Commit Graph

22 Commits

Author SHA1 Message Date
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 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 3659f5e858 fix(models): retain upstream identity and pause strict mismatches 2026-11-03 11:53:07 +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 e73bca94a0 fix: isolate model transport and stop replaying unknown requests 2026-11-02 20:11:21 +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 3b650275ff fix: separate model response and stream idle deadlines 2026-11-01 20:45:42 +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 96a7ed19c7 feat(vision): bind task screenshots, route vision and resume budget pauses 2026-11-01 00:48:38 +08:00
Agent Workbench Dev 31ed219477 feat(ui): show actual model route and inspect live stream evidence 2026-10-31 22:42:47 +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 578cf88eca feat(models): register protocols and evidence-bound capabilities 2026-10-31 21:56:41 +08:00
Agent Workbench Dev 72a496adfa feat(models): persist explicitly saved credentials with user-scoped DPAPI 2026-10-31 09:30:38 +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 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 fb58a41e08 feat: add model center and pool routing 2026-10-30 16:52:05 +08:00