Video unavailable. Open the source below.
NewTouchpress mobile end-to-end testing
my mobile e2e testing library powered by @agent_device and AI sdk now supports Jev from @typesafeai Same test, same loop: Jev: 29s, $0.003 Haiku 4.5: 37s, $0.07
Video unavailable. Open the source below.
Newmy mobile e2e testing library powered by @agent_device and AI sdk now supports Jev from @typesafeai Same test, same loop: Jev: 29s, $0.003 Haiku 4.5: 37s, $0.07
Touchpress can configure TypeSafe Jev as its evaluation model for `device.act`. At each step, the test captures the screen, lists offered moves, and asks which move should come next; Jev returns a typed Choice rather than writing text.
Choose the offered move that advances the task or correctly finishes it.
Task and current mobile screen with no offered element or fill moves; only fixed verdict/navigation moves remain.
Set the app identifier, ready condition, platform, and simulator or emulator in Playwright configuration.
Configure the AI SDK evaluation model as TypeSafe Jev for `device.act`.
Call `device.act` with an instruction; the model chooses among moves available on screen until the instruction is satisfied or it cannot proceed.
Use Playwright locators and expectations to verify the resulting UI state.
It brings typed decision-model control into ordinary Playwright mobile tests, so a test can describe an action in English and continue with normal locator assertions.