GenericAgent tested by Argusic Runner
Attempt 2 of 3 · Runs with mocks · Argusic Score 92.0 of 100
all runs of GenericAgentai-agentautomationautonomous-agentbrowser-automationclaudecomputer-control
Session recording
Download the original recording · fingerprint ad03c4886ca3bb86...
What the test found
After a venv install of the declared UI and test dependencies, 275 tests pass, the TUI starts, the Streamlit UI completes a mocked tool-using turn with MOCK_FINAL: 246810, and launch.pyw opens a live 1200x900 GenericAgent window on DISPLAY=:99 using PyQt6 and an extracted libxcb-cursor.
Python 3.12.3 was used. The editable package, core dependencies, [ui] extra, and test requirements installed successfully; the tracked worktree remains clean. No real API key was used: a local OpenAI-compatible mock returned schema-correct responses and exercised a real code_run tool call. Real-provider behavior was not tested. GTK/gi and the system xcb-cursor library were absent; the desktop launch used PyQt6 and an extracted prebuilt libxcb-cursor under DISPLAY=:99.
Argusic installed GenericAgent in 1 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 GenericAgent
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.