Files
sim/.github/workflows/ci.yml
T
Waleed 2f9144ebe3 improvement(ci): timeouts, docs-only PR skip, fork-isolated caches, Node pin; remove i18n workflow (#5714)
* improvement(ci): job timeouts everywhere, docs-only PR skip, event-scoped sticky disks, Node pin; drop dead i18n workflow

- timeout-minutes on every runnable job (defaults ran hung jobs to the
  6-hour cap — the i18n workflow burned three full 6-hour runs in Feb
  before its schedule was pulled)
- paths-ignore on the pull_request trigger: docs content and markdown
  don't affect the app build or images; push runs stay unfiltered
- sticky-disk keys scoped by event name so fork PR runs never share a
  disk with the push runs that feed production image builds
- node-version pinned to 22 (was 'latest', non-deterministic)
- delete i18n.yml: schedule already removed after repeated 6-hour hangs,
  workflow_dispatch-only since, comments stale

* improvement(ci): 45m migrate timeout (covers 30m lock wait), fork-namespaced PR sticky disks

- migrate.ts waits up to 30 minutes for the migration advisory lock
  (LOCK_ACQUIRE_DEADLINE_MS); the 15m job timeout would preempt that
  designed wait, so the bound is 45m
- fork PRs now get their own sticky-disk namespace so an untrusted fork
  run can't poison the disks that trusted internal-PR runs restore
2026-07-16 13:35:51 -07:00

533 lines
21 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
name: CI
on:
push:
branches: [main, staging, dev]
pull_request:
branches: [main, staging, dev]
# Docs content and markdown don't affect the app build or images; push
# runs stay unfiltered because they feed the deploy pipeline.
paths-ignore:
- 'apps/docs/content/**'
- '**/*.md'
concurrency:
group: ci-${{ github.ref }}
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
permissions:
contents: read
jobs:
test-build:
name: Test and Build
if: github.ref != 'refs/heads/dev' || github.event_name == 'pull_request'
uses: ./.github/workflows/test-build.yml
secrets: inherit
# Detect if this is a version release commit (e.g., "v0.5.24: ...")
detect-version:
name: Detect Version
runs-on: blacksmith-4vcpu-ubuntu-2404
timeout-minutes: 5
if: github.event_name == 'push' && (github.ref == 'refs/heads/main' || github.ref == 'refs/heads/staging' || github.ref == 'refs/heads/dev')
outputs:
version: ${{ steps.extract.outputs.version }}
is_release: ${{ steps.extract.outputs.is_release }}
steps:
- name: Extract version from commit message
id: extract
env:
COMMIT_MSG: ${{ github.event.head_commit.message }}
run: |
# Only tag versions on main branch
if [ "$GITHUB_REF" = "refs/heads/main" ] && [[ "$COMMIT_MSG" =~ ^(v[0-9]+\.[0-9]+\.[0-9]+): ]]; then
VERSION="${BASH_REMATCH[1]}"
echo "version=${VERSION}" >> $GITHUB_OUTPUT
echo "is_release=true" >> $GITHUB_OUTPUT
echo "✅ Detected release commit: ${VERSION}"
else
echo "version=" >> $GITHUB_OUTPUT
echo "is_release=false" >> $GITHUB_OUTPUT
echo "ℹ️ Not a release commit"
fi
# Run database migrations before images are promoted: the ECR latest/staging
# tag push triggers CodePipeline, so migrating first guarantees the schema is
# in place before the new app version deploys (replaces the removed ECS
# migration sidecar)
migrate:
name: Migrate DB
needs: [test-build]
if: >-
github.event_name == 'push' &&
(github.ref == 'refs/heads/main' || github.ref == 'refs/heads/staging')
uses: ./.github/workflows/migrations.yml
with:
environment: ${{ github.ref == 'refs/heads/main' && 'production' || 'staging' }}
secrets: inherit
# Same ordering for dev (schema push before the dev image lands in ECR)
migrate-dev:
name: Migrate Dev DB
if: github.event_name == 'push' && github.ref == 'refs/heads/dev'
uses: ./.github/workflows/migrations.yml
with:
environment: dev
secrets: inherit
# Dev: build all 3 images for ECR only (no GHCR, no ARM64)
build-dev:
name: Build Dev ECR
needs: [detect-version, migrate-dev]
if: github.event_name == 'push' && github.ref == 'refs/heads/dev'
runs-on: blacksmith-8vcpu-ubuntu-2404
timeout-minutes: 30
permissions:
contents: read
id-token: write
strategy:
fail-fast: false
matrix:
include:
- dockerfile: ./docker/app.Dockerfile
ecr_repo_secret: ECR_APP
- dockerfile: ./docker/db.Dockerfile
ecr_repo_secret: ECR_MIGRATIONS
- dockerfile: ./docker/realtime.Dockerfile
ecr_repo_secret: ECR_REALTIME
- dockerfile: ./docker/pii.Dockerfile
ecr_repo_secret: ECR_PII
steps:
- name: Checkout code
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@e7f100cf4c008499ea8adda475de1042d6975c7b # v6
with:
role-to-assume: ${{ secrets.DEV_AWS_ROLE_TO_ASSUME }}
aws-region: ${{ secrets.DEV_AWS_REGION }}
- name: Login to Amazon ECR
id: login-ecr
uses: aws-actions/amazon-ecr-login@d539f0932e70871a027e9d5a9d8fc38589180a64 # v2
- name: Login to Docker Hub
uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Set up Docker Buildx
uses: useblacksmith/setup-docker-builder@ab5c1da94f53f5cd75c1038092aa276dddfccbba # v1
- name: Resolve ECR repo name
id: ecr-repo
run: echo "name=$ECR_REPO" >> $GITHUB_OUTPUT
env:
ECR_REPO: ${{ matrix.ecr_repo_secret == 'ECR_APP' && secrets.ECR_APP || matrix.ecr_repo_secret == 'ECR_MIGRATIONS' && secrets.ECR_MIGRATIONS || matrix.ecr_repo_secret == 'ECR_REALTIME' && secrets.ECR_REALTIME || matrix.ecr_repo_secret == 'ECR_PII' && secrets.ECR_PII || '' }}
- name: Build and push
uses: useblacksmith/build-push-action@fb9e3e6a9299c78462bfadd0d93352c316adc9b8 # v2
with:
context: .
file: ${{ matrix.dockerfile }}
platforms: linux/amd64
push: true
tags: ${{ steps.login-ecr.outputs.registry }}/${{ steps.ecr-repo.outputs.name }}:dev
provenance: false
sbom: false
# Dev: deploy Trigger.dev background tasks to the preview "dev-sim" branch.
# Gated after migrate-dev for the same reason as build-dev — the new task
# code runs against the dev DB, so the schema must be pushed first.
deploy-trigger-dev:
name: Deploy Trigger.dev (Dev)
needs: [migrate-dev]
if: github.event_name == 'push' && github.ref == 'refs/heads/dev'
runs-on: blacksmith-4vcpu-ubuntu-2404
timeout-minutes: 15
steps:
- name: Checkout code
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6
- name: Setup Bun
uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
with:
bun-version: 1.3.13
- name: Cache Bun dependencies
uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5
with:
path: |
~/.bun/install/cache
node_modules
**/node_modules
key: ${{ runner.os }}-bun-${{ hashFiles('**/bun.lock') }}
restore-keys: |
${{ runner.os }}-bun-
- name: Install dependencies
run: bun install --frozen-lockfile
- name: Deploy to Trigger.dev
working-directory: ./apps/sim
env:
TRIGGER_ACCESS_TOKEN: ${{ secrets.DEV_TRIGGER_ACCESS_TOKEN }}
TRIGGER_PROJECT_ID: ${{ secrets.TRIGGER_PROJECT_ID }}
run: |
if [ -z "$TRIGGER_ACCESS_TOKEN" ] || [ -z "$TRIGGER_PROJECT_ID" ]; then
echo "ERROR: DEV_TRIGGER_ACCESS_TOKEN and TRIGGER_PROJECT_ID repo secrets must both be set" >&2
exit 1
fi
bunx trigger.dev@4.4.3 deploy --env preview --branch dev-sim
# Main/staging: build AMD64 images and push sha-tagged images to ECR + GHCR.
# Runs in parallel with tests — only immutable sha tags are pushed here, and
# the CodePipeline EventBridge triggers filter on exactly the
# latest/staging/dev ECR tags, so nothing deploys and no mutable tag moves
# until promote-images / create-ghcr-manifests retag after the gate.
build-amd64:
name: Build AMD64
if: >-
github.event_name == 'push' &&
(github.ref == 'refs/heads/main' || github.ref == 'refs/heads/staging')
runs-on: blacksmith-8vcpu-ubuntu-2404
timeout-minutes: 30
permissions:
contents: read
packages: write
id-token: write
strategy:
fail-fast: false
matrix:
include:
- dockerfile: ./docker/app.Dockerfile
ghcr_image: ghcr.io/simstudioai/simstudio
ecr_repo_secret: ECR_APP
- dockerfile: ./docker/db.Dockerfile
ghcr_image: ghcr.io/simstudioai/migrations
ecr_repo_secret: ECR_MIGRATIONS
- dockerfile: ./docker/realtime.Dockerfile
ghcr_image: ghcr.io/simstudioai/realtime
ecr_repo_secret: ECR_REALTIME
- dockerfile: ./docker/pii.Dockerfile
ghcr_image: ghcr.io/simstudioai/pii
ecr_repo_secret: ECR_PII
steps:
- name: Checkout code
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@e7f100cf4c008499ea8adda475de1042d6975c7b # v6
with:
role-to-assume: ${{ github.ref == 'refs/heads/main' && secrets.AWS_ROLE_TO_ASSUME || secrets.STAGING_AWS_ROLE_TO_ASSUME }}
aws-region: ${{ github.ref == 'refs/heads/main' && secrets.AWS_REGION || secrets.STAGING_AWS_REGION }}
- name: Login to Amazon ECR
id: login-ecr
uses: aws-actions/amazon-ecr-login@d539f0932e70871a027e9d5a9d8fc38589180a64 # v2
- name: Login to Docker Hub
uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Login to GHCR
if: github.ref == 'refs/heads/main'
uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Set up Docker Buildx
uses: useblacksmith/setup-docker-builder@ab5c1da94f53f5cd75c1038092aa276dddfccbba # v1
- name: Resolve ECR repo name
id: ecr-repo
run: echo "name=$ECR_REPO" >> $GITHUB_OUTPUT
env:
ECR_REPO: ${{ matrix.ecr_repo_secret == 'ECR_APP' && secrets.ECR_APP || matrix.ecr_repo_secret == 'ECR_MIGRATIONS' && secrets.ECR_MIGRATIONS || matrix.ecr_repo_secret == 'ECR_REALTIME' && secrets.ECR_REALTIME || matrix.ecr_repo_secret == 'ECR_PII' && secrets.ECR_PII || '' }}
# Only sha tags here — the ECR deploy tags (latest/staging) are applied
# by promote-images and the GHCR latest-amd64/version tags by
# create-ghcr-manifests, both after tests and migrations pass.
- name: Generate tags
id: meta
run: |
ECR_REGISTRY="${{ steps.login-ecr.outputs.registry }}"
ECR_REPO="${{ steps.ecr-repo.outputs.name }}"
GHCR_IMAGE="${{ matrix.ghcr_image }}"
TAGS="${ECR_REGISTRY}/${ECR_REPO}:${{ github.sha }}"
if [ "${{ github.ref }}" = "refs/heads/main" ] && [ -n "$GHCR_IMAGE" ]; then
TAGS="${TAGS},${GHCR_IMAGE}:${{ github.sha }}-amd64"
fi
echo "tags=${TAGS}" >> $GITHUB_OUTPUT
- name: Build and push images
uses: useblacksmith/build-push-action@fb9e3e6a9299c78462bfadd0d93352c316adc9b8 # v2
with:
context: .
file: ${{ matrix.dockerfile }}
platforms: linux/amd64
push: true
tags: ${{ steps.meta.outputs.tags }}
provenance: false
sbom: false
# Promote the sha-tagged ECR images to the deploy tags once tests and
# migrations pass. Pushing the ECR latest/staging tag is what triggers
# CodePipeline, so this seconds-long manifest retag is the deploy gate —
# the image builds themselves run in parallel with the tests. A single job
# (not a matrix) so all four sha manifests are verified before any tag
# moves; a missing image can't produce a partial mixed-version deploy.
promote-images:
name: Promote Images
needs: [migrate, build-amd64]
if: >-
github.event_name == 'push' &&
(github.ref == 'refs/heads/main' || github.ref == 'refs/heads/staging')
runs-on: blacksmith-2vcpu-ubuntu-2404
timeout-minutes: 10
permissions:
contents: read
id-token: write
steps:
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@e7f100cf4c008499ea8adda475de1042d6975c7b # v6
with:
role-to-assume: ${{ github.ref == 'refs/heads/main' && secrets.AWS_ROLE_TO_ASSUME || secrets.STAGING_AWS_ROLE_TO_ASSUME }}
aws-region: ${{ github.ref == 'refs/heads/main' && secrets.AWS_REGION || secrets.STAGING_AWS_REGION }}
- name: Login to Amazon ECR
id: login-ecr
uses: aws-actions/amazon-ecr-login@d539f0932e70871a027e9d5a9d8fc38589180a64 # v2
# Deploy-tag moves must be monotonic: a re-run of an old run must never
# retag latest/staging back to stale code. A superseded first-attempt
# run still promotes — the ci-<ref> concurrency group executes runs
# serially in commit order, so an ancestor of head is a forward deploy.
- name: Guard against stale promotion
id: guard
env:
GH_TOKEN: ${{ github.token }}
run: |
STATUS="$(gh api "repos/${{ github.repository }}/compare/${{ github.sha }}...${GITHUB_REF_NAME}" --jq '.status' || echo "unknown")"
if [ "$STATUS" = "identical" ] || { [ "$STATUS" = "ahead" ] && [ "${{ github.run_attempt }}" = "1" ]; }; then
echo "fresh=true" >> $GITHUB_OUTPUT
else
echo "::warning::Skipping promotion of ${{ github.sha }} (branch compare: ${STATUS}, attempt ${{ github.run_attempt }}). Moving the deploy tags here could deploy stale code; push a revert commit to roll back instead."
echo "fresh=false" >> $GITHUB_OUTPUT
fi
- name: Promote images to deploy tags
if: steps.guard.outputs.fresh == 'true'
env:
ECR_REPOS: >-
${{ secrets.ECR_APP }}
${{ secrets.ECR_MIGRATIONS }}
${{ secrets.ECR_REALTIME }}
${{ secrets.ECR_PII }}
run: |
REGISTRY="${{ steps.login-ecr.outputs.registry }}"
if [ "${{ github.ref }}" = "refs/heads/main" ]; then
ECR_TAG="latest"
else
ECR_TAG="staging"
fi
# Verify every sha image exists before moving any deploy tag, so a
# missing/expired image aborts the whole promotion up front.
for repo in $ECR_REPOS; do
echo "🔍 Verifying ${repo}:${{ github.sha }}"
docker buildx imagetools inspect "${REGISTRY}/${repo}:${{ github.sha }}" > /dev/null
done
for repo in $ECR_REPOS; do
echo "🚀 Promoting ${repo}:${{ github.sha }} to ${ECR_TAG}"
docker buildx imagetools create \
-t "${REGISTRY}/${repo}:${ECR_TAG}" \
"${REGISTRY}/${repo}:${{ github.sha }}"
done
# Build ARM64 images for GHCR (main branch only, runs in parallel with
# tests). Pushes only the immutable sha tag — latest-arm64/version-arm64
# are applied by create-ghcr-manifests after the gate, so a failing run
# never moves a documented tag.
build-ghcr-arm64:
name: Build ARM64 (GHCR Only)
runs-on: blacksmith-8vcpu-ubuntu-2404-arm
timeout-minutes: 30
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
permissions:
contents: read
packages: write
strategy:
fail-fast: false
matrix:
include:
- dockerfile: ./docker/app.Dockerfile
image: ghcr.io/simstudioai/simstudio
- dockerfile: ./docker/db.Dockerfile
image: ghcr.io/simstudioai/migrations
- dockerfile: ./docker/realtime.Dockerfile
image: ghcr.io/simstudioai/realtime
- dockerfile: ./docker/pii.Dockerfile
image: ghcr.io/simstudioai/pii
steps:
- name: Checkout code
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6
- name: Login to GHCR
uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Set up Docker Buildx
uses: useblacksmith/setup-docker-builder@ab5c1da94f53f5cd75c1038092aa276dddfccbba # v1
- name: Build and push ARM64 to GHCR
uses: useblacksmith/build-push-action@fb9e3e6a9299c78462bfadd0d93352c316adc9b8 # v2
with:
context: .
file: ${{ matrix.dockerfile }}
platforms: linux/arm64
push: true
tags: ${{ matrix.image }}:${{ github.sha }}-arm64
provenance: false
sbom: false
# Publish all mutable GHCR tags (latest, latest-amd64/arm64, version tags)
# and the multi-arch manifests from the immutable sha tags — only on main,
# after the deploy gate (promote-images) and the ARM64 build both pass.
create-ghcr-manifests:
name: Create GHCR Manifests
runs-on: blacksmith-2vcpu-ubuntu-2404
timeout-minutes: 10
needs: [promote-images, build-ghcr-arm64, detect-version]
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
permissions:
contents: read
packages: write
strategy:
matrix:
include:
- image: ghcr.io/simstudioai/simstudio
- image: ghcr.io/simstudioai/migrations
- image: ghcr.io/simstudioai/realtime
- image: ghcr.io/simstudioai/pii
steps:
- name: Login to GHCR
uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
# Same monotonic guard as promote-images, applied to the public latest
# tags only — immutable sha and version tags are always published.
- name: Guard against stale latest tags
id: guard
env:
GH_TOKEN: ${{ github.token }}
run: |
STATUS="$(gh api "repos/${{ github.repository }}/compare/${{ github.sha }}...${GITHUB_REF_NAME}" --jq '.status' || echo "unknown")"
if [ "$STATUS" = "identical" ] || { [ "$STATUS" = "ahead" ] && [ "${{ github.run_attempt }}" = "1" ]; }; then
echo "fresh=true" >> $GITHUB_OUTPUT
else
echo "::warning::Publishing immutable tags for ${{ github.sha }} but skipping the latest tags (branch compare: ${STATUS}, attempt ${{ github.run_attempt }})."
echo "fresh=false" >> $GITHUB_OUTPUT
fi
- name: Publish tags and manifests
run: |
IMAGE="${{ matrix.image }}"
SHA="${{ github.sha }}"
# Multi-arch manifest from the immutable per-arch sha tags
docker buildx imagetools create -t "${IMAGE}:${SHA}" \
"${IMAGE}:${SHA}-amd64" "${IMAGE}:${SHA}-arm64"
if [ "${{ needs.detect-version.outputs.is_release }}" = "true" ]; then
VERSION="${{ needs.detect-version.outputs.version }}"
echo "📦 Publishing version tags: ${VERSION}"
docker buildx imagetools create -t "${IMAGE}:${VERSION}-amd64" "${IMAGE}:${SHA}-amd64"
docker buildx imagetools create -t "${IMAGE}:${VERSION}-arm64" "${IMAGE}:${SHA}-arm64"
docker buildx imagetools create -t "${IMAGE}:${VERSION}" \
"${IMAGE}:${SHA}-amd64" "${IMAGE}:${SHA}-arm64"
fi
if [ "${{ steps.guard.outputs.fresh }}" = "true" ]; then
docker buildx imagetools create -t "${IMAGE}:latest-amd64" "${IMAGE}:${SHA}-amd64"
docker buildx imagetools create -t "${IMAGE}:latest-arm64" "${IMAGE}:${SHA}-arm64"
docker buildx imagetools create -t "${IMAGE}:latest" \
"${IMAGE}:${SHA}-amd64" "${IMAGE}:${SHA}-arm64"
fi
# Check if docs changed
check-docs-changes:
name: Check Docs Changes
runs-on: blacksmith-4vcpu-ubuntu-2404
timeout-minutes: 5
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
outputs:
docs_changed: ${{ steps.filter.outputs.docs }}
steps:
- uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6
with:
fetch-depth: 2 # Need at least 2 commits to detect changes
- uses: dorny/paths-filter@fbd0ab8f3e69293af611ebaee6363fc25e6d187d # v4
id: filter
with:
filters: |
docs:
- 'apps/docs/content/docs/en/**'
- 'apps/sim/scripts/process-docs.ts'
- 'apps/sim/lib/chunkers/**'
# Process docs embeddings (only when docs change, after images are promoted)
process-docs:
name: Process Docs
needs: [promote-images, check-docs-changes]
if: needs.check-docs-changes.outputs.docs_changed == 'true'
uses: ./.github/workflows/docs-embeddings.yml
secrets: inherit
# Create GitHub Release (only for version commits on main, after all builds complete)
create-release:
name: Create GitHub Release
runs-on: blacksmith-4vcpu-ubuntu-2404
timeout-minutes: 10
needs: [create-ghcr-manifests, detect-version]
if: needs.detect-version.outputs.is_release == 'true'
permissions:
contents: write
steps:
- name: Checkout code
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6
with:
fetch-depth: 0
- name: Setup Bun
uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
with:
bun-version: 1.3.13
- name: Install dependencies
run: bun install --frozen-lockfile
- name: Create release
env:
GH_PAT: ${{ secrets.GITHUB_TOKEN }}
run: bun run scripts/create-single-release.ts ${{ needs.detect-version.outputs.version }}