test(e2e): add comprehensive Senior QA E2E text analysis and LLM fallback funnel suite
This commit is contained in:
@@ -500,7 +500,8 @@ TextNLPClassifierApp/
|
||||
│ ├── test_extract_article_contents.py
|
||||
│ ├── test_select_article_extractor.py
|
||||
│ ├── test_convert_article_to_markdown.py # Testes da conversão para Markdown
|
||||
│ └── test_llm_fallback.py # Testes do Tier 3 LLM Fallback
|
||||
│ ├── test_llm_fallback.py # Testes do Tier 3 LLM Fallback
|
||||
│ └── test_e2e_text_analysis_pipeline.py # Suíte E2E do Funil de Análise e Fallback
|
||||
├── requirements.txt # Dependências do projeto
|
||||
├── pyproject.toml # Configurações de ferramentas (pytest, ruff, mypy)
|
||||
└── README.md # Documentação principal
|
||||
@@ -510,12 +511,15 @@ TextNLPClassifierApp/
|
||||
|
||||
## 🧪 Testes e Qualidade de Código
|
||||
|
||||
O repositório possui **196 testes automatizados** com 100% de aprovação cobrindo testes unitários, de regressão, de integração, Golden Fixtures exatas, testes de sensibilidade de mutação, testes de fallback para LLM (Tier 3) e testes End-to-End (E2E) via CLI subprocess:
|
||||
O repositório possui **209 testes automatizados** com 100% de aprovação cobrindo testes unitários, de regressão, de integração, Golden Fixtures exatas, testes de sensibilidade de mutação, testes de fallback para LLM (Tier 3), validações de degradação graciosa e testes End-to-End (E2E) via CLI subprocess:
|
||||
|
||||
```bash
|
||||
# Executar toda a suíte de testes do projeto (196 testes)
|
||||
# Executar toda a suíte de testes do projeto (209 testes)
|
||||
pytest -v
|
||||
|
||||
# Executar a Suíte E2E do Funil de Análise de Texto e Fallback para LLM
|
||||
pytest tests/test_e2e_text_analysis_pipeline.py -v
|
||||
|
||||
# Executar os testes do Fallback para LLM (Tier 3)
|
||||
pytest tests/test_llm_fallback.py -v
|
||||
|
||||
|
||||
@@ -99,7 +99,7 @@
|
||||
"97": "🧠 TextNLPClassifierApp",
|
||||
"98": "Extraction Pipeline Checklist: Article Content Multi-Engine Extractor",
|
||||
"99": "parametrize",
|
||||
"100": "models.py",
|
||||
"100": "main",
|
||||
"101": "ECPSnapshot",
|
||||
"102": "Feature Specification: Multilingual NLP Entity Inherence Classifier (POC)",
|
||||
"103": "4. Requisitos Funcionais (FR)",
|
||||
@@ -151,7 +151,7 @@
|
||||
"149": "sample_rss_xml",
|
||||
"150": "13. Estratégia de testes",
|
||||
"151": "6. Contrato de entrada",
|
||||
"152": "InherenceClassifier",
|
||||
"152": "LLMFallbackAdapter",
|
||||
"153": "convert_html_to_markdown",
|
||||
"154": "JSON Schema Contract: Deterministic Article Content Selection",
|
||||
"155": "5. Escopo",
|
||||
@@ -164,7 +164,7 @@
|
||||
"162": "test_normalize_date_iso_8601_variants",
|
||||
"163": "test_metadata_priority_original_url_all_fallbacks",
|
||||
"164": "test_normalize_scalar_non_string_types",
|
||||
"165": ".disambiguate",
|
||||
"165": "InherenceClassifier",
|
||||
"166": "remove_duplicate_initial_h1",
|
||||
"167": "test_normalize_scalar_whitespace_collapsing"
|
||||
}
|
||||
|
||||
@@ -1 +1 @@
|
||||
{"0": "36bdb6f09c457f7c", "1": "8c5bf6244cf710c6", "2": "efbcc9c62a3ee78b", "3": "8599153989b07faa", "4": "b5952a1f7fee9f20", "5": "5b8462a3f82d188c", "6": "80f79e9e2011a3e3", "7": "4654167fd211d027", "8": "50acfa00fe353440", "9": "c6d2f770737823f1", "10": "44f2ca451aea24be", "11": "feaac5ab67a8c17a", "12": "b71bd92e5edbf2e0", "13": "219d65ba6d2689e4", "14": "8e30bb8112fd02d1", "15": "03906ab80b99db85", "16": "5d51c60ba1bc2be0", "17": "a1da914f522dcd21", "18": "fbad840891b90569", "19": "0686ff2d6fe29fb3", "20": "060baa9e1924b465", "21": "a5c8f2c3080b8243", "22": "0d76852f1d29eeb1", "23": "6ff68619f2d72924", "24": "3da11675eee7ec46", "25": "a6696589e9556f97", "26": "6c752999e8a4d4b6", "27": "2d4e13ea2111d750", "28": "4b60cb0ee1ac186a", "29": "f56fbca9bb8235ec", "30": "c7beed940704509f", "31": "38be2d254fb31ae8", "32": "ee5596fcf7e7c0b3", "33": "e4d4e0a440bc599f", "34": "c897e49c001acdae", "35": "3aad272a2cf5d495", "36": "0a197439d306b956", "37": "f43acf5c8b1329af", "38": "6775efafc9b33338", "39": "8176a164778526f9", "40": "66b69189c0acc3ff", "41": "0322ff824966a4d8", "42": "784c9e3d336a7f53", "43": "4b8bb6c3f7b64856", "44": "18c0ff3e6225bcb2", "45": "b18defdea7d53e37", "46": "54c0fceb01591230", "47": "0fad42a4989aa7e3", "48": "0237e1e02ee47a27", "49": "0d0f9f015921feef", "50": "8d0c81e5ca23e9a6", "51": "f79963571b9c15ee", "52": "5935824c825606cb", "53": "9685f9cbe158e50b", "54": "3d5ab759f350bc79", "55": "d549f24931a990e9", "56": "3cc031dcb648797c", "57": "a0ab88e6c629251d", "58": "76bd6412e2a22ecd", "59": "54827845564490c9", "60": "0a9736c416c0c6b9", "61": "77358620ac528153", "62": "3b0c585df09df48a", "63": "7e78cd3b28828c20", "64": "1c0c958231735f61", "65": "60b0f81225f62f69", "66": "920754c65cc94b88", "67": "df911472140a9b94", "68": "8e17bc11bcea91b9", "69": "7e905b75e4f28b95", "70": "a28424eca5d36c55", "71": "2cdb53d5b6051ab6", "72": "e42fbd3dc744e730", "73": "7fe2cac980de160c", "74": "2b1343a6a9db1487", "75": "54a1bb232f1d4ceb", "76": "442ba11d31ec0e0a", "77": "852a25b8b95bf8d1", "78": "1810ab370b9cd608", "79": "0fc5dca02a3f02f6", "80": "6ff8a97e63c9a2f3", "81": "a38f84ae3d895236", "82": "08e48bd11f9714df", "83": "5095122914e83cf5", "84": "1aef305bd7d7d63f", "85": "f8bfd0cfe9e8b478", "86": "410d15a346bd5894", "87": "6b41d288cfd834ab", "88": "5aa6db96312a8811", "89": "80225792bb62ba04", "90": "fd291228c3311f40", "91": "d4579c5b7aa2742a", "92": "7b9ba7c3bff11361", "93": "71cd9c1fa4a857f0", "94": "34cd980be3c32d21", "95": "970093453f3b7d90", "96": "9e96780a2b7c4bd6", "97": "b7c10b0e09caac0b", "98": "089ea6a55861c693", "99": "cb6165a7dc822d29", "100": "8c97d8c400895e15", "101": "bd22248d0516e5d4", "102": "6aa00d5a83295f11", "103": "f58668f5b10ccdeb", "104": "4ec787414cc6f50b", "105": "1cf3077fd45d874a", "106": "edcd5d9bb3c4b00f", "107": "37f2f47110fe3eaa", "108": "b7ad5abb1da8cf8d", "109": "cb48a9c4f54efa38", "110": "f6dd36fd7f3edbe5", "111": "2925b620f0b1fd17", "112": "d8b3099917c3b711", "113": "3bb61caa0302c804", "114": "0d4f1d08dd056bb9", "115": "4ac2dcddeec2ff11", "116": "07da9aae9668f573", "117": "196f63e0c4536d30", "118": "ade84262e3cfac12", "119": "ebe4e5e0c42c613f", "120": "27256931b19a2867", "121": "5396e68ca6c185ad", "122": "aa8a1de55696b666", "123": "96618c9a362af46c", "124": "83f104cbb62fd03e", "125": "6db738fb27190349", "126": "6a087a22cbcef972", "127": "85fd71a0cad8d3a5", "128": "22dd4feed96c4229", "129": "c4d2f60f532e6f16", "130": "f6b0aa8a1568926b", "131": "142d0db70bad18fe", "132": "67ea4284cbc02c54", "133": "d899cfc86c7a4a27", "134": "ba9464410a9b4168", "135": "0d496a12149eca27", "136": "521f5c7b9d566b4d", "137": "9e37828bdd2ba8c5", "138": "ec03c97194c56f91", "139": "f4e6d5dfa30034c5", "140": "d9b47fa423cf0748", "141": "1e0330b8757f333e", "142": "f35d75e1194c008d", "143": "4d2ae7190b514a34", "144": "4a98716cabf43f86", "145": "56b2431193739c38", "146": "edc785fd71bb0675", "147": "4c7347f8f86e1fbd", "148": "8ca77cc4fd6fd437", "149": "8968e9e7d55afcbe", "150": "f4f4ce1a1180ddb1", "151": "e426746f6e9ee15f", "152": "b2337918dbdaf257", "153": "a3593e6f45bafb20", "154": "56747bad6345d66b", "155": "a8e7498fa7e257df", "156": "56e7b2355898077f", "157": "f2fc88f7d8214711", "158": "c966f6f8570c8c29", "159": "5f6094aa385f3bfe", "160": "2834e7d59672e756", "161": "cc6e436d94fd0033", "162": "64f33a2fc8969cd2", "163": "26ac1c0a00eabce1", "164": "cdcea44a6805ae55", "165": "a6e35f4937a5000c", "166": "85c97dab928b9b1b", "167": "7ab5695391e32126"}
|
||||
{"0": "36bdb6f09c457f7c", "1": "8c5bf6244cf710c6", "2": "efbcc9c62a3ee78b", "3": "8599153989b07faa", "4": "b5952a1f7fee9f20", "5": "5b8462a3f82d188c", "6": "80f79e9e2011a3e3", "7": "4654167fd211d027", "8": "50acfa00fe353440", "9": "c6d2f770737823f1", "10": "44f2ca451aea24be", "11": "feaac5ab67a8c17a", "12": "b71bd92e5edbf2e0", "13": "219d65ba6d2689e4", "14": "8e30bb8112fd02d1", "15": "03906ab80b99db85", "16": "5d51c60ba1bc2be0", "17": "a1da914f522dcd21", "18": "fbad840891b90569", "19": "0686ff2d6fe29fb3", "20": "060baa9e1924b465", "21": "a5c8f2c3080b8243", "22": "0d76852f1d29eeb1", "23": "6ff68619f2d72924", "24": "3da11675eee7ec46", "25": "a6696589e9556f97", "26": "6c752999e8a4d4b6", "27": "2d4e13ea2111d750", "28": "4b60cb0ee1ac186a", "29": "f56fbca9bb8235ec", "30": "c7beed940704509f", "31": "38be2d254fb31ae8", "32": "ee5596fcf7e7c0b3", "33": "e4d4e0a440bc599f", "34": "c897e49c001acdae", "35": "3aad272a2cf5d495", "36": "0a197439d306b956", "37": "f43acf5c8b1329af", "38": "6775efafc9b33338", "39": "8176a164778526f9", "40": "66b69189c0acc3ff", "41": "0322ff824966a4d8", "42": "784c9e3d336a7f53", "43": "4b8bb6c3f7b64856", "44": "18c0ff3e6225bcb2", "45": "d5eb5f4efd73cafb", "46": "57116576996271f5", "47": "0fad42a4989aa7e3", "48": "0237e1e02ee47a27", "49": "0d0f9f015921feef", "50": "8d0c81e5ca23e9a6", "51": "f79963571b9c15ee", "52": "5935824c825606cb", "53": "9685f9cbe158e50b", "54": "3d5ab759f350bc79", "55": "d549f24931a990e9", "56": "3cc031dcb648797c", "57": "a0ab88e6c629251d", "58": "76bd6412e2a22ecd", "59": "54827845564490c9", "60": "0a9736c416c0c6b9", "61": "77358620ac528153", "62": "3b0c585df09df48a", "63": "7e78cd3b28828c20", "64": "1c0c958231735f61", "65": "60b0f81225f62f69", "66": "920754c65cc94b88", "67": "df911472140a9b94", "68": "8e17bc11bcea91b9", "69": "7e905b75e4f28b95", "70": "a28424eca5d36c55", "71": "2cdb53d5b6051ab6", "72": "e42fbd3dc744e730", "73": "7fe2cac980de160c", "74": "2b1343a6a9db1487", "75": "54a1bb232f1d4ceb", "76": "442ba11d31ec0e0a", "77": "852a25b8b95bf8d1", "78": "1810ab370b9cd608", "79": "0fc5dca02a3f02f6", "80": "6ff8a97e63c9a2f3", "81": "a38f84ae3d895236", "82": "08e48bd11f9714df", "83": "5095122914e83cf5", "84": "1aef305bd7d7d63f", "85": "f8bfd0cfe9e8b478", "86": "410d15a346bd5894", "87": "6b41d288cfd834ab", "88": "5aa6db96312a8811", "89": "80225792bb62ba04", "90": "fd291228c3311f40", "91": "d4579c5b7aa2742a", "92": "7b9ba7c3bff11361", "93": "71cd9c1fa4a857f0", "94": "34cd980be3c32d21", "95": "970093453f3b7d90", "96": "9e96780a2b7c4bd6", "97": "b7c10b0e09caac0b", "98": "089ea6a55861c693", "99": "cb6165a7dc822d29", "100": "7bdb2c6abfbde762", "101": "3e1a3e8ca5030d57", "102": "6aa00d5a83295f11", "103": "f58668f5b10ccdeb", "104": "4ec787414cc6f50b", "105": "1cf3077fd45d874a", "106": "edcd5d9bb3c4b00f", "107": "37f2f47110fe3eaa", "108": "b7ad5abb1da8cf8d", "109": "cb48a9c4f54efa38", "110": "f6dd36fd7f3edbe5", "111": "2925b620f0b1fd17", "112": "d8b3099917c3b711", "113": "3bb61caa0302c804", "114": "0d4f1d08dd056bb9", "115": "4ac2dcddeec2ff11", "116": "07da9aae9668f573", "117": "196f63e0c4536d30", "118": "ade84262e3cfac12", "119": "ebe4e5e0c42c613f", "120": "16f0543249fafdd8", "121": "5396e68ca6c185ad", "122": "d1eeebf358bcab60", "123": "96618c9a362af46c", "124": "83f104cbb62fd03e", "125": "6db738fb27190349", "126": "6a087a22cbcef972", "127": "85fd71a0cad8d3a5", "128": "22dd4feed96c4229", "129": "c4d2f60f532e6f16", "130": "f6b0aa8a1568926b", "131": "142d0db70bad18fe", "132": "67ea4284cbc02c54", "133": "d899cfc86c7a4a27", "134": "ba9464410a9b4168", "135": "0d496a12149eca27", "136": "521f5c7b9d566b4d", "137": "9e37828bdd2ba8c5", "138": "ec03c97194c56f91", "139": "f4e6d5dfa30034c5", "140": "d9b47fa423cf0748", "141": "1e0330b8757f333e", "142": "f35d75e1194c008d", "143": "4d2ae7190b514a34", "144": "4a98716cabf43f86", "145": "56b2431193739c38", "146": "edc785fd71bb0675", "147": "4c7347f8f86e1fbd", "148": "8ca77cc4fd6fd437", "149": "8968e9e7d55afcbe", "150": "f4f4ce1a1180ddb1", "151": "e426746f6e9ee15f", "152": "4c30720833331d86", "153": "a3593e6f45bafb20", "154": "56747bad6345d66b", "155": "a8e7498fa7e257df", "156": "56e7b2355898077f", "157": "f2fc88f7d8214711", "158": "c966f6f8570c8c29", "159": "5f6094aa385f3bfe", "160": "2834e7d59672e756", "161": "cc6e436d94fd0033", "162": "64f33a2fc8969cd2", "163": "26ac1c0a00eabce1", "164": "cdcea44a6805ae55", "165": "1e217fe7a21a2501", "166": "85c97dab928b9b1b", "167": "7ab5695391e32126"}
|
||||
@@ -148,7 +148,7 @@
|
||||
"146": "Specification Quality Checklist: Convert Article JSON to Markdown",
|
||||
"147": "CLI Contract: `convert_article_to_markdown.py`",
|
||||
"148": "9. Interface CLI",
|
||||
"149": "get_hl_gl_ceid",
|
||||
"149": "sample_rss_xml",
|
||||
"150": "13. Estratégia de testes",
|
||||
"151": "6. Contrato de entrada",
|
||||
"152": "InherenceClassifier",
|
||||
@@ -164,7 +164,7 @@
|
||||
"162": "test_normalize_date_iso_8601_variants",
|
||||
"163": "test_metadata_priority_original_url_all_fallbacks",
|
||||
"164": "test_normalize_scalar_non_string_types",
|
||||
"165": "LLMFallbackAdapter",
|
||||
"165": ".disambiguate",
|
||||
"166": "remove_duplicate_initial_h1",
|
||||
"167": "test_normalize_scalar_whitespace_collapsing"
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Graph Report - TextNLPClassifierApp (2026-08-21)
|
||||
|
||||
## Corpus Check
|
||||
- 201 files · ~110,162 words
|
||||
- 201 files · ~110,615 words
|
||||
- Verdict: corpus is large enough that graph structure adds value.
|
||||
|
||||
## Summary
|
||||
@@ -10,7 +10,7 @@
|
||||
- Token cost: 0 input · 0 output
|
||||
|
||||
## Graph Freshness
|
||||
- Built from commit: `cb33dafa`
|
||||
- Built from commit: `31152d50`
|
||||
- Run `git rev-parse HEAD` and compare to check if the graph is stale.
|
||||
- Run `graphify update .` after code changes (no API cost).
|
||||
|
||||
@@ -157,7 +157,7 @@
|
||||
- Specification Quality Checklist: Convert Article JSON to Markdown
|
||||
- CLI Contract: `convert_article_to_markdown.py`
|
||||
- 9. Interface CLI
|
||||
- get_hl_gl_ceid
|
||||
- sample_rss_xml
|
||||
- 13. Estratégia de testes
|
||||
- 6. Contrato de entrada
|
||||
- InherenceClassifier
|
||||
@@ -173,7 +173,7 @@
|
||||
- test_normalize_date_iso_8601_variants
|
||||
- test_metadata_priority_original_url_all_fallbacks
|
||||
- test_normalize_scalar_non_string_types
|
||||
- LLMFallbackAdapter
|
||||
- .disambiguate
|
||||
- remove_duplicate_initial_h1
|
||||
- test_normalize_scalar_whitespace_collapsing
|
||||
|
||||
@@ -192,7 +192,7 @@
|
||||
## Surprising Connections (you probably didn't know these)
|
||||
- `main()` --uses--> `ECPSnapshot` [INFERRED]
|
||||
classify.py → src/models.py
|
||||
- `test_e2e_extract_google_news_live_pipeline()` --uses--> `ExtractionResult` [INFERRED]
|
||||
- `test_extract_google_news_orchestration_mocked()` --uses--> `ExtractionResult` [INFERRED]
|
||||
tests/test_extract_google_news.py → scripts/extract_google_news.py
|
||||
- `test_llm_adapter_interface()` --calls--> `LLMFallbackAdapter` [EXTRACTED]
|
||||
tests/test_adapters.py → src/adapters/llm.py
|
||||
@@ -371,16 +371,16 @@ Cohesion: 0.08
|
||||
Nodes (24): 1. Visão geral (arquitetura), 2.1 DTO de entrada (`googlenews_etl/application/dtos/extract_news_dto.py`), 2.2 Value Object de validação (`googlenews_etl/domain/entities/search_query.py`), 2. Entrada, 3.1 O caso de uso (`googlenews_etl/application/use_cases/extract_news_use_case.py`), 3.2 A porta (`googlenews_etl/domain/ports/news_extractor_port.py`), 3.3.1 Inicialização: sessão HTTP com impersonação de browser, 3.3.2 Mapeamento idioma → parâmetros `hl`/`gl` (`_get_hl_gl`) (+16 more)
|
||||
|
||||
### Community 82 - "extract_google_news.py"
|
||||
Cohesion: 0.20
|
||||
Nodes (14): extract_google_news(), _fetch_rss_content(), NewsArticle, _normalize_text_for_comparison(), parse_google_news_rss(), Remove pontuação e espaços extras para comparação de redundância., Parseia o XML do RSS do Google News e extrai os itens estruturados., Resolve em paralelo as URLs intermediárias do Google News para os links finais… (+6 more)
|
||||
Cohesion: 0.15
|
||||
Nodes (18): extract_google_news(), _fetch_rss_content(), get_hl_gl_ceid(), NewsArticle, _normalize_text_for_comparison(), parse_google_news_rss(), Mapeia idioma e locale para os parâmetros hl, gl e ceid do Google News., Remove pontuação e espaços extras para comparação de redundância. (+10 more)
|
||||
|
||||
### Community 83 - "ExtractionResult"
|
||||
Cohesion: 0.29
|
||||
Nodes (5): ExtractionResult, Any, Resultado consolidado da extração., Valida a consolidação do ExtractionResult a partir da busca mockada com URLs…, test_extract_google_news_orchestration_mocked()
|
||||
Nodes (5): ExtractionResult, Any, Resultado consolidado da extração., Valida E2E o fluxo completo de busca, parsing e resolução de URLs reais ao vivo., test_e2e_extract_google_news_live_pipeline()
|
||||
|
||||
### Community 84 - "test_extract_google_news.py"
|
||||
Cohesion: 0.16
|
||||
Nodes (14): Resolve a URL intermediária do Google News para a URL real do veículo., resolve_article_url(), fixture, Testes unitários e de integração para o Extrator de Manchetes do Google News.…, Valida o parsing do feed RSS, higienização de tags HTML e deduplicação., Valida fallback gracioso de URL quando não é link do Google News ou em erro., Valida resolução bem-sucedida de URL do Google News para o portal destino., Valida E2E que o decodificador resolve uma URL real do Google News para o… (+6 more)
|
||||
Cohesion: 0.15
|
||||
Nodes (15): Resolve a URL intermediária do Google News para a URL real do veículo., resolve_article_url(), Testes unitários e de integração para o Extrator de Manchetes do Google News.…, Valida fallback gracioso de URL quando não é link do Google News ou em erro., Valida resolução bem-sucedida de URL do Google News para o portal destino., Valida E2E que o decodificador resolve uma URL real do Google News para o…, Valida o mapeamento padrão de idiomas para pares (hl, gl, ceid)., Valida a sobrescrita geográfica quando o argumento locale é especificado. (+7 more)
|
||||
|
||||
### Community 85 - "Implementation Tasks: Google News Headlines Extractor"
|
||||
Cohesion: 0.14
|
||||
@@ -400,7 +400,7 @@ Nodes (7): Architecture & Pipeline, Documentation (this feature), Implementation
|
||||
|
||||
### Community 90 - "SearchQuery"
|
||||
Cohesion: 0.20
|
||||
Nodes (6): Value Object com parâmetros de busca validados., SearchQuery, Valida E2E o fluxo completo de busca, parsing e resolução de URLs reais ao vivo., Valida as regras de negócio e limites de SearchQuery., test_e2e_extract_google_news_live_pipeline(), test_search_query_validation()
|
||||
Nodes (6): Value Object com parâmetros de busca validados., SearchQuery, Valida a consolidação do ExtractionResult a partir da busca mockada com URLs…, Valida as regras de negócio e limites de SearchQuery., test_extract_google_news_orchestration_mocked(), test_search_query_validation()
|
||||
|
||||
### Community 91 - "1. Technical Decisions & Tradeoffs"
|
||||
Cohesion: 0.25
|
||||
@@ -622,9 +622,9 @@ Nodes (5): 1. Script Signature, 2. Command-Line Arguments, 3. Exit Codes, 4. Sta
|
||||
Cohesion: 0.40
|
||||
Nodes (5): 9.1 Script, 9.2 Argumentos, 9.3 Exemplos, 9.4 Saída do processo, 9. Interface CLI
|
||||
|
||||
### Community 149 - "get_hl_gl_ceid"
|
||||
Cohesion: 0.25
|
||||
Nodes (8): get_hl_gl_ceid(), Mapeia idioma e locale para os parâmetros hl, gl e ceid do Google News., Valida o mapeamento padrão de idiomas para pares (hl, gl, ceid)., Valida a sobrescrita geográfica quando o argumento locale é especificado., Valida fallback dinâmico para idiomas regionais não listados explicitamente., test_get_hl_gl_ceid_default_mappings(), test_get_hl_gl_ceid_dynamic_fallback(), test_get_hl_gl_ceid_with_custom_locale()
|
||||
### Community 149 - "sample_rss_xml"
|
||||
Cohesion: 0.67
|
||||
Nodes (3): fixture, Fixture que fornece o conteúdo do XML de exemplo para testes offline., sample_rss_xml()
|
||||
|
||||
### Community 150 - "13. Estratégia de testes"
|
||||
Cohesion: 0.50
|
||||
@@ -635,8 +635,8 @@ Cohesion: 0.50
|
||||
Nodes (4): 6.1 Formato, 6.2 Valores aceitos para `selected_extractor`, 6.3 Campos obrigatórios após a resolução, 6. Contrato de entrada
|
||||
|
||||
### Community 152 - "InherenceClassifier"
|
||||
Cohesion: 0.14
|
||||
Nodes (24): InherenceClassifier, Tier 1 Deterministic NLP Entity Inherence Classifier with optional Tier 2 /…, DecisionCategory, Unit tests for deterministic classification decision logic., test_contextual_inherent(), test_direct_inherent(), test_negative_anchor_suppression(), test_not_related() (+16 more)
|
||||
Cohesion: 0.11
|
||||
Nodes (31): LLMFallbackAdapter, Optional adapter for LLM fallback boundary disambiguation., InherenceClassifier, Any, Tier 1 Deterministic NLP Entity Inherence Classifier with optional Tier 2 /…, DecisionCategory, Unit tests for deterministic classification decision logic., test_contextual_inherent() (+23 more)
|
||||
|
||||
### Community 153 - "convert_html_to_markdown"
|
||||
Cohesion: 0.33
|
||||
@@ -650,9 +650,9 @@ Nodes (3): 1. Input JSON Schema, 2. Output JSON Schema, JSON Schema Contract: De
|
||||
Cohesion: 0.67
|
||||
Nodes (3): 5.1 Incluído, 5.2 Fora do escopo, 5. Escopo
|
||||
|
||||
### Community 165 - "LLMFallbackAdapter"
|
||||
Cohesion: 0.13
|
||||
Nodes (11): LLMFallbackAdapter, Optional adapter for LLM fallback boundary disambiguation., Returns True if an API key or custom provider function is configured., Constructs a structured disambiguation prompt for the LLM., Executes LLM fallback for ambiguous boundary cases. Returns a refined…, Parses and validates structured JSON response from LLM., Any, Valida detecção de disponibilidade por chave de API ou provider customizado. (+3 more)
|
||||
### Community 165 - ".disambiguate"
|
||||
Cohesion: 0.25
|
||||
Nodes (4): Executes LLM fallback for ambiguous boundary cases. Returns a refined…, Parses and validates structured JSON response from LLM., Returns True if an API key or custom provider function is configured., Constructs an expert-engineered prompt for multilingual entity inherence…
|
||||
|
||||
### Community 166 - "remove_duplicate_initial_h1"
|
||||
Cohesion: 0.50
|
||||
|
||||
+371
-371
File diff suppressed because it is too large
Load Diff
@@ -330,9 +330,9 @@
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/adapters/llm.py": {
|
||||
"mtime": 1787320047.0352886,
|
||||
"seen": 1787320239.0258572,
|
||||
"ast_hash": "ffcf26cb4e89395aa8771ddb4f5de785",
|
||||
"mtime": 1787320797.2485664,
|
||||
"seen": 1787320818.2953389,
|
||||
"ast_hash": "a5cd6f66048ee1d443c2c91ae9947a14",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/classifier.py": {
|
||||
@@ -912,9 +912,9 @@
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_llm_fallback.py": {
|
||||
"mtime": 1787320089.2120655,
|
||||
"seen": 1787320239.0310187,
|
||||
"ast_hash": "74bc17c4668551e77214d6581baf206c",
|
||||
"mtime": 1787320797.249565,
|
||||
"seen": 1787320818.2967606,
|
||||
"ast_hash": "e5d98de814ceeecd8bd601a7c206e92d",
|
||||
"semantic_hash": ""
|
||||
}
|
||||
}
|
||||
@@ -1,16 +1,16 @@
|
||||
# Graph Report - TextNLPClassifierApp (2026-08-21)
|
||||
|
||||
## Corpus Check
|
||||
- 201 files · ~110,615 words
|
||||
- 202 files · ~112,197 words
|
||||
- Verdict: corpus is large enough that graph structure adds value.
|
||||
|
||||
## Summary
|
||||
- 1554 nodes · 1970 edges · 168 communities (120 shown, 48 thin omitted)
|
||||
- Extraction: 97% EXTRACTED · 3% INFERRED · 0% AMBIGUOUS · INFERRED: 59 edges (avg confidence: 0.95)
|
||||
- 1579 nodes · 2030 edges · 168 communities (120 shown, 48 thin omitted)
|
||||
- Extraction: 96% EXTRACTED · 4% INFERRED · 0% AMBIGUOUS · INFERRED: 73 edges (avg confidence: 0.95)
|
||||
- Token cost: 0 input · 0 output
|
||||
|
||||
## Graph Freshness
|
||||
- Built from commit: `31152d50`
|
||||
- Built from commit: `bae14405`
|
||||
- Run `git rev-parse HEAD` and compare to check if the graph is stale.
|
||||
- Run `graphify update .` after code changes (no API cost).
|
||||
|
||||
@@ -110,7 +110,7 @@
|
||||
- 🧠 TextNLPClassifierApp
|
||||
- Extraction Pipeline Checklist: Article Content Multi-Engine Extractor
|
||||
- parametrize
|
||||
- models.py
|
||||
- main
|
||||
- ECPSnapshot
|
||||
- Feature Specification: Multilingual NLP Entity Inherence Classifier (POC)
|
||||
- 4. Requisitos Funcionais (FR)
|
||||
@@ -160,7 +160,7 @@
|
||||
- sample_rss_xml
|
||||
- 13. Estratégia de testes
|
||||
- 6. Contrato de entrada
|
||||
- InherenceClassifier
|
||||
- LLMFallbackAdapter
|
||||
- convert_html_to_markdown
|
||||
- JSON Schema Contract: Deterministic Article Content Selection
|
||||
- 5. Escopo
|
||||
@@ -173,16 +173,16 @@
|
||||
- test_normalize_date_iso_8601_variants
|
||||
- test_metadata_priority_original_url_all_fallbacks
|
||||
- test_normalize_scalar_non_string_types
|
||||
- .disambiguate
|
||||
- InherenceClassifier
|
||||
- remove_duplicate_initial_h1
|
||||
- test_normalize_scalar_whitespace_collapsing
|
||||
|
||||
## God Nodes (most connected - your core abstractions)
|
||||
1. `ECPSnapshot` - 40 edges
|
||||
2. `InherenceClassifier` - 29 edges
|
||||
3. `DecisionCategory` - 28 edges
|
||||
4. `LLMFallbackAdapter` - 26 edges
|
||||
5. `ClassificationResult` - 24 edges
|
||||
1. `ECPSnapshot` - 49 edges
|
||||
2. `InherenceClassifier` - 36 edges
|
||||
3. `DecisionCategory` - 35 edges
|
||||
4. `LLMFallbackAdapter` - 32 edges
|
||||
5. `ClassificationResult` - 26 edges
|
||||
6. `select_article_extractor()` - 23 edges
|
||||
7. `ExtractorName` - 21 edges
|
||||
8. `PRD — Conversão de artigo JSON para Markdown` - 16 edges
|
||||
@@ -347,12 +347,12 @@ Cohesion: 0.29
|
||||
Nodes (6): 1.1 Arguments & Options, 1. Command Line Interface, 2.1 Exit Codes, 2.2 Standard Output (`stdout`) / Standard Error (`stderr`), 2. Standard Streams & Exit Codes, CLI Contract & Interface Specification (POC)
|
||||
|
||||
### Community 45 - "ClassificationResult"
|
||||
Cohesion: 0.11
|
||||
Nodes (17): ABC, BaseNLPAdapter, Base abstract adapter interface for optional Tier 2 / Tier 3 NLP enhancers., Abstract interface for pluggable NLP classification adapters., Return True if the underlying provider or model is installed and configured., Compute semantic similarity score between text and a set of candidate terms., Optionally refine an ambiguous classification result., LocalEmbeddingsAdapter (+9 more)
|
||||
Cohesion: 0.10
|
||||
Nodes (20): ABC, BaseNLPAdapter, Base abstract adapter interface for optional Tier 2 / Tier 3 NLP enhancers., Abstract interface for pluggable NLP classification adapters., Return True if the underlying provider or model is installed and configured., Compute semantic similarity score between text and a set of candidate terms., Optionally refine an ambiguous classification result., LocalEmbeddingsAdapter (+12 more)
|
||||
|
||||
### Community 46 - "test_adversarial.py"
|
||||
Cohesion: 0.10
|
||||
Nodes (19): Any, RelatedEntity, Adversarial and robustness test suite for Multilingual NLP Entity Inherence…, Run CLI via subprocess without --output and verify stdout is pure parseable…, Run CLI via subprocess with empty content and verify error code and exit code., Content about city/state governance of São Paulo against ECP for São Paulo FC., Run CLI via subprocess with missing target_name and verify error payload., Run CLI via subprocess with corrupted JSON and verify error payload. (+11 more)
|
||||
Cohesion: 0.11
|
||||
Nodes (19): RelatedEntity, Adversarial and robustness test suite for Multilingual NLP Entity Inherence…, Run CLI via subprocess without --output and verify stdout is pure parseable…, Run CLI via subprocess with empty content and verify error code and exit code., Run CLI via subprocess with missing target_name and verify error payload., Run CLI via subprocess with corrupted JSON and verify error payload., Content about apple fruit/culinary recipe against Apple Inc. tech entity., High-weight related entity mentioned in passing without required domain anchors. (+11 more)
|
||||
|
||||
### Community 47 - "classifier.py"
|
||||
Cohesion: 0.16
|
||||
@@ -434,13 +434,13 @@ Nodes (34): 1. Requirement Completeness, 2. Requirement Clarity & Non-Ambiguity,
|
||||
Cohesion: 0.22
|
||||
Nodes (9): parametrize, Garante aceitação de URLs absolutas com esquema HTTP e HTTPS válidos., Garante rejeição de esquemas não permitidos, URLs relativas e strings vazias., Garante que a ausência de corpo no extrator selecionado NUNCA faça fallback…, Garante que todos os placeholders documentados no PRD sejam descartados…, test_normalize_scalar_placeholders_discarded(), test_resolve_article_body_strict_isolation_all_extractors(), test_validate_url_invalid_schemes() (+1 more)
|
||||
|
||||
### Community 100 - "models.py"
|
||||
Cohesion: 0.15
|
||||
Nodes (17): emit_error(), main(), parse_args(), Namespace, ClassificationError, ErrorCode, MatchedGraphEntity, Enum (+9 more)
|
||||
### Community 100 - "main"
|
||||
Cohesion: 0.17
|
||||
Nodes (15): emit_error(), main(), parse_args(), Namespace, ClassificationError, ErrorCode, Enum, str (+7 more)
|
||||
|
||||
### Community 101 - "ECPSnapshot"
|
||||
Cohesion: 0.24
|
||||
Nodes (10): ECPSnapshot, classifier(), fixture, parametrize, Controlled 24-case benchmark suite for Multilingual NLP Entity Inherence…, test_benchmark_case(), Unit tests for ECP models, schema validation, and structured error handling., test_ecp_snapshot_defaults() (+2 more)
|
||||
Cohesion: 0.18
|
||||
Nodes (12): ECPSnapshot, Any, classifier(), fixture, parametrize, Controlled 24-case benchmark suite for Multilingual NLP Entity Inherence…, test_benchmark_case(), Unit tests for ECP models, schema validation, and structured error handling. (+4 more)
|
||||
|
||||
### Community 102 - "Feature Specification: Multilingual NLP Entity Inherence Classifier (POC)"
|
||||
Cohesion: 0.14
|
||||
@@ -520,7 +520,7 @@ Nodes (16): detect_language(), extract_words(), normalize_text(), Lightweight mu
|
||||
|
||||
### Community 122 - "test_select_article_extractor.py"
|
||||
Cohesion: 0.18
|
||||
Nodes (16): generate_shingles(), normalize_text(), Executa a normalização determinística para comparação: 1. Decodificar entidades…, Gera conjunto de shingles ordenados de tamanho window_size (padrão 5). - Se…, Suíte de Testes Automatizados para o Seletor Determinístico de Extrator. Cobre…, Garante que marcação de imagem Markdown  seja descartada e link…, E2E: Executa scripts/select_article_extractor.py como subprocesso real na linha…, test_e2e_cli_subprocess_real_execution() (+8 more)
|
||||
Nodes (16): generate_shingles(), normalize_text(), Executa a normalização determinística para comparação: 1. Decodificar entidades…, Gera conjunto de shingles ordenados de tamanho window_size (padrão 5). - Se…, Suíte de Testes Automatizados para o Seletor Determinístico de Extrator. Cobre…, Garante que marcação de imagem Markdown  seja descartada e link…, E2E: Executa CLI com arquivo inexistente e valida código 1 e mensagem no stderr., test_e2e_cli_subprocess_missing_file() (+8 more)
|
||||
|
||||
### Community 123 - "Feature Specification: Deterministic Content Selection"
|
||||
Cohesion: 0.17
|
||||
@@ -634,9 +634,9 @@ Nodes (4): 13.1 Testes unitários, 13.2 Testes de integração do CLI, 13.3 Caso
|
||||
Cohesion: 0.50
|
||||
Nodes (4): 6.1 Formato, 6.2 Valores aceitos para `selected_extractor`, 6.3 Campos obrigatórios após a resolução, 6. Contrato de entrada
|
||||
|
||||
### Community 152 - "InherenceClassifier"
|
||||
Cohesion: 0.11
|
||||
Nodes (31): LLMFallbackAdapter, Optional adapter for LLM fallback boundary disambiguation., InherenceClassifier, Any, Tier 1 Deterministic NLP Entity Inherence Classifier with optional Tier 2 /…, DecisionCategory, Unit tests for deterministic classification decision logic., test_contextual_inherent() (+23 more)
|
||||
### Community 152 - "LLMFallbackAdapter"
|
||||
Cohesion: 0.08
|
||||
Nodes (26): LLMFallbackAdapter, Executes LLM fallback for ambiguous boundary cases. Returns a refined…, Parses and validates structured JSON response from LLM., Optional adapter for LLM fallback boundary disambiguation., Returns True if an API key or custom provider function is configured., Constructs an expert-engineered prompt for multilingual entity inherence…, Any, Suíte de Testes para o Adaptador de Fallback para LLM (Tier 3) do Classificador… (+18 more)
|
||||
|
||||
### Community 153 - "convert_html_to_markdown"
|
||||
Cohesion: 0.33
|
||||
@@ -650,9 +650,9 @@ Nodes (3): 1. Input JSON Schema, 2. Output JSON Schema, JSON Schema Contract: De
|
||||
Cohesion: 0.67
|
||||
Nodes (3): 5.1 Incluído, 5.2 Fora do escopo, 5. Escopo
|
||||
|
||||
### Community 165 - ".disambiguate"
|
||||
Cohesion: 0.25
|
||||
Nodes (4): Executes LLM fallback for ambiguous boundary cases. Returns a refined…, Parses and validates structured JSON response from LLM., Returns True if an API key or custom provider function is configured., Constructs an expert-engineered prompt for multilingual entity inherence…
|
||||
### Community 165 - "InherenceClassifier"
|
||||
Cohesion: 0.11
|
||||
Nodes (30): InherenceClassifier, Tier 1 Deterministic NLP Entity Inherence Classifier with optional Tier 2 /…, DecisionCategory, Content about city/state governance of São Paulo against ECP for São Paulo FC., test_adversarial_sao_paulo_city_vs_fc(), Unit tests for deterministic classification decision logic., test_contextual_inherent(), test_direct_inherent() (+22 more)
|
||||
|
||||
### Community 166 - "remove_duplicate_initial_h1"
|
||||
Cohesion: 0.50
|
||||
@@ -667,16 +667,16 @@ Nodes (4): Remove o primeiro título H1 do corpo somente quando ele for igual ao
|
||||
_Questions this graph is uniquely positioned to answer:_
|
||||
|
||||
- **Why does `PRD — Conversão de artigo JSON para Markdown` connect `PRD — Conversão de artigo JSON para Markdown` to `8. Regras funcionais`, `12. Critérios de aceite`, `11. Requisitos não funcionais`, `9. Interface CLI`, `13. Estratégia de testes`, `6. Contrato de entrada`, `5. Escopo`?**
|
||||
_High betweenness centrality (0.008) - this node is a cross-community bridge._
|
||||
- **Why does `Implementation Plan: Convert Article JSON to Markdown` connect `Implementation Plan: Convert Article JSON to Markdown` to `005-convert-json-markdown/plan.md`?**
|
||||
_High betweenness centrality (0.004) - this node is a cross-community bridge._
|
||||
_High betweenness centrality (0.006) - this node is a cross-community bridge._
|
||||
- **Why does `Tasks: Convert Article JSON to Markdown` connect `Tasks: Convert Article JSON to Markdown` to `005-convert-json-markdown/plan.md`?**
|
||||
_High betweenness centrality (0.004) - this node is a cross-community bridge._
|
||||
- **Are the 10 inferred relationships involving `ECPSnapshot` (e.g. with `main()` and `BaseNLPAdapter`) actually correct?**
|
||||
_`ECPSnapshot` has 10 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **Are the 6 inferred relationships involving `InherenceClassifier` (e.g. with `LocalEmbeddingsAdapter` and `LLMFallbackAdapter`) actually correct?**
|
||||
_`InherenceClassifier` has 6 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **Are the 18 inferred relationships involving `DecisionCategory` (e.g. with `LLMFallbackAdapter` and `InherenceClassifier`) actually correct?**
|
||||
_`DecisionCategory` has 18 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **Why does `ECPSnapshot` connect `ECPSnapshot` to `main`, `InherenceClassifier`, `ClassificationResult`, `test_adversarial.py`, `classifier.py`, `LLMFallbackAdapter`?**
|
||||
_High betweenness centrality (0.004) - this node is a cross-community bridge._
|
||||
- **Are the 16 inferred relationships involving `ECPSnapshot` (e.g. with `main()` and `BaseNLPAdapter`) actually correct?**
|
||||
_`ECPSnapshot` has 16 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **Are the 7 inferred relationships involving `InherenceClassifier` (e.g. with `LocalEmbeddingsAdapter` and `LLMFallbackAdapter`) actually correct?**
|
||||
_`InherenceClassifier` has 7 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **Are the 24 inferred relationships involving `DecisionCategory` (e.g. with `LLMFallbackAdapter` and `InherenceClassifier`) actually correct?**
|
||||
_`DecisionCategory` has 24 INFERRED edges - model-reasoned connections that need verification._
|
||||
- **Are the 4 inferred relationships involving `LLMFallbackAdapter` (e.g. with `ClassificationResult` and `DecisionCategory`) actually correct?**
|
||||
_`LLMFallbackAdapter` has 4 INFERRED edges - model-reasoned connections that need verification._
|
||||
+1
File diff suppressed because one or more lines are too long
+1
File diff suppressed because one or more lines are too long
+1
File diff suppressed because one or more lines are too long
Vendored
+1
-1
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
+1332
-356
File diff suppressed because it is too large
Load Diff
@@ -330,9 +330,9 @@
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/adapters/llm.py": {
|
||||
"mtime": 1787320797.2485664,
|
||||
"seen": 1787320818.2953389,
|
||||
"ast_hash": "a5cd6f66048ee1d443c2c91ae9947a14",
|
||||
"mtime": 1787321086.752706,
|
||||
"seen": 1787321205.5144775,
|
||||
"ast_hash": "21ac74a13ac5dfad7db498b17165f8b3",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"src/classifier.py": {
|
||||
@@ -654,9 +654,9 @@
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"README.md": {
|
||||
"mtime": 1787320219.5852203,
|
||||
"seen": 1787320239.0933797,
|
||||
"ast_hash": "ce59670fbaebc5e408a30a1009a58d12",
|
||||
"mtime": 1787321187.0812356,
|
||||
"seen": 1787321205.5201268,
|
||||
"ast_hash": "aedfaf7a245288227952a2e28e7e7b13",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"scripts/extract_article_contents.py": {
|
||||
@@ -916,5 +916,11 @@
|
||||
"seen": 1787320818.2967606,
|
||||
"ast_hash": "e5d98de814ceeecd8bd601a7c206e92d",
|
||||
"semantic_hash": ""
|
||||
},
|
||||
"tests/test_e2e_text_analysis_pipeline.py": {
|
||||
"mtime": 1787321086.751707,
|
||||
"seen": 1787321205.5156026,
|
||||
"ast_hash": "3a2d47f2ffcf8371ffdf90bb797b5346",
|
||||
"semantic_hash": ""
|
||||
}
|
||||
}
|
||||
+74
-6
@@ -1,19 +1,44 @@
|
||||
"""Optional LLM fallback adapter (Tier 3).
|
||||
|
||||
Disabled by default. Provides fallback interface for boundary disambiguation
|
||||
without requiring external API keys for core POC execution.
|
||||
supporting OpenAI and Gemini APIs with automatic .env loading and custom provider functions.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
from typing import Callable, Optional
|
||||
|
||||
from src.adapters.base import BaseNLPAdapter
|
||||
from src.models import ClassificationResult, DecisionCategory, ECPSnapshot
|
||||
|
||||
|
||||
def _load_env_file() -> None:
|
||||
"""Carrega variáveis do arquivo .env na raiz do projeto se existir."""
|
||||
for parent in [Path.cwd(), Path(__file__).parent.parent.parent]:
|
||||
env_file = parent / ".env"
|
||||
if env_file.is_file():
|
||||
try:
|
||||
for line in env_file.read_text(encoding="utf-8").splitlines():
|
||||
line = line.strip()
|
||||
if line and not line.startswith("#") and "=" in line:
|
||||
key, val = line.split("=", 1)
|
||||
key = key.strip()
|
||||
val = val.strip().strip("'\"")
|
||||
if key and key not in os.environ:
|
||||
os.environ[key] = val
|
||||
except Exception:
|
||||
pass
|
||||
break
|
||||
|
||||
|
||||
_load_env_file()
|
||||
|
||||
|
||||
class LLMFallbackAdapter(BaseNLPAdapter):
|
||||
"""Optional adapter for LLM fallback boundary disambiguation."""
|
||||
|
||||
@@ -23,13 +48,14 @@ class LLMFallbackAdapter(BaseNLPAdapter):
|
||||
api_key: str | None = None,
|
||||
provider_fn: Optional[Callable[[str], str]] = None,
|
||||
) -> None:
|
||||
self.model_name = model_name
|
||||
self.api_key = api_key or os.environ.get("OPENAI_API_KEY")
|
||||
self.model_name = os.environ.get("OPENAI_MODEL", model_name)
|
||||
self.openai_api_key = api_key or os.environ.get("OPENAI_API_KEY")
|
||||
self.gemini_api_key = os.environ.get("GEMINI_API_KEY") or os.environ.get("GOOGLE_API_KEY")
|
||||
self.provider_fn = provider_fn
|
||||
|
||||
def is_available(self) -> bool:
|
||||
"""Returns True if an API key or custom provider function is configured."""
|
||||
return bool(self.api_key or self.provider_fn)
|
||||
return bool(self.openai_api_key or self.gemini_api_key or self.provider_fn)
|
||||
|
||||
def evaluate_similarity(self, text: str, terms: list[str]) -> float:
|
||||
return 0.0
|
||||
@@ -135,12 +161,54 @@ Respond ONLY with a valid JSON object matching this schema:
|
||||
|
||||
prompt = self.build_prompt(ecp, content_md, initial_result)
|
||||
|
||||
# If custom provider function is provided (e.g. for testing or custom runtime)
|
||||
# 1. Custom provider function (testing or custom runtime)
|
||||
if self.provider_fn is not None:
|
||||
raw_response = self.provider_fn(prompt)
|
||||
return self._parse_llm_response(raw_response, initial_result)
|
||||
|
||||
# Stub default for POC when only API key string is present without active SDK
|
||||
# 2. Real OpenAI execution
|
||||
if self.openai_api_key:
|
||||
try:
|
||||
from openai import OpenAI
|
||||
|
||||
client = OpenAI(api_key=self.openai_api_key)
|
||||
response = client.chat.completions.create(
|
||||
model=self.model_name,
|
||||
messages=[{"role": "user", "content": prompt}],
|
||||
response_format={"type": "json_object"},
|
||||
temperature=0.0,
|
||||
)
|
||||
raw_text = response.choices[0].message.content or ""
|
||||
return self._parse_llm_response(raw_text, initial_result)
|
||||
except Exception as e:
|
||||
initial_result.warnings.append(f"OpenAI fallback invocation error: {e}")
|
||||
return None
|
||||
|
||||
# 3. Real Gemini execution via REST API
|
||||
if self.gemini_api_key:
|
||||
try:
|
||||
gemini_model = os.environ.get("GEMINI_MODEL", "gemini-2.5-flash")
|
||||
url = f"https://generativelanguage.googleapis.com/v1beta/models/{gemini_model}:generateContent?key={self.gemini_api_key}"
|
||||
payload = {
|
||||
"contents": [{"parts": [{"text": prompt}]}],
|
||||
"generationConfig": {
|
||||
"responseMimeType": "application/json",
|
||||
"temperature": 0.0,
|
||||
},
|
||||
}
|
||||
req = urllib.request.Request(
|
||||
url,
|
||||
data=json.dumps(payload).encode("utf-8"),
|
||||
headers={"Content-Type": "application/json"},
|
||||
)
|
||||
with urllib.request.urlopen(req, timeout=30) as resp:
|
||||
data = json.loads(resp.read().decode("utf-8"))
|
||||
raw_text = data["candidates"][0]["content"]["parts"][0]["text"]
|
||||
return self._parse_llm_response(raw_text, initial_result)
|
||||
except Exception as e:
|
||||
initial_result.warnings.append(f"Gemini fallback invocation error: {e}")
|
||||
return None
|
||||
|
||||
return None
|
||||
|
||||
def _parse_llm_response(
|
||||
|
||||
@@ -0,0 +1,388 @@
|
||||
"""
|
||||
Suíte de Testes E2E e de Integração Completa para Análise de Texto e Classificação de Inerência (QA Sênior).
|
||||
|
||||
Valida todo o funil de análise de texto:
|
||||
1. Sucesso no NLP Determinístico (Tier 1 DIRECT_INHERENT com bypass de LLM).
|
||||
2. Insucesso / Rejeição no NLP (Tier 1 NOT_RELATED por âncoras negativas e homônimos).
|
||||
3. Ambiguidade / Limiar detectada no NLP e resolvida com sucesso no LLM (Tier 3 Upgrade).
|
||||
4. Ambiguidade confirmada pelo LLM como TANGENTIAL (Tier 3 Confirmation).
|
||||
5. Insucesso / Falha de API de LLM com degradação graciosa para Tier 1.
|
||||
6. Cobertura Multilíngue E2E nos 6 idiomas (PT, EN, ES, DE, IT, FR).
|
||||
7. Execução E2E via CLI subprocess com contratos de entrada, saída e flags.
|
||||
8. Chamada real ao vivo a provedores de LLM (OpenAI/Gemini) quando credenciais estiverem disponíveis.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import subprocess
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from src.adapters.llm import LLMFallbackAdapter
|
||||
from src.classifier import InherenceClassifier
|
||||
from src.models import (
|
||||
ClassificationResult,
|
||||
DecisionCategory,
|
||||
ECPSnapshot,
|
||||
RelatedEntity,
|
||||
)
|
||||
|
||||
CLASSIFY_CLI = Path(__file__).parent.parent / "classify.py"
|
||||
|
||||
|
||||
# ==============================================================================
|
||||
# Fixtures e Helpers para o Funil de Teste E2E
|
||||
# ==============================================================================
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def ecp_river_plate() -> ECPSnapshot:
|
||||
"""Fixture ECP oficial para o Club Atlético River Plate."""
|
||||
return ECPSnapshot(
|
||||
target_entity_id="ecp_river_plate",
|
||||
target_name="Club Atlético River Plate",
|
||||
aliases=[
|
||||
"Club Atlético River Plate",
|
||||
"River Plate",
|
||||
"River",
|
||||
"El Millonario",
|
||||
"La Banda",
|
||||
"CARP",
|
||||
],
|
||||
domain="Futebol / Esportes",
|
||||
anchors=[
|
||||
"fútbol",
|
||||
"Copa Libertadores",
|
||||
"Libertadores",
|
||||
"Copa Sudamericana",
|
||||
"Sudamericana",
|
||||
"Monumental",
|
||||
"Estadio Monumental",
|
||||
"Eduardo Coudet",
|
||||
"Coudet",
|
||||
"Nicolás Otamendi",
|
||||
"Otamendi",
|
||||
"Rafael Santos Borré",
|
||||
],
|
||||
negative_anchors=[
|
||||
"River Plate de Montevideo",
|
||||
"River Plate de Asunción",
|
||||
"River de Piauí",
|
||||
"Rio da Prata",
|
||||
"Bacia do Rio da Prata",
|
||||
],
|
||||
related_entities=[
|
||||
RelatedEntity(
|
||||
entity_id="estadio_monumental",
|
||||
name="Estadio Mâs Monumental",
|
||||
relation_type="HOME_VENUE_OF",
|
||||
weight=0.95,
|
||||
aliases=["Monumental", "El Monumental"],
|
||||
),
|
||||
RelatedEntity(
|
||||
entity_id="copa_sudamericana",
|
||||
name="Copa Sudamericana",
|
||||
relation_type="COMPETES_IN",
|
||||
weight=0.85,
|
||||
aliases=["Sudamericana"],
|
||||
),
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
# ==============================================================================
|
||||
# 1. Funil de Sucesso NLP Determinístico (Tier 1)
|
||||
# ==============================================================================
|
||||
|
||||
|
||||
def test_funnel_nlp_deterministic_success(ecp_river_plate: ECPSnapshot):
|
||||
"""
|
||||
Cenário 1: Artigo com alta densidade de âncoras do River Plate.
|
||||
Oráculo: Decisão DIRECT_INHERENT, confiança alta (>=0.95), LLM não é chamado.
|
||||
"""
|
||||
content = """
|
||||
# River Plate vence com autoridade na Copa Sudamericana
|
||||
Em noite histórica no Estadio Monumental, o River dominou a partida sob o comando de Eduardo Coudet.
|
||||
Otamendi e Borré marcaram os gols que garantiram a classificação na Sudamericana.
|
||||
"""
|
||||
llm_called = {"status": False}
|
||||
|
||||
def mock_llm(prompt: str) -> str:
|
||||
llm_called["status"] = True
|
||||
return json.dumps({"decision": "DIRECT_INHERENT", "confidence": 0.99})
|
||||
|
||||
adapter = LLMFallbackAdapter(provider_fn=mock_llm)
|
||||
classifier = InherenceClassifier(enable_llm=True, llm_adapter=adapter)
|
||||
|
||||
result = classifier.classify(ecp_river_plate, content)
|
||||
|
||||
assert result.decision == DecisionCategory.DIRECT_INHERENT
|
||||
assert result.is_inherent is True
|
||||
assert result.confidence >= 0.95
|
||||
assert "River Plate" in result.matched_anchors or "River" in result.matched_anchors
|
||||
assert len(result.graph_matches) >= 1
|
||||
# Otimização de custo: LLM NÃO deve ser chamado em casos determinísticos claros
|
||||
assert llm_called["status"] is False
|
||||
|
||||
|
||||
# ==============================================================================
|
||||
# 2. Funil de Insucesso / Rejeição NLP (Tier 1 Negativas e Homônimos)
|
||||
# ==============================================================================
|
||||
|
||||
|
||||
def test_funnel_nlp_deterministic_rejection_homonym(ecp_river_plate: ECPSnapshot):
|
||||
"""
|
||||
Cenário 2: Artigo sobre a Bacia do Rio da Prata ou clube homônimo do Uruguai.
|
||||
Oráculo: Decisão NOT_RELATED, is_inherent=False, âncoras negativas detectadas.
|
||||
"""
|
||||
content = """
|
||||
# Expedição ambiental navega pela Bacia do Rio da Prata
|
||||
Pesquisadores mapearam a biodiversidade fluvial e os sedimentos do Rio da Prata durante o verão.
|
||||
"""
|
||||
classifier = InherenceClassifier(enable_llm=False)
|
||||
result = classifier.classify(ecp_river_plate, content)
|
||||
|
||||
assert result.decision == DecisionCategory.NOT_RELATED
|
||||
assert result.is_inherent is False
|
||||
assert any("Rio da Prata" in neg for neg in result.negative_matches)
|
||||
assert "Negative anchor" in result.rationale
|
||||
|
||||
|
||||
# ==============================================================================
|
||||
# 3. Funil de Ambiguidade NLP -> Resolução com Sucesso no LLM (Tier 3)
|
||||
# ==============================================================================
|
||||
|
||||
|
||||
def test_funnel_nlp_ambiguity_resolved_by_llm_upgrade(ecp_river_plate: ECPSnapshot):
|
||||
"""
|
||||
Cenário 3: Menção isolada do clube ('River') em contexto com poucas âncoras explícitas.
|
||||
Tier 1 preliminar: TANGENTIAL (baixa densidade).
|
||||
LLM Fallback: Analisa o contexto profundo e eleva para DIRECT_INHERENT.
|
||||
"""
|
||||
ambiguous_content = """
|
||||
# Bastidores do mercado sul-americano
|
||||
A diretoria do River finalizou os últimos detalhes contratuais para a renovação de jovens promessas.
|
||||
"""
|
||||
mock_llm_response = json.dumps(
|
||||
{
|
||||
"analysis_summary": "O artigo trata da gestão de elenco e renovações contratuais do clube River Plate.",
|
||||
"decision": "DIRECT_INHERENT",
|
||||
"confidence": 0.94,
|
||||
"rationale": "A análise contextual profunda comprova que a matéria é focada na administração do River Plate.",
|
||||
}
|
||||
)
|
||||
|
||||
adapter = LLMFallbackAdapter(provider_fn=lambda prompt: mock_llm_response)
|
||||
classifier = InherenceClassifier(enable_llm=True, llm_adapter=adapter)
|
||||
|
||||
result = classifier.classify(ecp_river_plate, ambiguous_content)
|
||||
|
||||
assert result.decision == DecisionCategory.DIRECT_INHERENT
|
||||
assert result.is_inherent is True
|
||||
assert result.confidence == 0.94
|
||||
assert "[Tier 3 LLM]" in result.rationale
|
||||
assert "[Tier 3 LLM Override applied]" in result.warnings
|
||||
|
||||
|
||||
# ==============================================================================
|
||||
# 4. Funil de Ambiguidade NLP -> Confirmação de Tangencial no LLM
|
||||
# ==============================================================================
|
||||
|
||||
|
||||
def test_funnel_nlp_ambiguity_confirmed_tangential_by_llm(ecp_river_plate: ECPSnapshot):
|
||||
"""
|
||||
Cenário 4: Menção metafórica ou turística a um local próximo.
|
||||
Tier 1 preliminar: TANGENTIAL.
|
||||
LLM Fallback: Confirma que é meramente periférico/ilustrativo.
|
||||
"""
|
||||
tangential_content = """
|
||||
# Melhores restaurantes do bairro de Núñez em Buenos Aires
|
||||
Ao visitar a capital portenha, próximo de onde fica o River, você encontra excelentes opções gastronômicas.
|
||||
"""
|
||||
mock_llm_response = json.dumps(
|
||||
{
|
||||
"analysis_summary": "Guia gastronômico sobre o bairro de Núñez com citação geográfica casual ao clube.",
|
||||
"decision": "TANGENTIAL",
|
||||
"confidence": 0.96,
|
||||
"rationale": "A entidade é usada apenas como ponto de referência geográfica em um artigo sobre restaurantes.",
|
||||
}
|
||||
)
|
||||
|
||||
adapter = LLMFallbackAdapter(provider_fn=lambda prompt: mock_llm_response)
|
||||
classifier = InherenceClassifier(enable_llm=True, llm_adapter=adapter)
|
||||
|
||||
result = classifier.classify(ecp_river_plate, tangential_content)
|
||||
|
||||
assert result.decision == DecisionCategory.TANGENTIAL
|
||||
assert result.is_inherent is False
|
||||
assert result.confidence == 0.96
|
||||
assert "[Tier 3 LLM]" in result.rationale
|
||||
|
||||
|
||||
# ==============================================================================
|
||||
# 5. Funil de Insucesso / Degradação Graciosa em Falha do LLM
|
||||
# ==============================================================================
|
||||
|
||||
|
||||
def test_funnel_llm_failure_graceful_degradation(ecp_river_plate: ECPSnapshot):
|
||||
"""
|
||||
Cenário 5: LLM configurado, caso ambíguo, mas a API externa sofre timeout/500.
|
||||
Oráculo: Mantém o resultado do Tier 1 determinístico com warning detalhado e sem quebrar.
|
||||
"""
|
||||
|
||||
def broken_llm(prompt: str) -> str:
|
||||
raise TimeoutError("Conexão com serviço de LLM excedeu 30 segundos.")
|
||||
|
||||
adapter = LLMFallbackAdapter(provider_fn=broken_llm)
|
||||
classifier = InherenceClassifier(enable_llm=True, llm_adapter=adapter)
|
||||
|
||||
content = "O River esteve presente no evento de inauguração da praça."
|
||||
result = classifier.classify(ecp_river_plate, content)
|
||||
|
||||
# Mantém o Tier 1 determinístico
|
||||
assert result.decision == DecisionCategory.TANGENTIAL
|
||||
assert result.is_inherent is False
|
||||
assert any("LLM fallback failed" in w for w in result.warnings)
|
||||
|
||||
|
||||
# ==============================================================================
|
||||
# 6. Cobertura Multilíngue nos 6 Idiomas (PT, EN, ES, DE, IT, FR)
|
||||
# ==============================================================================
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"lang_code,content,expected_lang",
|
||||
[
|
||||
("pt", "# Petrobras anuncia perfuração no pré-sal com tecnologia nacional.", "pt"),
|
||||
("en", "# Apple unveils new generative AI features for upcoming devices.", "en"),
|
||||
(
|
||||
"es",
|
||||
"# River Plate prepara su viaje a Bogotá para disputar el torneo continental.",
|
||||
"es",
|
||||
),
|
||||
(
|
||||
"de",
|
||||
"# Volkswagen investiert Milliarden in neue Batterie-Fabriken in Deutschland.",
|
||||
"de",
|
||||
),
|
||||
("it", "# Ferrari conquista la pole position nel Gran Premio di Monza.", "it"),
|
||||
(
|
||||
"fr",
|
||||
"# L'entreprise TotalEnergies accélère ses investissements solaires en France.",
|
||||
"fr",
|
||||
),
|
||||
],
|
||||
)
|
||||
def test_funnel_multilingual_language_detection(
|
||||
lang_code: str, content: str, expected_lang: str, ecp_river_plate: ECPSnapshot
|
||||
):
|
||||
"""Garante a identificação precisa de idioma e integridade nos 6 idiomas suportados."""
|
||||
classifier = InherenceClassifier(enable_llm=False)
|
||||
result = classifier.classify(ecp_river_plate, content)
|
||||
assert result.detected_language == expected_lang
|
||||
|
||||
|
||||
# ==============================================================================
|
||||
# 7. Execução E2E via CLI Subprocess
|
||||
# ==============================================================================
|
||||
|
||||
|
||||
def test_funnel_cli_subprocess_end_to_end(tmp_path: Path):
|
||||
"""Valida o contrato CLI completo classify.py com saída em arquivo JSON e flags ativas."""
|
||||
ecp_path = tmp_path / "ecp.json"
|
||||
ecp_path.write_text(
|
||||
json.dumps(
|
||||
{
|
||||
"target_entity_id": "ecp_test_e2e",
|
||||
"target_name": "Clube Teste",
|
||||
"aliases": ["Clube Teste", "Clube"],
|
||||
"domain": "Esportes",
|
||||
"anchors": ["campeonato", "vitória", "torneio"],
|
||||
}
|
||||
),
|
||||
encoding="utf-8",
|
||||
)
|
||||
doc_path = tmp_path / "artigo.md"
|
||||
doc_path.write_text(
|
||||
"# Clube Teste comemora vitória histórica no campeonato\n\nEquipe foi campeã do torneio.",
|
||||
encoding="utf-8",
|
||||
)
|
||||
out_path = tmp_path / "resultado.json"
|
||||
|
||||
res = subprocess.run(
|
||||
[
|
||||
sys.executable,
|
||||
str(CLASSIFY_CLI),
|
||||
"--ecp",
|
||||
str(ecp_path),
|
||||
"--content",
|
||||
str(doc_path),
|
||||
"--output",
|
||||
str(out_path),
|
||||
"--enable-llm",
|
||||
],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
)
|
||||
|
||||
assert res.returncode == 0, f"Erro na CLI: {res.stderr}"
|
||||
assert out_path.exists()
|
||||
|
||||
payload = json.loads(out_path.read_text(encoding="utf-8"))
|
||||
assert payload["decision"] == "DIRECT_INHERENT"
|
||||
assert payload["is_inherent"] is True
|
||||
assert payload["confidence"] >= 0.85
|
||||
assert isinstance(payload["matched_anchors"], list)
|
||||
assert isinstance(payload["evidence"], list)
|
||||
|
||||
|
||||
# ==============================================================================
|
||||
# 8. Teste Live Opt-In com API Real (OpenAI / Gemini) se .env Estiver Presente
|
||||
# ==============================================================================
|
||||
|
||||
|
||||
def test_funnel_live_api_execution_if_configured():
|
||||
"""
|
||||
Executa chamada ao vivo contra OpenAI ou Gemini caso OPENAI_API_KEY ou GEMINI_API_KEY
|
||||
esteja configurada no ambiente ou no arquivo .env.
|
||||
"""
|
||||
adapter = LLMFallbackAdapter()
|
||||
if not (adapter.openai_api_key or adapter.gemini_api_key):
|
||||
pytest.skip(
|
||||
"Chaves de API reais (OPENAI_API_KEY ou GEMINI_API_KEY) não configuradas no .env"
|
||||
)
|
||||
|
||||
ecp = ECPSnapshot(
|
||||
target_entity_id="ecp_live_test",
|
||||
target_name="Club Atlético River Plate",
|
||||
aliases=["River Plate", "River"],
|
||||
domain="Futebol",
|
||||
anchors=["Monumental", "Libertadores"],
|
||||
)
|
||||
initial_res = ClassificationResult(
|
||||
decision=DecisionCategory.TANGENTIAL,
|
||||
is_inherent=False,
|
||||
confidence=0.40,
|
||||
detected_language="es",
|
||||
matched_anchors=["River"],
|
||||
negative_matches=[],
|
||||
graph_matches=[],
|
||||
evidence=["River"],
|
||||
rationale="Passing mention detected by Tier 1.",
|
||||
warnings=[],
|
||||
)
|
||||
|
||||
# Texto de teste para a API ao vivo
|
||||
content = "O River Plate empatou em 1 a 1 em Bogotá com gols de Otamendi na Copa Sul-Americana."
|
||||
|
||||
refined = adapter.disambiguate(ecp, content, initial_res)
|
||||
assert refined is not None
|
||||
assert refined.decision in [
|
||||
DecisionCategory.DIRECT_INHERENT,
|
||||
DecisionCategory.CONTEXTUAL_INHERENT,
|
||||
]
|
||||
assert refined.is_inherent is True
|
||||
assert "[Tier 3 LLM]" in refined.rationale
|
||||
Reference in New Issue
Block a user