weichen dee06368ea Add real execution agent probe harness ...

Why: verify configured Agent CLIs one profile at a time before declaring them usable

Evidence: 53 focused tests, agent-exec validation, 397-test governance regression, and diff check

Impact: adds opt-in source-external probes, acceptance checks, and current task records

Refs: U5; docs/superpowers/plans/2026-10-15-project-agent-execution.md

2026-10-15 05:22:00 +00:00

..

archive

Close 1 merged task card(s) and archive them

2026-10-14 17:35:07 +00:00

artifacts

Archive the merged IAM integration task with actual gate results

2026-10-13 16:55:34 +00:00

e1-eval

Record the E1 verification evidence and the eval comparison

2026-10-10 09:47:05 +00:00

e3-eval

Record the E3 eval comparison and close out the card

2026-10-10 16:28:12 +00:00

e4-eval

Record the E4 verification evidence and finalize the card

2026-10-11 01:27:22 +00:00

e5-eval

Record the E5 three-arm comparison and the selection report

2026-10-10 17:21:01 +00:00

genui-u1

Record the U1 trial: harness, results, and task-card outcomes

2026-10-11 04:43:03 +00:00

model-ab

Complete the model A/B comparison and record the selection report

2026-10-10 02:24:56 +00:00

phase01-eval

Record the after-phase01 live eval and the before/after verdict

2026-10-09 14:04:05 +00:00

phase02-eval

Merge origin/main into the card-close branch (archive side wins)

2026-10-09 17:41:15 +00:00

phase03-eval

Record the phase03 live eval and result summary

2026-10-09 18:24:50 +00:00

phase04-eval

Record the phase04 live eval and result summary

2026-10-09 23:35:48 +00:00

phase05-eval

Record the phase05 live eval and result summary

2026-10-10 00:25:37 +00:00

reviews

Preserve reviewed planning evidence and explicit ownership gaps

2026-10-07 14:09:13 +00:00

feature-goal-first-delivery.md

Add real execution agent probe harness

2026-10-15 05:22:00 +00:00