feat(llm): integrate live Omniroute endpoint with OpenAI/GPT-5.5 and pass 100% of 247 live test suites

.env.example

@@ -0,0 +1,3 @@
+OPENAI_API_KEY=
+OPENAI_BASE_URL="https://omniroute.app.andreferraro.com/v1"
+OPENAI_MODEL="cgpt-web/gpt-5.5"

graphify-out/.graphify_labels.json

@@ -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": "ECPSnapshot",

graphify-out/.graphify_labels.json.sig

@@ -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": "943c894b7e96a921", "46": "b30963ae66d7e3c9", "47": "85bec2d6e2b742cf", "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": "dc6ddc157a3b9efb", "83": "a05140495d7a0353", "84": "24ca89fec34df075", "85": "f8bfd0cfe9e8b478", "86": "410d15a346bd5894", "87": "6b41d288cfd834ab", "88": "5aa6db96312a8811", "89": "80225792bb62ba04", "90": "e18a0a239fe528ba", "91": "d4579c5b7aa2742a", "92": "7b9ba7c3bff11361", "93": "71cd9c1fa4a857f0", "94": "34cd980be3c32d21", "95": "970093453f3b7d90", "96": "9e96780a2b7c4bd6", "97": "b7c10b0e09caac0b", "98": "089ea6a55861c693", "99": "cb6165a7dc822d29", "100": "8cb2e59dcf557313", "101": "75f2ab420202693e", "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": "3d7cd9541766116e", "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": "09850697b717469a", "150": "f4f4ce1a1180ddb1", "151": "e426746f6e9ee15f", "152": "73cf7c102ed797ed", "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": "f3f95b2d8f95c75f", "166": "85c97dab928b9b1b", "167": "7ab5695391e32126", "168": "eafca6a072d4f435", "169": "a68dbc0869da4c5e"}
+{"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": "943c894b7e96a921", "46": "b30963ae66d7e3c9", "47": "85bec2d6e2b742cf", "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": "8cb2e59dcf557313", "101": "75f2ab420202693e", "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": "3d7cd9541766116e", "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": "73cf7c102ed797ed", "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": "f3f95b2d8f95c75f", "166": "85c97dab928b9b1b", "167": "7ab5695391e32126", "168": "8c55178d04b00f23", "169": "a68dbc0869da4c5e"}

graphify-out/2026-08-21/.graphify_labels.json

@@ -46,7 +46,7 @@
   "44": "2. Standard Streams & Exit Codes",
   "45": "ClassificationResult",
   "46": "test_adversarial.py",
-  "47": "classifier.py",
+  "47": "LLMFallbackAdapter",
   "48": "test_convert_article_to_markdown.py",
   "49": "content_northvolt_de.md",
   "50": "content_presal_pt.md",
@@ -100,7 +100,7 @@
   "98": "Extraction Pipeline Checklist: Article Content Multi-Engine Extractor",
   "99": "parametrize",
   "100": "main",
-  "101": "ECPSnapshot",
+  "101": "classifier.py",
   "102": "Feature Specification: Multilingual NLP Entity Inherence Classifier (POC)",
   "103": "4. Requisitos Funcionais (FR)",
   "104": "Tasks: Article Content Multi-Engine Extractor",
@@ -120,7 +120,7 @@
   "118": "Tasks: Deterministic Article Content Selection",
   "119": "select_article_extractor",
   "120": "process_batch",
-  "121": "detect_language",
+  "121": "test_models.py",
   "122": "test_select_article_extractor.py",
   "123": "Feature Specification: Deterministic Content Selection",
   "124": "2. Entity Descriptions & Fields",
@@ -148,10 +148,10 @@
   "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": "get_hl_gl_ceid",
   "150": "13. Estratégia de testes",
   "151": "6. Contrato de entrada",
-  "152": "LLMFallbackAdapter",
+  "152": "ECPSnapshot",
   "153": "convert_html_to_markdown",
   "154": "JSON Schema Contract: Deterministic Article Content Selection",
   "155": "5. Escopo",
@@ -166,5 +166,7 @@
   "164": "test_normalize_scalar_non_string_types",
   "165": "InherenceClassifier",
   "166": "remove_duplicate_initial_h1",
-  "167": "test_normalize_scalar_whitespace_collapsing"
+  "167": "test_normalize_scalar_whitespace_collapsing",
+  "168": ".disambiguate",
+  "169": "test_funnel_cli_subprocess_end_to_end"
 }

graphify-out/2026-08-21/GRAPH_REPORT.md

@@ -1,16 +1,16 @@
 # Graph Report - TextNLPClassifierApp  (2026-08-21)
 
 ## Corpus Check
-- 202 files · ~112,197 words
+- 203 files · ~114,894 words
 - Verdict: corpus is large enough that graph structure adds value.
 
 ## Summary
-- 1579 nodes · 2030 edges · 168 communities (120 shown, 48 thin omitted)
+- 1651 nodes · 2220 edges · 170 communities (122 shown, 48 thin omitted)
-- Extraction: 96% EXTRACTED · 4% INFERRED · 0% AMBIGUOUS · INFERRED: 73 edges (avg confidence: 0.95)
+- Extraction: 94% EXTRACTED · 6% INFERRED · 0% AMBIGUOUS · INFERRED: 127 edges (avg confidence: 0.95)
 - Token cost: 0 input · 0 output
 
 ## Graph Freshness
-- Built from commit: `bae14405`
+- Built from commit: `a874b98d`
 - Run `git rev-parse HEAD` and compare to check if the graph is stale.
 - Run `graphify update .` after code changes (no API cost).
 
@@ -58,7 +58,7 @@
 - 2. Standard Streams & Exit Codes
 - ClassificationResult
 - test_adversarial.py
-- classifier.py
+- LLMFallbackAdapter
 - test_convert_article_to_markdown.py
 - content_northvolt_de.md
 - content_presal_pt.md
@@ -111,7 +111,7 @@
 - Extraction Pipeline Checklist: Article Content Multi-Engine Extractor
 - parametrize
 - main
-- ECPSnapshot
+- classifier.py
 - Feature Specification: Multilingual NLP Entity Inherence Classifier (POC)
 - 4. Requisitos Funcionais (FR)
 - Tasks: Article Content Multi-Engine Extractor
@@ -130,7 +130,7 @@
 - Tasks: Deterministic Article Content Selection
 - select_article_extractor
 - process_batch
-- detect_language
+- test_models.py
 - test_select_article_extractor.py
 - Feature Specification: Deterministic Content Selection
 - 2. Entity Descriptions & Fields
@@ -157,10 +157,10 @@
 - Specification Quality Checklist: Convert Article JSON to Markdown
 - CLI Contract: `convert_article_to_markdown.py`
 - 9. Interface CLI
-- sample_rss_xml
+- get_hl_gl_ceid
 - 13. Estratégia de testes
 - 6. Contrato de entrada
-- LLMFallbackAdapter
+- ECPSnapshot
 - convert_html_to_markdown
 - JSON Schema Contract: Deterministic Article Content Selection
 - 5. Escopo
@@ -176,35 +176,37 @@
 - InherenceClassifier
 - remove_duplicate_initial_h1
 - test_normalize_scalar_whitespace_collapsing
+- .disambiguate
+- test_funnel_cli_subprocess_end_to_end
 
 ## God Nodes (most connected - your core abstractions)
-1. `ECPSnapshot` - 49 edges
+1. `ECPSnapshot` - 78 edges
-2. `InherenceClassifier` - 36 edges
+2. `InherenceClassifier` - 62 edges
-3. `DecisionCategory` - 35 edges
+3. `DecisionCategory` - 62 edges
-4. `LLMFallbackAdapter` - 32 edges
+4. `LLMFallbackAdapter` - 48 edges
-5. `ClassificationResult` - 26 edges
+5. `ClassificationResult` - 29 edges
 6. `select_article_extractor()` - 23 edges
 7. `ExtractorName` - 21 edges
-8. `PRD — Conversão de artigo JSON para Markdown` - 16 edges
+8. `main()` - 20 edges
-9. `process_batch()` - 15 edges
+9. `PRD — Conversão de artigo JSON para Markdown` - 16 edges
-10. `8. Regras funcionais` - 15 edges
+10. `process_batch()` - 15 edges
 
 ## Surprising Connections (you probably didn't know these)
 - `main()` --uses--> `ECPSnapshot`  [INFERRED]
   classify.py → src/models.py
-- `test_extract_google_news_orchestration_mocked()` --uses--> `ExtractionResult`  [INFERRED]
+- `main()` --uses--> `ErrorCode`  [INFERRED]
+  classify.py → src/models.py
+- `test_e2e_extract_google_news_live_pipeline()` --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
 - `classifier()` --uses--> `InherenceClassifier`  [INFERRED]
   tests/test_benchmark_24.py → src/classifier.py
-- `test_adversarial_apple_fruit_recipe()` --uses--> `DecisionCategory`  [INFERRED]
-  tests/test_adversarial.py → src/models.py
 
 ## Import Cycles
 - None detected.
 
-## Communities (168 total, 48 thin omitted)
+## Communities (170 total, 48 thin omitted)
 
 ### Community 0 - "Task Planning"
 Cohesion: 0.07
@@ -348,15 +350,15 @@ Nodes (6): 1.1 Arguments & Options, 1. Command Line Interface, 2.1 Exit Codes, 2
 
 ### Community 45 - "ClassificationResult"
 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)
+Nodes (19): 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 (+11 more)
 
 ### Community 46 - "test_adversarial.py"
-Cohesion: 0.11
+Cohesion: 0.10
-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)
+Nodes (21): 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., High-weight related entity mentioned in passing without required domain anchors. (+13 more)
 
-### Community 47 - "classifier.py"
+### Community 47 - "LLMFallbackAdapter"
-Cohesion: 0.16
+Cohesion: 0.06
-Nodes (15): count_phrase_occurrences(), match_phrase_in_text(), Core deterministic classification engine (Tier 1 core)., Check if a normalized phrase appears in normalized text with word boundary…, Count occurrences of a phrase in text., Classify inherence of content against an ECP snapshot., extract_evidence_snippets(), extract_sentences() (+7 more)
+Nodes (43): LLMFallbackAdapter, Optional adapter for LLM fallback boundary disambiguation., Any, parametrize, Suíte de Testes Exaustiva para o Classificador de Inerência (classify.py e…, Cenário 4.1: Caso ambíguo elevado para DIRECT_INHERENT pelo LLM., Cenário 4.2: Caso ambíguo elevado para CONTEXTUAL_INHERENT pelo LLM., Cenário 4.3: LLM confirma categoricamente que a menção é periférica /… (+35 more)
 
 ### Community 48 - "test_convert_article_to_markdown.py"
 Cohesion: 0.08
@@ -371,16 +373,16 @@ 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: 0.15
+Cohesion: 0.20
-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)
+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)
 
 ### Community 83 - "ExtractionResult"
 Cohesion: 0.29
-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()
+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()
 
 ### Community 84 - "test_extract_google_news.py"
-Cohesion: 0.15
+Cohesion: 0.16
-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)
+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)
 
 ### Community 85 - "Implementation Tasks: Google News Headlines Extractor"
 Cohesion: 0.14
@@ -400,7 +402,7 @@ 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 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()
+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()
 
 ### Community 91 - "1. Technical Decisions & Tradeoffs"
 Cohesion: 0.25
@@ -435,12 +437,12 @@ 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 - "main"
-Cohesion: 0.17
+Cohesion: 0.14
-Nodes (15): emit_error(), main(), parse_args(), Namespace, ClassificationError, ErrorCode, Enum, str (+7 more)
+Nodes (20): main(), Path, Cenário 6.1: Caminho de ECP inexistente -> Exit Code 1, error_code:…, Cenário 6.2: Arquivo ECP com sintaxe JSON corrompida., Cenário 6.3: Valida erro para falta de cada um dos campos obrigatórios do ECP., Cenário 6.4: Caminho de arquivo Markdown inexistente., Cenário 6.5: Arquivo Markdown vazio ou contendo apenas espaços em branco., Cenário 6.6: A flag -o / --output cria diretórios aninhados automaticamente. (+12 more)
 
-### Community 101 - "ECPSnapshot"
+### Community 101 - "classifier.py"
-Cohesion: 0.18
+Cohesion: 0.17
-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)
+Nodes (12): emit_error(), parse_args(), Namespace, Core deterministic classification engine (Tier 1 core)., ErrorCode, MatchedGraphEntity, Enum, str (+4 more)
 
 ### Community 102 - "Feature Specification: Multilingual NLP Entity Inherence Classifier (POC)"
 Cohesion: 0.14
@@ -514,13 +516,13 @@ Nodes (35): CandidateStatus, extract_candidate_data(), ExtractorName, Any, Enum,
 Cohesion: 0.11
 Nodes (24): atomic_save_json(), process_batch(), Path, Salva dados em JSON de forma atômica utilizando arquivo temporário e rename., Lê o JSON de entrada, valida a estrutura, processa todos os artigos e grava o…, Path, CT-012: A entrada já contém selected_extractor -> Recalcular e substituir…, CT-013: articles está vazio -> Gerar saída válida com articles vazio. (+16 more)
 
-### Community 121 - "detect_language"
+### Community 121 - "test_models.py"
-Cohesion: 0.19
+Cohesion: 0.07
-Nodes (16): detect_language(), extract_words(), normalize_text(), Lightweight multilingual language detection and text normalization., Normalize text by converting to lowercase and stripping combining diacritical…, Tokenize text into lowercase alphanumeric words., Detect the ISO-639-1 language code of text among supported languages (pt, en,…, Unit tests for language detection and text normalization. (+8 more)
+Nodes (37): count_phrase_occurrences(), match_phrase_in_text(), Check if a normalized phrase appears in normalized text with word boundary…, Count occurrences of a phrase in text., Classify inherence of content against an ECP snapshot., detect_language(), extract_words(), normalize_text() (+29 more)
 
 ### 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 ![alt](url) 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)
+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 ![alt](url) seja descartada e link…, E2E: Executa scripts/select_article_extractor.py como subprocesso real na linha…, test_e2e_cli_subprocess_real_execution() (+8 more)
 
 ### Community 123 - "Feature Specification: Deterministic Content Selection"
 Cohesion: 0.17
@@ -622,9 +624,9 @@ 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 - "sample_rss_xml"
+### Community 149 - "get_hl_gl_ceid"
-Cohesion: 0.67
+Cohesion: 0.25
-Nodes (3): fixture, Fixture que fornece o conteúdo do XML de exemplo para testes offline., sample_rss_xml()
+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 150 - "13. Estratégia de testes"
 Cohesion: 0.50
@@ -634,9 +636,9 @@ 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 - "LLMFallbackAdapter"
+### Community 152 - "ECPSnapshot"
-Cohesion: 0.08
+Cohesion: 0.13
-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)
+Nodes (20): ECPSnapshot, parametrize, test_benchmark_case(), Suíte de Testes para o Adaptador de Fallback para LLM (Tier 3) do Classificador…, Valida extração de JSON quando a resposta do LLM vem formatada em bloco…, Valida que respostas corrompidas ou JSONs sem campos obrigatórios retornem None…, Garante que o classificador dispare o Tier 3 LLM para casos ambíguos…, Garante que casos claros (alta confiança e alta densidade de âncoras) NÃO… (+12 more)
 
 ### Community 153 - "convert_html_to_markdown"
 Cohesion: 0.33
@@ -651,13 +653,21 @@ Cohesion: 0.67
 Nodes (3): 5.1 Incluído, 5.2 Fora do escopo, 5. Escopo
 
 ### Community 165 - "InherenceClassifier"
-Cohesion: 0.11
+Cohesion: 0.07
-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)
+Nodes (45): InherenceClassifier, Tier 1 Deterministic NLP Entity Inherence Classifier with optional Tier 2 /…, DecisionCategory, Content about apple fruit/culinary recipe against Apple Inc. tech entity., test_adversarial_apple_fruit_recipe(), Unit tests for deterministic classification decision logic., test_contextual_inherent(), test_direct_inherent() (+37 more)
 
 ### Community 166 - "remove_duplicate_initial_h1"
 Cohesion: 0.50
 Nodes (4): Remove o primeiro título H1 do corpo somente quando ele for igual ao título…, remove_duplicate_initial_h1(), Testa remoção de H1 inicial coincidente com título com variações de espaços e…, test_remove_duplicate_initial_h1_exact_and_variations()
 
+### Community 168 - ".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 169 - "test_funnel_cli_subprocess_end_to_end"
+Cohesion: 0.67
+Nodes (3): Path, Valida o contrato CLI completo classify.py com saída em arquivo JSON e flags…, test_funnel_cli_subprocess_end_to_end()
+
 ## Knowledge Gaps
 - **696 isolated node(s):** `text-nlp-classifier`, `MatchedGraphEntity`, `graphify`, `Usage`, `What graphify is for` (+691 more)
   These have ≤1 connection - possible missing edges or undocumented components.
@@ -666,17 +676,17 @@ Nodes (4): Remove o primeiro título H1 do corpo somente quando ele for igual ao
 ## Suggested Questions
 _Questions this graph is uniquely positioned to answer:_
 
+- **Why does `ECPSnapshot` connect `ECPSnapshot` to `main`, `classifier.py`, `InherenceClassifier`, `.disambiguate`, `ClassificationResult`, `test_adversarial.py`, `LLMFallbackAdapter`, `test_models.py`?**
+  _High betweenness centrality (0.009) - this node is a cross-community bridge._
 - **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 (0.006) - 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._
-- **Why does `ECPSnapshot` connect `ECPSnapshot` to `main`, `InherenceClassifier`, `ClassificationResult`, `test_adversarial.py`, `classifier.py`, `LLMFallbackAdapter`?**
+- **Why does `InherenceClassifier` connect `InherenceClassifier` to `main`, `classifier.py`, `ClassificationResult`, `test_adversarial.py`, `LLMFallbackAdapter`, `ECPSnapshot`, `test_models.py`?**
   _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?**
+- **Are the 42 inferred relationships involving `ECPSnapshot` (e.g. with `main()` and `BaseNLPAdapter`) actually correct?**
-  _`ECPSnapshot` has 16 INFERRED edges - model-reasoned connections that need verification._
+  _`ECPSnapshot` has 42 INFERRED edges - model-reasoned connections that need verification._
-- **Are the 7 inferred relationships involving `InherenceClassifier` (e.g. with `LocalEmbeddingsAdapter` and `LLMFallbackAdapter`) actually correct?**
+- **Are the 8 inferred relationships involving `InherenceClassifier` (e.g. with `LocalEmbeddingsAdapter` and `LLMFallbackAdapter`) actually correct?**
-  _`InherenceClassifier` has 7 INFERRED edges - model-reasoned connections that need verification._
+  _`InherenceClassifier` has 8 INFERRED edges - model-reasoned connections that need verification._
-- **Are the 24 inferred relationships involving `DecisionCategory` (e.g. with `LLMFallbackAdapter` and `InherenceClassifier`) actually correct?**
+- **Are the 50 inferred relationships involving `DecisionCategory` (e.g. with `LLMFallbackAdapter` and `InherenceClassifier`) actually correct?**
-  _`DecisionCategory` has 24 INFERRED edges - model-reasoned connections that need verification._
+  _`DecisionCategory` has 50 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._

graphify-out/2026-08-21/manifest.json

@@ -336,9 +336,9 @@
     "semantic_hash": ""
   },
   "src/classifier.py": {
-    "mtime": 1787320047.0362887,
+    "mtime": 1787321309.8981817,
-    "seen": 1787320239.025866,
+    "seen": 1787321481.1505442,
-    "ast_hash": "d6cc674d407a99ab52f6d5156f9b3d8e",
+    "ast_hash": "a4e5dafed12aa4eaf096988b2c6a8ae0",
     "semantic_hash": ""
   },
   "src/language.py": {
@@ -654,9 +654,9 @@
     "semantic_hash": ""
   },
   "README.md": {
-    "mtime": 1787321187.0812356,
+    "mtime": 1787321467.0542295,
-    "seen": 1787321205.5201268,
+    "seen": 1787321481.1561577,
-    "ast_hash": "aedfaf7a245288227952a2e28e7e7b13",
+    "ast_hash": "0cde8e800125cbba61a1d7de9d9d2c9e",
     "semantic_hash": ""
   },
   "scripts/extract_article_contents.py": {
@@ -922,5 +922,11 @@
     "seen": 1787321205.5156026,
     "ast_hash": "3a2d47f2ffcf8371ffdf90bb797b5346",
     "semantic_hash": ""
+  },
+  "tests/test_classify_exhaustive_suite.py": {
+    "mtime": 1787321371.2658408,
+    "seen": 1787321481.15137,
+    "ast_hash": "08e3c680d8669b2849a19d73b27b869a",
+    "semantic_hash": ""
   }
 }

graphify-out/GRAPH_REPORT.md

@@ -1,7 +1,7 @@
 # Graph Report - TextNLPClassifierApp  (2026-08-21)
 
 ## Corpus Check
-- 203 files · ~114,894 words
+- 203 files · ~114,931 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: `a874b98d`
+- Built from commit: `2cdd3547`
 - 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
 - ECPSnapshot
@@ -196,7 +196,7 @@
   classify.py → src/models.py
 - `main()` --uses--> `ErrorCode`  [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
@@ -373,16 +373,16 @@ 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
+Cohesion: 0.15
-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)
+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
+Cohesion: 0.15
-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)
+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
@@ -402,7 +402,7 @@ 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
@@ -624,9 +624,9 @@ 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"
+### Community 149 - "sample_rss_xml"
-Cohesion: 0.25
+Cohesion: 0.67
-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()
+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

graphify-out/graph.json

@@ -1689,52 +1689,16 @@
       "source_location": "L755"
     },
     {
-      "id": "scripts_extract_google_news_get_hl_gl_ceid",
+      "id": "tests_test_extract_google_news_sample_rss_xml",
-      "label": "get_hl_gl_ceid()",
+      "label": "sample_rss_xml()",
       "_callable": true,
       "_origin": "ast",
       "community": 149,
-      "community_name": "get_hl_gl_ceid",
+      "community_name": "sample_rss_xml",
       "file_type": "code",
-      "norm_label": "get_hl_gl_ceid()",
+      "norm_label": "sample_rss_xml()",
-      "source_file": "scripts/extract_google_news.py",
-      "source_location": "L107"
-    },
-    {
-      "id": "tests_test_extract_google_news_test_get_hl_gl_ceid_default_mappings",
-      "label": "test_get_hl_gl_ceid_default_mappings()",
-      "_callable": true,
-      "_origin": "ast",
-      "community": 149,
-      "community_name": "get_hl_gl_ceid",
-      "file_type": "code",
-      "norm_label": "test_get_hl_gl_ceid_default_mappings()",
       "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L37"
+      "source_location": "L32"
-    },
-    {
-      "id": "tests_test_extract_google_news_test_get_hl_gl_ceid_dynamic_fallback",
-      "label": "test_get_hl_gl_ceid_dynamic_fallback()",
-      "_callable": true,
-      "_origin": "ast",
-      "community": 149,
-      "community_name": "get_hl_gl_ceid",
-      "file_type": "code",
-      "norm_label": "test_get_hl_gl_ceid_dynamic_fallback()",
-      "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L78"
-    },
-    {
-      "id": "tests_test_extract_google_news_test_get_hl_gl_ceid_with_custom_locale",
-      "label": "test_get_hl_gl_ceid_with_custom_locale()",
-      "_callable": true,
-      "_origin": "ast",
-      "community": 149,
-      "community_name": "get_hl_gl_ceid",
-      "file_type": "code",
-      "norm_label": "test_get_hl_gl_ceid_with_custom_locale()",
-      "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L60"
     },
     {
       "id": "src_models_ecpsnapshot_from_json_str",
@@ -2310,7 +2274,7 @@
       "file_type": "code",
       "norm_label": "._parse_llm_response()",
       "source_file": "src/adapters/llm.py",
-      "source_location": "L214"
+      "source_location": "L225"
     },
     {
       "id": "tests_test_e2e_text_analysis_pipeline_test_funnel_cli_subprocess_end_to_end",
@@ -3548,6 +3512,18 @@
       "source_file": "scripts/extract_google_news.py",
       "source_location": "L253"
     },
+    {
+      "id": "scripts_extract_google_news_get_hl_gl_ceid",
+      "label": "get_hl_gl_ceid()",
+      "_callable": true,
+      "_origin": "ast",
+      "community": 82,
+      "community_name": "extract_google_news.py",
+      "file_type": "code",
+      "norm_label": "get_hl_gl_ceid()",
+      "source_file": "scripts/extract_google_news.py",
+      "source_location": "L107"
+    },
     {
       "id": "scripts_extract_google_news_normalize_text_for_comparison",
       "label": "_normalize_text_for_comparison()",
@@ -3584,6 +3560,18 @@
       "source_file": "scripts/extract_google_news.py",
       "source_location": "L220"
     },
+    {
+      "id": "tests_test_extract_google_news_test_parse_google_news_rss_with_fixture",
+      "label": "test_parse_google_news_rss_with_fixture()",
+      "_callable": true,
+      "_origin": "ast",
+      "community": 82,
+      "community_name": "extract_google_news.py",
+      "file_type": "code",
+      "norm_label": "test_parse_google_news_rss_with_fixture()",
+      "source_file": "tests/test_extract_google_news.py",
+      "source_location": "L111"
+    },
     {
       "id": "tests_test_extract_google_news_test_resolve_articles_urls_batch",
       "label": "test_resolve_articles_urls_batch()",
@@ -3621,16 +3609,16 @@
       "source_location": "L73"
     },
     {
-      "id": "tests_test_extract_google_news_test_extract_google_news_orchestration_mocked",
+      "id": "tests_test_extract_google_news_test_e2e_extract_google_news_live_pipeline",
-      "label": "test_extract_google_news_orchestration_mocked()",
+      "label": "test_e2e_extract_google_news_live_pipeline()",
       "_callable": true,
       "_origin": "ast",
       "community": 83,
       "community_name": "ExtractionResult",
       "file_type": "code",
-      "norm_label": "test_extract_google_news_orchestration_mocked()",
+      "norm_label": "test_e2e_extract_google_news_live_pipeline()",
       "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L186"
+      "source_location": "L302"
     },
     {
       "id": "scripts_extract_google_news_resolve_article_url",
@@ -3644,18 +3632,6 @@
       "source_file": "scripts/extract_google_news.py",
       "source_location": "L207"
     },
-    {
-      "id": "tests_test_extract_google_news_sample_rss_xml",
-      "label": "sample_rss_xml()",
-      "_callable": true,
-      "_origin": "ast",
-      "community": 84,
-      "community_name": "test_extract_google_news.py",
-      "file_type": "code",
-      "norm_label": "sample_rss_xml()",
-      "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L32"
-    },
     {
       "id": "tests_test_extract_google_news_test_e2e_resolve_real_google_news_url",
       "label": "test_e2e_resolve_real_google_news_url()",
@@ -3669,16 +3645,40 @@
       "source_location": "L281"
     },
     {
-      "id": "tests_test_extract_google_news_test_parse_google_news_rss_with_fixture",
+      "id": "tests_test_extract_google_news_test_get_hl_gl_ceid_default_mappings",
-      "label": "test_parse_google_news_rss_with_fixture()",
+      "label": "test_get_hl_gl_ceid_default_mappings()",
       "_callable": true,
       "_origin": "ast",
       "community": 84,
       "community_name": "test_extract_google_news.py",
       "file_type": "code",
-      "norm_label": "test_parse_google_news_rss_with_fixture()",
+      "norm_label": "test_get_hl_gl_ceid_default_mappings()",
       "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L111"
+      "source_location": "L37"
+    },
+    {
+      "id": "tests_test_extract_google_news_test_get_hl_gl_ceid_dynamic_fallback",
+      "label": "test_get_hl_gl_ceid_dynamic_fallback()",
+      "_callable": true,
+      "_origin": "ast",
+      "community": 84,
+      "community_name": "test_extract_google_news.py",
+      "file_type": "code",
+      "norm_label": "test_get_hl_gl_ceid_dynamic_fallback()",
+      "source_file": "tests/test_extract_google_news.py",
+      "source_location": "L78"
+    },
+    {
+      "id": "tests_test_extract_google_news_test_get_hl_gl_ceid_with_custom_locale",
+      "label": "test_get_hl_gl_ceid_with_custom_locale()",
+      "_callable": true,
+      "_origin": "ast",
+      "community": 84,
+      "community_name": "test_extract_google_news.py",
+      "file_type": "code",
+      "norm_label": "test_get_hl_gl_ceid_with_custom_locale()",
+      "source_file": "tests/test_extract_google_news.py",
+      "source_location": "L60"
     },
     {
       "id": "tests_test_extract_google_news_test_resolve_article_url_fallback",
@@ -3753,16 +3753,16 @@
       "source_location": "L40"
     },
     {
-      "id": "tests_test_extract_google_news_test_e2e_extract_google_news_live_pipeline",
+      "id": "tests_test_extract_google_news_test_extract_google_news_orchestration_mocked",
-      "label": "test_e2e_extract_google_news_live_pipeline()",
+      "label": "test_extract_google_news_orchestration_mocked()",
       "_callable": true,
       "_origin": "ast",
       "community": 90,
       "community_name": "SearchQuery",
       "file_type": "code",
-      "norm_label": "test_e2e_extract_google_news_live_pipeline()",
+      "norm_label": "test_extract_google_news_orchestration_mocked()",
       "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L302"
+      "source_location": "L186"
     },
     {
       "id": "tests_test_extract_google_news_test_search_query_validation",
@@ -11112,48 +11112,26 @@
       "source_location": "L290"
     },
     {
-      "id": "scripts_extract_google_news_rationale_108",
+      "id": "tests_test_extract_google_news_py_fixture",
-      "label": "Mapeia idioma e locale para os par\u00e2metros hl, gl e ceid do Google News.",
+      "label": "fixture",
       "_origin": "ast",
       "community": 149,
-      "community_name": "get_hl_gl_ceid",
+      "community_name": "sample_rss_xml",
-      "file_type": "rationale",
+      "file_type": "code",
-      "norm_label": "mapeia idioma e locale para os parametros hl, gl e ceid do google news.",
+      "norm_label": "fixture",
-      "source_file": "scripts/extract_google_news.py",
+      "source_file": "",
-      "source_location": "L108"
+      "source_location": ""
     },
     {
-      "id": "tests_test_extract_google_news_rationale_38",
+      "id": "tests_test_extract_google_news_rationale_33",
-      "label": "Valida o mapeamento padr\u00e3o de idiomas para pares (hl, gl, ceid).",
+      "label": "Fixture que fornece o conte\u00fado do XML de exemplo para testes offline.",
       "_origin": "ast",
       "community": 149,
-      "community_name": "get_hl_gl_ceid",
+      "community_name": "sample_rss_xml",
       "file_type": "rationale",
-      "norm_label": "valida o mapeamento padrao de idiomas para pares (hl, gl, ceid).",
+      "norm_label": "fixture que fornece o conteudo do xml de exemplo para testes offline.",
       "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L38"
+      "source_location": "L33"
-    },
-    {
-      "id": "tests_test_extract_google_news_rationale_61",
-      "label": "Valida a sobrescrita geogr\u00e1fica quando o argumento locale \u00e9 especificado.",
-      "_origin": "ast",
-      "community": 149,
-      "community_name": "get_hl_gl_ceid",
-      "file_type": "rationale",
-      "norm_label": "valida a sobrescrita geografica quando o argumento locale e especificado.",
-      "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L61"
-    },
-    {
-      "id": "tests_test_extract_google_news_rationale_79",
-      "label": "Valida fallback din\u00e2mico para idiomas regionais n\u00e3o listados explicitamente.",
-      "_origin": "ast",
-      "community": 149,
-      "community_name": "get_hl_gl_ceid",
-      "file_type": "rationale",
-      "norm_label": "valida fallback dinamico para idiomas regionais nao listados explicitamente.",
-      "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L79"
     },
     {
       "id": "specify_templates_plan_template",
@@ -12145,7 +12123,7 @@
       "source_location": "L155"
     },
     {
-      "id": "src_adapters_llm_rationale_219",
+      "id": "src_adapters_llm_rationale_230",
       "label": "Parses and validates structured JSON response from LLM.",
       "_origin": "ast",
       "community": 168,
@@ -12153,7 +12131,7 @@
       "file_type": "rationale",
       "norm_label": "parses and validates structured json response from llm.",
       "source_file": "src/adapters/llm.py",
-      "source_location": "L219"
+      "source_location": "L230"
     },
     {
       "id": "src_adapters_llm_rationale_57",
@@ -17171,6 +17149,17 @@
       "source_file": "scripts/extract_google_news.py",
       "source_location": "L1"
     },
+    {
+      "id": "scripts_extract_google_news_rationale_108",
+      "label": "Mapeia idioma e locale para os par\u00e2metros hl, gl e ceid do Google News.",
+      "_origin": "ast",
+      "community": 82,
+      "community_name": "extract_google_news.py",
+      "file_type": "rationale",
+      "norm_label": "mapeia idioma e locale para os parametros hl, gl e ceid do google news.",
+      "source_file": "scripts/extract_google_news.py",
+      "source_location": "L108"
+    },
     {
       "id": "scripts_extract_google_news_rationale_152",
       "label": "Remove pontua\u00e7\u00e3o e espa\u00e7os extras para compara\u00e7\u00e3o de redund\u00e2ncia.",
@@ -17237,6 +17226,17 @@
       "source_file": "scripts/extract_google_news.py",
       "source_location": "L65"
     },
+    {
+      "id": "tests_test_extract_google_news_rationale_112",
+      "label": "Valida o parsing do feed RSS, higieniza\u00e7\u00e3o de tags HTML e deduplica\u00e7\u00e3o.",
+      "_origin": "ast",
+      "community": 82,
+      "community_name": "extract_google_news.py",
+      "file_type": "rationale",
+      "norm_label": "valida o parsing do feed rss, higienizacao de tags html e deduplicacao.",
+      "source_file": "tests/test_extract_google_news.py",
+      "source_location": "L112"
+    },
     {
       "id": "tests_test_extract_google_news_rationale_162",
       "label": "Valida a resolu\u00e7\u00e3o concorrente em lote de uma lista de NewsArticle.",
@@ -17271,15 +17271,15 @@
       "source_location": "L85"
     },
     {
-      "id": "tests_test_extract_google_news_rationale_187",
+      "id": "tests_test_extract_google_news_rationale_303",
-      "label": "Valida a consolida\u00e7\u00e3o do ExtractionResult a partir da busca mockada com URLs\u2026",
+      "label": "Valida E2E o fluxo completo de busca, parsing e resolu\u00e7\u00e3o de URLs reais ao vivo.",
       "_origin": "ast",
       "community": 83,
       "community_name": "ExtractionResult",
       "file_type": "rationale",
-      "norm_label": "valida a consolidacao do extractionresult a partir da busca mockada com urls...",
+      "norm_label": "valida e2e o fluxo completo de busca, parsing e resolucao de urls reais ao vivo.",
       "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L187"
+      "source_location": "L303"
     },
     {
       "id": "tests_test_extract_google_news",
@@ -17292,17 +17292,6 @@
       "source_file": "tests/test_extract_google_news.py",
       "source_location": "L1"
     },
-    {
-      "id": "tests_test_extract_google_news_py_fixture",
-      "label": "fixture",
-      "_origin": "ast",
-      "community": 84,
-      "community_name": "test_extract_google_news.py",
-      "file_type": "code",
-      "norm_label": "fixture",
-      "source_file": "",
-      "source_location": ""
-    },
     {
       "id": "scripts_extract_google_news_rationale_208",
       "label": "Resolve a URL intermedi\u00e1ria do Google News para a URL real do ve\u00edculo.",
@@ -17325,17 +17314,6 @@
       "source_file": "tests/test_extract_google_news.py",
       "source_location": "L1"
     },
-    {
-      "id": "tests_test_extract_google_news_rationale_112",
-      "label": "Valida o parsing do feed RSS, higieniza\u00e7\u00e3o de tags HTML e deduplica\u00e7\u00e3o.",
-      "_origin": "ast",
-      "community": 84,
-      "community_name": "test_extract_google_news.py",
-      "file_type": "rationale",
-      "norm_label": "valida o parsing do feed rss, higienizacao de tags html e deduplicacao.",
-      "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L112"
-    },
     {
       "id": "tests_test_extract_google_news_rationale_139",
       "label": "Valida fallback gracioso de URL quando n\u00e3o \u00e9 link do Google News ou em erro.",
@@ -17370,15 +17348,37 @@
       "source_location": "L282"
     },
     {
-      "id": "tests_test_extract_google_news_rationale_33",
+      "id": "tests_test_extract_google_news_rationale_38",
-      "label": "Fixture que fornece o conte\u00fado do XML de exemplo para testes offline.",
+      "label": "Valida o mapeamento padr\u00e3o de idiomas para pares (hl, gl, ceid).",
       "_origin": "ast",
       "community": 84,
       "community_name": "test_extract_google_news.py",
       "file_type": "rationale",
-      "norm_label": "fixture que fornece o conteudo do xml de exemplo para testes offline.",
+      "norm_label": "valida o mapeamento padrao de idiomas para pares (hl, gl, ceid).",
       "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L33"
+      "source_location": "L38"
+    },
+    {
+      "id": "tests_test_extract_google_news_rationale_61",
+      "label": "Valida a sobrescrita geogr\u00e1fica quando o argumento locale \u00e9 especificado.",
+      "_origin": "ast",
+      "community": 84,
+      "community_name": "test_extract_google_news.py",
+      "file_type": "rationale",
+      "norm_label": "valida a sobrescrita geografica quando o argumento locale e especificado.",
+      "source_file": "tests/test_extract_google_news.py",
+      "source_location": "L61"
+    },
+    {
+      "id": "tests_test_extract_google_news_rationale_79",
+      "label": "Valida fallback din\u00e2mico para idiomas regionais n\u00e3o listados explicitamente.",
+      "_origin": "ast",
+      "community": 84,
+      "community_name": "test_extract_google_news.py",
+      "file_type": "rationale",
+      "norm_label": "valida fallback dinamico para idiomas regionais nao listados explicitamente.",
+      "source_file": "tests/test_extract_google_news.py",
+      "source_location": "L79"
     },
     {
       "id": "specs_002_google_news_extractor_tasks_implementation_for_user_story_1",
@@ -18055,15 +18055,15 @@
       "source_location": "L33"
     },
     {
-      "id": "tests_test_extract_google_news_rationale_303",
+      "id": "tests_test_extract_google_news_rationale_187",
-      "label": "Valida E2E o fluxo completo de busca, parsing e resolu\u00e7\u00e3o de URLs reais ao vivo.",
+      "label": "Valida a consolida\u00e7\u00e3o do ExtractionResult a partir da busca mockada com URLs\u2026",
       "_origin": "ast",
       "community": 90,
       "community_name": "SearchQuery",
       "file_type": "rationale",
-      "norm_label": "valida e2e o fluxo completo de busca, parsing e resolucao de urls reais ao vivo.",
+      "norm_label": "valida a consolidacao do extractionresult a partir da busca mockada com urls...",
       "source_file": "tests/test_extract_google_news.py",
-      "source_location": "L303"
+      "source_location": "L187"
     },
     {
       "id": "tests_test_extract_google_news_rationale_87",
@@ -20530,7 +20530,7 @@
       "confidence_score": 1.0,
       "context": "call",
       "source_file": "src/adapters/llm.py",
-      "source_location": "L239",
+      "source_location": "L250",
       "weight": 1.0
     },
     {
@@ -20542,7 +20542,7 @@
       "confidence_score": 1.0,
       "context": "call",
       "source_file": "src/adapters/llm.py",
-      "source_location": "L248",
+      "source_location": "L259",
       "weight": 1.0
     },
     {
@@ -39911,7 +39911,7 @@
       "confidence": "EXTRACTED",
       "confidence_score": 1.0,
       "source_file": "src/adapters/llm.py",
-      "source_location": "L214",
+      "source_location": "L225",
       "weight": 1.0
     },
     {
@@ -40828,14 +40828,14 @@
       "weight": 1.0
     },
     {
-      "source": "src_adapters_llm_rationale_219",
+      "source": "src_adapters_llm_rationale_230",
       "target": "src_adapters_llm_llmfallbackadapter_parse_llm_response",
       "relation": "rationale_for",
       "_origin": "ast",
       "confidence": "EXTRACTED",
       "confidence_score": 1.0,
       "source_file": "src/adapters/llm.py",
-      "source_location": "L219",
+      "source_location": "L230",
       "weight": 1.0
     },
     {
@@ -43674,7 +43674,7 @@
       "confidence": "INFERRED",
       "confidence_score": 0.95,
       "source_file": "src/adapters/llm.py",
-      "source_location": "L239",
+      "source_location": "L250",
       "weight": 0.8
     },
     {
@@ -44625,5 +44625,5 @@
     }
   ],
   "hyperedges": [],
-  "built_at_commit": "a874b98dac4bd7e25da62c6cb4b0acb92a60f57a"
+  "built_at_commit": "2cdd3547b22ed202328985e763812c3704892d7b"
 }

graphify-out/manifest.json

@@ -330,9 +330,9 @@
     "semantic_hash": ""
   },
   "src/adapters/llm.py": {
-    "mtime": 1787321086.752706,
+    "mtime": 1787321869.4176295,
-    "seen": 1787321205.5144775,
+    "seen": 1787322035.8922434,
-    "ast_hash": "21ac74a13ac5dfad7db498b17165f8b3",
+    "ast_hash": "357b505df0d92f76b1d0cd606741d1a5",
     "semantic_hash": ""
   },
   "src/classifier.py": {

src/adapters/llm.py

@@ -49,7 +49,7 @@ class LLMFallbackAdapter(BaseNLPAdapter):
         provider_fn: Optional[Callable[[str], str]] = None,
     ) -> None:
         self.model_name = os.environ.get("OPENAI_MODEL", model_name)
-        self.openai_api_key = api_key or os.environ.get("OPENAI_API_KEY")
+        self.openai_api_key = api_key if api_key is not None else 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
 
@@ -166,18 +166,29 @@ Respond ONLY with a valid JSON object matching this schema:
             raw_response = self.provider_fn(prompt)
             return self._parse_llm_response(raw_response, initial_result)
 
-        # 2. Real OpenAI execution
+        # 2. Real OpenAI / Custom Base URL execution
         if self.openai_api_key:
             try:
                 from openai import OpenAI
 
-                client = OpenAI(api_key=self.openai_api_key)
+                base_url = os.environ.get("OPENAI_BASE_URL")
+                client = OpenAI(api_key=self.openai_api_key, base_url=base_url)
+
+                try:
                     response = client.chat.completions.create(
                         model=self.model_name,
                         messages=[{"role": "user", "content": prompt}],
                         response_format={"type": "json_object"},
                         temperature=0.0,
                     )
+                except Exception:
+                    # Fallback for models or endpoints that don't support response_format json_object
+                    response = client.chat.completions.create(
+                        model=self.model_name,
+                        messages=[{"role": "user", "content": prompt}],
+                        temperature=0.0,
+                    )
+
                 raw_text = response.choices[0].message.content or ""
                 return self._parse_llm_response(raw_text, initial_result)
             except Exception as e: