Rapid-MLX tested by Argusic Runner

Attempt 1 of 3 · Runs with mocks · Argusic Score 78.7 of 100

all runs of Rapid-MLXanthropic-apiapple-siliconclaude-codecoding-agentscontinuous-batchinginference-server

Session recording

Loading recording...

Download the original recording · fingerprint 9644971ec316cc39...

What the test found

Rapid-MLX 1.0.4 installed from source in a uv venv on Linux x86_64. The Python package, CLI entry point, and 10962 unit tests pass. Engine-lifecycle, parser, anthropic adapter, agent, telemetry, and install tests all pass. Only MLX/Metal-dependent model kernel, VLM, audio, and lane-matmul tests are skipped because this host has no Apple Silicon GPU — matching the project's intended macOS-only target.

Apple Silicon MLX project tested on Linux x86_64. MLX, mlx-lm, mlx-vlm, mlx-audio, and torch installed but cannot run on this platform (no Metal/libmlx.so). Headless MLX stubs enable 62K+ test collection and 11K+ passing unit tests. Verified: rapid-mlx --help works, 63 engine lifecycle tests pass, 1467+ unit tests pass, ruff lint/format pass, CLI-audit passes. All 5 real-MLX-requiring test files cleanly excluded at collection time. Full test output: 1 failed (pre-existing env issue), 10962 passed, 467 skipped, 13 xfailed.

Argusic installed Rapid-MLX in 9.7 minutes and launched it; verification reached Verified with mock services. 1 of 3 recorded errors were worked through (see the timeline below).

Runs with mocksall runs of Rapid-MLX

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