wifi-densepose/.github/workflows/ci.yml

526 lines
18 KiB
YAML

name: Continuous Integration
on:
push:
branches: [ main, develop, 'feature/*', 'feat/*', 'hotfix/*' ]
pull_request:
branches: [ main, develop ]
workflow_dispatch:
env:
PYTHON_VERSION: '3.11'
NODE_VERSION: '18'
REGISTRY: ghcr.io
IMAGE_NAME: ${{ github.repository }}
jobs:
# Code Quality and Security Checks
# The Python codebase moved to `archive/v1/` when the runtime was rewritten in
# Rust under `v2/`. The lint/format/type/scan checks below still run against
# the archive for hygiene, but with `continue-on-error: true` everywhere — the
# archive is frozen reference code, not active development, so a stale lint
# rule shouldn't gate PRs to the Rust workspace.
code-quality:
name: Code Quality & Security
runs-on: ubuntu-latest
continue-on-error: true
steps:
- name: Checkout code
continue-on-error: true
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Set up Python
continue-on-error: true
uses: actions/setup-python@v6
with:
python-version: ${{ env.PYTHON_VERSION }}
cache: 'pip'
- name: Install dependencies
continue-on-error: true
run: |
python -m pip install --upgrade pip
pip install -r requirements.txt
pip install black flake8 mypy bandit safety
- name: Code formatting check (Black)
continue-on-error: true
run: black --check --diff archive/v1/src archive/v1/tests
- name: Linting (Flake8)
continue-on-error: true
run: flake8 archive/v1/src archive/v1/tests --max-line-length=88 --extend-ignore=E203,W503
- name: Type checking (MyPy)
continue-on-error: true
run: mypy archive/v1/src --ignore-missing-imports
- name: Security scan (Bandit)
run: bandit -r archive/v1/src -f json -o bandit-report.json
continue-on-error: true
- name: Dependency vulnerability scan (Safety)
run: safety check --json --output safety-report.json
continue-on-error: true
- name: Upload security reports
continue-on-error: true
uses: actions/upload-artifact@v4
if: always()
with:
name: security-reports
path: |
bandit-report.json
safety-report.json
# Build Verification — ensure the Rust workspace compiles cleanly before running tests.
# Catches type errors, missing imports, and dependency resolution issues early.
rust-build:
name: Rust Build Check
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install Tauri / GTK / serial system dev libraries
run: |
sudo apt-get update
sudo apt-get install -y --no-install-recommends \
libglib2.0-dev \
libgtk-3-dev \
libsoup-3.0-dev \
libjavascriptcoregtk-4.1-dev \
libwebkit2gtk-4.1-dev \
libayatana-appindicator3-dev \
librsvg2-dev \
libxdo-dev \
libudev-dev \
libdbus-1-dev \
libssl-dev \
pkg-config
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
- name: Cache cargo
uses: actions/cache@v4
with:
path: |
~/.cargo/registry
~/.cargo/git
v2/target
key: ${{ runner.os }}-cargo-build-${{ hashFiles('v2/Cargo.lock') }}
restore-keys: |
${{ runner.os }}-cargo-build-
- name: Build Rust workspace
working-directory: v2
run: cargo build --workspace --no-default-features
- name: TypeScript type-check (dashboard)
if: success()
run: |
cd ${{ github.workspace }}/dashboard
npm ci
npx tsc --noEmit
# Rust Workspace Tests
rust-tests:
name: Rust Workspace Tests
runs-on: ubuntu-latest
needs: [rust-build]
steps:
- name: Checkout code
uses: actions/checkout@v4
# `wifi-densepose-desktop` is a Tauri v2 app — `glib-sys`, `gtk-sys`,
# `webkit2gtk-sys`, etc. need the Linux dev libraries via pkg-config or the
# workspace test fails at the build step before any test runs (every recent
# main CI run has been red on this for exactly this reason). Install the
# standard Tauri-on-Ubuntu set.
- name: Install Tauri / GTK / serial system dev libraries
run: |
sudo apt-get update
sudo apt-get install -y --no-install-recommends \
libglib2.0-dev \
libgtk-3-dev \
libsoup-3.0-dev \
libjavascriptcoregtk-4.1-dev \
libwebkit2gtk-4.1-dev \
libayatana-appindicator3-dev \
librsvg2-dev \
libxdo-dev \
libudev-dev \
libdbus-1-dev \
libssl-dev \
pkg-config
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
- name: Cache cargo
uses: actions/cache@v4
with:
path: |
~/.cargo/registry
~/.cargo/git
v2/target
key: ${{ runner.os }}-cargo-${{ hashFiles('v2/Cargo.lock') }}
restore-keys: |
${{ runner.os }}-cargo-
- name: Run Rust tests
working-directory: v2
run: cargo test --workspace --no-default-features
- name: Run ADR-147 worldmodel tests
working-directory: v2
run: cargo test -p wifi-densepose-worldmodel --no-default-features
# ADR-134 CIR tests are behind the `cir` feature so the bench dependency
# (Criterion) only pulls when actually exercised. Run them as a separate
# step so a CIR-only regression is unambiguously attributable.
- name: Run ADR-134 CIR tests
working-directory: v2
run: cargo test -p wifi-densepose-signal --no-default-features --features cir --tests
# ADR-134 + ADR-028 witness guard. The CIR proof runner produces a
# bit-deterministic SHA-256 over CirEstimator output on the synthetic
# reference signal. Any algorithmic regression — changes to ISTA
# convergence, sensing matrix construction, soft-thresholding, or input
# padding — breaks the hash and fails the build. To regenerate after an
# *intentional* change:
# cd v2 && cargo run -p wifi-densepose-signal --bin cir_proof_runner \
# --release --no-default-features -- --generate-hash \
# > ../archive/v1/data/proof/expected_cir_features.sha256
- name: ADR-134 CIR witness proof (determinism guard)
run: bash scripts/verify-cir-proof.sh
- name: ADR-135 calibration witness proof (determinism guard)
run: bash scripts/verify-calibration-proof.sh
# Unit and Integration Tests
# Python pytest matrix — runs against the archived v1 Python tree.
# `continue-on-error: true` for the same reason as code-quality above:
# the archive is frozen reference, not blocking the Rust workspace PRs.
test:
name: Tests
runs-on: ubuntu-latest
continue-on-error: true
strategy:
fail-fast: false
matrix:
python-version: ['3.10', '3.11', '3.12']
services:
postgres:
image: postgres:15
env:
POSTGRES_PASSWORD: postgres
POSTGRES_DB: test_wifi_densepose
options: >-
--health-cmd pg_isready
--health-interval 10s
--health-timeout 5s
--health-retries 5
ports:
- 5432:5432
redis:
image: redis:7
options: >-
--health-cmd "redis-cli ping"
--health-interval 10s
--health-timeout 5s
--health-retries 5
ports:
- 6379:6379
steps:
- name: Checkout code
continue-on-error: true
uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
continue-on-error: true
uses: actions/setup-python@v6
with:
python-version: ${{ matrix.python-version }}
cache: 'pip'
- name: Install dependencies
continue-on-error: true
run: |
python -m pip install --upgrade pip
pip install -r requirements.txt
pip install pytest-cov pytest-xdist
- name: Run unit tests
continue-on-error: true
env:
DATABASE_URL: postgresql://postgres:postgres@localhost:5432/test_wifi_densepose
REDIS_URL: redis://localhost:6379/0
ENVIRONMENT: test
run: |
pytest archive/v1/tests/unit/ -v --cov=archive/v1/src --cov-report=xml --cov-report=html --junitxml=junit.xml
- name: Run integration tests
continue-on-error: true
env:
DATABASE_URL: postgresql://postgres:postgres@localhost:5432/test_wifi_densepose
REDIS_URL: redis://localhost:6379/0
ENVIRONMENT: test
run: |
pytest archive/v1/tests/integration/ -v --junitxml=integration-junit.xml
- name: Upload coverage reports
continue-on-error: true
uses: codecov/codecov-action@v6
with:
file: ./coverage.xml
flags: unittests
name: codecov-umbrella
- name: Upload test results
continue-on-error: true
uses: actions/upload-artifact@v4
if: always()
with:
name: test-results-${{ matrix.python-version }}
path: |
junit.xml
integration-junit.xml
htmlcov/
# Performance and Load Tests
# NOTE: tests/performance/locustfile.py and the src.api.main app path both
# predate the v1→archive/v1 reorganisation. continue-on-error: true until a
# proper locust suite is added under archive/v1/tests/performance/.
performance-test:
name: Performance Tests
runs-on: ubuntu-latest
needs: [test]
continue-on-error: true
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v6
with:
python-version: ${{ env.PYTHON_VERSION }}
cache: 'pip'
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements.txt
pip install pytest # the perf suite is pytest, not locust
# No "Start application" step: the gated test (test_frame_budget.py) drives
# the CSIProcessor pipeline in-process and makes no HTTP calls, so the old
# uvicorn server + `sleep 10` were dead weight — they only existed for the
# now-excluded api_throughput/inference_speed tests, and on every run dumped
# ~50 misleading "router requires hardware setup" ERROR lines for a server
# no test touched. MOCK_POSE_DATA is server-only and unused here.
- name: Run performance tests
working-directory: archive/v1
run: |
# Gate only on the genuine, deterministic perf guard:
# test_frame_budget.py times the *real* CSIProcessor pipeline against
# the ADR 50 ms per-frame budget (single-frame, p95 over 100 frames,
# +Doppler) — a true regression signal.
#
# test_api_throughput.py / test_inference_speed.py are excluded: every
# test there is a TDD red-phase stub (suffix `_should_fail_initially`)
# that times a *mock that sleeps* — meaningless as a perf signal, with
# machine-dependent wall-clock asserts (e.g. `actual_rps >= 40`,
# `batch_time < individual_time`) that are inherently flaky on shared
# CI runners, plus a cross-class fixture-scope bug. Forcing them green
# would be manufacturing a false signal; they stay in-repo for local
# TDD but do not gate CI until the underlying features are implemented.
#
# `python -m pytest` (not the bare `pytest` script) puts the cwd
# (archive/v1) on sys.path so `from src.core...` resolves — the bare
# script omits cwd and raises ModuleNotFoundError: No module named 'src'.
# -o addopts="" drops the root pyproject's --cov/--cov-fail-under=100.
python -m pytest tests/performance/test_frame_budget.py \
-o addopts="" -v --junitxml=perf-junit.xml
- name: Upload performance results
if: always()
uses: actions/upload-artifact@v4
with:
name: performance-results
path: archive/v1/perf-junit.xml
# Docker Build and Test
# NOTE: the canonical Docker build for the sensing-server is now
# `.github/workflows/sensing-server-docker.yml` (multi-registry push, asset
# smoke tests, bearer-auth smoke tests — #520/#514/#443). This job predates
# that workflow, points at a non-existent root `Dockerfile` with a
# non-existent `target: production`, and pushes to a mis-cased image name —
# `continue-on-error: true` until it's deleted or rewired to call the new
# workflow, so it doesn't gate the rest of the pipeline.
docker-build:
name: Docker Build & Test
runs-on: ubuntu-latest
needs: [code-quality, test, rust-tests]
continue-on-error: true
steps:
- name: Checkout code
continue-on-error: true
uses: actions/checkout@v4
- name: Set up Docker Buildx
continue-on-error: true
uses: docker/setup-buildx-action@v3
- name: Log in to Container Registry
continue-on-error: true
uses: docker/login-action@v3
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract metadata
continue-on-error: true
id: meta
uses: docker/metadata-action@v6
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
tags: |
type=ref,event=branch
type=ref,event=pr
type=sha,prefix={{branch}}-
type=raw,value=latest,enable={{is_default_branch}}
- name: Build and push Docker image
continue-on-error: true
uses: docker/build-push-action@v7
with:
context: .
target: production
push: true
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
cache-from: type=gha
cache-to: type=gha,mode=max
platforms: linux/amd64,linux/arm64
- name: Test Docker image
continue-on-error: true
run: |
docker run --rm -d --name test-container -p 8000:8000 ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ github.sha }}
sleep 10
curl -f http://localhost:8000/health || exit 1
docker stop test-container
- name: Run container security scan
continue-on-error: true
uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
with:
image-ref: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ github.sha }}
format: 'sarif'
output: 'trivy-results.sarif'
- name: Upload Trivy scan results
continue-on-error: true
uses: github/codeql-action/upload-sarif@v3
if: always()
with:
sarif_file: 'trivy-results.sarif'
# API Documentation
docs:
name: API Documentation
runs-on: ubuntu-latest
needs: [docker-build]
if: github.ref == 'refs/heads/main'
permissions:
contents: write # gh-pages deploy needs write (GITHUB_TOKEN is read-only by default -> 403)
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v6
with:
python-version: ${{ env.PYTHON_VERSION }}
cache: 'pip'
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements.txt
- name: Generate OpenAPI spec
working-directory: archive/v1
env:
MOCK_POSE_DATA: "true" # no CSI hardware in CI
run: |
python -c "
from src.api.main import app
import json
with open('openapi.json', 'w') as f:
json.dump(app.openapi(), f, indent=2)
"
- name: Deploy to GitHub Pages
uses: peaceiris/actions-gh-pages@v4
continue-on-error: true # openapi generation above is the real validation; deploy is best-effort (Pages may be disabled)
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
publish_dir: ./docs
destination_dir: api-docs
# Notification
notify:
name: Notify
runs-on: ubuntu-latest
needs: [code-quality, test, rust-tests, performance-test, docker-build, docs]
if: always()
permissions:
contents: write # required by softprops/action-gh-release
# GitHub Actions does not allow `secrets.X` directly in step-level `if:`
# expressions — only `env.X`. Promote the secret to env at job scope so
# the gating expression below is parseable.
env:
SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
steps:
- name: Notify Slack on success
if: ${{ env.SLACK_WEBHOOK_URL != '' && needs.code-quality.result == 'success' && needs.test.result == 'success' && needs.docker-build.result == 'success' }}
uses: 8398a7/action-slack@v3
with:
status: success
channel: '#ci-cd'
text: '✅ CI pipeline completed successfully for ${{ github.ref }}'
- name: Notify Slack on failure
if: ${{ env.SLACK_WEBHOOK_URL != '' && (needs.code-quality.result == 'failure' || needs.test.result == 'failure' || needs.docker-build.result == 'failure') }}
uses: 8398a7/action-slack@v3
with:
status: failure
channel: '#ci-cd'
text: '❌ CI pipeline failed for ${{ github.ref }}'
- name: Create GitHub Release
if: github.ref == 'refs/heads/main' && needs.docker-build.result == 'success'
uses: softprops/action-gh-release@v2
with:
tag_name: v${{ github.run_number }}
name: Release v${{ github.run_number }}
body: |
Automated release from CI pipeline
**Changes:**
${{ github.event.head_commit.message }}
**Docker Image:**
`${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ github.sha }}`
draft: false
prerelease: false