Commit Graph
423 Commits
Author SHA1 Message Date
ZacharyZhang-NYandClaude Opus 5.5 d5bc987e0f Q137: an opt-in live-model suite checks evidence reading, authority and no duplicate work on a real provider
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 22:01:50 -04:00
ZacharyZhang-NYandClaude Opus 5.5 6e210301db Q136: remove rollback records that marked restores nothing performed
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 21:53:26 -04:00
ZacharyZhang-NYandClaude Opus 5.5 f8f852c326 Q135: remove the thread replay that only digested events and reconstructed nothing
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 21:47:48 -04:00
ZacharyZhang-NYandClaude Opus 5.5 403c57785c Q134: a signal's category comes from its runtime source, so self-checks cannot pass as real traffic
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 21:43:21 -04:00
ZacharyZhang-NYandClaude Opus 5.5 3849b96192 Q133: remove chaos drills that never injected a fault, and the signals they wrote
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 21:39:36 -04:00
ZacharyZhang-NYandClaude Opus 5.5 e562444487 Q132: remove PR bot gates that no task completion or goal close consulted
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 21:36:07 -04:00
ZacharyZhang-NYandClaude Opus 5.5 fe45cd4d46 Q131: remove review agents and eval suites whose pass only counted configuration rows
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 21:33:03 -04:00
ZacharyZhang-NYandClaude Opus 5.5 074a1fc8e3 Q130: every open task says why it is not moving, when it resumes, and who must act
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 21:27:29 -04:00
ZacharyZhang-NYandClaude Opus 5.5 271a83a7bc Q129: a run with failed actions it never redid does not count as completed
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 21:15:47 -04:00
ZacharyZhang-NYandClaude Opus 5.5 6afd7bef2a Q128: every model call of a run is recorded with its purpose and listed in the run
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 20:55:18 -04:00
ZacharyZhang-NYandClaude Opus 5.5 1f484df894 Q127: erasure removes the subject's content and keeps only a receipt
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 20:42:23 -04:00
ZacharyZhang-NYandClaude Opus 5.5 5799a3561f Q126: a file write and its record succeed or fail together
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 20:27:28 -04:00
ZacharyZhang-NYandClaude Opus 5.5 11cdc4af20 Q125: imports stream through a bounded window and refuse files over 1 GiB
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 20:17:28 -04:00
ZacharyZhang-NYandClaude Opus 5.5 7a9059fbea Q124: the file scan covers the whole file and says what it did and did not check
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 20:09:03 -04:00
ZacharyZhang-NYandClaude Opus 5.5 91fa6b5f1e Q123: files shared in a private conversation stay with its members
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 19:52:37 -04:00
ZacharyZhang-NYandClaude Opus 5.5 69b83d6b77 Q122: reading a recorded file checks its bytes against the recorded hash
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 19:44:51 -04:00
ZacharyZhang-NYandClaude Opus 5.5 8f192eabe7 Q121: a file id keeps the bytes it was recorded with; rewrites get new ids
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 19:34:44 -04:00
ZacharyZhang-NYandClaude Opus 5.5 04c8cce0c4 Q120: every IPC call passes one gate - the app's own page, input checked against a typed contract
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 19:25:32 -04:00
ZacharyZhang-NYandClaude Opus 5.5 43591d4c99 Q119: the CEO's rank is fixed and shown as such, never picked as a seniority
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 19:14:11 -04:00
ZacharyZhang-NYandClaude Opus 5.5 754f9ba44b Q118: read_messages reads restricted channels and direct threads only for their members
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 19:10:40 -04:00
ZacharyZhang-NYandClaude Opus 5.5 cb1a4be167 Q117: commands run in an allowlisted environment, and records and approvals say host isolation is advisory
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 19:07:28 -04:00
ZacharyZhang-NYandClaude Opus 5.5 d67996fd25 Q116: a task without file access cannot write files, and its prompt says to use documents
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 19:00:42 -04:00
ZacharyZhang-NYandClaude Opus 5.5 938c8cad79 Q115: a goal closes only with its tasks done and nothing its verdict rests on changed during the audit
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 18:56:38 -04:00
ZacharyZhang-NYandClaude Opus 5.5 abfcbf4824 Q114: goal audits use the org's own auditor model and see pointers, not the executor's account
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 18:35:39 -04:00
ZacharyZhang-NYandClaude Opus 5.5 0ae014af05 Q113: a goal audit approves only with the decision alone on its last line
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 18:21:46 -04:00
ZacharyZhang-NYandClaude Opus 5.5 7e38414591 Q112: a goal auditor with approved file access builds and tests in a throwaway copy
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 18:15:59 -04:00
ZacharyZhang-NYandClaude Opus 5.5 fc3bc1b4d1 Q111: a goal audit approves only after reading the work itself
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 18:08:00 -04:00
ZacharyZhang-NYandClaude Opus 5.5 5aab82b7c3 Q110: an approval pins the content it approved, and later changes show against it
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 18:01:15 -04:00
ZacharyZhang-NYandClaude Opus 5.5 e90b15a7a2 Q109: a declined deliverable reopens its task and tells the next session why
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 17:54:28 -04:00
ZacharyZhang-NYandClaude Opus 5.5 34c5557a32 Q108: deliverables under review are held until approved instead of written first
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 17:45:39 -04:00
ZacharyZhang-NYandClaude Opus 5.5 4765683b86 Q107: a task approval covers the content it was given; edits need a fresh one
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 17:34:40 -04:00
ZacharyZhang-NYandClaude Opus 5.5 c695fdb0f6 Q106: a hire awaiting approval is not on staff until approved, and a declined hire leaves
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 17:24:31 -04:00
ZacharyZhang-NYandClaude Opus 5.5 170b977bf8 Q105: the Connectors page grants and revokes connector access
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 17:12:59 -04:00
ZacharyZhang-NYandClaude Opus 5.5 558d678ba2 Q104: connector grants can narrow a toolkit to named actions and fixed argument values
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 17:05:23 -04:00
ZacharyZhang-NYandClaude Opus 5.5 b02834893f Q103: connector changes write the local result first and delete remotely last
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 16:52:57 -04:00
ZacharyZhang-NYandClaude Opus 5.5 0ebe0febdb Q102: several remote accounts of a toolkit are each adopted, none folded into another
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 16:49:15 -04:00
ZacharyZhang-NYandClaude Opus 5.5 4a6641fd49 Q101: a connector can hold several labelled company accounts, each granted and used by name
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 16:46:46 -04:00
ZacharyZhang-NYandClaude Opus 5.5 736c45c0ee Q100: reconnecting keeps the working connector account until the new one is authorized
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 16:32:46 -04:00
ZacharyZhang-NYandClaude Opus 5.5 6f8731cbac Q99: connector actions keep an execution record so a lost reply is not resent
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 16:23:23 -04:00
ZacharyZhang-NYandClaude Opus 5.5 552dfcb6ce Q98: external calls have a time limit and stop with the run
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 16:12:45 -04:00
ZacharyZhang-NYandClaude Opus 5.5 989127bed3 Q97: external calls that report failure are failed calls
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 16:04:15 -04:00
ZacharyZhang-NYandClaude Opus 5.5 a9620eaa5a Q96: connector action schemas reach the agent whole
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 16:00:12 -04:00
ZacharyZhang-NYandClaude Opus 5.5 f6447319a3 Q95: a run names the capabilities it could not load
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 15:55:33 -04:00
ZacharyZhang-NYandClaude Opus 5.5 d92bdbad90 Q94: agents search and run every connector action instead of the first twenty
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 15:48:19 -04:00
ZacharyZhang-NYandClaude Opus 5.5 7cd386a38c Q93: disconnect erases the secret here and revokes at the provider where it can
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 15:33:58 -04:00
ZacharyZhang-NYandClaude Opus 5.5 06eb2ce8dc Q92: an unreadable or unrenewable credential is logged on its request
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 15:20:36 -04:00
ZacharyZhang-NYandClaude Opus 5.5 6655982368 Q91: sign-in and renewal requests end on cancel or a stalled server
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 15:17:31 -04:00
ZacharyZhang-NYandClaude Opus 5.5 bcab38f003 Q90: model lists renew an expired sign-in the way runs do
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 15:08:54 -04:00
ZacharyZhang-NYandClaude Opus 5.5 bfe891009d Q89: an expired sign-in is refreshed once, shared by every run that needs it
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 15:06:05 -04:00
ZacharyZhang-NYandClaude Opus 5.5 7eef3d459f Q88: a sign-in is saved only if a run can use and renew it
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 15:02:12 -04:00