browser-use tested by Argusic Runner

Attempt 1 of 3 · Runs · Argusic Score 100.0 of 100

all runs of browser-useai-agentsai-toolsbrowser-automationbrowser-usellmplaywright

Session recording

Loading recording...

Download the original recording · fingerprint 28773c20bea455ab...

What the test found

browser-use v0.13.10 installed in a Python 3.12 venv with uv, Chromium headless installed via playwright, and all 563 CI tests pass (529 passed, 34 skipped) after fixing 2 test identity comparison bugs in test_beta_agent.py that only manifest under xdist worker parallelism.

browser-use v0.13.10. Tests use real Chromium headless with local HTTP servers (pytest-httpserver). No API keys required thanks to mock_llm fixture and SKIP_LLM_API_KEY_VERIFICATION env var. The bu CLI doctor reports FAIL for 'chrome running' and 'daemon alive' which is expected in this container - those require a running Chrome process and daemon. All 563 CI tests pass (528 passed, 34 skipped, 1 error fixed). The skipped tests are browser interaction tests that need special dropdown/iframe setup, and 2 LLM tests that require real API keys.

Argusic installed browser-use in 0.15 minutes and launched it; verification reached Verified running for real. 2 of 2 recorded errors were worked through (see the timeline below).

Runsall runs of browser-use

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