What problem does it solve? Investigating memory leaks in VS Code requires repeatable scenario automation, reliable heap snapshot capture, and verified run evidence — doing this manually is slow, error-prone, and hard to reproduce. ## Core Features & Use Cases - Scenario Automation: Launch Code OSS with Playwright over CDP, drive repeatable UI workflows, and capture screenshots, summary.json, and renderer heap samples. - Checked-in Runners: Use bundled runners like chat-memory-smoke.mts and chat-session-switch-smoke.mts for multi-turn chat and session-switching memory probes with targeted heap snapshot labels. - Fix and Verify Loop: Compare before/after snapshots via the heap-snapshot-analysis skill, make root-cause product-code fixes, and rerun identical scenarios to confirm memory stays flat. - Use Case: A user suspects the Chat view leaks memory across turns. Run the chat memory smoke runner with 8 iterations and two snapshot labels, compare the heapsnapshots, identify the retaining service, fix the disposal logic, and rerun to verify. ## Quick Start Ask the agent to run the chat memory smoke runner with a few iterations and no heap snapshots to validate the scenario, then capture targeted heap snapshots for leak analysis.
