Playwright

How a loop of infinite timeouts turned into three nested deadlines, a watchdog, and a repeatable method for writing agent skills that survive production.

Playwright v1.60 introduces scoped HAR recording that captures every network request and response during a failing test, turning failures into consumable evidence for humans and AI. This guide dives deep into the new `tracing.startHar()` API, shows real-world patterns, and reveals gotchas you'll encounter in CI.

Private, self-healing Playwright test loop on WSL2 using llama.cpp via Docker, GPU acceleration, and OpenCode agents

A practical guide to transforming sluggish, flaky Playwright test suites into fast, reliable CI/CD pipelines using Docker containers and intelligent parallelization strategies.

Gemini CLI v0.32.0 moves beyond simple command recall with a Generalist Agent, Model Steering, and an Experimental Browser Agent. For developers and QA, this means your terminal can now think, adapt, and even browse the web autonomously.

Learn how to build a specialized QA Engineer agent in OpenCode that can autonomously create, execute, and maintain Playwright end-to-end tests using Playwright CLI and AI-powered test agents.

Playwright 1.57/1.58 introduces AI agents for self-healing tests, Model Context Protocol for intelligent automation, and significant framework improvements. Learn how these changes reduce flakiness and transform your testing workflow.