Commit Graph

231 Commits

Author SHA1 Message Date
Agent Workbench Dev dcea76b732 fix(budget): verify reservation history in ledger order and preserve output bounds 2026-11-04 19:34:36 +08:00
Agent Workbench Dev 78abbc3eb9 docs: plan reliability fixes and bounded delivery verification for 1.25.2 2026-11-04 19:29:37 +08:00
Agent Workbench Dev 62961cf128 docs(qa): record 1.25.1 formal upgrade and bounded real sample W results
Formal 1.25.1 upgrade retained PID 36552/Provider/key and all data exact; measured update 156369ms vs 1.25.0 774098ms (~5x faster). The first upgrade attempt was safely rolled back by the HOST_VERSION_MISMATCH guard before the APP_VERSION constant fix. Sample W network diagnostic and single identity preflight passed; the bounded Node task stopped at no_progress after 6 reading-only requests without proposing the allowed files, so it did not close the loop and did not reach R's reservation wall. v2 benefit remains proven at unit level with R's real receipts; no Purge AB/BA run per plan.

Docs only; evidence stays under gitignored .qa.
2026-11-04 19:06:51 +08:00
Agent Workbench Dev fe6db0aea5 test(live): add bounded real-model sample W drivers for formal 1.25.1
Faithful restoration of the sealed R live-delivery driver set (initial/network/preflight/node) targeting formal 1.25.1 and the observed-route-max-v2 reservation fix. Connection revision is read from the live snapshot rather than hardcoded; state helpers reuse the committed retained-host-state module. Same fixed expense-report task, jojocode GPT chat connection and 16K/2048/8-request/90000-token caps. No key value is ever read or re-saved.

Drivers only; no product code change.
2026-11-04 19:00:23 +08:00
Agent Workbench Dev e05b8fe008 docs: hand off unresolved delivery, network, budget and update questions 2026-11-04 15:40:44 +08:00
Agent Workbench Dev ddefe5f108 docs(release): seal and deliver task agreement 1.25 with retained production state 2026-11-04 15:34:29 +08:00
Agent Workbench Dev 78976ac775 docs(release): approve verified 1.25 installed flows and retained upgrade gates 2026-11-04 15:03:00 +08:00
Agent Workbench Dev f4ce7e6eef docs(qa): preserve timed out installer and reconcile its completed owned sample 2026-11-04 14:41:06 +08:00
Agent Workbench Dev 4b4ab676f6 docs(qa): review source and portable 1.25 task flows 2026-11-04 14:30:43 +08:00
Agent Workbench Dev 6c7191a169 docs(release): review immutable 1.25 candidate and original contract evidence 2026-11-04 14:13:16 +08:00
Agent Workbench Dev cb54b75abe chore(release): prepare immutable task agreement 1.25 delivery 2026-11-04 14:00:26 +08:00
Agent Workbench Dev 929d12ba66 feat(tasks): bind diagnostics to original failures and explain delivery gaps 2026-11-04 13:53:54 +08:00
Agent Workbench Dev d389b23c99 feat(ui): review original-text drafts and explicit task scope 2026-11-04 13:38:08 +08:00
Agent Workbench Dev b963e73301 feat(tasks): preserve reviewable original-text drafts and scope agreements 2026-11-04 13:28:00 +08:00
Agent Workbench Dev f702b70678 docs: seal adoption A/B release evidence and final review 2026-11-04 13:18:02 +08:00
Agent Workbench Dev 1366ee3233 test: verify adoption release with exact retained production state 2026-11-04 13:12:00 +08:00
Agent Workbench Dev a72151621b test: verify adoption A/B portable and real installed lifecycle 2026-11-04 12:52:42 +08:00
Agent Workbench Dev 59a14e9612 test: record independent adoption release rebuild and archive review 2026-11-04 12:27:11 +08:00
Agent Workbench Dev 1561560cbb build: prepare independent adoption A/B release and retained-host gates 2026-11-04 12:18:12 +08:00
Agent Workbench Dev 6fe04042c5 feat(runtime): observe turn evidence without changing execution controls 2026-11-04 11:26:47 +08:00
Agent Workbench Dev 785dd0c54d feat(tasks): review sourced requirements against current original evidence 2026-11-04 10:36:50 +08:00
Agent Workbench Dev ce3afb2f0d docs: seal Tianshu research and scoped adoption baseline 2026-11-04 10:03:32 +08:00
Agent Workbench Dev 676fc55420 test: seal live delivery V network stop and preserve original state 2026-11-04 08:59:41 +08:00
Agent Workbench Dev 19214ba3ad test: freeze bounded live delivery V contract before requests 2026-11-04 08:54:12 +08:00
Agent Workbench Dev 13849d038f test: seal working memory U release and retrospective 2026-11-04 08:39:17 +08:00
Agent Workbench Dev 7e77fd65c3 fix(context): retain observed file fragments and current engineering facts 2026-11-04 07:52:59 +08:00
Agent Workbench Dev 0644407b2c test: seal live delivery T and reproduce working memory gaps 2026-11-04 07:21:32 +08:00
Agent Workbench Dev 28d21e75f4 test: freeze bounded live delivery T contract before new calls 2026-11-04 06:53:14 +08:00
Agent Workbench Dev 8f41611b1b docs: seal reading reliability S release and next live validation plan 2026-11-04 01:35:36 +08:00
Agent Workbench Dev 5dcd6d7c3f fix: retain source continuation and explain request reservation pauses 2026-11-04 00:45:53 +08:00
Agent Workbench Dev fbedb7381b test: seal real delivery R evidence and reading reliability review 2026-11-04 00:17:51 +08:00
Agent Workbench Dev ea82bde3bc test: freeze bounded real delivery R plan and drivers 2026-11-04 00:00:50 +08:00
Agent Workbench Dev 8cf152e3ab docs: seal connection diagnostics Q release and retrospective 2026-11-03 23:53:31 +08:00
Agent Workbench Dev 54dbe3d6fc feat: add bounded connection network diagnostics 2026-11-03 23:11:33 +08:00
Agent Workbench Dev dca6cbdb2c test: seal jojocode delivery trial and network diagnosis review 2026-11-03 22:45:26 +08:00
Agent Workbench Dev 9d549a71a3 docs: seal 1.24.5 release and bounded real Node results 2026-11-03 22:28:14 +08:00
Agent Workbench Dev 676103c426 docs: retain task-plan UI acceptance before freezing context fix release 2026-11-03 21:39:54 +08:00
Agent Workbench Dev 13eb37efa7 fix: deduplicate mandatory task context and clarify check-plan evidence 2026-11-03 21:39:34 +08:00
Agent Workbench Dev a77bc9810b docs: audit routing changes after confirmed GPT configuration error 2026-11-03 20:44:08 +08:00
Agent Workbench Dev 860a191b8b docs: seal Messages release and rejected Claude identity preflight 2026-11-03 20:14:37 +08:00
Agent Workbench Dev 65ddee16b0 feat(models): add native Anthropic Messages and observed endpoint diagnostics 2026-11-03 18:58:59 +08:00
Agent Workbench Dev b832982d46 docs: investigate apikey protocol mismatch and preserve route evidence 2026-11-03 17:56:32 +08:00
Agent Workbench Dev cd5af2eb7b docs: seal 1.24.3 model selection acceptance and formal retention 2026-11-03 15:37:04 +08:00
Agent Workbench Dev f53eebb717 fix(release): validate long archive paths and support repeated 1.24.3 upgrades 2026-11-03 14:58:28 +08:00
Agent Workbench Dev d22448d1f2 fix(release): preserve Windows long paths when archiving source evidence 2026-11-03 14:45:46 +08:00
Agent Workbench Dev 6bd605ad15 fix(models): unify model selection entries and preserve routes on budget saves 2026-11-03 14:40:45 +08:00
Agent Workbench Dev 641c712b6e test: verify saved Claude route with one real identity preflight 2026-11-03 13:32:06 +08:00
Agent Workbench Dev 84b37fd636 test: seal 1.24.2 delivery integrity release and preserve formal state 2026-11-03 13:06:32 +08:00
Agent Workbench Dev 1153e19a4c release: prepare 1.24.2 identity and delivery integrity candidate 2026-11-03 12:20:50 +08:00
Agent Workbench Dev 410b347894 test: seal live retest and flag upstream model identity mismatch 2026-11-03 09:49:07 +08:00