Add accuracy, correctness, and performance CI/CD workflows

.github/workflows/accuracy_performance.yml

@@ -0,0 +1,162 @@
+name: PR Evaluation
+
+# NOTE: GitHub-hosted runners are noisy. Latency numbers are indicative only.
+# For precise benchmarks, register a self-hosted runner once asap-tools infra
+# is decoupled from Cloudlab. See PDF eval guide Phase 3.
+
+on:
+  pull_request:
+    branches:
+      - main
+    paths:
+      - 'asap-query-engine/**'
+      - 'asap-planner-rs/**'
+      - 'asap-summary-ingest/**'
+      - 'asap-quickstart/**'
+      - '.github/workflows/accuracy_performance.yml'
+      - 'benchmarks/**'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  packages: write
+  pull-requests: write
+
+jobs:
+  # ---------------------------------------------------------------------------
+  # Job 1: build images once from branch code and push with a SHA-based tag.
+  # All downstream jobs pull these images instead of rebuilding.
+  # ---------------------------------------------------------------------------
+  build:
+    name: Build CI images
+    runs-on: ubuntu-latest
+    outputs:
+      image-tag: ${{ steps.tag.outputs.value }}
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Compute image tag
+        id: tag
+        run: echo "value=sha-$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
+
+      - name: Build and push asap-planner-rs
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: asap-planner-rs/Dockerfile
+          push: true
+          tags: ghcr.io/projectasap/asap-planner-rs:${{ steps.tag.outputs.value }}
+          cache-from: type=registry,ref=ghcr.io/projectasap/asap-planner-rs:buildcache
+          cache-to: type=registry,ref=ghcr.io/projectasap/asap-planner-rs:buildcache,mode=max
+
+      - name: Build and push asap-summary-ingest
+        uses: docker/build-push-action@v6
+        with:
+          context: asap-summary-ingest
+          file: asap-summary-ingest/Dockerfile
+          push: true
+          tags: ghcr.io/projectasap/asap-summary-ingest:${{ steps.tag.outputs.value }}
+
+      - name: Build and push asap-query-engine
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: asap-query-engine/Dockerfile
+          push: true
+          tags: ghcr.io/projectasap/asap-query-engine:${{ steps.tag.outputs.value }}
+          cache-from: type=registry,ref=ghcr.io/projectasap/asap-query-engine:buildcache
+          cache-to: type=registry,ref=ghcr.io/projectasap/asap-query-engine:buildcache,mode=max
+
+  # ---------------------------------------------------------------------------
+  # Job 2: pull the images built above, deploy the full stack, and evaluate.
+  # ---------------------------------------------------------------------------
+  eval:
+    name: Full-stack PR evaluation
+    needs: build
+    runs-on: ubuntu-latest
+    timeout-minutes: 60
+    env:
+      ASAP_IMAGE_TAG: ${{ needs.build.outputs.image-tag }}
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Log in to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Pull and start full stack
+        run: |
+          docker compose \
+            -f asap-quickstart/docker-compose.yml \
+            -f benchmarks/docker-compose.yml \
+            up -d
+
+      - name: Show running containers
+        run: |
+          docker compose \
+            -f asap-quickstart/docker-compose.yml \
+            -f benchmarks/docker-compose.yml \
+            ps
+
+      - name: Wait for all services to be healthy
+        run: bash benchmarks/scripts/wait_for_stack.sh
+
+      - name: Wait for pipeline and data ingestion
+        run: bash benchmarks/scripts/ingest_wait.sh
+
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install Python dependencies
+        run: pip install requests
+
+      - name: Run baseline queries (Prometheus)
+        run: python benchmarks/scripts/run_baseline.py
+
+      - name: Run ASAP queries (query engine)
+        run: python benchmarks/scripts/run_asap.py
+
+      - name: Compare results and evaluate
+        run: python benchmarks/scripts/compare.py
+
+      - name: Upload evaluation reports
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: eval-reports-${{ github.run_id }}
+          path: benchmarks/reports/
+
+      - name: Print docker logs on failure
+        if: failure()
+        run: |
+          docker compose \
+            -f asap-quickstart/docker-compose.yml \
+            -f benchmarks/docker-compose.yml \
+            logs --no-color
+
+      - name: Teardown stack
+        if: always()
+        run: |
+          docker compose \
+            -f asap-quickstart/docker-compose.yml \
+            -f benchmarks/docker-compose.yml \
+            down -v

.github/workflows/correctness.yml

@@ -0,0 +1,168 @@
+name: Correctness Tests
+
+# Verifies cross-language parity between Python and Rust implementations of
+# PromQL pattern matching and sketch serialisation. Ephemeral GitHub Actions
+# VMs are well-suited for these deterministic correctness checks.
+
+on:
+  push:
+    branches: [ main ]
+    paths:
+      - 'asap-common/tests/**'
+      - 'asap-common/dependencies/**'
+      - 'asap-common/sketch-core/**'
+      - '.github/workflows/correctness.yml'
+  pull_request:
+    branches: [ main ]
+    paths:
+      - 'asap-common/tests/**'
+      - 'asap-common/dependencies/**'
+      - 'asap-common/sketch-core/**'
+      - '.github/workflows/correctness.yml'
+  workflow_dispatch:
+
+jobs:
+  # ── 1. Cross-language token matching (Python vs Rust) ──────────────────────
+  cross-language-token-matching:
+    name: Cross-language PromQL token matching
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install Python dependencies
+        run: |
+          python -m pip install --upgrade pip
+          if [ -f asap-common/dependencies/py/requirements.txt ]; then
+            pip install -r asap-common/dependencies/py/requirements.txt
+          fi
+          pip install -e asap-common/dependencies/py/promql_utilities/
+
+      - name: Install Rust
+        uses: dtolnay/rust-toolchain@stable
+
+      - name: Install protoc
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -y protobuf-compiler
+
+      - name: Run sccache
+        uses: mozilla-actions/sccache-action@v0.0.4
+
+      - name: Cache cargo
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            target
+          key: ${{ runner.os }}-cargo-correctness-${{ hashFiles('**/Cargo.lock', '**/Cargo.toml') }}
+
+      - name: Run master test runner (Python + Rust + comparison)
+        working-directory: asap-common/tests/compare_matched_tokens
+        run: python utilities/master_test_runner.py
+        env:
+          RUSTC_WRAPPER: sccache
+
+      - name: Upload test artefacts
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: cross-language-token-results
+          path: |
+            asap-common/tests/compare_matched_tokens/python_tests/python_test_results.json
+            asap-common/tests/compare_matched_tokens/rust_tests/rust_test_results.json
+            asap-common/tests/compare_matched_tokens/comparison_tests/comparison_report.json
+            asap-common/tests/compare_matched_tokens/test_summary.json
+          if-no-files-found: warn
+
+  # ── 2. Cross-language serialised pattern comparison ────────────────────────
+  cross-language-pattern-serialisation:
+    name: Cross-language pattern serialisation
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install Python dependencies
+        run: |
+          python -m pip install --upgrade pip
+          if [ -f asap-common/dependencies/py/requirements.txt ]; then
+            pip install -r asap-common/dependencies/py/requirements.txt
+          fi
+          pip install -e asap-common/dependencies/py/promql_utilities/
+
+      - name: Install Rust
+        uses: dtolnay/rust-toolchain@stable
+
+      - name: Install protoc
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -y protobuf-compiler
+
+      - name: Run sccache
+        uses: mozilla-actions/sccache-action@v0.0.4
+
+      - name: Cache cargo
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            target
+          key: ${{ runner.os }}-cargo-correctness-${{ hashFiles('**/Cargo.lock', '**/Cargo.toml') }}
+
+      - name: Generate Python patterns
+        working-directory: asap-common/tests/compare_patterns
+        run: python python_generate_patterns.py
+
+      - name: Build and run Rust pattern generator
+        working-directory: asap-common/tests/compare_patterns
+        run: cargo run --release
+        env:
+          RUSTC_WRAPPER: sccache
+
+      - name: Compare serialised patterns
+        working-directory: asap-common/tests/compare_patterns
+        run: python compare_serialized_patterns.py
+
+  # ── 3. Rust pattern-matching unit tests ────────────────────────────────────
+  rust-pattern-matching:
+    name: Rust pattern matching unit tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Rust
+        uses: dtolnay/rust-toolchain@stable
+
+      - name: Install protoc
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -y protobuf-compiler
+
+      - name: Run sccache
+        uses: mozilla-actions/sccache-action@v0.0.4
+
+      - name: Cache cargo
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            target
+          key: ${{ runner.os }}-cargo-correctness-${{ hashFiles('**/Cargo.lock', '**/Cargo.toml') }}
+
+      - name: Run Rust pattern matching tests
+        working-directory: asap-common/tests/rust_pattern_matching
+        run: cargo test --release
+        env:
+          RUSTC_WRAPPER: sccache

asap-common/.gitignore

@@ -8,4 +8,5 @@ dependencies/py/promql_utilities/promql_utilities.egg-info/
 dependencies/rs/**/target/
 
 tests/**/*.json
+!tests/**/test_data/*.json
 tests/**/target/

asap-common/tests/compare_matched_tokens/rust_tests/Cargo.toml

@@ -1,3 +1,5 @@
+[workspace]
+
 [package]
 name = "promql_cross_lang_tests"
 version = "0.1.0"