup Prompt returned by https://browser.lexmount.cn/api/agent-setup/browser-cli.
Continue only after installation, authentication, and environment validation all pass; otherwise stop and report the failure truthfully.

Task:
Use browser-cli only to inspect the following pages concurrently and save the combined results as structured JSON in artifacts/parallel-browser-results.json:
- https://docs.python.org/3/
- https://nodejs.org/docs/latest/api/
- https://go.dev/doc/

Execution:
1. Create no more than three temporary Lexmount Cloud Browser Sessions concurrently, with one dedicated Session per URL. Do not replace independent Sessions with multiple tabs in one Session.
2. For each page, collect the requested URL, final URL, status code, document title, first visible H1, elapsed time, and sanitized error. Record null when no H1 is visible.
3. A failure on one page must not cancel the other tasks. Combine all results in input order, then verify that the JSON report exists, is non-empty, and parses successfully.
4. Each task must close only its own Session.

Acceptance:
Every input URL must have an explicit result, and the generated JSON must be available as a clickable file in the final Codex response. If any page or cleanup operation fails, report partial success.

Cleanup:
On success, failure, timeout, or cancellation, attempt to close every Session created by this task. Never close a pre-existing Session.

Return:
Report only the overall status, success and failure counts, report path, cleanup result, and sanitized error summary. Do not expose API keys, Project IDs, Session IDs, connect URLs, or WebSocket URLs.