Commit Graph
5926 Commits
Author SHA1 Message Date
Dotta ea6dc42d2b Add finite owned public HTTPS origin handoff for chat evals 2026-10-27 01:31:43 -05:00
Dotta a0c5ad9805 test(evals): scope vault AWS credentials to selected server 2026-10-27 01:31:00 -05:00
Dotta 717974e7f7 test(evals): add finite private public-origin sign-in operation 2026-10-27 01:19:25 -05:00
Dotta 7813e24256 Permit one recorded revalidation after qualifying identity invalidation 2026-10-27 01:15:48 -05:00
Dotta 589c90df67 Bind computer tests to saved Morgan runtime and preserve configuration 2026-10-27 01:15:21 -05:00
Dotta 522c5f1bec test(evals): author actual Slack file transfer and size phases 2026-10-27 01:15:20 -05:00
Dotta 9aa09b51c7 Author actual operator computer qualification journeys 2026-10-27 01:09:33 -05:00
Dotta 19510abe5e test(evals): retain missing Grok HTTPS harness binding gap 2026-10-27 01:04:45 -05:00
Dotta 28abc602be test(evals): require genuine existing Bot authorization and challenge 2026-10-27 01:01:36 -05:00
Dotta 1bb90f12cf test(evals): add finite protected Grok routine form entry 2026-10-27 01:01:18 -05:00
Dotta 0af670575d test(evals): calibrate review negation and format new cases 2026-10-27 01:01:18 -05:00
Dotta eeef850419 test(evals): close scoped tool review outcome branches 2026-10-27 00:55:31 -05:00
Dotta 7c77384469 test(evals): require real owned cloud choices before hire 2026-10-27 00:51:51 -05:00
Dotta 325af67e3d Qualify exact Docker Desktop private bind translation 2026-10-27 00:43:54 -05:00
Dotta c1d36080ac test(evals): require genuine saved target authentication failure 2026-10-27 00:43:18 -05:00
Dotta 5c40b00e04 test(evals): author least-scope native secret delivery 2026-10-27 00:42:43 -05:00
Dotta 2f2ecc8269 test(evals): author real human Claude runner conversion 2026-10-27 00:37:21 -05:00
Dotta 772c29dad9 Add explicit owned Docker PostgreSQL E2E lane 2026-10-27 00:35:32 -05:00
Dotta a7373c02dd test(evals): author own personal credential delivery 2026-10-27 00:32:20 -05:00
Dotta 7244c70f11 test(evals): reconcile real account setup requests before resuming 2026-10-27 00:28:33 -05:00
Dotta 3e75b69e05 test(evals): return verified gateway prerequisite receipt 2026-10-27 00:25:11 -05:00
Dotta 41ebbb1272 test(evals): author scoped gateway error diagnosis 2026-10-27 00:24:29 -05:00
Dotta b81b95b36e test(evals): author missing Claude account and real hire resumption 2026-10-27 00:20:51 -05:00
Dotta 7986c118ef test(evals): independently verify secret proposal denial and approval 2026-10-27 00:15:49 -05:00
Dotta a097298ed8 test(evals): bind Claude target to actual Environment contract 2026-10-27 00:10:30 -05:00
Dotta 0d0a7defbe Bind partial archive replies to confirmed outcome counts 2026-10-27 00:04:02 -05:00
Dotta 270035738e test(evals): author real Claude hire and private qualification 2026-10-27 00:03:22 -05:00
Dotta 84e807f546 test(evals): preserve delegated work across personal grant revocation 2026-10-27 00:02:01 -05:00
Dotta 6d9865068a Reconcile archive transport and 210 authored catalog cases 2026-10-26 23:58:56 -05:00
Dotta 4043cf8984 Add owned native archive fault transport lifecycle 2026-10-26 23:54:28 -05:00
Dotta caff11daf6 test(evals): release post-stop gate only after cleanup proof 2026-10-26 23:50:53 -05:00
Dotta 22064ecbd5 test(evals): enforce actual addressed connection resolver identity 2026-10-26 23:50:08 -05:00
Dotta 83d06d6f6b test(evals): author same-source post-stop native continuation 2026-10-26 23:47:29 -05:00
Dotta b117aabd21 test(evals): independently render retrieved Slack launch artifacts 2026-10-26 23:45:59 -05:00
Dotta 8c1cbee398 test(evals): author real Slack thread handoff and isolation case 2026-10-26 23:41:13 -05:00
Dotta eb10c18bee test(evals): guard real native Stop canonical boundary 2026-10-26 23:40:30 -05:00
Dotta 819c1622d1 Reconcile campaign metadata and preserve startup diagnosis 2026-10-26 23:35:32 -05:00
Dotta 05b29a381c test(evals): bind one genuine Slack distractor setup exchange 2026-10-26 23:35:15 -05:00
Dotta 9d850991d9 test(evals): prepare owned real Slack endpoint fixtures 2026-10-26 23:32:28 -05:00
Dotta e4b62f48aa test(evals): author remaining internal catalog journeys 2026-10-26 23:30:48 -05:00
Dotta e670ad77ab test(evals): bind scoped Slack identity and audited AgentMail recipient 2026-10-26 23:20:40 -05:00
Dotta 85f49cb351 test(evals): add signed disposable Slack relay for genuine replay proof 2026-10-26 23:11:36 -05:00
Dotta 83ed9d1477 test(evals): require actual unsupported Slack file phase after transfer 2026-10-26 23:10:33 -05:00
Dotta 9c1e30e2c9 test(evals): bind canonical Slack ingress to actual native source 2026-10-26 23:06:56 -05:00
Dotta c2b8cb697a test(evals): qualify finite Slack companion provider and source contracts 2026-10-26 23:04:03 -05:00
Dotta 7d357062f5 test(evals): probe unsupported effective skill-use prerequisites 2026-10-26 23:01:42 -05:00
Dotta fccad2fb5b test(evals): exercise real card refresh failure and retained output 2026-10-26 22:58:50 -05:00
Dotta 1fc2c961a2 test(evals): include named profile prerequisite in inventory controls 2026-10-26 22:56:20 -05:00
Dotta f2c3d07357 test(evals): author named Notion read-only profile wizard 2026-10-26 22:55:18 -05:00
Dotta 49dbaf516b test: cover card explanation after real source removal 2026-10-26 22:52:51 -05:00