hermes-agent/.github/workflows/docker.yml
ethernet 3fc4e413d2 feat(ci): track time.sleep in docker test profiler
The profiler now monkey-patches time.sleep alongside subprocess.run,
capturing the invisible "gap" time from polling loops (wait_for_container_ready,
poll_container, wait_for_log, etc.) that was previously unaccounted for.

The JSON report now includes per-test total_sleep_s, sleep_count, and
a sleeps[] array with caller location. The summary includes
total_sleep_s and total_wall_s (docker + sleep). The CI merge step
also aggregates sleep totals.

Local profile now shows: 201s docker + 75s sleep = 276s wall (38s
runner wall with 32-way parallelism). The biggest sleep consumer is
test_dashboard_insecure_env_var_no_longer_bypasses at 11.8s of
poll_container sleeps.
2026-07-14 16:22:05 -04:00

271 lines
11 KiB
YAML

name: Docker Build, Test, and Publish
on:
release:
types: [published]
workflow_call:
permissions:
contents: read
# Concurrency: push/release runs are NEVER cancelled so every merge gets
# its own image. PR runs reuse a PR-scoped group with
# cancel-in-progress: true so rapid pushes to the same PR collapse to
# the latest commit.
concurrency:
group: docker-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
env:
IMAGE_NAME: nousresearch/hermes-agent
jobs:
# Build, test, and optionally push the image for each architecture.
build:
if: github.repository == 'NousResearch/hermes-agent'
strategy:
fail-fast: false
matrix:
include:
- arch: amd64
runner: ubuntu-latest
platform: linux/amd64
cache-from: type=gha,scope=docker-amd64
cache-to: type=gha,mode=max,scope=docker-amd64
- arch: arm64
runner: ubuntu-24.04-arm
platform: linux/arm64
cache-from: type=gha,scope=docker-arm64
cache-to: type=gha,mode=max,scope=docker-arm64
runs-on: ${{ matrix.runner }}
timeout-minutes: 45
steps:
- name: Checkout code
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
# Build once, load into the local daemon for testing. Cached
# per-arch; the push step below reuses every layer from this build.
- name: Build image (${{ matrix.arch }})
uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
with:
context: .
file: Dockerfile
load: true
platforms: ${{ matrix.platform }}
tags: ${{ env.IMAGE_NAME }}:test
build-args: |
HERMES_GIT_SHA=${{ github.sha }}
cache-from: ${{ matrix.cache-from }}
cache-to: ${{ (github.event_name != 'pull_request') && matrix.cache-to || '' }}
- name: Log in to Docker Hub
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4.1.0
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
# Push by digest only (no tag). The merge job assembles the
# tagged manifest list. `push-by-digest=true` is docker's recommended
# pattern for multi-runner multi-platform builds.
- name: Push ${{ matrix.arch }} by digest
id: push
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
with:
context: .
file: Dockerfile
platforms: ${{ matrix.platform }}
labels: |
org.opencontainers.image.revision=${{ github.sha }}
build-args: |
HERMES_GIT_SHA=${{ github.sha }}
outputs: type=image,name=${{ env.IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
cache-from: ${{ matrix.cache-from }}
cache-to: ${{ matrix.cache-to }}
# Write the digest to a file and upload it as an artifact so the
# merge job can stitch both per-arch digests into a manifest list.
- name: Export digest
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
run: |
mkdir -p /tmp/digests
digest="${{ steps.push.outputs.digest }}"
touch "/tmp/digests/${digest#sha256:}"
- name: Upload digest artifact
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
with:
name: digest-${{ matrix.arch }}
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
# Run the docker-integration test suite against the freshly-built
# image already loaded into the local daemon (`:test`).
#
# Piggybacking here avoids a second image build: the build step
# already loaded the image into the daemon under
# `${IMAGE_NAME}:test`, so we just point ``HERMES_TEST_IMAGE`` at
# that. The fixture's ``HERMES_TEST_IMAGE`` branch (see
# tests/docker/conftest.py:62-63) short-circuits the rebuild.
#
# Why this job and not a standalone one: the image is 5GB+; passing
# it between jobs via ``docker save``/``upload-artifact`` is slower
# than the build itself. Reusing the existing daemon state is the
# cheapest path to coverage on every PR that touches docker code.
# ---------------------------------------------------------------------
- name: Install uv (for docker tests)
uses: astral-sh/setup-uv@fac544c07dec837d0ccb6301d7b5580bf5edae39 # 8.2.0
- name: Set up Python 3.11 (for docker tests)
run: uv python install 3.11
- name: Install Python dependencies (for docker tests)
run: |
# ``dev`` extra pulls in pytest, pytest-asyncio —
# everything tests/docker/ needs. We deliberately avoid ``all``
# here because the docker tests only drive the container via
# subprocess and don't import hermes_agent's optional deps.
uv sync --locked --python 3.11 --extra dev
- name: Run docker integration tests
env:
# Skip rebuild; use the image already loaded by the build step.
HERMES_TEST_IMAGE: ${{ env.IMAGE_NAME }}:test
# Match the policy in tests.yml :: test job — no accidental
# real-API calls from inside the harness.
OPENROUTER_API_KEY: ""
OPENAI_API_KEY: ""
NOUS_API_KEY: ""
# Profile every docker subprocess call so we can diagnose why
# the suite is slow on CI vs. local. Each per-file subprocess
# writes its own docker-test-profile-<pid>.json; the merge
# step below combines them into a single report.
HERMES_DOCKER_TEST_PROFILE: "1"
run: |
scripts/run_tests.sh tests/docker/ --file-timeout 600
- name: Merge docker test profiles
if: always()
run: |
python3 -c "
import json, glob, sys
files = sorted(glob.glob('docker-test-profile-*.json'))
if not files:
print('No per-PID profile files found — profiling may not have activated')
sys.exit(0)
merged = {'tests': [], 'summary': {}}
for f in files:
with open(f) as fh:
data = json.load(fh)
merged['tests'].extend(data.get('tests', []))
# Recompute summary aggregates from merged tests.
subcmd_totals = {}
subcmd_counts = {}
total_sleep = 0
total_sleeps = 0
for t in merged['tests']:
for sub, info in t.get('by_subcommand', {}).items():
subcmd_totals[sub] = subcmd_totals.get(sub, 0) + info['total_s']
subcmd_counts[sub] = subcmd_counts.get(sub, 0) + info['count']
total_sleep += t.get('total_sleep_s', 0)
total_sleeps += t.get('sleep_count', 0)
total_docker = sum(subcmd_totals.values())
merged['summary'] = {
'total_tests': len(merged['tests']),
'total_calls': sum(subcmd_counts.values()),
'total_sleeps': total_sleeps,
'total_docker_s': round(total_docker, 3),
'total_sleep_s': round(total_sleep, 3),
'total_wall_s': round(total_docker + total_sleep, 3),
'by_subcommand': {
sub: {
'count': subcmd_counts[sub],
'total_s': round(subcmd_totals[sub], 3),
'avg_s': round(subcmd_totals[sub] / subcmd_counts[sub], 3) if subcmd_counts[sub] else 0,
}
for sub in sorted(subcmd_totals, key=lambda s: subcmd_totals[s], reverse=True)
},
}
with open('docker-test-profile.json', 'w') as fh:
json.dump(merged, fh, indent=2)
print(f'Merged {len(files)} per-PID profiles ({len(merged[\"tests\"])} tests, {total_docker:.0f}s docker + {total_sleep:.0f}s sleep = {total_docker + total_sleep:.0f}s wall)')
"
- name: Upload docker test profile
if: always()
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
with:
name: docker-test-profile-${{ matrix.arch }}
path: docker-test-profile.json
retention-days: 14
if-no-files-found: warn
# ---------------------------------------------------------------------------
# Stitch both per-arch digests into a single tagged multi-arch manifest.
# This is a registry-side operation — no building, no layer re-push —
# so it runs in ~30 seconds.
#
# On main pushes: tags both :main and :latest.
# On releases: tags :<release_tag_name>.
# ---------------------------------------------------------------------------
merge:
if: github.repository == 'NousResearch/hermes-agent' && (github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release')
runs-on: ubuntu-latest
needs: [build]
timeout-minutes: 10
steps:
- name: Download digests
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4
with:
path: /tmp/digests
pattern: digest-*
merge-multiple: true
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
- name: Log in to Docker Hub
uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4.1.0
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Create manifest list and push
working-directory: /tmp/digests
env:
IMAGE_NAME: ${{ env.IMAGE_NAME }}
RELEASE_TAG: ${{ github.event.release.tag_name }}
run: |
set -euo pipefail
args=()
for digest_file in *; do
args+=("${IMAGE_NAME}@sha256:${digest_file}")
done
if [ "${{ github.event_name }}" = "release" ]; then
docker buildx imagetools create \
-t "${IMAGE_NAME}:${RELEASE_TAG}" \
"${args[@]}"
else
docker buildx imagetools create \
-t "${IMAGE_NAME}:main" \
-t "${IMAGE_NAME}:latest" \
"${args[@]}"
fi
- name: Inspect image
env:
IMAGE_NAME: ${{ env.IMAGE_NAME }}
RELEASE_TAG: ${{ github.event.release.tag_name }}
run: |
if [ "${{ github.event_name }}" = "release" ]; then
docker buildx imagetools inspect "${IMAGE_NAME}:${RELEASE_TAG}"
else
docker buildx imagetools inspect "${IMAGE_NAME}:main"
fi