From c52e2f1de74e71fb4e1ce7b5be33174d60c1c52a Mon Sep 17 00:00:00 2001 From: Joshua Temple Date: Fri, 26 Jun 2026 02:05:38 -0400 Subject: [PATCH] fix(fleet): raise per-repo suite watch cap to clear the longer 4env run The dispatch-and-watch step capped at 30 attempts (~30 min), but the 4env suite now runs the full lifecycle plus a chained multi-env hotfix and the Step 13 conflict probe, each a serial cascade run, exceeding 30 minutes. The fleet job timed out while the suite was still passing its probes. Raise the cap to 75 attempts (~75 min) to clear the suite's 60-minute internal job timeout with headroom. Signed-off-by: Joshua Temple --- .github/actions/dispatch-suite/action.yaml | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/.github/actions/dispatch-suite/action.yaml b/.github/actions/dispatch-suite/action.yaml index 407ac0e3..d9cb74bb 100644 --- a/.github/actions/dispatch-suite/action.yaml +++ b/.github/actions/dispatch-suite/action.yaml @@ -110,8 +110,11 @@ runs: # This loop retries on transient API errors while still failing closed on # real run failures and on timeout. # - # MAX_ATTEMPTS * WATCH_INTERVAL = wall-clock cap (~30 min at 60s each). - MAX_ATTEMPTS=30 + # MAX_ATTEMPTS * WATCH_INTERVAL = wall-clock cap (~75 min at 60s each). + # The 4env suite runs the full lifecycle plus a chained multi-env hotfix + # and the Step 13 conflict probe, each a serial cascade run, so the cap + # must clear its 60-minute internal job timeout with headroom. + MAX_ATTEMPTS=75 CONSEC_ERRORS=0 MAX_CONSEC_ERRORS=5 attempt=0