Files
multica/.github/workflows/ci.yml
milymarkovic 09dce598df MUL-5155: KAP-1051: diagnose Codex thread/start timeouts fail-closed (#5759)
* fix(agent/codex): diagnose thread start timeouts (KAP-1051)

Co-authored-by: multica-agent <github@multica.ai>

* fix(agent/codex): validate thread ID before success lifecycle

Co-authored-by: multica-agent <github@multica.ai>

* fix(agent/codex): confirm process tree cleanup

Co-authored-by: multica-agent <github@multica.ai>

* fix(agent/codex): bound Windows pipe cleanup

Co-authored-by: multica-agent <github@multica.ai>

* ci: run bounded Codex cleanup test on Windows

Co-authored-by: multica-agent <github@multica.ai>

* fix(agent): reap initialize timeout process groups

* fix(agent): redact initialize timeout stderr

* fix(agent): redact initialize context failures

---------

Co-authored-by: multica-agent <github@multica.ai>
2026-07-23 15:09:50 +08:00

242 lines
9.2 KiB
YAML

name: CI
on:
push:
branches: [main]
pull_request:
branches: [main]
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
# Decides whether the (heavy, ~6min) frontend job has anything to do.
# The frontend job validates the web/desktop apps, the shared packages,
# the install graph, and the selfhost / reserved-slugs scripts it runs;
# a pure backend-only or docs-only PR touches none of those and gains
# nothing from a full web build. This job emits a single `frontend`
# output consumed by the frontend job below.
changes:
runs-on: ubuntu-latest
permissions:
contents: read
pull-requests: read
outputs:
frontend: ${{ steps.decide.outputs.frontend }}
steps:
- name: Checkout
uses: actions/checkout@v6
- name: Filter paths
id: filter
uses: dorny/paths-filter@v3
with:
# apps/docs is excluded from the frontend turbo run, so a
# docs-only change does not need this job. apps/mobile has its
# own mobile-verify workflow. Everything else the frontend job
# touches is listed here; bias toward over-matching since a
# missed path silently skips validation.
filters: |
frontend:
- 'apps/web/**'
- 'apps/desktop/**'
- 'packages/**'
- 'package.json'
- '.npmrc'
- 'pnpm-lock.yaml'
- 'pnpm-workspace.yaml'
- 'turbo.json'
- '.github/workflows/ci.yml'
- 'scripts/generate-reserved-slugs.mjs'
- 'server/internal/handler/reserved_slugs.json'
- 'scripts/selfhost-config.test.sh'
- 'scripts/check.sh'
- 'scripts/dev.sh'
- 'scripts/local-env.sh'
- '.env.example'
- 'docker-compose.selfhost.yml'
- name: Decide
id: decide
# Always run the frontend job on push to main (full validation);
# on pull_request, run only when frontend-relevant paths changed.
# The frontend job itself always runs and reports success — its
# steps are gated on this output rather than the job being skipped
# — so the required "frontend" status check is satisfied with a
# genuine green instead of being left pending on filtered PRs.
env:
EVENT_NAME: ${{ github.event_name }}
FRONTEND_CHANGED: ${{ steps.filter.outputs.frontend }}
run: |
if [ "$EVENT_NAME" != "pull_request" ] || [ "$FRONTEND_CHANGED" = "true" ]; then
echo "frontend=true" >> "$GITHUB_OUTPUT"
else
echo "frontend=false" >> "$GITHUB_OUTPUT"
fi
frontend:
needs: changes
runs-on: ubuntu-latest
steps:
- name: Checkout
if: ${{ needs.changes.outputs.frontend == 'true' }}
uses: actions/checkout@v6
- name: Setup pnpm
if: ${{ needs.changes.outputs.frontend == 'true' }}
uses: pnpm/action-setup@v4
- name: Setup Node.js
if: ${{ needs.changes.outputs.frontend == 'true' }}
uses: actions/setup-node@v6
with:
node-version: 22
cache: pnpm
- name: Install dependencies
if: ${{ needs.changes.outputs.frontend == 'true' }}
run: pnpm install
- name: Test self-host env derivation
if: ${{ needs.changes.outputs.frontend == 'true' }}
run: bash scripts/selfhost-config.test.sh
- name: Verify reserved-slugs.ts is up to date
if: ${{ needs.changes.outputs.frontend == 'true' }}
# Re-runs the generator and fails on any drift from the
# checked-in TypeScript output. The Go side embeds the JSON
# source directly, so a passing diff here proves both sides
# share one source of truth.
run: |
pnpm generate:reserved-slugs
git diff --exit-code -- packages/core/paths/reserved-slugs.ts
- name: Build, type check, lint, and test
if: ${{ needs.changes.outputs.frontend == 'true' }}
# Mobile lives in a parallel mobile-verify workflow (path-filtered
# to apps/mobile/** + packages/core/**) so it doesn't add
# ~50s of expo-lint + tsc to every web/desktop PR. Keep this
# filter in sync with the root package.json scripts, which also
# exclude @multica/mobile.
run: pnpm exec turbo build typecheck lint test --filter='!@multica/docs' --filter='!@multica/mobile'
backend:
runs-on: ubuntu-latest
services:
postgres:
image: pgvector/pgvector:pg17
env:
POSTGRES_DB: multica
POSTGRES_USER: multica
POSTGRES_PASSWORD: multica
ports:
- 5432:5432
options: >-
--health-cmd "pg_isready -U multica -d multica"
--health-interval 5s
--health-timeout 5s
--health-retries 20
redis:
image: redis:7-alpine
ports:
- 6379:6379
options: >-
--health-cmd "redis-cli ping"
--health-interval 5s
--health-timeout 5s
--health-retries 10
env:
DATABASE_URL: postgres://multica:multica@localhost:5432/multica?sslmode=disable
# Wires up the RedisLocalSkill*_test.go suite. Distinct from REDIS_URL
# (which would flip the server binary itself onto the Redis-backed
# realtime relay + request stores); the tests talk to this Redis
# directly so they run alongside the Postgres-backed suite.
REDIS_TEST_URL: redis://localhost:6379/1
steps:
- name: Checkout
uses: actions/checkout@v6
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: "1.26.1"
cache-dependency-path: server/go.sum
- name: Build
run: cd server && go build ./...
- name: Run migrations
run: cd server && go run ./cmd/migrate up
- name: Verify Go test wrapper
run: bash scripts/test-go.test.sh
- name: Test
run: bash scripts/test-go.sh --race
windows-execenv:
# The environment-preparation deadline owns a process tree, not just a Go
# process. This Windows runtime test verifies Job Object cancellation kills
# a delayed descendant before an immediate retry can reuse the same root.
runs-on: windows-latest
steps:
- name: Checkout
uses: actions/checkout@v6
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: "1.26.1"
cache-dependency-path: server/go.sum
- name: Test Windows execution-environment isolation
working-directory: server
# Keep this job scoped to the runtime regression it exists to prove.
# The package's legacy OpenClaw HOME tests are not Windows-safe and are
# outside this PR; the normal backend job still runs the full package.
run: go test ./internal/daemon/execenv -run '^TestPrepareIsolated_WindowsKillsDescendantBeforeRetry$' -count=1 -timeout=5m
- name: Test Windows agent launcher argv/stdin handling
working-directory: server
# Agent prompts must never reach a Windows launcher through argv: the
# official cursor-agent.ps1 ends in `& node.exe index.js $args`, and
# PowerShell re-serialises $args onto the child command line. Under
# Legacy native argument passing (powershell.exe 5.1, pwsh <= 7.2) a
# prompt holding embedded quotes is re-tokenised and fragments like
# `-X` become flags (#5649). Only a real PowerShell host proves this,
# so it cannot live in the ubuntu backend job. Scoped to the launcher
# tests, which are windows-tagged and therefore run nowhere else today;
# the backend job still runs the full package on Linux.
# -v so a silent skip (no PowerShell host resolved, or a -run pattern
# that stops matching) is visible in the log instead of passing as "ok".
run: go test ./pkg/agent -v -run '^(TestCursorExecutePromptSurvivesPowerShellShim|TestPlatformCursorInvocation|TestPlatformCopilotInvocation|TestPlatformPiInvocation)' -count=1 -timeout=5m
- name: Test bounded Codex cleanup with inherited stdout descendant
working-directory: server
# Windows cannot prove whole-tree termination without a Job Object,
# but a descendant holding inherited stdout must never keep Result
# blocked forever. -v makes RUN/PASS evidence explicit in CI logs.
run: go test ./pkg/agent -v -run '^TestCodexWindowsInheritedStdoutDescendantCleanupIsBounded$' -count=1 -timeout=5m
- name: Build Windows CLI helper entrypoint
working-directory: server
run: go build ./cmd/multica
installer:
# Stub-driven shell tests for scripts/install.sh. Kept off the heavy
# backend job so installer regressions surface independently, and
# exercised on macOS too because the installer targets macOS/Homebrew
# and `tar` / `sed` / `mktemp` differ between BSD and GNU userlands.
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest]
runs-on: ${{ matrix.os }}
steps:
- name: Checkout
uses: actions/checkout@v6
- name: Test shell installers
run: bash scripts/install.test.sh