Claude abaed3c49d agent: phase2-tokei-001 — first auto-accepted win from the unattended loop ...

Ledger row: class 5 (algorithmic) on tokei, first-byte gate table for
the per-byte token matchers in perform_multi_line_analysis.
Speedup median 1.107, 95% CI [1.084, 1.131] vs the banked-wins baseline,
workload: 221 MB / 4360 files, single rayon thread, pinned core.

Manual audit gates (pipeline covers tests+golden+bench only):
- Differential fuzz, 10k mutated inputs across 200 batched runs:
  0 divergences after canonicalizing tokei's benign parallel-walker
  output ordering (present in pristine baseline; counts identical).
  Fuzzer added as scripts/diff-fuzz-tokei.py.
- ASan run recorded in the case study (next commit).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2

2026-07-10 05:08:16 +00:00

..

agent-isolated.sh

agent: OS-level isolation for the agent tool boundary (SPEC §10)

2026-07-10 04:43:08 +00:00

audit-attempt.py

agent: per-attempt audit script for the Phase 2 grind

2026-07-10 04:52:43 +00:00

diff-fuzz-tokei.py

agent: phase2-tokei-001 — first auto-accepted win from the unattended loop

2026-07-10 05:08:16 +00:00

isolation-check.sh

agent: OS-level isolation for the agent tool boundary (SPEC §10)

2026-07-10 04:43:08 +00:00