Skip to content

Documentation Index

This is a comprehensive, searchable index of all TNH Scholar documentation with descriptions and metadata.

For a simpler hierarchical view, see the Documentation Map section at the bottom of the main index.

Getting Started

Title Description Created Path
Configuration TNH Scholar requires some initial configuration to function properly. This guide covers the essential configuration steps and options. 2025-02-01 docs/getting-started/configuration.md
Getting Started Table of contents for getting-started 2025-12-11 docs/getting-started/index.md
Installation Install instructions for TNH Scholar, a Python package for text processing and analysis, using pip. 2025-02-01 docs/getting-started/installation.md
Quick Start Guide TNH Scholar provides powerful text processing capabilities through several command-line tools. This guide will help you get started with the basic workflows. 2025-02-01 docs/getting-started/quick-start-guide.md

User Guide

Title Description Created Path
Best Practices This guide outlines recommended practices for using TNH Scholar effectively. 2025-02-01 docs/user-guide/best-practices.md
TNH Scholar Prompt System This document describes the TNH Scholar Prompt System (formerly called patterns). The system allows for template-based prompting of AI interactions, with version control and concurrent access management. 2025-01-19 docs/user-guide/prompt-system.md
User Guide Table of contents for user-guide 2025-12-11 docs/user-guide/index.md
User Guide Overview Practical guide for using TNH Scholar as a tool user or workflow designer, covering main workflows and how the pieces fit together. 2025-12-02 docs/user-guide/overview.md

Project

Title Description Created Path
Conceptual Architecture of TNH-Scholar High-level, implementation-agnostic view of TNH-Scholar’s layers, abstractions, and how they interact. 2025-12-11 docs/project/conceptual-architecture.md
Future Directions of TNH-Scholar Blue-sky exploration of potential long-term evolutions of TNH-Scholar built on the project’s philosophy and architecture. 2025-12-11 docs/project/future-directions.md
Project Table of contents for project 2025-12-11 docs/project/index.md
Repo Root Repository root documentation surfaced in the MkDocs site. 2025-12-17 docs/project/repo-root/index.md
TNH Scholar CHANGELOG Chronological log of notable TNH Scholar changes. 2025-02-28 docs/project/repo-root/changelog.md
TNH Scholar CONTRIBUTING TNH Scholar is rapidly evolving, but we strive for a predictable, reproducible development workflow. 2024-10-21 docs/project/repo-root/contributing-root.md
TNH Scholar README TNH Scholar is an AI-driven project designed to explore, query, process and translate the teachings of Thich Nhat Hanh and the Plum Village community. The project provides tools for practitioners and scholars to engage with mindfulness and spiritual wisdom through natural language processing and machine learning models. 2024-10-21 docs/project/repo-root/repo-readme.md
TNH Scholar Release Checklist Checklist of tasks required before publishing a TNH Scholar release. 2025-01-22 docs/project/repo-root/release_checklist.md
TNH Scholar TODO List Roadmap tracking the highest-priority TNH Scholar tasks and release blockers. 2025-01-20 docs/project/repo-root/todo-list.md
TNH Scholar Versioning Policy Versioning policy for TNH Scholar during rapid prototype phase (0.x) and post-1.0 stable releases 2025-12-06 docs/project/repo-root/versioning.md
TNH-Scholar DEV_SETUP This document outlines the standard development environment for TNH‑Scholar. 2025-11-19 docs/project/repo-root/dev-setup-guide.md
TNH-Scholar Project Philosophy Foundational philosophy guiding TNH-Scholar’s conceptual, ethical, and methodological approach. 2025-12-11 docs/project/philosophy.md
TNH-Scholar Project Principles Guiding principles, values, and constraints for design and engineering decisions in TNH-Scholar. 2025-12-11 docs/project/principles.md
TNH-Scholar Project Vision North star for TNH-Scholar: purpose, scope, aspirations, and long-term directions. 2025-12-11 docs/project/vision.md

Community

Title Description Created Path
Community & Outreach Documentation for community partners, stakeholders, and collaborators in the Plum Village tradition. 2025-12-11 docs/community/index.md
TNH-Scholar: Project Overview for Parallax Press & Plum Village Editorial Community Non-technical overview of TNH-Scholar for Parallax Press and Plum Village editors, highlighting goals, benefits, and collaboration opportunities. 2025-12-11 docs/community/parallax-overview.md

CLI Reference

Title Description Created Path
audio-transcribe Command-line tool for audio transcription tasks. 2025-01-21 docs/cli-reference/audio-transcribe.md
CLI Reference Table of contents for cli-reference 2025-12-11 docs/cli-reference/index.md
Command Line Tools Overview TNH Scholar provides a suite of command-line tools designed to work together for text processing. Each tool focuses on specific tasks while maintaining consistent interfaces and behavior. This overview introduces the available tools and their primary functions. 2025-02-01 docs/cli-reference/overview.md
json-to-srt Convert JSONL transcription output (from audio-transcribe) into SRT subtitle files. 2025-12-10 docs/cli-reference/json-to-srt.md
nfmt nfmt, a newline formatting utility, standardizes line endings and spacing in text files. 2025-02-01 docs/cli-reference/nfmt.md
sent-split Split text into sentences using NLTK, with newline or space separators. 2025-12-10 docs/cli-reference/sent-split.md
srt-translate Translate SRT subtitle files while preserving timecodes, using TNH Scholar translation patterns. 2025-12-10 docs/cli-reference/srt-translate.md
tnh-fab User-facing reference for the tnh-fab CLI covering commands, options, and example workflows. 2025-01-19 docs/cli-reference/tnh-fab.md
tnh-setup The tnh-setup command configures the TNH Scholar environment, setting up necessary directories and downloading default patterns. 2025-02-01 docs/cli-reference/tnh-setup.md
token-count The token-count command calculates the OpenAI API token count for text input. This is useful for ensuring that a text is within maximum token limits for the API model and also for estimating API costs. 2025-02-01 docs/cli-reference/token-count.md
ytt-fetch (Y)ou(T)ube (T)ranscript-(Fetch)ing utility. 2025-01-21 docs/cli-reference/ytt-fetch.md

API

Title Description Created Path
API Reference ::: tnh_scholar 2025-01-19 docs/api/index.md

Architecture

Title Description Created Path
Adr Table of contents for architecture/video-processing/adr 2025-12-11 docs/architecture/video-processing/adr/index.md
Adr Table of contents for architecture/tnh-gen/adr 2025-12-11 docs/architecture/tnh-gen/adr/index.md
Adr Table of contents for architecture/transcription/adr 2025-12-11 docs/architecture/transcription/adr/index.md
Adr Table of contents for architecture/knowledge-base/adr 2025-12-11 docs/architecture/knowledge-base/adr/index.md
Adr Table of contents for architecture/docs-system/adr 2025-12-11 docs/architecture/docs-system/adr/index.md
Adr Table of contents for architecture/project-policies/adr 2025-12-11 docs/architecture/project-policies/adr/index.md
Adr Table of contents for architecture/ai-text-processing/adr 2025-12-11 docs/architecture/ai-text-processing/adr/index.md
Adr Table of contents for architecture/metadata/adr 2025-12-11 docs/architecture/metadata/adr/index.md
Adr Table of contents for architecture/ytt-fetch/adr 2025-12-11 docs/architecture/ytt-fetch/adr/index.md
Adr Table of contents for architecture/object-service/adr 2025-12-11 docs/architecture/object-service/adr/index.md
Adr Table of contents for architecture/prompt-system/adr 2025-12-11 docs/architecture/prompt-system/adr/index.md
Adr Table of contents for architecture/gen-ai-service/adr 2025-12-11 docs/architecture/gen-ai-service/adr/index.md
ADR-A01: Adopt Object-Service for GenAI Interactions Standardizes GenAI interactions with an Object-Service pattern that separates domain shapes from provider orchestration. 2025-11-15 docs/architecture/gen-ai-service/adr/adr-a01-object-service-genai.md
ADR-A02: PatternCatalog Integration (V1) Describes the V1 contract for plugging the legacy PatternCatalog into GenAI Service via rendered system prompts. 2025-11-15 docs/architecture/gen-ai-service/adr/adr-a02-patterncatalog-integration-v1.md
ADR-A08: Configuration / Parameters / Policy Taxonomy Establishes the Config/Params/Policy taxonomy for GenAI Service to prevent parameter soup and clarify ownership. 2025-11-15 docs/architecture/gen-ai-service/adr/adr-a08-config-params-policy-taxonomy.md
ADR-A09: V1 Simplified Implementation Pathway Defines the minimum viable GenAI Service implementation that preserves architectural seams while shipping quickly. 2025-11-15 docs/architecture/gen-ai-service/adr/adr-a09-v1-simplified.md
ADR-A11: Model Parameters and Strong Typing Fix Enforces typed parameter objects and removes literals from GenAI Service so provider flows stay consistent. 2025-11-15 docs/architecture/gen-ai-service/adr/adr-a11-model-parameters-fix.md
ADR-A12: Prompt System & Fingerprinting Architecture (V1) Replaces the Pattern Catalog adapter with a Prompt-first design that yields domain objects plus fingerprints. 2025-02-04 docs/architecture/gen-ai-service/adr/adr-a12-prompt-system-fingerprinting-v1.md
ADR-A13: Migrate All OpenAI Interactions to GenAIService Retires the legacy OpenAI client and standardizes every caller on the typed GenAI Service pipeline. 2025-11-17 docs/architecture/gen-ai-service/adr/adr-a13-migrate-openai-to-genaiservice.md
ADR-A14: File-Based Registry System for Provider Metadata Establishes a JSONC-based registry system for model capabilities, pricing, and provider metadata with auto-update mechanisms, aligned with VS Code's native configuration format. 2025-12-10 docs/architecture/gen-ai-service/adr/adr-a14-file-based-registry-system.md
ADR-AT01: AI Text Processing Pipeline Redesign Defines the modular TextObject pipeline, metadata handling, and configuration strategy for AI processing. 2025-02-26 docs/architecture/ai-text-processing/adr/adr-at01-ai-text-processing.md
ADR-AT02: TextObject Architecture Decision Records Captures the historical TextObject design comparisons and links to the original/new design documents. 2025-02-01 docs/architecture/ai-text-processing/adr/adr-at02-sectioning-textobject.md
ADR-AT03.1: AT03→AT04 Transition Plan Phased transition strategy: minimal refactor (AT03) for tnh-gen release, followed by comprehensive platform (AT04) 2025-12-12 docs/architecture/ai-text-processing/adr/adr-at03.1-transition-plan.md
ADR-AT03.2: NumberedText Section Boundary Validation Adds robust validation, coverage reporting, and gap/overlap detection to NumberedText to support reliable sectioning in ai_text_processing 2025-12-12 docs/architecture/ai-text-processing/adr/adr-at03.2-numberedtext-validation.md
ADR-AT03.3: TextObject Robustness and Metadata Management Fixes metadata propagation bugs, enhances section validation, and adds merge strategies to TextObject for reliable ai_text_processing workflows 2025-12-12 docs/architecture/ai-text-processing/adr/adr-at03.3-textobject-robustness.md
ADR-AT03: Minimal AI Text Processing Refactor for tnh-gen Focused refactor of ai_text_processing module to support tnh-gen CLI release: TextObject robustness, GenAI Service integration, and basic prompt system adoption 2025-12-07 docs/architecture/ai-text-processing/adr/adr-at03-object-service-refactor.md
ADR-AT04: AI Text Processing Platform Strategy Platform architecture for extensible, evaluation-driven text processing with strategy polymorphism and context fidelity 2025-12-11 docs/architecture/ai-text-processing/adr/adr-at04-ai-text-processing-platform-strat.md
ADR-DD01: Documentation System Reorganization Strategy Rebuilds the documentation architecture with new directories, automation, and Prompt terminology. 2024-11-09 docs/architecture/docs-system/adr/adr-dd01-docs-reorg-strategy.md
ADR-DD02: Documentation Main Content and Navigation Strategy Defines content architecture, sync mechanisms, and navigation patterns for README.md, docs/index.md, and filesystem-driven documentation. 2025-11-23 docs/architecture/docs-system/adr/adr-dd02-main-content-nav.md
ADR-DD03: Pattern to Prompt Terminology Standardization Standardizes documentation terminology from 'Pattern' to 'Prompt' to align with industry conventions and gen-ai-service refactoring. 2025-11-28 docs/architecture/docs-system/adr/adr-dd03-pattern-to-prompt.md
ADR-DD03: Phase 1 Execution Punch List Pre-merge checklist to complete Pattern→Prompt terminology updates and related navigation changes. 2025-11-28 docs/architecture/docs-system/adr/adr-dd03-phase1-punchlist.md
adr-jv03-canonical-xml-ast docs/architecture/jvb-viewer/adr/adr-jv03-canonical-xml-ast.md
adr-jvb01_as-built_jvb_viewer_v1 docs/architecture/jvb-viewer/adr/adr-jvb01_as-built_jvb_viewer_v1.md
ADR-K01: Preliminary Architectural Strategy for TNH Scholar Knowledge Base Proposes a phased managed-to-open-source knowledge base rollout to validate retrieval before scaling. 2025-11-15 docs/architecture/knowledge-base/adr/adr-k01-kb-architecture-strategy.md
ADR-MD01: Adoption of JSON-LD for Metadata Management Chooses JSON-LD as the canonical metadata format to capture provenance, relationships, and future semantic queries. 2025-02-01 docs/architecture/metadata/adr/adr-md01-json-ld-metadata.md
ADR-MD02: Metadata Infrastructure Object-Service Integration Defines metadata system's role as foundational infrastructure in the object-service architecture, establishing patterns for cross-layer usage and ensuring compliance with design principles. 2025-12-07 docs/architecture/metadata/adr/adr-md02-metadata-object-service-integration.md
ADR-OS01: Object-Service Design Architecture V3 Establishes layered architecture for complex objects and API-backed services across TNH Scholar, defining clear boundaries between domain, service, and transport layers. 2025-10-24 docs/architecture/object-service/adr/adr-os01-object-service-architecture-v3.md
ADR-PP01: Rapid Prototype Versioning Policy Establishes versioning policy for TNH Scholar during 0.x releases, allowing breaking changes in any release to enable fast iteration and architectural improvements. 2025-12-06 docs/architecture/project-policies/adr/adr-pp01-rapid-prototype-versioning.md
ADR-PT03: Prompt System Current Status & Roadmap Current as-built status of the TNH Scholar prompt system, documentation terminology standardization, and planned enhancements. 2025-11-29 docs/architecture/prompt-system/adr/adr-pt03-prompt-system-status-roadmap.md
ADR-PT04: Prompt System Refactor Plan (Revised) Refactors the legacy pattern-based prompt system into a modular, object-service compliant PromptCatalog with validation, transport isolation, and clean dependency injection seams. 2025-12-05 docs/architecture/prompt-system/adr/adr-pt04-prompt-system-refactor.md
ADR-TG01: tnh-gen CLI Architecture Core command structure, error handling, and configuration for the unified TNH Scholar CLI tool 2025-12-07 docs/architecture/tnh-gen/adr/adr-tg01-cli-architecture.md
ADR-TG02: TNH-Gen CLI Prompt System Integration Integration pattern for tnh-gen CLI with prompt system via PromptsAdapter 2025-12-07 docs/architecture/tnh-gen/adr/adr-tg02-prompt-integration.md
ADR-TR01: AssemblyAI Integration for Transcription Service Introduces a pluggable transcription interface with AssemblyAI and Whisper providers. 2025-05-01 docs/architecture/transcription/adr/adr-tr01-assemblyai-integration.md
ADR-TR02: Optimized SRT Generation Design Uses provider-native SRT generation to simplify the transcription pipeline. 2025-05-01 docs/architecture/transcription/adr/adr-tr02-optimized-srt-design.md
ADR-TR03: Standardizing Timestamps to Milliseconds Aligns all transcription providers on millisecond timestamps to avoid float drift. 2025-05-01 docs/architecture/transcription/adr/adr-tr03-ms-timestamps.md
ADR-TR04: AssemblyAI Service Implementation Improvements Refactors the AssemblyAI adapter to use the official SDK, richer options, and better error handling. 2025-05-01 docs/architecture/transcription/adr/adr-tr04-assemblyai-improvements.md
ADR-VP01: Video Processing Return Types and Configuration Centralizes yt-dlp configuration and return types so video tooling emits consistent metadata. 2025-02-01 docs/architecture/video-processing/adr/adr-vp01-video-processing.md
ADR-VSC01: VS Code Integration Strategy (TNH-Scholar Extension v0.1.0) Strategy ADR defining a CLI-first VS Code integration built on the unified tnh-gen interface for extension v0.1.0. 2025-01-28 docs/architecture/ui-ux/vs-code-integration/adr-vsc01-vscode-integration-strategy.md
ADR-VSC02: VS Code Extension Integration with tnh-gen CLI VS Code extension strategy for consuming tnh-gen CLI and providing GenAI text processing UI 2025-01-28 docs/architecture/ui-ux/vs-code-integration/adr-vsc02-tnh-gen-cli-implementation.md
ADR-VSC03.2: Real-World Survey Addendum (VS Code as a UI/UX Platform) Online survey of existing systems and patterns that de-risk Python↔TypeScript boundaries for TNH-Scholar’s VS Code UI/UX strategy docs/architecture/ui-ux/vs-code-integration/adr-vsc03.2-real-world-survey-addendum.md
ADR-VSC03.3: Investigation Synthesis - Validation of Design Choices Synthesis of real-world survey findings validating TNH Scholar's VS Code integration strategy and design decisions docs/architecture/ui-ux/vs-code-integration/adr-vsc03.3-investigation-synthesis.md
ADR-VSC03: Preliminary Investigation Findings Phase 1 research findings on Python-JavaScript impedance mitigation strategies docs/architecture/ui-ux/vs-code-integration/adr-vsc03.1-findings.md
ADR-VSC03: Python-JavaScript Impedance Mismatch Investigation Decision to investigate architectural strategies for mitigating Python-JavaScript platform mismatch in VS Code integration 2025-12-12 docs/architecture/ui-ux/vs-code-integration/adr-vsc03-python-javascript-impedance-investigation.md
ADR-YF00: Early yt-fetch Transcript Decisions (Historical) Consolidates the original transcript ADR notes for yt-fetch before they were split into discrete records. 2025-01-17 docs/architecture/ytt-fetch/adr/adr-yf00-early-decisions.md
ADR-YF01: YouTube Transcript Source Handling Documents how yt-fetch prioritizes manual subtitles while accepting auto captions for maximum coverage. 2025-01-21 docs/architecture/ytt-fetch/adr/adr-yf01-yt-transcript-source-handling.md
ADR-YF02: YouTube Transcript Format Selection Locks yt-fetch to a single transcript format (initially VTT) for predictable downstream processing. 2025-01-21 docs/architecture/ytt-fetch/adr/adr-yf02-yt-transcript-format-selection.md
Ai Text Processing Table of contents for architecture/ai-text-processing 2025-12-11 docs/architecture/ai-text-processing/index.md
Architecture Table of contents for architecture 2025-12-11 docs/architecture/index.md
Architecture Overview High-level conceptual view of TNH Scholar's layered, object-service oriented architecture with links to detailed design documents and ADRs. 2025-12-02 docs/architecture/overview.md
Audio Chunking Algorithm Design Document Design for splitting diarization segments into five-minute audio chunks using greedy accumulation and speaker-aware boundaries. 2025-05-01 docs/architecture/transcription/design/audio-chunking-design.md
Configuration Table of contents for architecture/configuration 2025-12-11 docs/architecture/configuration/index.md
Design Table of contents for architecture/transcription/design 2025-12-11 docs/architecture/transcription/design/index.md
Design Table of contents for architecture/docs-system/design 2025-12-11 docs/architecture/docs-system/design/index.md
Design Table of contents for architecture/ai-text-processing/design 2025-12-11 docs/architecture/ai-text-processing/design/index.md
Design Table of contents for architecture/utilities/design 2025-12-11 docs/architecture/utilities/design/index.md
Design Table of contents for architecture/ui-ux/design 2025-12-11 docs/architecture/ui-ux/design/index.md
Design Table of contents for architecture/ytt-fetch/design 2025-12-11 docs/architecture/ytt-fetch/design/index.md
Design Table of contents for architecture/setup-tnh/design 2025-12-11 docs/architecture/setup-tnh/design/index.md
Design Table of contents for architecture/gen-ai-service/design 2025-12-11 docs/architecture/gen-ai-service/design/index.md
Design Table of contents for architecture/jvb-viewer/design 2025-12-11 docs/architecture/jvb-viewer/design/index.md
Design Strategy: VS Code as UI/UX Platform for TNH Scholar --- 2025-11-15 docs/architecture/ui-ux/design/vs-code-as-ui-platform.md
Diarization Algorithms This document details the key algorithms in the diarization system, focusing on high-level design without implementation details. Each algorithm is presented with its inputs, outputs, and process flow. 2025-05-01 docs/architecture/transcription/design/diarization-algorithms.md
Diarization Chunker Module Design Strategy I've analyzed the current system and PoC code to propose a modular, extensible design for integrating the diarization chunking functionality into your tnh-scholar project. 2025-05-05 docs/architecture/transcription/design/diarization-chunker-design.md
Diarization System Design Detailed architecture for the diarization pipeline, covering segmentation, track extraction, and transcript remapping. 2025-05-01 docs/architecture/transcription/design/diarization-system-design.md
Docs System Table of contents for architecture/docs-system 2025-12-11 docs/architecture/docs-system/index.md
Documentation Design Reference for the documentation stack, covering tooling choices, information architecture, and publishing workflow. 2025-01-19 docs/architecture/docs-system/design/documentation-design.md
Gen Ai Service Table of contents for architecture/gen-ai-service 2025-12-11 docs/architecture/gen-ai-service/index.md
GenAI Service — Design Strategy Strategy for unifying GenAI Service capabilities, personas, and phased releases. 2025-11-15 docs/architecture/gen-ai-service/design/genai-service-design-strategy.md
Generate Markdown Translation JSON Pairs Instructions for producing paired Vietnamese-English Markdown JSON lines from scanned journal pages with strict formatting. 2025-11-15 docs/architecture/jvb-viewer/design/generate-md-translation-json-pairs.md
Generate Markdown Vietnamese Guidelines for rewriting Vietnamese journal pages into structured Markdown with one sentence per line and preserved metadata. 2025-11-15 docs/architecture/jvb-viewer/design/generate-md-vietnamese.md
Interval-to-Segment Mapping Algorithm Algorithm for mapping chunk-relative transcription intervals back to diarization segments using overlap and proximity. 2025-05-08 docs/architecture/transcription/design/interval-to-segment-mapping.md
Jvb Viewer Table of contents for architecture/jvb-viewer 2025-12-11 docs/architecture/jvb-viewer/index.md
JVB Viewer — Version 2 Strategy & High‑Level Design Strategy for a projection-first VS Code-based viewer/editor that reconciles OCR outputs into a canonical JSON artifact. 2025-11-15 docs/architecture/jvb-viewer/design/jvb-viewer-v2-strategy.md
Knowledge Base Table of contents for architecture/knowledge-base 2025-12-11 docs/architecture/knowledge-base/index.md
Language-Aware Chunking Orchestrator Notes Working notes for extending the DiarizationChunker orchestrator with language-aware strategies. 2025-06-24 docs/architecture/transcription/design/language-aware-chunking-orchestrator-notes.md
LUÂN-HỒI Transcribed Markdown sample of the 'Luân-Hồi Một Thực-Thể' article used to validate viewer output. 2025-11-15 docs/architecture/jvb-viewer/design/luan-hoi.md
Metadata Table of contents for architecture/metadata 2025-12-11 docs/architecture/metadata/index.md
minimal but extensible setup tool for the prototyping phase Core Requirements: 2025-01-21 docs/architecture/setup-tnh/design/setup-tnh-minimal-extensible-tool.md
Modular Pipeline Design: Best Practices for Audio Transcription and Diarization This document summarizes a detailed design and refactoring discussion on building a clean, modular, and production-ready audio transcription pipeline, with a focus on diarization chunking and robust system structure. It includes architectural patterns, file organization, and code hygiene practices. 2025-06-10 docs/architecture/transcription/design/modular-pipeline-best-practices.md
Object Service Table of contents for architecture/object-service 2025-12-11 docs/architecture/object-service/index.md
Object-Service Design Gaps Gaps, resolved items, and outstanding work needed to fully satisfy the Object-Service design blueprint. 2025-10-24 docs/architecture/object-service/object-service-design-gaps.md
Object-Service Design Overview High-level overview of TNH Scholar's layered architecture for complex objects and API-backed services. 2025-11-29 docs/architecture/object-service/object-service-design-overview.md
Object-Service Implementation Status Implementation status, resolved gaps, and outstanding work for the Object-Service design architecture. 2025-10-24 docs/architecture/object-service/object-service-implementation-status.md
OpenAI Interface Migration Plan Step-by-step plan for migrating from the legacy openai_interface module to the typed GenAI Service. 2025-11-17 docs/architecture/gen-ai-service/design/openai-interface-migration-plan.md
Package Version Checker Design Document Specification for a reusable package version checking utility with flexible strategies and clear reporting. 2025-06-10 docs/architecture/utilities/design/package-version-checker-design.md
Practical Language-Aware Chunking Design Practical heuristics for detecting language changes during chunking when diarization output is noisy. 2025-06-24 docs/architecture/transcription/design/practical-language-aware-chunking.md
Project Policies Cross-cutting architectural policies and decisions affecting the entire TNH Scholar codebase 2025-12-06 docs/architecture/project-policies/index.md
Prompt System Table of contents for architecture/prompt-system 2025-12-11 docs/architecture/prompt-system/index.md
Prompt System Architecture Current and planned architecture for the TNH Scholar prompt system, including VS Code integration and PromptCatalog service design. 2025-11-29 docs/architecture/prompt-system/prompt-system-architecture.md
Setup Tnh Table of contents for architecture/setup-tnh 2025-12-11 docs/architecture/setup-tnh/index.md
Simplified Language-Aware Chunking Design Language-aware chunking strategy that augments diarization splits with practical language detection heuristics. 2025-06-24 docs/architecture/transcription/design/language-aware-chunking-design.md
Speaker Diarization Algorithm Design This document details the key algorithms referenced in the main diarization system design. Each algorithm is presented with a clear breakdown of its inputs, outputs, and processing steps. 2025-05-01 docs/architecture/transcription/design/speaker-diarization-algorithm-design.md
Speaker Diarization and Time-Mapped Transcription System Design System design for mapping diarization outputs to speaker-specific transcriptions with accurate global timelines. 2025-05-01 docs/architecture/transcription/design/speaker-diarization-time-mapped-design.md
TextObject Original Design Legacy TextObject design notes capturing the original sectioning models, metadata strategy, and validation approach. 2025-02-01 docs/architecture/ai-text-processing/design/textobject-original-design.md
TextObject System Design Document Detailed blueprint for the modern TextObject pipeline, outlining segmentation models, metadata, and API surfaces. 2025-02-01 docs/architecture/ai-text-processing/design/textobject-system-design.md
TimelineMapper Design Document Design for the TimelineMapper component that reprojects chunk-level transcripts into the original audio timeline. 2025-05-08 docs/architecture/transcription/design/timelinemapper-design.md
TNH Configuration Management Architecture decisions and a phased plan for consolidating TNH Scholar configuration across modules, CLIs, and environments. 2025-02-01 docs/architecture/configuration/tnh-configuration-management.md
TNH-Gen CLI Architecture Unified command-line interface for TNH Scholar GenAI operations 2025-12-07 docs/architecture/tnh-gen/index.md
TNH‑Scholar Utilities Catalog This catalog lists core utility modules used across the TNH‑Scholar codebase. It provides a quick reference for shared abstractions, their purpose, API highlights, and stability. All modules are currently in Prototype phase, with most stable in active use. 2025-11-15 docs/architecture/utilities/design/utilities-catalog.md
Transcription Table of contents for architecture/transcription 2025-12-11 docs/architecture/transcription/index.md
Ui Ux Table of contents for architecture/ui-ux 2025-12-11 docs/architecture/ui-ux/index.md
Utilities Table of contents for architecture/utilities 2025-12-11 docs/architecture/utilities/index.md
Versioning Policy Documentation Additions Summary of documentation updates to clarify rapid prototype versioning policy 2025-12-06 docs/architecture/project-policies/versioning-policy-implementation-summary.md
Video Processing Table of contents for architecture/video-processing 2025-12-11 docs/architecture/video-processing/index.md
Vs Code Integration Table of contents for architecture/ui-ux/vs-code-integration 2025-12-11 docs/architecture/ui-ux/vs-code-integration/index.md
YouTube API vs yt-dlp Evaluation Comparison of using the YouTube Data API versus yt-dlp for fetching Plum Village media assets. 2025-01-21 docs/architecture/ytt-fetch/design/youtube-api-vs-yt-dlp-eval.md
Ytt Fetch Table of contents for architecture/ytt-fetch 2025-12-11 docs/architecture/ytt-fetch/index.md

Development

Title Description Created Path
2025 12 07 Reference Table of contents for development/incident-reports/2025-12-07-reference 2025-12-11 docs/development/incident-reports/2025-12-07-reference/index.md
Contributing to TNH Scholar (Prototype Phase) TNH Scholar is currently in rapid prototype phase, focusing on core functionality and basic usability. We welcome contributions that help validate and improve the prototype implementation. 2025-01-19 docs/development/contributing-prototype-phase.md
Development Table of contents for development 2025-12-11 docs/development/index.md
Development Documentation Landing page for contributor guides, design principles, and engineering practices for TNH Scholar. 2025-12-03 docs/development/overview.md
Fine Tuning Strategy Strategy outline and development plan for fine-tuning foundation models on Thich Nhat Hanh translations. 2025-02-26 docs/development/fine-tuning-strategy.md
Forensic Analysis: December 7, 2025 Git Data Loss Incident Post-incident analysis detailing the stale-branch reset that temporarily orphaned prompt system work and the safeguards required to prevent recurrence. 2025-12-08 docs/development/incident-reports/2025-12-07-reference/forensic-analysis.md
Git Workflow & Safety Guide Safe git practices for TNH Scholar development to prevent data loss 2025-12-07 docs/development/git-workflow.md
Human-AI Software Engineering Principles This document presents the Human-AI Software Engineering Principles, a comprehensive framework that builds upon established software engineering, architecture, and design principles from human-only teams and extends them to optimize collaboration between humans and AI agents. Central to this framework is the clear distinction between the Design Phase and the Coding Phase, each with distinct goals, modes, and workflows. It also addresses challenges such as context window limitations and maintaining alignment despite session resets. In addition to general principles, this framework incorporates concrete documentation and planning strategies designed to support long-term, sustainable human-AI collaboration. 2025-11-15 docs/development/human-ai-software-engineering-principles.md
Implementation Summary: Git Safety Improvements Summary of remediation work completed after the 2025-12-07 git recovery incident. 2025-12-08 docs/development/incident-reports/2025-12-07-reference/implementation-summary.md
Improvements / Initial structure Initial high-level view of the TNH Scholar ecosystem. 2025-02-01 docs/development/improvements-initial-structure.md
Incident Report: Git Recovery - December 7, 2025 Post-mortem analysis of orphaned commits and successful recovery of prompt system implementation (ADR-PT04) 2025-12-08 docs/development/incident-reports/2025-12-07-git-recovery.md
Incident Reports Table of contents for development/incident-reports 2025-12-11 docs/development/incident-reports/index.md
Proposed Updates to Incident Report Recommended edits to the December 7, 2025 incident report to capture the stale branch reset root cause and updated safeguards. 2025-12-08 docs/development/incident-reports/2025-12-07-reference/incident-report-updates.md
Release Workflow Automated release process for TNH Scholar with biweekly cadence during rapid prototyping. 2025-12-06 docs/development/release-workflow.md
TNH Scholar Design Principles Architectural patterns, design philosophy, and system organization principles for TNH Scholar development. 2025-11-29 docs/development/design-principles.md
TNH Scholar Style Guide Code formatting, naming conventions, and Python standards for TNH Scholar development. 2025-11-29 docs/development/style-guide.md
TNH Scholar System Design High-level system design describing the cyclical AI processing architecture powering TNH Scholar. 2025-02-01 docs/development/system-design.md

Docs Ops

Title Description Created Path
ADR Template Reusable template for TNH Scholar architecture decision records. 2025-02-27 docs/docs-ops/adr-template.md
Docs Ops Table of contents for docs-ops 2025-12-11 docs/docs-ops/index.md
Markdown Standards House style, linting, and structure requirements for TNH Scholar documentation. 2025-02-27 docs/docs-ops/markdown-standards.md
MkDocs Strict Warning Backlog Checklist to drive MkDocs builds to zero warnings in strict mode. 2025-11-25 docs/docs-ops/mkdocs-strict-warning-backlog.md
Preview TNH Scholar Theme Quick guide to previewing the custom zen theme locally 2025-12-02 docs/docs-ops/preview-theme.md
TNH Scholar Theme Design Zen-inspired documentation theme blending mindfulness aesthetics with modern AI tooling 2025-12-02 docs/docs-ops/theme-design.md

Research

Title Description Created Path
1-3 Word Queries Prompt experiments for generating search query and passage pairs used to train retrieval models. 2024-10-28 docs/research/gpt4o-search-query-testing/queries-1-3-words.md
GPT Development Convos Link log of early GPT design, feasibility, and data processing conversations for the project. 2024-10-23 docs/research/gpt_development_convos.md
Gpt4O Search Query Testing Table of contents for research/gpt4o-search-query-testing 2025-12-11 docs/research/gpt4o-search-query-testing/index.md
Gpt4O Translation Experiments Table of contents for research/gpt4o-translation-experiments 2025-12-11 docs/research/gpt4o-translation-experiments/index.md
Passage Test Spot-checks comparing GPT-4o translation outputs with bilingual baselines on short passages. 2024-11-08 docs/research/gpt4o-translation-experiments/passage_test.md
Preliminary Feasibility Study Feasibility study exploring an interactive translation, search, and conversation system built on Thich Nhat Hanh’s teachings. 2024-10-21 docs/research/preliminary-feasibility-study.md
RAG Research Directions for TNH Scholar Exploratory roadmap for retrieval-augmented generation (RAG) within the TNH Scholar project, with emphasis on multilingual Buddhist corpora and Plum Village practice contexts. 2025-12-05 docs/research/rag-research-directions.md
Research Entry points to research notes, experiments, and feasibility studies. 2025-12-11 docs/research/index.md
Structural-Informed Adaptive Processing (SIAP) Methodology Methodology for structure-aware adaptive processing that selects AI strategies based on content fingerprints. 2025-06-24 docs/research/siap-methodology.md
Summary Report on Metadata Extraction, Source Parsing, and Model Training for TNH-Scholar Summary of metadata extraction lessons, tooling, and training implications across Thich Nhat Hanh sources. 2024-10-24 docs/research/metadata-summary-report.md
TNH Scholar Knowledge Base: Design Document Design document for the TNH Scholar knowledge base and semantic search stack. 2025-06-10 docs/research/kb-design-document.md

Root

Title Description Created Path
TNH Scholar Comprehensive documentation for TNH Scholar, an AI-driven project exploring, processing, and translating the teachings of Thich Nhat Hanh. 2025-12-11 docs/index.md