Marius CiepluchandClaude Opus 5.5 6d27c9bfcf unseen-eval: calibrated replay deadline + native agreement check, docker-lane diagnostics, proof 4.4 record; engine runner cleans up fetched sources ...

gVisor replays exhausted the hook's 30 s deadline in the snapshot step on a
1,725-file repository; cluster replays now use 30 s x a measured slowdown
factor, verified on a native sample. The engine runner deletes each pin's fetched
source (1.8 GB had accumulated), caps the cache at 500 MB and refuses below
1.5 GB free. Proof 4.4: two engine pins via the generic dispatcher match the VM
baseline exactly. Implemented with Codex.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

2026-10-05 08:14:57 +02:00

..

brief.md

steering: roadmap re-centred on generalisation to unseen repositories (G0-G5); specs updated; unseen-repo-evaluation brief and requirements (approved)

2026-10-04 17:34:57 +02:00

design.md

unseen-eval: calibrated replay deadline + native agreement check, docker-lane diagnostics, proof 4.4 record; engine runner cleans up fetched sources

2026-10-05 08:14:57 +02:00

requirements.md

spec(unseen-repo-evaluation): design and tasks approved; run through the baseline

2026-10-04 18:48:13 +02:00

spec.json

spec(unseen-repo-evaluation): design and tasks approved; run through the baseline

2026-10-04 18:48:13 +02:00

tasks.md

unseen-eval groups 4-6: generic AX batch dispatcher (engine_trace on it), replay task and image stage, scorer with adoption gate

2026-10-04 20:19:14 +02:00