feat(runtime): implement single-article consolidation runtime and modularize codebase

scripts/build_release_metadata.py

@@ -0,0 +1,48 @@
+"""Release packaging script generating src/core/release-metadata.json."""
+
+from __future__ import annotations
+
+import hashlib
+import json
+from pathlib import Path
+
+
+def build_release_metadata() -> Path:
+    cfg_file = Path("runtime_config.local.json")
+    cfg_bytes = cfg_file.read_bytes()
+    cfg_sha = hashlib.sha256(cfg_bytes).hexdigest()
+
+    metadata = {
+        "release_version": "1.0.0",
+        "runtime_config_sha256": cfg_sha,
+        "certified_models": [
+            "llama-3.1-8b-instant",
+            "llama-3.3-70b-versatile",
+            "deepseek-chat",
+            "deepseek-reasoner",
+            "gpt-4o-mini",
+            "claude-3-haiku-20240307",
+        ],
+        "schemas": {
+            "article_input": "1.0.0",
+            "ecp_snapshot": "1.0.0",
+            "candidates_payload": "1.0.0",
+            "hygiene_response": "1.0.0",
+            "repair_operations": "1.0.0",
+            "enrichment_response": "1.0.0",
+            "manifest_output": "1.0.0",
+        },
+        "prompts": {
+            "article_content_hygiene": "1.0.0",
+            "article_sentiment_tags": "1.0.0",
+        },
+    }
+
+    out_file = Path("src/runtime/core/release-metadata.json")
+    out_file.write_text(json.dumps(metadata, indent=2), encoding="utf-8")
+    return out_file
+
+
+if __name__ == "__main__":
+    p = build_release_metadata()
+    print(f"Generated release metadata at {p}")

scripts/ci_check.py

@@ -0,0 +1,25 @@
+"""CI multi-tier trigger runner and verification script."""
+
+from __future__ import annotations
+
+import subprocess
+import sys
+
+
+def run_ci_checks() -> int:
+    print("=== STEP 1: Static Zero Regex and Schema Policy Check ===")
+    res_static = subprocess.run([sys.executable, "tests/scripts/check_zero_regex.py"])
+    if res_static.returncode != 0:
+        return 1
+
+    print("\n=== STEP 2: Pytest Automated Suites ===")
+    res_pytest = subprocess.run([sys.executable, "-m", "pytest", "tests/", "-v"])
+    if res_pytest.returncode != 0:
+        return 1
+
+    print("\n=== ALL CI QUALITY GATES PASSED SUCCESSFULLY ===")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(run_ci_checks())

scripts/prepare_reference_20.py

@@ -0,0 +1,50 @@
+"""Helper script to extract the 20 reference articles into individual unit files for evals/reference_20/."""
+
+import json
+from pathlib import Path
+
+
+def main() -> None:
+    source_file = Path("out/river_plate_extracted.json")
+    ecp_source = Path("examples/ecp_club_atletico_river_plate.json")
+    target_dir = Path("evals/reference_20")
+    target_dir.mkdir(parents=True, exist_ok=True)
+
+    if not source_file.exists():
+        print(f"Source file {source_file} does not exist.")
+        return
+
+    data = json.loads(source_file.read_text(encoding="utf-8"))
+    articles = data.get("articles", [])
+    print(f"Found {len(articles)} articles in {source_file}")
+
+    ecp_data = json.loads(ecp_source.read_text(encoding="utf-8")) if ecp_source.exists() else {}
+    (target_dir / "ecp_snapshot.json").write_text(
+        json.dumps(ecp_data, indent=2, ensure_ascii=False),
+        encoding="utf-8"
+    )
+
+    for idx, article in enumerate(articles, start=1):
+        # Ensure selected_extractor is populated if missing or null in raw crawl
+        if not article.get("selected_extractor"):
+            if article.get("trafilatura") and article["trafilatura"].get("body_text"):
+                article["selected_extractor"] = "trafilatura"
+            elif article.get("newspaper4k") and article["newspaper4k"].get("body_text"):
+                article["selected_extractor"] = "newspaper4k"
+            elif article.get("readability") and article["readability"].get("body_text"):
+                article["selected_extractor"] = "readability"
+            else:
+                article["selected_extractor"] = "trafilatura"
+
+        out_path = target_dir / f"article_{idx:02d}.json"
+        out_path.write_text(
+            json.dumps(article, indent=2, ensure_ascii=False),
+            encoding="utf-8"
+        )
+        print(f"Wrote {out_path}")
+
+    print("Reference 20 dataset creation completed.")
+
+
+if __name__ == "__main__":
+    main()