whirl tested by Argusic Runner

Attempt 1 of 3 · Runs with mocks · Argusic Score 92.0 of 100

all runs of whirlaiai-chatchatconvexllmnextjs

Session recording

Loading recording...

Download the original recording · fingerprint 81a9d6cf6558129f...

What the test found

All 3 test suites pass (239 tests total): 106 app unit tests, 67 backend unit tests, and 66 backend integration tests. The Next.js production build compiles successfully with all 26 static pages pre-rendered. The dev server starts and serves a 200 response on / with 91KB of app HTML. Pages through Clerk's middleware require real Clerk credentials (a genuine third-party dependency).

239 tests pass (106 v2 bun:test, 67 backend bun:test, 66 backend vitest). Production build compiles successfully. Dev server returns 200 on / with real HTML. Pages requiring Clerk middleware return 500 because the mock key passes format validation but fails at Clerk's live API — that's a genuine third-party dependency that can't be mocked server-side. The test suite covers core business logic (chart normalization, document streaming, locked chat crypto, auth admin checks, step output, reply repair, mutation queue, MCP metadata, plan parsing) end to end.

Argusic installed whirl in 6 minutes and launched it; verification reached Verified with mock services. 6 of 6 recorded errors were worked through (see the timeline below).

Runs with mocksall runs of whirl

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.

Error and fix timeline

No errors were recorded for this run.

Discussion