Exploring again never wipes your edits
Scenarios you create while the agent explores keep their IDs; a new exploration updates only its own entries, and user stories keep their names.
Wopee.io · Changelog
Product updates and improvements, as they ship to production.
Running in productionAPI v5.241.0CMD v3.458.3Agent v3.146.0since
Scenarios you create while the agent explores keep their IDs; a new exploration updates only its own entries, and user stories keep their names.
After checkout you return to Wopee.io, your plan is active on arrival and you continue to Projects, even when the payment confirmation is slow to arrive.
Every reasoning level from none to max is checked against the model it is set for, GPT-6 runs as a reasoning model, and the AI chat respects the setting.
Each reported issue is checked against what the run did: a claim the record contradicts is withdrawn, and locator failures are listed apart from bugs.
A run that did every step and failed only on its checks now leaves a Playwright test asserting the expected values, so it turns green once the bug is fixed.
The agent gets a screenshot after every action and can look at the page when it needs to; existing projects switch on unless they chose Off.
Quick start and Advanced Setup are one dialog now: pick a demo app or paste a URL, and framework, mode and name wait under one Advanced settings row.
A run that asserted nothing or skipped a step can no longer show green: it is flagged for review in amber, and runs left hanging are closed.
Expected text the agent never saw while exploring is flagged, its own scenario picks run first, steps visit only pages it saw, and broken images are reported.
Test data can follow a pattern you define, and Slovak and Czech IBAN generators now produce real, bank-valid account numbers that sign-up forms accept.