Commit Graph
8 Commits
Author SHA1 Message Date
DottaandPaperclip 664c1899ef Fix blocker browser grading and retain the complete native comparison
Accept the requested marker plus concrete blocker explanation, calibrate contradictory and future-condition replies, and clarify future fixture punctuation. Preserve every original paid failure and label retained-DOM replay separately from live qualification.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 17:31:40 -05:00
DottaandPaperclip 12d9276baf test(evals): qualify native blocked reports with persisted outcomes
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 17:31:40 -05:00
DottaandPaperclip c0861720ba Clarify native Runner completion tool guidance
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 17:31:21 -05:00
DottaandPaperclip b85668c406 Fix skill capability metadata and publish the bounded repair comparison
Regenerate both capability inventories for the early issue-document recipe and reject stale derived manifests before stock-harness provider admission. Preserve the eight measured repair results, automatic recovery cost, and OpenCode delivery diagnosis.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 16:30:31 -05:00
DottaandPaperclip 19b22b907a Clarify legacy issue document delivery in the operational skill
Preserve the tiny hire manual and original assigned-skill case. Add a focused public document/revision/link oracle and explicit presence/absence provenance for a matched skill-only comparison.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 16:29:38 -05:00
DottaandPaperclip f65f1b9454 fix(evals): prepare cold prerequisites and fingerprint connection guidance
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 16:29:37 -05:00
DottaandPaperclip a2b9d62e52 test(evals): enforce exact-source stock harness prerequisites
Run credential-free gates before live admission and verify retained evidence in direct browser execution. Include evaluated instruction sources in suite revisions and calibrate stale/missing evidence rejection.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 16:29:37 -05:00
DottaandPaperclip 668d8d9591 test(evals): cover production default hires across stock harnesses
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 16:29:37 -05:00