chore: add pre-commit hooks, GitHub Actions CI, dev deps, editorconfig

.editorconfig

@@ -0,0 +1,18 @@
+root = true
+
+[*]
+charset = utf-8
+indent_style = space
+indent_size = 4
+end_of_line = lf
+trim_trailing_whitespace = true
+insert_final_newline = true
+
+[*.{yaml,yml,toml,json}]
+indent_size = 2
+
+[*.rs]
+indent_size = 4
+
+[*.md]
+trim_trailing_whitespace = false

.github/workflows/ci.yml

@@ -0,0 +1,86 @@
+name: CI
+
+on:
+  push:
+    branches: [master, main]
+  pull_request:
+
+jobs:
+  # ── Job 1: lint (fast — blocks everything else if it fails) ──────────────────
+  # Runs pre-commit hooks directly so CI uses the exact same ruff version and
+  # config as local development — no drift between the two.
+  # SKIP the pytest hooks (testmon/xdist): those need the compiled Rust
+  # extension and run in the dedicated test job instead.
+  lint:
+    name: Lint & format (pre-commit)
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: astral-sh/setup-uv@v6
+        with:
+          version: "latest"
+          python-version: "3.11"
+
+      - name: Install dev dependencies (includes pre-commit)
+        run: uv sync
+
+      - name: Run pre-commit hooks
+        run: SKIP=pytest-testmon,pytest-xdist-full uv run pre-commit run --all-files
+
+  # ── Job 2: build Rust extension + run tests ──────────────────────────────────
+  test:
+    name: Build & test
+    runs-on: ubuntu-latest
+    needs: lint
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+
+      - uses: astral-sh/setup-uv@v6
+        with:
+          version: "latest"
+          python-version: "3.11"
+
+      - name: Install dev dependencies
+        run: uv sync
+
+      - name: Build Rust extension (in-place)
+        run: uv run maturin develop --release
+
+      - name: Run tests in parallel
+        run: >
+          uv run pytest tests/
+          -n auto
+          --tb=short
+          -q
+          --cov=chem_engine
+          --cov-report=term-missing
+
+  # ── Job 3: RDKit cross-validation (optional, runs on main only) ──────────────
+  rdkit-validation:
+    name: RDKit cross-validation
+    runs-on: ubuntu-latest
+    needs: test
+    if: github.ref == 'refs/heads/master' || github.ref == 'refs/heads/main'
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+
+      - uses: astral-sh/setup-uv@v6
+        with:
+          version: "latest"
+          python-version: "3.11"
+
+      - name: Install dev dependencies + RDKit
+        run: uv sync && uv pip install rdkit
+
+      - name: Build Rust extension
+        run: uv run maturin develop --release
+
+      - name: Run RDKit cross-validation tests
+        run: uv run pytest tests/test_correctness_vs_rdkit.py --tb=short -q

.gitignore

@@ -28,5 +28,3 @@ dist/
 *.egg-info/*.iml
 
 docs/specs
-
-

.pre-commit-config.yaml

@@ -0,0 +1,58 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-merge-conflict
+      - id: check-added-large-files
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.11.0
+    hooks:
+      - id: ruff
+        args: [--fix]
+      - id: ruff-format
+
+  - repo: https://github.com/Yelp/detect-secrets
+    rev: v1.5.0
+    hooks:
+      - id: detect-secrets
+        args: ["--baseline", ".secrets.baseline"]
+
+  # ── Affected-test selection (pre-commit) + full suite (pre-push) ─────────────
+  #
+  # NOTE: chem-engine is a Rust-Python extension (maturin).
+  # Build the extension and set up the dev environment with uv first:
+  #
+  #   uv sync                             # install dev deps into .venv
+  #   maturin develop --release           # compile Rust extension in-place
+  #   uv run detect-secrets scan > .secrets.baseline
+  #   uv run pre-commit install --install-hooks
+  #   uv run pre-commit install --hook-type pre-push
+  #
+  # pytest-testmon (pre-commit):
+  #   Skips tests whose covered lines haven't changed since last run.
+  #   First run builds the .testmondata DB (full suite).
+  #
+  # pytest-xdist (pre-push):
+  #   Full suite in parallel — authoritative green-light before push.
+  #
+  - repo: local
+    hooks:
+      - id: pytest-testmon
+        name: "pytest-testmon: run only affected tests"
+        language: system
+        entry: uv run pytest tests/ --testmon --ignore=tests/test_correctness_vs_rdkit.py
+        pass_filenames: false
+        types: [python]
+        stages: [pre-commit]
+
+      - id: pytest-xdist-full
+        name: "pytest-xdist: full test suite in parallel (pre-push)"
+        language: system
+        entry: uv run pytest tests/ -n auto --ignore=tests/test_correctness_vs_rdkit.py
+        pass_filenames: false
+        types: [python]
+        stages: [pre-push]

.secrets.baseline

@@ -0,0 +1 @@
+{"version": "1.5.0", "plugins_used": [], "filters_used": [], "results": {}, "generated_at": ""}

README.md

@@ -36,19 +36,28 @@ See [docs/BENCHMARKS.md](docs/BENCHMARKS.md) for full throughput tables at 1K, 5
 
 ## Installation
 
-### From source (requires Rust toolchain + maturin)
+### From source (requires Rust toolchain)
 
 ```bash
-# Install Rust: https://rustup.rs
+# 1. Install Rust: https://rustup.rs
 curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
 
-# Install maturin
-pip install maturin
+# 2. Install uv (if not already installed): https://docs.astral.sh/uv/
+curl -LsSf https://astral.sh/uv/install.sh | sh
 
-# Build and install chem-engine
+# 3. Clone and build
 git clone https://github.com/vandan-revanur/chem-engine.git
 cd chem-engine
-maturin develop --release
+uv sync                          # creates .venv, installs all dev deps (incl. maturin)
+uv run maturin develop --release # compiles Rust extension in-place
+```
+
+### Dev environment setup (first time)
+
+```bash
+uv run detect-secrets scan > .secrets.baseline   # initialise secrets baseline
+uv run pre-commit install --install-hooks         # hook runs on git commit
+uv run pre-commit install --hook-type pre-push    # hook runs on git push
 ```
 
 ---
@@ -59,32 +68,32 @@ maturin develop --release
 import chem_engine as ce
 
 # Parse SMILES
-mol = ce.parse_smiles("CC(=O)Oc1ccccc1C(=O)O")   # aspirin
-print(mol.num_atoms)              # 13
-print(mol.num_bonds)              # 13
-print(mol.amw)                    # ~180 (heavy atoms only)
-print(mol.num_rotatable_bonds)    # 3
+mol = ce.parse_smiles("CC(=O)Oc1ccccc1C(=O)O")  # aspirin
+print(mol.num_atoms)  # 13
+print(mol.num_bonds)  # 13
+print(mol.amw)  # ~180 (heavy atoms only)
+print(mol.num_rotatable_bonds)  # 3
 
 # Canonical SMILES
 can = ce.canonicalize(mol)
-print(can)   # deterministic string
+print(can)  # deterministic string
 
 # 2D layout
 mol2d = ce.generate_2d_coords(mol)
-print(mol2d.coords_2d)   # [[x, y], ...]
+print(mol2d.coords_2d)  # [[x, y], ...]
 
 # 3D embedding
 mol3d = ce.generate_3d_coords(mol)
-print(mol3d.coords_3d)   # [[x, y, z], ...]
+print(mol3d.coords_3d)  # [[x, y, z], ...]
 
 # Fingerprint and similarity
-fp = mol.get_fingerprint()          # 2048-bit ECFP2
-sim = mol.similarity(mol)           # 1.0
+fp = mol.get_fingerprint()  # 2048-bit ECFP2
+sim = mol.similarity(mol)  # 1.0
 print(sim)
 
 # Substructure search
 benzene = ce.parse_smiles("c1ccccc1")
-print(mol.has_substruct_match(benzene))   # True
+print(mol.has_substruct_match(benzene))  # True
 
 # Tautomers
 acetone = ce.parse_smiles("CC(=O)C")
@@ -106,16 +115,16 @@ from rdkit import Chem
 # chem-engine -> RDKit
 rust_mol = ce.parse_smiles("c1ccccc1")
 rd_mol = to_rdkit(rust_mol)
-print(Chem.MolToSmiles(rd_mol))   # RDKit canonical SMILES
+print(Chem.MolToSmiles(rd_mol))  # RDKit canonical SMILES
 
 # RDKit -> chem-engine
 rd_mol = Chem.MolFromSmiles("CC(=O)O")
 rust_mol = from_rdkit(rd_mol)
-print(rust_mol.num_atoms)         # 4
+print(rust_mol.num_atoms)  # 4
 
 # Typical pattern: fast Rust pipeline, RDKit for accuracy-critical steps
 rust_mol = ce.generate_3d_coords(ce.parse_smiles(smiles))
-rd_mol = to_rdkit(rust_mol)       # hand off to RDKit
+rd_mol = to_rdkit(rust_mol)  # hand off to RDKit
 ```
 
 ---
@@ -168,11 +177,17 @@ See [docs/BENCHMARKS.md](docs/BENCHMARKS.md) for full benchmark methodology and
 ## Running the tests
 
 ```bash
-# Full test suite (481 tests, 0 failures)
-python -m pytest tests/ -q
+# Full test suite in parallel (286 tests, 0 failures)
+uv run pytest tests/ -n auto -q
 
-# With verbose output
-python -m pytest tests/ -v
+# With coverage report
+uv run pytest tests/ -n auto --cov=chem_engine --cov-report=term-missing
+
+# Affected tests only (fast, uses testmon — re-runs only tests touching changed files)
+uv run pytest tests/ --testmon
+
+# RDKit cross-validation (requires rdkit: uv pip install rdkit)
+uv run pytest tests/test_correctness_vs_rdkit.py -v
 ```
 
 Test files:
@@ -251,5 +266,3 @@ See [docs/FEATURES.md#limitations](docs/FEATURES.md#13-limitations-and-known-gap
 ## License
 
 [MIT](LICENSE) - Copyright (c) 2026 Vandan Revanur
-
-