Skip to content

Add docfs benchmark pilot runner#5

Draft
rgodha24 wants to merge 1 commit into
mainfrom
docfs-benchmark
Draft

Add docfs benchmark pilot runner#5
rgodha24 wants to merge 1 commit into
mainfrom
docfs-benchmark

Conversation

@rgodha24

@rgodha24 rgodha24 commented Jul 10, 2026

Copy link
Copy Markdown

Summary

  • add a local-filesystem docfs runner for the existing task dataset
  • capture shell command and cache-hydration metrics instead of HTTP fetch/404 metrics
  • document the 20-site pilot, token audit, and study limitations

Validation

  • python3 -m py_compile url_discovery_bench/runners.py url_discovery_bench/docfs_run.py
  • python3 -m url_discovery_bench.docfs_run --help
  • live cold-mount Claude/Codex pilot across 20 sites

The documented token means include two runaway navigation attempts; medians and outlier-free means are included in DOCFS_PILOT.md.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant