ci: collapse built artifact test consumers

This commit is contained in:
Peter Steinberger
2026-04-23 03:24:41 +01:00
parent aa27a9474f
commit 5a22d16bde
2 changed files with 101 additions and 240 deletions

View File

@@ -455,7 +455,9 @@ jobs:
runs-on: ${{ github.repository == 'openclaw/openclaw' && 'blacksmith-8vcpu-ubuntu-2404' || 'ubuntu-24.04' }}
timeout-minutes: 20
outputs:
gateway-watch-result: ${{ steps.gateway_watch.outcome }}
channels-result: ${{ steps.built_artifact_checks.outputs['channels-result'] }}
core-support-boundary-result: ${{ steps.built_artifact_checks.outputs['core-support-boundary-result'] }}
gateway-watch-result: ${{ steps.built_artifact_checks.outputs['gateway-watch-result'] }}
steps:
- name: Checkout
shell: bash
@@ -568,11 +570,75 @@ jobs:
- name: Check CLI startup memory
run: pnpm test:startup:memory
- name: Run gateway watch regression
id: gateway_watch
if: needs.preflight.outputs.run_check_additional == 'true'
continue-on-error: true
run: node scripts/check-gateway-watch-regression.mjs --skip-build
- name: Run built artifact checks
id: built_artifact_checks
if: needs.preflight.outputs.run_checks == 'true' || needs.preflight.outputs.run_checks_node_core_dist == 'true' || needs.preflight.outputs.run_check_additional == 'true'
env:
RUN_CHANNELS: ${{ needs.preflight.outputs.run_checks }}
RUN_CORE_SUPPORT_BOUNDARY: ${{ needs.preflight.outputs.run_checks_node_core_dist }}
RUN_GATEWAY_WATCH: ${{ needs.preflight.outputs.run_check_additional }}
shell: bash
run: |
set -uo pipefail
names=()
pids=()
logs=()
declare -A results=(
["channels"]="skipped"
["core-support-boundary"]="skipped"
["gateway-watch"]="skipped"
)
start_check() {
local name="$1"
shift
local log="${RUNNER_TEMP}/${name}.log"
names+=("$name")
logs+=("$log")
echo "starting ${name}: $*"
"$@" >"$log" 2>&1 &
pids+=("$!")
}
if [ "$RUN_CHANNELS" = "true" ]; then
start_check "channels" env \
NODE_OPTIONS=--max-old-space-size=6144 \
OPENCLAW_VITEST_MAX_WORKERS=1 \
pnpm test:channels
fi
if [ "$RUN_CORE_SUPPORT_BOUNDARY" = "true" ]; then
start_check "core-support-boundary" env \
NODE_OPTIONS=--max-old-space-size=6144 \
OPENCLAW_VITEST_MAX_WORKERS=2 \
node scripts/run-vitest.mjs run --config test/vitest/vitest.full-core-support-boundary.config.ts
fi
if [ "$RUN_GATEWAY_WATCH" = "true" ]; then
start_check "gateway-watch" node scripts/check-gateway-watch-regression.mjs --skip-build
fi
for index in "${!pids[@]}"; do
name="${names[$index]}"
log="${logs[$index]}"
pid="${pids[$index]}"
if wait "$pid"; then
result="success"
else
result="failure"
fi
echo "::group::${name} log"
cat "$log"
echo "::endgroup::"
results["$name"]="$result"
done
for name in channels core-support-boundary gateway-watch; do
echo "${name}-result=${results[$name]}" >> "$GITHUB_OUTPUT"
done
- name: Upload gateway watch regression artifacts
if: always() && needs.preflight.outputs.run_check_additional == 'true'
@@ -936,117 +1002,25 @@ jobs:
name: ${{ matrix.check_name }}
needs: [preflight, build-artifacts]
if: ${{ !cancelled() && always() && needs.preflight.outputs.run_checks == 'true' && needs.build-artifacts.result == 'success' }}
runs-on: ${{ github.repository == 'openclaw/openclaw' && 'blacksmith-8vcpu-ubuntu-2404' || 'ubuntu-24.04' }}
timeout-minutes: 60
runs-on: ubuntu-24.04
timeout-minutes: 5
strategy:
fail-fast: false
matrix: ${{ fromJson(needs.preflight.outputs.checks_matrix) }}
steps:
- name: Checkout
shell: bash
env:
CHECKOUT_REPO: ${{ github.repository }}
CHECKOUT_SHA: ${{ github.sha }}
CHECKOUT_TOKEN: ${{ github.token }}
run: |
set -euo pipefail
workdir="$GITHUB_WORKSPACE"
auth_header="$(printf 'x-access-token:%s' "$CHECKOUT_TOKEN" | base64 | tr -d '\n')"
reset_checkout_dir() {
mkdir -p "$workdir"
find "$workdir" -mindepth 1 -maxdepth 1 -exec rm -rf {} +
}
checkout_attempt() {
local attempt="$1"
reset_checkout_dir
git init "$workdir" >/dev/null
git config --global --add safe.directory "$workdir"
git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}"
git -C "$workdir" config gc.auto 0
timeout --signal=TERM 30s git -C "$workdir" \
-c protocol.version=2 \
-c "http.https://github.com/.extraheader=AUTHORIZATION: basic ${auth_header}" \
fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
"+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
git -C "$workdir" checkout --force --detach "$CHECKOUT_SHA" || return 1
test -f "$workdir/.github/actions/setup-node-env/action.yml" || return 1
echo "checkout attempt ${attempt}/2 succeeded"
}
for attempt in 1 2; do
if checkout_attempt "$attempt"; then
exit 0
fi
echo "checkout attempt ${attempt}/2 failed"
sleep $((attempt * 5))
done
echo "checkout failed after 2 attempts" >&2
exit 1
- name: Setup Node environment
uses: ./.github/actions/setup-node-env
with:
node-version: "${{ matrix.node_version || '24.x' }}"
cache-key-suffix: "${{ matrix.cache_key_suffix || 'node24' }}"
install-bun: "false"
- name: Configure Node test resources
if: matrix.runtime == 'node' && (matrix.task == 'test' || matrix.task == 'channels')
- name: Verify ${{ matrix.task }} (${{ matrix.runtime }})
env:
TASK: ${{ matrix.task }}
run: |
echo "OPENCLAW_VITEST_MAX_WORKERS=2" >> "$GITHUB_ENV"
if [ "$TASK" = "test" ]; then
echo "OPENCLAW_TEST_PROJECTS_LEAF_SHARDS=1" >> "$GITHUB_ENV"
echo "OPENCLAW_TEST_SKIP_FULL_EXTENSIONS_SHARD=1" >> "$GITHUB_ENV"
fi
if [ "$TASK" = "channels" ]; then
echo "OPENCLAW_VITEST_MAX_WORKERS=1" >> "$GITHUB_ENV"
fi
- name: Restore dist cache
if: matrix.task == 'test'
id: checks-dist-cache
uses: actions/cache@v5
with:
path: |
dist/
dist-runtime/
key: ${{ runner.os }}-dist-build-${{ github.sha }}
- name: Verify dist cache
if: matrix.task == 'test' && steps.checks-dist-cache.outputs.cache-hit != 'true'
run: |
echo "Missing same-run dist cache for ${RUNNER_OS}-dist-build-${GITHUB_SHA}" >&2
exit 1
- name: Download A2UI bundle artifact
if: matrix.task == 'test' || matrix.task == 'channels'
uses: actions/download-artifact@v8
with:
name: canvas-a2ui-bundle
path: src/canvas-host/a2ui/
- name: Run ${{ matrix.task }} (${{ matrix.runtime }})
env:
TASK: ${{ matrix.task }}
NODE_OPTIONS: --max-old-space-size=6144
CHANNELS_RESULT: ${{ needs.build-artifacts.outputs['channels-result'] }}
shell: bash
run: |
set -euo pipefail
case "$TASK" in
test)
pnpm test
;;
channels)
pnpm test:channels
if [ "$CHANNELS_RESULT" != "success" ]; then
echo "Channel tests failed in build-artifacts: $CHANNELS_RESULT" >&2
exit 1
fi
;;
*)
echo "Unsupported checks task: $TASK" >&2
@@ -1261,144 +1235,31 @@ jobs:
name: ${{ matrix.check_name }}
needs: [preflight, build-artifacts]
if: ${{ !cancelled() && always() && needs.preflight.outputs.run_checks_node_core_dist == 'true' && needs.build-artifacts.result == 'success' }}
runs-on: ${{ github.repository == 'openclaw/openclaw' && 'blacksmith-8vcpu-ubuntu-2404' || 'ubuntu-24.04' }}
timeout-minutes: 60
runs-on: ubuntu-24.04
timeout-minutes: 5
strategy:
fail-fast: false
matrix: ${{ fromJson(needs.preflight.outputs.checks_node_core_dist_matrix) }}
steps:
- name: Checkout
shell: bash
- name: Verify Node test shard
env:
CHECKOUT_REPO: ${{ github.repository }}
CHECKOUT_SHA: ${{ github.sha }}
CHECKOUT_TOKEN: ${{ github.token }}
run: |
set -euo pipefail
workdir="$GITHUB_WORKSPACE"
auth_header="$(printf 'x-access-token:%s' "$CHECKOUT_TOKEN" | base64 | tr -d '\n')"
reset_checkout_dir() {
mkdir -p "$workdir"
find "$workdir" -mindepth 1 -maxdepth 1 -exec rm -rf {} +
}
checkout_attempt() {
local attempt="$1"
reset_checkout_dir
git init "$workdir" >/dev/null
git config --global --add safe.directory "$workdir"
git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}"
git -C "$workdir" config gc.auto 0
timeout --signal=TERM 30s git -C "$workdir" \
-c protocol.version=2 \
-c "http.https://github.com/.extraheader=AUTHORIZATION: basic ${auth_header}" \
fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
"+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
git -C "$workdir" checkout --force --detach "$CHECKOUT_SHA" || return 1
test -f "$workdir/.github/actions/setup-node-env/action.yml" || return 1
echo "checkout attempt ${attempt}/2 succeeded"
}
for attempt in 1 2; do
if checkout_attempt "$attempt"; then
exit 0
fi
echo "checkout attempt ${attempt}/2 failed"
sleep $((attempt * 5))
done
echo "checkout failed after 2 attempts" >&2
exit 1
- name: Setup Node environment
uses: ./.github/actions/setup-node-env
with:
node-version: "${{ matrix.node_version || '24.x' }}"
cache-key-suffix: "${{ matrix.cache_key_suffix || 'node24' }}"
install-bun: "false"
- name: Configure Node test resources
run: echo "OPENCLAW_VITEST_MAX_WORKERS=2" >> "$GITHUB_ENV"
- name: Restore dist cache
id: dist-cache
uses: actions/cache@v5
with:
path: |
dist/
dist-runtime/
key: ${{ runner.os }}-dist-build-${{ github.sha }}
- name: Verify dist cache
if: steps.dist-cache.outputs.cache-hit != 'true'
run: |
echo "Missing same-run dist cache for ${RUNNER_OS}-dist-build-${GITHUB_SHA}" >&2
exit 1
- name: Download A2UI bundle artifact
uses: actions/download-artifact@v8
with:
name: canvas-a2ui-bundle
path: src/canvas-host/a2ui/
- name: Run Node test shard
env:
NODE_OPTIONS: --max-old-space-size=6144
OPENCLAW_NODE_TEST_CONFIGS_JSON: ${{ toJson(matrix.configs) }}
OPENCLAW_NODE_TEST_INCLUDE_PATTERNS_JSON: ${{ toJson(matrix.includePatterns) }}
CORE_SUPPORT_BOUNDARY_RESULT: ${{ needs.build-artifacts.outputs['core-support-boundary-result'] }}
SHARD_NAME: ${{ matrix.shard_name }}
shell: bash
run: |
set -euo pipefail
node --input-type=module <<'EOF'
import { spawnSync } from "node:child_process";
import { writeFileSync } from "node:fs";
import { join } from "node:path";
import { resolveVitestCliEntry, resolveVitestNodeArgs } from "./scripts/run-vitest.mjs";
const configs = JSON.parse(process.env.OPENCLAW_NODE_TEST_CONFIGS_JSON ?? "[]");
if (!Array.isArray(configs) || configs.length === 0) {
console.error("Missing node test shard configs");
process.exit(1);
}
const includePatterns = JSON.parse(process.env.OPENCLAW_NODE_TEST_INCLUDE_PATTERNS_JSON ?? "null");
const childEnv = { ...process.env };
if (Array.isArray(includePatterns) && includePatterns.length > 0) {
const includeFile = join(
process.env.RUNNER_TEMP ?? ".",
`node-test-include-${process.env.GITHUB_JOB ?? "local"}-${Date.now()}.json`,
);
writeFileSync(includeFile, JSON.stringify(includePatterns), "utf8");
childEnv.OPENCLAW_VITEST_INCLUDE_FILE = includeFile;
}
for (const config of configs) {
console.error(`[test] starting ${config}`);
const result = spawnSync(
"pnpm",
[
"exec",
"node",
...resolveVitestNodeArgs(process.env),
resolveVitestCliEntry(),
"run",
"--config",
config,
],
{
env: childEnv,
stdio: "inherit",
},
);
if ((result.status ?? 1) !== 0) {
process.exit(result.status ?? 1);
}
}
EOF
case "$SHARD_NAME" in
core-support-boundary)
if [ "$CORE_SUPPORT_BOUNDARY_RESULT" != "success" ]; then
echo "Core support boundary shard failed in build-artifacts: $CORE_SUPPORT_BOUNDARY_RESULT" >&2
exit 1
fi
;;
*)
echo "Unsupported built-artifact shard: $SHARD_NAME" >&2
exit 1
;;
esac
checks-node-core-test:
permissions:

View File

@@ -18,7 +18,7 @@ The CI runs on every push to `main` and every pull request. It uses smart scopin
| `security-scm-fast` | Private key detection and workflow audit via `zizmor` | Always on non-draft pushes and PRs |
| `security-dependency-audit` | Dependency-free production lockfile audit against npm advisories | Always on non-draft pushes and PRs |
| `security-fast` | Required aggregate for the fast security jobs | Always on non-draft pushes and PRs |
| `build-artifacts` | Build `dist/`, Control UI, gateway watch, and reusable downstream artifacts | Node-relevant changes |
| `build-artifacts` | Build `dist/`, Control UI, built-artifact checks, and reusable downstream artifacts | Node-relevant changes |
| `checks-fast-core` | Fast Linux correctness lanes such as bundled/plugin-contract/protocol checks | Node-relevant changes |
| `checks-fast-contracts-channels` | Sharded channel contract checks with a stable aggregate check result | Node-relevant changes |
| `checks-node-extensions` | Full bundled-plugin test shards across the extension suite | Node-relevant changes |
@@ -27,7 +27,7 @@ The CI runs on every push to `main` and every pull request. It uses smart scopin
| `check` | Sharded main local gate equivalent: prod types, lint, guards, test types, and strict smoke | Node-relevant changes |
| `check-additional` | Architecture, boundary, extension-surface guards, package-boundary, and gateway-watch shards | Node-relevant changes |
| `build-smoke` | Built-CLI smoke tests and startup-memory smoke | Node-relevant changes |
| `checks` | Remaining Linux Node lanes: channel tests and push-only Node 22 compatibility | Node-relevant changes |
| `checks` | Verifier for built-artifact channel tests plus push-only Node 22 compatibility | Node-relevant changes |
| `check-docs` | Docs formatting, lint, and broken-link checks | Docs changed |
| `skills-python` | Ruff + pytest for Python-backed skills | Python-skill-relevant changes |
| `checks-windows` | Windows-specific test lanes | Windows-relevant changes |
@@ -53,7 +53,7 @@ Local changed-lane logic lives in `scripts/changed-lanes.mjs` and is executed by
On pushes, the `checks` matrix adds the push-only `compat-node22` lane. On pull requests, that lane is skipped and the matrix stays focused on the normal test/channel lanes.
The slowest Node test families are split or balanced so each job stays small: channel contracts split registry and core coverage into six weighted shards total, bundled plugin tests balance across six extension workers, auto-reply runs as three balanced workers instead of six tiny workers, and agentic gateway/plugin configs are spread across the existing source-only agentic Node jobs instead of waiting on built artifacts. Broad browser, QA, media, and miscellaneous plugin tests use their dedicated Vitest configs instead of the shared plugin catch-all. The broad agents lane uses the shared Vitest file-parallel scheduler because it is import/scheduling dominated rather than owned by a single slow test file. `runtime-config` runs with the infra core-runtime shard to keep the shared runtime shard from owning the tail. `check-additional` keeps package-boundary compile/canary work together and separates runtime topology architecture from gateway watch coverage; the boundary guard shard runs its small independent guards concurrently inside one job, and the gateway watch regression runs inside `build-artifacts` after `dist/` and `dist-runtime/` are already built so it measures watch stability without reserving another runner or rebuilding runtime artifacts.
The slowest Node test families are split or balanced so each job stays small: channel contracts split registry and core coverage into six weighted shards total, bundled plugin tests balance across six extension workers, auto-reply runs as three balanced workers instead of six tiny workers, and agentic gateway/plugin configs are spread across the existing source-only agentic Node jobs instead of waiting on built artifacts. Broad browser, QA, media, and miscellaneous plugin tests use their dedicated Vitest configs instead of the shared plugin catch-all. The broad agents lane uses the shared Vitest file-parallel scheduler because it is import/scheduling dominated rather than owned by a single slow test file. `runtime-config` runs with the infra core-runtime shard to keep the shared runtime shard from owning the tail. `check-additional` keeps package-boundary compile/canary work together and separates runtime topology architecture from gateway watch coverage; the boundary guard shard runs its small independent guards concurrently inside one job. Gateway watch, channel tests, and the core support-boundary shard run concurrently inside `build-artifacts` after `dist/` and `dist-runtime/` are already built, keeping their old check names as lightweight verifier jobs while avoiding two extra Blacksmith workers and a second artifact-consumer queue.
Android CI runs both `testPlayDebugUnitTest` and `testThirdPartyDebugUnitTest`, then builds the Play debug APK. The third-party flavor has no separate source set or manifest; its unit-test lane still compiles that flavor with the SMS/call-log BuildConfig flags, while avoiding a duplicate debug APK packaging job on every Android-relevant push.
`extension-fast` is PR-only because push runs already execute the full bundled plugin shards. That keeps changed-plugin feedback for reviews without reserving an extra Blacksmith worker on `main` for coverage already present in `checks-node-extensions`.
@@ -65,7 +65,7 @@ The CI concurrency key is versioned (`CI-v7-*`) so a GitHub-side zombie in an ol
| Runner | Jobs |
| -------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `ubuntu-24.04` | `preflight`, fast security jobs and aggregates (`security-scm-fast`, `security-dependency-audit`, `security-fast`), fast protocol/contract/bundled checks, sharded channel contract checks, `check` shards except lint, `check-additional` shards and aggregates, Node test aggregate verifiers, docs checks, Python skills, workflow-sanity, labeler, auto-response; install-smoke preflight also uses GitHub-hosted Ubuntu so the Blacksmith matrix can queue earlier |
| `blacksmith-8vcpu-ubuntu-2404` | `build-artifacts`, build-smoke, Linux Node test shards, bundled plugin test shards, remaining built-artifact consumers, `android` |
| `blacksmith-8vcpu-ubuntu-2404` | `build-artifacts`, build-smoke, Linux Node test shards, bundled plugin test shards, `android` |
| `blacksmith-16vcpu-ubuntu-2404` | `check-lint`, which remains CPU-sensitive enough that 8 vCPU cost more than it saved; install-smoke Docker builds, where 32-vCPU queue time cost more than it saved |
| `blacksmith-16vcpu-windows-2025` | `checks-windows` |
| `blacksmith-6vcpu-macos-latest` | `macos-node` on `openclaw/openclaw`; forks fall back to `macos-latest` |