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
d038191832
feat(models): discover upstream catalogs and select shared-source model pools
2026-11-05 00:44:35 +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
929d12ba66
feat(tasks): bind diagnostics to original failures and explain delivery gaps
2026-11-04 13:53:54 +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
13eb37efa7
fix: deduplicate mandatory task context and clarify check-plan evidence
2026-11-03 21:39:34 +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
bb45dabac4
fix: bind observed models and calibrate every model dispatch budget
2026-11-02 20:50:42 +08:00
Agent Workbench Dev
0a58c0d09f
fix(engine): bound native history and preserve verified continuation context
2026-11-02 19:42:29 +08:00
Agent Workbench Dev
d5d9df8275
feat: verify existing file results and preserve honest task delivery
2026-11-02 14:30:38 +08:00
Agent Workbench Dev
befae3313d
feat: ship lean runtime bundles and attributable update progress
2026-11-02 09:50:08 +08:00
Agent Workbench Dev
70ac4c40b5
fix: add web project folder picker and isolated HTML file previews
2026-11-02 08:54:31 +08:00
Agent Workbench Dev
dc32c899f1
feat: add owned Vite previews and isolated task browser with approved actions
2026-11-02 03:46:40 +08:00
Agent Workbench Dev
a94807fa60
feat: add owned dependency preparation and reproducible environment evidence
2026-11-01 23:44:45 +08:00
Agent Workbench Dev
97c8dde70d
fix: preserve upstream model errors and native request parameters
2026-11-01 22:05:08 +08:00
Agent Workbench Dev
0efc3450d2
fix: seal pause inputs before publishing a terminal run state
2026-11-01 13:41:32 +08:00
Agent Workbench Dev
441785a8b7
fix: account failed attempts and stop unchanged task loops in 1.20.1
2026-11-01 13:18:03 +08:00
Agent Workbench Dev
0736eca4cd
fix: preserve task intent across diagnostics and review continuation
2026-11-01 13:03:20 +08:00
Agent Workbench Dev
2a44f15693
feat: add fixed engineering evaluations and controlled candidate adoption
2026-11-01 09:52:50 +08:00
Agent Workbench Dev
be126525c5
feat(context): persist bounded source-verified parsing cache
2026-11-01 02:29:58 +08:00
Agent Workbench Dev
96a7ed19c7
feat(vision): bind task screenshots, route vision and resume budget pauses
2026-11-01 00:48:38 +08:00
Agent Workbench Dev
eeb11d6a76
feat(models): execute Responses and validated streams with capability routing
2026-10-31 22:27:53 +08:00
Agent Workbench Dev
dfe2e40387
feat(companion): add HTTPS pairing and scoped device authority
2026-10-31 17:38:57 +08:00
Agent Workbench Dev
249f191ebc
feat(desktop): attest and manage the owned Windows host lifecycle
2026-10-31 09:03:01 +08:00
Agent Workbench Dev
53e196af59
fix: preserve engine activity and host state through 1.14 upgrades
2026-10-31 06:48:36 +08:00
Agent Workbench Dev
f0eecbda47
feat: connect controlled engines to owned Tasks, approvals and budget ledger
2026-10-31 05:04:55 +08:00
Agent Workbench Dev
2ada7b899f
feat: seal isolated worker recovery, parent integration and review console
2026-10-31 02:02:06 +08:00
Agent Workbench Dev
1a847c1577
feat: execute two owned workers in isolated Git workspaces with frozen scopes
2026-10-31 01:05:32 +08:00
Agent Workbench Dev
f4bd0ad8dc
fix: preserve model state, isolate commands and harden local HTTP in 1.12.1
2026-10-30 23:01:19 +08:00
Agent Workbench Dev
3f6797b8ee
feat: integrate approved MCP tools and recovery for 1.12
2026-10-30 20:34:54 +08:00
Agent Workbench Dev
601f13c4f8
feat: add source-verified project skills
2026-10-30 18:58:55 +08:00
Agent Workbench Dev
b25b7ef974
feat: add evidence-bound task recovery checkpoints
2026-10-30 18:41:56 +08:00
Agent Workbench Dev
af0a42b610
feat: use verified project memory within request budgets
2026-10-30 18:16:46 +08:00
Agent Workbench Dev
fb58a41e08
feat: add model center and pool routing
2026-10-30 16:52:05 +08:00
Agent Workbench Dev
a103ab1b22
feat: verify task dependency plans against original execution evidence
2026-10-30 10:25:55 +08:00
Agent Workbench Dev
5921b8efdc
feat: add task-bound real browser checks and verified page delivery
2026-10-30 08:46:53 +08:00
Agent Workbench Dev
91981c1400
feat: verify owned DeepSeek engine connections and responsive task execution
2026-10-30 07:25:09 +08:00
Agent Workbench Dev
6a1ef125a0
feat: integrate task-bound REA research and portable runtime
2026-10-30 05:21:17 +08:00
Agent Workbench Dev
4d06618f62
fix: preserve advancing pages across resumed task runs
2026-10-30 04:15:08 +08:00
Agent Workbench Dev
f291a7ed6a
feat: ship bounded tool feedback and Python engineering checks in 1.7.0
2026-10-30 03:29:36 +08:00
Agent Workbench Dev
f12a12e12e
fix: retain verifiable task observations within context budgets
2026-10-30 01:28:23 +08:00