Dotta and Paperclip
b68826b5df
test(runner): join real finish diagnostic producer to retention
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-06 00:36:12 -06:00
Dotta and Paperclip
88c4f35718
test(evals): recognize current unresolved team skill conflicts
...
Accept truthful exact-skill unresolved installation reports while rejecting unrelated or denied conflicts and independent current recovery claims. Keep saved state, actor, phase, links and original bounds strict.
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-06 00:20:54 -06:00
Dotta
bf311b939b
fix(evals): await mounted personal secret navigation controls
2026-11-06 00:20:38 -06:00
Dotta
1cb6160d0c
fix(evals): discover personal secure entry through visible menus
2026-11-06 00:20:38 -06:00
Dotta and Paperclip
bb32fea713
test(chat): declare company completion diagnostic provenance
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-06 00:12:15 -06:00
Dotta and Paperclip
f9ac63b821
test(evals): supply the existing multipart form as task context
...
Record only current question metadata through the ordinary source description. Bind first-turn duplicate detection to the real human query and native run, while preserving later follow-up questions and all submitted-answer checks.
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-06 00:12:00 -06:00
Dotta and Paperclip
76918553c8
fix(runner): emit finish diagnostics only after a bound rejection
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-06 00:12:00 -06:00
Dotta and Paperclip
e72803a2b6
fix(runner): retain closed OpenCode finish diagnostics
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-06 00:12:00 -06:00
Dotta and Paperclip
f5692c57da
test(chat): declare question failure-retirement provenance
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 23:00:31 -06:00
Dotta
8c01c75733
fix(evals): retire failed chat work before bounded diagnostics
2026-11-05 22:58:47 -06:00
Dotta and Paperclip
1d529b4e95
test(chat): match production confirmation prompt whitespace
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 22:57:32 -06:00
Dotta and Paperclip
c619ebbb7b
test(evals): state team runtime fixture provenance accurately
...
Record original and effective package identities, distinguish preserved non-runtime fields from rewritten sidecar bytes, and document one-shot supervisor bootstrap with non-overwrite coverage.
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 22:55:49 -06:00
Dotta and Paperclip
5dc8314e39
test(evals): normalize disposable team fixture runtime
...
Preserve the shipped team graph and non-runtime sidecar fields while selecting the campaign OpenCode account through the catalog package. Verify the actual no-overrides installer without model execution.
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 22:55:49 -06:00
Dotta and Paperclip
c9e3418fef
test(chat): declare human-input guidance provenance for affected cases
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 22:45:46 -06:00
Dotta and Paperclip
754788b2be
chore(runner): regenerate composed human-input guidance contracts
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 22:43:59 -06:00
Dotta and Paperclip
88781d8386
fix(runner): show complete human-input invocation examples
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 22:40:44 -06:00
Dotta and Paperclip
6be8ef50d1
fix(evals): scope negated skill-update completion claims
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 22:40:44 -06:00
Dotta and Paperclip
8cb77e382f
fix(evals): retain direct ACK identity and wake policy
...
Co-Authored-By: Paperclip <paperclip@paperclip.ing >
2026-11-05 22:33:56 -06:00
Dotta and Paperclip
6a30965f80
fix(evals): acknowledge actual human secure secret saves
...
Co-Authored-By: Paperclip <paperclip@paperclip.ing >
2026-11-05 22:26:21 -06:00
Dotta
936c3bbe0e
test(evals): bind timeline command notation to worker bullets
2026-11-05 20:48:50 -06:00
Dotta and Paperclip
2c99c248e8
test(evals): declare API discovery ranking provenance
...
Co-Authored-By: Paperclip <paperclip@paperclip.ing >
2026-11-05 19:42:50 -06:00
Dotta
e0cce66b7b
fix(api-search): ignore function words when ranking operations
2026-11-05 19:41:54 -06:00
Dotta and Paperclip
0e281cc0ba
test(evals): declare company approval route provenance
...
Co-Authored-By: Paperclip <paperclip@paperclip.ing >
2026-11-05 19:33:10 -06:00
Dotta and Paperclip
a260ff4962
fix(chat): use one continuation for secret binding approval
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 19:32:13 -06:00
Dotta and Paperclip
1b0ee51877
fix(evals): admit bounded environment-name questions by purpose
...
Co-Authored-By: Paperclip <paperclip@paperclip.ing >
2026-11-05 19:29:56 -06:00
Dotta and Paperclip
fe547be848
fix(evals): verify governed company secret binding approval
...
Co-Authored-By: Paperclip <paperclip@paperclip.ing >
2026-11-05 18:46:11 -06:00
Dotta
62300ee07d
test(evals): bind completed artifact edits to attached results
2026-11-05 18:22:07 -06:00
Dotta and Paperclip
d1ab241cac
fix(evals): scope company secret creation dialog waiter
...
Co-Authored-By: Paperclip <paperclip@paperclip.ing >
2026-11-05 17:22:46 -06:00
Dotta and Paperclip
4b277227e7
fix(evals): admit saved-secret-name metadata defaults
...
Co-Authored-By: Paperclip <paperclip@paperclip.ing >
2026-11-05 17:08:41 -06:00
Dotta and Paperclip
4b1db675c3
fix(evals): retain explicitly negated global assignment
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 16:53:24 -06:00
Dotta
abf45f414e
test(evals): version the corrected credential guard consumers
2026-11-05 16:51:08 -06:00
Dotta and Paperclip
47ad2fd7cf
fix(evals): retain unsafe credential destination continuations
...
Co-Authored-By: Paperclip <paperclip@paperclip.ing >
2026-11-05 16:49:32 -06:00
Dotta and Paperclip
04da1afa34
test(evals): bind global assignment negation to its verb
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 16:49:32 -06:00
Dotta and Paperclip
39203fd131
test(evals): admit proven author-only skill self-use
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 16:49:32 -06:00
Dotta and Paperclip
7ccfc33bf0
fix(evals): retain secure page suffixes in destination context
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 15:46:15 -06:00
Dotta and Paperclip
923624ce94
fix(evals): follow account settings and the nearest secure destination
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 15:46:15 -06:00
Dotta and Paperclip
1e9b50941c
test(evals): retain bounded historical coordination scope
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 15:37:42 -06:00
Dotta and Paperclip
4848a1e234
fix(evals): preserve canonical secret references and handoff actor scope
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 15:34:12 -06:00
Dotta and Paperclip
78890012ab
test(evals): separate coordinated current skill assertions
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 15:30:47 -06:00
Dotta and Paperclip
c59ac9d398
test(evals): scope team history to the named state assertion
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 15:30:47 -06:00
Dotta and Paperclip
de897ddd46
fix(chat): guide completed resource reports to usable links
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 15:17:22 -06:00
Dotta and Paperclip
b269f98160
fix(evals): read secret menu directions through Markdown emphasis
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 15:16:05 -06:00
Dotta and Paperclip
6d9421a3f3
fix(evals): admit ordinary secret menu directions without route examples
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 15:15:18 -06:00
Dotta and Paperclip
9ecaf0ad23
fix(evals): follow visible company secret menu directions
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 15:15:18 -06:00
Dotta and Paperclip
434aae3745
test(evals): bind team status claims to current skill state
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 15:10:39 -06:00
Dotta and Paperclip
e03ce0e27d
test(evals): version the changed secure-entry language consumers
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 15:10:39 -06:00
Dotta and Paperclip
3943038b35
fix(evals): keep parenthetical chat exclusions local to secure entry
...
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-11-05 15:10:39 -06:00
Dotta
84527f3b6c
fix(evals): acknowledge secure personal value save in followup
2026-11-05 15:09:43 -06:00
Dotta
2b68f4a902
fix(evals): bind personal save wait to entry dialog
2026-11-05 14:59:59 -06:00
Dotta and Paperclip
3514765f29
fix(evals): observe secure handoffs before private value entry
...
Co-Authored-By: Paperclip <paperclip@paperclip.ing >
2026-11-05 14:55:30 -06:00