From f3dd00e84c767e043b398720304bc42c067978a1 Mon Sep 17 00:00:00 2001 From: Agent Workbench Dev Date: Sat, 31 Oct 2026 18:22:04 +0800 Subject: [PATCH] test(companion): seal regression and prepare iPhone verification --- .gitattributes | 6 + .gitignore | 1 + AGENTS.md | 2 +- docs/IPHONE-COMPANION.md | 40 + docs/NEXT-STEPS.md | 4 +- docs/QA-1.16.md | 14 + docs/RETROSPECTIVE-1.16.md | 6 + docs/companion-f-local-evidence/all-ui.json | 201 + docs/companion-f-local-evidence/all-ui.log | 249 + .../full-source.tap | 3131 ++++ .../iphone/app-manifest.json | 171 + .../iphone/desktop-certificate.png | Bin 0 -> 180946 bytes .../iphone/desktop-offline-task.png | Bin 0 -> 114808 bytes .../iphone/frozen-candidate.json | 1592 ++ .../iphone/inspect-candidate.mjs | 30 + .../iphone/prepare-candidate.mjs | 52 + .../iphone/setup-candidate.mjs | 62 + .../iphone/setup.json | 33 + .../iphone/setup.log | 1 + .../iphone/ui-readiness.json | 24 + .../iphone/ui-readiness.log | 1 + docs/companion-f-local-evidence/manifest.json | 863 ++ .../seal-first-failure/original-failure.log | 24 + .../seal-first-failure/original-seal.mjs | 59 + .../seal-local-evidence.mjs | 70 + .../ui/01-companion/original.log | 8 + .../ui/01-companion/result.json | 37 + .../screenshots/01-desktop-certificate.png | Bin 0 -> 174733 bytes .../screenshots/02-desktop-pairing.png | Bin 0 -> 176160 bytes .../screenshots/03-mobile-task-list.png | Bin 0 -> 22235 bytes .../04-mobile-original-approval.png | Bin 0 -> 86864 bytes .../screenshots/05-mobile-original-diff.png | Bin 0 -> 19793 bytes .../screenshots/06-mobile-original-report.png | Bin 0 -> 29460 bytes .../screenshots/07-mobile-disconnected.png | Bin 0 -> 58330 bytes .../screenshots/08-tablet-task-list.png | Bin 0 -> 25030 bytes .../09-desktop-management-narrow.png | Bin 0 -> 60366 bytes .../screenshots/10-mobile-revoked.png | Bin 0 -> 36012 bytes .../ui/02-controlled/original.log | 10 + .../ui/02-controlled/result.json | 12858 ++++++++++++++++ .../01-desktop-controlled-parent.png | Bin 0 -> 158611 bytes .../02-mobile-controlled-parent.png | Bin 0 -> 66573 bytes .../03-mobile-controlled-input.png | Bin 0 -> 84547 bytes .../04-mobile-controlled-approval.png | Bin 0 -> 50608 bytes .../05-desktop-controlled-completed.png | Bin 0 -> 156797 bytes .../06-mobile-controlled-recovery.png | Bin 0 -> 84112 bytes .../ui/03-purge/original.log | 11 + .../ui/03-purge/result.json | 5809 +++++++ .../screenshots/01-desktop-purge-source.png | Bin 0 -> 184309 bytes .../screenshots/02-mobile-purge-source.png | Bin 0 -> 73136 bytes .../screenshots/03-mobile-purge-run.png | Bin 0 -> 63254 bytes .../ui/04-workers/original.log | 11 + .../ui/04-workers/result.json | 1009 ++ .../screenshots/01-mobile-worker-plan.png | Bin 0 -> 57466 bytes .../02-desktop-workers-collected.png | Bin 0 -> 146378 bytes .../03-mobile-workers-conflict.png | Bin 0 -> 57523 bytes .../04-mobile-workers-recovery-retained.png | Bin 0 -> 53611 bytes .../ui/05-task-plans/original.log | 9 + .../ui/05-task-plans/result.json | 31 + .../01-task-plan-desktop-editor.png | Bin 0 -> 166503 bytes .../02-task-plan-desktop-verified.png | Bin 0 -> 109713 bytes .../03-task-plan-mobile-editor.png | Bin 0 -> 55861 bytes .../04-task-plan-mobile-artifact.png | Bin 0 -> 90483 bytes .../screenshots/05-task-plan-mobile-steps.png | Bin 0 -> 47608 bytes .../06-task-plan-mobile-overview.png | Bin 0 -> 53647 bytes .../ui/06-browser/original.log | 11 + .../ui/06-browser/result.json | 175 + .../01-browser-desktop-results.png | Bin 0 -> 105400 bytes .../02-browser-desktop-original-image.png | Bin 0 -> 491143 bytes .../screenshots/03-browser-mobile-results.png | Bin 0 -> 44877 bytes .../04-browser-mobile-original-image.png | Bin 0 -> 202403 bytes .../ui/07-ui/original.log | 37 + .../ui/07-ui/result.json | 27 + .../ui/08-diagnostics/original.log | 29 + .../ui/08-diagnostics/result.json | 20 + .../ui/09-execution/original.log | 26 + .../ui/09-execution/result.json | 19 + .../ui/10-delivery/original.log | 40 + .../ui/10-delivery/result.json | 31 + .../ui/11-index/original.log | 19 + .../ui/11-index/result.json | 19 + .../ui/12-change-sets/original.log | 29 + .../ui/12-change-sets/result.json | 29 + ...-mobile-companion-batch-desktop-review.png | Bin 0 -> 156601 bytes ...obile-companion-batch-desktop-conflict.png | Bin 0 -> 172623 bytes ...obile-companion-batch-desktop-recovery.png | Bin 0 -> 167163 bytes ...4-mobile-companion-batch-mobile-review.png | Bin 0 -> 68312 bytes ...mobile-companion-batch-mobile-rollback.png | Bin 0 -> 73947 bytes .../ui/13-context/original.log | 45 + .../ui/13-context/result.json | 34 + .../01-mobile-companion-desktop-plan.png | Bin 0 -> 148127 bytes .../02-mobile-companion-desktop-history.png | Bin 0 -> 181995 bytes .../03-mobile-companion-mobile-history.png | Bin 0 -> 67361 bytes .../04-mobile-companion-mobile-original.png | Bin 0 -> 81542 bytes ...5-mobile-companion-mobile-request-body.png | Bin 0 -> 96912 bytes .../06-mobile-companion-mobile-read-pause.png | Bin 0 -> 56129 bytes ...ile-companion-desktop-working-evidence.png | Bin 0 -> 216524 bytes ...bile-companion-mobile-working-evidence.png | Bin 0 -> 89413 bytes .../ui/14-workspaces/original.log | 37 + .../ui/14-workspaces/result.json | 28 + ...le-companion-workspaces-review-desktop.png | Bin 0 -> 288811 bytes ...ile-companion-workspaces-ready-desktop.png | Bin 0 -> 140881 bytes ...-companion-workspaces-recovery-desktop.png | Bin 0 -> 145821 bytes ...ile-companion-workspaces-review-mobile.png | Bin 0 -> 63781 bytes ...bile-companion-workspaces-child-mobile.png | Bin 0 -> 49926 bytes .../ui/15-python/original.log | 42 + .../ui/15-python/result.json | 35 + .../ui/16-react-delivery/original.log | 82 + .../ui/16-react-delivery/result.json | 76 + .../ui/17-research/original.log | 19 + .../ui/17-research/result.json | 138 + .../01-mobile-companion-research-desktop.png | Bin 0 -> 206343 bytes .../02-mobile-companion-research-mobile.png | Bin 0 -> 63017 bytes ...ile-companion-research-evidence-mobile.png | Bin 0 -> 74314 bytes ...mobile-companion-research-stop-desktop.png | Bin 0 -> 172641 bytes .../ui/18-engines/original.log | 11 + .../ui/18-engines/result.json | 232 + .../screenshots/01-engines-native-desktop.png | Bin 0 -> 190434 bytes .../screenshots/02-engines-record-mobile.png | Bin 0 -> 86425 bytes .../screenshots/03-engines-native-mobile.png | Bin 0 -> 63363 bytes .../ui/19-model-center/original.log | 7 + .../ui/19-model-center/result.json | 23 + .../screenshots/01-desktop-operations.png | Bin 0 -> 158591 bytes .../screenshots/02-mobile-operations.png | Bin 0 -> 55013 bytes .../screenshots/03-mobile-connections.png | Bin 0 -> 54295 bytes .../ui/20-project-memory/original.log | 5 + .../ui/20-project-memory/result.json | 24 + .../screenshots/01-desktop-expired-memory.png | Bin 0 -> 151208 bytes .../02-mobile-incomplete-memory.png | Bin 0 -> 63401 bytes .../screenshots/03-desktop-sent-memory.png | Bin 0 -> 204055 bytes .../screenshots/04-mobile-sent-memory.png | Bin 0 -> 96634 bytes .../ui/21-task-checkpoints/original.log | 4 + .../ui/21-task-checkpoints/result.json | 20 + .../01-desktop-original-checkpoint.png | Bin 0 -> 277840 bytes .../02-mobile-checkpoint-ready.png | Bin 0 -> 46681 bytes .../ui/22-skills/original.log | 5 + .../ui/22-skills/result.json | 22 + .../screenshots/01-desktop-skill-source.png | Bin 0 -> 154040 bytes .../screenshots/02-mobile-skill-source.png | Bin 0 -> 64823 bytes .../03-desktop-sent-skill-catalog.png | Bin 0 -> 183409 bytes .../ui/23-mcp/original.log | 7 + .../ui/23-mcp/result.json | 24 + .../screenshots/01-desktop-mcp-registry.png | Bin 0 -> 156881 bytes .../screenshots/02-mobile-mcp-registry.png | Bin 0 -> 70637 bytes .../ui/24-mcp-recovery/original.log | 3 + .../ui/24-mcp-recovery/result.json | 16 + .../01-desktop-mcp-interrupted-input.png | Bin 0 -> 172885 bytes .../02-mobile-mcp-interrupted-input.png | Bin 0 -> 74897 bytes .../screenshots/03-mobile-mcp-review.png | Bin 0 -> 73585 bytes docs/mobile-companion-all-ui-validation.json | 201 + .../mobile-companion-basic-ui-validation.json | 27 + .../mobile-companion-batch-ui-validation.json | 29 + ...obile-companion-browser-ui-validation.json | 175 + ...e-companion-change-sets-ui-validation.json | 29 + ...ile-companion-companion-ui-validation.json | 37 + ...obile-companion-context-ui-validation.json | 34 + ...panion-controlled-final-ui-validation.json | 12858 ++++++++++++++++ ...bile-companion-delivery-ui-validation.json | 31 + ...e-companion-diagnostics-ui-validation.json | 20 + ...obile-companion-engines-ui-validation.json | 232 + ...ile-companion-execution-ui-validation.json | 19 + .../mobile-companion-index-ui-validation.json | 19 + docs/mobile-companion-iphone-readiness.json | 46 + ...-companion-mcp-recovery-ui-validation.json | 16 + docs/mobile-companion-mcp-ui-validation.json | 24 + ...-companion-model-center-ui-validation.json | 23 + ...ompanion-project-memory-ui-validation.json | 24 + ...e-companion-purge-final-ui-validation.json | 5809 +++++++ ...mobile-companion-python-ui-validation.json | 35 + ...e-companion-react-delivery-validation.json | 76 + ...bile-companion-research-ui-validation.json | 138 + ...mobile-companion-skills-ui-validation.json | 22 + ...panion-task-checkpoints-ui-validation.json | 20 + docs/mobile-companion-task-ui-validation.json | 31 + ...obile-companion-workers-ui-validation.json | 1009 ++ ...le-companion-workspaces-ui-validation.json | 28 + findings.md | 2 + progress.md | 2 + task_plan.md | 2 +- 178 files changed, 48893 insertions(+), 4 deletions(-) create mode 100644 docs/IPHONE-COMPANION.md create mode 100644 docs/companion-f-local-evidence/all-ui.json create mode 100644 docs/companion-f-local-evidence/all-ui.log create mode 100644 docs/companion-f-local-evidence/full-source.tap create mode 100644 docs/companion-f-local-evidence/iphone/app-manifest.json create mode 100644 docs/companion-f-local-evidence/iphone/desktop-certificate.png create mode 100644 docs/companion-f-local-evidence/iphone/desktop-offline-task.png create mode 100644 docs/companion-f-local-evidence/iphone/frozen-candidate.json create mode 100644 docs/companion-f-local-evidence/iphone/inspect-candidate.mjs create mode 100644 docs/companion-f-local-evidence/iphone/prepare-candidate.mjs create mode 100644 docs/companion-f-local-evidence/iphone/setup-candidate.mjs create mode 100644 docs/companion-f-local-evidence/iphone/setup.json create mode 100644 docs/companion-f-local-evidence/iphone/setup.log create mode 100644 docs/companion-f-local-evidence/iphone/ui-readiness.json create mode 100644 docs/companion-f-local-evidence/iphone/ui-readiness.log create mode 100644 docs/companion-f-local-evidence/manifest.json create mode 100644 docs/companion-f-local-evidence/seal-first-failure/original-failure.log create mode 100644 docs/companion-f-local-evidence/seal-first-failure/original-seal.mjs create mode 100644 docs/companion-f-local-evidence/seal-local-evidence.mjs create mode 100644 docs/companion-f-local-evidence/ui/01-companion/original.log create mode 100644 docs/companion-f-local-evidence/ui/01-companion/result.json create mode 100644 docs/companion-f-local-evidence/ui/01-companion/screenshots/01-desktop-certificate.png create mode 100644 docs/companion-f-local-evidence/ui/01-companion/screenshots/02-desktop-pairing.png create mode 100644 docs/companion-f-local-evidence/ui/01-companion/screenshots/03-mobile-task-list.png create mode 100644 docs/companion-f-local-evidence/ui/01-companion/screenshots/04-mobile-original-approval.png create mode 100644 docs/companion-f-local-evidence/ui/01-companion/screenshots/05-mobile-original-diff.png create mode 100644 docs/companion-f-local-evidence/ui/01-companion/screenshots/06-mobile-original-report.png create mode 100644 docs/companion-f-local-evidence/ui/01-companion/screenshots/07-mobile-disconnected.png create mode 100644 docs/companion-f-local-evidence/ui/01-companion/screenshots/08-tablet-task-list.png create mode 100644 docs/companion-f-local-evidence/ui/01-companion/screenshots/09-desktop-management-narrow.png create mode 100644 docs/companion-f-local-evidence/ui/01-companion/screenshots/10-mobile-revoked.png create mode 100644 docs/companion-f-local-evidence/ui/02-controlled/original.log create mode 100644 docs/companion-f-local-evidence/ui/02-controlled/result.json create mode 100644 docs/companion-f-local-evidence/ui/02-controlled/screenshots/01-desktop-controlled-parent.png create mode 100644 docs/companion-f-local-evidence/ui/02-controlled/screenshots/02-mobile-controlled-parent.png create mode 100644 docs/companion-f-local-evidence/ui/02-controlled/screenshots/03-mobile-controlled-input.png create mode 100644 docs/companion-f-local-evidence/ui/02-controlled/screenshots/04-mobile-controlled-approval.png create mode 100644 docs/companion-f-local-evidence/ui/02-controlled/screenshots/05-desktop-controlled-completed.png create mode 100644 docs/companion-f-local-evidence/ui/02-controlled/screenshots/06-mobile-controlled-recovery.png create mode 100644 docs/companion-f-local-evidence/ui/03-purge/original.log create mode 100644 docs/companion-f-local-evidence/ui/03-purge/result.json create mode 100644 docs/companion-f-local-evidence/ui/03-purge/screenshots/01-desktop-purge-source.png create mode 100644 docs/companion-f-local-evidence/ui/03-purge/screenshots/02-mobile-purge-source.png create mode 100644 docs/companion-f-local-evidence/ui/03-purge/screenshots/03-mobile-purge-run.png create mode 100644 docs/companion-f-local-evidence/ui/04-workers/original.log create mode 100644 docs/companion-f-local-evidence/ui/04-workers/result.json create mode 100644 docs/companion-f-local-evidence/ui/04-workers/screenshots/01-mobile-worker-plan.png create mode 100644 docs/companion-f-local-evidence/ui/04-workers/screenshots/02-desktop-workers-collected.png create mode 100644 docs/companion-f-local-evidence/ui/04-workers/screenshots/03-mobile-workers-conflict.png create mode 100644 docs/companion-f-local-evidence/ui/04-workers/screenshots/04-mobile-workers-recovery-retained.png create mode 100644 docs/companion-f-local-evidence/ui/05-task-plans/original.log create mode 100644 docs/companion-f-local-evidence/ui/05-task-plans/result.json create mode 100644 docs/companion-f-local-evidence/ui/05-task-plans/screenshots/01-task-plan-desktop-editor.png create mode 100644 docs/companion-f-local-evidence/ui/05-task-plans/screenshots/02-task-plan-desktop-verified.png create mode 100644 docs/companion-f-local-evidence/ui/05-task-plans/screenshots/03-task-plan-mobile-editor.png create mode 100644 docs/companion-f-local-evidence/ui/05-task-plans/screenshots/04-task-plan-mobile-artifact.png create mode 100644 docs/companion-f-local-evidence/ui/05-task-plans/screenshots/05-task-plan-mobile-steps.png create mode 100644 docs/companion-f-local-evidence/ui/05-task-plans/screenshots/06-task-plan-mobile-overview.png create mode 100644 docs/companion-f-local-evidence/ui/06-browser/original.log create mode 100644 docs/companion-f-local-evidence/ui/06-browser/result.json create mode 100644 docs/companion-f-local-evidence/ui/06-browser/screenshots/01-browser-desktop-results.png create mode 100644 docs/companion-f-local-evidence/ui/06-browser/screenshots/02-browser-desktop-original-image.png create mode 100644 docs/companion-f-local-evidence/ui/06-browser/screenshots/03-browser-mobile-results.png create mode 100644 docs/companion-f-local-evidence/ui/06-browser/screenshots/04-browser-mobile-original-image.png create mode 100644 docs/companion-f-local-evidence/ui/07-ui/original.log create mode 100644 docs/companion-f-local-evidence/ui/07-ui/result.json create mode 100644 docs/companion-f-local-evidence/ui/08-diagnostics/original.log create mode 100644 docs/companion-f-local-evidence/ui/08-diagnostics/result.json create mode 100644 docs/companion-f-local-evidence/ui/09-execution/original.log create mode 100644 docs/companion-f-local-evidence/ui/09-execution/result.json create mode 100644 docs/companion-f-local-evidence/ui/10-delivery/original.log create mode 100644 docs/companion-f-local-evidence/ui/10-delivery/result.json create mode 100644 docs/companion-f-local-evidence/ui/11-index/original.log create mode 100644 docs/companion-f-local-evidence/ui/11-index/result.json create mode 100644 docs/companion-f-local-evidence/ui/12-change-sets/original.log create mode 100644 docs/companion-f-local-evidence/ui/12-change-sets/result.json create mode 100644 docs/companion-f-local-evidence/ui/12-change-sets/screenshots/01-mobile-companion-batch-desktop-review.png create mode 100644 docs/companion-f-local-evidence/ui/12-change-sets/screenshots/02-mobile-companion-batch-desktop-conflict.png create mode 100644 docs/companion-f-local-evidence/ui/12-change-sets/screenshots/03-mobile-companion-batch-desktop-recovery.png create mode 100644 docs/companion-f-local-evidence/ui/12-change-sets/screenshots/04-mobile-companion-batch-mobile-review.png create mode 100644 docs/companion-f-local-evidence/ui/12-change-sets/screenshots/05-mobile-companion-batch-mobile-rollback.png create mode 100644 docs/companion-f-local-evidence/ui/13-context/original.log create mode 100644 docs/companion-f-local-evidence/ui/13-context/result.json create mode 100644 docs/companion-f-local-evidence/ui/13-context/screenshots/01-mobile-companion-desktop-plan.png create mode 100644 docs/companion-f-local-evidence/ui/13-context/screenshots/02-mobile-companion-desktop-history.png create mode 100644 docs/companion-f-local-evidence/ui/13-context/screenshots/03-mobile-companion-mobile-history.png create mode 100644 docs/companion-f-local-evidence/ui/13-context/screenshots/04-mobile-companion-mobile-original.png create mode 100644 docs/companion-f-local-evidence/ui/13-context/screenshots/05-mobile-companion-mobile-request-body.png create mode 100644 docs/companion-f-local-evidence/ui/13-context/screenshots/06-mobile-companion-mobile-read-pause.png create mode 100644 docs/companion-f-local-evidence/ui/13-context/screenshots/07-mobile-companion-desktop-working-evidence.png create mode 100644 docs/companion-f-local-evidence/ui/13-context/screenshots/08-mobile-companion-mobile-working-evidence.png create mode 100644 docs/companion-f-local-evidence/ui/14-workspaces/original.log create mode 100644 docs/companion-f-local-evidence/ui/14-workspaces/result.json create mode 100644 docs/companion-f-local-evidence/ui/14-workspaces/screenshots/01-mobile-companion-workspaces-review-desktop.png create mode 100644 docs/companion-f-local-evidence/ui/14-workspaces/screenshots/02-mobile-companion-workspaces-ready-desktop.png create mode 100644 docs/companion-f-local-evidence/ui/14-workspaces/screenshots/03-mobile-companion-workspaces-recovery-desktop.png create mode 100644 docs/companion-f-local-evidence/ui/14-workspaces/screenshots/04-mobile-companion-workspaces-review-mobile.png create mode 100644 docs/companion-f-local-evidence/ui/14-workspaces/screenshots/05-mobile-companion-workspaces-child-mobile.png create mode 100644 docs/companion-f-local-evidence/ui/15-python/original.log create mode 100644 docs/companion-f-local-evidence/ui/15-python/result.json create mode 100644 docs/companion-f-local-evidence/ui/16-react-delivery/original.log create mode 100644 docs/companion-f-local-evidence/ui/16-react-delivery/result.json create mode 100644 docs/companion-f-local-evidence/ui/17-research/original.log create mode 100644 docs/companion-f-local-evidence/ui/17-research/result.json create mode 100644 docs/companion-f-local-evidence/ui/17-research/screenshots/01-mobile-companion-research-desktop.png create mode 100644 docs/companion-f-local-evidence/ui/17-research/screenshots/02-mobile-companion-research-mobile.png create mode 100644 docs/companion-f-local-evidence/ui/17-research/screenshots/03-mobile-companion-research-evidence-mobile.png create mode 100644 docs/companion-f-local-evidence/ui/17-research/screenshots/04-mobile-companion-research-stop-desktop.png create mode 100644 docs/companion-f-local-evidence/ui/18-engines/original.log create mode 100644 docs/companion-f-local-evidence/ui/18-engines/result.json create mode 100644 docs/companion-f-local-evidence/ui/18-engines/screenshots/01-engines-native-desktop.png create mode 100644 docs/companion-f-local-evidence/ui/18-engines/screenshots/02-engines-record-mobile.png create mode 100644 docs/companion-f-local-evidence/ui/18-engines/screenshots/03-engines-native-mobile.png create mode 100644 docs/companion-f-local-evidence/ui/19-model-center/original.log create mode 100644 docs/companion-f-local-evidence/ui/19-model-center/result.json create mode 100644 docs/companion-f-local-evidence/ui/19-model-center/screenshots/01-desktop-operations.png create mode 100644 docs/companion-f-local-evidence/ui/19-model-center/screenshots/02-mobile-operations.png create mode 100644 docs/companion-f-local-evidence/ui/19-model-center/screenshots/03-mobile-connections.png create mode 100644 docs/companion-f-local-evidence/ui/20-project-memory/original.log create mode 100644 docs/companion-f-local-evidence/ui/20-project-memory/result.json create mode 100644 docs/companion-f-local-evidence/ui/20-project-memory/screenshots/01-desktop-expired-memory.png create mode 100644 docs/companion-f-local-evidence/ui/20-project-memory/screenshots/02-mobile-incomplete-memory.png create mode 100644 docs/companion-f-local-evidence/ui/20-project-memory/screenshots/03-desktop-sent-memory.png create mode 100644 docs/companion-f-local-evidence/ui/20-project-memory/screenshots/04-mobile-sent-memory.png create mode 100644 docs/companion-f-local-evidence/ui/21-task-checkpoints/original.log create mode 100644 docs/companion-f-local-evidence/ui/21-task-checkpoints/result.json create mode 100644 docs/companion-f-local-evidence/ui/21-task-checkpoints/screenshots/01-desktop-original-checkpoint.png create mode 100644 docs/companion-f-local-evidence/ui/21-task-checkpoints/screenshots/02-mobile-checkpoint-ready.png create mode 100644 docs/companion-f-local-evidence/ui/22-skills/original.log create mode 100644 docs/companion-f-local-evidence/ui/22-skills/result.json create mode 100644 docs/companion-f-local-evidence/ui/22-skills/screenshots/01-desktop-skill-source.png create mode 100644 docs/companion-f-local-evidence/ui/22-skills/screenshots/02-mobile-skill-source.png create mode 100644 docs/companion-f-local-evidence/ui/22-skills/screenshots/03-desktop-sent-skill-catalog.png create mode 100644 docs/companion-f-local-evidence/ui/23-mcp/original.log create mode 100644 docs/companion-f-local-evidence/ui/23-mcp/result.json create mode 100644 docs/companion-f-local-evidence/ui/23-mcp/screenshots/01-desktop-mcp-registry.png create mode 100644 docs/companion-f-local-evidence/ui/23-mcp/screenshots/02-mobile-mcp-registry.png create mode 100644 docs/companion-f-local-evidence/ui/24-mcp-recovery/original.log create mode 100644 docs/companion-f-local-evidence/ui/24-mcp-recovery/result.json create mode 100644 docs/companion-f-local-evidence/ui/24-mcp-recovery/screenshots/01-desktop-mcp-interrupted-input.png create mode 100644 docs/companion-f-local-evidence/ui/24-mcp-recovery/screenshots/02-mobile-mcp-interrupted-input.png create mode 100644 docs/companion-f-local-evidence/ui/24-mcp-recovery/screenshots/03-mobile-mcp-review.png create mode 100644 docs/mobile-companion-all-ui-validation.json create mode 100644 docs/mobile-companion-basic-ui-validation.json create mode 100644 docs/mobile-companion-batch-ui-validation.json create mode 100644 docs/mobile-companion-browser-ui-validation.json create mode 100644 docs/mobile-companion-change-sets-ui-validation.json create mode 100644 docs/mobile-companion-companion-ui-validation.json create mode 100644 docs/mobile-companion-context-ui-validation.json create mode 100644 docs/mobile-companion-controlled-final-ui-validation.json create mode 100644 docs/mobile-companion-delivery-ui-validation.json create mode 100644 docs/mobile-companion-diagnostics-ui-validation.json create mode 100644 docs/mobile-companion-engines-ui-validation.json create mode 100644 docs/mobile-companion-execution-ui-validation.json create mode 100644 docs/mobile-companion-index-ui-validation.json create mode 100644 docs/mobile-companion-iphone-readiness.json create mode 100644 docs/mobile-companion-mcp-recovery-ui-validation.json create mode 100644 docs/mobile-companion-mcp-ui-validation.json create mode 100644 docs/mobile-companion-model-center-ui-validation.json create mode 100644 docs/mobile-companion-project-memory-ui-validation.json create mode 100644 docs/mobile-companion-purge-final-ui-validation.json create mode 100644 docs/mobile-companion-python-ui-validation.json create mode 100644 docs/mobile-companion-react-delivery-validation.json create mode 100644 docs/mobile-companion-research-ui-validation.json create mode 100644 docs/mobile-companion-skills-ui-validation.json create mode 100644 docs/mobile-companion-task-checkpoints-ui-validation.json create mode 100644 docs/mobile-companion-task-ui-validation.json create mode 100644 docs/mobile-companion-workers-ui-validation.json create mode 100644 docs/mobile-companion-workspaces-ui-validation.json diff --git a/.gitattributes b/.gitattributes index bafc6632..d4286892 100644 --- a/.gitattributes +++ b/.gitattributes @@ -9,6 +9,12 @@ docs/companion-c-e-evidence/**/*.tap binary docs/companion-c-e-evidence/*.tap binary docs/companion-c-e-evidence/**/*.json -text docs/companion-c-e-evidence/*.json -text +docs/companion-f-local-evidence/** -text +docs/companion-f-local-evidence/**/*.tap binary +docs/companion-f-local-evidence/*.tap binary +docs/companion-f-local-evidence/**/*.log binary +docs/companion-f-local-evidence/*.log binary +docs/mobile-companion-*.json -text whitespace=blank-at-eol,blank-at-eof,space-before-tab,cr-at-eol tests/fixtures/legacy-workbench-0.1/dist-server/server.mjs binary docs/workers-*.tap binary docs/workers-*.log binary diff --git a/.gitignore b/.gitignore index 89adb101..9b936b43 100644 --- a/.gitignore +++ b/.gitignore @@ -9,6 +9,7 @@ /.data/ /.local/ *.log +!/docs/companion-f-local-evidence/**/*.log *.tmp /.qa/ /releases/ diff --git a/AGENTS.md b/AGENTS.md index 535b564f..ad1222ef 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -1,6 +1,6 @@ # Agent Workbench项目执行规范 -1.16在feat/mobile-companion-1.16实施;A/B默认关闭HTTPS网关、Windows DPAPI证书、单次配对/设备授权与脱敏投影已通过54/54本地专项及关联回归,见docs/QA-1.16.md。手机C界面、D真实原Runtime竞争、E断线/撤销和F真实iPhone/独立发行仍分别验收,不能把390px/协议夹具写成真实手机交付。正式1.15宿主保持;新增开发仅使用自有项目/数据/端口,不读取原模型Key。手机根证书需用户手动信任,不自动改OS信任或防火墙。 +1.16在feat/mobile-companion-1.16实施;A/B54/54、C–E新增24/24专项与7组Edge流程通过。来源2ecdfa2当前源码519/519、24类186组历史UI全部通过,313份源码输入和140份原字节证据封存,见docs/QA-1.16.md。版本1.16.0仍为候选;真实iPhone、最终独立源码/完整发行及正式升级仍待完成。独立手机候选使用4320管理与4321 HTTPS、自有示例/数据/Node24;Windows与iPhone通过同局域网Safari/PWA联调,无须Mac,原生iOS分发另议。不能把390px/中继/协议夹具写成真实手机交付。正式1.15宿主保持;不读取原模型Key。手机根证书需用户手动信任,不自动改OS信任或防火墙。 ## 范围与目标 diff --git a/docs/IPHONE-COMPANION.md b/docs/IPHONE-COMPANION.md new file mode 100644 index 00000000..2cfd6318 --- /dev/null +++ b/docs/IPHONE-COMPANION.md @@ -0,0 +1,40 @@ +# 用 Windows 与 iPhone 联调手机伴随端 + +Windows 运行 Agent Workbench 和项目任务,iPhone 用 Safari 查看同一任务、审批和停止。电脑可以接网线,只要手机 Wi-Fi 与电脑所在局域网互通。此方案不需要 Mac;原生 iOS 应用的编译、签名和 App Store 分发需要另外准备 Apple 开发环境。 + +1.16 当前是候选版本。手机真实验收、独立发行和正式升级的状态见 [1.16 验收](QA-1.16.md)。电脑浏览器的窄屏验证不能替代下面的 iPhone 操作。 + +## 首次连接 + +1. 在电脑打开指定的候选工作台,点击「手机连接」。使用当前真实网卡的局域网地址,开启 HTTPS。手机不能使用电脑的 `127.0.0.1` 地址。 +2. 点击「下载手机根证书」,通过自己的文件传输方式把 `.cer` 文件保存到 iPhone。只传公开证书,不传工作台数据目录。 +3. 在 iPhone 打开证书,前往「设置 → 通用 → VPN 与设备管理」安装对应证书描述文件,再在「设置 → 通用 → 关于本机 → 证书信任设置」开启完全信任。核对电脑显示的证书 SHA-256 指纹。 +4. 回到电脑,选择要授权的项目,按需要勾选审批、停止权限,点击「生成一次性配对码」。配对码两分钟内有效,准备好手机后再生成。 +5. 用 iPhone 相机扫码,在 Safari 输入设备名称并连接。电脑应显示这台设备,手机应只显示授权项目。 +6. 在 Safari 的分享菜单选择「添加到主屏幕」,再从主屏幕打开,核对是否保持连接;具体表现按实机结果记录。 + +证书安装入口可能随 iOS 版本略有不同。若文件没有出现安装入口,先记录 iOS 版本和出现的提示,再核对文件传输及证书类型,不通过忽略 HTTPS 警告完成验收。 + +## 联调步骤 + +先使用候选内的离线示例任务;此流程无需模型 Key,也不发送真实模型请求。 + +示例等待超过运行时间预算时会显示暂停。手机准备好后,在电脑核对原记录并显式恢复验收任务;旧审批不会因重新联网自动执行。 + +| 操作 | 核对结果 | +| --- | --- | +| 查看任务详情 | 手机和电脑的 Task / Run 相同,进展和状态一致 | +| 核对文件差异 | 能打开原差异,完整读取后显示 SHA-256 核对结果 | +| 确认待审批命令 | 先核对原命令,再确认;重复点按不产生第二次执行 | +| 锁屏后重新打开 | 恢复同一任务;完成过的工具没有重新执行 | +| 暂时关闭手机 Wi-Fi 再恢复 | 提示断线,重新连接后同步原进展;不创建新 Run | +| 在手机停止自有测试任务 | 电脑同一任务停止,所属进程结束 | +| 在电脑撤销这台设备 | 手机失去项目访问,重新打开仍需重新配对;电脑任务保留 | + +主屏幕应用与 Safari 的会话是否共享,以实际 iOS 表现为准;需要时重新生成一次性配对码,不能复制设备 cookie。 + +## 无法连接时 + +先确认手机与电脑在同一路由网络、候选服务仍运行、电脑「手机连接」里的 HTTPS 地址没有变化。访客 Wi-Fi 或无线设备隔离可能阻止互访。Windows 防火墙规则需由用户针对当前私有网络和指定端口核对;工作台不会自动关闭防火墙。 + +电脑重新启动宿主后需要重新开启手机连接。IP 改变时,重新选择地址开启网关并生成配对码。关闭手机连接只关闭网关,任务仍由 Windows 宿主保留。 diff --git a/docs/NEXT-STEPS.md b/docs/NEXT-STEPS.md index 37d0b19a..3c72cf31 100644 --- a/docs/NEXT-STEPS.md +++ b/docs/NEXT-STEPS.md @@ -1,10 +1,10 @@ # 后续执行计划 -更新:2026-10-31。当前正式1.15.0;当前2连接配置/1池、17项目/29全部会话/2567记录/4599事件,正式纠正升级前后每行/全导出/全部工件原字节保持(相对初始16项目,用户启动新增1个示例并将原列表顺移;体验期间另新增1个空白idle会话及对应1事件,全部原28会话/记录/工件保持);旧PID23172已在恢复检查前退出,用户体验时手动启动1.14/PID36552,随后保留这个进程/Provider升级;旧内存Key不可恢复,需在界面重新填写。Windows桌面、可选本机加密、安装/回退与完整巡检A–F已交付,原失败/当前身份见[QA-1.15](QA-1.15.md)。下一[1.16手机伴随端](PLAN-1.16.md)具体计划保持,真实手机、模型工程/Purge收益及其它能力仍按实际结果分别验收。 +更新:2026-10-31。当前正式1.15.0;以下为1.15交付时核对记录:2连接配置/1池、17项目/29全部会话/2567记录/4599事件,正式纠正升级前后每行/全导出/全部工件原字节保持(相对初始16项目,用户启动新增1个示例并将原列表顺移;体验期间另新增1个空白idle会话及对应1事件,全部原28会话/记录/工件保持);旧PID23172已在恢复检查前退出,用户体验时手动启动1.14/PID36552,随后保留这个进程/Provider升级;旧内存Key不可恢复,需在界面重新填写。Windows桌面、可选本机加密、安装/回退与完整巡检A–F已交付,原失败/身份见[QA-1.15](QA-1.15.md)。[1.16手机伴随端](PLAN-1.16.md)本地实现和当前源码/历史UI已通过,真实手机、最终独立发行及模型工程/Purge收益仍按实际结果分别验收。 产品目标是让用户给出需求后,工作台能保留项目基线,完成定位、计划、修改、检查、必要修复、审查和Git交付,并在停止、故障、断线后明确保留已完成结果。桌面与手机共享同一执行宿主、任务和证据。 -当前接续:1.15完整发行与正式部署已收口,下一进入1.16 A的独立HTTPS配对网关,随后设备权限、手机界面、同Run审批/停止、断线/撤销和真实手机验收。手机与网关仍需实际实现和设备结果,原宿主继续保留现有项目与连接。 +当前接续:1.16 A/B网关与权限、C–E本地手机界面/原审批/停止/断线已实现,24项专项和7组实际Edge流程、当前源码519/519及24类186组历史UI通过。已启动与正式4318隔离的4320/4321 iPhone联调候选;先完成用户手动证书信任、Safari/主屏幕/后台切网/撤销真实验收,再固定完整发行、独立源码/随包与保留状态升级。设备操作说明见[Windows与iPhone联调](IPHONE-COMPANION.md),实时门槛见[QA-1.16](QA-1.16.md)。原宿主继续保留现有项目与连接。 ## 执行顺序与完成门槛 diff --git a/docs/QA-1.16.md b/docs/QA-1.16.md index a81cd3ae..5f009ee5 100644 --- a/docs/QA-1.16.md +++ b/docs/QA-1.16.md @@ -21,3 +21,17 @@ 实际Edge执行7组流程:桌面1440px显式开启/下载证书,390px配对/同一Task/Run审批、实际命令、分页差异、1项真实工程测试和报告SHA;断线/刷新只读恢复;PWA只缓存壳;768px列表和窄屏管理;桌面撤销后手机清空项目内容。7组通过且页面异常0;最终浏览器收据为[原结果](companion-c-e-evidence/final-ui/result.json)。已实际观察原审批、报告和管理页截图,修正虚拟网卡优先、waiting中文、任务全文折叠和对话框视口。原失败独立保留:检查准备分别早于命令收尾/文件审查完成,均由正确409保护拒绝,脚本明确完成原流程后复验。 浏览器验收使用自有loopback QA中继,并逐请求验证真实网关CA,没有安装根证书或绕过TLS警告;测试cookie仅在中继内存,故这些结果**不证明**iPhone Safari原生Secure cookie、系统证书信任和主屏幕PWA已完成。原生iPhone、后台/切网与实际软键盘仍待F。当前尚未发布1.16或升级正式4318。 + +## F:独立 iPhone 联调候选已就绪 + +来源提交`2ecdfa2`的32个程序文件和313份源码输入已冻结到`D:\AWQA16\iphone-ca3891a9\app`,清单逐文件SHA核对;数据单独存放在其同级`data`。通过原HostController启动候选PID33324/Node24.22.1,电脑管理入口`http://127.0.0.1:4320/`,手机入口`https://192.168.66.91:4321/`。电脑可接网线,iPhone须在能互通的同一路由Wi-Fi;Windows与Safari/PWA联调不需要Mac。 + +已用实际公开CA验证网关TLS和原mobile.html完整SHA,未配对访问任务返回401;管理页实际渲染核对6项、页面错误0。公开证书为候选根目录下`Agent-Workbench-Mobile-CA.cer`,SHA-256为`908958fe819dae8ec1527ec0dc352e0282b375d88c370bd2435574edb4e61bd7`。自有离线示例已创建原审批,只读命令为`node --version`;任务预算到期时按实际状态重新核对,不能承诺原审批永久有效。没有读取正式bootstrap/模型Key,没有真实模型请求,没有变更系统信任或防火墙,没有预先生成短效配对票据。 + +启动前后正式health仍为PID36552/1.15.0,本轮仅只读核对health,未执行正式升级。当前是用于实机验收的独立候选,不是最终发行。真实iPhone步骤见[联调指引](IPHONE-COMPANION.md),设备型号/iOS/证书信任、原生cookie、主屏幕、后台/切网、停止和撤销仍待设备证据。原示例在等待时间预算到期后正常暂停,仍保留同一Task/Run;手机准备好后显式恢复,不自动延长预算或重放原命令。[最新就绪复核](mobile-companion-iphone-readiness.json)再次核对32个程序文件SHA、候选和正式PID/版本、原Task/Run及零已配对设备。 + +## 当前源码与完整历史 UI:通过 + +来源`2ecdfa2`的本轮完整源码回归已正常结束,519/519通过,0失败、0取消、0跳过,耗时1247127.7223ms;独立端口/数据的24类历史UI串行全部通过,共186组。完整原TAP、24组原报告/日志和截图、手机候选来源/实际TLS/管理界面及封存器均按原字节保存,共140份、10096575字节,映射和SHA见[封存清单](companion-f-local-evidence/manifest.json)。313份源码输入与候选冻结时的原SHA一致;本轮是当前工作区完整回归,最终完整发行中的独立源码/随包验收仍另外执行。 + +首次封存预检误把`inputs`中的PNG图标路径也当截图,并未识别部分旧报告的截图basename,已在创建输出前拒绝。保留[原脚本和失败日志](companion-f-local-evidence/seal-first-failure/original-failure.log),封存器改为按截图字段及原日志EVIDENCE目录定位,先验证原result.json与保存报告原字节相同,再核对自有QA路径和逐文件SHA。产品源码、原通过测试和原证据均未改写,不重跑已通过测试。真实iPhone与正式发行门槛仍保持待验。 diff --git a/docs/RETROSPECTIVE-1.16.md b/docs/RETROSPECTIVE-1.16.md index ae3e36b7..f887896c 100644 --- a/docs/RETROSPECTIVE-1.16.md +++ b/docs/RETROSPECTIVE-1.16.md @@ -17,3 +17,9 @@ 任务队列/详情围绕原审批、差异、检查和报告组成,避免把桌面编辑器缩小到手机。7组实际宽窄屏流程与24项专项通过。实际原Runtime命令/进程检验证明操作归属和停止结果;浏览器截图只能证明页面结果,原生Safari证书/cookie与PWA留给真实iPhone,测试中继身份清楚记录。 两次UI检查均由产品正确409保护拒绝,原因分别是脚本过早开始检查、未审查待应用文件;补全原流程后通过。回顾发现WSL网卡默认地址会误导用户,已优先真实网卡;操作请求ID固定于一次确认,未知回执持久查询,刷新不再丢失。设备授权/日期登记损坏时明确拒绝并保留原数据,不把格式问题降级为永久授权。发行前继续全量回归和独立实机候选,正式4318保持原状。 + +## 独立手机候选回顾 + +用户核对Windows能否联调iPhone。实际方案是Windows运行HTTPS宿主、iPhone Safari/PWA接续同一任务,无须引入Mac或原生打包链。独立候选冻结当前源码/构建/Node并用完整清单核对,程序与自有示例数据分离;4320/4321不替换正式4318。候选真实TLS和管理页面就绪已观察,手机手动信任及实际操作尚未发生,状态明确保留待验。网络复核发现无线接口保留地址但未连接,选择已有默认网关的真实以太网;手机能否经Wi-Fi互访仍以实机为准。 + +当前源码519/519与24类186组历史UI完整通过,140份原字节证据和313源码输入已核对封存。封存首次预检拒绝暴露报告格式差异:输入图标不等于截图、旧报告使用basename;依据原日志EVIDENCE目录及原报告SHA定位,未改原报告或放宽自有路径边界。封存工具修正不触发产品整轮重跑。独立手机样例因等候超过原预算而暂停,原Task/Run保持,说明联调也需尊重原执行期限;实机准备后显式恢复,不能让示例永久自动续期。下一步保持真实iPhone→最终独立源码/完整发行→保留状态正式升级的顺序。 diff --git a/docs/companion-f-local-evidence/all-ui.json b/docs/companion-f-local-evidence/all-ui.json new file mode 100644 index 00000000..35fa4edd --- /dev/null +++ b/docs/companion-f-local-evidence/all-ui.json @@ -0,0 +1,201 @@ +{ + "success": true, + "version": "1.16.0", + "at": "2026-10-31T10:07:14.345Z", + "groups": 186, + "results": [ + { + "script": "verify-companion-ui.mjs", + "success": true, + "groups": 7, + "durationMs": 17070, + "evidence": "docs/mobile-companion-companion-ui-validation.json", + "log": ".qa/mobile-companion-verify-companion-ui.log" + }, + { + "script": "verify-controlled-ui.mjs", + "success": true, + "groups": 9, + "durationMs": 68197, + "evidence": "docs/mobile-companion-controlled-final-ui-validation.json", + "log": ".qa/mobile-companion-verify-controlled-ui.log" + }, + { + "script": "verify-purge-ui.mjs", + "success": true, + "groups": 9, + "durationMs": 26458, + "evidence": "docs/mobile-companion-purge-final-ui-validation.json", + "log": ".qa/mobile-companion-verify-purge-ui.log" + }, + { + "script": "verify-workers-ui.mjs", + "success": true, + "groups": 10, + "durationMs": 137416, + "evidence": "docs/mobile-companion-workers-ui-validation.json", + "log": ".qa/mobile-companion-verify-workers-ui.log" + }, + { + "script": "verify-task-plans-ui.mjs", + "success": true, + "groups": 8, + "durationMs": 16344, + "evidence": "docs/mobile-companion-task-ui-validation.json", + "log": ".qa/mobile-companion-verify-task-plans-ui.log" + }, + { + "script": "verify-browser-ui.mjs", + "success": true, + "groups": 10, + "durationMs": 26332, + "evidence": "docs/mobile-companion-browser-ui-validation.json", + "log": ".qa/mobile-companion-verify-browser-ui.log" + }, + { + "script": "verify-ui.mjs", + "success": true, + "groups": 10, + "durationMs": 25812, + "evidence": "docs/mobile-companion-basic-ui-validation.json", + "log": ".qa/mobile-companion-verify-ui.log" + }, + { + "script": "verify-diagnostics-ui.mjs", + "success": true, + "groups": 9, + "durationMs": 27995, + "evidence": "docs/mobile-companion-diagnostics-ui-validation.json", + "log": ".qa/mobile-companion-verify-diagnostics-ui.log" + }, + { + "script": "verify-execution-ui.mjs", + "success": true, + "groups": 7, + "durationMs": 34911, + "evidence": "docs/mobile-companion-execution-ui-validation.json", + "log": ".qa/mobile-companion-verify-execution-ui.log" + }, + { + "script": "verify-delivery-ui.mjs", + "success": true, + "groups": 9, + "durationMs": 54080, + "evidence": "docs/mobile-companion-delivery-ui-validation.json", + "log": ".qa/mobile-companion-verify-delivery-ui.log" + }, + { + "script": "verify-index-ui.mjs", + "success": true, + "groups": 8, + "durationMs": 7922, + "evidence": "docs/mobile-companion-index-ui-validation.json", + "log": ".qa/mobile-companion-verify-index-ui.log" + }, + { + "script": "verify-change-sets-ui.mjs", + "success": true, + "groups": 11, + "durationMs": 18208, + "evidence": "docs/mobile-companion-change-sets-ui-validation.json", + "log": ".qa/mobile-companion-verify-change-sets-ui.log" + }, + { + "script": "verify-context-ui.mjs", + "success": true, + "groups": 11, + "durationMs": 24828, + "evidence": "docs/mobile-companion-context-ui-validation.json", + "log": ".qa/mobile-companion-verify-context-ui.log" + }, + { + "script": "verify-workspaces-ui.mjs", + "success": true, + "groups": 9, + "durationMs": 29044, + "evidence": "docs/mobile-companion-workspaces-ui-validation.json", + "log": ".qa/mobile-companion-verify-workspaces-ui.log" + }, + { + "script": "verify-python-ui.mjs", + "success": true, + "groups": 7, + "durationMs": 25892, + "evidence": "docs/mobile-companion-python-ui-validation.json", + "log": ".qa/mobile-companion-verify-python-ui.log" + }, + { + "script": "verify-react-delivery.mjs", + "success": true, + "groups": 6, + "durationMs": 46955, + "evidence": "docs/mobile-companion-react-delivery-validation.json", + "log": ".qa/mobile-companion-verify-react-delivery.log" + }, + { + "script": "verify-research-ui.mjs", + "success": true, + "groups": 11, + "durationMs": 29511, + "evidence": "docs/mobile-companion-research-ui-validation.json", + "log": ".qa/mobile-companion-verify-research-ui.log" + }, + { + "script": "verify-engines-ui.mjs", + "success": true, + "groups": 10, + "durationMs": 13824, + "evidence": "docs/mobile-companion-engines-ui-validation.json", + "log": ".qa/mobile-companion-verify-engines-ui.log" + }, + { + "script": "verify-model-center-ui.mjs", + "success": true, + "groups": 6, + "durationMs": 12791, + "evidence": "docs/mobile-companion-model-center-ui-validation.json", + "log": ".qa/mobile-companion-verify-model-center-ui.log" + }, + { + "script": "verify-project-memory-ui.mjs", + "success": true, + "groups": 4, + "durationMs": 8218, + "evidence": "docs/mobile-companion-project-memory-ui-validation.json", + "log": ".qa/mobile-companion-verify-project-memory-ui.log" + }, + { + "script": "verify-task-checkpoints-ui.mjs", + "success": true, + "groups": 3, + "durationMs": 9730, + "evidence": "docs/mobile-companion-task-checkpoints-ui-validation.json", + "log": ".qa/mobile-companion-verify-task-checkpoints-ui.log" + }, + { + "script": "verify-skills-ui.mjs", + "success": true, + "groups": 4, + "durationMs": 8764, + "evidence": "docs/mobile-companion-skills-ui-validation.json", + "log": ".qa/mobile-companion-verify-skills-ui.log" + }, + { + "script": "verify-mcp-ui.mjs", + "success": true, + "groups": 6, + "durationMs": 13201, + "evidence": "docs/mobile-companion-mcp-ui-validation.json", + "log": ".qa/mobile-companion-verify-mcp-ui.log" + }, + { + "script": "verify-mcp-recovery-ui.mjs", + "success": true, + "groups": 2, + "durationMs": 9467, + "evidence": "docs/mobile-companion-mcp-recovery-ui-validation.json", + "log": ".qa/mobile-companion-verify-mcp-recovery-ui.log" + } + ], + "scope": "Every verifier owns an independent port and synthetic data directory. Synthetic provider fixtures verify protocols; configured-model acceptance is separate. No production service or real key read/copied." +} diff --git a/docs/companion-f-local-evidence/all-ui.log b/docs/companion-f-local-evidence/all-ui.log new file mode 100644 index 00000000..2b91d5b9 --- /dev/null +++ b/docs/companion-f-local-evidence/all-ui.log @@ -0,0 +1,249 @@ +UI regression: verify-companion-ui.mjs +PASS verify-companion-ui.mjs: 7 groups +UI regression: verify-controlled-ui.mjs +PASS verify-controlled-ui.mjs: 9 groups +UI regression: verify-purge-ui.mjs +PASS verify-purge-ui.mjs: 9 groups +UI regression: verify-workers-ui.mjs +PASS verify-workers-ui.mjs: 10 groups +UI regression: verify-task-plans-ui.mjs +PASS verify-task-plans-ui.mjs: 8 groups +UI regression: verify-browser-ui.mjs +PASS verify-browser-ui.mjs: 10 groups +UI regression: verify-ui.mjs +PASS verify-ui.mjs: 10 groups +UI regression: verify-diagnostics-ui.mjs +PASS verify-diagnostics-ui.mjs: 9 groups +UI regression: verify-execution-ui.mjs +PASS verify-execution-ui.mjs: 7 groups +UI regression: verify-delivery-ui.mjs +PASS verify-delivery-ui.mjs: 9 groups +UI regression: verify-index-ui.mjs +PASS verify-index-ui.mjs: 8 groups +UI regression: verify-change-sets-ui.mjs +PASS verify-change-sets-ui.mjs: 11 groups +UI regression: verify-context-ui.mjs +PASS verify-context-ui.mjs: 11 groups +UI regression: verify-workspaces-ui.mjs +PASS verify-workspaces-ui.mjs: 9 groups +UI regression: verify-python-ui.mjs +PASS verify-python-ui.mjs: 7 groups +UI regression: verify-react-delivery.mjs +PASS verify-react-delivery.mjs: 6 groups +UI regression: verify-research-ui.mjs +PASS verify-research-ui.mjs: 11 groups +UI regression: verify-engines-ui.mjs +PASS verify-engines-ui.mjs: 10 groups +UI regression: verify-model-center-ui.mjs +PASS verify-model-center-ui.mjs: 6 groups +UI regression: verify-project-memory-ui.mjs +PASS verify-project-memory-ui.mjs: 4 groups +UI regression: verify-task-checkpoints-ui.mjs +PASS verify-task-checkpoints-ui.mjs: 3 groups +UI regression: verify-skills-ui.mjs +PASS verify-skills-ui.mjs: 4 groups +UI regression: verify-mcp-ui.mjs +PASS verify-mcp-ui.mjs: 6 groups +UI regression: verify-mcp-recovery-ui.mjs +PASS verify-mcp-recovery-ui.mjs: 2 groups +{ + "success": true, + "version": "1.16.0", + "at": "2026-10-31T10:07:14.345Z", + "groups": 186, + "results": [ + { + "script": "verify-companion-ui.mjs", + "success": true, + "groups": 7, + "durationMs": 17070, + "evidence": "docs/mobile-companion-companion-ui-validation.json", + "log": ".qa/mobile-companion-verify-companion-ui.log" + }, + { + "script": "verify-controlled-ui.mjs", + "success": true, + "groups": 9, + "durationMs": 68197, + "evidence": "docs/mobile-companion-controlled-final-ui-validation.json", + "log": ".qa/mobile-companion-verify-controlled-ui.log" + }, + { + "script": "verify-purge-ui.mjs", + "success": true, + "groups": 9, + "durationMs": 26458, + "evidence": "docs/mobile-companion-purge-final-ui-validation.json", + "log": ".qa/mobile-companion-verify-purge-ui.log" + }, + { + "script": "verify-workers-ui.mjs", + "success": true, + "groups": 10, + "durationMs": 137416, + "evidence": "docs/mobile-companion-workers-ui-validation.json", + "log": ".qa/mobile-companion-verify-workers-ui.log" + }, + { + "script": "verify-task-plans-ui.mjs", + "success": true, + "groups": 8, + "durationMs": 16344, + "evidence": "docs/mobile-companion-task-ui-validation.json", + "log": ".qa/mobile-companion-verify-task-plans-ui.log" + }, + { + "script": "verify-browser-ui.mjs", + "success": true, + "groups": 10, + "durationMs": 26332, + "evidence": "docs/mobile-companion-browser-ui-validation.json", + "log": ".qa/mobile-companion-verify-browser-ui.log" + }, + { + "script": "verify-ui.mjs", + "success": true, + "groups": 10, + "durationMs": 25812, + "evidence": "docs/mobile-companion-basic-ui-validation.json", + "log": ".qa/mobile-companion-verify-ui.log" + }, + { + "script": "verify-diagnostics-ui.mjs", + "success": true, + "groups": 9, + "durationMs": 27995, + "evidence": "docs/mobile-companion-diagnostics-ui-validation.json", + "log": ".qa/mobile-companion-verify-diagnostics-ui.log" + }, + { + "script": "verify-execution-ui.mjs", + "success": true, + "groups": 7, + "durationMs": 34911, + "evidence": "docs/mobile-companion-execution-ui-validation.json", + "log": ".qa/mobile-companion-verify-execution-ui.log" + }, + { + "script": "verify-delivery-ui.mjs", + "success": true, + "groups": 9, + "durationMs": 54080, + "evidence": "docs/mobile-companion-delivery-ui-validation.json", + "log": ".qa/mobile-companion-verify-delivery-ui.log" + }, + { + "script": "verify-index-ui.mjs", + "success": true, + "groups": 8, + "durationMs": 7922, + "evidence": "docs/mobile-companion-index-ui-validation.json", + "log": ".qa/mobile-companion-verify-index-ui.log" + }, + { + "script": "verify-change-sets-ui.mjs", + "success": true, + "groups": 11, + "durationMs": 18208, + "evidence": "docs/mobile-companion-change-sets-ui-validation.json", + "log": ".qa/mobile-companion-verify-change-sets-ui.log" + }, + { + "script": "verify-context-ui.mjs", + "success": true, + "groups": 11, + "durationMs": 24828, + "evidence": "docs/mobile-companion-context-ui-validation.json", + "log": ".qa/mobile-companion-verify-context-ui.log" + }, + { + "script": "verify-workspaces-ui.mjs", + "success": true, + "groups": 9, + "durationMs": 29044, + "evidence": "docs/mobile-companion-workspaces-ui-validation.json", + "log": ".qa/mobile-companion-verify-workspaces-ui.log" + }, + { + "script": "verify-python-ui.mjs", + "success": true, + "groups": 7, + "durationMs": 25892, + "evidence": "docs/mobile-companion-python-ui-validation.json", + "log": ".qa/mobile-companion-verify-python-ui.log" + }, + { + "script": "verify-react-delivery.mjs", + "success": true, + "groups": 6, + "durationMs": 46955, + "evidence": "docs/mobile-companion-react-delivery-validation.json", + "log": ".qa/mobile-companion-verify-react-delivery.log" + }, + { + "script": "verify-research-ui.mjs", + "success": true, + "groups": 11, + "durationMs": 29511, + "evidence": "docs/mobile-companion-research-ui-validation.json", + "log": ".qa/mobile-companion-verify-research-ui.log" + }, + { + "script": "verify-engines-ui.mjs", + "success": true, + "groups": 10, + "durationMs": 13824, + "evidence": "docs/mobile-companion-engines-ui-validation.json", + "log": ".qa/mobile-companion-verify-engines-ui.log" + }, + { + "script": "verify-model-center-ui.mjs", + "success": true, + "groups": 6, + "durationMs": 12791, + "evidence": "docs/mobile-companion-model-center-ui-validation.json", + "log": ".qa/mobile-companion-verify-model-center-ui.log" + }, + { + "script": "verify-project-memory-ui.mjs", + "success": true, + "groups": 4, + "durationMs": 8218, + "evidence": "docs/mobile-companion-project-memory-ui-validation.json", + "log": ".qa/mobile-companion-verify-project-memory-ui.log" + }, + { + "script": "verify-task-checkpoints-ui.mjs", + "success": true, + "groups": 3, + "durationMs": 9730, + "evidence": "docs/mobile-companion-task-checkpoints-ui-validation.json", + "log": ".qa/mobile-companion-verify-task-checkpoints-ui.log" + }, + { + "script": "verify-skills-ui.mjs", + "success": true, + "groups": 4, + "durationMs": 8764, + "evidence": "docs/mobile-companion-skills-ui-validation.json", + "log": ".qa/mobile-companion-verify-skills-ui.log" + }, + { + "script": "verify-mcp-ui.mjs", + "success": true, + "groups": 6, + "durationMs": 13201, + "evidence": "docs/mobile-companion-mcp-ui-validation.json", + "log": ".qa/mobile-companion-verify-mcp-ui.log" + }, + { + "script": "verify-mcp-recovery-ui.mjs", + "success": true, + "groups": 2, + "durationMs": 9467, + "evidence": "docs/mobile-companion-mcp-recovery-ui-validation.json", + "log": ".qa/mobile-companion-verify-mcp-recovery-ui.log" + } + ], + "scope": "Every verifier owns an independent port and synthetic data directory. Synthetic provider fixtures verify protocols; configured-model acceptance is separate. No production service or real key read/copied." +} diff --git a/docs/companion-f-local-evidence/full-source.tap b/docs/companion-f-local-evidence/full-source.tap new file mode 100644 index 00000000..002fb981 --- /dev/null +++ b/docs/companion-f-local-evidence/full-source.tap @@ -0,0 +1,3131 @@ +TAP version 13 +# Subtest: the bundled local service enforces host, origin, token and JSON object contracts +ok 1 - the bundled local service enforces host, origin, token and JSON object contracts + --- + duration_ms: 2276.5119 + type: 'test' + ... +# Subtest: an in-flight connection probe prevents configuration changes and another probe until its actual result returns +ok 2 - an in-flight connection probe prevents configuration changes and another probe until its actual result returns + --- + duration_ms: 2590.8475 + type: 'test' + ... +# Subtest: API review applies verified content, detects conflicts, exports sessions and keeps keys in memory +ok 3 - API review applies verified content, detects conflicts, exports sessions and keeps keys in memory + --- + duration_ms: 4599.7375 + type: 'test' + ... +# Subtest: a real bundle restart preserves proposals, interrupts old approvals and requests fresh consent on resume +ok 4 - a real bundle restart preserves proposals, interrupts old approvals and requests fresh consent on resume + --- + duration_ms: 10887.624 + type: 'test' + ... +# Subtest: runtime diagnostics and model-response validation use actual records and preserve the saved connection +ok 5 - runtime diagnostics and model-response validation use actual records and preserve the saved connection + --- + duration_ms: 2072.6035 + type: 'test' + ... +# Subtest: persistent event replay is read-only and keeps run/artifact identity across reconnects +ok 6 - persistent event replay is read-only and keeps run/artifact identity across reconnects + --- + duration_ms: 7180.6788 + type: 'test' + ... +# Subtest: real browser HTTP plans, original field pages and PNG bytes preserve ownership and survive host restart +ok 7 - real browser HTTP plans, original field pages and PNG bytes preserve ownership and survive host restart + --- + duration_ms: 8258.0795 + type: 'test' + ... +# Subtest: self harness browser tools require approval and feed verified actual page fields back to the original Task +ok 8 - self harness browser tools require approval and feed verified actual page fields back to the original Task + --- + duration_ms: 11399.3394 + type: 'test' + ... +# Subtest: browser host recovery retains unknown root outcome, blocks replay, and requires an explicit owned acknowledgement +ok 9 - browser host recovery retains unknown root outcome, blocks replay, and requires an explicit owned acknowledgement + --- + duration_ms: 4383.024 + type: 'test' + ... +# Subtest: late HTTP stop of a finished browser job cannot interrupt a later job in the same Task +ok 10 - late HTTP stop of a finished browser job cannot interrupt a later job in the same Task + --- + duration_ms: 8205.5647 + type: 'test' + ... +# Subtest: actual failed page blocks source-passed delivery; a new passing page permits a bound commit and preserves both original records +ok 11 - actual failed page blocks source-passed delivery; a new passing page permits a bound commit and preserves both original records + --- + duration_ms: 18436.9181 + type: 'test' + ... +# Subtest: a build-only change after Git review invalidates the actual browser evidence and leaves HEAD and the protected index intact +ok 12 - a build-only change after Git review invalidates the actual browser evidence and leaves HEAD and the protected index intact + --- + duration_ms: 8662.2399 + type: 'test' + ... +# Subtest: actual DOM controls include validated unique CSS selectors across repeated parent buttons and escaped labels +ok 13 - actual DOM controls include validated unique CSS selectors across repeated parent buttons and escaped labels + --- + duration_ms: 9570.7452 + type: 'test' + ... +# Subtest: browser field coverage distinguishes sections and Run windows while retaining original source identity +ok 14 - browser field coverage distinguishes sections and Run windows while retaining original source identity + --- + duration_ms: 0.8316 + type: 'test' + ... +# Subtest: repeated original browser pages pause a live Task without re-opening the browser or breaking tool pairing +ok 15 - repeated original browser pages pause a live Task without re-opening the browser or breaking tool pairing + --- + duration_ms: 5075.5441 + type: 'test' + ... +# Subtest: browser plan rejects outside builds, invalid interaction scope and unbounded steps before execution +ok 16 - browser plan rejects outside builds, invalid interaction scope and unbounded steps before execution + --- + duration_ms: 0.9929 + type: 'test' + ... +# Subtest: real owned Edge interactions, assertions, raw PNG and stopped process survive exact result reuse and host reopen +ok 17 - real owned Edge interactions, assertions, raw PNG and stopped process survive exact result reuse and host reopen + --- + duration_ms: 4056.4515 + type: 'test' + ... +# Subtest: failed real page assertion preserves actual value and forbids silent retry of the original plan +ok 18 - failed real page assertion preserves actual value and forbids silent retry of the original plan + --- + duration_ms: 8614.662 + type: 'test' + ... +# Subtest: build/source mutation and sealed step tampering reject before browser dispatch; earlier task cannot execute plan +ok 19 - build/source mutation and sealed step tampering reject before browser dispatch; earlier task cannot execute plan + --- + duration_ms: 1774.6137 + type: 'test' + ... +# Subtest: outside network never reaches another local service, and original JavaScript/console failures remain failures +ok 20 - outside network never reaches another local service, and original JavaScript/console failures remain failures + --- + duration_ms: 2931.6716 + type: 'test' + ... +# Subtest: stopping a real in-flight browser preserves finished steps, closes its owned root and never replays +ok 21 - stopping a real in-flight browser preserves finished steps, closes its owned root and never replays + --- + duration_ms: 3125.7164 + type: 'test' + ... +# Subtest: 原PNG损坏使原结果校验失败,不能以已有通过状态复用 +ok 22 - 原PNG损坏使原结果校验失败,不能以已有通过状态复用 + --- + duration_ms: 3372.6915 + type: 'test' + ... +# Subtest: batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart +ok 23 - batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart + --- + duration_ms: 6053.7387 + type: 'test' + ... +# Subtest: delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files +ok 24 - delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files + --- + duration_ms: 3841.7562 + type: 'test' + ... +# Subtest: a compatible model can seal proposals through the real HTTP loop while application stays behind user review +ok 25 - a compatible model can seal proposals through the real HTTP loop while application stays behind user review + --- + duration_ms: 7548.2802 + type: 'test' + ... +# Subtest: a step-limited sealed batch applies and continues the same Task into actual checks without replaying saved tools +ok 26 - a step-limited sealed batch applies and continues the same Task into actual checks without replaying saved tools + --- + duration_ms: 16053.4263 + type: 'test' + ... +# Subtest: applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation +ok 27 - applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation + --- + duration_ms: 2284.7039 + type: 'test' + ... +# Subtest: actual process exit at file-batch prepared preserves durable identity and never replays writes +ok 28 - actual process exit at file-batch prepared preserves durable identity and never replays writes + --- + duration_ms: 2296.881 + type: 'test' + ... +# Subtest: actual process exit at file-batch application_started preserves durable identity and never replays writes +ok 29 - actual process exit at file-batch application_started preserves durable identity and never replays writes + --- + duration_ms: 2258.7437 + type: 'test' + ... +# Subtest: actual process exit at file-batch write_intent preserves durable identity and never replays writes +ok 30 - actual process exit at file-batch write_intent preserves durable identity and never replays writes + --- + duration_ms: 1753.382 + type: 'test' + ... +# Subtest: actual process exit at file-batch staged preserves durable identity and never replays writes +ok 31 - actual process exit at file-batch staged preserves durable identity and never replays writes + --- + duration_ms: 2735.0214 + type: 'test' + ... +# Subtest: actual process exit at file-batch replaced preserves durable identity and never replays writes +ok 32 - actual process exit at file-batch replaced preserves durable identity and never replays writes + --- + duration_ms: 2881.4415 + type: 'test' + ... +# Subtest: actual process exit at file-batch file_recorded preserves durable identity and never replays writes +ok 33 - actual process exit at file-batch file_recorded preserves durable identity and never replays writes + --- + duration_ms: 3307.6524 + type: 'test' + ... +# Subtest: actual process exit at file-batch finished preserves durable identity and never replays writes +ok 34 - actual process exit at file-batch finished preserves durable identity and never replays writes + --- + duration_ms: 2794.5632 + type: 'test' + ... +# Subtest: actual process exit at file-batch rollback_started preserves durable identity and never replays writes +ok 35 - actual process exit at file-batch rollback_started preserves durable identity and never replays writes + --- + duration_ms: 3438.368 + type: 'test' + ... +# Subtest: actual process exit at file-batch restore_intent preserves durable identity and never replays writes +ok 36 - actual process exit at file-batch restore_intent preserves durable identity and never replays writes + --- + duration_ms: 3854.6676 + type: 'test' + ... +# Subtest: actual process exit at file-batch restore_staged preserves durable identity and never replays writes +ok 37 - actual process exit at file-batch restore_staged preserves durable identity and never replays writes + --- + duration_ms: 3957.0325 + type: 'test' + ... +# Subtest: actual process exit at file-batch restored preserves durable identity and never replays writes +ok 38 - actual process exit at file-batch restored preserves durable identity and never replays writes + --- + duration_ms: 4006.842 + type: 'test' + ... +# Subtest: actual process exit at file-batch restore_recorded preserves durable identity and never replays writes +ok 39 - actual process exit at file-batch restore_recorded preserves durable identity and never replays writes + --- + duration_ms: 4178.3445 + type: 'test' + ... +# Subtest: actual process exit at file-batch rollback_finished preserves durable identity and never replays writes +ok 40 - actual process exit at file-batch rollback_finished preserves durable identity and never replays writes + --- + duration_ms: 3525.2511 + type: 'test' + ... +# warning: in the working copy of 'README.md', LF will be replaced by CRLF the next time Git touches it +# warning: in the working copy of 'src/two.mjs', LF will be replaced by CRLF the next time Git touches it +# Subtest: sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files +ok 41 - sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files + --- + duration_ms: 2658.2568 + type: 'test' + ... +# Switched to a new branch 'owner-branch' +# Subtest: a conflict in the last file or Git branch prevents writing every file in the batch +ok 42 - a conflict in the last file or Git branch prevents writing every file in the batch + --- + duration_ms: 3618.252 + type: 'test' + ... +# Subtest: duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch +ok 43 - duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch + --- + duration_ms: 1686.6648 + type: 'test' + ... +# Subtest: fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target +ok 44 - fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target + --- + duration_ms: 3374.5129 + type: 'test' + ... +# Subtest: a failure after replacement restores only batch bytes and never retries an old application +ok 45 - a failure after replacement restores only batch bytes and never retries an old application + --- + duration_ms: 2548.9706 + type: 'test' + ... +# Subtest: rollback preserves owner edits, blocks other project writers, and explicit acknowledgement releases recovery +ok 46 - rollback preserves owner edits, blocks other project writers, and explicit acknowledgement releases recovery + --- + duration_ms: 2882.1989 + type: 'test' + ... +# Subtest: an unattempted owner-created file identical to a suggestion remains external and is never removed +ok 47 - an unattempted owner-created file identical to a suggestion remains external and is never removed + --- + duration_ms: 2148.3974 + type: 'test' + ... +# Subtest: active batch requests are serialized and cancellation leaves a verifiable ended batch +ok 48 - active batch requests are serialized and cancellation leaves a verifiable ended batch + --- + duration_ms: 2097.2045 + type: 'test' + ... +# Subtest: batch application and rollback preserve unrelated Git index and worktree bytes +ok 49 - batch application and rollback preserve unrelated Git index and worktree bytes + --- + duration_ms: 3494.2291 + type: 'test' + ... +# Subtest: recovery reuses exact staged bytes but retains a conflicting temporary file for owner inspection +ok 50 - recovery reuses exact staged bytes but retains a conflicting temporary file for owner inspection + --- + duration_ms: 2832.5819 + type: 'test' + ... +# Subtest: one Task can seal pending proposals from earlier Runs while snapshots retain each source Run +ok 51 - one Task can seal pending proposals from earlier Runs while snapshots retain each source Run + --- + duration_ms: 2065.691 + type: 'test' + ... +# Subtest: engineering inspection preserves a dirty Git baseline and treats project rules as data +ok 52 - engineering inspection preserves a dirty Git baseline and treats project rules as data + --- + duration_ms: 3419.1609 + type: 'test' + ... +# Subtest: real npm tests and build produce counted results, log artifacts and persistent verification +ok 53 - real npm tests and build produce counted results, log artifacts and persistent verification + --- + duration_ms: 2468.3621 + type: 'test' + ... +# Subtest: an actual failing test retains the nonzero exit code and failed count +ok 54 - an actual failing test retains the nonzero exit code and failed count + --- + duration_ms: 2611.3325 + type: 'test' + ... +# Subtest: zero tests, skipped tests and unrecognized stdout cannot become verification passes +ok 55 - zero tests, skipped tests and unrecognized stdout cannot become verification passes + --- + duration_ms: 8317.398 + type: 'test' + ... +# Subtest: a successful build with no selected tests does not verify the task +ok 56 - a successful build with no selected tests does not verify the task + --- + duration_ms: 2056.7561 + type: 'test' + ... +# Subtest: stale check plans and forged script names execute no project commands +ok 57 - stale check plans and forged script names execute no project commands + --- + duration_ms: 1853.7043 + type: 'test' + ... +# Subtest: applying a later proposal invalidates the prior passed engineering snapshot +ok 58 - applying a later proposal invalidates the prior passed engineering snapshot + --- + duration_ms: 3497.6245 + type: 'test' + ... +# Subtest: stopping an actual check terminates its child process and blocks concurrent jobs +ok 59 - stopping an actual check terminates its child process and blocks concurrent jobs + --- + duration_ms: 2336.8173 + type: 'test' + ... +# Subtest: check timeout records a failure with its actual termination result +ok 60 - check timeout records a failure with its actual termination result + --- + duration_ms: 2539.0651 + type: 'test' + ... +# Subtest: source edits during a successful check make the result stale +ok 61 - source edits during a successful check make the result stale + --- + duration_ms: 3394.2461 + type: 'test' + ... +# Subtest: bounded large logs retain the test footer and readable artifact instead of inventing counts +ok 62 - bounded large logs retain the test footer and readable artifact instead of inventing counts + --- + duration_ms: 2668.4447 + type: 'test' + ... +# Subtest: model-selected checks require a run-bound decision and denial creates no check job +ok 63 - model-selected checks require a run-bound decision and denial creates no check job + --- + duration_ms: 4436.9866 + type: 'test' + ... +# Subtest: check APIs expose owned plans and jobs and preserve the authoritative results across restart +ok 64 - check APIs expose owned plans and jobs and preserve the authoritative results across restart + --- + duration_ms: 7123.2631 + type: 'test' + ... +# Subtest: reviewed changes continue the original task without reopening a generic completed run +ok 65 - reviewed changes continue the original task without reopening a generic completed run + --- + duration_ms: 3840.3903 + type: 'test' + ... +# Subtest: concurrent review-continuation API requests accept one run and retain the goal after restart +ok 66 - concurrent review-continuation API requests accept one run and retain the goal after restart + --- + duration_ms: 10229.6022 + type: 'test' + ... +# Subtest: the model reads owned failure logs without running the check again +ok 67 - the model reads owned failure logs without running the check again + --- + duration_ms: 4098.3123 + type: 'test' + ... +# Subtest: process exit at check queued preserves results and never replays commands +ok 68 - process exit at check queued preserves results and never replays commands + --- + duration_ms: 1348.885 + type: 'test' + ... +# Subtest: process exit at check result_committed preserves results and never replays commands +ok 69 - process exit at check result_committed preserves results and never replays commands + --- + duration_ms: 2157.2369 + type: 'test' + ... +# Subtest: model code tools keep Task/Run ownership, index evidence and exact proposals across storage recovery +ok 70 - model code tools keep Task/Run ownership, index evidence and exact proposals across storage recovery + --- + duration_ms: 5770.1308 + type: 'test' + ... +# Subtest: bundled code APIs isolate project results, validate queries and create review-only patches with conflicts +ok 71 - bundled code APIs isolate project results, validate queries and create review-only patches with conflicts + --- + duration_ms: 3415.6316 + type: 'test' + ... +# Subtest: code tool arguments reject malformed ownership-independent inputs before side effects +ok 72 - code tool arguments reject malformed ownership-independent inputs before side effects + --- + duration_ms: 0.34 + type: 'test' + ... +# Subtest: pairing is short lived, single-use, generation-bound and validates exact permissions +ok 73 - pairing is short lived, single-use, generation-bound and validates exact permissions + --- + duration_ms: 1171.689 + type: 'test' + ... +# Subtest: device transaction failure neither consumes the ticket nor leaves a credential +ok 74 - device transaction failure neither consumes the ticket nor leaves a credential + --- + duration_ms: 1386.9151 + type: 'test' + ... +# Subtest: devices have project and action boundaries; rotation, expiration, revocation and host changes reject old authority +ok 75 - devices have project and action boundaries; rotation, expiration, revocation and host changes reject old authority + --- + duration_ms: 1193.8428 + type: 'test' + ... +# Subtest: persistent registry stores hashes and a bounded audit, never raw credentials +ok 76 - persistent registry stores hashes and a bounded audit, never raw credentials + --- + duration_ms: 1050.2035 + type: 'test' + ... +# Subtest: real TLS verifies IP SAN, CA chain, encrypted restart and public fingerprint +ok 77 - real TLS verifies IP SAN, CA chain, encrypted restart and public fingerprint + --- + duration_ms: 1069.3724 + type: 'test' + ... +# Subtest: TLS sealing failure leaves listener closed and no plaintext or successful TLS registration +ok 78 - TLS sealing failure leaves listener closed and no plaintext or successful TLS registration + --- + duration_ms: 639.8618 + type: 'test' + ... +# Subtest: HTTP pairing is concurrent single-use; secure cookie and strict origin/host checks +ok 79 - HTTP pairing is concurrent single-use; secure cookie and strict origin/host checks + --- + duration_ms: 1421.6199 + type: 'test' + ... +# Subtest: gateway never exposes management routes, arbitrary assets or unpaired project data +ok 80 - gateway never exposes management routes, arbitrary assets or unpaired project data + --- + duration_ms: 985.2654 + type: 'test' + ... +# Subtest: authorized project events paginate from original seq without leaking other project events or payloads +ok 81 - authorized project events paginate from original seq without leaking other project events or payloads + --- + duration_ms: 1816.8706 + type: 'test' + ... +# Subtest: remote task projection excludes raw model history, host configuration, tool input and credentials +ok 82 - remote task projection excludes raw model history, host configuration, tool input and credentials + --- + duration_ms: 1084.3574 + type: 'test' + ... +# Subtest: permission checks apply to direct remote mutation, not only UI controls +ok 83 - permission checks apply to direct remote mutation, not only UI controls + --- + duration_ms: 1283.7892 + type: 'test' + ... +# Subtest: approval fingerprint and exact task/revision are bound; duplicate requests never execute twice +ok 84 - approval fingerprint and exact task/revision are bound; duplicate requests never execute twice + --- + duration_ms: 1803.8588 + type: 'test' + ... +# Subtest: unknown original operation is recorded and never replayed after response failure +ok 85 - unknown original operation is recorded and never replayed after response failure + --- + duration_ms: 1460.6741 + type: 'test' + ... +# Subtest: revocation and gateway closure reject old access without invoking runtime stop +ok 86 - revocation and gateway closure reject old access without invoking runtime stop + --- + duration_ms: 1468.1577 + type: 'test' + ... +# Subtest: rate limits reject pairing brute force and do not persist candidate secrets +ok 87 - rate limits reject pairing brute force and do not persist candidate secrets + --- + duration_ms: 1427.3703 + type: 'test' + ... +# Subtest: real Windows CurrentUser DPAPI persists only a sealed CA and reopens it +ok 88 - real Windows CurrentUser DPAPI persists only a sealed CA and reopens it + --- + duration_ms: 2346.1339 + type: 'test' + ... +# Subtest: mobile approval executes the original Runtime command exactly once and rejects the later desktop decision +ok 89 - mobile approval executes the original Runtime command exactly once and rejects the later desktop decision + --- + duration_ms: 2793.5864 + type: 'test' + ... +# Subtest: desktop rejection wins a concurrent mobile request and original command remains unexecuted +ok 90 - desktop rejection wins a concurrent mobile request and original command remains unexecuted + --- + duration_ms: 2517.4017 + type: 'test' + ... +# Subtest: phone stop waits for the original process exit and prevents later heartbeats and command replay +ok 91 - phone stop waits for the original process exit and prevents later heartbeats and command replay + --- + duration_ms: 3759.9281 + type: 'test' + ... +# Subtest: Run replacement during parent-stop wait is rejected rather than stopping the new Run +ok 92 - Run replacement during parent-stop wait is rejected rather than stopping the new Run + --- + duration_ms: 1291.6828 + type: 'test' + ... +# Subtest: diff pages preserve source SHA; report reads verify blobs and exclude unrelated artifact kinds +ok 93 - diff pages preserve source SHA; report reads verify blobs and exclude unrelated artifact kinds + --- + duration_ms: 1169.8336 + type: 'test' + ... +# Subtest: hot upgrade refuses an active gateway and restores closed gateway ownership on failure +ok 94 - hot upgrade refuses an active gateway and restores closed gateway ownership on failure + --- + duration_ms: 779.9559 + type: 'test' + ... +# Subtest: damaged device permissions or expiry fail closed and never overwrite the original registry +ok 95 - damaged device permissions or expiry fail closed and never overwrite the original registry + --- + duration_ms: 847.404 + type: 'test' + ... +# Subtest: device revocation destroys its actual authenticated TLS connection +ok 96 - device revocation destroys its actual authenticated TLS connection + --- + duration_ms: 1350.0304 + type: 'test' + ... +# Subtest: actual config HTTP failure preserves the committed selection, config and volatile credential before a successful retry +ok 97 - actual config HTTP failure preserves the committed selection, config and volatile credential before a successful retry + --- + duration_ms: 1684.1557 + type: 'test' + ... +# Subtest: controlled installation pins the native kernel and bridge independently of the existing connection-probe identity +ok 98 - controlled installation pins the native kernel and bridge independently of the existing connection-probe identity + --- + duration_ms: 1225.489 + type: 'test' + ... +# Subtest: controlled profiles disable every native project/terminal provider and native model/retry route using the actual include patch contract +ok 99 - controlled profiles disable every native project/terminal provider and native model/retry route using the actual include patch contract + --- + duration_ms: 0.619 + type: 'test' + ... +# Subtest: owned tool catalogues seal full schemas canonically and reject duplicate or malformed declarations +ok 100 - owned tool catalogues seal full schemas canonically and reject duplicate or malformed declarations + --- + duration_ms: 6.3951 + type: 'test' + ... +# Subtest: bridge authentication, current Run, process, SDK session and browser-origin checks reject before dispatch +ok 101 - bridge authentication, current Run, process, SDK session and browser-origin checks reject before dispatch + --- + duration_ms: 696.3257 + type: 'test' + ... +# Subtest: bridge duplicates, unknown tools, malformed arguments and source changes are refused before a second side effect +ok 102 - bridge duplicates, unknown tools, malformed arguments and source changes are refused before a second side effect + --- + duration_ms: 700.7583 + type: 'test' + ... +# Subtest: bridge model requests bind the exact catalogue, route and output bound and preserve raw request/result identity +ok 103 - bridge model requests bind the exact catalogue, route and output bound and preserve raw request/result identity + --- + duration_ms: 936.4227 + type: 'test' + ... +# Subtest: stopped and oversized bridge requests never reach a local model or tool callback +ok 104 - stopped and oversized bridge requests never reach a local model or tool callback + --- + duration_ms: 901.3396 + type: 'test' + ... +# Subtest: a Windows virtual data-directory name binds new storage and credentials to its actual physical root +ok 105 - a Windows virtual data-directory name binds new storage and credentials to its actual physical root + --- + duration_ms: 1894.7122 + type: 'test' + ... +# Subtest: physical data-root adoption still rejects explicit junctions at the directory or any ancestor +ok 106 - physical data-root adoption still rejects explicit junctions at the directory or any ancestor + --- + duration_ms: 1077.381 + type: 'test' + ... +# Subtest: actual Windows CurrentUser DPAPI roundtrips owned UTF-8 and rejects damaged bytes and wrong entropy +ok 107 - actual Windows CurrentUser DPAPI roundtrips owned UTF-8 and rejects damaged bytes and wrong entropy + --- + duration_ms: 1356.0165 + type: 'test' + ... +# Subtest: only explicitly supplied keys persist; new provider restores original revisions and public views contain no key +ok 108 - only explicitly supplied keys persist; new provider restores original revisions and public views contain no key + --- + duration_ms: 2796.6288 + type: 'test' + ... +# Subtest: registry and cipher commit failure restores original routing, keys, block and every database row +ok 109 - registry and cipher commit failure restores original routing, keys, block and every database row + --- + duration_ms: 2070.7354 + type: 'test' + ... +# Subtest: a two-key import with a protection failure rolls back all registry and cipher entries and retains its preview +ok 110 - a two-key import with a protection failure rolls back all registry and cipher entries and retains its preview + --- + duration_ms: 2186.6587 + type: 'test' + ... +# Subtest: connection revision changes retain the original saved block and report a source mismatch on restart +ok 111 - connection revision changes retain the original saved block and report a source mismatch on restart + --- + duration_ms: 2361.4786 + type: 'test' + ... +# Subtest: disable skips real restart loading, explicit enable restores, delete preserves memory and forget removes both +ok 112 - disable skips real restart loading, explicit enable restores, delete preserves memory and forget removes both + --- + duration_ms: 2737.2567 + type: 'test' + ... +# Subtest: corrupt saved block and another SID do not load; failures are visible without returning ciphertext or plaintext +ok 113 - corrupt saved block and another SID do not load; failures are visible without returning ciphertext or plaintext + --- + duration_ms: 2849.4482 + type: 'test' + ... +# Subtest: legacy persistence requires a new explicit key and binds config and credential revisions; stale requests cannot save +ok 114 - legacy persistence requires a new explicit key and binds config and credential revisions; stale requests cannot save + --- + duration_ms: 2811.8143 + type: 'test' + ... +# Subtest: owned plaintext keys never reach SQLite pages, WAL, config or public execution exports +ok 115 - owned plaintext keys never reach SQLite pages, WAL, config or public execution exports + --- + duration_ms: 1778.6322 + type: 'test' + ... +# Subtest: actual process exit at Git queued never replays a commit and can reconcile the durable result +ok 116 - actual process exit at Git queued never replays a commit and can reconcile the durable result + --- + duration_ms: 10700.5364 + type: 'test' + ... +# Subtest: actual process exit at Git preparing never replays a commit and can reconcile the durable result +ok 117 - actual process exit at Git preparing never replays a commit and can reconcile the durable result + --- + duration_ms: 11029.3065 + type: 'test' + ... +# Subtest: actual process exit at Git index_locked never replays a commit and can reconcile the durable result +ok 118 - actual process exit at Git index_locked never replays a commit and can reconcile the durable result + --- + duration_ms: 11107.7553 + type: 'test' + ... +# Subtest: actual process exit at Git prepared never replays a commit and can reconcile the durable result +ok 119 - actual process exit at Git prepared never replays a commit and can reconcile the durable result + --- + duration_ms: 11484.133 + type: 'test' + ... +# Subtest: actual process exit at Git ref_prepared never replays a commit and can reconcile the durable result +ok 120 - actual process exit at Git ref_prepared never replays a commit and can reconcile the durable result + --- + duration_ms: 12734.3559 + type: 'test' + ... +# Subtest: actual process exit at Git publishing never replays a commit and can reconcile the durable result +ok 121 - actual process exit at Git publishing never replays a commit and can reconcile the durable result + --- + duration_ms: 12723.8988 + type: 'test' + ... +# Subtest: actual process exit at Git committed never replays a commit and can reconcile the durable result +ok 122 - actual process exit at Git committed never replays a commit and can reconcile the durable result + --- + duration_ms: 8190.3156 + type: 'test' + ... +# Subtest: actual process exit at Git index_published never replays a commit and can reconcile the durable result +ok 123 - actual process exit at Git index_published never replays a commit and can reconcile the durable result + --- + duration_ms: 9412.5044 + type: 'test' + ... +# Subtest: actual process exit at Git finished never replays a commit and can reconcile the durable result +ok 124 - actual process exit at Git finished never replays a commit and can reconcile the durable result + --- + duration_ms: 8558.2492 + type: 'test' + ... +# Subtest: an unknown Git result cannot overwrite an externally changed index or delete an unrelated lock +ok 125 - an unknown Git result cannot overwrite an externally changed index or delete an unrelated lock + --- + duration_ms: 7725.3169 + type: 'test' + ... +# Subtest: known publication with a later source edit retains the commit and marks the delivery for inspection +ok 126 - known publication with a later source edit retains the commit and marks the delivery for inspection + --- + duration_ms: 8282.3639 + type: 'test' + ... +# Subtest: CRLF normalization, multiple applied revisions and unrelated special index flags preserve exact bytes and ownership +ok 127 - CRLF normalization, multiple applied revisions and unrelated special index flags preserve exact bytes and ownership + --- + duration_ms: 9832.5178 + type: 'test' + ... +# Subtest: adding new durable record kinds to an existing hot Store preserves all existing Maps and records +ok 128 - adding new durable record kinds to an existing hot Store preserves all existing Maps and records + --- + duration_ms: 7278.2907 + type: 'test' + ... +# Subtest: an unrelated owner deletion is fingerprinted and preserved while linked task paths are rejected +ok 129 - an unrelated owner deletion is fingerprinted and preserved while linked task paths are rejected + --- + duration_ms: 12485.3612 + type: 'test' + ... +# Subtest: actual failed tests become a reviewed local commit and evidence report while preserving unrelated index and files +ok 130 - actual failed tests become a reviewed local commit and evidence report while preserving unrelated index and files + --- + duration_ms: 12041.1377 + type: 'test' + ... +# Subtest: selected preexisting unstaged, staged and untracked owner edits cannot enter a task commit +ok 131 - selected preexisting unstaged, staged and untracked owner edits cannot enter a task commit + --- + duration_ms: 15012.005 + type: 'test' + ... +# Switched to a new branch 'owner-branch' +# Subtest: source, unrelated stage and branch changes after review invalidate a commit plan without changing HEAD +ok 132 - source, unrelated stage and branch changes after review invalidate a commit plan without changing HEAD + --- + duration_ms: 19466.7481 + type: 'test' + ... +# Switched to a new branch 'delivery-branch' +# Subtest: a later Git metadata change keeps matching source evidence valid but a real source edit requires checks +ok 133 - a later Git metadata change keeps matching source evidence valid but a real source edit requires checks + --- + duration_ms: 8738.4972 + type: 'test' + ... +# Subtest: a corrupt passed-check log and a pending proposal block Git delivery instead of inventing evidence +ok 134 - a corrupt passed-check log and a pending proposal block Git delivery instead of inventing evidence + --- + duration_ms: 4343.5992 + type: 'test' + ... +# HEAD is now at c167ddb Sealed delivery fixture baseline +# Subtest: Git filters, merge state, detached HEAD and old task ownership are explicitly rejected +ok 135 - Git filters, merge state, detached HEAD and old task ownership are explicitly rejected + --- + duration_ms: 20147.6224 + type: 'test' + ... +# Subtest: local snapshot commits disable repository hooks and signing and isolate the Git child environment +ok 136 - local snapshot commits disable repository hooks and signing and isolate the Git child environment + --- + duration_ms: 7577.4562 + type: 'test' + ... +# Subtest: stopping before publication cancels safely; stopping after publication preserves the actual completed commit +ok 137 - stopping before publication cancels safely; stopping after publication preserves the actual completed commit + --- + duration_ms: 13946.622 + type: 'test' + ... +# Subtest: delivery API confirms exactly one owned plan, serves verified reports and preserves results across restart +ok 138 - delivery API confirms exactly one owned plan, serves verified reports and preserves results across restart + --- + duration_ms: 12174.5802 + type: 'test' + ... +# Subtest: the model can prepare an owned Git review and evidence report while publishing remains a separate user action +ok 139 - the model can prepare an owned Git review and evidence report while publishing remains a separate user action + --- + duration_ms: 9478.8559 + type: 'test' + ... +# Subtest: HTTP Git review pairs deferred calls, survives reload and never requests more work until the saved preview is resolved +ok 140 - HTTP Git review pairs deferred calls, survives reload and never requests more work until the saved preview is resolved + --- + duration_ms: 11122.3653 + type: 'test' + ... +# Subtest: a reviewed Git preview can be revised or withdrawn without publishing or losing the current Task +ok 141 - a reviewed Git preview can be revised or withdrawn without publishing or losing the current Task + --- + duration_ms: 8446.2207 + type: 'test' + ... +# Subtest: actual Electron debug argument ordering retains exactly the compiled entry and rejects extra or repeated actions +ok 142 - actual Electron debug argument ordering retains exactly the compiled entry and rejects extra or repeated actions + --- + duration_ms: 1.0602 + type: 'test' + ... +# Subtest: native bridge refuses other origins, subframes, other windows and unsupported inputs before connecting +ok 143 - native bridge refuses other origins, subframes, other windows and unsupported inputs before connecting + --- + duration_ms: 1064.78 + type: 'test' + ... +# Subtest: file reveal binds the current project, task, path, UTF-8 bytes and original SHA without executing the file +ok 144 - file reveal binds the current project, task, path, UTF-8 bytes and original SHA without executing the file + --- + duration_ms: 922.3757 + type: 'test' + ... +# Subtest: file changed during asynchronous task recheck is not revealed as the old bytes +ok 145 - file changed during asynchronous task recheck is not revealed as the old bytes + --- + duration_ms: 599.5056 + type: 'test' + ... +# Subtest: desktop browser profile and aliases stay outside project inventory and file access +ok 146 - desktop browser profile and aliases stay outside project inventory and file access + --- + duration_ms: 617.4813 + type: 'test' + ... +# Subtest: native picker cancel and origin change after dialog publish no project registration +ok 147 - native picker cancel and origin change after dialog publish no project registration + --- + duration_ms: 689.2402 + type: 'test' + ... +# Subtest: pending native action is not dispatched twice, and current task review returns its original seq +ok 148 - pending native action is not dispatched twice, and current task review returns its original seq + --- + duration_ms: 905.8533 + type: 'test' + ... +# Subtest: native stop cancellation and changed original host never stop a replacement process +ok 149 - native stop cancellation and changed original host never stop a replacement process + --- + duration_ms: 745.3858 + type: 'test' + ... +# Subtest: window register rejects host PID, stale installation, extra fields and missing creation identity +ok 150 - window register rejects host PID, stale installation, extra fields and missing creation identity + --- + duration_ms: 0.349 + type: 'test' + ... +# Subtest: a rebuilt source archive binds actual generated client assets and retains its original running identity after disk changes +ok 151 - a rebuilt source archive binds actual generated client assets and retains its original running identity after disk changes + --- + duration_ms: 1848.2742 + type: 'test' + ... +# Subtest: host challenge proof rejects a stale challenge, changed identity and changed signature +ok 152 - host challenge proof rejects a stale challenge, changed identity and changed signature + --- + duration_ms: 0.8161 + type: 'test' + ... +# Subtest: stop confirmation binds the original instance, creation and loaded runtime +ok 153 - stop confirmation binds the original instance, creation and loaded runtime + --- + duration_ms: 0.194 + type: 'test' + ... +# Subtest: state paths reject escaping, linked ancestors, ambiguous hardlinks and damaged JSON +ok 154 - state paths reject escaping, linked ancestors, ambiguous hardlinks and damaged JSON + --- + duration_ms: 1414.4405 + type: 'test' + ... +# Subtest: failed registration publishes no initialized memory and can complete after its actual inputs are supplied +ok 155 - failed registration publishes no initialized memory and can complete after its actual inputs are supplied + --- + duration_ms: 3212.6677 + type: 'test' + ... +# Subtest: host shutdown cancels an un-signalled HTTP model request and refuses later requests until recovered +ok 156 - host shutdown cancels an un-signalled HTTP model request and refuses later requests until recovered + --- + duration_ms: 1.4745 + type: 'test' + ... +# Subtest: host shutdown cancels model-pool acquisition and releases queue ownership without inventing attempts +ok 157 - host shutdown cancels model-pool acquisition and releases queue ownership without inventing attempts + --- + duration_ms: 813.8035 + type: 'test' + ... +# Subtest: full candidate validation returns the exact loaded-input host identity and rejects undeclared or altered files +ok 158 - full candidate validation returns the exact loaded-input host identity and rejects undeclared or altered files + --- + duration_ms: 1335.8387 + type: 'test' + ... +# Subtest: installation requires separate absolute program/data directories and a candidate in its own versions namespace +ok 159 - installation requires separate absolute program/data directories and a candidate in its own versions namespace + --- + duration_ms: 1273.8898 + type: 'test' + ... +# Subtest: staging retains the original data and pointer without querying or restarting a host +ok 160 - staging retains the original data and pointer without querying or restarting a host + --- + duration_ms: 2212.5535 + type: 'test' + ... +# Subtest: a post-pointer failure restores every original pointer byte and persistent row; a first-install failure removes only its published pointer +ok 161 - a post-pointer failure restores every original pointer byte and persistent row; a first-install failure removes only its published pointer + --- + duration_ms: 5795.0152 + type: 'test' + ... +# Subtest: changed active manifest and concurrent pointer changes are rejected without overwriting the unknown record +ok 162 - changed active manifest and concurrent pointer changes are rejected without overwriting the unknown record + --- + duration_ms: 3071.5235 + type: 'test' + ... +# Subtest: an unregistered non-HTTP listener blocks preflight even when service-info is absent +ok 163 - an unregistered non-HTTP listener blocks preflight even when service-info is absent + --- + duration_ms: 1288.9215 + type: 'test' + ... +# Subtest: uninstall archives its original pointer and preserves every data row/artifact instead of recursively deleting data +ok 164 - uninstall archives its original pointer and preserves every data row/artifact instead of recursively deleting data + --- + duration_ms: 3884.7616 + type: 'test' + ... +# Subtest: preflight rejects an unrelated program root or changed native bootstrap while preserving its original bytes +ok 165 - preflight rejects an unrelated program root or changed native bootstrap while preserving its original bytes + --- + duration_ms: 1385.3388 + type: 'test' + ... +# Subtest: a changed owned bootstrap follows its candidate and a post-pointer fault restores both original bytes +ok 166 - a changed owned bootstrap follows its candidate and a post-pointer fault restores both original bytes + --- + duration_ms: 7021.8609 + type: 'test' + ... +# Subtest: an external bootstrap change after preflight is preserved and never overwritten as an update or rollback +ok 167 - an external bootstrap change after preflight is preserved and never overwritten as an update or rollback + --- + duration_ms: 3825.6931 + type: 'test' + ... +# Subtest: a question about the previous workbench error receives local error context and current change states +ok 168 - a question about the previous workbench error receives local error context and current change states + --- + duration_ms: 2030.4859 + type: 'test' + ... +# Subtest: a transient model failure after an approved command retries only the model request +ok 169 - a transient model failure after an approved command retries only the model request + --- + duration_ms: 2907.3553 + type: 'test' + ... +# Subtest: exhausted model retries preserve tool results, and explicit resume adds no new user turn or replay +ok 170 - exhausted model retries preserve tool results, and explicit resume adds no new user turn or replay + --- + duration_ms: 3370.2421 + type: 'test' + ... +# Subtest: stopping during model backoff cancels further requests and clears the running request state +ok 171 - stopping during model backoff cancels further requests and clears the running request state + --- + duration_ms: 2102.6358 + type: 'test' + ... +# Subtest: HTTP authentication errors are classified, redacted and never automatically retried +ok 172 - HTTP authentication errors are classified, redacted and never automatically retried + --- + duration_ms: 22.2119 + type: 'test' + ... +# Subtest: temporary HTTP service errors retry and recover with recorded attempt counts +ok 173 - temporary HTTP service errors retry and recover with recorded attempt counts + --- + duration_ms: 22.443 + type: 'test' + ... +# Subtest: invalid and oversized protocol responses fail once with a useful response-format diagnosis +ok 174 - invalid and oversized protocol responses fail once with a useful response-format diagnosis + --- + duration_ms: 3.977 + type: 'test' + ... +# Subtest: HTTP rate limits expose their source and obey the service retry interval before recovery +ok 175 - HTTP rate limits expose their source and obey the service retry interval before recovery + --- + duration_ms: 1011.7828 + type: 'test' + ... +# Subtest: Windows commands preserve Chinese through a PowerShell pipeline into Node +ok 176 - Windows commands preserve Chinese through a PowerShell pipeline into Node + --- + duration_ms: 997.1911 + type: 'test' + ... +# Subtest: Windows shell syntax errors stay readable and native command exit codes are retained +ok 177 - Windows shell syntax errors stay readable and native command exit codes are retained + --- + duration_ms: 1309.9472 + type: 'test' + ... +# Subtest: review and completed states do not turn a generic continue click into a new model request +ok 178 - review and completed states do not turn a generic continue click into a new model request + --- + duration_ms: 1065.6389 + type: 'test' + ... +# Subtest: old session data receives a truthful historical connection diagnosis without rewriting history +ok 179 - old session data receives a truthful historical connection diagnosis without rewriting history + --- + duration_ms: 1328.7231 + type: 'test' + ... +# Subtest: engine HTTP checks bind the detected installation and current task, page original bytes and preserve them across host restart +ok 180 - engine HTTP checks bind the detected installation and current task, page original bytes and preserve them across host restart + --- + duration_ms: 6615.4576 + type: 'test' + ... +# Subtest: HTTP stop seals a pending SDK call, rejects automatic replay and keeps failures attached to the original session +ok 181 - HTTP stop seals a pending SDK call, rejects automatic replay and keeps failures attached to the original session + --- + duration_ms: 4967.3394 + type: 'test' + ... +# Subtest: controlled engine HTTP freezes one child, pages original owned input/report, rejects foreign reads and prevents changed-source reuse +ok 182 - controlled engine HTTP freezes one child, pages original owned input/report, rejects foreign reads and prevents changed-source reuse + --- + duration_ms: 16256.4995 + type: 'test' + ... +# Subtest: native text and call IDs preserve original result pairing while unsupported content fails closed +ok 183 - native text and call IDs preserve original result pairing while unsupported content fails closed + --- + duration_ms: 0.8087 + type: 'test' + ... +# Subtest: one engine child freezes real installation identity before creating tasks and rejects a changed source +ok 184 - one engine child freezes real installation identity before creating tasks and rejects a changed source + --- + duration_ms: 8227.5581 + type: 'test' + ... +# Subtest: owned native tools return saved results, use real approvals/checks and account each actual request once across new engine Runs +ok 185 - owned native tools return saved results, use real approvals/checks and account each actual request once across new engine Runs + --- + duration_ms: 26102.0521 + type: 'test' + ... +# Subtest: forged native scope cannot change a parent file and a final completion claim cannot replace worker proof +ok 186 - forged native scope cannot change a parent file and a final completion claim cannot replace worker proof + --- + duration_ms: 14016.8367 + type: 'test' + ... +# Subtest: duplicate native IDs are rejected without replaying a saved tool +ok 187 - duplicate native IDs are rejected without replaying a saved tool + --- + duration_ms: 13859.3176 + type: 'test' + ... +# Subtest: native input exceeding the context budget is retained and sends no model request +ok 188 - native input exceeding the context budget is retained and sends no model request + --- + duration_ms: 10659.5042 + type: 'test' + ... +# Subtest: stop retains a late reported model usage once and executes no tool from that output +ok 189 - stop retains a late reported model usage once and executes no tool from that output + --- + duration_ms: 10909.0404 + type: 'test' + ... +# Subtest: a source change after the original model intent stops before native tools execute +ok 190 - a source change after the original model intent stops before native tools execute + --- + duration_ms: 12027.0274 + type: 'test' + ... +# Subtest: an engine source change while approval is pending invalidates the old permission before any check starts +ok 191 - an engine source change while approval is pending invalidates the old permission before any check starts + --- + duration_ms: 15303.9087 + type: 'test' + ... +# Subtest: missing or noncompleted turn end cannot be adopted even with an owned receipt and assistant text +ok 192 - missing or noncompleted turn end cannot be adopted even with an owned receipt and assistant text + --- + duration_ms: 0.5605 + type: 'test' + ... +# Subtest: closed root with an original live descendant remains unknown and retains its process tree +ok 193 - closed root with an original live descendant remains unknown and retains its process tree + --- + duration_ms: 0.2584 + type: 'test' + ... +# Subtest: host recovery reserves original pending attempts exactly once and explicit review preserves unknown outcomes +ok 194 - host recovery reserves original pending attempts exactly once and explicit review preserves unknown outcomes + --- + duration_ms: 16446.3644 + type: 'test' + ... +# Subtest: corrupted model reservation cannot reduce recovered budget or permit a new engine request +ok 195 - corrupted model reservation cannot reduce recovered budget or permit a new engine request + --- + duration_ms: 12790.7958 + type: 'test' + ... +# Subtest: engine detection seals the actual CLI, SDK, profile and Node and rejects mixed versions without launch +ok 196 - engine detection seals the actual CLI, SDK, profile and Node and rejects mixed versions without launch + --- + duration_ms: 956.4509 + type: 'test' + ... +# Subtest: owned engine probe waits for real ready identity, verifies six native responses and saves immutable task evidence +ok 197 - owned engine probe waits for real ready identity, verifies six native responses and saves immutable task evidence + --- + duration_ms: 1856.0628 + type: 'test' + ... +# Subtest: an invalid startup nonce is rejected before initialize and preserves the process close and partial report +ok 198 - an invalid startup nonce is rejected before initialize and preserves the process close and partial report + --- + duration_ms: 1621.9118 + type: 'test' + ... +# Subtest: SDK identity and session directory mismatches retain raw responses and never become verified +ok 199 - SDK identity and session directory mismatches retain raw responses and never become verified + --- + duration_ms: 4724.0133 + type: 'test' + ... +# Subtest: cancel during a pending initialize closes only the owned process without sending an unsupported MCP cancellation +ok 200 - cancel during a pending initialize closes only the owned process without sending an unsupported MCP cancellation + --- + duration_ms: 1714.187 + type: 'test' + ... +# Subtest: cancel before readiness sends no protocol request and a user retry creates a different process and record +ok 201 - cancel before readiness sends no protocol request and a user retry creates a different process and record + --- + duration_ms: 2312.3578 + type: 'test' + ... +# Subtest: source or scratch changes and unexpected model traffic fail after preserving the actual observed result +ok 202 - source or scratch changes and unexpected model traffic fail after preserving the actual observed result + --- + duration_ms: 4444.3575 + type: 'test' + ... +# Subtest: unowned idle notifications stay quarantined and server requests receive a rejection without granting operations +ok 203 - unowned idle notifications stay quarantined and server requests receive a rejection without granting operations + --- + duration_ms: 3442.3107 + type: 'test' + ... +# Subtest: engine probe environment excludes parent secrets and NODE_OPTIONS while preserving operating system paths +ok 204 - engine probe environment excludes parent secrets and NODE_OPTIONS while preserving operating system paths + --- + duration_ms: 2092.3336 + type: 'test' + ... +# Subtest: foreign sessions and altered reports or task bindings cannot reuse verified engine evidence +ok 205 - foreign sessions and altered reports or task bindings cannot reuse verified engine evidence + --- + duration_ms: 1902.5045 + type: 'test' + ... +# Subtest: restart never replays an active engine check or stops a historical PID, and keeps prior task state +ok 206 - restart never replays an active engine check or stops a historical PID, and keeps prior task state + --- + duration_ms: 1761.4991 + type: 'test' + ... +# Subtest: model argument validation and runtime activity do not grant external engine prompt or project execution +ok 207 - model argument validation and runtime activity do not grant external engine prompt or project execution + --- + duration_ms: 813.5858 + type: 'test' + ... +# Subtest: a follow-up question receives the actual failed engine check from its original Task and keeps its report unchanged +ok 208 - a follow-up question receives the actual failed engine check from its original Task and keeps its report unchanged + --- + duration_ms: 2931.2197 + type: 'test' + ... +# Subtest: JSON migration survives process exit before commit and retains exact legacy backups +ok 209 - JSON migration survives process exit before commit and retains exact legacy backups + --- + duration_ms: 2943.1091 + type: 'test' + ... +# Subtest: process exit after_state rolls back state, event and outbox together +ok 210 - process exit after_state rolls back state, event and outbox together + --- + duration_ms: 3153.78 + type: 'test' + ... +# Subtest: process exit after_event rolls back state, event and outbox together +ok 211 - process exit after_event rolls back state, event and outbox together + --- + duration_ms: 2121.9329 + type: 'test' + ... +# Subtest: crash recovery at accepted retains execution identity and never replays side effects +ok 212 - crash recovery at accepted retains execution identity and never replays side effects + --- + duration_ms: 2037.8362 + type: 'test' + ... +# Subtest: crash recovery at queued retains execution identity and never replays side effects +ok 213 - crash recovery at queued retains execution identity and never replays side effects + --- + duration_ms: 2179.7148 + type: 'test' + ... +# Subtest: crash recovery at approval_wait retains execution identity and never replays side effects +ok 214 - crash recovery at approval_wait retains execution identity and never replays side effects + --- + duration_ms: 3503.785 + type: 'test' + ... +# Subtest: crash recovery at approved retains execution identity and never replays side effects +ok 215 - crash recovery at approved retains execution identity and never replays side effects + --- + duration_ms: 3549.5601 + type: 'test' + ... +# Subtest: crash recovery at effect_unrecorded retains execution identity and never replays side effects +ok 216 - crash recovery at effect_unrecorded retains execution identity and never replays side effects + --- + duration_ms: 3562.8708 + type: 'test' + ... +# Subtest: crash recovery at result_committed retains execution identity and never replays side effects +ok 217 - crash recovery at result_committed retains execution identity and never replays side effects + --- + duration_ms: 2949.8137 + type: 'test' + ... +# Subtest: crash recovery at before_next_model retains execution identity and never replays side effects +ok 218 - crash recovery at before_next_model retains execution identity and never replays side effects + --- + duration_ms: 4434.4661 + type: 'test' + ... +# Subtest: state and event failures publish no success and preserve the last committed memory snapshot +ok 219 - state and event failures publish no success and preserve the last committed memory snapshot + --- + duration_ms: 944.238 + type: 'test' + ... +# Subtest: tool result artifacts and event cursors retain project ownership across restart +ok 220 - tool result artifacts and event cursors retain project ownership across restart + --- + duration_ms: 2107.522 + type: 'test' + ... +# Subtest: token budgets pause before tools execute and continuation keeps original task and accumulated usage +ok 221 - token budgets pause before tools execute and continuation keeps original task and accumulated usage + --- + duration_ms: 1698.1971 + type: 'test' + ... +# Subtest: a time budget interrupts an unresponsive model and persists a resumable run +ok 222 - a time budget interrupts an unresponsive model and persists a resumable run + --- + duration_ms: 970.6993 + type: 'test' + ... +# Subtest: a corrupted large result artifact cannot become a recovered success +ok 223 - a corrupted large result artifact cannot become a recovered success + --- + duration_ms: 1326.2934 + type: 'test' + ... +# Subtest: hard-link aliases cannot expose protected bytes through reads, proposals, inventory or automatic project rules +ok 224 - hard-link aliases cannot expose protected bytes through reads, proposals, inventory or automatic project rules + --- + duration_ms: 1204.0739 + type: 'test' + ... +# Subtest: ambiguous project hard links are explicit and ordinary independent file copies remain readable +ok 225 - ambiguous project hard links are explicit and ordinary independent file copies remain readable + --- + duration_ms: 1296.1795 + type: 'test' + ... +# Subtest: proposals preserve project bytes until review; apply backs up the exact original bytes +ok 226 - proposals preserve project bytes until review; apply backs up the exact original bytes + --- + duration_ms: 1051.0705 + type: 'test' + ... +# Subtest: new nested files are created only on apply and unchanged content creates no proposal +ok 227 - new nested files are created only on apply and unchanged content creates no proposal + --- + duration_ms: 848.3544 + type: 'test' + ... +# Subtest: stale reads and changed baselines are rejected without overwriting external edits +ok 228 - stale reads and changed baselines are rejected without overwriting external edits + --- + duration_ms: 907.8623 + type: 'test' + ... +# Subtest: file paths reject traversal, absolute paths, credentials and outside junctions +ok 229 - file paths reject traversal, absolute paths, credentials and outside junctions + --- + duration_ms: 583.7994 + type: 'test' + ... +# Subtest: read and search expose bounded text scopes and reject non UTF-8 / oversized files +ok 230 - read and search expose bounded text scopes and reject non UTF-8 / oversized files + --- + duration_ms: 700.4832 + type: 'test' + ... +# Subtest: project-local junctions cannot expose or create protected Git and credential files +ok 231 - project-local junctions cannot expose or create protected Git and credential files + --- + duration_ms: 950.5065 + type: 'test' + ... +# Subtest: Windows trailing-dot and trailing-space path aliases cannot bypass protected paths +ok 232 - Windows trailing-dot and trailing-space path aliases cannot bypass protected paths + --- + duration_ms: 696.8305 + type: 'test' + ... +# Subtest: a starter is copied into user data once; restarting from another program version preserves existing projects and editable bytes +ok 233 - a starter is copied into user data once; restarting from another program version preserves existing projects and editable bytes + --- + duration_ms: 1467.6872 + type: 'test' + ... +# Subtest: startup does not insert a demo or rewrite/reorder an existing user project registry +ok 234 - startup does not insert a demo or rewrite/reorder an existing user project registry + --- + duration_ms: 882.3293 + type: 'test' + ... +# Subtest: MCP registration stays disabled until an explicit real stdio probe and schema-based tool selection, with actual process cleanup +ok 235 - MCP registration stays disabled until an explicit real stdio probe and schema-based tool selection, with actual process cleanup + --- + duration_ms: 2881.5147 + type: 'test' + ... +# Subtest: MCP probe holds the project operation lock until its owned process and report are settled +ok 236 - MCP probe holds the project operation lock until its owned process and report are settled + --- + duration_ms: 2591.6595 + type: 'test' + ... +# Subtest: MCP validates the declared JSON schema subset and rejects unsupported schemas before external dispatch +ok 237 - MCP validates the declared JSON schema subset and rejects unsupported schemas before external dispatch + --- + duration_ms: 0.602 + type: 'test' + ... +# Subtest: actual model MCP call approves long schema-valid arguments, validates the sent catalog and stores one original result without leaking environment secrets +ok 238 - actual model MCP call approves long schema-valid arguments, validates the sent catalog and stores one original result without leaking environment secrets + --- + duration_ms: 5316.6237 + type: 'test' + ... +# Subtest: denying an MCP call never starts another process or executes the external tool +ok 239 - denying an MCP call never starts another process or executes the external tool + --- + duration_ms: 4100.3694 + type: 'test' + ... +# Subtest: actual handshake drift rejects tools/call even if program entry hash is unchanged +ok 240 - actual handshake drift rejects tools/call even if program entry hash is unchanged + --- + duration_ms: 5763.9782 + type: 'test' + ... +# Subtest: cancelled dispatched external side effect stays unknown, closes its owned process and cannot replay on reopen +ok 241 - cancelled dispatched external side effect stays unknown, closes its owned process and cannot replay on reopen + --- + duration_ms: 4996.7117 + type: 'test' + ... +# Subtest: changed executable input, foreign project IDs and corrupted original contracts block enable and dispatch +ok 242 - changed executable input, foreign project IDs and corrupted original contracts block enable and dispatch + --- + duration_ms: 2269.367 + type: 'test' + ... +# Subtest: registered MCP HTTP API uses fixed execution contracts and project-owned probe records with no model requests +ok 243 - registered MCP HTTP API uses fixed execution contracts and project-owned probe records with no model requests + --- + duration_ms: 4470.9043 + type: 'test' + ... +# Subtest: unknown MCP pauses later tool calls and all project writers; fingerprinted acknowledgement clears only the review gates and explicit resume does not replay +ok 244 - unknown MCP pauses later tool calls and all project writers; fingerprinted acknowledgement clears only the review gates and explicit resume does not replay + --- + duration_ms: 6344.0052 + type: 'test' + ... +# Subtest: MCP acknowledgement persistence failure restores both job and tool review gates; corrupt evidence cannot be acknowledged +ok 245 - MCP acknowledgement persistence failure restores both job and tool review gates; corrupt evidence cannot be acknowledged + --- + duration_ms: 4498.0874 + type: 'test' + ... +# Subtest: actual host exit after an external effect restores unknown jobs without a fabricated report, allows source-bound review and never replays the call +ok 246 - actual host exit after an external effect restores unknown jobs without a fabricated report, allows source-bound review and never replays the call + --- + duration_ms: 4429.1816 + type: 'test' + ... +# Subtest: changed enabled MCP programs can be explicitly disabled without launching or trusting their changed source +ok 247 - changed enabled MCP programs can be explicitly disabled without launching or trusting their changed source + --- + duration_ms: 2230.9134 + type: 'test' + ... +# Subtest: stdio preserves split UTF-8 frames and final replies drained after process exit +ok 248 - stdio preserves split UTF-8 frames and final replies drained after process exit + --- + duration_ms: 2134.8931 + type: 'test' + ... +# Subtest: server-initiated model requests are refused instead of inheriting provider privileges +ok 249 - server-initiated model requests are refused instead of inheriting provider privileges + --- + duration_ms: 1095.6642 + type: 'test' + ... +# Subtest: invalid or over-budget protocol invalid closes only its owned process and is not retried +ok 250 - invalid or over-budget protocol invalid closes only its owned process and is not retried + --- + duration_ms: 1181.5339 + type: 'test' + ... +# Subtest: invalid or over-budget protocol oversized closes only its owned process and is not retried +ok 251 - invalid or over-budget protocol oversized closes only its owned process and is not retried + --- + duration_ms: 1267.9008 + type: 'test' + ... +# Subtest: cancel and timeout do not resend a dispatched request and pre-cancel has no request trace +ok 252 - cancel and timeout do not resend a dispatched request and pre-cancel has no request trace + --- + duration_ms: 1131.4746 + type: 'test' + ... +# Subtest: startup failure remains undispatched and has no process PID to terminate +ok 253 - startup failure remains undispatched and has no process PID to terminate + --- + duration_ms: 883.4452 + type: 'test' + ... +# Subtest: REA launch filters a fixture credential canary and rejects changed entry identity before a new connection +ok 254 - REA launch filters a fixture credential canary and rejects changed entry identity before a new connection + --- + duration_ms: 1400.5459 + type: 'test' + ... +# Subtest: model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart +ok 255 - model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart + --- + duration_ms: 1267.1751 + type: 'test' + ... +# Subtest: config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts +ok 256 - config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts + --- + duration_ms: 974.4407 + type: 'test' + ... +# Subtest: real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity +ok 257 - real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity + --- + duration_ms: 4076.1636 + type: 'test' + ... +# Subtest: pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests +ok 258 - pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests + --- + duration_ms: 4836.9146 + type: 'test' + ... +# Subtest: 401 blocks the credential revision; updating the key restores availability without leaking error echoes +ok 259 - 401 blocks the credential revision; updating the key restores availability without leaking error echoes + --- + duration_ms: 2032.5428 + type: 'test' + ... +# Subtest: queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request +ok 260 - queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request + --- + duration_ms: 1562.793 + type: 'test' + ... +# Subtest: compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model +ok 261 - compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model + --- + duration_ms: 3164.0362 + type: 'test' + ... +# Subtest: model registry disk failures restore routing, pool profiles and credential references without partial updates +ok 262 - model registry disk failures restore routing, pool profiles and credential references without partial updates + --- + duration_ms: 1227.9426 + type: 'test' + ... +# Subtest: model selection and saved configuration commit together and failures preserve the original mode and endpoint +ok 263 - model selection and saved configuration commit together and failures preserve the original mode and endpoint + --- + duration_ms: 1399.6462 + type: 'test' + ... +# Subtest: configuration imports roll back the entire batch and retain one usable preview after validation or commit failure +ok 264 - configuration imports roll back the entire batch and retain one usable preview after validation or commit failure + --- + duration_ms: 1085.4207 + type: 'test' + ... +# Subtest: paged inspection finds a corrupted old artifact outside the recent fifty and retains original evidence without model/tool execution +ok 265 - paged inspection finds a corrupted old artifact outside the recent fifty and retains original evidence without model/tool execution + --- + duration_ms: 5914.8644 + type: 'test' + ... +# Subtest: inspection rejects ambiguous/out-of-range pagination and reports unknown tool/task identity without resolving it +ok 266 - inspection rejects ambiguous/out-of-range pagination and reports unknown tool/task identity without resolving it + --- + duration_ms: 1119.3777 + type: 'test' + ... +# Subtest: exact patches preserve BOM/CRLF, unicode and all unselected bytes and back up the original on apply +ok 267 - exact patches preserve BOM/CRLF, unicode and all unselected bytes and back up the original on apply + --- + duration_ms: 1616.1902 + type: 'test' + ... +# Subtest: several patches are matched against one original snapshot in any input order and keep LF +ok 268 - several patches are matched against one original snapshot in any input order and keep LF + --- + duration_ms: 859.1506 + type: 'test' + ... +# Subtest: mixed line endings require exact anchors and preserve untouched formatting +ok 269 - mixed line endings require exact anchors and preserve untouched formatting + --- + duration_ms: 1131.9774 + type: 'test' + ... +# Subtest: ambiguous, overlapping, missing and malformed patch anchors never create a proposal or write +ok 270 - ambiguous, overlapping, missing and malformed patch anchors never create a proposal or write + --- + duration_ms: 1052.1221 + type: 'test' + ... +# Subtest: stale original hashes and changes before apply preserve owner edits and mark conflicts +ok 271 - stale original hashes and changes before apply preserve owner edits and mark conflicts + --- + duration_ms: 1301.23 + type: 'test' + ... +# Subtest: no-op BOM patches/full content produce no change and replacements cannot split Unicode bytes +ok 272 - no-op BOM patches/full content produce no change and replacements cannot split Unicode bytes + --- + duration_ms: 917.2972 + type: 'test' + ... +# Subtest: an actual shell command keeps Node and UTF-8 output while omitting host-only credentials +ok 273 - an actual shell command keeps Node and UTF-8 output while omitting host-only credentials + --- + duration_ms: 1083.7034 + type: 'test' + ... +# Subtest: real npm tests and build do not inherit arbitrary host credentials or Node injection settings +ok 274 - real npm tests and build do not inherit arbitrary host credentials or Node injection settings + --- + duration_ms: 3067.2175 + type: 'test' + ... +# Subtest: real Python tests and compilation keep their sealed inputs without host credentials +ok 275 - real Python tests and compilation keep their sealed inputs without host credentials + --- + duration_ms: 2998.4926 + type: 'test' + ... +# Subtest: JS/TS/React AST indexes actual declarations, exports, imports and verified source lines +ok 276 - JS/TS/React AST indexes actual declarations, exports, imports and verified source lines + --- + duration_ms: 978.5755 + type: 'test' + ... +# Subtest: default expressions, named default exports and declared functions retain their AST evidence +ok 277 - default expressions, named default exports and declared functions retain their AST evidence + --- + duration_ms: 1049.1484 + type: 'test' + ... +# Subtest: incremental refresh invalidates changed/deleted symbols and recalculates reused import targets +ok 278 - incremental refresh invalidates changed/deleted symbols and recalculates reused import targets + --- + duration_ms: 1243.1435 + type: 'test' + ... +# Subtest: Python candidates exclude comments and multiline strings and declare limited evidence +ok 279 - Python candidates exclude comments and multiline strings and declare limited evidence + --- + duration_ms: 983.226 + type: 'test' + ... +# Subtest: indexes isolate project identity and root and evict bounded caches without sharing results +ok 280 - indexes isolate project identity and root and evict bounded caches without sharing results + --- + duration_ms: 1271.76 + type: 'test' + ... +# Subtest: Git ignore, credential paths and links stay outside the index and no project files are executed +ok 281 - Git ignore, credential paths and links stay outside the index and no project files are executed + --- + duration_ms: 1534.544 + type: 'test' + ... +# Subtest: malformed, binary, non-UTF8 and bounded files expose partial coverage while good files remain searchable +ok 282 - malformed, binary, non-UTF8 and bounded files expose partial coverage while good files remain searchable + --- + duration_ms: 1493.9412 + type: 'test' + ... +# Subtest: index query rejects invalid limits/types and does not imply reference or alias resolution +ok 283 - index query rejects invalid limits/types and does not imply reference or alias resolution + --- + duration_ms: 1031.0674 + type: 'test' + ... +# Subtest: read-only engineering inspection disables configured Git clean filters and preserves index bytes +ok 284 - read-only engineering inspection disables configured Git clean filters and preserves index bytes + --- + duration_ms: 2540.4502 + type: 'test' + ... +# Subtest: Python multiline declarations retain candidate scope without interpreting expressions as declarations +ok 285 - Python multiline declarations retain candidate scope without interpreting expressions as declarations + --- + duration_ms: 1029.9861 + type: 'test' + ... +# Subtest: TypeScript module candidates support import-equals and MTS/CTS while opaque imports stay explicit +ok 286 - TypeScript module candidates support import-equals and MTS/CTS while opaque imports stay explicit + --- + duration_ms: 1084.3017 + type: 'test' + ... +# Subtest: actual HTTP requests reuse only this project source-checked memory as redacted data and preserve sent evidence after archive/restart +ok 287 - actual HTTP requests reuse only this project source-checked memory as redacted data and preserve sent evidence after archive/restart + --- + duration_ms: 3199.8402 + type: 'test' + ... +# Subtest: actual HTTP request excludes archived, timed-out and foreign-project memories +ok 288 - actual HTTP request excludes archived, timed-out and foreign-project memories + --- + duration_ms: 3818.3281 + type: 'test' + ... +# Subtest: actual next HTTP request removes expired memory after a tool observes a source change without replaying that tool +ok 289 - actual next HTTP request removes expired memory after a tool observes a source change without replaying that tool + --- + duration_ms: 3980.9926 + type: 'test' + ... +# Subtest: incomplete inventory and excluded-file SHA changes cannot enter actual HTTP memory context or inspect_session snapshots +ok 290 - incomplete inventory and excluded-file SHA changes cannot enter actual HTTP memory context or inspect_session snapshots + --- + duration_ms: 4516.9735 + type: 'test' + ... +# Subtest: corrupt original artifact expires its memory and cannot reach an HTTP model request +ok 291 - corrupt original artifact expires its memory and cannot reach an HTTP model request + --- + duration_ms: 3174.2254 + type: 'test' + ... +# Subtest: memory JSON is bounded in escaped UTF-8 bytes and entry count, skips oversized entries and retains complete multilingual values +ok 292 - memory JSON is bounded in escaped UTF-8 bytes and entry count, skips oversized entries and retains complete multilingual values + --- + duration_ms: 4837.3517 + type: 'test' + ... +# Subtest: optional memory yields to the complete goal and original code evidence under the whole-request budget +ok 293 - optional memory yields to the complete goal and original code evidence under the whole-request budget + --- + duration_ms: 1780.6192 + type: 'test' + ... +# Subtest: changed sealed memory artifacts or binding fields fail verification while the original request remains immutable +ok 294 - changed sealed memory artifacts or binding fields fail verification while the original request remains immutable + --- + duration_ms: 1817.1388 + type: 'test' + ... +# Subtest: a malformed project declaration omits optional memory while the repair Task still reaches the owned HTTP service +ok 295 - a malformed project declaration omits optional memory while the repair Task still reaches the owned HTTP service + --- + duration_ms: 2149.0947 + type: 'test' + ... +# Subtest: an expiration persistence failure prevents dispatch and is not hidden as an optional scan failure +ok 296 - an expiration persistence failure prevents dispatch and is not hidden as an optional scan failure + --- + duration_ms: 1839.0773 + type: 'test' + ... +# Subtest: project memories persist across restart, keep source provenance, and are visible across tasks +ok 297 - project memories persist across restart, keep source provenance, and are visible across tasks + --- + duration_ms: 1974.1915 + type: 'test' + ... +# Subtest: source changes expire current project memories and keep the original evidence +ok 298 - source changes expire current project memories and keep the original evidence + --- + duration_ms: 1855.6655 + type: 'test' + ... +# Subtest: incomplete source scans mark current memories unverified without expiring or reusing them +ok 299 - incomplete source scans mark current memories unverified without expiring or reusing them + --- + duration_ms: 1666.3958 + type: 'test' + ... +# Subtest: explicit file provenance is rechecked even when the inventory excludes that path +ok 300 - explicit file provenance is rechecked even when the inventory excludes that path + --- + duration_ms: 1911.2449 + type: 'test' + ... +# Subtest: execution snapshots do not expose project memories before their source scope is validated +ok 301 - execution snapshots do not expose project memories before their source scope is validated + --- + duration_ms: 1218.5136 + type: 'test' + ... +# Subtest: project memory records stay isolated and archive requires the owning session +ok 302 - project memory records stay isolated and archive requires the owning session + --- + duration_ms: 1943.1947 + type: 'test' + ... +# Subtest: project memory HTTP API exposes read-only source status and explicit writes +ok 303 - project memory HTTP API exposes read-only source status and explicit writes + --- + duration_ms: 3339.5661 + type: 'test' + ... +# Subtest: two Purge source versions lock nine original inputs without executing JavaScript or postinstall and remain disabled by default +ok 304 - two Purge source versions lock nine original inputs without executing JavaScript or postinstall and remain disabled by default + --- + duration_ms: 947.8624 + type: 'test' + ... +# Subtest: incomplete, unsupported, relative and oversized sources cannot enable the experiment +ok 305 - incomplete, unsupported, relative and oversized sources cannot enable the experiment + --- + duration_ms: 1073.3619 + type: 'test' + ... +# Subtest: invalid source fingerprints and invented privilege or retry fields fail before any parent Task is created +ok 306 - invalid source fingerprints and invented privilege or retry fields fail before any parent Task is created + --- + duration_ms: 3010.3727 + type: 'test' + ... +# Subtest: source edits between detection and plan are rejected without creating a parent Task +ok 307 - source edits between detection and plan are rejected without creating a parent Task + --- + duration_ms: 2457.4517 + type: 'test' + ... +# Subtest: source edits after sealing cannot launch a child and do not reset its cumulative budget +ok 308 - source edits after sealing cannot launch a child and do not reset its cumulative budget + --- + duration_ms: 8933.6082 + type: 'test' + ... +# Subtest: literal experiment text is sealed into the parent, worker and each new Run while actual host approvals and saved results remain required +ok 309 - literal experiment text is sealed into the parent, worker and each new Run while actual host approvals and saved results remain required + --- + duration_ms: 26178.4072 + type: 'test' + ... +# Subtest: source changes after a model response stop before any native tool is accepted, retaining the actual usage once +ok 310 - source changes after a model response stop before any native tool is accepted, retaining the actual usage once + --- + duration_ms: 10866.7532 + type: 'test' + ... +# Subtest: source changes while approval is pending invalidate the old permission before an engineering check starts +ok 311 - source changes while approval is pending invalidate the old permission before an engineering check starts + --- + duration_ms: 14469.0129 + type: 'test' + ... +# Subtest: altered text, interpolation, section order and policy flags cannot reuse a sealed experiment +ok 312 - altered text, interpolation, section order and policy flags cannot reuse a sealed experiment + --- + duration_ms: 3262.7912 + type: 'test' + ... +# Subtest: the observed SDK system-message layout and the explicit system field both require exactly one effective section, never a user or tool copy +ok 313 - the observed SDK system-message layout and the explicit system field both require exactly one effective section, never a user or tool copy + --- + duration_ms: 3305.6996 + type: 'test' + ... +# Subtest: a missing or duplicated experimental section in the actual input is rejected before any model dispatch +ok 314 - a missing or duplicated experimental section in the actual input is rejected before any model dispatch + --- + duration_ms: 22188.7311 + type: 'test' + ... +# Subtest: experimental prompt overhead still participates in the original complete-input budget guard +ok 315 - experimental prompt overhead still participates in the original complete-input budget guard + --- + duration_ms: 11118.043 + type: 'test' + ... +# Subtest: source detection HTTP remains local-authenticated and read-only with no configured model requests +ok 316 - source detection HTTP remains local-authenticated and read-only with no configured model requests + --- + duration_ms: 2265.6478 + type: 'test' + ... +# Subtest: Python HTTP plans keep npm defaults, require owned approval and preserve actual results across restart +ok 317 - Python HTTP plans keep npm defaults, require owned approval and preserve actual results across restart + --- + duration_ms: 9597.5843 + type: 'test' + ... +# Subtest: an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls +ok 318 - an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls + --- + duration_ms: 37216.2256 + type: 'test' + ... +# Subtest: Python static inspection does not import project code or probe a project interpreter before approval +ok 319 - Python static inspection does not import project code or probe a project interpreter before approval + --- + duration_ms: 1105.8078 + type: 'test' + ... +# Subtest: a real three-module Python failure, reviewed repairs, tests and compilation retain exact structured evidence +ok 320 - a real three-module Python failure, reviewed repairs, tests and compilation retain exact structured evidence + --- + duration_ms: 5284.2059 + type: 'test' + ... +# Subtest: unittest counts repeated execution ordinals and subtest skips rather than deduplicating display names +ok 321 - unittest counts repeated execution ordinals and subtest skips rather than deduplicating display names + --- + duration_ms: 3004.5494 + type: 'test' + ... +# Subtest: unittest empty, skipped, expected failure and class initialization errors never verify a task +ok 322 - unittest empty, skipped, expected failure and class initialization errors never verify a task + --- + duration_ms: 9908.2778 + type: 'test' + ... +# Subtest: stdout claims cannot replace actual unittest results and an early exit cannot forge a successful collector +ok 323 - stdout claims cannot replace actual unittest results and an early exit cannot forge a successful collector + --- + duration_ms: 2984.9671 + type: 'test' + ... +# Subtest: compilation reads actual Python source bytes without executing top-level project code +ok 324 - compilation reads actual Python source bytes without executing top-level project code + --- + duration_ms: 2849.3259 + type: 'test' + ... +# Subtest: Node and Python mixed projects retain the existing npm default and require an explicit Python selection +ok 325 - Node and Python mixed projects retain the existing npm default and require an explicit Python selection + --- + duration_ms: 2646.0794 + type: 'test' + ... +# Subtest: changed project interpreters and forged Python plan bindings execute no check +ok 326 - changed project interpreters and forged Python plan bindings execute no check + --- + duration_ms: 2011.8589 + type: 'test' + ... +# Subtest: malformed TOML and invalid Python test paths are reported without expanding npm check scope +ok 327 - malformed TOML and invalid Python test paths are reported without expanding npm check scope + --- + duration_ms: 1661.4485 + type: 'test' + ... +# Subtest: stopping a real Python check terminates its child and keeps the completed result as cancelled +ok 328 - stopping a real Python check terminates its child and keeps the completed result as cancelled + --- + duration_ms: 2262.6527 + type: 'test' + ... +# Subtest: real pytest pass, failure, skip, collection errors and teardown errors use collected case outcomes +ok 329 - real pytest pass, failure, skip, collection errors and teardown errors use collected case outcomes + --- + duration_ms: 17014.3641 + type: 'test' + ... +# Subtest: a real project virtual environment is detected statically and its actual version is recorded only during the approved check +ok 330 - a real project virtual environment is detected statically and its actual version is recorded only during the approved check + --- + duration_ms: 8894.2478 + type: 'test' + ... +# Subtest: a missing interpreter and repeated pytest item objects cannot create a false verification pass +ok 331 - a missing interpreter and repeated pytest item objects cannot create a false verification pass + --- + duration_ms: 3428.4015 + type: 'test' + ... +# Subtest: continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause +ok 332 - continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause + --- + duration_ms: 2.345 + type: 'test' + ... +# Subtest: a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget +ok 333 - a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget + --- + duration_ms: 0.6919 + type: 'test' + ... +# Subtest: budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters +ok 334 - budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters + --- + duration_ms: 10.0037 + type: 'test' + ... +# Subtest: known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress +ok 335 - known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress + --- + duration_ms: 0.3528 + type: 'test' + ... +# Subtest: actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools +ok 336 - actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools + --- + duration_ms: 4637.8491 + type: 'test' + ... +# Subtest: a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly +ok 337 - a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly + --- + duration_ms: 5975.0501 + type: 'test' + ... +# Subtest: actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay +ok 338 - actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay + --- + duration_ms: 7779.9737 + type: 'test' + ... +# Subtest: an installed app outside the source drive resolves registered SDK and Purge through actual input verification +ok 339 - an installed app outside the source drive resolves registered SDK and Purge through actual input verification + --- + duration_ms: 864.0353 + type: 'test' + ... +# Subtest: standalone registration resolves the upstream metadata directory and missing upstream falls back to the other registered source +ok 340 - standalone registration resolves the upstream metadata directory and missing upstream falls back to the other registered source + --- + duration_ms: 1268.8261 + type: 'test' + ... +# Subtest: registered hints keep explicit roots, environment and existing app-relative candidates in their original priority +ok 341 - registered hints keep explicit roots, environment and existing app-relative candidates in their original priority + --- + duration_ms: 1258.9823 + type: 'test' + ... +# Subtest: unknown IDs, duplicate registered IDs, wrong versions and relative or inconsistent metadata are not lookup candidates +ok 342 - unknown IDs, duplicate registered IDs, wrong versions and relative or inconsistent metadata are not lookup candidates + --- + duration_ms: 955.7162 + type: 'test' + ... +# Subtest: oversized, malformed, invalid UTF-8 and non-file registry inputs cannot silently enable a source +ok 343 - oversized, malformed, invalid UTF-8 and non-file registry inputs cannot silently enable a source + --- + duration_ms: 1171.0228 + type: 'test' + ... +# Subtest: a linked registry directory is rejected without reading or deleting its external source +ok 344 - a linked registry directory is rejected without reading or deleting its external source + --- + duration_ms: 1043.1926 + type: 'test' + ... +# Subtest: matching research declarations do not replace actual installed version and critical-source checks +ok 345 - matching research declarations do not replace actual installed version and critical-source checks + --- + duration_ms: 867.4705 + type: 'test' + ... +# Subtest: context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs +ok 346 - context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs + --- + duration_ms: 4330.066 + type: 'test' + ... +# Subtest: delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification +ok 347 - delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification + --- + duration_ms: 2788.8259 + type: 'test' + ... +# Subtest: direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget +ok 348 - direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget + --- + duration_ms: 2225.019 + type: 'test' + ... +# Subtest: one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments +ok 349 - one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments + --- + duration_ms: 5496.3572 + type: 'test' + ... +# Subtest: tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests +ok 350 - tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests + --- + duration_ms: 983.4178 + type: 'test' + ... +# Subtest: oversized required user instructions pause intact and can be explicitly resumed after increasing the window +ok 351 - oversized required user instructions pause intact and can be explicitly resumed after increasing the window + --- + duration_ms: 2341.8355 + type: 'test' + ... +# Subtest: all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix +ok 352 - all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix + --- + duration_ms: 1468.8847 + type: 'test' + ... +# Subtest: a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived +ok 353 - a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived + --- + duration_ms: 1323.6809 + type: 'test' + ... +# Subtest: invalid orphan result is rejected before archive or network preparation +ok 354 - invalid orphan result is rejected before archive or network preparation + --- + duration_ms: 846.9853 + type: 'test' + ... +# Subtest: invalid missing result is rejected before archive or network preparation +ok 355 - invalid missing result is rejected before archive or network preparation + --- + duration_ms: 778.6651 + type: 'test' + ... +# Subtest: invalid wrong result is rejected before archive or network preparation +ok 356 - invalid wrong result is rejected before archive or network preparation + --- + duration_ms: 963.2598 + type: 'test' + ... +# Subtest: invalid duplicate call is rejected before archive or network preparation +ok 357 - invalid duplicate call is rejected before archive or network preparation + --- + duration_ms: 1110.9371 + type: 'test' + ... +# Subtest: a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON +ok 358 - a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON + --- + duration_ms: 2275.0647 + type: 'test' + ... +# Subtest: changed or missing archived evidence stops reuse and is never silently recreated +ok 359 - changed or missing archived evidence stops reuse and is never silently recreated + --- + duration_ms: 1276.9178 + type: 'test' + ... +# Subtest: transaction failure prevents publishing a plan and any corresponding model request +ok 360 - transaction failure prevents publishing a plan and any corresponding model request + --- + duration_ms: 1310.0854 + type: 'test' + ... +# Subtest: the Provider rejects body mutation after a sealed plan before calling HTTP +ok 361 - the Provider rejects body mutation after a sealed plan before calling HTTP + --- + duration_ms: 1195.6762 + type: 'test' + ... +# Subtest: HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command +ok 362 - HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command + --- + duration_ms: 8111.4124 + type: 'test' + ... +# Subtest: a real process exit after plan persistence marks interruption and never issues an automatic model request +ok 363 - a real process exit after plan persistence marks interruption and never issues an automatic model request + --- + duration_ms: 1814.9161 + type: 'test' + ... +# Subtest: deep Windows data directories keep REA output within the external path allowance and retain owned evidence +ok 364 - deep Windows data directories keep REA output within the external path allowance and retain owned evidence + --- + duration_ms: 3177.5407 + type: 'test' + ... +# Subtest: user research registration creates an owned Task without model requests and seals the exact artifact identity +ok 365 - user research registration creates an owned Task without model requests and seals the exact artifact identity + --- + duration_ms: 1237.2896 + type: 'test' + ... +# Subtest: complete research binds original Evidence and Bundle, pages exact fields and reuses verified results after reload +ok 366 - complete research binds original Evidence and Bundle, pages exact fields and reuses verified results after reload + --- + duration_ms: 2530.948 + type: 'test' + ... +# Subtest: artifact changes before analysis refuse dispatch and changes during analysis preserve unverified original responses +ok 367 - artifact changes before analysis refuse dispatch and changes during analysis preserve unverified original responses + --- + duration_ms: 3371.5073 + type: 'test' + ... +# Subtest: owned cancellation closes the connection, concurrent and automatic retries are refused, explicit new analysis preserves history +ok 368 - owned cancellation closes the connection, concurrent and automatic retries are refused, explicit new analysis preserves history + --- + duration_ms: 2630.9083 + type: 'test' + ... +# Subtest: a dispatched transport timeout stays unknown and reload never launches or kills a saved PID +ok 369 - a dispatched transport timeout stays unknown and reload never launches or kills a saved PID + --- + duration_ms: 2408.1235 + type: 'test' + ... +# Subtest: corrupt Evidence parts and changed binding records are refused instead of silently re-analysed +ok 370 - corrupt Evidence parts and changed binding records are refused instead of silently re-analysed + --- + duration_ms: 2600.0027 + type: 'test' + ... +# Subtest: research documents over the single-artifact limit preserve exact Unicode bytes with owned verifiable parts +ok 371 - research documents over the single-artifact limit preserve exact Unicode bytes with owned verifiable parts + --- + duration_ms: 1239.1158 + type: 'test' + ... +# Subtest: research tools are only sent for registered Task artifacts and actual HTTP uses the sealed tool contract without replay +ok 372 - research tools are only sent for registered Task artifacts and actual HTTP uses the sealed tool contract without replay + --- + duration_ms: 4513.9145 + type: 'test' + ... +# Subtest: file identity rejects directory and invalid formats without running a target +ok 373 - file identity rejects directory and invalid formats without running a target + --- + duration_ms: 677.0361 + type: 'test' + ... +# Subtest: a stop from the event loop interrupts immediate model replies before later tools +ok 374 - a stop from the event loop interrupts immediate model replies before later tools + --- + duration_ms: 1889.8982 + type: 'test' + ... +# Subtest: a stop after the first tool preserves a complete interrupted multi-call protocol group +ok 375 - a stop after the first tool preserves a complete interrupted multi-call protocol group + --- + duration_ms: 2792.3363 + type: 'test' + ... +# Subtest: the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands +ok 376 - the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands + --- + duration_ms: 6091.5232 + type: 'test' + ... +# Subtest: denial prevents command execution and produces a paired denied result +ok 377 - denial prevents command execution and produces a paired denied result + --- + duration_ms: 2602.7045 + type: 'test' + ... +# Subtest: stopping during approval interrupts pending calls without executing or replaying them +ok 378 - stopping during approval interrupts pending calls without executing or replaying them + --- + duration_ms: 1968.9531 + type: 'test' + ... +# Subtest: stopping a running fixture command terminates its own process tree and retains uncertain state +ok 379 - stopping a running fixture command terminates its own process tree and retains uncertain state + --- + duration_ms: 2446.1751 + type: 'test' + ... +# Subtest: command output decodes split UTF-8 and excludes the workbench key from child environment +ok 380 - command output decodes split UTF-8 and excludes the workbench key from child environment + --- + duration_ms: 1450.1783 + type: 'test' + ... +# Subtest: model-list testing uses a tentative key without changing the saved connection and redacts service errors +ok 381 - model-list testing uses a tentative key without changing the saved connection and redacts service errors + --- + duration_ms: 7.2302 + type: 'test' + ... +# Subtest: truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities +ok 382 - truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities + --- + duration_ms: 3308.3946 + type: 'test' + ... +# Subtest: request projection keeps exact tool pairs and complete recent user instructions while preserving disk history +ok 383 - request projection keeps exact tool pairs and complete recent user instructions while preserving disk history + --- + duration_ms: 1817.6833 + type: 'test' + ... +# Subtest: local skill revisions require explicit enable, retain original text, survive restart and stay within the selected project +ok 384 - local skill revisions require explicit enable, retain original text, survive restart and stay within the selected project + --- + duration_ms: 1382.6899 + type: 'test' + ... +# Subtest: registration rejects non-SKILL paths, oversized/non-UTF8 files, duplicate sources and wrong field shapes without running project code +ok 385 - registration rejects non-SKILL paths, oversized/non-UTF8 files, duplicate sources and wrong field shapes without running project code + --- + duration_ms: 1079.1966 + type: 'test' + ... +# Subtest: actual HTTP models receive only enabled current-project metadata, then a redacted owned skill page with complete tool pairing +ok 386 - actual HTTP models receive only enabled current-project metadata, then a redacted owned skill page with complete tool pairing + --- + duration_ms: 3206.6589 + type: 'test' + ... +# Subtest: source edits after a catalog request prevent the read and appear as changed on the next request without replay +ok 387 - source edits after a catalog request prevent the read and appear as changed on the next request without replay + --- + duration_ms: 2937.0579 + type: 'test' + ... +# Subtest: disabled and foreign skills cannot be read by guessing their IDs from another project +ok 388 - disabled and foreign skills cannot be read by guessing their IDs from another project + --- + duration_ms: 2940.2385 + type: 'test' + ... +# Subtest: skill catalog takes remaining escaped JSON budget and cannot evict the user goal or current code +ok 389 - skill catalog takes remaining escaped JSON budget and cannot evict the user goal or current code + --- + duration_ms: 1403.0579 + type: 'test' + ... +# Subtest: multilingual skill body pages fit actual tool JSON bytes and every page uses the same immutable artifact +ok 390 - multilingual skill body pages fit actual tool JSON bytes and every page uses the same immutable artifact + --- + duration_ms: 4282.6176 + type: 'test' + ... +# Subtest: registry failures roll back enable and refresh state; corrupted snapshots block requests before network +ok 391 - registry failures roll back enable and refresh state; corrupted snapshots block requests before network + --- + duration_ms: 1579.8693 + type: 'test' + ... +# Subtest: saved skill catalogs retain SHA-bound historical evidence and reject corrupt catalog blobs +ok 392 - saved skill catalogs retain SHA-bound historical evidence and reject corrupt catalog blobs + --- + duration_ms: 2325.0983 + type: 'test' + ... +# Subtest: HTTP skill administration enforces project scope, revision checks and idle mutation without model calls +ok 393 - HTTP skill administration enforces project scope, revision checks and idle mutation without model calls + --- + duration_ms: 3430.526 + type: 'test' + ... +# Subtest: JSON state keeps an atomic backup and preserves corrupt primary files +ok 394 - JSON state keeps an atomic backup and preserves corrupt primary files + --- + duration_ms: 916.7804 + type: 'test' + ... +# Subtest: tool-pair recovery fills missing results and drops orphan or duplicate results +ok 395 - tool-pair recovery fills missing results and drops orphan or duplicate results + --- + duration_ms: 0.3227 + type: 'test' + ... +# Subtest: restart pauses unfinished work, retains proposals and never replays a command +ok 396 - restart pauses unfinished work, retains proposals and never replays a command + --- + duration_ms: 737.4083 + type: 'test' + ... +# Subtest: public snapshots carry increasing revisions without the private provider transcript or config key +ok 397 - public snapshots carry increasing revisions without the private provider transcript or config key + --- + duration_ms: 1152.4341 + type: 'test' + ... +# Subtest: a checkpoint seals all task requirements and original results without a model request and explicit continuation keeps the same Task without replay +ok 398 - a checkpoint seals all task requirements and original results without a model request and explicit continuation keeps the same Task without replay + --- + duration_ms: 4010.6984 + type: 'test' + ... +# Subtest: checkpoint sources, requirements, plan and original tool changes block continuation and leave original checkpoint bytes intact +ok 399 - checkpoint sources, requirements, plan and original tool changes block continuation and leave original checkpoint bytes intact + --- + duration_ms: 2371.2442 + type: 'test' + ... +# Subtest: unknown tool effects and pending proposals stay blocked in recovery packages rather than being changed into completed work +ok 400 - unknown tool effects and pending proposals stay blocked in recovery packages rather than being changed into completed work + --- + duration_ms: 2511.541 + type: 'test' + ... +# Subtest: checkpoint and referenced result corruption are rejected before dispatch and historical blobs are never rebuilt +ok 401 - checkpoint and referenced result corruption are rejected before dispatch and historical blobs are never rebuilt + --- + duration_ms: 2922.6581 + type: 'test' + ... +# Subtest: checkpoint ownership, exact confirmation and concurrent operations reject foreign or stale resumes +ok 402 - checkpoint ownership, exact confirmation and concurrent operations reject foreign or stale resumes + --- + duration_ms: 3489.5411 + type: 'test' + ... +# Subtest: Git identity changes and altered plan proofs cannot be accepted as the sealed recovery state +ok 403 - Git identity changes and altered plan proofs cannot be accepted as the sealed recovery state + --- + duration_ms: 3758.1393 + type: 'test' + ... +# Subtest: checkpoint records survive SQLite reopen and do not trigger automatic model or tool replay +ok 404 - checkpoint records survive SQLite reopen and do not trigger automatic model or tool replay + --- + duration_ms: 2799.0144 + type: 'test' + ... +# Subtest: incomplete scans and in-progress project activity refuse checkpoint creation while private credentials are redacted from saved requirements +ok 405 - incomplete scans and in-progress project activity refuse checkpoint creation while private credentials are redacted from saved requirements + --- + duration_ms: 2254.4948 + type: 'test' + ... +# Subtest: oversized recovery evidence is refused before reading or publishing the checkpoint +ok 406 - oversized recovery evidence is refused before reading or publishing the checkpoint + --- + duration_ms: 2099.2077 + type: 'test' + ... +# Subtest: compiled checkpoint HTTP APIs bind current Task/Run, isolate sessions and only resume on an explicit matching confirmation +ok 407 - compiled checkpoint HTTP APIs bind current Task/Run, isolate sessions and only resume on an explicit matching confirmation + --- + duration_ms: 6043.2037 + type: 'test' + ... +# Subtest: actual process exit before checkpoint commit retains only durable records without replay +ok 408 - actual process exit before checkpoint commit retains only durable records without replay + --- + duration_ms: 2219.8633 + type: 'test' + ... +# Subtest: actual process exit after checkpoint commit retains only durable records without replay +ok 409 - actual process exit after checkpoint commit retains only durable records without replay + --- + duration_ms: 2131.1341 + type: 'test' + ... +# Subtest: task-plan HTTP mutations bind current Task/Run and retain original evidence through real host restart +ok 410 - task-plan HTTP mutations bind current Task/Run and retain original evidence through real host restart + --- + duration_ms: 5385.145 + type: 'test' + ... +# Subtest: concurrent stale HTTP plan revisions cannot replace conditions or attach proofs to a different plan +ok 411 - concurrent stale HTTP plan revisions cannot replace conditions or attach proofs to a different plan + --- + duration_ms: 3030.7089 + type: 'test' + ... +# Subtest: a real escaped long-file tool message keeps its proof identity within a tight request budget +ok 412 - a real escaped long-file tool message keeps its proof identity within a tight request budget + --- + duration_ms: 1714.3478 + type: 'test' + ... +# Subtest: task plans reject fabricated completion, invalid scopes and cyclic or missing dependencies +ok 413 - task plans reject fabricated completion, invalid scopes and cyclic or missing dependencies + --- + duration_ms: 0.4586 + type: 'test' + ... +# Subtest: sealed plans retain goal, contract hash and original steps through SQLite reopen without executing tools +ok 414 - sealed plans retain goal, contract hash and original steps through SQLite reopen without executing tools + --- + duration_ms: 1166.0492 + type: 'test' + ... +# Subtest: proofs require original owned reads, honor dependencies and reject altered invocation arguments and bytes +ok 415 - proofs require original owned reads, honor dependencies and reject altered invocation arguments and bytes + --- + duration_ms: 2078.5233 + type: 'test' + ... +# Subtest: new user requirements invalidate current proofs and reseal the same original operations in a new revision +ok 416 - new user requirements invalidate current proofs and reseal the same original operations in a new revision + --- + duration_ms: 1867.6061 + type: 'test' + ... +# Subtest: applied change-set evidence binds reviewed current files and invalidates dependent steps after outside edits +ok 417 - applied change-set evidence binds reviewed current files and invalidates dependent steps after outside edits + --- + duration_ms: 2628.3678 + type: 'test' + ... +# Subtest: actual npm checks are verified by original counted logs and current source, with failure history retained +ok 418 - actual npm checks are verified by original counted logs and current source, with failure history retained + --- + duration_ms: 7153.8999 + type: 'test' + ... +# Subtest: real desktop and mobile browser proofs bind required actions and PNGs, rejecting source changes, a later failed plan and changed builds +ok 419 - real desktop and mobile browser proofs bind required actions and PNGs, rejecting source changes, a later failed plan and changed builds + --- + duration_ms: 12903.0697 + type: 'test' + ... +# Subtest: Git delivery blocks incomplete plans and changed preview bindings, preserving HEAD and owner index before a fresh verified commit +ok 420 - Git delivery blocks incomplete plans and changed preview bindings, preserving HEAD and owner index before a fresh verified commit + --- + duration_ms: 11297.0311 + type: 'test' + ... +# Subtest: the runtime supplies owned read IDs and completes a plan only after original step evidence verification +ok 421 - the runtime supplies owned read IDs and completes a plan only after original step evidence verification + --- + duration_ms: 3398.1831 + type: 'test' + ... +# Subtest: premature model completion pauses the original Task and resume preserves the existing plan without replay +ok 422 - premature model completion pauses the original Task and resume preserves the existing plan without replay + --- + duration_ms: 4616.5629 + type: 'test' + ... +# Subtest: plan operations participate in project activity and orderly shutdown +ok 423 - plan operations participate in project activity and orderly shutdown + --- + duration_ms: 769.6681 + type: 'test' + ... +# Subtest: actual process exit before plan save restores only committed plan evidence without replay +ok 424 - actual process exit before plan save restores only committed plan evidence without replay + --- + duration_ms: 1405.4097 + type: 'test' + ... +# Subtest: actual process exit after plan save restores only committed plan evidence without replay +ok 425 - actual process exit after plan save restores only committed plan evidence without replay + --- + duration_ms: 1918.1163 + type: 'test' + ... +# Subtest: actual process exit before proof save restores only committed plan evidence without replay +ok 426 - actual process exit before proof save restores only committed plan evidence without replay + --- + duration_ms: 1918.8974 + type: 'test' + ... +# Subtest: actual process exit after proof save restores only committed plan evidence without replay +ok 427 - actual process exit after proof save restores only committed plan evidence without replay + --- + duration_ms: 1444.1892 + type: 'test' + ... +# Subtest: the latest oversized session result reaches the next request together with already read source modules +ok 428 - the latest oversized session result reaches the next request together with already read source modules + --- + duration_ms: 2138.1905 + type: 'test' + ... +# Subtest: every call in a large latest group keeps its actual outcome, including denied and unknown results +ok 429 - every call in a large latest group keeps its actual outcome, including denied and unknown results + --- + duration_ms: 2019.0278 + type: 'test' + ... +# Subtest: a small complete latest tool group is sent once and needs no duplicate feedback view +ok 430 - a small complete latest tool group is sent once and needs no duplicate feedback view + --- + duration_ms: 1175.145 + type: 'test' + ... +# Subtest: real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing +ok 431 - real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing + --- + duration_ms: 2822.1713 + type: 'test' + ... +# Subtest: a live SQLite host with the actual 1.9 artifact object upgrades, keeps its original blobs and verifies real browser PNG bytes +ok 432 - a live SQLite host with the actual 1.9 artifact object upgrades, keeps its original blobs and verifies real browser PNG bytes + --- + duration_ms: 3895.4421 + type: 'test' + ... +# Subtest: failed upgrade restores the original artifact object, provider and request handler +ok 433 - failed upgrade restores the original artifact object, provider and request handler + --- + duration_ms: 1627.4643 + type: 'test' + ... +# Subtest: claiming the same runtime owner twice preserves its original metadata and every database row +ok 434 - claiming the same runtime owner twice preserves its original metadata and every database row + --- + duration_ms: 861.065 + type: 'test' + ... +# Subtest: sessions without controlled-engine history retain their prior export shape and never expose another session record +ok 435 - sessions without controlled-engine history retain their prior export shape and never expose another session record + --- + duration_ms: 1001.4323 + type: 'test' + ... +# Subtest: live workers, controlled drivers, or MCP operations refuse an upgrade before changing handlers, managers or database rows +ok 436 - live workers, controlled drivers, or MCP operations refuse an upgrade before changing handlers, managers or database rows + --- + duration_ms: 1055.7659 + type: 'test' + ... +# Subtest: an idle upgrade loads the newly introduced engine record map, resets obsolete managers and preserves original rows, sessions and provider objects +ok 437 - an idle upgrade loads the newly introduced engine record map, resets obsolete managers and preserves original rows, sessions and provider objects + --- + duration_ms: 1079.6512 + type: 'test' + ... +# Subtest: an installation failure restores old managers, original record maps, handlers and all existing database rows +ok 438 - an installation failure restores old managers, original record maps, handlers and all existing database rows + --- + duration_ms: 1531.1783 + type: 'test' + ... +# Subtest: the owned controlled driver remains an active session and project even after outer task activity has ended +ok 439 - the owned controlled driver remains an active session and project even after outer task activity has ended + --- + duration_ms: 1019.0333 + type: 'test' + ... +# Subtest: release and upgrade help or invalid arguments have no file or network setup side effects in an independent directory +ok 440 - release and upgrade help or invalid arguments have no file or network setup side effects in an independent directory + --- + duration_ms: 1044.2352 + type: 'test' + ... +# Subtest: hot upgrade adopts a retained virtual data root without reopening SQLite or changing rows, Provider or routing +ok 441 - hot upgrade adopts a retained virtual data root without reopening SQLite or changing rows, Provider or routing + --- + duration_ms: 1383.8303 + type: 'test' + ... +# Subtest: failed adoption restores the original virtual data-root name and original open database +ok 442 - failed adoption restores the original virtual data-root name and original open database + --- + duration_ms: 935.6407 + type: 'test' + ... +# Subtest: hot upgrade refreshes retained model and importer methods while preserving credential and routing objects +ok 443 - hot upgrade refreshes retained model and importer methods while preserving credential and routing objects + --- + duration_ms: 912.3748 + type: 'test' + ... +# Subtest: hot upgrade refuses active probes and restores retained model methods if installation fails +ok 444 - hot upgrade refuses active probes and restores retained model methods if installation fails + --- + duration_ms: 1029.7805 + type: 'test' + ... +# Subtest: a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider +ok 445 - a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider + --- + duration_ms: 3618.8973 + type: 'test' + ... +# Subtest: the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection +ok 446 - the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection + --- + duration_ms: 7364.1566 + type: 'test' + ... +# Subtest: HTTP worker identities require a current sealed plan, reject overrides and close unused plans without touching source +ok 447 - HTTP worker identities require a current sealed plan, reject overrides and close unused plans without touching source + --- + duration_ms: 13360.8558 + type: 'test' + ... +# Subtest: HTTP unknown recovery only accepts the original evidence SHA and preserves changed source for explicit retention +ok 448 - HTTP unknown recovery only accepts the original evidence SHA and preserves changed source for explicit retention + --- + duration_ms: 17331.9326 + type: 'test' + ... +# Subtest: verified isolated outputs form a new parent batch, rerun real checks and commit only reviewed source +ok 449 - verified isolated outputs form a new parent batch, rerun real checks and commit only reviewed source + --- + duration_ms: 45540.1727 + type: 'test' + ... +# Subtest: overlapping worker paths are explicit conflicts even if each independent task checks successfully +ok 450 - overlapping worker paths are explicit conflicts even if each independent task checks successfully + --- + duration_ms: 30487.8382 + type: 'test' + ... +# Subtest: source edits after isolated work preserve the owner file and invalidate collection without proposing a merge +ok 451 - source edits after isolated work preserve the owner file and invalidate collection without proposing a merge + --- + duration_ms: 27852.8944 + type: 'test' + ... +# Subtest: changed child bytes after parent preview block the entire batch before any parent write +ok 452 - changed child bytes after parent preview block the entire batch before any parent write + --- + duration_ms: 35067.1163 + type: 'test' + ... +# Subtest: corrupt original check logs cannot become collected outputs or a parent review +ok 453 - corrupt original check logs cannot become collected outputs or a parent review + --- + duration_ms: 26149.4111 + type: 'test' + ... +# Subtest: stopping a parent accounts late responses and executes none of their proposed tools +ok 454 - stopping a parent accounts late responses and executes none of their proposed tools + --- + duration_ms: 14190.7893 + type: 'test' + ... +# Subtest: unreported interrupted requests reserve estimated usage and the total deadline cannot reset on resume +ok 455 - unreported interrupted requests reserve estimated usage and the total deadline cannot reset on resume + --- + duration_ms: 13922.0036 + type: 'test' + ... +# Subtest: a response exceeding the cumulative token allocation stops before registering or executing its tools +ok 456 - a response exceeding the cumulative token allocation stops before registering or executing its tools + --- + duration_ms: 14143.5424 + type: 'test' + ... +# Subtest: cumulative tool allocation rejects the entire returned batch before any tool side effect +ok 457 - cumulative tool allocation rejects the entire returned batch before any tool side effect + --- + duration_ms: 14047.6527 + type: 'test' + ... +# Subtest: single response 16 tool ceiling rejects the entire returned batch before any tool side effect +ok 458 - single response 16 tool ceiling rejects the entire returned batch before any tool side effect + --- + duration_ms: 13600.8582 + type: 'test' + ... +# Subtest: consumed request steps remain consumed across explicit worker resumes +ok 459 - consumed request steps remain consumed across explicit worker resumes + --- + duration_ms: 15260.9131 + type: 'test' + ... +# Subtest: a saved completed response with missing usage is conservatively accounted exactly once during recovery +ok 460 - a saved completed response with missing usage is conservatively accounted exactly once during recovery + --- + duration_ms: 10974.138 + type: 'test' + ... +# Subtest: an unexecuted second workspace plan resumes its original identity without recreating the first checkout +ok 461 - an unexecuted second workspace plan resumes its original identity without recreating the first checkout + --- + duration_ms: 12157.384 + type: 'test' + ... +# Subtest: a verified interrupted parent proposal resumes sealing without duplicating or replacing its original change +ok 462 - a verified interrupted parent proposal resumes sealing without duplicating or replacing its original change + --- + duration_ms: 38141.8265 + type: 'test' + ... +# Subtest: recovery attaches a sealed parent batch saved before its group reference without creating another batch +ok 463 - recovery attaches a sealed parent batch saved before its group reference without creating another batch + --- + duration_ms: 33803.4049 + type: 'test' + ... +# Subtest: explicitly retaining an unexecuted parent merge cancels its batch and frees the next parent goal +ok 464 - explicitly retaining an unexecuted parent merge cancels its batch and frees the next parent goal + --- + duration_ms: 37005.5134 + type: 'test' + ... +# Subtest: unknown collaboration blocks ordinary proposals but permits only original batch recovery and rollback +ok 465 - unknown collaboration blocks ordinary proposals but permits only original batch recovery and rollback + --- + duration_ms: 40154.6755 + type: 'test' + ... +# Subtest: after a restart the batch application lazily reinstates the worker result guard before any parent write +ok 466 - after a restart the batch application lazily reinstates the worker result guard before any parent write + --- + duration_ms: 33833.4667 + type: 'test' + ... +# Subtest: unknown original tool inputs must match before acknowledgement, and reviewed checkpoint IDs preserve the unknown fact +ok 467 - unknown original tool inputs must match before acknowledgement, and reviewed checkpoint IDs preserve the unknown fact + --- + duration_ms: 13415.4994 + type: 'test' + ... +# Subtest: a parent stop observes and waits for a manually approved child check and its real descendant process +ok 468 - a parent stop observes and waits for a manually approved child check and its real descendant process + --- + duration_ms: 13029.184 + type: 'test' + ... +# Subtest: a real host crash preserves unknown checks, refuses a still living owned PID and never replays a model or tool +ok 469 - a real host crash preserves unknown checks, refuses a still living owned PID and never replays a model or tool + --- + duration_ms: 22534.3418 + type: 'test' + ... +# Subtest: a persisted child initialization resumes the original control run after a failure before its worker record +ok 470 - a persisted child initialization resumes the original control run after a failure before its worker record + --- + duration_ms: 11962.2046 + type: 'test' + ... +# Subtest: failed request intent persistence never dispatches a worker request or changes source +ok 471 - failed request intent persistence never dispatches a worker request or changes source + --- + duration_ms: 11755.6015 + type: 'test' + ... +# Subtest: failed usage persistence rolls back the uncommitted usage and conservatively reserves one unknown request without tools +ok 472 - failed usage persistence rolls back the uncommitted usage and conservatively reserves one unknown request without tools + --- + duration_ms: 12918.5614 + type: 'test' + ... +# Subtest: a child file change after observation prevents acknowledgement even when the tool inputs did not change +ok 473 - a child file change after observation prevents acknowledgement even when the tool inputs did not change + --- + duration_ms: 11894.8826 + type: 'test' + ... +# Subtest: worker scopes and allocated budgets reject aliases, extra permissions and aggregate overflow +ok 474 - worker scopes and allocated budgets reject aliases, extra permissions and aggregate overflow + --- + duration_ms: 570.0419 + type: 'test' + ... +# Subtest: two sequential Git workspaces freeze a new parent goal, separate owned tasks and preserve all source bytes +ok 475 - two sequential Git workspaces freeze a new parent goal, separate owned tasks and preserve all source bytes + --- + duration_ms: 10514.3399 + type: 'test' + ... +# Subtest: real isolated changes, approvals and npm checks produce original owned outputs, not model completion claims +ok 476 - real isolated changes, approvals and npm checks produce original owned outputs, not model completion claims + --- + duration_ms: 26867.4067 + type: 'test' + ... +# Subtest: forged worker tools cannot execute terminal or Git even when absent from the advertised tool list +ok 477 - forged worker tools cannot execute terminal or Git even when absent from the advertised tool list + --- + duration_ms: 11991.8665 + type: 'test' + ... +# Subtest: a completion-only model pauses each worker without fabricated changes or checks +ok 478 - a completion-only model pauses each worker without fabricated changes or checks + --- + duration_ms: 14213.5962 + type: 'test' + ... +# Subtest: restart retains frozen scope and marks interrupted parent and workers unknown without sending requests +ok 479 - restart retains frozen scope and marks interrupted parent and workers unknown without sending requests + --- + duration_ms: 11179.1466 + type: 'test' + ... +# Subtest: small code and actual failed command stay visible when their original multi-tool group cannot fit +ok 480 - small code and actual failed command stay visible when their original multi-tool group cannot fit + --- + duration_ms: 1499.5301 + type: 'test' + ... +# Subtest: mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes +ok 481 - mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes + --- + duration_ms: 2106.1897 + type: 'test' + ... +# Subtest: working observations are bound to the current Task and stop treating a pre-application file revision as current evidence +ok 482 - working observations are bound to the current Task and stop treating a pre-application file revision as current evidence + --- + duration_ms: 2039.8519 + type: 'test' + ... +# Subtest: a sealed observation rejects changed or missing original result artifacts instead of recreating evidence +ok 483 - a sealed observation rejects changed or missing original result artifacts instead of recreating evidence + --- + duration_ms: 1261.0587 + type: 'test' + ... +# Subtest: a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid +ok 484 - a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid + --- + duration_ms: 4535.0138 + type: 'test' + ... +# Subtest: budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries +ok 485 - budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries + --- + duration_ms: 4.349 + type: 'test' + ... +# Subtest: actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening +ok 486 - actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening + --- + duration_ms: 10664.5616 + type: 'test' + ... +# Subtest: actual HTTP file pagination advances over a long file with each returned page visible in the next request +ok 487 - actual HTTP file pagination advances over a long file with each returned page visible in the next request + --- + duration_ms: 2890.2964 + type: 'test' + ... +# Subtest: later mixed history pages cannot displace the actual module sources and complete requirements +ok 488 - later mixed history pages cannot displace the actual module sources and complete requirements + --- + duration_ms: 5741.5844 + type: 'test' + ... +# Subtest: a later narrow page of the same file revision cannot evict the wider actual observation +ok 489 - a later narrow page of the same file revision cannot evict the wider actual observation + --- + duration_ms: 3117.9046 + type: 'test' + ... +# Subtest: historical read-artifact navigation points to the original artifact and next page, never its result wrapper +ok 490 - historical read-artifact navigation points to the original artifact and next page, never its result wrapper + --- + duration_ms: 1421.9159 + type: 'test' + ... +# Subtest: a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view +ok 491 - a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view + --- + duration_ms: 1409.0497 + type: 'test' + ... +# Subtest: actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes +ok 492 - actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes + --- + duration_ms: 11309.4721 + type: 'test' + ... +# Subtest: workspace HTTP ownership, reviewed creation and reopen survive restart without changing source files +ok 493 - workspace HTTP ownership, reviewed creation and reopen survive restart without changing source files + --- + duration_ms: 8789.5639 + type: 'test' + ... +# Subtest: isolated model Task applies a batch, executes real checks and commits at the Git review boundary with a source-bound report +ok 494 - isolated model Task applies a batch, executes real checks and commits at the Git review boundary with a source-bound report + --- + duration_ms: 26708.8792 + type: 'test' + ... +# warning: in the working copy of 'src/空 格.mjs', LF will be replaced by CRLF the next time Git touches it +# Subtest: worktree checkout disables hooks, fsmonitor and all filter command variants while honoring built-in EOL conversion +ok 495 - worktree checkout disables hooks, fsmonitor and all filter command variants while honoring built-in EOL conversion + --- + duration_ms: 5818.8965 + type: 'test' + ... +# Subtest: an ignored external file at checkout is observed and never accepted as pristine creation +ok 496 - an ignored external file at checkout is observed and never accepted as pristine creation + --- + duration_ms: 4289.8915 + type: 'test' + ... +# Subtest: outside content hidden by assume-unchanged cannot pass workspace verification and blocks further source execution +ok 497 - outside content hidden by assume-unchanged cannot pass workspace verification and blocks further source execution + --- + duration_ms: 3673.3883 + type: 'test' + ... +# Subtest: workspace preparation refuses known shared-repository activity and preserves archived child sessions +ok 498 - workspace preparation refuses known shared-repository activity and preserves archived child sessions + --- + duration_ms: 4517.0357 + type: 'test' + ... +# Subtest: compact checkout identities create in deep Unicode source directories while retaining the human branch name +ok 499 - compact checkout identities create in deep Unicode source directories while retaining the human branch name + --- + duration_ms: 4900.6708 + type: 'test' + ... +# Subtest: Windows Git metadata path limits reject creation before publishing a branch or changing source bytes +ok 500 - Windows Git metadata path limits reject creation before publishing a branch or changing source bytes + --- + duration_ms: 2182.9903 + type: 'test' + ... +# Subtest: a pending source snapshot participates in shutdown and completes before storage can close +ok 501 - a pending source snapshot participates in shutdown and completes before storage can close + --- + duration_ms: 2143.9731 + type: 'test' + ... +# Subtest: source configuration values stay private and a configuration change invalidates a saved review +ok 502 - source configuration values stay private and a configuration change invalidates a saved review + --- + duration_ms: 2775.529 + type: 'test' + ... +# Subtest: workspace review rejects excluded dependency before any checkout +ok 503 - workspace review rejects excluded dependency before any checkout + --- + duration_ms: 2224.2845 + type: 'test' + ... +# Subtest: workspace review rejects large committed blob before any checkout +ok 504 - workspace review rejects large committed blob before any checkout + --- + duration_ms: 2095.4104 + type: 'test' + ... +# Subtest: workspace review rejects case collision before any checkout +ok 505 - workspace review rejects case collision before any checkout + --- + duration_ms: 2156.3857 + type: 'test' + ... +# Subtest: workspace review rejects committed symbolic link before any checkout +ok 506 - workspace review rejects committed symbolic link before any checkout + --- + duration_ms: 2533.6894 + type: 'test' + ... +# Subtest: workspace review rejects external config include before any checkout +ok 507 - workspace review rejects external config include before any checkout + --- + duration_ms: 1965.0137 + type: 'test' + ... +# Subtest: actual process exit at workspace intent preserves source and reconciles without creation replay +ok 508 - actual process exit at workspace intent preserves source and reconciles without creation replay + --- + duration_ms: 4029.1733 + type: 'test' + ... +# Subtest: actual process exit at workspace git_started preserves source and reconciles without creation replay +ok 509 - actual process exit at workspace git_started preserves source and reconciles without creation replay + --- + duration_ms: 5525.3448 + type: 'test' + ... +# Subtest: actual process exit at workspace git_finished preserves source and reconciles without creation replay +ok 510 - actual process exit at workspace git_finished preserves source and reconciles without creation replay + --- + duration_ms: 5656.8669 + type: 'test' + ... +# Subtest: actual process exit at workspace verifying preserves source and reconciles without creation replay +ok 511 - actual process exit at workspace verifying preserves source and reconciles without creation replay + --- + duration_ms: 5397.2951 + type: 'test' + ... +# Subtest: actual process exit at workspace registering preserves source and reconciles without creation replay +ok 512 - actual process exit at workspace registering preserves source and reconciles without creation replay + --- + duration_ms: 7083.7477 + type: 'test' + ... +# Subtest: actual process exit at workspace project_registered preserves source and reconciles without creation replay +ok 513 - actual process exit at workspace project_registered preserves source and reconciles without creation replay + --- + duration_ms: 6510.7759 + type: 'test' + ... +# Subtest: actual process exit at workspace session_registered preserves source and reconciles without creation replay +ok 514 - actual process exit at workspace session_registered preserves source and reconciles without creation replay + --- + duration_ms: 6988.7504 + type: 'test' + ... +# Subtest: actual process exit at workspace ready preserves source and reconciles without creation replay +ok 515 - actual process exit at workspace ready preserves source and reconciles without creation replay + --- + duration_ms: 5364.4379 + type: 'test' + ... +# Subtest: outside changes at project registration remain unknown and preserve the already registered child identity +ok 516 - outside changes at project registration remain unknown and preserve the already registered child identity + --- + duration_ms: 5827.0897 + type: 'test' + ... +# Subtest: managed worktree preserves source index and dirty files, opens a distinct project and binds Run identity +ok 517 - managed worktree preserves source index and dirty files, opens a distinct project and binds Run identity + --- + duration_ms: 4807.7946 + type: 'test' + ... +# Subtest: stale review, branch/path collisions and forged ownership do not run worktree creation +ok 518 - stale review, branch/path collisions and forged ownership do not run worktree creation + --- + duration_ms: 3054.132 + type: 'test' + ... +# Subtest: workspace project verification is read-only and rejects physical Git identity changes +ok 519 - workspace project verification is read-only and rejects physical Git identity changes + --- + duration_ms: 4290.5832 + type: 'test' + ... +1..519 +# tests 519 +# suites 0 +# pass 519 +# fail 0 +# cancelled 0 +# skipped 0 +# todo 0 +# duration_ms 1247127.7223 diff --git a/docs/companion-f-local-evidence/iphone/app-manifest.json b/docs/companion-f-local-evidence/iphone/app-manifest.json new file mode 100644 index 00000000..a43b9c51 --- /dev/null +++ b/docs/companion-f-local-evidence/iphone/app-manifest.json @@ -0,0 +1,171 @@ +{ + "app": "agent-workbench", + "version": "1.16.0", + "kind": "source", + "candidate": true, + "purpose": "isolated-iphone-companion-manual-qa", + "createdAt": "2026-10-31T10:00:12.757Z", + "sourceCommit": "2ecdfa2cedbc3dd28abaea2f32b22a203f785847", + "files": [ + { + "path": "dist-client/.vite/manifest.json", + "bytes": 552, + "sha256": "f961899ac70d80a3e21a3112c9a61eb3bdcb7dc58f32f825da3dcd31190b8471" + }, + { + "path": "dist-client/assets/desktop-BaQ1ZMRu.css", + "bytes": 134240, + "sha256": "0029a99d996ec583d0de6436520d96b898a27bb3348e449868a1e51a31860543" + }, + { + "path": "dist-client/assets/desktop-DmqBcePV.js", + "bytes": 277303, + "sha256": "d87c9b84abaa3a9aa47181f4cdc5c511a20dd2873397d6b448657b8e0ffc0d15" + }, + { + "path": "dist-client/assets/mobile-CPi1xsK3.css", + "bytes": 11100, + "sha256": "554cb3020c31edd7a8b9b32a7312264ba38be22b7393bb3f86472bfe7b5e00ee" + }, + { + "path": "dist-client/assets/mobile-tKLJoem9.js", + "bytes": 21376, + "sha256": "49e76f7502a11d453ef9dfd0e9dbaae448b76eba06821fe05b3e15acadfda03a" + }, + { + "path": "dist-client/assets/x-Cc3T3VuL.js", + "bytes": 225509, + "sha256": "b5c3edb8b21cad106d0cd2ac1e90accaa7084a9954f06247bcb834bdebcef465" + }, + { + "path": "dist-client/favicon.svg", + "bytes": 268, + "sha256": "538fa42445dfd8e78135717e2f30dada6d790d5c05b9011ae7a9bf80d416ae1d" + }, + { + "path": "dist-client/index.html", + "bytes": 577, + "sha256": "6d93311412745e1233e16827742b258708df04e39b4702635f46881dfaf6c604" + }, + { + "path": "dist-client/mobile-assets.json", + "bytes": 95, + "sha256": "6c180e6d8a22511fd01c268ceb45da11fdea214d9576dc0f464ac523ae594fe3" + }, + { + "path": "dist-client/mobile-icon.svg", + "bytes": 307, + "sha256": "2241a24a26e67e2587614819d7860575e76bdaf9e2c3de6abeb58538d3f2b81c" + }, + { + "path": "dist-client/mobile-sw.js", + "bytes": 1140, + "sha256": "6805876026d02fdd8a1e79d946a332e9fad7806f93ef089b292d5ec66695795d" + }, + { + "path": "dist-client/mobile-touch-icon.png", + "bytes": 1073, + "sha256": "120b1168132b7664af0b159de8fea1ac0a2aead3a43ae0e2ae11833d97a09d6e" + }, + { + "path": "dist-client/mobile.html", + "bytes": 822, + "sha256": "a67a1c742b5a5dcfd3b7d7ba1b125de25bc89fa5e95c0c3958eabe0b3b37e001" + }, + { + "path": "dist-client/mobile.webmanifest", + "bytes": 372, + "sha256": "1d2a9bf8216aadce8fc47de1e236c4c7adda60ce96609133ee7e19e361b4673b" + }, + { + "path": "dist-client/workbench-icon.ico", + "bytes": 1095, + "sha256": "f1879074e45f01c480ad9bf50b818637cc60ad56526056c886f808a4812d7b0c" + }, + { + "path": "dist-client/workbench-icon.png", + "bytes": 1073, + "sha256": "120b1168132b7664af0b159de8fea1ac0a2aead3a43ae0e2ae11833d97a09d6e" + }, + { + "path": "dist-server/host-launcher.mjs", + "bytes": 28906, + "sha256": "3dd26a1fc6e45ccf6c4e42c216bebc4645e344efd3eff8fb58786952b2670bbb" + }, + { + "path": "dist-server/hot-upgrade.mjs", + "bytes": 2346217, + "sha256": "ec26817ac75be2e75080b2cc0fbac50c94d1c01ba64e52c6153e01fe2a0ed67b" + }, + { + "path": "dist-server/install-manager.mjs", + "bytes": 64983, + "sha256": "ecf785e7656e582ce77f9ecc4f01e24fb15503e49e121f3af16788d66764813c" + }, + { + "path": "dist-server/server.mjs", + "bytes": 2344597, + "sha256": "434b1d5ad08dc2ef204cb5d0b2b68db3836cca6bc115621ccc329a7119e1c139" + }, + { + "path": "examples/starter-project/package.json", + "bytes": 98, + "sha256": "34b29e888a5384745711c9c0ed81a8e6e80312a37751fd692b1dbc220210a1c9" + }, + { + "path": "examples/starter-project/README.md", + "bytes": 334, + "sha256": "d76b1e793eaad3db8cb56f97d3a785bb9d03b5cefa7d94d49d9546fd4e28dc9e" + }, + { + "path": "examples/starter-project/src/catalog.js", + "bytes": 684, + "sha256": "4cc12126e0e86c0909ce066a26bf095a6f425f3dbebc70ac3edd65a56906a3d7" + }, + { + "path": "examples/starter-project/tests/catalog.test.mjs", + "bytes": 1007, + "sha256": "af478ecb0eabc3d5d2c6738339db66913575bc62eefeae24013d30edf3547f58" + }, + { + "path": "package.json", + "bytes": 3162, + "sha256": "bcc2685fd554ffa4573f9d2709d2aa76bfc086907fd91bc786cd3e6767b3deb2" + }, + { + "path": "public/favicon.svg", + "bytes": 268, + "sha256": "538fa42445dfd8e78135717e2f30dada6d790d5c05b9011ae7a9bf80d416ae1d" + }, + { + "path": "public/mobile-icon.svg", + "bytes": 307, + "sha256": "2241a24a26e67e2587614819d7860575e76bdaf9e2c3de6abeb58538d3f2b81c" + }, + { + "path": "public/mobile.webmanifest", + "bytes": 372, + "sha256": "1d2a9bf8216aadce8fc47de1e236c4c7adda60ce96609133ee7e19e361b4673b" + }, + { + "path": "public/workbench-icon.ico", + "bytes": 1095, + "sha256": "f1879074e45f01c480ad9bf50b818637cc60ad56526056c886f808a4812d7b0c" + }, + { + "path": "public/workbench-icon.png", + "bytes": 1073, + "sha256": "120b1168132b7664af0b159de8fea1ac0a2aead3a43ae0e2ae11833d97a09d6e" + }, + { + "path": "runtime/LICENSE", + "bytes": 160555, + "sha256": "ed34dd8e3f0a78dbaf00d0444ce8e285b015b765379c2e17880455f70370f8e9" + }, + { + "path": "runtime/node.exe", + "bytes": 93915464, + "sha256": "d702daa815eabbff763c7d3808e235cf031cf2ca70211b56847bc72f51e240e5" + } + ] +} diff --git a/docs/companion-f-local-evidence/iphone/desktop-certificate.png b/docs/companion-f-local-evidence/iphone/desktop-certificate.png new file mode 100644 index 0000000000000000000000000000000000000000..4d727ac307d9ccda4f9613c8172fe7823b3ae64a GIT binary patch literal 180946 zcmYhCWl$VIldy4jmxbW&?y$JKTX2Wq1P$(sJHc&ncXubaySsY``SRV}TX(;vs;5V4 zx@T(U>7FQ6Wf@c?A|wb12vj*)Np%Pa*n9{G=u-r!f08o7nPLbC3Qnu4w+P^+c% zt;AT0Ys?kcIGxn$vxwB`*`*a*q3Q=rF7I+0UyLt)Oud-Lev9KjUi;#6l`cWyQW*#xzC+?^)OyCFBINQM zj4yOIpz>KujZ!@k+8@ z>?lc!L|H1VGN{xqN$5kO!l)3RMk1$A|Dc`)-zdq7GUn6cPZP;DYCj}q5?4Rp24~uY|1+1ib^_b9!(JqeE4w!@dz(0KN5Z=X zY?awMd<6^ma8Y;Qm470^Y$x}6_BhU^vS=uiVZakfe2Jk@z@_5<9hHVc-x20F2wZ`w z7T?Xww0&x&NpBF>Q-EmBogGuo`G41j7@;DXu^InRAqc!v zn6;KF>$XZc3$Cbi76@~!pkc9X11|BFO5}+WRFU7*`DHE`m4C8(=)4t4DDfYIA@%3w zD!JqS=r5bR3?nOPeGR3(Ws1%II+dwKU^@>z4LN~Bl8hSv$4qDx2(!?`QQLa*dpNYU z9mO}zKUSeV8%Aay&&+0BBA(o)l!rcxtY@ zPtHN&92_}K6A}!Cw(Ikoi{z-_URifZG#|!pG03nGb`TaoAX2U*it zo`Kk5%FB1Q40mKF3*%}SN|^<1h27c%zw48ofU6hyMgz~xxe5ot4X;##c!jDf>nYn; zZi7ZtiHe*l7fhMhwzmo_B^BPQj#>TDUmgjU?u+*Q04GW6zkPNiqR;8{J=G6_i1}cm z1||&$ZWvim`@kUQ>QstFjboVf5J9S%W^oJ;`;yM^am;XObRp9FR2rX4UiC1FCXA3v zM|}c;zx=~HPjdNmsW=4(@kJ8YR=J;}&Z>+}FxS|M;(6B2G9;i>*8|m^BI#LOJrjjC zn{;$uSQ8qnFVcK~sx~l9LT6aisfemQ z`79uMjKw=Mg2tM}@uN`J`8%jt*_p16#)NB>ygY9lt?3eO?k9V+Cus*pe-P)-Y4UHQ zD)l5l3YQahOJ2`85u|Y z*w?RBKPn)ZW7zNb$Qd+Jw@!cO;vN|6B8Z(7S0I@ckC6lxwPnq6>%y(=*7=9^^P?amRIvuE zT-G$TYuOFhHPSMq{}gWwq?BO=RHc2W!7M1|3aPQPvzO@)ew@$+A7G&+BbM?_-1mV( zpW^fuOS5DFpgF!3G&_^sKPV5JjUQ#`b zp^3X971l~zJr#VNSFBGLkkZ>OCr2Oe0AUo@99yh#A8x8%ON{L))*E%1Gvce%UaYv6 z8fz!e`SiP+{L0f&@M&fuKKOiV<|#ejxN#irf!Z@=%oGp-yGfS`Hur zP)IPmOsTXkih$;F)XWTx5ZhdZ4=={^Pm2509ADv~_KJ@M@A<7v(=1Lb*)~4I zRczAnfYgq8YZ2j9JYjwfhFC@w*pz1k5yw~Rb3qTkGW#v*K$gl0mxjY|09f>`r;O10 z%e2|gQOIGwhY7Tt7nXjiuUW>OEUO&x4aAC$kB5>G!aNAD!u7!@Qk|g#?vKFaib^Rb z0m#I+jG#1+hFvU%$HaESY6IsBRNllFI2HY)7w7k9y_O-D<)5W@C>~bxYofG#&6F}UVE2=zp8h}~HyHsF=>?LX94Hvj8)9N@= zbe~Z`urJ{DDyYK61-z8!yzZnLMCUqN`*(y@>Q&OC&lx2qgt+~s`&$2`JI{AkTf3RGCUUz*q;sPXcX8q@HX?Tb{RauA03a#_KDQdNg? z*ON$egm&V%x$ua58vYs_@JWhu;O3(8tqMamNJqA43^z~iN#x^}*2BTBHF4tx>ki(i zaRsb?>%tKIMaU6Y1(xW9ar6lo^+W-WP|)ycRif=mGcEj`7l5>aSnj(Ar>4e{U zJP0P}UGoSn4REi%Z)W_>MOgM;ktiUz)LBRDVOBx`S2!`TWlO?LGwIEE$g?Etqy>pZ zFc7Y>gC8gHXtzG?tf@3PtW(Y3uicnG&^{#9#ae-*otWiYuE5F2DIkf+j~_$7iA>>w zSZ6&FBwwgt>Ap<)N0L}yVKxI6E-bw4T2*tKRTIWBGa4fCy?JoVEyIIQ5r0wh6a$giQ1aIRCQF4Tuzfe*TDu9cqn|G^9ynd@xewDTeKN_oy_`z z=v4vSdqo#jEXvP*?&Z~M`|D{Q%J~~*$q6X?TRhf%?yw~uv-&wYS*L7o<_DU*nTDbC z&@5!}?UqD_QXFHc+QrY**0fa+N4_p?%>m04&(K*H_JzL-N9|#-N`ruADrPOp_Z*KV z0)Ztu#|)J6`$S^NT(VrzoVvL)=-^9=Jmx*S`_To%i0mW;Zf6N49}Ym&kPb&y9D|L#W{Waz^8KLG*Z-7_)HSGVE;3IPmLAvPUnp zgdPGLuG{yHNS5xCLa+X42FqQS*aInRVu88N$&M}qc5srSFEf#07i0;q=D0g0L`BS1 zLvCo{f@_?kV{GI=l80*Ki3b2_2$J3fqQL?dqGLR$oOJ6EdVjO{WeUB+?Cay!0AhYe z%OYA+DGAJ-vTMzTK*|@0W+O-&twSv8zv`4wny@)!$AbB2u?#wJIprw_7`o$}+23$V zD?`yO0R7@uQiG)U`cYN;?!KBgEGC+UXo$g13$Ur=bo<>Aa1eI~bZ%Wb@VrK2wzhsP z5|*@srjUur(AQ5xvT?Zs<|Vtf1}ORO>Ou|`hd44{Y;vkO0LpY^%N^#)*o}jx(M15p zg?ir9`TY9Fp&HViE~rIW^it?dJF4i!lxmUE%4aGb)(Zr*M}Gr^(-bA^5&BcYFlb-{ zb1ZhKy!tZ{CU;5%&CtSvjrw};#rbVOK!Fsll`xNG6Z*C9VnE+x_Trk7qLPbAY!~ua*LU)*g#+r zqm;-3m74VL6z3^DD2wOhUtuznHrLAtY#{J5QNA;vW7l^%auT0Z!5ytU;^R7J$V#{+ z?oW_tR+P(k>O0j#+1tV$eE0gMF1M&gDOWc})bKI1jiZZn9*x*Xmh{+Vend7Bkw2I0 zt3gygx9+GTwu0K~FicwET)d2~nd8ooMu?}yt2N1lEY;m{L&b%v)AE(A6Z84^t-bK= zH5A2GUV}k(?l=#9H)O?TC1PMlWOG^D&zRms@*D|{iKHL2q@sp7&C{}lli~{EKqJ6m zgJuqV%=c8|R*rzHTk+PC#5E z_D|JEtG2lU03Gzaafg!z7-U=_rpLIDHcHHCRzIq^h_+#H_wqT8`wdwws~;)Ye9DQy z2zuU96El%kW~fg*afNlpNw&X{Ut4Rx&Qh20SJ@Y7ySQUjkmx?g{k^F^zqgEOruJVGI&aRHfl(+13Q@0LIDX!#r#FC@ z?8xAQ4gzPDyXY)>c;AbXcsk~|bS z?%QF8m(E4H9J0N)4I0j|o}TE%UevV`{OP~-{kXgCx4L1+sL47Y80WIuwyiLk6?kI& z%PO5)rGrx+qBW4q8a$8OUE3$Iq|A&IOh*V=ImAFYXf-(bSwR*WrBhhX-p`PX9#pS#P{ZWbl6C`; ztl9i~S6>7B5A620vK^7MV4G+B_R=!T#k)`nO)+^gf#;A8Pt90@ii2GID2NqV>6;8m z_V}+vjzlAvixhp{Bvlp55NXc8K=exuRA0Lap*HYM{lT}4X+pHTQ;v!$LEV@d8XlWt zV^7zlOV$!@nm3;VPHA0D0%OIZgKI(+o~*o_v(f zl6JQC{@_kNw6moT$v61bZ$oo+#03kJo@KcM1gf1#v2;P*Frz7380oYhoK0WeqCILS z^g)B=sH(2$3Q>&*hFfMdr2w@syIJlLoB~^WtAklBxl@s6&ax9jHr=nEh={N>Q>O%!jS*hA&aIB?drh%_{hI3K> z-B~J4Y9hO!r|XDYBG7{qNfqI~vsq=NE5jYPhSF_M{w9aCtT}?q8j_}P8N@thdbb7`;l2l1HOkUf3A(v z(s1^d?s?!RV^9R%NW)P2uNH#q3or3a8|Mm*8*C8_h+fg)6%JTFnW}O$w6HZj7Kh#0 zGU14ihoCU1^VU$yr1d?%S2W2&94`)#GFF~-sF1b1sg+|P2TI+lx6nmnSb`YVxLVn!)*M%F%_||kb#!e zB}TbQ=96rQpKqJZqkJ*Jyz&IAZFN(K{Sx4*$M2+g_pz^ChhZu9IhKE|wJY&}sKw{e z+IKWE$uVxemz{KMoeK`>)GL4vB{QKww4~IjeO^ASaV*!Mu>8>uE$K-~rQ3u{;bnzo zJXoRQvaw^`uhxv<{)^nZx_WXgau?i4D>q?!SfYDnS9*##b%kg|u-rJO@@v{P+pnlljy{O8L7; ze5HWB$gnh*LRc(MzGo)-ayD|wHtqdApHafs#-M9Xzo2B^qEeoK$w9;T#`Ko|eo!=r z6zM@lXavf;qTDu3_k=q8?UbO^HArGD@~X#oEG8=w0PJ8B4b zz~UEO@}UK1xcuv`F$6IuOonx21Hotp9_4)GfsK_r<1CXbY%L&$W#1B!c@$Cy(GHf0 z0}@15@do0XrORW<(}72Luf}~Of<(`RH)({ja1F%`(7?JA!#5$H-=4boeX6g7ZUwYy zg0fj6Hn=WK{1e3*Es^Y~Hv7FKT1#9xK&SaI+@1`3@KsB@e_z_Sc(TTGK6kQy$&TEB z@A~37lHpvxMky9%r8T4Y%rO~Qd(5XFw@|ekE!8MJLE3Aa%$O6}w~|~v;G=^cW!ArP z&pT5lQ_j7eZg!W{`nnZWlB2^=4%yr^JPf@tqj@En?VBwAE#kvRD?$IN=M!(#!`ns>|&z*yhEVXpcSbotzGDis;DMQ6|;P|6d& zBek{@=n5cc0be@O33RTe(eVdaD^yurTnxCV-uy(-U{tJe2>)?Ee#rnP|BhA)<!!3 z-~s|h^$p%-VKEaQSyI@wvUCE@pwI@2?t}dXH8C-S-@@YBpzNvdHq?ecS^CV5Q2xD= zmaK7~teO46LG`s1b_AJL_=U5c$MPviT+!iM z3!}PvqdyG}pgAW#B~+&cWvMpwW}kzk-`-j3EZoVe10*O^kVq^#9e=2hV%RLU8?Ad_ zfdev5FrpuEa<{$*GVu-lsA%5Cg^A!cSl;%b;rKqO?hiGw$C0nmd5bvU^wSZ}eeg%~ zvDixSK6pu4ui1i@SrRmD;ok3p6gC03WuX~~OQXZ%AU*%KhNVdYQyIS{yP!wQHc+6U zKE~6rwk4ls8*{yNbZ^5o!p9%cZzHd1=0rQ{pFxjgB&S#_)KSVrsM~|KjxIj}S&jz)Bp^0XU&j)2GuR z;9zWyAWpz3!yKj6mn(|MvF-*Le&pF@k?}3w6q;=543omG}-UK7&@rE zk~3Y>FwQ)gRxl4sJ1+6xUFKa?Duu4#d`D~Zb}I~R-;{A%GA$@vWF31k(YEcXs0x?z z^}V<~@}8PKfWpQz`Ci{BKmmO_P8=`^h+co5vJRTQb3P;13jW})tR7}%SUTq@$(G#+ zR&T7p9t4aAp0I5+auVrmnX2YfHXKmWZDbgS z-{+ceAq;}Tu=^f~sa>cnN16zdv2!66K%XWK2z-pR5+yOtG@o@-z0i`K0^PNW$ejg8 zjKCFbeEi>|{Sk9;HZ_nP0w&VXJ(}Gejm%F3t|Ug!(6$#g@rN0<4q5CfC=>!997STy z{C=V%9n|uZ4F2H{0^TzZl3JM#zrNt8wc|doYFce&yci9hb)z$thIOXrPijy zgs4<UN}SbFvZcNJLQl5EKEXg+I~ir! z6nfgCj1wDeT&s7>bMWuph^Mdd&c?G#(5HK!1Sy~QWkk@qiY2ciVmk42wrAKJ)HnIEP^=DK(kt}xEg?&JO^)ni& zI+X!LY)j;ox+JMg1k`F-wkRAqkOKw)o+ia;AOzQ-F!Q*qS08U4zQikIecWZYovD!0ArYMKt@ zPN=nNvgv6wzVt09S*#+lWg>k=!CD-W%ekZ>iO2s#d(@vX<1JJNugC%aPoP zbfs>Sau;}roC~~2&p3LZD%FwYb9@k|RtP&%)zLAMo1ZL8Vk3%j#46Eu6WF*a=dzzn z++F^G@eac@CAnjE{%EDa_FD~~Yn2+fx58wAnEHP5Cz8-e%;m~WiafK0^+V{;E*w@Q zV_2i9!pctuuF0fQD`1HWH4)$0n9NuL@ucQc!V+(ts*#p(@uP>&+>9DhLQ9YQxQnzj zR5vUgCR8)ho5dFjk%y&;OvJE;&zm9fgJDQwBp9?Hxxezbn)snGK@SoqUpw@7vKmNW zWG;`?D;gLj05J_$(svN6IcGWv$xh^tVMlNEGxV1RI59_Y33OeBlL4VI3TWP7d{2oS zG&~Kd}w0h57_^?D98IuCV>mwnfdel() zUfD<|glO66jj*l1jWXe5(-QQ6lY zhHI&NC2nTn<=<0q7~_(arjiT1tch2)54}6=X6cx*J&V*MxE?03Ferc~B$B;r~L@t!=lgtuR4}(@Fq1>tnGWIMy5{zeeG>8Pzvd5gCw_Mvd{srRVfB6t1Sei-z)* z(_%$sqw9C^w3|29L}{iYbVQrNp!*M4!@y(+2NSO-vTJ>h3f@`0Ey`@oGSEGGA)=bH zv|fP$3C_1d;g{zM)GNo#l_@x{%hm{X*3a^J4Y#~HV(JJ)ZD8nmB2N^e2lASaDk=M*02;-W1#`m9yQuq|lWqj60e31d=#f4@7oi@9cU zvmr0=!>3=xfo*Y}wc2HbUz*yC76m-8v1!XRH!iD+WdWh*q(RD?0vYr6A1DO881%t4 z`a|wobIb14VvF^DrT18v!=z(q&x5M#rRE_?Tov!hAM_%8Yc%Wg@h$X2BZU*51r_q626SP-uh6F9 z>pGwM$Stq*_7A2s7hTed1!%UcqA@Ts4)7!X{E)>h#Hya<4*3^TkLXE=gNe>LG`*Qx+t zptLmSm$glEr!b?SF}7lhP$CzHCmp`6Ml|QstL5|FO5qWjz5B`=P@`*Eb8c(CM;t=7 zbZNOi@hsZ!!vx-=zAu{02Aiv6q%bLaW?fnCOalND^S;AnS)6(mkxCUy7(tz;gcrtcL91Px5RpnfS#Linovh3^bBI#QnBHLN}y*cq1-`Z}05R{85I< zKN}Bhti!3X2{IxL69H*$VZa{~smvn*wOZRMBr(peo2 z90z>~;x>~Gur@?ivY6L?uNzHR-Tx#nv39>qiybO_~e)=zcAY^l@*(mCz#ge$!}?J0EY_rjWlkik{z) z=_YDS#uq~fi5e4T9!ahVht6&IAA+MPMd)z?6u%Oohg4Qz{Kg+Lv;4VX!asjYvJ6 zO>Fv^6RDXK&!I5CL_(3|R#X;Sa=xfUO(YevOiGUT31#I|!pfv$q>qK-*^sr)|IxEARQfPIl-`1E`4EiVuXN?M^>eoJsa?%ks>zuK3!fqJ zT4_)SBo-vcOC5VZWy-f^hW-s}!6PydLJ0YeOfKw(O7X+-!BwIk8YY+OU*ZSc6#A}+ zCPe5SWzYQi6B}o{iYVyY@01R{nAw@PuzgxXMm^<0fZA_IJ`W~KH8ZMaDhAe3mZ^!)nZY^g2qBP&6}a#Ef12yQR7? z*IPGwGYpaM3<3GOrcggSb=@X}-FJ7x*|>Znl@LmsH_&7R;twsrei5FO(gGzNJHk*y zDDqsglvnbK7`6D|Z5(D|KGu=(GVmv!m zVTHSqQjnxe3(nYM<*9&O)trY@n`w=-{g*oZ3`9ATb4Ha;a1XS=6NRdw%Pk_mk;`BK zJUw5x9)C5+i2(CQUXiVFw7zI!JzhRnbURtxL5Q4quvy>2peM34gQS_vOKBay+zNfv zz&BJb8$wa!akY2{PfD~h68AQo`Os_>C@w%mNwJO{B}PCNiOCKKLx-XQr6?IQLx6!k zoftZk9o%#>7+GI%)#vVRFpjY!1^`Wr7Cvj*zo~A>XzZKqQy;@*kr$+v$jp~l$!P~l z?~Hv%wH2Lnq7mxxEto^)X)@2EB?o^Vq?~~#6%i=V$KlHqc%Esx$FqZc%&B+x%4`J33ztVu4wb