7 Commits

Author	SHA1	Message	Date
mateaix	0c045eaff8	fix: fence goal evaluations against definition revisions	2026-09-13 22:40:59 +08:00
mateaix	88cd78af5e	fix(goal): reject checklist passes without evidence	2026-09-13 20:38:19 +08:00
taobig	2090d09704	fix(goal): preserve continuation instructions and verified progress ... Keep autonomous prompts separate from persisted user messages while retaining conversation history and queued user attachment routing. Carry verified checklist evidence across segments and evaluate only changed criteria. Cancel model streams without interrupting checkpoint database writes. Fence late worker admission during shutdown, persist accepted queued messages and attachments, and leave interrupted execution leases recoverable. Add regressions for prompt selection, cumulative evidence, cancellation I/O, queued input durability and shutdown recovery. Verify 250 focused tests, 200 real General Assistant conversation rounds, 12 checkpoints across 13 autonomous segments, and pause/resume/disconnect/restart boundaries.	2026-08-26 06:17:05 -04:00
matevip	3883b68cca	fix(goal): drop score gate, bill failed evaluator calls, fix Evaluator SPI + tool prompt + bootstrap cap	2026-06-03 21:19:27 +08:00
matevip	a756da7817	test(goal): rewrite evaluator tests for bootstrap/verdict modes	2026-06-03 21:19:27 +08:00
matevip	9e93c52d9a	fix(goal): real evaluator, retry refactor, hardened node + extra edges	2026-05-21 22:27:00 +08:00
matevip	ce74a0ae48	feat(goal): graph topology + evaluation node wired into ReAct + Plan-Execute	2026-05-21 14:43:13 +08:00