fix: production hardening — 20 code quality fixes

.github/workflows/ci.yml

@@ -0,0 +1,57 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  rust:
+    name: Rust Tests & Clippy
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+        with:
+          components: clippy
+
+      - name: Cache cargo registry & build
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            target
+          key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
+
+      - name: Build
+        run: cargo build --verbose
+
+      - name: Run tests
+        run: cargo test --verbose
+
+      - name: Clippy (deny warnings)
+        run: cargo clippy -- -D warnings
+
+  python:
+    name: Python Tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install dependencies
+        run: pip install -r requirements.txt
+
+      - name: Run tests
+        run: python -m pytest tests/ -v

.gitignore

@@ -21,5 +21,9 @@ Thumbs.db
 .vscode/
 .idea/
 
+# Generated docs artifacts (regenerated by pipeline)
+docs/candidates.json
+docs/validation_results.json
+
 # Keep the data directory structure
 !data/lightcurves/.gitkeep

Cargo.toml

@@ -30,4 +30,4 @@ tempfile = "3"
 opt-level = 3
 lto = true
 codegen-units = 1
-target-cpu = "native"
+# Note: For native CPU optimizations, set RUSTFLAGS="-C target-cpu=native"

Makefile

@@ -18,19 +18,19 @@ all: setup download hunt analyze
 # Install Python dependencies
 setup:
 	@echo "📦 Installing dependencies..."
-	pip install lightkurve astroquery pandas numpy matplotlib tqdm --quiet
+	python3.11 -m pip install -r requirements.txt --quiet
 
 # Download light curves
 download:
 	@echo "🛰️  Downloading light curves..."
-	python python/download_lightcurves.py \
+	python3.11 python/download_lightcurves.py \
 		--mission $(MISSION) --sector $(SECTOR) \
 		--limit $(LIMIT) --catalog
 
 # Download unconfirmed candidates (best for discovery!)
 download-candidates:
 	@echo "🎯 Downloading unconfirmed TOI candidates..."
-	python python/download_lightcurves.py \
+	python3.11 python/download_lightcurves.py \
 		--candidates-only --limit $(LIMIT) --catalog
 
 # Build and run Rust BLS engine
@@ -49,7 +49,7 @@ target/release/hunt: src/main.rs Cargo.toml
 # Analyze candidates and generate plots
 analyze:
 	@echo "📊 Analyzing candidates..."
-	python python/analyze_candidates.py \
+	python3.11 python/analyze_candidates.py \
 		--input candidates.json \
 		--lightcurves data/lightcurves/ \
 		--crossmatch \

python/analyze_candidates.py

@@ -13,6 +13,8 @@
     python analyze_candidates.py --input candidates.json --crossmatch  # check if any are NEW
 """
 
+from __future__ import annotations
+
 import argparse
 import json
 import sys
@@ -40,7 +42,7 @@
     "transit": "#ef4444",
 }
 
-def setup_style():
+def setup_style() -> None:
     plt.rcParams.update({
         "figure.facecolor": COLORS["bg"],
         "axes.facecolor": COLORS["bg"],
@@ -60,13 +62,15 @@ def setup_style():
 # Phase-folded light curve plot
 # ============================================================================
 
-def plot_phase_folded(candidate: dict, lc_dir: Path, output_dir: Path):
+def plot_phase_folded(candidate: dict, lc_dir: Path, output_dir: Path) -> Path | None:
     """Create a phase-folded light curve plot for a candidate."""
     filepath = lc_dir / candidate["filename"]
     if not filepath.exists():
         return None
 
     df = pd.read_csv(filepath)
+    if "time" not in df.columns or "flux" not in df.columns:
+        return None
     time = df["time"].values
     flux = df["flux"].values
 
@@ -138,7 +142,7 @@ def plot_phase_folded(candidate: dict, lc_dir: Path, output_dir: Path):
              bbox=dict(boxstyle="round,pad=0.5", facecolor=COLORS["grid"], alpha=0.8))
 
     plt.tight_layout()
-    safe_name = candidate["filename"].replace(".csv", "")
+    safe_name = Path(candidate["filename"]).stem
     outpath = output_dir / f"phase_fold_{safe_name}.png"
     fig.savefig(outpath, dpi=150, bbox_inches="tight")
     plt.close(fig)
@@ -149,7 +153,7 @@ def plot_phase_folded(candidate: dict, lc_dir: Path, output_dir: Path):
 # Overview plots
 # ============================================================================
 
-def plot_candidate_overview(candidates: list, output_dir: Path):
+def plot_candidate_overview(candidates: list[dict], output_dir: Path) -> None:
     """Create overview scatter plots of all candidates."""
     if not candidates:
         return
@@ -206,7 +210,7 @@ def plot_candidate_overview(candidates: list, output_dir: Path):
 # Cross-matching
 # ============================================================================
 
-def crossmatch_known_planets(candidates: list, catalog_path: Path) -> pd.DataFrame:
+def crossmatch_known_planets(candidates: list[dict], catalog_path: Path) -> pd.DataFrame:
     """Cross-match candidates with the known exoplanet catalog."""
     if not catalog_path.exists():
         print("   ⚠️  No catalog file found. Run downloader with --catalog first.")
@@ -254,7 +258,7 @@ def crossmatch_known_planets(candidates: list, catalog_path: Path) -> pd.DataFra
 # Report generation
 # ============================================================================
 
-def generate_report(report: dict, crossmatch_df: pd.DataFrame, output_dir: Path):
+def generate_report(report: dict, crossmatch_df: pd.DataFrame, output_dir: Path) -> None:
     """Generate a markdown report."""
     candidates = report["candidates"]
 
@@ -324,7 +328,7 @@ def generate_report(report: dict, crossmatch_df: pd.DataFrame, output_dir: Path)
 # Main
 # ============================================================================
 
-def main():
+def main() -> None:
     parser = argparse.ArgumentParser(description="📊 Analyze BLS transit detection results")
     parser.add_argument("--input", default="candidates.json", help="BLS results JSON")
     parser.add_argument("--lightcurves", default="data/lightcurves", help="Light curve directory")
@@ -344,7 +348,11 @@ def main():
     print("\n📊 Exoplanet Hunter — Analysis")
     print("━" * 50)
 
-    with open(args.input) as f:
+    input_path = Path(args.input)
+    if not input_path.exists():
+        print(f"   Error: {input_path} not found")
+        sys.exit(1)
+    with open(input_path) as f:
         report = json.load(f)
 
     candidates = report["candidates"]

python/deep_analysis.py

@@ -11,6 +11,7 @@
 
 Targets: TOI 133.01, TOI 210.01, TOI 155.01 (top 3 plausible planet candidates)
 """
+from __future__ import annotations
 
 import os
 import sys
@@ -22,7 +23,9 @@
 import matplotlib.pyplot as plt
 from datetime import datetime
 
-warnings.filterwarnings('ignore')
+warnings.filterwarnings('ignore', category=FutureWarning)
+warnings.filterwarnings('ignore', category=DeprecationWarning)
+warnings.filterwarnings('ignore', message='.*overflow.*')
 
 RESULTS_DIR = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'results')
 DEEP_DIR = os.path.join(RESULTS_DIR, 'deep_analysis')
@@ -35,17 +38,15 @@
     {"toi": "TOI 155.01", "tic": "TIC 129637892", "tic_id": 129637892, "period": 5.4504, "rp_earth": 5.3, "snr": 44.3},
 ]
 
-findings = {}
 
-
-def log(msg):
+def log(msg: str) -> None:
     print(f"[{datetime.now().strftime('%H:%M:%S')}] {msg}")
 
 
 # ===========================================================================
 # STEP 1: Target Pixel Files + Centroid Analysis
 # ===========================================================================
-def step1_centroid_analysis():
+def step1_centroid_analysis(findings: dict) -> None:
     log("STEP 1: Downloading TPFs and running centroid analysis...")
     import lightkurve as lk
 
@@ -166,7 +167,9 @@ def step1_centroid_analysis():
             axes[2].legend(fontsize=8)
 
             plt.tight_layout()
-            plot_path = os.path.join(DEEP_DIR, f'centroid_{name.replace(" ", "_").replace(".", "_")}.png')
+            safe_name = name.replace(" ", "_").replace(".", "_")
+            safe_name = os.path.basename(safe_name)  # strip any directory components
+            plot_path = os.path.join(DEEP_DIR, f'centroid_{safe_name}.png')
             plt.savefig(plot_path, dpi=150, bbox_inches='tight')
             plt.close()
             log(f"  Saved centroid plot: {plot_path}")
@@ -179,7 +182,7 @@ def step1_centroid_analysis():
 # ===========================================================================
 # STEP 2: Gaia DR3 Nearby Source Check
 # ===========================================================================
-def step2_gaia_query():
+def step2_gaia_query(findings: dict) -> None:
     log("STEP 2: Querying Gaia DR3 for nearby contaminating sources...")
     from astroquery.mast import Catalogs
     from astroquery.gaia import Gaia
@@ -212,19 +215,19 @@ def step2_gaia_query():
             search_radius = 120  # arcsec = 2 arcmin
 
             log(f"  Querying Gaia DR3 within {search_radius}\" of target...")
-            query = f"""
-            SELECT source_id, ra, dec, phot_g_mean_mag, parallax,
-                   DISTANCE(
-                     POINT('ICRS', ra, dec),
-                     POINT('ICRS', {ra}, {dec})
-                   ) AS ang_sep
-            FROM gaiadr3.gaia_source
-            WHERE DISTANCE(
-                    POINT('ICRS', ra, dec),
-                    POINT('ICRS', {ra}, {dec})
-                  ) < {search_radius / 3600.0}
-            ORDER BY ang_sep ASC
-            """
+            # Sanitize numeric inputs for ADQL (TAP doesn't support parameterized queries)
+            safe_ra = float(ra)
+            safe_dec = float(dec)
+            safe_radius = float(search_radius) / 3600.0
+            query = (
+                "SELECT source_id, ra, dec, phot_g_mean_mag, parallax,"
+                " DISTANCE(POINT('ICRS', ra, dec),"
+                f" POINT('ICRS', {safe_ra:.6f}, {safe_dec:.6f})) AS ang_sep"
+                " FROM gaiadr3.gaia_source"
+                " WHERE DISTANCE(POINT('ICRS', ra, dec),"
+                f" POINT('ICRS', {safe_ra:.6f}, {safe_dec:.6f})) < {safe_radius:.8f}"
+                " ORDER BY ang_sep ASC"
+            )
 
             job = Gaia.launch_job(query)
             results = job.get_results()
@@ -277,7 +280,7 @@ def step2_gaia_query():
 # ===========================================================================
 # STEP 3: Check NASA SPOC DV Reports on MAST
 # ===========================================================================
-def step3_dv_reports():
+def step3_dv_reports(findings: dict) -> None:
     log("STEP 3: Checking NASA SPOC Data Validation reports on MAST...")
     from astroquery.mast import Observations
 
@@ -352,7 +355,7 @@ def step3_dv_reports():
 # ===========================================================================
 # STEP 4: Transit Least Squares (TLS)
 # ===========================================================================
-def step4_tls():
+def step4_tls(findings: dict) -> None:
     log("STEP 4: Running Transit Least Squares (TLS) analysis...")
     try:
         from transitleastsquares import transitleastsquares
@@ -469,7 +472,9 @@ def step4_tls():
             axes[1].legend(fontsize=9)
 
             plt.tight_layout()
-            plot_path = os.path.join(DEEP_DIR, f'tls_{name.replace(" ", "_").replace(".", "_")}.png')
+            safe_name = name.replace(" ", "_").replace(".", "_")
+            safe_name = os.path.basename(safe_name)  # strip any directory components
+            plot_path = os.path.join(DEEP_DIR, f'tls_{safe_name}.png')
             plt.savefig(plot_path, dpi=150, bbox_inches='tight')
             plt.close()
             log(f"  Saved TLS plot: {plot_path}")
@@ -482,7 +487,7 @@ def step4_tls():
 # ===========================================================================
 # STEP 5: Multi-sector secondary eclipse check
 # ===========================================================================
-def step5_multisector_secondary():
+def step5_multisector_secondary(findings: dict) -> None:
     log("STEP 5: Multi-sector secondary eclipse search...")
     import lightkurve as lk
 
@@ -568,7 +573,9 @@ def step5_multisector_secondary():
             ax.set_title(f'{name} — Multi-sector Secondary Eclipse Search ({len(search)} sectors, {len(time)} pts)')
             ax.legend(fontsize=8)
             plt.tight_layout()
-            plot_path = os.path.join(DEEP_DIR, f'secondary_{name.replace(" ", "_").replace(".", "_")}.png')
+            safe_name = name.replace(" ", "_").replace(".", "_")
+            safe_name = os.path.basename(safe_name)  # strip any directory components
+            plot_path = os.path.join(DEEP_DIR, f'secondary_{safe_name}.png')
             plt.savefig(plot_path, dpi=150, bbox_inches='tight')
             plt.close()
 
@@ -580,7 +587,7 @@ def step5_multisector_secondary():
 # ===========================================================================
 # WRITE RESULTS
 # ===========================================================================
-def write_results():
+def write_results(findings: dict) -> None:
     log("Writing results...")
 
     # Save JSON
@@ -702,12 +709,14 @@ def write_results():
     log("Targets: " + ", ".join(t['toi'] for t in TARGETS))
     log("=" * 60)
 
-    step1_centroid_analysis()
-    step2_gaia_query()
-    step3_dv_reports()
-    step4_tls()
-    step5_multisector_secondary()
-    write_results()
+    findings: dict = {}
+
+    step1_centroid_analysis(findings)
+    step2_gaia_query(findings)
+    step3_dv_reports(findings)
+    step4_tls(findings)
+    step5_multisector_secondary(findings)
+    write_results(findings)
 
     log("=" * 60)
     log("DEEP ANALYSIS COMPLETE")