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

2026-08-24 00:14:07 -03:00
parent e1e0be1353
commit 23de7d8fe7
176 changed files with 266754 additions and 10179 deletions
@@ -0,0 +1,37 @@
+"""Unit tests for deterministic fingerprint calculation covering scenarios ID-001 to ID-010."""
+
+from src.runtime.core.fingerprint import calculate_execution_fingerprint
+
+
+def test_deterministic_fingerprint_identical_inputs():
+    article = {
+        "crawled_url": "https://example.com/art1",
+        "selected_extractor": "trafilatura",
+        "trafilatura": {"title": "Title 1", "body_text": "Body 1"},
+    }
+    ecp = {"qid": "Q123", "version": "1.0.0", "canonical_name": "Test Entity"}
+    prompts = {"hygiene": "hash1", "enrichment": "hash2"}
+    models = {"primary": "groq", "fallback": "deepseek"}
+
+    fp1 = calculate_execution_fingerprint(article, ecp, "1.0.0", prompts, models)
+    fp2 = calculate_execution_fingerprint(article, ecp, "1.0.0", prompts, models)
+
+    assert len(fp1) == 64
+    assert fp1 == fp2
+
+
+def test_fingerprint_changes_on_config_or_ecp_change():
+    article = {
+        "crawled_url": "https://example.com/art1",
+        "selected_extractor": "trafilatura",
+        "trafilatura": {"title": "Title 1", "body_text": "Body 1"},
+    }
+    ecp1 = {"qid": "Q123", "version": "1.0.0", "canonical_name": "Test Entity"}
+    ecp2 = {"qid": "Q999", "version": "1.0.0", "canonical_name": "Different Entity"}
+    prompts = {"hygiene": "hash1", "enrichment": "hash2"}
+    models = {"primary": "groq", "fallback": "deepseek"}
+
+    fp1 = calculate_execution_fingerprint(article, ecp1, "1.0.0", prompts, models)
+    fp2 = calculate_execution_fingerprint(article, ecp2, "1.0.0", prompts, models)
+
+    assert fp1 != fp2