feat: add deterministic content extractor selector engine with F1 consensus

2026-08-20 22:09:43 -03:00
parent 6a45368cb0
commit ff7a50e0eb
46 changed files with 18503 additions and 2813 deletions
@@ -654,9 +654,9 @@
    "semantic_hash": ""
  },
  "README.md": {
-    "mtime": 1787264334.4498444,
-    "seen": 1787264519.0577974,
-    "ast_hash": "196db110cfde06179fb750fc75afb6fe",
+    "mtime": 1787274445.4631622,
+    "seen": 1787274455.3244681,
+    "ast_hash": "5270e11cfba31a235ba379effb2db0d5",
    "semantic_hash": ""
  },
  "scripts/extract_article_contents.py": {
@@ -736,5 +736,83 @@
    "seen": 1787240516.6008823,
    "ast_hash": "d95c4763728496703cd89590288a2bed",
    "semantic_hash": ""
+  },
+  "scripts/select_article_extractor.py": {
+    "mtime": 1787273522.903319,
+    "seen": 1787273548.728257,
+    "ast_hash": "3e6938964c7e4549051cb1637207698d",
+    "semantic_hash": ""
+  },
+  "tests/test_select_article_extractor.py": {
+    "mtime": 1787274189.7777488,
+    "seen": 1787274207.7989414,
+    "ast_hash": "9f91e09d47f06140b243b6f516d14c60",
+    "semantic_hash": ""
+  },
+  "docs/prd_deterministic_content_selection.md": {
+    "mtime": 1787264674.2038286,
+    "seen": 1787272611.6604555,
+    "ast_hash": "2c421402df8b6469ce60eaa984dce666",
+    "semantic_hash": ""
+  },
+  "specs/004-deterministic-content-selection/checklists/deterministic-selection.md": {
+    "mtime": 1787272346.8692143,
+    "seen": 1787272611.6713927,
+    "ast_hash": "6d9bcda99dbd284ffcbce372102fd868",
+    "semantic_hash": ""
+  },
+  "specs/004-deterministic-content-selection/checklists/requirements.md": {
+    "mtime": 1787264728.7202728,
+    "seen": 1787272611.6713977,
+    "ast_hash": "074efe6ba551e93f7d005c5462805693",
+    "semantic_hash": ""
+  },
+  "specs/004-deterministic-content-selection/contracts/cli-contract.md": {
+    "mtime": 1787274329.2175446,
+    "seen": 1787274402.0944166,
+    "ast_hash": "2cd795eaed6198dc343424bd20673728",
+    "semantic_hash": ""
+  },
+  "specs/004-deterministic-content-selection/contracts/json-schema.md": {
+    "mtime": 1787271837.7328393,
+    "seen": 1787272611.6714034,
+    "ast_hash": "155f0bccb7bcffabcedb6ef86b8003c5",
+    "semantic_hash": ""
+  },
+  "specs/004-deterministic-content-selection/data-model.md": {
+    "mtime": 1787271825.5970395,
+    "seen": 1787272611.671406,
+    "ast_hash": "23ec4a144f4aeeed9fee259b6165bea3",
+    "semantic_hash": ""
+  },
+  "specs/004-deterministic-content-selection/plan.md": {
+    "mtime": 1787271850.1744206,
+    "seen": 1787272611.671409,
+    "ast_hash": "3bebc2a73a9632d42ccca646af592133",
+    "semantic_hash": ""
+  },
+  "specs/004-deterministic-content-selection/quickstart.md": {
+    "mtime": 1787274324.1467915,
+    "seen": 1787274402.0946271,
+    "ast_hash": "a7886ca618af43f33971213e2255b3c6",
+    "semantic_hash": ""
+  },
+  "specs/004-deterministic-content-selection/research.md": {
+    "mtime": 1787274316.8544433,
+    "seen": 1787274402.0946283,
+    "ast_hash": "73ac1637d31472e25b0a1709cd137e5c",
+    "semantic_hash": ""
+  },
+  "specs/004-deterministic-content-selection/spec.md": {
+    "mtime": 1787274311.1564865,
+    "seen": 1787274402.0946293,
+    "ast_hash": "b2c994a14871c2e6e1cf4a11db7dbeb5",
+    "semantic_hash": ""
+  },
+  "specs/004-deterministic-content-selection/tasks.md": {
+    "mtime": 1787272595.8186145,
+    "seen": 1787272611.6714194,
+    "ast_hash": "3a2617478f44c6400ed57088d2039f93",
+    "semantic_hash": ""
  }
 }