forked from molecule-ai/molecule-core
fix(ci): remove Fly registry from publish pipeline, push tenant to GHCR
Fly.io was deleted — EC2 tenant instances now pull from GHCR. - Remove Fly registry push step (401 Unauthorized since Fly deleted) - Remove flyctl deploy step - Push tenant image to ghcr.io/molecule-ai/platform-tenant instead - Simplify GHCR auth config (remove Fly token) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Hongming Wang
parent
286a845239
commit
440e09b360
114
.github/workflows/publish-platform-image.yml
vendored
114
.github/workflows/publish-platform-image.yml
vendored
@ -1,39 +1,25 @@
|
||||
name: publish-platform-image
|
||||
|
||||
# Builds and pushes the tenant-platform Docker image to GHCR whenever a
|
||||
# commit lands on main. The private molecule-controlplane provisioner sets
|
||||
# TENANT_IMAGE=ghcr.io/molecule-ai/platform:<tag> to spawn tenant Fly
|
||||
# Machines from this image. See molecule-controlplane README for the pairing.
|
||||
# Builds and pushes the platform Docker images to GHCR whenever a commit
|
||||
# lands on main. EC2 tenant instances pull the tenant image from GHCR.
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
paths:
|
||||
# Only rebuild when something platform-relevant changes — saves GHA
|
||||
# minutes on docs-only / canvas-only / MCP-only PRs.
|
||||
- 'platform/**'
|
||||
- 'canvas/**'
|
||||
- 'manifest.json'
|
||||
- '.github/workflows/publish-platform-image.yml'
|
||||
# Templates now live in standalone repos — template changes no longer
|
||||
# trigger a platform rebuild. Use workflow_dispatch to manually rebuild
|
||||
# if a template repo update needs to be baked into the image.
|
||||
# Manual trigger for re-publishing a tag after a non-platform merge.
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
packages: write # required to push to ghcr.io/${{ github.repository_owner }}/*
|
||||
packages: write
|
||||
|
||||
env:
|
||||
# GHCR accepts mixed-case, but most tooling lowercases — keep us consistent.
|
||||
IMAGE_NAME: ghcr.io/molecule-ai/platform
|
||||
# Fly registry mirror — tenant machines provisioned by the private
|
||||
# `molecule-controlplane` pull from here (private GHCR image can't be
|
||||
# pulled by Fly machines without auth plumbing we don't want to add).
|
||||
# Fly auto-authenticates same-org machines against registry.fly.io, so
|
||||
# mirroring keeps GHCR private while tenants still boot.
|
||||
FLY_IMAGE_NAME: registry.fly.io/molecule-tenant
|
||||
TENANT_IMAGE_NAME: ghcr.io/molecule-ai/platform-tenant
|
||||
|
||||
jobs:
|
||||
build-and-push:
|
||||
@ -42,83 +28,33 @@ jobs:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Configure registry auth (write auths map; do NOT call docker login)
|
||||
# `docker login` on macOS unconditionally writes credentials to the
|
||||
# osxkeychain credential helper, even when DOCKER_CONFIG/config.json
|
||||
# declares `credsStore: ""` and even when invoked with `--config`.
|
||||
# Verified locally 2026-04-16 — after a successful login, Docker
|
||||
# rewrites the same config file to:
|
||||
# { "auths": { "ghcr.io": {} }, "credsStore": "osxkeychain" }
|
||||
# i.e. the auth lives in the Keychain, not the config file. The
|
||||
# Mac mini runner is a launchd user agent with a locked Keychain,
|
||||
# so storage fails with `User interaction is not allowed (-25308)`.
|
||||
#
|
||||
# Six prior PRs (#273, #319, #322, #341, #484, #486) all kept calling
|
||||
# `docker login` and tried to coerce credsStore — none worked.
|
||||
# The only reliable fix is to skip `docker login` entirely and write
|
||||
# the auth strings directly. `docker/build-push-action@v5` and the
|
||||
# daemon honor the `auths` map for push without needing login.
|
||||
#
|
||||
# Fly registry username MUST be literal "x" (verified 2026-04-15) —
|
||||
# any other value returns 401. FLY_API_TOKEN lives in GitHub Actions
|
||||
# secrets AND in `fly secrets` on molecule-cp; see
|
||||
# docs/runbooks/saas-secrets.md before rotating.
|
||||
- name: Configure GHCR auth
|
||||
shell: bash
|
||||
env:
|
||||
GHCR_USER: ${{ github.actor }}
|
||||
GHCR_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
FLY_TOKEN: ${{ secrets.FLY_API_TOKEN }}
|
||||
run: |
|
||||
set -eu
|
||||
mkdir -p "${RUNNER_TEMP}/docker-config"
|
||||
GHCR_AUTH=$(printf '%s:%s' "${GHCR_USER}" "${GHCR_TOKEN}" | base64)
|
||||
FLY_AUTH=$(printf '%s:%s' 'x' "${FLY_TOKEN}" | base64)
|
||||
umask 077
|
||||
cat > "${RUNNER_TEMP}/docker-config/config.json" <<JSON
|
||||
{
|
||||
"auths": {
|
||||
"ghcr.io": { "auth": "${GHCR_AUTH}" },
|
||||
"registry.fly.io": { "auth": "${FLY_AUTH}" }
|
||||
}
|
||||
}
|
||||
JSON
|
||||
printf '{"auths":{"ghcr.io":{"auth":"%s"}}}' "${GHCR_AUTH}" > "${RUNNER_TEMP}/docker-config/config.json"
|
||||
echo "DOCKER_CONFIG=${RUNNER_TEMP}/docker-config" >> "${GITHUB_ENV}"
|
||||
# Diagnostics that don't leak the tokens.
|
||||
echo "=== docker ==="
|
||||
command -v docker || echo "(docker not in PATH)"
|
||||
docker --version 2>&1 || true
|
||||
ls -la /usr/local/bin/docker /opt/homebrew/bin/docker 2>&1 || true
|
||||
echo "=== auths registries (no values) ==="
|
||||
grep -o '"[a-zA-Z0-9.-]*\.io"' "${RUNNER_TEMP}/docker-config/config.json" || true
|
||||
|
||||
- name: Set up QEMU
|
||||
# Required on the Apple-silicon self-hosted runner — Fly tenant machines
|
||||
# pull linux/amd64, and buildx needs binfmt handlers in Docker Desktop's
|
||||
# VM to emulate amd64 during the build.
|
||||
uses: docker/setup-qemu-action@v3
|
||||
with:
|
||||
platforms: linux/amd64
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
# Buildx enables cache-from/cache-to via GHA cache and multi-arch
|
||||
# builds without local docker daemon wrangling.
|
||||
uses: docker/setup-buildx-action@v3
|
||||
|
||||
- name: Compute tags
|
||||
id: tags
|
||||
# Emit two tags per build: `latest` (floating, always the main tip)
|
||||
# and the short commit SHA (immutable, pin-friendly). Control plane
|
||||
# can deploy `latest` today and pin to :sha in Phase H hardening.
|
||||
run: |
|
||||
echo "sha=${GITHUB_SHA::7}" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Build & push to GHCR
|
||||
# Split from the Fly mirror so a registry.fly.io outage doesn't block
|
||||
# GHCR (or vice versa) — each registry's failure mode is isolated.
|
||||
# GHA cache is shared because both steps re-use the same Dockerfile
|
||||
# context + build args.
|
||||
# Explicit linux/amd64 target: the runner is Apple-silicon (arm64),
|
||||
# but Fly tenant machines are amd64. QEMU handles the emulation.
|
||||
- name: Build & push platform image to GHCR
|
||||
uses: docker/build-push-action@v5
|
||||
with:
|
||||
context: .
|
||||
@ -133,13 +69,9 @@ jobs:
|
||||
labels: |
|
||||
org.opencontainers.image.source=https://github.com/${{ github.repository }}
|
||||
org.opencontainers.image.revision=${{ github.sha }}
|
||||
org.opencontainers.image.description=Molecule AI tenant platform (one instance per org)
|
||||
org.opencontainers.image.description=Molecule AI platform (Go API server)
|
||||
|
||||
- name: Build & push tenant image to Fly registry
|
||||
# Tenant image = Go platform + Canvas (Next.js) in one container.
|
||||
# Uses Dockerfile.tenant which includes the canvas build + reverse proxy.
|
||||
# Continues even if GHCR push failed.
|
||||
if: always()
|
||||
- name: Build & push tenant image to GHCR
|
||||
uses: docker/build-push-action@v5
|
||||
with:
|
||||
context: .
|
||||
@ -147,31 +79,11 @@ jobs:
|
||||
platforms: linux/amd64
|
||||
push: true
|
||||
tags: |
|
||||
${{ env.FLY_IMAGE_NAME }}:latest
|
||||
${{ env.FLY_IMAGE_NAME }}:sha-${{ steps.tags.outputs.sha }}
|
||||
${{ env.TENANT_IMAGE_NAME }}:latest
|
||||
${{ env.TENANT_IMAGE_NAME }}:sha-${{ steps.tags.outputs.sha }}
|
||||
cache-from: type=gha
|
||||
cache-to: type=gha,mode=max
|
||||
labels: |
|
||||
org.opencontainers.image.source=https://github.com/${{ github.repository }}
|
||||
org.opencontainers.image.revision=${{ github.sha }}
|
||||
org.opencontainers.image.description=Molecule AI tenant platform + canvas (one instance per org)
|
||||
|
||||
- name: Install flyctl
|
||||
uses: superfly/flyctl-actions/setup-flyctl@master
|
||||
|
||||
- name: Deploy to Fly tenant machines
|
||||
env:
|
||||
FLY_API_TOKEN: ${{ secrets.FLY_API_TOKEN }}
|
||||
run: |
|
||||
MACHINES=$(flyctl machines list -a molecule-tenant --json | jq -r '.[] | select(.state == "started" or .state == "stopped") | .id')
|
||||
if [ -z "$MACHINES" ]; then
|
||||
echo "No tenant machines found — skipping deploy (control plane provisions on demand)"
|
||||
exit 0
|
||||
fi
|
||||
for id in $MACHINES; do
|
||||
echo "Updating machine $id to sha-${{ steps.tags.outputs.sha }}..."
|
||||
flyctl machines update "$id" \
|
||||
--image "${{ env.FLY_IMAGE_NAME }}:sha-${{ steps.tags.outputs.sha }}" \
|
||||
-a molecule-tenant \
|
||||
--yes
|
||||
done
|
||||
echo "All tenant machines updated to sha-${{ steps.tags.outputs.sha }}"
|
||||
org.opencontainers.image.description=Molecule AI tenant platform + canvas (one EC2 instance per org)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user