ci(vps): hermetic nightly pre-flight on the release runner (descoped: e2e/integration/electron stay hosted) (#6305)

* ci(vps): extend the dynamic omni-release runner to e2e/integration/electron + nightly pre-flight

Completes the #6284 rollout to the jobs where the VPS pays the most:
- test-e2e (9 shards, 15-20min/shard hosted — dominated by setup, not tests),
  test-integration (2 shards) and electron-package-smoke now pick the
  self-hosted omni-release runner under the same gate: vars.USE_VPS_RUNNER
  == 'true' AND own-origin (fork PRs never reach self-hosted).
- nightly-release-green (the release pre-flight) becomes runner-dynamic too:
  on the VPS it runs in a clean env — no operator OMNIROUTE_API_KEY, no
  local noauth CLIs — eliminating the machine-specific false positives that
  dominated the 2026-07-05 pre-flight; passes --hermetic (no-op until the
  #6300 validator lands, then belt-and-suspenders).

Validation plan (per operator request): release-runner-up.sh -> full ci.yml
workflow_dispatch on this branch exercising e2e/integration/electron on the
VPS (proves playwright --with-deps + xvfb on the runner) -> down.sh -> VM
off verified.

* fix(mitm): test suite and CI must never mutate the OS trust store (OMNIROUTE_SKIP_SYSTEM_TRUST)

Incident 2026-07-05 on the self-hosted release runner (VM 113): the
integration test 'POST /cert: installs trust when cert exists' exercised the
REAL install path, wrote a 105-byte fake PEM (FakeMITMCertForTestingOnly)
into /usr/local/share/ca-certificates and update-ca-certificates baked the
invalid entry into ca-certificates.crt — breaking ALL system TLS on the VM
(curl error 77, apt cert failures, and the intermittent gzip-corrupted
next-build artifacts that failed 6/9 e2e shards in run 28754447912). Hosted
runners are ephemeral, so the same mutation went unnoticed for months.

- installCert/uninstallCert: skip the OS dispatch under
  OMNIROUTE_SKIP_SYSTEM_TRUST=1 — AFTER the input checks, so the #4546
  environment-skip contract (missing file throws -> structured skip) and the
  already-installed/not-installed early returns are preserved.
- installTproxyCa/uninstallTproxyCa: same guard, only when no run dep is
  injected (DI'd tests keep exercising the full command sequence with mocks).
- tests/_setup/isolateDataDir.ts sets the env for every node:test process;
  ci.yml/quality.yml/nightly-release-green.yml set it workflow-wide (e2e runs
  the real app outside the test setup).

TDD: tests/unit/system-trust-test-guard.test.ts (guard exported to every test
process; guarded install resolves on a real file without touching the OS;
missing-file contract preserved). 82/82 across the affected cert/tproxy/
agent-bridge suites.

* ci(vps): descope — e2e/integration/electron stay on hosted runners; keep the hermetic nightly pre-flight dynamic

Validation verdict (runs 28754447912 + 28757670732, VM 113):
- e2e cannot run >1 per VM: both jobs bind port 20128 ('already used') — needs
  a per-job port in the playwright runner before any VM rollout.
- concurrent ~1GB artifact downloads truncate on the VM uplink (gzip 'invalid
  compressed data' — with 2 runners the e2e shard passed; corruption returned
  at 4) — actions/download-artifact has no integrity retry here.
- integration shard 2 exceeded its 15-min timeout twice on the VM.
The VPS remains a win for whole-machine jobs: build/unit/vitest (already
dynamic via #6284) and nightly-release-green (single job, clean env, hermetic
pre-flight) — which this PR keeps.
This commit is contained in:
Diego Rodrigues de Sa e Souza
2026-07-05 21:49:48 -03:00
committed by GitHub
parent 6c1d597d42
commit b74c63a39e

View File

@@ -37,7 +37,11 @@ env:
jobs:
release-green:
name: Validate active release branch
runs-on: ubuntu-latest
# Dynamic runner: with USE_VPS_RUNNER=true (release window / on-demand pre-flight)
# this runs on the dedicated VPS runner — clean env (no operator OMNIROUTE_API_KEY,
# no local noauth CLIs => zero machine-specific false positives) and no contention.
# Nightly cron normally finds the var false (VM off) and falls back to hosted.
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && fromJSON('["self-hosted","omni-release"]')) || 'ubuntu-latest' }}
env:
JWT_SECRET: ci-nightly-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-nightly-api-key-secret-long
@@ -91,7 +95,9 @@ jobs:
id: validate
run: |
set +e
node scripts/quality/validate-release-green.mjs --json --with-build \
# --hermetic: scrub live-test trigger vars (self-hosted runner may carry
# operator env; hosted ignores the unknown flag before #6300 lands).
node scripts/quality/validate-release-green.mjs --json --with-build --hermetic \
1> release-green.json 2> release-green.log
echo "exit=$?" >> "$GITHUB_OUTPUT"
echo "------- report -------"