Dotta and Paperclip
bc2d1efbe9
fix(evals): stop company warning removal at instruction boundaries
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 17:24:59 -06:00
Dotta and Paperclip
cad346555b
fix(evals): require the actual secure credential entry destination
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 17:24:59 -06:00
Dotta and Paperclip
877f2fd519
fix(evals): bound timeline possessives and heading scope
...
Co-Authored-By: Paperclip <paperclip@paperclip.ing >
2026-11-04 17:24:59 -06:00
Dotta
e75ba027fa
fix(evals): preserve private report bytes and restore derived attachments
2026-11-04 17:24:59 -06:00
Dotta
91d905c38f
fix(evals): retain canonical private framework attachments once
2026-11-04 17:24:59 -06:00
Dotta and Paperclip
b81c689651
test(evals): retain recovered team reply truthfulness
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 17:14:27 -06:00
Dotta and Paperclip
5e9d29b62f
fix(evals): admit verified team skill conflict recovery
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 17:14:27 -06:00
Dotta and Paperclip
17bdbeb0cc
fix(evals): preserve independent hire revision observations
...
Apply only the reviewed delta from 1590aa72a11af5b2bc3334f63e399947d8655329 to 2490177cb302e2ddee7eb226cb17e266ecc64e33; the original implementation and future v4 metadata are already integrated.
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 17:14:08 -06:00
Dotta and Paperclip
afb7890a7d
fix(evals): distinguish credential-value questions from safe guidance
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 17:13:59 -06:00
Dotta and Paperclip
969b4d7a31
fix(evals): keep company environment-name guidance single-purpose
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 17:13:59 -06:00
Dotta and Paperclip
500613d7b9
fix(evals): normalize contracted negative credential warnings
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 17:13:59 -06:00
Dotta and Paperclip
06e7ac0bd7
fix(evals): require authored skill company prefix
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 16:59:19 -06:00
Dotta
f0717eda1c
test(evals): inject invalid announcement deadline without readonly assignment
2026-11-04 16:59:19 -06:00
Dotta and Paperclip
554a647853
fix(evals): retain contrary worker scope for unnamed attempts
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 16:59:19 -06:00
Dotta
2a7d9b029b
test(evals): accept bound hire revision chat history
2026-11-04 16:44:18 -06:00
Dotta and Paperclip
ccd9ca6f35
fix(evals): answer bound company credential environment-name questions
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 16:44:18 -06:00
Dotta and Paperclip
12c5d4148a
test(evals): follow actual Files tab before skill Edit
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 16:43:52 -06:00
Dotta and Paperclip
1f4ab5571f
fix(evals): inspect authored skills through canonical editor
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 16:43:52 -06:00
Dotta and Paperclip
574e14692a
fix(evals): grade unnamed initial timeline attempts
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 16:43:52 -06:00
Dotta and Paperclip
03d0211b25
test(evals): version negative-warning admission correction
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 16:43:52 -06:00
Dotta and Paperclip
f6123a5377
fix(evals): preserve negative credential warnings after dashes
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 16:43:52 -06:00
Dotta and Paperclip
34d748d06f
test(evals): preserve announcement original response clock
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 16:43:52 -06:00
Dotta and Paperclip
c6cc59282a
fix(evals): separate dash-prefixed credential requests
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 15:32:41 -06:00
Dotta and Paperclip
0c2a776717
fix(evals): distinguish message objects from destinations
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 15:20:26 -06:00
Dotta and Paperclip
99e56b32d7
fix(evals): preserve omitted credential objects at chat requests
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 15:18:58 -06:00
Dotta and Paperclip
f00b2a5fa2
fix(evals): normalize solicitation contrast boundaries once
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 15:03:59 -06:00
Dotta and Paperclip
64fca2061a
fix(evals): reset credential requests at explicit contrasts
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 15:03:59 -06:00
Dotta and Paperclip
566b73729a
fix(evals): retain governing credential request clauses
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 14:53:32 -06:00
Dotta and Paperclip
fc33bb0eb8
fix(evals): share positive credential request classification
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 14:44:30 -06:00
Dotta and Paperclip
5aa9e33492
fix(evals): preserve imperative boundaries in credential warnings
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 14:30:34 -06:00
Dotta and Paperclip
07eb8e67ce
fix(runner): deliver configured task environment to OpenCode
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 14:14:17 -06:00
Dotta
65978bb6d0
fix(evals): retain qualified nonhuman handoff actors
2026-11-04 14:14:02 -06:00
Dotta and Paperclip
68fa733d47
fix(evals): bind personal publishing proof to native output receipt
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 14:13:51 -06:00
Dotta
6d6dc6e397
fix(evals): retain correlative success and known-source takeover
2026-11-04 14:13:29 -06:00
Dotta
1ad2507b85
fix(evals): distinguish timeline actors from deadline adjuncts
2026-11-04 14:13:29 -06:00
Dotta
9f8394c532
fix(evals): bound timeline object and result assertions
2026-11-04 14:13:29 -06:00
Dotta
58ff18c731
fix(evals): validate timeline actor clauses and exit outcomes
2026-11-04 13:46:54 -06:00
Dotta
1b5ebfaf7b
fix(evals): share timeline takeover provenance guards
2026-11-04 13:40:12 -06:00
Dotta
3a9c3fa8cc
fix(evals): recognize successor takeover in timeline context
2026-11-04 13:40:12 -06:00
Dotta
2569e44944
fix(evals): accept recorded passive timeline handoffs
2026-11-04 13:40:12 -06:00
Dotta
b20730d647
fix(server): clarify failed-action chat completion feedback
2026-11-04 13:36:09 -06:00
Dotta and Paperclip
5c378d5837
test(evals): version all credential destination consumers
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 13:27:42 -06:00
Dotta and Paperclip
8da511c603
fix(evals): preserve credential destination clauses
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 13:27:02 -06:00
Dotta and Paperclip
249b487a2d
test(e2e): read paired emphasis before review outcome checks
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 12:29:25 -06:00
Dotta
4713327d22
fix(runner): clarify active task history discovery scope
2026-11-04 12:29:25 -06:00
Dotta and Paperclip
b111963000
fix(evals): use completed personal setup context for acknowledgements
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 11:57:25 -06:00
Dotta and Paperclip
4a2c0e5dd9
test(evals): reject unsafe company optional-note placeholders
...
Keep the safe note label and reject a rendered request for credential text; preserve company oracle v4.
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 11:24:20 -06:00
Dotta and Paperclip
54643f501d
test(evals): reject unsafe personal question placeholders
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 11:23:34 -06:00
Dotta and Paperclip
78d36b0899
fix(evals): inspect rendered secret-question placeholder
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 11:23:34 -06:00
Dotta and Paperclip
9b17aa2c98
test(evals): declare company addressed-human acknowledgement v4
...
Exercise canonical anyone audience and safe optional-note affordance while retaining enumerated answers and saved-reference proof.
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-04 11:09:21 -06:00