mirror of
https://github.com/MBombeck/HealthLog.git
synced 2026-11-09 21:10:59 +00:00
ci: shard both suites by measured duration and split the unit suite
Vitest's --shard cut the file list into slices of equal length, which gave the integration shards 954 s to 1 449 s. A sequencer now deals files out by their measured duration, plus a fixed per-file cost for import and setup, longest first to the shard with the least work, and starts the longest files first inside a shard. Timings live in tests/durations/*.json and are regenerated from Vitest JSON reports with scripts/test-durations.mjs; every CI shard uploads its report. Integration shards run three workers each, one cloned database per worker. The unit suite runs as three projects decided per file from its source: guards and unit share a module graph inside a worker, isolated keeps a fresh one for every file that mocks, spies, stubs or resets. In CI it is three duration-balanced shards next to a job for lint, format, types and the OpenAPI drift check. The required check names stay as they were. "Lint, Typecheck & Test" is now the job that answers for the static checks and every unit shard, the way "integration" already answers for its shards. The browser-install guard recognises a direct, flags-only vitest run as a run of the unit suite.
This commit is contained in:
Marc-André Bombeck committed
1 parent
28f9b1948b
commit
e9f89bbebf
10 files changed
+3736
-47
No files matched your search
@@ -10,20 +10,23 @@ permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
# The suite outgrew a single runner, then a half-suite outgrew a slow one,
|
||||
# and then a third of it did too. Three shards of about 68 files cleared in
|
||||
# 13 minutes on an ordinary runner, but a slow runner day ran every test at
|
||||
# twice its usual duration and the first shard was still working through
|
||||
# its list when the 25-minute guard cut it off: three of four pushes to main
|
||||
# between 2026-08-31 and 2026-09-01 failed that way, with green tests logged
|
||||
# up to the last second. Four shards keep each slice around 50 files, and
|
||||
# the guard sits at three times the ordinary run rather than under two. A
|
||||
# wedged test still surfaces through vitest's own 60-second budget, so the
|
||||
# job timeout only needs to catch a container that never boots. Each shard
|
||||
# boots its own Postgres testcontainer.
|
||||
# Four shards of about equal duration, each running its files in parallel
|
||||
# against one database per worker. The shards used to be four slices of
|
||||
# equal file count, run serially: 954 s to 1 449 s, because a slice holding
|
||||
# the sharing matrix and the backup files took half again as long as one
|
||||
# holding small files. `--shard` now goes through the duration sequencer
|
||||
# (`tests/durations/sequencer.ts`, timings in
|
||||
# `tests/durations/integration.json`), and every file in a shard runs on
|
||||
# one of three workers, each against its own clone of the migrated template
|
||||
# (`tests/integration/worker-database.ts`). Three workers leave a core of
|
||||
# the four-core runner to the Postgres container. The job guard stays well
|
||||
# above an ordinary run; a wedged test still surfaces through vitest's own
|
||||
# 60-second budget, so the guard only needs to catch a container that never
|
||||
# boots. Each shard boots its own Postgres testcontainer and uploads its
|
||||
# JSON report, which `scripts/test-durations.mjs` turns into the timing file.
|
||||
shard:
|
||||
runs-on: ubuntu-24.04
|
||||
timeout-minutes: 40
|
||||
timeout-minutes: 30
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
@@ -48,8 +51,13 @@ jobs:
|
||||
# vitest a stray positional argument and the shard flag never applies —
|
||||
# both "shards" then run the full suite. Proven by a paired local run
|
||||
# before this workflow shipped.
|
||||
- run: pnpm exec vitest run --config vitest.integration.config.mts --shard=${{ matrix.shard }}/4
|
||||
- run: >-
|
||||
pnpm exec vitest run --config vitest.integration.config.mts
|
||||
--shard=${{ matrix.shard }}/4
|
||||
--reporter=default --reporter=json
|
||||
--outputFile.json=integration-report-${{ matrix.shard }}.json
|
||||
env:
|
||||
HEALTHLOG_INTEGRATION_WORKERS: "3"
|
||||
# The integration suite boots a Postgres testcontainer and points
|
||||
# Prisma at it via DATABASE_URL set inside `tests/integration/setup.ts`.
|
||||
# These env vars satisfy code paths that read them at module load.
|
||||
@@ -63,6 +71,15 @@ jobs:
|
||||
ENCRYPTION_KEY: "0000000000000000000000000000000000000000000000000000000000000000"
|
||||
SESSION_SECRET: "integration-tests"
|
||||
|
||||
- name: Upload the timing report
|
||||
if: always()
|
||||
uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
|
||||
with:
|
||||
name: integration-report-${{ matrix.shard }}
|
||||
path: integration-report-${{ matrix.shard }}.json
|
||||
if-no-files-found: ignore
|
||||
retention-days: 14
|
||||
|
||||
# Branch protection requires a check named exactly "integration". This job
|
||||
# carries that name and answers for every shard: it fails when any shard
|
||||
# failed or was cancelled, so a half-green matrix cannot satisfy the gate.
|
||||
|
||||
@@ -15,11 +15,72 @@ permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
quality:
|
||||
name: Lint, Typecheck & Test
|
||||
# The static checks: everything in the old single quality job except the
|
||||
# unit suite, which runs sharded below.
|
||||
static:
|
||||
name: Lint, Typecheck & OpenAPI
|
||||
runs-on: ubuntu-24.04
|
||||
if: github.event_name != 'schedule'
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
|
||||
- uses: pnpm/action-setup@ea17c68df8912ef543352723c149a84f56e3d413 # v6.1.0
|
||||
|
||||
- uses: actions/setup-node@949feb2413d6458794dcd2491c4babbbce0c15c1 # v7.1.0
|
||||
with:
|
||||
node-version: 22
|
||||
cache: "pnpm"
|
||||
|
||||
- run: pnpm install --frozen-lockfile
|
||||
|
||||
- run: pnpm db:generate
|
||||
|
||||
# Blocking since v1.15.20 — the settings-split refactor that kept
|
||||
# this warn-only is long done and the tree lints clean.
|
||||
- name: ESLint
|
||||
run: pnpm lint
|
||||
|
||||
# Prettier formatting gate. The format pass excludes generator-owned
|
||||
# artifacts via .prettierignore (notably docs/api/openapi.yaml, which
|
||||
# the OpenAPI drift check below enforces byte-for-byte).
|
||||
- name: Prettier format check
|
||||
run: pnpm format:check
|
||||
|
||||
- name: TypeScript strict check
|
||||
run: pnpm typecheck
|
||||
|
||||
# OpenAPI spec drift gate — hard-fail (flipped from warn-only in v1.4.25).
|
||||
#
|
||||
# The Zod registry is the source of truth for the public API contract.
|
||||
# Any route signature change must be reflected in `docs/api/openapi.yaml`
|
||||
# so downstream consumers (notably the v1.5 iOS Swift codegen) stay in
|
||||
# lockstep. If this step fails, run `pnpm openapi:generate` locally and
|
||||
# commit the regenerated spec.
|
||||
- name: OpenAPI spec drift check
|
||||
run: |
|
||||
pnpm openapi:generate
|
||||
if ! git diff --exit-code docs/api/openapi.yaml; then
|
||||
echo "::error::OpenAPI drift detected — regenerate the spec via 'pnpm openapi:generate' and commit the result. The Zod registry under src/lib/openapi/ is the source of truth for the public API contract."
|
||||
exit 1
|
||||
fi
|
||||
echo "::notice::OpenAPI spec in sync with Zod source schemas."
|
||||
|
||||
# The unit suite in three slices of about equal duration. `--shard` goes
|
||||
# through the duration sequencer in `vitest.config.mts`, which deals files
|
||||
# out by their measured time (`tests/durations/unit.json`) instead of by
|
||||
# count. Each slice uploads its JSON report, which is what
|
||||
# `scripts/test-durations.mjs` regenerates the timing file from.
|
||||
unit:
|
||||
runs-on: ubuntu-24.04
|
||||
if: github.event_name != 'schedule'
|
||||
timeout-minutes: 30
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
shard: [1, 2, 3]
|
||||
name: unit shard ${{ matrix.shard }}/3
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
|
||||
@@ -38,7 +99,8 @@ jobs:
|
||||
# real browser and measures the boxes. Without a browser here it caught
|
||||
# its own launch failure and passed anyway, so from its first day until
|
||||
# v1.38 it measured nothing on any run of this job. The browser is part
|
||||
# of the gate now; the test refuses to skip when CI is set.
|
||||
# of the gate now; the test refuses to skip when CI is set. Every slice
|
||||
# installs it, because the sequencer decides which slice the file lands in.
|
||||
#
|
||||
# Headless shell only: `chromium.launch()` resolves to
|
||||
# chromium_headless_shell, which is what the failing runs named, and the
|
||||
@@ -54,38 +116,40 @@ jobs:
|
||||
|
||||
- run: pnpm exec playwright install --only-shell chromium
|
||||
|
||||
# Blocking since v1.15.20 — the settings-split refactor that kept
|
||||
# this warn-only is long done and the tree lints clean.
|
||||
- name: ESLint
|
||||
run: pnpm lint
|
||||
|
||||
# Prettier formatting gate. The format pass excludes generator-owned
|
||||
# artifacts via .prettierignore (notably docs/api/openapi.yaml, which
|
||||
# the OpenAPI drift check below enforces byte-for-byte).
|
||||
- name: Prettier format check
|
||||
run: pnpm format:check
|
||||
|
||||
- name: TypeScript strict check
|
||||
run: pnpm typecheck
|
||||
|
||||
# vitest directly, not `pnpm test --`: pnpm hands the separator through
|
||||
# literally and the shard flag would never reach vitest.
|
||||
- name: Unit tests
|
||||
run: pnpm test
|
||||
run: >-
|
||||
pnpm exec vitest run --shard=${{ matrix.shard }}/3
|
||||
--reporter=default --reporter=json
|
||||
--outputFile.json=unit-report-${{ matrix.shard }}.json
|
||||
|
||||
# OpenAPI spec drift gate — hard-fail (flipped from warn-only in v1.4.25).
|
||||
#
|
||||
# The Zod registry is the source of truth for the public API contract.
|
||||
# Any route signature change must be reflected in `docs/api/openapi.yaml`
|
||||
# so downstream consumers (notably the v1.5 iOS Swift codegen) stay in
|
||||
# lockstep. If this step fails, run `pnpm openapi:generate` locally and
|
||||
# commit the regenerated spec.
|
||||
- name: OpenAPI spec drift check
|
||||
- name: Upload the timing report
|
||||
if: always()
|
||||
uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
|
||||
with:
|
||||
name: unit-report-${{ matrix.shard }}
|
||||
path: unit-report-${{ matrix.shard }}.json
|
||||
if-no-files-found: ignore
|
||||
retention-days: 14
|
||||
|
||||
# Branch protection requires a check named exactly "Lint, Typecheck & Test".
|
||||
# That used to be one job running everything in turn; it is now this one,
|
||||
# which answers for the static checks and every unit slice, so a half-green
|
||||
# set cannot satisfy the gate.
|
||||
quality:
|
||||
name: Lint, Typecheck & Test
|
||||
runs-on: ubuntu-24.04
|
||||
needs: [static, unit]
|
||||
if: always() && github.event_name != 'schedule'
|
||||
timeout-minutes: 5
|
||||
steps:
|
||||
- name: The static checks and every unit slice finished green
|
||||
run: |
|
||||
pnpm openapi:generate
|
||||
if ! git diff --exit-code docs/api/openapi.yaml; then
|
||||
echo "::error::OpenAPI drift detected — regenerate the spec via 'pnpm openapi:generate' and commit the result. The Zod registry under src/lib/openapi/ is the source of truth for the public API contract."
|
||||
if [ "${{ needs.static.result }}" != "success" ] || [ "${{ needs.unit.result }}" != "success" ]; then
|
||||
echo "static: ${{ needs.static.result }}, unit: ${{ needs.unit.result }}"
|
||||
exit 1
|
||||
fi
|
||||
echo "::notice::OpenAPI spec in sync with Zod source schemas."
|
||||
|
||||
# Not on pull requests. `pnpm audit` answers a question about the published
|
||||
# advisory database, not about the diff: the same lockfile passes on Monday
|
||||
|
||||
Reference in new issue
Block a user