Commit Graph

165 Commits

Author SHA1 Message Date
Agent Workbench Dev 36c6be4ff8 fix(ci): keep binary source explicit and Python logs in UTF-8 2026-11-07 22:17:31 +08:00
Agent Workbench Dev 0b4f1de439 fix(ci): log Electron setup and verify the product Edge runtime 2026-11-07 22:03:18 +08:00
Agent Workbench Dev af42b949ef feat(ci): verify clean source builds and pinned official contracts 2026-11-07 21:53:43 +08:00
Agent Workbench Dev a43262c112 docs(ci): pin Gitea sources and reproducible verification plan 2026-11-07 21:43:15 +08:00
Agent Workbench Dev ee97aaae73 feat(models): expose connection affinity and native-state provenance 2026-11-07 20:31:50 +08:00
Agent Workbench Dev 9e1feeebb3 feat(models): retain native cache blocks and bind cross-run provider state 2026-11-07 20:00:33 +08:00
Agent Workbench Dev 71f1805561 docs(models): pin native cache and provider-state sources 2026-11-07 19:51:54 +08:00
Agent Workbench Dev f95507ab25 feat(models): freeze provider request contracts and observe actual headers 2026-11-07 15:36:33 +08:00
Agent Workbench Dev 337d1bc922 docs(models): pin request version and header contract sources 2026-11-07 14:53:51 +08:00
Agent Workbench Dev ba4b449164 feat(models): version official specifications and preserve catalog provenance 2026-11-07 13:57:38 +08:00
Agent Workbench Dev 0cbf14a2e9 docs(models): pin official registry sources and current discovery gaps 2026-11-07 13:10:08 +08:00
Agent Workbench Dev da2e631381 feat(models): preserve complete incremental request ledger and exports 2026-11-07 12:38:44 +08:00
Agent Workbench Dev cb60fb1149 fix(models): preserve cache usage categories and receipt sources 2026-11-07 11:20:02 +08:00
Agent Workbench Dev 231db3a1f9 fix: preserve full MCP schemas and relay server validation errors 2026-11-07 10:47:31 +08:00
Agent Workbench Dev 32780bee8d fix: remove open execution record caps and preserve recovery history 2026-11-07 03:17:05 +08:00
Agent Workbench Dev dcaecd8b0a fix: select capable models and align effective permission evidence 2026-11-07 00:18:24 +08:00
Agent Workbench Dev 68603f9c76 fix: preserve native model parameters and align official Claude reasoning 2026-11-06 23:07:49 +08:00
Agent Workbench Dev 2bd7b24aa2 fix: use published Claude capacity when upstream metadata is missing 2026-11-06 20:52:39 +08:00
Agent Workbench Dev 341f5f69f6 fix: report actual output fields in upstream truncation diagnostics 2026-11-06 20:23:56 +08:00
Agent Workbench Dev ae5123c569 fix: refresh upstream catalog facts without invalidating saved credentials 2026-11-06 20:23:47 +08:00
Agent Workbench Dev fa74f5888d feat: bind collaboration roles and verify outputs with required Messages limits 2026-11-06 18:45:48 +08:00
Agent Workbench Dev 8c36296c7c feat: expose reversible experience adoption with isolated optional failures 2026-11-06 17:35:05 +08:00
Agent Workbench Dev 52cd60f226 feat: preserve source-bound experience drafts and reversible adoption 2026-11-06 17:06:29 +08:00
Agent Workbench Dev 7f87feeb83 release: prepare Orven 1.25.10 with retained-state reminder upgrade validation 2026-11-06 16:12:45 +08:00
Agent Workbench Dev 01377b24c0 feat: wire optional progress reminders to actual requests and verified readback 2026-11-06 16:05:21 +08:00
Agent Workbench Dev 7725cb2ad8 feat: add scoped optional reminder queue and verified readback 2026-11-06 15:38:50 +08:00
Agent Workbench Dev b3cb5d3420 feat: integrate Orven workspace and engineering repairs for 1.25.9 2026-11-06 15:06:07 +08:00
Agent Workbench Dev 1763d90db7 fix: reconcile terminal Git evidence and finalize delivery reports 2026-11-06 14:42:21 +08:00
Agent Workbench Dev 5e824dae0f fix: select the Python interpreter for each check plan 2026-11-06 14:17:57 +08:00
Agent Workbench Dev a6e31dec9d feat(context): audit tool visibility and isolate diagnostic history 2026-11-06 12:22:37 +08:00
Agent Workbench Dev ebd605f9ee fix(models): unify connection editing and remove demo entry points 2026-11-06 10:07:59 +08:00
Agent Workbench Dev 3494ae7ab2 fix: identify source archive bytes after Git newline conversion 2026-11-06 09:34:36 +08:00
Agent Workbench Dev fda264e40a fix: show active passthrough capacity and separate program source publication 2026-11-06 09:24:33 +08:00
Agent Workbench Dev 5acb657157 fix: retain installation receipts without a size ceiling 2026-11-06 08:35:07 +08:00
Agent Workbench Dev e86f576ff2 fix: retain previous patch upgrade compatibility 2026-11-06 08:03:02 +08:00
Agent Workbench Dev 0c4895b7c8 fix: honor complete REA contract and synchronize UI verification 2026-11-06 07:26:36 +08:00
Agent Workbench Dev b8a5f95018 fix: advance offline demo from original conversation 2026-11-06 06:55:29 +08:00
Agent Workbench Dev c9c77c7ee6 fix: complete unrestricted waits catalog and network flows 2026-11-06 06:21:59 +08:00
Agent Workbench Dev c93c434808 fix(runtime): apply open policy when continuing legacy tasks 2026-11-06 05:08:02 +08:00
Agent Workbench Dev 2fa220735d feat(runtime): default to passthrough and persist execution permissions 2026-11-06 04:58:57 +08:00
Agent Workbench Dev 67c034f4b6 fix(context): pair route capacities and preserve source evidence within bounded requests 2026-11-06 02:37:52 +08:00
Agent Workbench Dev 3e8c2f99fe test(release): preserve full-history diagnostics and recover the user-closed host baseline 2026-11-06 02:06:43 +08:00
Agent Workbench Dev 72115647d9 fix(runtime): preserve model capacity history and cache evidence with resumable file proposals 2026-11-06 01:18:37 +08:00
Agent Workbench Dev 2b17821138 fix(models): accept streamed thinking signatures and publish valid plan tools 2026-11-06 00:34:04 +08:00
Agent Workbench Dev 0fefa65eeb feat(runtime): recover a bounded number of output-ceiling truncations
When a turn stops at the output-token ceiling (output_truncated), the run no
longer dies. The truncated turn is still dropped whole - no tool is executed
and the invalid assistant message is never appended - but the model is given a
standalone instruction to split its proposals and the run continues. Recoveries
are capped per run (2); past that the original diagnostic still fails the run.
The connection is not cooled down for a truncation, since it responded fine and
only the model overran its budget, so the recovery turn can reach it. Both the
failed attempt and the recovering turn are accounted; neither is unknown.
Fixture regression covers recover-then-continue and the exhausted cap.
2026-11-05 05:56:10 +08:00
Agent Workbench Dev dfb6029f33 fix(models): give an actionable diagnostic when output hits the token ceiling
A response stopped at finish_reason=length (or Messages max_tokens /
Responses max_output_tokens) is still rejected whole - a complete leading
tool call is never applied because a later call may be cut mid-argument.
Previously the model only saw a generic incompleteness message and would
repeat the same oversized multi-tool turn. Now these paths raise a shared
output_truncated diagnostic telling the model to split proposals into one
file per response. Regression covers streaming/non-streaming Chat,
Responses and Messages, including the AB sample shape.
2026-11-05 04:47:42 +08:00
Agent Workbench Dev 6741510b2d fix(release): pair retained upgrades with the current package version 2026-11-05 01:23:34 +08:00
Agent Workbench Dev d038191832 feat(models): discover upstream catalogs and select shared-source model pools 2026-11-05 00:44:35 +08:00
Agent Workbench Dev f1242ee800 feat(models): pair reasoning controls with provider profiles and tool history 2026-11-05 00:13:53 +08:00
Agent Workbench Dev 3ab3a6e46a fix(models): reject empty Messages responses with retained evidence 2026-11-04 23:53:49 +08:00