hermes-agent/.github/workflows/ci.yml
ethernet 4dd535c8ea
fix(ci): route critical supply-chain findings through review gate (#68833)
Let the scanner report critical findings without failing. The review-label
gate owns the action-required status and blocking result, allowing the
ci-reviewed label rerun to clear both CI and the PR comment.
2026-07-21 18:51:26 +00:00

399 lines
17 KiB
YAML

name: CI
# Orchestrator workflow. Runs ``detect-changes`` once, then conditionally
# calls the sub-workflows that a PR can actually affect. A final
# ``all-checks-pass`` gate job aggregates results so branch protection only
# needs to require a single check.
#
# Sub-workflows are triggered via ``workflow_call`` and keep their own job
# definitions, matrices, and concurrency settings. They no longer have
# ``push:`` / ``pull_request:`` triggers of their own — everything flows
# through this file.
on:
pull_request:
push:
branches: [main]
permissions:
contents: read
pull-requests: write # needed by lint (PR comment) + supply-chain review_status
actions: read # needed by osv-scanner (SARIF upload)
security-events: write # needed by osv-scanner (SARIF upload)
packages: write # needed by docker build
concurrency:
group: ci-${{ github.ref }}
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
jobs:
# ─────────────────────────────────────────────────────────────────────
# detect: run the classifier once. Every downstream job reads its outputs
# to decide whether to run. On push/dispatch the classifier fails open
# (all lanes true) so post-merge validation is never weakened.
# ─────────────────────────────────────────────────────────────────────
detect:
name: Detect affected areas
runs-on: ubuntu-latest
timeout-minutes: 10
outputs:
python: ${{ steps.classify.outputs.python }}
frontend: ${{ steps.classify.outputs.frontend }}
site: ${{ steps.classify.outputs.site }}
scan: ${{ steps.classify.outputs.scan }}
deps: ${{ steps.classify.outputs.deps }}
npm_lock: ${{ steps.classify.outputs.npm_lock }}
docker_meta: ${{ steps.classify.outputs.docker_meta }}
mcp_catalog: ${{ steps.classify.outputs.mcp_catalog }}
ci_review: ${{ steps.classify.outputs.ci_review }}
event_name: ${{ github.event_name }}
steps:
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
- name: Get GitHub App token
id: app-token
uses: ./.github/actions/get-app-token
with:
client-id: ${{ secrets.APP_CLIENT_ID }}
private-key: ${{ secrets.APP_PRIVATE_KEY }}
- name: Detect affected areas
id: classify
uses: ./.github/actions/detect-changes
with:
# The get-app-token composite action falls back to GITHUB_TOKEN
# on fork PRs where APP_ID is unavailable.
github-token: ${{ steps.app-token.outputs.token }}
# ─────────────────────────────────────────────────────────────────────
# Lane-gated sub-workflows. Each runs in parallel after detect finishes.
# Skipped workflows (if condition is false) don't spin up runners.
# ─────────────────────────────────────────────────────────────────────
tests:
name: Python tests
needs: detect
if: needs.detect.outputs.python == 'true'
uses: ./.github/workflows/tests.yml
with:
slice_count: 8
secrets: inherit
lint:
name: Python lints
needs: detect
if: needs.detect.outputs.python == 'true'
uses: ./.github/workflows/lint.yml
with:
event_name: ${{ needs.detect.outputs.event_name }}
secrets: inherit
js-tests:
name: JS & TS checks
needs: detect
if: needs.detect.outputs.frontend == 'true'
uses: ./.github/workflows/js-tests.yml
secrets: inherit
e2e-desktop:
name: Desktop E2E
needs: detect
if: needs.detect.outputs.python == 'true' || needs.detect.outputs.frontend == 'true'
uses: ./.github/workflows/e2e-desktop.yml
docs-site:
name: Docs Site
needs: detect
if: needs.detect.outputs.site == 'true'
uses: ./.github/workflows/docs-site-checks.yml
secrets: inherit
history-check:
name: Deny unrelated histories
needs: detect
if: needs.detect.outputs.event_name == 'pull_request'
uses: ./.github/workflows/history-check.yml
secrets: inherit
contributor-check:
name: Check contributors
needs: detect
if: needs.detect.outputs.python == 'true'
uses: ./.github/workflows/contributor-check.yml
secrets: inherit
uv-lockfile:
name: Check uv.lock
needs: detect
uses: ./.github/workflows/uv-lockfile-check.yml
secrets: inherit
lockfile-diff:
name: package-lock.json diff
needs: detect
if: needs.detect.outputs.event_name == 'pull_request' && needs.detect.outputs.npm_lock == 'true'
uses: ./.github/workflows/lockfile-diff.yml
secrets: inherit
docker-lint:
name: Lint Docker scripts
needs: detect
if: needs.detect.outputs.docker_meta == 'true'
uses: ./.github/workflows/docker-lint.yml
secrets: inherit
docker:
name: Build&Test Docker image
needs: detect
if: needs.detect.outputs.python == 'true' || needs.detect.outputs.frontend == 'true' || needs.detect.outputs.docker_meta == 'true'
uses: ./.github/workflows/docker.yml
secrets: inherit
supply-chain:
name: Supply-chain scan
needs: detect
if: needs.detect.outputs.event_name == 'pull_request' && (needs.detect.outputs.scan == 'true' || needs.detect.outputs.deps == 'true')
uses: ./.github/workflows/supply-chain-audit.yml
with:
event_name: ${{ needs.detect.outputs.event_name }}
scan: ${{ needs.detect.outputs.scan == 'true' }}
deps: ${{ needs.detect.outputs.deps == 'true' }}
review-labels:
name: Review label gate
needs: [detect, supply-chain]
if: always() && needs.detect.outputs.event_name == 'pull_request' && (needs.detect.outputs.ci_review == 'true' || needs.detect.outputs.mcp_catalog == 'true' || needs.supply-chain.outputs.critical_findings == 'true')
uses: ./.github/workflows/review-labels.yml
with:
ci_review: ${{ needs.detect.outputs.ci_review == 'true' }}
mcp_catalog: ${{ needs.detect.outputs.mcp_catalog == 'true' }}
supply_chain: ${{ needs.supply-chain.outputs.critical_findings == 'true' }}
secrets: inherit
osv-scanner:
name: OSV scan
uses: ./.github/workflows/osv-scanner.yml
secrets: inherit
# ─────────────────────────────────────────────────────────────────────
# Live-updating PR review comment.
#
# A single ``comment-live`` job polls the GitHub Actions API every 15s
# for job statuses in this run, re-assembles the review comment from
# whatever results are available, and upserts it via the
# ``<!-- hermes-ci-review-bot -->`` marker.
#
# The poller exits when all non-infra jobs are completed (or on
# timeout). ci-timings' review_status is picked up automatically when
# its artifact becomes available — the poller downloads and merges it.
# ─────────────────────────────────────────────────────────────────────
comment-live:
name: CI review comment (live)
needs: [detect, review-labels, lockfile-diff, supply-chain, osv-scanner, uv-lockfile, history-check, contributor-check]
if: always() && github.event_name == 'pull_request' && github.event.pull_request.head.repo.fork != true
runs-on: ubuntu-latest
timeout-minutes: 40
steps:
- name: Checkout code
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
- name: Run live comment poller
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
GITHUB_REPOSITORY: ${{ github.repository }}
GITHUB_RUN_ID: ${{ github.run_id }}
PR_NUMBER: ${{ github.event.pull_request.number }}
RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
# Commit info for the review comment header.
COMMIT_SHA: ${{ github.event.pull_request.head.sha }}
COMMIT_MESSAGE: ${{ github.event.pull_request.head.commit.message }}
COMMIT_URL: ${{ github.server_url }}/${{ github.repository }}/pull/${{ github.event.pull_request.number }}/commits/${{ github.event.pull_request.head.sha }}
# Structured review statuses from workflow_call jobs.
# Each job outputs a JSON array of {source, results: [...]} objects
# that the assembler renders directly — no hardcoded job-name
# matching. We merge all available outputs into one array.
REVIEW_STATUSES: ${{ toJSON(needs.*.outputs.review_status) }}
run: |
set -uo pipefail
# REVIEW_STATUSES is a JSON array of strings (some may be empty
# when a job was skipped). Parse each string and merge into one
# flat array for the assembler.
python3 - <<'PYEOF'
import json, os, sys
raw = os.environ.get("REVIEW_STATUSES", "")
merged = []
if raw:
try:
arr = json.loads(raw)
except (json.JSONDecodeError, TypeError):
arr = []
for item in arr:
if not item:
continue
try:
statuses = json.loads(item)
except (json.JSONDecodeError, TypeError):
continue
if isinstance(statuses, list):
merged.extend(statuses)
# Write merged array to a temp file the poller reads.
with open("/tmp/review_statuses.json", "w") as f:
json.dump(merged, f)
print(f"Merged {len(merged)} review status entries")
PYEOF
python3 scripts/ci/live_comment.py \
--interval 15 \
--timeout 2100 \
--review-statuses-file /tmp/review_statuses.json
# ─────────────────────────────────────────────────────────────────────
# Gate: runs after everything. ``if: always()`` ensures it reports a
# status even when some deps were skipped. Only actual ``failure``
# results cause it to fail; ``skipped`` is treated as success.
#
# Branch protection should require ONLY this check.
#
# Outputs ``needs-json`` — a compact ``{job_name: result}`` dict — so
# the live comment poller can list failed jobs in the PR comment.
# ─────────────────────────────────────────────────────────────────────
all-checks-pass:
name: All required checks pass
needs:
- detect
- tests
- lint
- js-tests
- e2e-desktop
- docs-site
- history-check
- contributor-check
- uv-lockfile
- lockfile-diff
- docker-lint
- supply-chain
- review-labels
- osv-scanner
# comment-live is a polling job — it doesn't block the gate.
# we don't require docker to pass rn because it's so slow lol
# - docker
if: always()
runs-on: ubuntu-latest
timeout-minutes: 10
outputs:
needs-json: ${{ steps.evaluate.outputs.needs-json }}
steps:
- name: Evaluate job results
id: evaluate
env:
NEEDS: ${{ toJSON(needs) }}
run: |
echo "$NEEDS" | python3 -c "
import json, sys
needs = json.load(sys.stdin)
# Emit compact {job_name: result} for the comment assembler.
compact = {name: info['result'] for name, info in needs.items()}
print(f'needs-json={json.dumps(compact)}')
with open('$GITHUB_OUTPUT', 'a') as f:
f.write(f'needs-json={json.dumps(compact)}\n')
failed = [name for name, info in needs.items() if info['result'] == 'failure']
for name, info in sorted(needs.items()):
result = info['result']
icon = '✅' if result in ('success', 'skipped') else '❌'
print(f'{icon} {name}: {result}')
if failed:
print(f'::error::{len(failed)} job(s) failed: {\", \".join(failed)}')
sys.exit(1)
print('All checks passed (or were skipped)')
"
# ─────────────────────────────────────────────────────────────────────
# CI timing report: collect per-job/step durations from the GitHub API,
# cache them on main (as a baseline), and on PRs generate an HTML diff
# report with a gantt chart + per-step breakdown. The report is uploaded
# as an artifact and a markdown summary is written to $GITHUB_STEP_SUMMARY.
#
# The live comment poller picks up ci-timings' completion automatically —
# it reads review-status.json from the artifact when the job finishes.
# ─────────────────────────────────────────────────────────────────────
ci-timings:
name: CI timing report
needs: [all-checks-pass, docker]
if: always()
runs-on: ubuntu-latest
timeout-minutes: 10
steps:
- name: Checkout code
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
- name: Get GitHub App token
id: app-token
uses: ./.github/actions/get-app-token
with:
client-id: ${{ secrets.APP_CLIENT_ID }}
private-key: ${{ secrets.APP_PRIVATE_KEY }}
- name: Restore baseline cache (PR only)
if: github.event_name == 'pull_request'
uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
with:
path: ci-timings-baseline.json
# Prefix-match: exact key will never hit (run_id differs), so
# restore-keys finds the most recent baseline from main.
key: ci-timings-baseline-never-exact
restore-keys: |
ci-timings-baseline-
- name: Collect timings and generate report
env:
# Forks get no repo secrets (AUTOFIX_BOT_PAT is empty); fall back to
# the built-in read-only token so the timings API read still works
# there instead of hard-failing this advisory job on every fork PR.
# The get-app-token composite action falls back to GITHUB_TOKEN
# on fork PRs where APP_ID is unavailable.
GITHUB_TOKEN: ${{ steps.app-token.outputs.token }}
run: |
python3 scripts/ci/timings_report.py \
--baseline ci-timings-baseline.json \
--output ci-timings-report.html \
--json-out ci-timings.json \
--summary-out ci-timings-summary.md \
--review-status-out review-status.json
- name: Upload HTML report + review status
# Advisory report — artifact-service blips must not fail the job.
continue-on-error: true
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
id: ci-timings-artifact
with:
name: ci-timings-report
path: |
ci-timings-report.html
review-status.json
retention-days: 14
- name: Output summary
env:
REPORT_URL: ${{ steps.ci-timings-artifact.outputs.artifact-url}}
run: |
echo "# CI Timing report" >> "$GITHUB_STEP_SUMMARY"
echo "[View the full interactive report]($REPORT_URL)" >> "$GITHUB_STEP_SUMMARY"
cat ci-timings-summary.md >> "$GITHUB_STEP_SUMMARY"
- name: Save baseline cache (main only)
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
run: |
# Degraded runs (API rate-limited) produce no ci-timings.json —
# skip rather than fail, and never cache an empty baseline.
if [ -f ci-timings.json ]; then
cp ci-timings.json ci-timings-baseline.json
else
echo "No timings JSON this run — skipping baseline update"
fi
- name: Upload baseline to cache (main only)
if: github.event_name == 'push' && github.ref == 'refs/heads/main' && hashFiles('ci-timings-baseline.json') != ''
uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
with:
path: ci-timings-baseline.json
key: ci-timings-baseline-${{ github.run_id }}