Live E2E Notifications #269
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Live E2E Notifications | |
| on: | |
| workflow_run: | |
| workflows: [Live E2E, Release] | |
| types: [completed] | |
| permissions: | |
| actions: read | |
| contents: read | |
| jobs: | |
| notify: | |
| if: github.event.workflow_run.conclusion == 'failure' || github.event.workflow_run.conclusion == 'success' | |
| runs-on: ubuntu-latest | |
| timeout-minutes: 5 | |
| continue-on-error: true | |
| steps: | |
| - name: Notify Slack | |
| env: | |
| GH_TOKEN: ${{ github.token }} | |
| REPOSITORY: ${{ github.repository }} | |
| RUN_ID: ${{ github.event.workflow_run.id }} | |
| RUN_NUMBER: ${{ github.event.workflow_run.run_number }} | |
| RUN_ATTEMPT: ${{ github.event.workflow_run.run_attempt }} | |
| WORKFLOW_ID: ${{ github.event.workflow_run.workflow_id }} | |
| WORKFLOW_NAME: ${{ github.event.workflow_run.name }} | |
| SHA: ${{ github.event.workflow_run.head_sha }} | |
| BRANCH: ${{ github.event.workflow_run.head_branch }} | |
| CONCLUSION: ${{ github.event.workflow_run.conclusion }} | |
| SLACK_WEBHOOK: ${{ secrets.SLACK_RELEASE_WEBHOOK }} | |
| run: | | |
| set -euo pipefail | |
| # A reusable suite job is named "Live e2e" or ends with the exact | |
| # " / Live e2e" suffix. Keep this aligned with the producer and gate. | |
| suite_conclusion() { | |
| jq -r '([.jobs[]? | select(.name == "Live e2e" or (.name | endswith(" / Live e2e"))) | .conclusion] | if any(.[]; . == "failure") then "failure" elif any(.[]; . == "success") then "success" else "none" end)' | |
| } | |
| if ! current_jobs="$(gh api --paginate "/repos/${REPOSITORY}/actions/runs/${RUN_ID}/attempts/${RUN_ATTEMPT}/jobs?per_page=100")"; then | |
| echo "::warning::Could not inspect jobs for ${WORKFLOW_NAME} run ${RUN_ID}; suppressing notification because the suite result is unknown." | |
| exit 0 | |
| fi | |
| current_suite="$(printf '%s\n' "$current_jobs" | jq -s '{jobs: map(.jobs[])}' | suite_conclusion)" | |
| startup_failure=false | |
| if [[ "$current_suite" == none && "$WORKFLOW_NAME" == "Live E2E" && "$CONCLUSION" == failure ]]; then | |
| current_suite=failure | |
| startup_failure=true | |
| elif [[ "$current_suite" == none || ("$current_suite" == failure && "$WORKFLOW_NAME" == "Release") ]]; then | |
| # Release's generic notification covers release failures and runs | |
| # that reused a staging result without creating a suite job. | |
| exit 0 | |
| fi | |
| prior_conclusion="" | |
| if (( RUN_ATTEMPT > 1 )); then | |
| if ! prior_jobs="$(gh api --paginate "/repos/${REPOSITORY}/actions/runs/${RUN_ID}/attempts/$((RUN_ATTEMPT - 1))/jobs?per_page=100")"; then | |
| echo "::warning::Could not inspect the prior attempt for ${WORKFLOW_NAME} run ${RUN_ID}; suppressing transition notification." | |
| exit 0 | |
| fi | |
| prior_conclusion="$(printf '%s\n' "$prior_jobs" | jq -s '{jobs: map(.jobs[])}' | suite_conclusion)" | |
| [[ "$prior_conclusion" != none ]] || prior_conclusion="" | |
| fi | |
| if ! history="$(gh api -X GET "/repos/${REPOSITORY}/actions/workflows/${WORKFLOW_ID}/runs" -f "branch=${BRANCH}" -F per_page=25)"; then | |
| if [[ "$current_suite" == success && -z "$prior_conclusion" ]]; then | |
| echo "::warning::Could not inspect recent ${WORKFLOW_NAME} history; suppressing recovery notification." | |
| exit 0 | |
| fi | |
| echo "::warning::Could not inspect recent ${WORKFLOW_NAME} history; continuing with the confirmed current result." | |
| else | |
| candidates="$(jq -r --argjson current_number "$RUN_NUMBER" --argjson current_attempt "$RUN_ATTEMPT" '(.workflow_runs // []) | map(select((.run_number != $current_number or (.run_attempt // 1) != $current_attempt) and .status == "completed" and (.conclusion == "failure" or .conclusion == "success"))) | sort_by(.run_number, (.run_attempt // 1)) | reverse | .[] | [.id, (.run_attempt // 1), .run_number, .conclusion] | @tsv' <<< "$history")" | |
| while IFS=$'\t' read -r candidate_id candidate_attempt candidate_number candidate_conclusion; do | |
| [[ -z "$candidate_id" ]] && continue | |
| if (( candidate_number > RUN_NUMBER || (candidate_number == RUN_NUMBER && candidate_attempt > RUN_ATTEMPT) )); then | |
| relation=newer | |
| else | |
| relation=older | |
| fi | |
| if [[ "$relation" == newer || -z "$prior_conclusion" ]]; then | |
| if ! candidate_jobs="$(gh api --paginate "/repos/${REPOSITORY}/actions/runs/${candidate_id}/attempts/${candidate_attempt}/jobs?per_page=100")"; then | |
| echo "::warning::Could not inspect candidate run ${candidate_id}; suppressing notification because history is incomplete." | |
| exit 0 | |
| fi | |
| candidate_suite="$(printf '%s\n' "$candidate_jobs" | jq -s '{jobs: map(.jobs[])}' | suite_conclusion)" | |
| if [[ "$candidate_suite" == none && "$WORKFLOW_NAME" == "Live E2E" && "$candidate_conclusion" == failure ]]; then | |
| candidate_suite=failure | |
| fi | |
| if [[ "$candidate_suite" == failure || "$candidate_suite" == success ]]; then | |
| if [[ "$relation" == newer ]]; then | |
| echo "A newer completed relevant suite exists; suppressing stale notification." | |
| exit 0 | |
| fi | |
| prior_conclusion="$candidate_suite" | |
| break | |
| fi | |
| fi | |
| done <<< "$candidates" | |
| fi | |
| if [[ "$current_suite" == success ]]; then | |
| [[ "$prior_conclusion" == failure ]] || exit 0 | |
| header="✅ Live E2E recovered" | |
| text="Live E2E recovered" | |
| detail="The previous relevant ${WORKFLOW_NAME} live suite failed; this run passed." | |
| else | |
| [[ "$prior_conclusion" != failure ]] || exit 0 | |
| if [[ "$startup_failure" == true ]]; then | |
| header="❌ Live E2E failed to start" | |
| text="Live E2E failed to start" | |
| detail="The Live E2E workflow failed before it produced a Live e2e job." | |
| else | |
| header="❌ Live E2E failed" | |
| text="Live E2E failed" | |
| detail="The ${WORKFLOW_NAME} live suite failed." | |
| fi | |
| fi | |
| run_url="https://github.com/${REPOSITORY}/actions/runs/${RUN_ID}" | |
| commit_url="https://github.com/${REPOSITORY}/commit/${SHA}" | |
| payload="$(jq -n --arg text "$text" --arg header "$header" --arg detail "$detail" --arg run_url "$run_url" --arg commit_url "$commit_url" --arg branch "$BRANCH" --arg sha "${SHA:0:7}" '{text:$text,blocks:[{type:"header",text:{type:"plain_text",text:$header,emoji:true}},{type:"section",text:{type:"mrkdwn",text:($detail + "\n*Branch:* `" + $branch + "`\n*Commit:* <" + $commit_url + "|" + $sha + ">\n*Workflow run:* <" + $run_url + "|view logs and failed tests>")}}]}')" | |
| curl -fsSL -X POST -H 'Content-type: application/json' --data "$payload" "$SLACK_WEBHOOK" |