diff --git a/.github/workflows/conleche-nightly.yml b/.github/workflows/conleche-nightly.yml index 63285936a7..767e167d96 100644 --- a/.github/workflows/conleche-nightly.yml +++ b/.github/workflows/conleche-nightly.yml @@ -42,7 +42,6 @@ jobs: # 2.6 min) -> T = max(15, 68, 65) = 68, rounded up for a shared host. The first three runs replace this basis. timeout-minutes: 90 env: - CI_CACHE: /mnt/nvme-raid0/ci-cache/pvl-conleche ELAN_VERSION: v4.2.4 ELAN_SHA256: 42b94d4244e8353142c456ec0e4ca6528fd898a6c604d4059f494e706e431f63 LEAN_NUM_THREADS: '8' @@ -55,6 +54,11 @@ jobs: - name: Pinned elan in the job's own directory (sha256-checked, never a host install) run: | set -euo pipefail + # The cache lives beside the runner's _work dir, as nightly.yml's cache-nightly does. The old + # /mnt/nvme-raid0/ci-cache path exists only on lambda; on the clean-room hosts /mnt/nvme-raid0 is + # root-owned, so mkdir failed and the job never ran (runs 37082537768, 37163229207). + CI_CACHE="$(cd "$GITHUB_WORKSPACE/../.." && pwd)/cache-conleche" + echo "CI_CACHE=$CI_CACHE" >> "$GITHUB_ENV" export ELAN_HOME="$CI_CACHE/elan" mkdir -p "$CI_CACHE" if [ ! -x "$ELAN_HOME/bin/elan" ] || ! "$ELAN_HOME/bin/elan" --version | grep -q "${ELAN_VERSION#v}"; then diff --git a/docs/roadmaps/entries/PMAT-4715.yaml b/docs/roadmaps/entries/PMAT-4715.yaml new file mode 100644 index 0000000000..398c99140b --- /dev/null +++ b/docs/roadmaps/entries/PMAT-4715.yaml @@ -0,0 +1,19 @@ +- id: PMAT-4715 + github_issue: 4715 + item_type: task + title: 'B2: root-cause fixes for red nightlies on main' + status: inprogress + priority: critical + assigned_to: aprender-wmainred + created: 2026-10-04T00:00:00Z + updated: 2026-10-04T00:00:00Z + acceptance_criteria: + - Each red or cancelled scheduled workflow on main has a root cause named in its fix PR, one PR per defect, listed on issue #4715 + - Each fix PR changes no gate's acceptance; a threshold or acceptance change goes to the train lead's sign-off batch instead + - After each fix merges, the next scheduled or dispatched run of that workflow on main gets past the step that failed + phases: [] + subtasks: [] + estimated_effort: null + labels: + - kind:ci + notes: 'Parent #4678 (0.70.2), bar B2: no check red on main for more than 24 h. Proposed by aprender-a7, minted by cop aprender-14.' diff --git a/docs/roadmaps/roadmap.yaml b/docs/roadmaps/roadmap.yaml index f65016f6ce..6d12cec68b 100644 --- a/docs/roadmaps/roadmap.yaml +++ b/docs/roadmaps/roadmap.yaml @@ -24060,3 +24060,22 @@ Not done, pending the ruling: moving the 31 fixture files to an obviously synthe labels: - kind:docs notes: 'Operator C197, 2026-10-01 12:40Z: re-date via the spec''s own procedure; check unchanged; not a waiver.' +- id: PMAT-4715 + github_issue: 4715 + item_type: task + title: 'B2: root-cause fixes for red nightlies on main' + status: inprogress + priority: critical + assigned_to: aprender-wmainred + created: 2026-10-04T00:00:00Z + updated: 2026-10-04T00:00:00Z + acceptance_criteria: + - Each red or cancelled scheduled workflow on main has a root cause named in its fix PR, one PR per defect, listed on issue #4715 + - Each fix PR changes no gate's acceptance; a threshold or acceptance change goes to the train lead's sign-off batch instead + - After each fix merges, the next scheduled or dispatched run of that workflow on main gets past the step that failed + phases: [] + subtasks: [] + estimated_effort: null + labels: + - kind:ci + notes: 'Parent #4678 (0.70.2), bar B2: no check red on main for more than 24 h. Proposed by aprender-a7, minted by cop aprender-14.'