feat: add deterministic content extractor selector engine with F1 consensus

This commit is contained in:
2026-08-20 22:09:43 -03:00
parent 6a45368cb0
commit ff7a50e0eb
46 changed files with 18503 additions and 2813 deletions
+150 -72
View File
@@ -294,15 +294,15 @@
"semantic_hash": ""
},
"classify.py": {
"mtime": 1787197110.3753626,
"seen": 1787197159.9828603,
"ast_hash": "d09a35a5e25d42f6ecc537d5b67bef8e",
"mtime": 1787264412.2457643,
"seen": 1787264519.0539427,
"ast_hash": "e89fc4b64bd7606fc466d5338108705b",
"semantic_hash": ""
},
"pyproject.toml": {
"mtime": 1787234982.768605,
"seen": 1787235020.6850271,
"ast_hash": "26f5f979658067bf447f375f044a8f21",
"mtime": 1787264482.8509245,
"seen": 1787264519.0539448,
"ast_hash": "409c1fc0d7bbda6830ccb71c6196cb2f",
"semantic_hash": ""
},
"src/__init__.py": {
@@ -318,45 +318,45 @@
"semantic_hash": ""
},
"src/adapters/base.py": {
"mtime": 1787196396.6199949,
"seen": 1787196463.0953116,
"ast_hash": "40dc6e175c8708467748c1f42a0e064a",
"mtime": 1787264412.2437606,
"seen": 1787264519.0542011,
"ast_hash": "220635d5d74e73f58259069bf5207908",
"semantic_hash": ""
},
"src/adapters/embeddings.py": {
"mtime": 1787196402.7484262,
"seen": 1787196463.0953145,
"ast_hash": "0444823bb05720d4c4ca1662a00b2c01",
"mtime": 1787264437.92723,
"seen": 1787264519.0542023,
"ast_hash": "7beb0ecfb7482c1fd10422da99f69abe",
"semantic_hash": ""
},
"src/adapters/llm.py": {
"mtime": 1787196408.180451,
"seen": 1787196463.0953166,
"ast_hash": "3d95d98625df3fcd343f2fecb78707c5",
"mtime": 1787264412.2437606,
"seen": 1787264519.0542035,
"ast_hash": "ba2990328f5b25ac6cdfc3b57acc9d39",
"semantic_hash": ""
},
"src/classifier.py": {
"mtime": 1787197085.0250447,
"seen": 1787197159.985785,
"ast_hash": "a2e70f968109d213fdab0ae81ac819ff",
"mtime": 1787264459.052089,
"seen": 1787264519.0542045,
"ast_hash": "b8fb440374ecd66bb8bf67c70c19ed1f",
"semantic_hash": ""
},
"src/language.py": {
"mtime": 1787196384.5545745,
"seen": 1787196463.0953217,
"ast_hash": "985619013e58a7f55af2e955817f223c",
"mtime": 1787264437.9312274,
"seen": 1787264519.0542057,
"ast_hash": "cbaf52272ebb05372e34a05cd201c270",
"semantic_hash": ""
},
"src/models.py": {
"mtime": 1787195855.3266282,
"seen": 1787196463.0953236,
"ast_hash": "ce73bfe85eb54f907e2052c80636ecaf",
"mtime": 1787264437.9302285,
"seen": 1787264519.054207,
"ast_hash": "16e604c14f7d66634dc9e2ed7959dd7c",
"semantic_hash": ""
},
"src/parser.py": {
"mtime": 1787195873.9119804,
"seen": 1787196463.0953257,
"ast_hash": "0a1d64ee7088b266125af071f85f3826",
"mtime": 1787264437.9312274,
"seen": 1787264519.054208,
"ast_hash": "d43fca3f063534e3626f86f36a97a2cc",
"semantic_hash": ""
},
"tests/__init__.py": {
@@ -366,39 +366,39 @@
"semantic_hash": ""
},
"tests/test_adapters.py": {
"mtime": 1787196418.6328156,
"seen": 1787196463.09533,
"ast_hash": "5caf95327ea030dbcc37a99bd9052ebd",
"mtime": 1787264437.9292288,
"seen": 1787264519.0543096,
"ast_hash": "7ed9ba6f62fef404bfc28a2e16ada647",
"semantic_hash": ""
},
"tests/test_benchmark_24.py": {
"mtime": 1787196325.5409796,
"seen": 1787196463.0953324,
"ast_hash": "487d30d6de2dee529fa91b86a1d62c0a",
"mtime": 1787264437.9302285,
"seen": 1787264519.0543122,
"ast_hash": "052a51561002be035de1a79455256b67",
"semantic_hash": ""
},
"tests/test_classifier.py": {
"mtime": 1787196364.7195728,
"seen": 1787196463.0953343,
"ast_hash": "4350a5b11a08d12ccb85a3f332d71e87",
"mtime": 1787264437.92723,
"seen": 1787264519.0543132,
"ast_hash": "14da0c7a7d4c08762437ca777c086dea",
"semantic_hash": ""
},
"tests/test_cli.py": {
"mtime": 1787195939.567137,
"seen": 1787196463.0953364,
"ast_hash": "90b0131d43cfc64a76e499c7a65d95de",
"mtime": 1787264437.9292288,
"seen": 1787264519.0543146,
"ast_hash": "b6f57994937363f8a1b0f2f66ea53d3a",
"semantic_hash": ""
},
"tests/test_language.py": {
"mtime": 1787195891.3329668,
"seen": 1787196463.0953388,
"ast_hash": "66191b43fcd7aef47c07cd20d5a8f03c",
"mtime": 1787264437.9292288,
"seen": 1787264519.0543184,
"ast_hash": "f1a09702410864434274f1b347769742",
"semantic_hash": ""
},
"tests/test_models.py": {
"mtime": 1787195886.5009987,
"seen": 1787196463.095341,
"ast_hash": "1fd725c8ca0f52e52f56c7223e9574d0",
"mtime": 1787264437.9302285,
"seen": 1787264519.0543194,
"ast_hash": "7ec72b612bf758be8c9a3617ce18b132",
"semantic_hash": ""
},
"examples/content_northvolt_de.md": {
@@ -570,27 +570,27 @@
"semantic_hash": ""
},
"tests/test_adversarial.py": {
"mtime": 1787197141.2340336,
"seen": 1787197159.9881344,
"ast_hash": "5e8daf517ee32c261617d96264ef0473",
"mtime": 1787264437.9242287,
"seen": 1787264519.0543108,
"ast_hash": "d353633ce31a624a8dcda790efec4d5e",
"semantic_hash": ""
},
"scripts/extract_google_news.py": {
"mtime": 1787236453.5231855,
"seen": 1787236509.1147037,
"ast_hash": "4216de490a87378d21dab707a3166679",
"mtime": 1787264437.92723,
"seen": 1787264519.0540311,
"ast_hash": "97d8a193901d5e2edf6359fad256b7ef",
"semantic_hash": ""
},
"tests/test_extract_google_news.py": {
"mtime": 1787236301.513448,
"seen": 1787236353.5582018,
"ast_hash": "1fc9a108a8abfecf1d37c8642a885e9e",
"mtime": 1787264437.9312274,
"seen": 1787264519.054317,
"ast_hash": "7561ad8fedcf1bc6cc8ed1e86a345532",
"semantic_hash": ""
},
"docs/googlenews_extractor_guia_completo.md": {
"mtime": 1787231605.0830677,
"seen": 1787234772.8112028,
"ast_hash": "59db8e652000ba6087a00289a0ce0959",
"mtime": 1787264437.9282286,
"seen": 1787264519.0578,
"ast_hash": "d7c3c64e2009dded496a08c7c91f63b9",
"semantic_hash": ""
},
"specs/002-google-news-extractor/checklists/readiness.md": {
@@ -654,21 +654,21 @@
"semantic_hash": ""
},
"README.md": {
"mtime": 1787240502.4633865,
"seen": 1787240516.5990582,
"ast_hash": "a075f140e2dd8383bec3991f92b32b26",
"mtime": 1787264334.4498444,
"seen": 1787264519.0577974,
"ast_hash": "196db110cfde06179fb750fc75afb6fe",
"semantic_hash": ""
},
"scripts/extract_article_contents.py": {
"mtime": 1787241061.3097162,
"seen": 1787241108.1811028,
"ast_hash": "08cd37738da1500b6912ffa1fb2fc0cc",
"mtime": 1787264465.3415215,
"seen": 1787264519.0540295,
"ast_hash": "2bea6b2a048526cb49d95fb88a001600",
"semantic_hash": ""
},
"tests/test_extract_article_contents.py": {
"mtime": 1787240910.5980105,
"seen": 1787241108.1826632,
"ast_hash": "98cf3b30fa6ce044d943eff381eaf8a7",
"mtime": 1787264437.9292288,
"seen": 1787264519.0543158,
"ast_hash": "56aee72480f05c714865791a935d539c",
"semantic_hash": ""
},
"docs/prd_extrator_artigos_nlp.md": {
@@ -708,9 +708,9 @@
"semantic_hash": ""
},
"specs/003-article-content-extractor/plan.md": {
"mtime": 1787239601.395844,
"seen": 1787240516.6008782,
"ast_hash": "406c3ebad1d32984c1b98f8a9b7ae9f1",
"mtime": 1787264323.707266,
"seen": 1787264519.0605621,
"ast_hash": "b2232491829a303a49e749c75f3adca2",
"semantic_hash": ""
},
"specs/003-article-content-extractor/quickstart.md": {
@@ -726,9 +726,9 @@
"semantic_hash": ""
},
"specs/003-article-content-extractor/spec.md": {
"mtime": 1787239197.9064422,
"seen": 1787240516.6008813,
"ast_hash": "9fd196b7ba4d9ba7adb2cad25d094764",
"mtime": 1787264319.2883234,
"seen": 1787264519.060745,
"ast_hash": "187b1307e28a02f0ac44895b5f9cca55",
"semantic_hash": ""
},
"specs/003-article-content-extractor/tasks.md": {
@@ -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": ""
}
}