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
@@ -45,13 +45,13 @@
  "43": "2. Basic CLI Usage Examples",
  "44": "2. Standard Streams & Exit Codes",
  "45": "ClassificationResult",
-  "46": "test_adversarial.py",
-  "47": "InherenceClassifier",
-  "48": "test_convert_article_to_markdown.py",
+  "46": "ECPSnapshot",
+  "47": "LLMFallbackAdapter",
+  "48": "classifier.py",
  "49": "content_northvolt_de.md",
  "50": "content_presal_pt.md",
  "51": "content_tangential_es.md",
-  "52": "adapters/__init__.py",
+  "52": "config.py",
  "53": "src/__init__.py",
  "54": "de/contextual.md",
  "55": "de/direct.md",
@@ -96,10 +96,10 @@
  "94": "Specification Quality Checklist: Google News Headlines Extractor",
  "95": "CLI Contract: Google News Headlines Extractor",
  "96": "readiness.md",
-  "97": "🧠 TextNLPClassifierApp",
+  "97": "5. 📝 Conversor de Artigo JSON para Markdown",
  "98": "Extraction Pipeline Checklist: Article Content Multi-Engine Extractor",
-  "99": "parametrize",
-  "100": "Path",
+  "99": "ModelGatewayClient",
+  "100": "SQLiteStore",
  "101": "main",
  "102": "Feature Specification: Multilingual NLP Entity Inherence Classifier (POC)",
  "103": "4. Requisitos Funcionais (FR)",
@@ -148,29 +148,184 @@
  "146": "Specification Quality Checklist: Convert Article JSON to Markdown",
  "147": "CLI Contract: `convert_article_to_markdown.py`",
  "148": "9. Interface CLI",
-  "149": "sample_rss_xml",
+  "149": "test_convert_article_to_markdown.py",
  "150": "13. Estratégia de testes",
  "151": "6. Contrato de entrada",
-  "152": "ECPSnapshot",
+  "152": "test_models.py",
  "153": "convert_html_to_markdown",
-  "154": "JSON Schema Contract: Deterministic Article Content Selection",
+  "154": "properties",
  "155": "5. Escopo",
  "156": "Los puntajes de River vs. Independiente Santa Fe, por la Copa Sudamericana - TyC Sports",
  "157": "valid_newspaper4k.md",
  "158": "valid_readability.md",
-  "159": "test_normalize_list_author_url_filtering",
-  "160": "test_normalize_date_invalid_and_placeholders",
-  "161": "test_normalize_list_deduplication_preserves_case_and_order",
-  "162": "test_normalize_date_iso_8601_variants",
-  "163": "test_metadata_priority_original_url_all_fallbacks",
-  "164": "test_normalize_scalar_non_string_types",
-  "165": "test_e2e_text_analysis_pipeline.py",
-  "166": "remove_duplicate_initial_h1",
-  "167": "test_normalize_scalar_whitespace_collapsing",
-  "168": "LLMFallbackAdapter",
-  "169": "test_funnel_cli_subprocess_end_to_end",
-  "170": "test_models.py",
-  "171": "extract_evidence_snippets",
-  "172": ".classify",
-  "173": "🧪 Documentação da Suíte de Testes Automatizados"
+  "159": "consolidate.py",
+  "160": "run_preflight_checks",
+  "161": "adapter.py",
+  "162": "validate_and_extract_enrichment",
+  "163": "candidate/parser.py",
+  "164": "hygiene/harness.py",
+  "165": "SanitizedJsonLogger",
+  "166": "InputSizeExceededError",
+  "167": "CandidateObject",
+  "168": "enum",
+  "169": "Plano de testes e evals — Runtime de consolidação de artigos",
+  "170": "Especificação de prompt, contexto e harness — Runtime",
+  "171": "ExecutionStateMachine",
+  "172": "Implementation Tasks: Article Consolidation and Hygiene Runtime",
+  "173": "🧪 Documentação da Suíte de Testes Automatizados",
+  "174": "properties",
+  "175": "repair-operations.schema.json",
+  "176": "Functional Requirements",
+  "177": "test_equivalence_mapping.py",
+  "178": "enrichment-response.schema.json",
+  "179": "create_manifest_dict",
+  "180": "Catálogo de métricas e KPIs — Runtime de consolidação de artigos",
+  "181": "article_content_hygiene",
+  "182": "._get_connection",
+  "183": "Documento de Arquitetura — Runtime de consolidação de artigos",
+  "184": "null",
+  "185": "Runbook de produção — Runtime de consolidação de artigos",
+  "186": "article_content_hygiene",
+  "187": "properties",
+  "188": "properties",
+  "189": "PRD — Runtime de consolidação e higienização de artigos",
+  "190": "required",
+  "191": "properties",
+  "192": "type",
+  "193": "properties",
+  "194": "build_minimal_hygiene_projection",
+  "195": "check_zero_regex.py",
+  "196": "properties",
+  "197": "runtime-config.schema.json",
+  "198": "properties",
+  "199": "object",
+  "200": "candidates-payload.schema.json",
+  "201": "limits",
+  "202": "langfuse",
+  "203": "string",
+  "204": "type",
+  "205": "CLI Interface Contract: Article Consolidation and Hygiene Runtime",
+  "206": "2. Entity Definitions",
+  "207": "3. Concrete Architectural & Technical Decisions",
+  "208": "Requirements Readiness Checklist: Article Consolidation and Hygiene Runtime",
+  "209": "object",
+  "210": "null",
+  "211": "properties",
+  "212": "calculate_execution_fingerprint",
+  "213": "model_versions",
+  "214": "3. Operational Execution Scenarios",
+  "215": "type",
+  "216": "test_cli_subprocess_pipeline.py",
+  "217": "clean_body_images",
+  "218": "ecp",
+  "219": "paths",
+  "220": "properties",
+  "221": "properties",
+  "222": "properties",
+  "223": "required",
+  "224": "required",
+  "225": "kept_block_ids",
+  "226": "parametrize",
+  "227": "4. 🎯 Seletor Determinístico de Conteúdo de Artigos",
+  "228": "1. Operational Commands",
+  "229": "sqlite",
+  "230": "required",
+  "231": "pricing",
+  "232": "article-input.schema.json",
+  "233": "properties",
+  "234": "enum",
+  "235": "required",
+  "236": "Implementation Plan: Article Consolidation and Hygiene Runtime",
+  "237": "verify_all_11_invariants",
+  "238": "enum",
+  "239": "required",
+  "240": "manifest-output.schema.json",
+  "241": "Prompts Versioned Contract: Article Consolidation and Hygiene Runtime",
+  "242": "6. 🚀 Runtime de Consolidação e Higienização de Artigos (006-article-consolidation-runtime)",
+  "243": "13. Parsing estrutural sem regex",
+  "244": "metadata_candidates",
+  "245": "enum",
+  "246": "required",
+  "247": "enum",
+  "248": "ecp-snapshot.schema.json",
+  "249": "hygiene-response.schema.json",
+  "250": "🧠 TextNLPClassifierApp",
+  "251": "ADR-003 — Usar orquestração explícita em Python, sem LangChain ou LangGraph",
+  "252": "required",
+  "253": "Specification Quality Checklist: Article Consolidation and Hygiene Runtime",
+  "254": "enum",
+  "255": "enum",
+  "256": "1. 🧠 Classificador de Conteúdo e Inerência (NLP / LLM / ECP)",
+  "257": "10. Contrato de saída",
+  "258": "14. Higienização por LLM",
+  "259": "4. Regras mandatórias",
+  "260": "8. Contrato de entrada do artigo",
+  "261": "18. Integração ECP",
+  "262": "7. Orquestração",
+  "263": "ADR-001 — Separar runtime e self-healing",
+  "264": "ADR-002 — Iniciar o runtime após a seleção do extrator",
+  "265": "ADR-004 — Gateway agnóstico com apenas modelos baratos no runtime",
+  "266": "ADR-005 — Proibir regex e palavras-chave manuais em decisões textuais",
+  "267": "ADR-006 — LLM seleciona evidências e propõe reparos, não regenera o artigo",
+  "268": "ADR-007 — Tornar o ECP obrigatório antes de toda saída editorial",
+  "269": "ADR-008 — Langfuse no runtime e Promptfoo no CI",
+  "270": "ADR-009 — Persistir estado em SQLite e saídas no filesystem",
+  "271": "ADR-010 — Produzir resultado estruturado sempre e Markdown condicionalmente",
+  "272": "ADR-011 — Definir SLOs de custo e latência a partir de staging",
+  "273": "7. Checklist de release",
+  "274": "eval_runner.py",
+  "275": "ecp-profile.schema.json",
+  "276": "prompt_versions",
+  "277": "12. Preparação determinística",
+  "278": "15. Pequenos reparos textuais",
+  "279": "9. Contrato do ECP",
+  "280": "15. Higienização extrativa",
+  "281": "16. Pequenos reparos",
+  "282": "20. Model Gateway",
+  "283": "23. Observabilidade",
+  "284": "3. Limites do sistema",
+  "285": "9. Política de dependências",
+  "286": "12. Monitoramento",
+  "287": "14. Reprocessamento",
+  "288": "16. Falha do provider primário",
+  "289": "21. Falha do SQLite",
+  "290": "6. Configuração obrigatória",
+  "291": "build_release_metadata.py",
+  "292": "removal_reasons",
+  "293": "kept_image_ids",
+  "296": "test_prompts_contract.py",
+  "298": "Release Quality Summary Report",
+  "299": "Comandos e Utilitários CLI",
+  "300": "13. Candidatos e proveniência",
+  "301": "16. Imagens e links",
+  "302": "17. Gate ECP",
+  "303": "18. Enriquecimento",
+  "304": "5. Escopo",
+  "305": "14. Modelo de candidatos",
+  "306": "22. Renderer e arquivos",
+  "307": "Architecture Decision Records — Runtime de consolidação de artigos",
+  "308": "15. Falha de validação de entrada",
+  "309": "17. Falha semântica ou de grounding",
+  "310": "18. Falha do ECP",
+  "311": "20. Falha do Langfuse",
+  "312": "22. Falha de filesystem ou disco",
+  "313": "26. Rollback manual",
+  "314": "ci_check.py",
+  "315": "prepare_reference_20.py",
+  "316": "test_contract_parity.py",
+  "317": "test_zero_regex_enforcement.py",
+  "318": "sample_rss_xml",
+  "319": "runtime/__init__.py",
+  "320": "adapters/__init__.py",
+  "321": "tools/__init__.py",
+  "322": "test_normalize_list_author_url_filtering",
+  "323": "test_normalize_list_deduplication_preserves_case_and_order",
+  "324": "test_normalize_date_iso_8601_variants",
+  "325": "test_normalize_date_invalid_and_placeholders",
+  "326": "test_metadata_priority_original_url_all_fallbacks",
+  "327": "test_normalize_scalar_whitespace_collapsing",
+  "328": "test_normalize_scalar_non_string_types",
+  "329": "2. 📰 Extrator de Manchetes do Google News",
+  "331": "⚙️ Instalação e Setup",
+  "332": "3. 📄 Extrator e Parser Multimotor de Artigos"
 }