TheRock/rocm-libraries/.github/workflows/auto-retry-failed.yml

# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
# SPDX-License-Identifier: MIT

# Automatically re-runs the failed jobs of a watched CI run, up to a fixed
# number of attempts. This mirrors clicking "Re-run failed jobs" in the web UI:
# `gh run rerun --failed` calls the same rerun-failed-jobs API, so each retry
# lands on a fresh runner and is recorded as a new attempt on the SAME run
# (prior attempts stay visible in the run's attempt history).
#
# The retry loop is self-capping: `workflow_run` fires whenever an attempt of
# the watched run completes, so a failed attempt N triggers this workflow with
# run_attempt == N, which re-runs and produces attempt N+1, and so on until the
# run_attempt cap below is reached.
#
# Motivation: most nightly failures are infrastructure flakes (no GPU assigned,
# an overloaded/wedged machine, or a network blip during artifact fetch) rather
# than real test regressions. Those clear on a fresh runner, which a same-runner
# step retry cannot provide.
#
# NOTE: `workflow_run` always uses the copy of this file on the repository's
# default branch, and only fires for runs there. It has no effect from a PR
# branch until merged.

name: Auto-retry failed CI

on:
  workflow_run:
    workflows:
      - "TheRock CI Nightly"
      - "TheRock Multi-Arch Nightly CI"
    types:
      - completed

permissions:
  # Required to trigger a re-run of the watched workflow run.
  actions: write
  contents: read

jobs:
  rerun-failed:
    name: Rerun failed jobs
    runs-on: ubuntu-24.04
    timeout-minutes: 5
    # Only genuine failures under the attempt cap. run_attempt < 4 allows up to
    # 4 total attempts (the original run plus 3 auto-retries). 'cancelled'
    # (concurrency / superseded runs) and 'startup_failure' are intentionally
    # excluded so we never retry work that was deliberately abandoned.
    if: >-
      github.event.workflow_run.conclusion == 'failure' &&
      github.event.workflow_run.run_attempt < 4
    env:
      GH_TOKEN: ${{ github.token }}
      RUN_ID: ${{ github.event.workflow_run.id }}
      ATTEMPT: ${{ github.event.workflow_run.run_attempt }}
    steps:
      - name: Re-run failed jobs
        run: |
          echo "Run ${RUN_ID} failed on attempt ${ATTEMPT}; re-running failed jobs on fresh runners."
          gh run rerun "${RUN_ID}" --failed --repo "${{ github.repository }}"