Commit Graph
11 Commits
Author SHA1 Message Date
DottaandPaperclip 55ce97b675 test(evals): qualify native blocked reports with persisted outcomes
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 14:23:42 -05:00
DottaandPaperclip 26c0e552a0 Clarify native Runner completion tool guidance
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 14:23:42 -05:00
DottaandPaperclip 792533866c docs(evals): close the unchanged-source baseline recovery
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 14:02:14 -05:00
DottaandPaperclip 6c27174cd4 docs(evals): retain matched stock-harness results and failures
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 13:56:35 -05:00
DottaandPaperclip 1eb5ba4206 fix(evals): retain prerequisites inside the campaign artifact root
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 12:59:07 -05:00
DottaandPaperclip f02d8d0df3 fix(evals): use complete Rust protocol test preparation
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 12:35:11 -05:00
DottaandPaperclip 712dc98cf5 fix(evals): bind protocol evidence to the built daemon
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 12:31:35 -05:00
DottaandPaperclip ac6ddefb58 fix(evals): build the cold daemon before protocol prerequisites
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 12:23:54 -05:00
DottaandPaperclip 4163dbfd0f fix(evals): prepare cold prerequisites and fingerprint connection guidance
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 12:11:37 -05:00
DottaandPaperclip 36e987246b 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 11:49:11 -05:00
DottaandPaperclip a63437069d test(evals): cover production default hires across stock harnesses
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 11:26:28 -05:00