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
f95507ab25
feat(models): freeze provider request contracts and observe actual headers
2026-11-07 15:36:33 +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
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
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
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
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
5acb657157
fix: retain installation receipts without a size ceiling
2026-11-06 08:35:07 +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
c9c77c7ee6
fix: complete unrestricted waits catalog and network flows
2026-11-06 06:21:59 +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
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
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
Agent Workbench Dev
4a49f02daf
fix(context): size sealed browser-result reads without mutation reserve
2026-11-04 20:29:02 +08:00
Agent Workbench Dev
3647296a8d
perf(reading): share bounded file and log budgets across independent reads
2026-11-04 19:53:13 +08:00
Agent Workbench Dev
d2703ad340
fix(reading): preserve mixed-turn progress without disabling no-op guards
2026-11-04 19:43:48 +08:00
Agent Workbench Dev
1037031e82
fix(install): recheck file ownership after the manifest scan
2026-11-04 19:40:33 +08:00
Agent Workbench Dev
19f919ce52
perf(install): verify each manifest file with one native realpath instead of re-walking ancestors
...
The root chain is checked before and after each scan; each file uses one lstat+realpath equality, nlink and stream-name checks, and size is rechecked after read. Directory inventory keeps full checks for directories. Same hashes and manifest scope; junctioned subdirectory, hard link, stream path and escape stay rejected. Warm per-file cost on a real 1.16 tree 2.08ms -> 0.17ms with identical hashes.
2026-11-04 16:59:47 +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
b963e73301
feat(tasks): preserve reviewable original-text drafts and scope agreements
2026-11-04 13:28:00 +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
7e77fd65c3
fix(context): retain observed file fragments and current engineering facts
2026-11-04 07:52:59 +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
54dbe3d6fc
feat: add bounded connection network diagnostics
2026-11-03 23:11:33 +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
6bd605ad15
fix(models): unify model selection entries and preserve routes on budget saves
2026-11-03 14:40:45 +08:00
Agent Workbench Dev
983af1416e
fix(engines): preserve verified review pauses and always close native sessions
2026-11-03 12:20:20 +08:00
Agent Workbench Dev
ecdc939c29
fix(context): preserve progress counters and reserve fresh read evidence
2026-11-03 12:03:42 +08:00
Agent Workbench Dev
10dbd8f500
fix(runtime): provide current delivery evidence after reviewed application
2026-11-03 11:57:42 +08:00
Agent Workbench Dev
3659f5e858
fix(models): retain upstream identity and pause strict mismatches
2026-11-03 11:53:07 +08:00
Agent Workbench Dev
c1521e6cd2
fix: hand off complete changes and retain verified source context
2026-11-03 07:58:13 +08:00
Agent Workbench Dev
9106655d46
feat: integrate pinned original Purge with host execution gates
2026-11-02 22:32:31 +08:00