orca/.github/workflows/adhoc-mac-build.yml

419 lines
21 KiB
YAML

name: Adhoc macOS Dev Build
# Why: lets anyone cut a signed macOS build of an unlanded branch so the team can
# actually run an experimental feature for a few days, instead of reasoning about
# it from a diff. Hourly covers main; this covers everything that is not main yet.
#
# Deliberately narrow scope, same trade as hourly:
# - macOS only. Other platforms keep using RC/stable.
# - No tests, no lint, no e2e. PR CI and release-cut remain the gates.
# - Signed AND notarized, exactly like a release. macOS anchors a notarized
# app's TCC grants on identifier + team rather than on its cdhash, so those
# grants survive an update; an unnotarized build reads as a new client and
# silently loses file access under Documents/Desktop/Downloads.
#
# Artifacts publish to stablyai/orca-adhoc — separate from both orca and
# orca-hourly. Separate from orca because the main repo's releases atom feed
# exposes only its 10 newest entries. Separate from orca-hourly because a build
# from someone's branch must never be picked up by a developer who only meant to
# ride main; the two are different levels of "unvetted".
#
# From the Actions tab: pick this workflow, "Run workflow", leave "Use workflow
# from" on main, and type your branch in the first field. Or from the CLI:
#
# gh workflow run adhoc-mac-build.yml --ref main -f ref=my-branch -f label=wasm-terminal
#
# Leaving the ref field empty builds whatever "Use workflow from" is set to, which
# is what someone who only touched that picker means. Naming the branch explicitly
# is still better: the workflow file is always read from the dispatch ref, so a
# branch carrying a stale copy of this file would otherwise run that copy.
#
# GITHUB_TOKEN is scoped to this repo and cannot publish there, so writes use the
# same GitHub App as hourly, additionally installed on orca-adhoc with
# Contents: Read and write. The secret names below are historical — one App, one
# private key, both dev-channel repos — and rotating it stays a single operation.
# Provision with `bash config/scripts/setup-hourly-release-token.sh`.
#
# The requested ref is vetted before checkout: it must be a branch or tag of this
# repo, or a commit reachable from one. PR refs are refused outright — this
# workflow runs the checked-out code next to MAC_CERTS and the notary password,
# so "just build that community PR" must not become a way to hand fork code the
# release identity. A branch here always belongs to someone with write access,
# which is the same trust the dispatch button itself already requires.
on:
workflow_dispatch:
inputs:
ref:
# Why optional: the Actions UI already shows its own "Use workflow from"
# branch picker directly above this field, and picking a branch there is
# what most people will read as "build this". Defaulting to that branch
# makes the obvious action correct. Fill this in only to build a ref other
# than the one the workflow file itself is read from — normally leave the
# picker on main and name your branch here, so a stale copy of this
# workflow on an old branch is not what runs.
description: 'Branch, tag, or SHA to build — must live in stablyai/orca; PR refs are refused (default: the branch selected above)'
required: false
default: ''
type: string
label:
description: 'Short name shown in the release title (default: the ref)'
required: false
default: ''
type: string
permissions:
contents: read
concurrency:
# Why keyed on the ref rather than global: two people cutting builds from two
# different branches at the same time is the ordinary case here, and serialising
# them would make each wait out the other's notary queue. Re-dispatching the
# *same* branch still queues, so a push mid-build cannot race itself.
group: adhoc-mac-build-${{ inputs.ref || github.ref_name }}
cancel-in-progress: false
env:
ADHOC_REPO: stablyai/orca-adhoc
# Why age and not a count like hourly: this channel is low-volume and bursty, so
# a count would either hold one week's experiments forever or evict a build
# someone is still running after a busy afternoon. A month is well past the "few
# days" these exist for, and by then the branch has landed or been abandoned.
ADHOC_RETAIN_DAYS: 30
jobs:
build-adhoc-mac:
if: github.repository == 'stablyai/orca'
# Why an environment: it gives the signing/notary/App secrets somewhere to
# live that a stale copy of this workflow on an old branch cannot reach.
# Referencing it is a no-op until repo settings give it teeth; the intended
# follow-up is to move MAC_CERTS, MAC_CERTS_PASSWORD, APPLE_ID,
# APPLE_APP_SPECIFIC_PASSWORD, APPLE_TEAM_ID, HOURLY_RELEASE_APP_ID, and
# HOURLY_RELEASE_APP_PRIVATE_KEY into it, then pin its deployment branch
# policy to main so only main's copy of this file can read them.
environment: adhoc-mac-build
runs-on: blacksmith-6vcpu-macos-15
# Why 150: it must exceed the worst case the retry budgets below can produce
# (install 3x10 + publish 2x45 = 120, plus ~25 for checkout/build/verify), or
# the job is killed mid-retry and no cleanup step runs at all.
timeout-minutes: 150
env:
NODE_OPTIONS: --max-old-space-size=4096
steps:
# Why vet before checkout: everything after this step runs the checked-out
# code with release signing credentials in reach. Branches and tags of this
# repo are the intended audience; refs/pull/* would smuggle in fork code,
# and a raw SHA is only accepted when some branch or tag of this repo can
# actually reach it. Resolving to a pinned SHA here also means the commit
# that was vetted is the commit that gets checked out — a push to the
# branch between the two steps cannot swap it.
- name: Vet the requested ref
id: vetted
shell: bash
env:
REQUESTED_REF: ${{ inputs.ref || github.ref_name }}
REPO_URL: https://github.com/${{ github.repository }}
run: |
set -euo pipefail
case "$REQUESTED_REF" in
refs/pull/*|pull/*)
echo "::error::Refusing to build PR ref '$REQUESTED_REF': this workflow signs with release credentials, so it only builds branches, tags, or commits of stablyai/orca. Push the code to a branch of this repo instead."
exit 1
;;
esac
# Bare: a work-tree repo refuses to fetch over its own checked-out
# branch. tree:0 keeps the fetch to the commit graph — no trees, no
# blobs — so this stays cheap next to the build it fronts.
scratch="$RUNNER_TEMP/vet-requested-ref"
git init -q --bare "$scratch"
git -C "$scratch" fetch -q --filter=tree:0 "$REPO_URL" '+refs/heads/*:refs/heads/*' '+refs/tags/*:refs/tags/*'
# Branch first to keep actions/checkout's old tie-break: bare
# rev-parse would prefer the tag when a branch shares its name.
sha=""
for cand in "refs/heads/$REQUESTED_REF" "refs/tags/$REQUESTED_REF" "$REQUESTED_REF"; do
if sha="$(git -C "$scratch" rev-parse --verify --quiet "$cand^{commit}")"; then
break
fi
sha=""
done
if [[ -z "$sha" ]]; then
echo "::error::'$REQUESTED_REF' does not resolve to a branch, tag, or commit of stablyai/orca."
exit 1
fi
# The object resolving locally is not proof a branch or tag reaches
# it: a partial clone can lazily fetch a bare SHA on demand, and
# GitHub serves PR-only commits by SHA. Reachability is the actual
# trust test.
if [[ -z "$(git -C "$scratch" for-each-ref --contains "$sha" refs/heads refs/tags | head -1)" ]]; then
echo "::error::Commit $REQUESTED_REF is not reachable from any branch or tag of stablyai/orca; refusing to build it with release credentials."
exit 1
fi
echo "Vetted $REQUESTED_REF -> $sha"
echo "sha=$sha" >>"$GITHUB_OUTPUT"
- name: Checkout the requested ref
uses: actions/checkout@v6
with:
# Why an input at all rather than just github.ref: the whole point is to
# build code that has not landed, and the workflow definition itself
# always comes from the dispatch ref — naming the branch here instead
# applies main's current copy of this file to an arbitrary branch.
ref: ${{ steps.vetted.outputs.sha }}
fetch-depth: 0
# This job only reads stablyai/orca and never pushes; every write goes
# to the adhoc repo through a minted App token passed by env. Not
# persisting the checkout credential shrinks the blast radius if a build
# step is compromised (zizmor: artipacked).
persist-credentials: false
- name: Setup pnpm
uses: pnpm/action-setup@v6
with:
run_install: false
- name: Setup Node.js
uses: actions/setup-node@v6
with:
node-version-file: package.json
cache: pnpm
- name: Cache electron-builder downloads
uses: actions/cache@v5
with:
path: |
~/Library/Caches/electron
~/Library/Caches/electron-builder
key: electron-builder-mac-${{ hashFiles('pnpm-lock.yaml') }}
restore-keys: |
electron-builder-mac-
- name: Install dependencies
uses: nick-fields/retry@v4
with:
timeout_minutes: 10
max_attempts: 3
retry_wait_seconds: 30
command: pnpm install --frozen-lockfile
# Why: signing is what makes an adhoc build installable over an existing
# Orca, so a missing cert must fail here rather than after a 20-minute build.
- name: Verify macOS signing environment
run: node config/scripts/verify-macos-release-env.mjs
env:
CSC_LINK: ${{ secrets.MAC_CERTS }}
CSC_KEY_PASSWORD: ${{ secrets.MAC_CERTS_PASSWORD }}
APPLE_ID: ${{ secrets.APPLE_ID }}
APPLE_APP_SPECIFIC_PASSWORD: ${{ secrets.APPLE_APP_SPECIFIC_PASSWORD }}
APPLE_TEAM_ID: ${{ secrets.APPLE_TEAM_ID }}
- name: Compute adhoc version
id: adhoc
shell: bash
env:
REF: ${{ inputs.ref || github.ref_name }}
LABEL: ${{ inputs.label }}
MAIN_REPO_TOKEN: ${{ github.token }}
run: |
set -euo pipefail
# Why this check: the version scripts are read from the branch being built,
# not from main, so a branch cut before the adhoc channel landed has no
# copy of them. Say that plainly instead of failing with a module-not-found.
for script in adhoc-build-version dev-channel-base-version; do
if [[ ! -f "config/scripts/$script.mjs" ]]; then
echo "::error::$REF has no config/scripts/$script.mjs; rebase it onto a main that has the adhoc channel."
exit 1
fi
done
echo "head_sha=$(git rev-parse HEAD)" >>"$GITHUB_OUTPUT"
# Why the main repo's tags: package.json on a branch is as stale as the
# main it forked from, and stable patches never merge back into it.
published="$(GH_TOKEN="$MAIN_REPO_TOKEN" gh release list \
--repo "$GITHUB_REPOSITORY" --limit 100 --exclude-drafts \
--json tagName --jq '.[].tagName' || true)"
ORCA_PUBLISHED_VERSIONS="$published" ORCA_ADHOC_LABEL="${LABEL:-$REF}" \
node config/scripts/adhoc-build-version.mjs \
>"$RUNNER_TEMP/adhoc-identity.txt"
if ! grep -q '^name=' "$RUNNER_TEMP/adhoc-identity.txt"; then
echo "::error::adhoc-build-version.mjs emitted no release name; $REF's copy of the script is out of sync with this workflow."
exit 1
fi
cat "$RUNNER_TEMP/adhoc-identity.txt" >>"$GITHUB_OUTPUT"
- name: Build app
run: pnpm build:release
env:
NODE_OPTIONS: --max-old-space-size=4096
# Why: adhoc builds are not an official channel — telemetry's transport
# gate accepts only 'stable' or 'rc', so leaving this unset keeps them
# silent, which is correct for unvetted branch artifacts.
ORCA_DIAGNOSTICS_TOKEN_URL: https://www.onorca.dev/diagnostics/token
# Why the token is minted here and not at the top: installation tokens live
# one hour, everything before this point writes nothing, and the notary round
# trip inside the publish step can be tens of minutes. Minting after the build
# starts the clock at the first call that actually uses it.
- name: Mint adhoc repo token
id: app_token
uses: actions/create-github-app-token@v2
with:
app-id: ${{ secrets.HOURLY_RELEASE_APP_ID }}
private-key: ${{ secrets.HOURLY_RELEASE_APP_PRIVATE_KEY }}
owner: stablyai
repositories: orca-adhoc
- name: Create adhoc release
id: release
shell: bash
env:
GH_TOKEN: ${{ steps.app_token.outputs.token }}
TAG: v${{ steps.adhoc.outputs.version }}
NAME: ${{ steps.adhoc.outputs.name }}
SHA: ${{ steps.adhoc.outputs.head_sha }}
REF: ${{ inputs.ref || github.ref_name }}
# Via env, not inline `${{ }}`: both land inside a shell string, and an
# expression expanded there is substituted before bash parses the line
# (zizmor: template-injection).
ACTOR: ${{ github.actor }}
run: |
set -euo pipefail
short_sha="${SHA:0:12}"
# Why create it up front: electron-builder then uploads into a known tag
# rather than inferring one from package.json.
#
# Why --draft: everything between here and the manifest check is a window
# where the release exists but has no installable assets. A draft is
# absent from the releases list and from listReleaseBuilds, so a job that
# dies in that window — including a hard kill by the job timeout, which
# runs no cleanup step at all — leaves something invisible rather than a
# tag the picker offers and the download 404s on.
gh release create "$TAG" \
--repo "$ADHOC_REPO" \
--title "$NAME" \
--draft \
--notes "Adhoc macOS dev build of \`$REF\` at commit \`$short_sha\`.
Built from [\`stablyai/orca@$short_sha\`](https://github.com/stablyai/orca/commit/$SHA), cut by @$ACTOR.
**Unlanded and unvetted.** This is somebody's branch, not main. No tests
ran. Signed and notarized like a release, so it installs through Orca's
in-app updater and opens without a Gatekeeper prompt — but the branch may
never merge, and this build is deleted after $ADHOC_RETAIN_DAYS days."
echo "tag=$TAG" >>"$GITHUB_OUTPUT"
- name: Publish adhoc macOS artifacts
uses: nick-fields/retry@v4
with:
# Why 45: an attempt is pack + notarize + upload, and the notary queue is
# the unbounded part. Two attempts, because a failed adhoc build has a
# person waiting on it who can simply dispatch again.
timeout_minutes: 45
max_attempts: 2
retry_wait_seconds: 30
command: node config/scripts/ensure-native-runtime.mjs --runtime=electron && ORCA_MAC_ADHOC=1 pnpm exec electron-builder --config config/electron-builder.config.cjs --mac --publish always
env:
# Why: electron-builder's github publisher targets the repo named in the
# config; the token must therefore carry write access to orca-adhoc.
GH_TOKEN: ${{ steps.app_token.outputs.token }}
ORCA_ADHOC_BUILD_VERSION: ${{ steps.adhoc.outputs.version }}
ORCA_BUILD_COMMIT: ${{ steps.adhoc.outputs.commit }}
CSC_LINK: ${{ secrets.MAC_CERTS }}
CSC_KEY_PASSWORD: ${{ secrets.MAC_CERTS_PASSWORD }}
# Why all three: electron-builder's notarize step authenticates to the
# Apple notary service with the app-specific password, not with the
# signing cert. Omitting them fails the build rather than skipping it.
APPLE_ID: ${{ secrets.APPLE_ID }}
APPLE_APP_SPECIFIC_PASSWORD: ${{ secrets.APPLE_APP_SPECIFIC_PASSWORD }}
APPLE_TEAM_ID: ${{ secrets.APPLE_TEAM_ID }}
# Why: the updater resolves a tag, then fetches latest-mac.yml from it. A
# release missing that manifest is a tag the picker offers and the download
# 404s on, so fail loudly instead of leaving a broken entry.
- name: Verify update manifest published
shell: bash
env:
GH_TOKEN: ${{ steps.app_token.outputs.token }}
TAG: ${{ steps.release.outputs.tag }}
run: |
set -euo pipefail
assets="$(gh release view "$TAG" --repo "$ADHOC_REPO" --json assets --jq '.assets[].name')"
echo "Published assets:"
echo "$assets"
# Why exit 1 without deleting here: the release is still a draft, so it is
# already invisible to users, and the failure handler below owns cleanup.
for required in latest-mac.yml; do
if ! grep -qx "$required" <<<"$assets"; then
echo "::error::Adhoc draft $TAG is missing $required; the updater could not install it."
exit 1
fi
done
if ! grep -q '\.zip$' <<<"$assets"; then
echo "::error::Adhoc draft $TAG has no ZIP artifact for the updater to download."
exit 1
fi
# Why this is the last mutating step: publishing the draft is what makes the
# build visible to listReleaseBuilds. Doing it only after the manifest check
# means the picker can never offer a release whose assets are incomplete.
- name: Publish the verified release
id: publish_live
shell: bash
env:
GH_TOKEN: ${{ steps.app_token.outputs.token }}
TAG: ${{ steps.release.outputs.tag }}
NAME: ${{ steps.adhoc.outputs.name }}
run: |
set -euo pipefail
# --title again: electron-builder resolves this draft by tag and may
# rewrite its title on upload. Re-asserting here means the name the
# picker reads is the one composed above, whatever it did in between.
gh release edit "$TAG" --repo "$ADHOC_REPO" --draft=false --prerelease --title "$NAME"
echo "Published $TAG as \"$NAME\""
# Why: a draft left behind by a failed publish is invisible to users but still
# holds its tag name. Gated on publish_live not having succeeded so a later
# failure (the prune step) cannot delete a release that already went live and
# that people may already be installing. Why cancelled() too: a run stopped
# from the Actions UI is not a failure(), so without it a manual cancel
# mid-publish would strand the draft.
- name: Discard the draft release on failure
if: >-
(failure() || cancelled()) && steps.release.outputs.tag != '' &&
steps.publish_live.outcome != 'success'
shell: bash
env:
GH_TOKEN: ${{ steps.app_token.outputs.token }}
TAG: ${{ steps.release.outputs.tag }}
run: |
set -uo pipefail
# No --cleanup-tag: an unpublished draft never created a git tag.
echo "Run failed before publish; discarding draft $TAG"
gh release delete "$TAG" --repo "$ADHOC_REPO" --yes ||
echo "::warning::Could not discard draft $TAG; remove it manually."
- name: Prune expired adhoc releases
shell: bash
env:
GH_TOKEN: ${{ steps.app_token.outputs.token }}
run: |
set -euo pipefail
# Why compute the cutoff in bash rather than with jq's `now`: this runs
# once per dispatch, and a fixed epoch makes the threshold visible in the
# log when someone asks where their build went.
cutoff=$(( $(date -u +%s) - ADHOC_RETAIN_DAYS * 86400 ))
echo "Pruning adhoc releases created before $(date -u -r "$cutoff" '+%Y-%m-%dT%H:%M:%SZ')"
# --cleanup-tag so pruning does not leave orphan tags with no release or
# assets attached. Drafts are excluded: a stale draft is the failure
# path's business, not the retention window's.
stale="$(gh release list --repo "$ADHOC_REPO" --limit 200 --json tagName,createdAt,isDraft \
--jq "map(select(.isDraft | not)) | map(select((.createdAt | fromdateiso8601) < $cutoff)) | .[].tagName")"
if [[ -z "$stale" ]]; then
echo "Nothing to prune."
exit 0
fi
while read -r tag; do
[[ -n "$tag" ]] || continue
echo "Pruning $tag"
gh release delete "$tag" --repo "$ADHOC_REPO" --yes --cleanup-tag || \
echo "::warning::Could not prune $tag"
done <<<"$stale"