andreferraro/TextNLPClassifierApp

Fork 0

Files

T

andreferraro 67cc40f91a feat(classifier): add multilingual ECP inherence classifier POC

2026-08-20 00:51:02 -03:00

15 KiB

Raw Blame History

Graph Report - TextNLPClassifierApp (2026-08-20)

Corpus Check

132 files · ~53,988 words
Verdict: corpus is large enough that graph structure adds value.

Summary

579 nodes · 674 edges · 80 communities (43 shown, 37 thin omitted)
Extraction: 96% EXTRACTED · 4% INFERRED · 0% AMBIGUOUS · INFERRED: 28 edges (avg confidence: 0.95)
Token cost: 0 input · 0 output

Graph Freshness

Built from commit: d371b81a
Run git rev-parse HEAD and compare to check if the graph is stale.
Run graphify update . after code changes (no API cost).

Task Planning
Convergence Workflow
SpecKit Utilities
Graphify Commands
speckit-analyze/SKILL.md
Tasks: Multilingual NLP Entity Inherence Classifier (POC)
Feature Specification Template
Graphify Rules
Implementation Planning
Feature Specification
Task Generation
Project Constitution
Constitution Template
Graphify Exports
Ponytail Configuration
Implementation Planning Template
Ponytail Help
Checklist Generation
Clarification Workflow
Implementation Workflow
Graph Query
Constitution Workflow
Feature Branch Creation
Ponytail Audit
Ponytail Metrics
Ponytail Review
Task Issue Conversion
Checklist Template
Graphify Watch Mode
Graphify Hooks
Graphify Updates
Ponytail Debt
Repository Merge
Media Transcription
Extraction Specification
Graphify Workflows
Feature Specification: Multilingual NLP Entity Inherence Classifier (POC)
1. Technical Decisions & Tradeoffs
1. Input Schemas
1. Basic CLI Usage Examples
1. Standard Streams & Exit Codes
ECPSnapshot
classifier.py
detect_language
main
content_northvolt_de.md
content_presal_pt.md
content_tangential_es.md
adapters/__init__.py
src/__init__.py
de/contextual.md
de/direct.md
de/not_related.md
de/tangential.md
en/contextual.md
en/direct.md
en/not_related.md
en/tangential.md
es/contextual.md
es/direct.md
es/not_related.md
es/tangential.md
fr/contextual.md
fr/direct.md
fr/not_related.md
fr/tangential.md
it/contextual.md
it/direct.md
it/not_related.md
it/tangential.md
pt/contextual.md
pt/direct.md
pt/not_related.md
pt/tangential.md
tests/__init__.py
text-nlp-classifier

God Nodes (most connected - your core abstractions)

ECPSnapshot - 27 edges
InherenceClassifier - 21 edges
ClassificationResult - 17 edges
LocalEmbeddingsAdapter - 14 edges
LLMFallbackAdapter - 14 edges
detect_language() - 14 edges
DecisionCategory - 14 edges
main() - 13 edges
Tasks: [FEATURE NAME] - 13 edges
BaseNLPAdapter - 12 edges

Surprising Connections (you probably didn't know these)

main() --uses--> ECPSnapshot [INFERRED] classify.py → src/models.py
main() --uses--> ErrorCode [INFERRED] classify.py → src/models.py
test_classification_result_serialization() --uses--> DecisionCategory [INFERRED] tests/test_models.py → src/models.py
petrobras_ecp() --uses--> ECPSnapshot [INFERRED] tests/test_classifier.py → src/models.py
emit_error() --uses--> ErrorCode [INFERRED] classify.py → src/models.py

Import Cycles

None detected.

Communities (80 total, 37 thin omitted)

Community 0 - "Task Planning"

Cohesion: 0.07 Nodes (26): Dependencies & Execution Order, Format: [ID] [P?] [Story] Description, Implementation for User Story 1, Implementation for User Story 2, Implementation for User Story 3, Implementation Strategy, Incremental Delivery, MVP First (User Story 1 Only) (+18 more)

Community 1 - "Convergence Workflow"

Cohesion: 0.12 Nodes (15): 1. Initialize Convergence Context, 2. Load Artifacts (Progressive Disclosure), 3. Build the Intent Inventory, 4. Assess the Codebase and Classify Findings, 5. Assign Severity, 6. Present the In-Session Findings Summary, 7. Append Convergence Tasks (or report converged), 8. Provide Next Actions (Handoff) (+7 more)

Community 2 - "SpecKit Utilities"

Cohesion: 0.23 Nodes (13): Find-SpecifyRoot(), Format-SpecKitCommand(), Get-CurrentBranch(), Get-FeaturePathsEnv(), Get-InvokeSeparator(), Get-NormalizedPriority(), Get-Python3Command(), Get-RepoRoot() (+5 more)

Community 3 - "Graphify Commands"

Cohesion: 0.08 Nodes (24): For /graphify add and --watch, For /graphify query, For the commit hook and native CLAUDE.md integration, For --update and --cluster-only, /graphify, Honesty Rules, Interpreter guard for subcommands, Part A - Structural extraction for code files (+16 more)

Community 4 - "speckit-analyze/SKILL.md"

Cohesion: 0.08 Nodes (25): 1. Initialize Analysis Context, 2. Load Artifacts (Progressive Disclosure), 3. Build Semantic Models, 4. Detection Passes (Token-Efficient Analysis), 5. Severity Assignment, 6. Produce Compact Analysis Report, 7. Provide Next Actions, 8. Offer Remediation (+17 more)

Community 5 - "Tasks: Multilingual NLP Entity Inherence Classifier (POC)"

Cohesion: 0.06 Nodes (33): 1. Requirement Completeness & Scope Boundaries, 2. Requirement Clarity & Decision Semantics, 3. Requirement Consistency & Alignment, 4. Acceptance Criteria & Measurability, 5. Scenario & Edge Case Coverage, Notes, POC Readiness & Requirements Quality Checklist: Multilingual NLP Entity Inherence Classifier, Content Quality (+25 more)

Community 6 - "Feature Specification Template"

Cohesion: 0.15 Nodes (12): Assumptions, Edge Cases, Feature Specification: [FEATURE NAME], Functional Requirements, Key Entities (include if feature involves data), Measurable Outcomes, Requirements (mandatory), Success Criteria (mandatory) (+4 more)

Community 8 - "Implementation Planning"

Cohesion: 0.18 Nodes (10): Completion Report, Done When, Key rules, Mandatory Post-Execution Hooks, Outline, Phase 0: Outline & Research, Phase 1: Design & Contracts, Phases (+2 more)

Community 9 - "Feature Specification"

Cohesion: 0.18 Nodes (10): Completion Report, Done When, For AI Generation, Mandatory Post-Execution Hooks, Outline, Pre-Execution Checks, Quick Guidelines, Section Requirements (+2 more)

Community 10 - "Task Generation"

Cohesion: 0.18 Nodes (10): Checklist Format (REQUIRED), Completion Report, Done When, Mandatory Post-Execution Hooks, Outline, Phase Structure, Pre-Execution Checks, Task Generation Rules (+2 more)

Community 11 - "Project Constitution"

Cohesion: 0.18 Nodes (10): Core Principles, Governance, [PRINCIPLE_1_NAME], [PRINCIPLE_2_NAME], [PRINCIPLE_3_NAME], [PRINCIPLE_4_NAME], [PRINCIPLE_5_NAME], [PROJECT_NAME] Constitution (+2 more)

Community 12 - "Constitution Template"

Cohesion: 0.18 Nodes (10): Core Principles, Governance, [PRINCIPLE_1_NAME], [PRINCIPLE_2_NAME], [PRINCIPLE_3_NAME], [PRINCIPLE_4_NAME], [PRINCIPLE_5_NAME], [PROJECT_NAME] Constitution (+2 more)

Community 13 - "Graphify Exports"

Cohesion: 0.22 Nodes (8): graphify reference: extra exports and benchmark, Step 6b - Wiki (only if --wiki flag), Step 7 - Neo4j export (only if --neo4j or --neo4j-push flag), Step 7a - FalkorDB export (only if --falkordb or --falkordb-push flag), Step 7b - SVG export (only if --svg flag), Step 7c - GraphML export (only if --graphml flag), Step 7d - MCP server (only if --mcp flag), Step 8 - Token reduction benchmark (only if total_words > 5000)

Community 14 - "Ponytail Configuration"

Cohesion: 0.22 Nodes (8): Boundaries, Intensity, Output, Persistence, Ponytail, Rules, The ladder, When NOT to be lazy

Community 15 - "Implementation Planning Template"

Cohesion: 0.22 Nodes (8): Complexity Tracking, Constitution Check, Documentation (this feature), Implementation Plan: [FEATURE], Project Structure, Source Code (repository root), Summary, Technical Context

Community 16 - "Ponytail Help"

Cohesion: 0.25 Nodes (7): Configure Default Mode, Deactivate, Levels, More, Ponytail Help, Skills, Update

Community 17 - "Checklist Generation"

Cohesion: 0.25 Nodes (7): Anti-Examples: What NOT To Do, Checklist Purpose: "Unit Tests for English", Example Checklist Types & Sample Items, Execution Steps, Post-Execution Checks, Pre-Execution Checks, User Input

Community 18 - "Clarification Workflow"

Cohesion: 0.29 Nodes (6): Completion Report, Done When, Mandatory Post-Execution Hooks, Outline, Pre-Execution Checks, User Input

Community 19 - "Implementation Workflow"

Cohesion: 0.29 Nodes (6): Completion Report, Done When, Mandatory Post-Execution Hooks, Outline, Pre-Execution Checks, User Input

Community 20 - "Graph Query"

Cohesion: 0.33 Nodes (5): For /graphify explain, For /graphify path, graphify reference: query, path, explain, Step 0 — Constrained query expansion (REQUIRED before traversal), Step 1 — Traversal

Community 21 - "Constitution Workflow"

Cohesion: 0.33 Nodes (5): Outline, Post-Execution Checks, Pre-Execution Checks, Scope Guard, User Input

Community 23 - "Ponytail Audit"

Cohesion: 0.40 Nodes (4): Boundaries, Hunt, Output, Tags

Community 24 - "Ponytail Metrics"

Cohesion: 0.40 Nodes (4): Boundaries, Honesty boundary, Ponytail Gain, Scoreboard

Community 25 - "Ponytail Review"

Cohesion: 0.40 Nodes (4): Boundaries, Examples, Format, Scoring

Community 26 - "Task Issue Conversion"

Cohesion: 0.40 Nodes (4): Outline, Post-Execution Checks, Pre-Execution Checks, User Input

Community 27 - "Checklist Template"

Cohesion: 0.40 Nodes (4): [Category 1], [Category 2], [CHECKLIST TYPE] Checklist: [FEATURE NAME], Notes

Community 28 - "Graphify Watch Mode"

Cohesion: 0.50 Nodes (3): For /graphify add, For --watch, graphify reference: add a URL and watch a folder

Community 29 - "Graphify Hooks"

Cohesion: 0.50 Nodes (3): For git commit hook, For native CLAUDE.md integration, graphify reference: commit hook and native CLAUDE.md integration

Community 30 - "Graphify Updates"

Cohesion: 0.50 Nodes (3): For --cluster-only, For --update (incremental re-extraction), graphify reference: incremental update and cluster-only

Community 31 - "Ponytail Debt"

Cohesion: 0.50 Nodes (3): Boundaries, Output, Scan

Community 40 - "Feature Specification: Multilingual NLP Entity Inherence Classifier (POC)"

Cohesion: 0.14 Nodes (14): Assumptions, Assumptions & Scope, Clarifications, Explicit Out of Scope (POC), Feature Specification: Multilingual NLP Entity Inherence Classifier (POC), Functional Requirements, Key Entities (data models & domain entities), Measurable Outcomes (+6 more)

Community 41 - "1. Technical Decisions & Tradeoffs"

Cohesion: 0.22 Nodes (8): 1. Technical Decisions & Tradeoffs, 2. Standardized Error Handling Strategy, Decision 1: Execution Engine & CLI Architecture, Decision 2: Multilingual Language Detection & Normalization (Tier 1 Core), Decision 3: Materialized ECP Snapshot Contract & Matching Logic, Decision 4: Tier 2 (Embeddings) & Tier 3 (LLM) Optional Adapters, Decision 5: Controlled 24-Case POC Benchmark Suite, Technical Research & Architecture Decisions (POC)

Community 42 - "1. Input Schemas"

Cohesion: 0.25 Nodes (7): 1.1 ECP Snapshot Schema (snapshot.json), 1.2 Content Item Schema (content.md), 1. Input Schemas, 2.1 Classification Success Result Schema (result.json), 2.2 Error Result Schema, 2. Output Schemas, Data Models & Schemas (POC)

Community 43 - "2. Basic CLI Usage Examples"

Cohesion: 0.25 Nodes (7): 1. Prerequisites & Installation, 2.1 Direct Inherence (Portuguese), 2.2 Contextual Inherence via Graph Snapshot (German), 2.3 Tangential Mention (Spanish), 2. Basic CLI Usage Examples, 3. Running the Controlled 24-Case Benchmark, Quickstart & Validation Guide (POC)

Community 44 - "2. Standard Streams & Exit Codes"

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 - "ECPSnapshot"

Cohesion: 0.07 Nodes (26): ABC, Any, parametrize, 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. (+18 more)

Community 46 - "classifier.py"

Cohesion: 0.09 Nodes (39): emit_error(), Enum, count_phrase_occurrences(), InherenceClassifier, 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. (+31 more)

Community 47 - "detect_language"

Cohesion: 0.19 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)

Community 48 - "main"

Cohesion: 0.31 Nodes (9): main(), parse_args(), Namespace, CLI execution tests covering flags, arguments, stdout, and error handling., test_cli_empty_content_file(), test_cli_missing_ecp_file(), test_cli_missing_required_ecp_field(), test_cli_output_file() (+1 more)

Knowledge Gaps

291 isolated node(s): text-nlp-classifier, MatchedGraphEntity, graphify, Usage, What graphify is for (+286 more) These have ≤1 connection - possible missing edges or undocumented components.
37 thin communities (<3 nodes) omitted from report — run graphify query to explore isolated nodes.

15 KiB Raw Blame History