Commit Graph
5 Commits
Author SHA1 Message Date
Marius CiepluchandClaude Fable 5.1 b44fb56d8d ax batch: workload-kind prefixes in task names (pass-, replay-) [skip ci]
The operator keys per-host egress rules on the task-name prefix; engine passes and
replays had none. Names stay within 49 bytes.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
2026-10-05 20:33:35 +02:00
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
Marius CiepluchandClaude Opus 5.5 c6e87a8517 unseen-eval groups 4-6: generic AX batch dispatcher (engine_trace on it), replay task and image stage, scorer with adoption gate
Implemented with Codex.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-04 20:19:14 +02:00
Marius CiepluchandClaude Opus 5.5 48ae918dec unseen-eval group 2 (2.1-2.4): advisory sourcing, vulnerability-introducing ranges, ordinary-commit draw, draft manifest and slices; journal with resume
Implemented with Codex. Sourcing run (2.5) next, by the coordinator.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-04 19:51:30 +02:00
Marius CiepluchandClaude Opus 5.5 8213d3baad unseen-eval group 1: used set (1,029 repositories, every source read), extended guard, usage ledger; record 01
Implemented with Codex; task 1.5 run by the coordinator against the real
sources (S3 memory read-only).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-04 19:17:35 +02:00