Commit Graph
18 Commits
Author SHA1 Message Date
DottaandPaperclip da8d4454ae Bind cloud Pi memory reads to the current agent and run
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-08 08:19:25 -05:00
Dotta 53c6e0c0a1 test(pi): bind memory reads to exact contents and repair remote fixtures 2026-10-08 05:47:17 -05:00
Dotta dabe81befe test(pi): require native reads across the memory restart fixture 2026-10-08 05:18:36 -05:00
Dotta 0104942b02 test(pi): qualify Sonnet and simplify exact-byte memory fixture 2026-10-08 05:10:06 -05:00
DottaandPaperclip 061c02f7fc Bind Pi fixtures to browser-created task identity
Use explicit titles for strict native actions and the creation response ID for scoped task lookup, preserving all native behavior and cleanup grading.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-07 12:03:25 -05:00
Dotta dda1b5fb82 Preserve Pi qualification errors when diagnostic storage fails 2026-10-05 21:18:13 -05:00
Dotta 8ce546da0e Fix Pi memory parent setup and retired observer cleanup 2026-10-05 21:14:26 -05:00
Dotta ab0483d0cc fix: retain Pi fixture evidence before failed grades 2026-10-05 19:54:21 -05:00
Dotta 926104e4d6 Order Pi memory verification and cross-root denial before completion 2026-10-05 17:13:42 -05:00
Dotta 14c48ff408 fix: select actionable Pi permission cards after setup approval 2026-10-04 21:14:20 -05:00
Dotta 9cb5ac2c41 fix: scope Pi remote fixture setup approval to its published read 2026-10-04 20:50:07 -05:00
DottaandPaperclip 59bd71dff2 Preserve the owned Pi runner across controller-only E2E restart
Separate durable runner preservation from final process retirement. Bind
restart preservation to the public run identity and observed ancestry, and
drain every retained owner after the replacement controller shuts down.

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-10-02 09:43:06 -05:00
DottaandPaperclip 4c6adcadcb test(runner-e2e): verify pending Pi input after provider loss
Add one explicit Daytona Product cell that admits the exact Pi child before faulting it, then requires production expiry of the original native question, failed-run Blocked disposition, stale-answer rejection, distinct unanswered fallback, and no replay through owned retirement. Retain the existing local scope and pending qualification.

Calibrate public lifecycle evidence, generated observer one-shot dispatch, and candidate failure classification. Runtime, provider profile, dependency closure, deadlines, and lockfiles are unchanged.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-01 19:26:25 -05:00
Dotta 5cd6d3d523 test: strengthen Pi editing and pending native recovery qualification 2026-10-01 17:36:20 -05:00
DottaandPaperclip d6ff17fd0d test(runner-e2e): isolate denied-target watchers from startup churn
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-29 21:40:17 -05:00
DottaandPaperclip d1bb5729f9 Add Pi remote native evidence and browser denial fixtures
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-29 17:13:41 -05:00
DottaandPaperclip a0d916a8c9 fix(evals): retain Pi native terminal API evidence
Capture the required final issue, runs, comments, interactions and paginated run events before native fixture success. Regress the real flow through evidence packaging and fail closed when terminal capture is unavailable.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-29 15:32:30 -05:00
DottaandPaperclip 6f163033a4 test(runner): add explicit Pi native product boundaries
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-29 09:56:30 -05:00