5 Commits

Include renames

Author	SHA1	Message	Date
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
Marius CiepluchandClaude Opus 5.5	60512fff88	spec(unseen-repo-evaluation): design and tasks approved; run through the baseline ... Decisions: long-deadline arm (300 s), adoption needs no unseen regression (Req 5.4), permissive repositories by name only, two AX lanes. Also adds the trained-classifier and joint-optimisation arms to learned-decision-engine. Co-Authored-By: Claude Opus 5.5 <[email protected]>	2026-10-04 18:48:13 +02:00
Marius CiepluchandClaude Opus 5.5	d4467f4236	steering: roadmap re-centred on generalisation to unseen repositories (G0-G5); specs updated; unseen-repo-evaluation brief and requirements (approved) ... Maintainer 2026-10-04: the safety net is for unseen code and the A/B tests exist to prove the approach generalises; infrastructure work had drifted from that. Runs are designed for AX on kube-ax, kind is the fallback. Co-Authored-By: Claude Opus 5.5 <[email protected]>	2026-10-04 17:34:57 +02:00