agentic-toolkit/skills/engineering
Khalim Conn-Kowlessar db76a9f361 fix(ralph-loop): single-pr autopromote across DAG; env vs ticket failures
Two issues found running /ralph-loop end-to-end on a real project:

1. single-pr mode mirrored the toolkit's autopromote rule (blockers must
   be `Done`), which halts after each phase since tickets stay
   `In progress` until the final PR merges. That contradicts the
   README's "one PR for the whole DAG" semantics. Now `single-pr`
   counts a blocker resolved at status `In progress | In review | Done`
   so the loop completes the whole DAG in one invocation. `per-ticket`
   keeps the strict `Done` rule.

2. v1 failure handling treated all failures as ticket-failures and
   parked the issue as `Needs human` with a failure comment — wrong
   for environmental failures (Claude usage limit, network, interrupt)
   where the issue itself is fine. Now distinguished: env failures
   reset issue to `Ready` + un-assign; ticket failures park as before.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-05 13:51:37 +00:00
..
ralph-loop fix(ralph-loop): single-pr autopromote across DAG; env vs ticket failures 2026-05-05 13:51:37 +00:00
to-project feat: scaffold agentic-toolkit (runner + skills + setup) 2026-05-03 12:40:26 +01:00