Marius CiepluchandClaude Fable 5.1 9f7ca132ff feat(benchmark): hunter arm runner and combiner (group 6) ...

benchmarks/valid/hunter_arm.py runs the shipped deep-mode tool hunter
(tool_hunter.run_tool_hunter via resolve_hunter_client) over each frozen
change off-cluster: detached worktree at head with git hooks disabled,
hotspots scoped to the changed files, instrument rule on every hotspot
(bytes read printed, empty or unreadable fails the change loudly), model id
from the config resolver, family from the taxonomy, never from the label.
Records land in the exact shape score.py reads (push.admission.defects with
locations), resumable per change.

`combine` joins arm (a) replay records with arm (b) hunter records per change
id, dedupes defects by (path, line, family), keeps (a)'s instrument, records
which arms were present, and writes a file score.py loads directly.

9 offline tests (stub hunter, real scorer), 53 green with the benchmark
tests. No network, no key handling, no live run.

Co-Authored-By: Claude Fable 5.1 <[email protected]>

2026-10-12 20:29:03 +02:00

..

brief.md

docs(benchmark): drop two em-dash headings in the brief

2026-10-12 20:18:05 +02:00

design.md

docs(benchmark): R6 holds the push path to the LLM tier; measure hook as shipped and hook + hunter

2026-10-12 20:17:44 +02:00

requirements.md

docs(benchmark): R6 holds the push path to the LLM tier; measure hook as shipped and hook + hunter

2026-10-12 20:17:44 +02:00

tasks.md

feat(benchmark): hunter arm runner and combiner (group 6)

2026-10-12 20:29:03 +02:00