ci: build Docker on main + release only, never on PRs

The image build + smoke test + integration suite are the heaviest jobs in CI
(~9-11 min) and ran on every PR. Gate them to push-to-main and release: a
broken build surfaces on the main push, while the cheap pre-merge guards
(docker-lint hadolint/shellcheck, uv-lockfile-check) still run on PRs to
catch the common Dockerfile/lockfile breakage. Steps skip on PRs so the job
stays green; the dead PR-only arm64 cache-warm build is removed.
This commit is contained in:
Brooklyn Nicholson 2026-06-19 16:46:11 -05:00 committed by ethernet
parent 45540cfb5e
commit 2977e74543

View file

@ -56,13 +56,21 @@ jobs:
- name: Checkout code
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
# The image build + smoke test + integration tests run ONLY on
# push-to-main and release — never on PRs. They are the heaviest jobs
# in CI (~15-45 min) and a broken build surfaces on the main push (and
# is gated pre-merge by docker-lint + uv-lockfile-check). Every step
# below is skipped on PRs, so the job still reports green and the
# required check never hangs.
- name: Set up Docker Buildx
if: github.event_name != 'pull_request'
uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
# Build once, load into the local daemon for smoke testing. Cached
# to gha with a per-arch scope; the push step below reuses every
# layer from this build.
- name: Build image (amd64, smoke test)
if: github.event_name != 'pull_request'
uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
with:
context: .
@ -76,6 +84,7 @@ jobs:
cache-to: type=gha,mode=max,scope=docker-amd64
- name: Smoke test image
if: github.event_name != 'pull_request'
uses: ./.github/actions/hermes-smoke-test
with:
image: ${{ env.IMAGE_NAME }}:test
@ -102,12 +111,15 @@ jobs:
# cheapest path to coverage on every PR that touches docker code.
# ---------------------------------------------------------------------
- name: Install uv (for docker tests)
if: github.event_name != 'pull_request'
uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86 # v5
- name: Set up Python 3.11 (for docker tests)
if: github.event_name != 'pull_request'
run: uv python install 3.11
- name: Install Python dependencies (for docker tests)
if: github.event_name != 'pull_request'
run: |
uv venv .venv --python 3.11
source .venv/bin/activate
@ -118,6 +130,7 @@ jobs:
uv pip install -e ".[dev]"
- name: Run docker integration tests
if: github.event_name != 'pull_request'
env:
# Skip rebuild; use the image already loaded by the build step.
HERMES_TEST_IMAGE: ${{ env.IMAGE_NAME }}:test
@ -190,7 +203,9 @@ jobs:
- name: Checkout code
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
# arm64 build runs only on push-to-main and release (see build-amd64).
- name: Set up Docker Buildx
if: github.event_name != 'pull_request'
uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
# Log in to ghcr.io so the registry-backed build cache below can be
@ -201,41 +216,21 @@ jobs:
# crashed the build before the smoke test (the reason the gha cache
# was removed from arm64 PRs in the first place).
- name: Log in to ghcr.io (build cache)
if: github.event_name != 'pull_request'
uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4.1.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
# Build once, load into the local daemon for smoke testing.
#
# PR builds use the registry-backed cache READ-ONLY (cache-from only):
# they pull warm layers pushed by the most recent main build but never
# write, so rapid PR pushes don't race on cache writes or pollute the
# cache ref. This restores warm-cache speed to arm64 PR builds (which
# were running fully uncached and were ~45% slower than amd64, making
# them the job most often cancelled on supersede).
# Build once, load into the local daemon for smoke testing, then push
# by digest below. Reads AND writes the registry-backed cache so the
# push reuses layers from this build and the next build starts warm.
#
# Registry cache (type=registry on ghcr.io) is used instead of the gha
# cache that previously broke here: its credential is the job-lifetime
# GITHUB_TOKEN, not a short-lived SAS token, so the cold-build-outlives-
# token failure mode cannot recur.
- name: Build image (arm64, smoke test, cache read-only PR)
if: github.event_name == 'pull_request'
uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
with:
context: .
file: Dockerfile
load: true
platforms: linux/arm64
tags: ${{ env.IMAGE_NAME }}:test
build-args: |
HERMES_GIT_SHA=${{ github.sha }}
cache-from: type=registry,ref=ghcr.io/nousresearch/hermes-agent:buildcache-arm64
# Main/release builds read AND write the registry cache so the digest
# push below reuses layers from this smoke-test build, and so the next
# PR/main build starts warm.
- name: Build image (arm64, smoke test, cached publish)
if: github.event_name != 'pull_request'
uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
@ -251,6 +246,7 @@ jobs:
cache-to: type=registry,ref=ghcr.io/nousresearch/hermes-agent:buildcache-arm64,mode=max
- name: Smoke test image
if: github.event_name != 'pull_request'
uses: ./.github/actions/hermes-smoke-test
with:
image: ${{ env.IMAGE_NAME }}:test