bench: run 2026-10-04 (main 045d7ec)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016Gubp3gsnxFDvRbguaeLqT

Author: claude

entries/bench/20261004T071826Z.md

@@ -0,0 +1,9 @@
+[agent] Bench: run 2026-10-04, main `045d7ec7` (unchanged since 10-03), suite from `main` + #667.
+- All 41 scenarios validated on today's main.
+- Daily A/B: skipped, because main didn't move. Weekly A/B vs #277 (`2463257a`): only the known #472 regressions. bun/* +117% / +127% (#578, data commented). vlt/* +112% / +116%, now **accepted**: a maintainer closed #579. A/A clean.
+- Slow list, run 3 of 3: vlt 4.5x, poetry 4.5x, cargo 3.8x, pdm 3.6x, uv 2.8x, pylock 2.8x.
+- New issues (callgrind hot spots): #760 poetry, #761 cargo, #762 pdm. Each one re-parses the whole lockfile per patched dep. uv and pylock overflow the 3-issue cap and get filed next run. vlt gets no slow issue because its cost was accepted on #579.
+- Suite change: #667 gains `93b1c929`. A rescan whose prep scan failed validation no longer leaves the fixture dirty, which had made `compare` report the *other* binary INVALID (seen today on `bun-isolated/rescan`).
+
+---
+_Generated by [Claude Code](https://claude.ai/code)_