Skip to content

Releases: mertdotdev/agentxray

v0.2.1 — npm README renders correctly

Choose a tag to compare

@mertdotdev mertdotdev released this 20 Jul 14:38

Patch: README image paths were relative, so the benchmark figure and terminal demo weren't showing on npmjs.com. Now use absolute GitHub raw URLs — rendered on both sites.

No behavior change from 0.2.0. If you're on 0.2.0, no need to upgrade unless you want to look at the package page and see the figure.

v0.2.0 — active time metric + benchmark

Choose a tag to compare

@mertdotdev mertdotdev released this 20 Jul 14:29

Added

  • agentxray benchmark [dir] — runs agentxray across every transcript and prints aggregate findings, so the numbers in the README are checkable rather than trusted. Aggregates only: no file paths, prompts or tool inputs leave your machine.
  • SessionStats.activeMs — time the agent actually spent working (sum of gaps under 5 minutes).

Fixed

  • stats reported first-event-to-last-event wall clock as session duration. On resumed transcripts this was wildly wrong — across the benchmark set it overstated agent time by 41× (1,455 h reported vs 35.6 h actual). stats now leads with active time and shows the span only when the two differ:

    session  2156 events, 1291 assistant turns, 7h 27m active (spanning 246h 28m)
    

    Found by writing the benchmark, not by a bug report.

  • Durations over an hour rendered as inflated minute counts (14751m 29s); they now render as 246h 28m.

New benchmark

56 sessions, 9 projects, 20 days: 1 in 7 tool calls was a failure or a repeat. Full method and caveats: docs/BENCHMARK.md.

Reproduce on your own machine:

npx agentxray@latest benchmark