Commit Graph
227 Commits
Author SHA1 Message Date
Dotta 010e5c51a7 test(evals): verify operator synthetic plugin installation 2026-10-26 19:48:23 -05:00
Dotta 35f601cec2 test(e2e): expose explicit agent access grant setup blockers 2026-10-26 19:46:56 -05:00
Dotta d54e55b708 test(evals): cover admitted gateway client profile access 2026-10-26 19:46:13 -05:00
DottaandPaperclip 8f67a700a4 test(evals): qualify owned published sources for two operator chat cases
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-26 19:45:12 -05:00
Dotta 3344de11b3 test(e2e): author real company model service controls 2026-10-26 19:41:42 -05:00
DottaandPaperclip 5f8a3c8eec test(evals): erase selected secrets outside retained diagnostics
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-26 19:41:13 -05:00
Dotta 99513b6c48 test(evals): author real bounded CLI device authorization journey 2026-10-26 19:38:30 -05:00
Dotta 15989bc518 test(e2e): bind plan decisions and draft revision provenance 2026-10-26 19:37:30 -05:00
Dotta 4b54b90b90 test(evals): scope external inputs and close probe credential lifetimes 2026-10-26 19:33:54 -05:00
Dotta 5cc4d6f1fa test(e2e): cover missing links and personal announcements 2026-10-26 19:32:09 -05:00
DottaandPaperclip 9be9c65e85 test(evals): isolate declared case credentials and private provider inputs
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-26 19:31:15 -05:00
Dotta dbabcc4e0d test(evals): add real disposable plugin management journeys 2026-10-26 19:29:28 -05:00
Dotta 62c6745930 test(e2e): author real identity onboarding boundaries 2026-10-26 19:28:56 -05:00
Dotta 5da3ff9ce0 test(evals): verify restoration across a real concurrent edit 2026-10-26 19:24:13 -05:00
Dotta 747eb78c7b test(evals): scan secret outputs privately and cover catalog quarantine 2026-10-26 19:22:29 -05:00
Dotta a1859e0e67 test(e2e): reconcile finite catalog authoring checkpoint 2026-10-26 19:16:40 -05:00
Dotta 50775edc48 test(evals): bind conversational approvals and race real question answers 2026-10-26 19:14:54 -05:00
Dotta 4cde887b01 Exercise property edits under actual later execution ownership denial 2026-10-26 19:14:03 -05:00
Dotta b33f3b8b64 test(e2e): author bounded privileged operator journeys 2026-10-26 19:12:54 -05:00
Dotta 24016a4ac2 Add actual two-principal notification and explicit mention journey 2026-10-26 19:09:46 -05:00
Dotta 51bd1c8138 test(evals): finish stale approvals and one-action tool review coverage 2026-10-26 19:07:50 -05:00
Dotta 483d5f2b9b test(evals): close question continuation and sidebar scope gaps 2026-10-26 19:00:15 -05:00
Dotta 0b69bdef99 Add historical final-artifact search through public migration evidence 2026-10-26 18:59:55 -05:00
Dotta f232f03d0e test(evals): exercise human CLI authorization and revocation 2026-10-26 18:54:07 -05:00
Dotta 874035eca4 Add genuine generated website delivery and retained revision journeys 2026-10-26 18:51:39 -05:00
Dotta 0f95be3f07 test(evals): author real expired-session browser boundary 2026-10-26 18:48:58 -05:00
Dotta 4c4408b85d Use immutable production attachment origin for completion evidence 2026-10-26 18:46:48 -05:00
Dotta 6a28921e39 test(evals): cover human profile and company lifecycle journeys 2026-10-26 18:44:07 -05:00
Dotta 80ba3b2d35 Add real stale assignment read and execution ownership conflict journey 2026-10-26 18:43:30 -05:00
Dotta b1f30d7d51 eval: add real operator companions and finite disabled-chat boundary 2026-10-26 18:39:51 -05:00
Dotta 6e5df53427 Add genuine interrupted execution and continuation history journey 2026-10-26 18:39:50 -05:00
Dotta ba04d3761b test(evals): retain identity probe credentials for one attempt 2026-10-26 18:37:03 -05:00
Dotta 55ad3f3498 Add run-bound agent feedback and authorized human commentary journey 2026-10-26 18:35:40 -05:00
Dotta 25328a9b17 test(evals): verify workspace closure retains promised work and scope 2026-10-26 18:34:14 -05:00
Dotta e123f1ff77 Add decision listing journey with real resolver and history evidence 2026-10-26 18:31:16 -05:00
Dotta 4fc55b2fac test(evals): cover governed hiring decisions and actual workspace diffs 2026-10-26 18:28:49 -05:00
Dotta 20702d9a2b Add approved design search catalog journey with private exclusion 2026-10-26 18:27:36 -05:00
Dotta a44d8063a1 test(evals): add native delegated work tracking and completion case 2026-10-26 18:20:45 -05:00
Dotta 2391af2c04 Evaluate personal inbox archive pagination and real operation undo 2026-10-26 18:20:19 -05:00
Dotta cada0b6ec4 eval: author owned operator and developer reference cases 2026-10-26 18:18:30 -05:00
Dotta 965f1f7476 test(evals): add native history reset reconnect and retirement cases 2026-10-26 18:17:54 -05:00
Dotta d22f561ce8 Grade confidential delegation by its real audience rather than adjectives 2026-10-26 18:16:19 -05:00
Dotta 65c0137e15 Evaluate private attachment sharing and copied download denial 2026-10-26 18:11:57 -05:00
Dotta caa71d29c8 Evaluate confidential delegation across real private audiences 2026-10-26 18:08:58 -05:00
Dotta f8b2bb3b49 test(evals): align runtime UI oracles and private evidence checks 2026-10-26 18:07:39 -05:00
Dotta 5578c71a61 eval: checkpoint catalog readiness and bind discovered repositories 2026-10-26 18:05:30 -05:00
Dotta 9920727210 Bind repository aliases to verified authorized provider identities 2026-10-26 18:03:43 -05:00
Dotta a55eaa86e6 Reuse attempt-private domain probe credentials until cleanup 2026-10-26 18:00:54 -05:00
Dotta 865a191bce Evaluate native delivered work with an outstanding human review gate 2026-10-26 18:00:53 -05:00
Dotta b53c596bc2 Preserve paused inventory owners with explicit readiness proofs 2026-10-26 17:57:20 -05:00