# LLM Integration Implementation Issues **Generated**: 2025-10-03 **Source**: LLM_INTEGRATION_GAMEPLAN.md **Target Features**: Issue #98 (OpenRoute Integration) & Issue #99 (Auto Fill Templates) This document contains 10 specific GitHub issues ready for implementation, broken down from the comprehensive gameplan into actionable development tasks. ## Priority Matrix | Priority | Issue Count | Description | |----------|-------------|-------------| | **High** | 4 issues | Core infrastructure and foundational components | | **Medium** | 4 issues | User-facing features and integration | | **Low** | 2 issues | Advanced capabilities and polish | ## Dependency Chain ``` Foundation Layer: ├── Issue 1: OpenRouter Client ← (no dependencies) ├── Issue 2: Config Extensions ← depends on Issue 1 ├── Issue 6: Template Field Analysis ← (no dependencies) └── Issue 8: Profile Management ← (no dependencies) Integration Layer: ├── Issue 3: Context Builder ← depends on Issue 1 ├── Issue 4: Natural Language Enhancement ← depends on Issues 1, 3 ├── Issue 5: Basic LLM CLI ← depends on Issues 1, 2 └── Issue 7: Interactive Questionnaire ← depends on Issue 6 Advanced Layer: ├── Issue 9: LLM Auto-Fill ← depends on Issues 1, 6, 8 └── Issue 10: Advanced Fill Commands ← depends on Issues 7, 9 ``` --- ## Issue 1: Implement OpenRouter LLM Client Infrastructure **Priority**: HIGH | **Effort**: 2 days | **Dependencies**: None ### User Story As a developer, I want a robust OpenRouter client so that MarkiTect can connect to and interact with various LLM models through the OpenRouter API. ### Description Create the foundational OpenRouter client infrastructure that will enable all LLM-powered features in MarkiTect. This includes API communication, model management, rate limiting, and error handling. ### Technical Implementation - **New Files**: - `markitect/llm/__init__.py` - `markitect/llm/openrouter_client.py` - `markitect/llm/exceptions.py` - `tests/test_openrouter_client.py` - **Modified Files**: - `requirements.txt` (add httpx, pydantic) - `markitect/config_manager.py` (add OpenRouter config keys) - **Dependencies**: None ### Acceptance Criteria - [ ] OpenRouterClient class with async API communication - [ ] Support for multiple models (GPT-4, Claude, etc.) - [ ] Rate limiting and retry logic with exponential backoff - [ ] Comprehensive error handling for API failures - [ ] Token usage tracking and cost estimation - [ ] Unit tests with >90% coverage - [ ] Integration tests with mock API responses - [ ] Documentation with usage examples --- ## Issue 2: Extend Configuration System for LLM Integration **Priority**: HIGH | **Effort**: 1 day | **Dependencies**: Issue 1 ### User Story As a user, I want to configure my OpenRouter API credentials and LLM preferences through MarkiTect's configuration system so that I can seamlessly use AI features. ### Description Extend the existing configuration management system to support OpenRouter API keys, model preferences, and LLM-related settings with proper validation and secure storage. ### Technical Implementation - **New Files**: None - **Modified Files**: - `markitect/config_manager.py` - `tests/test_issue_18_config_management.py` - **Dependencies**: Issue 1 ### Acceptance Criteria - [ ] Add openrouter.api_key, openrouter.default_model config keys - [ ] Implement sensitive data masking for API keys - [ ] Add validation for OpenRouter API key format - [ ] Support for model-specific settings (temperature, max_tokens) - [ ] CLI commands: `markitect config-set openrouter.api_key ` - [ ] CLI command: `markitect config-show --show-sensitive` - [ ] Configuration file format documentation - [ ] Tests for new configuration functionality --- ## Issue 3: Create LLM Content Context Builder **Priority**: HIGH | **Effort**: 3 days | **Dependencies**: Issue 1 ### User Story As a user, I want the LLM to have relevant context from my MarkiTect content when answering questions so that responses are accurate and cite my actual documents. ### Description Build a smart context builder that extracts relevant content from the MarkiTect database, uses FTS search for content discovery, and constructs context within token limits while maintaining source citations. ### Technical Implementation - **New Files**: - `markitect/llm/context_builder.py` - `markitect/llm/content_selector.py` - `tests/test_context_builder.py` - **Modified Files**: None - **Dependencies**: Issue 1 ### Acceptance Criteria - [ ] ContextBuilder class with intelligent content selection - [ ] Integration with existing FTS search capabilities - [ ] Token-aware context truncation and optimization - [ ] Source tracking and citation generation - [ ] Relevance scoring for content ranking - [ ] Support for different context strategies (recent, relevant, comprehensive) - [ ] Performance optimization for large content repositories - [ ] Unit tests with mock database content --- ## Issue 4: Enhance Natural Language Paradigm with Real LLM Integration **Priority**: MEDIUM | **Effort**: 2 days | **Dependencies**: Issues 1, 3 ### User Story As a user, I want to ask natural language questions about my content and receive intelligent, contextual responses from actual LLMs rather than mock responses. ### Description Upgrade the existing Natural Language Query Paradigm to use real OpenRouter LLM integration, replacing the current translation-based approach with context-aware LLM processing. ### Technical Implementation - **New Files**: None - **Modified Files**: - `markitect/query_paradigms/paradigms/natural_language_paradigm.py` - `tests/test_natural_language_paradigm.py` - **Dependencies**: Issues 1, 3 ### Acceptance Criteria - [ ] Replace query translation with direct LLM processing - [ ] Context injection from MarkiTect content - [ ] Source citations in LLM responses - [ ] Support for follow-up questions and conversations - [ ] Response formatting with markdown support - [ ] Error handling for LLM API failures - [ ] Integration with existing paradigm registry - [ ] Comprehensive tests with mock LLM responses --- ## Issue 5: Add Basic LLM CLI Commands **Priority**: MEDIUM | **Effort**: 1 day | **Dependencies**: Issues 1, 2 ### User Story As a user, I want basic CLI commands to test my OpenRouter connection and perform simple LLM interactions so that I can verify my setup and explore AI capabilities. ### Description Implement fundamental CLI commands for LLM interaction, including connection testing, model listing, and basic query execution with MarkiTect context. ### Technical Implementation - **New Files**: - `markitect/llm/commands.py` - `tests/test_llm_commands.py` - **Modified Files**: - `markitect/cli.py` - **Dependencies**: Issues 1, 2 ### Acceptance Criteria - [ ] Command: `markitect llm test` - Test OpenRouter connection - [ ] Command: `markitect llm models` - List available models - [ ] Command: `markitect llm ask "question"` - Basic LLM query - [ ] Command: `markitect llm chat` - Interactive chat mode - [ ] Proper error handling and user feedback - [ ] Integration with existing Click CLI framework - [ ] Support for configuration options and flags - [ ] CLI help documentation and examples --- ## Issue 6: Implement Template Field Analysis and Parsing **Priority**: HIGH | **Effort**: 3 days | **Dependencies**: None ### User Story As a template creator, I want enhanced template parsing that can identify field types, descriptions, and validation rules so that the system can intelligently handle template completion. ### Description Extend the existing template system to parse advanced field annotations, extract metadata, and support various input types for the interactive questionnaire system. ### Technical Implementation - **New Files**: - `markitect/template/field_analyzer.py` - `markitect/template/field_types.py` - `tests/test_template_field_analyzer.py` - **Modified Files**: - `markitect/template/parser.py` - **Dependencies**: None ### Acceptance Criteria - [ ] Parse template annotations: `{{name:string:Your full name}}` - [ ] Support field types: text, choice, date, number, boolean, email - [ ] Extract field descriptions and validation rules - [ ] Identify required vs optional fields - [ ] Support nested field structures and conditional logic - [ ] Backward compatibility with existing templates - [ ] Field validation and constraint checking - [ ] Comprehensive tests with various template formats --- ## Issue 7: Create Interactive Template Questionnaire System **Priority**: MEDIUM | **Effort**: 4 days | **Dependencies**: Issue 6 ### User Story As a user, I want to fill templates through an interactive terminal questionnaire that guides me through each field with appropriate input validation and user-friendly prompts. ### Description Build a terminal-based interactive questionnaire engine that presents template fields to users, handles different input types, validates responses, and provides a smooth completion experience. ### Technical Implementation - **New Files**: - `markitect/template/questionnaire.py` - `markitect/template/input_handlers.py` - `tests/test_template_questionnaire.py` - **Modified Files**: None - **Dependencies**: Issue 6 ### Acceptance Criteria - [ ] Interactive terminal interface with clear prompts - [ ] Support for all field types (text, choice, date, number, boolean) - [ ] Input validation with re-prompting on errors - [ ] Progress tracking and partial save capability - [ ] Skip/default options for optional fields - [ ] Colorful and user-friendly terminal output - [ ] Keyboard shortcuts and navigation - [ ] Tests with simulated user input --- ## Issue 8: Implement User Profile Management System **Priority**: HIGH | **Effort**: 2 days | **Dependencies**: None ### User Story As a user, I want to create and manage multiple profiles containing my personal and professional information so that templates can be auto-filled with my preferred data. ### Description Create a comprehensive user profile management system with CRUD operations, multiple profile support, and integration with the database for persistent storage. ### Technical Implementation - **New Files**: - `markitect/profile/__init__.py` - `markitect/profile/manager.py` - `markitect/profile/schema.py` - `markitect/profile/commands.py` - `tests/test_profile_manager.py` - **Modified Files**: - `markitect/cli.py` - Database schema (migration script needed) - **Dependencies**: None ### Acceptance Criteria - [ ] Profile CRUD operations (create, read, update, delete) - [ ] Support for multiple named profiles (personal, work, etc.) - [ ] JSON Schema validation for profile data - [ ] Database integration with user_profiles table - [ ] CLI commands: `markitect profile create/show/set/list/export` - [ ] Profile inheritance and template support - [ ] Data export/import functionality - [ ] Comprehensive tests for all profile operations --- ## Issue 9: Develop LLM-Powered Template Auto-Fill System **Priority**: MEDIUM | **Effort**: 4 days | **Dependencies**: Issues 1, 6, 8 ### User Story As a user, I want templates to be automatically filled with appropriate values based on my profile and the template context using AI assistance so that I can complete forms quickly and accurately. ### Description Create an intelligent auto-fill system that uses OpenRouter LLMs to suggest field values based on user profiles, template context, and learned preferences. ### Technical Implementation - **New Files**: - `markitect/template/auto_filler.py` - `markitect/template/smart_suggestions.py` - `tests/test_template_auto_filler.py` - **Modified Files**: None - **Dependencies**: Issues 1, 6, 8 ### Acceptance Criteria - [ ] LLMAutoFiller class with context-aware suggestions - [ ] Integration with user profile data for personalization - [ ] Smart field completion based on template purpose - [ ] Learning from user corrections and preferences - [ ] Support for complex field generation (descriptions, summaries) - [ ] Confidence scoring for suggestions - [ ] Fallback mechanisms when LLM is unavailable - [ ] Tests with mock LLM responses and profiles --- ## Issue 10: Integrate Advanced Template Fill Commands **Priority**: LOW | **Effort**: 2 days | **Dependencies**: Issues 7, 9 ### User Story As a user, I want advanced template filling commands that combine interactive questionnaires with AI auto-fill so that I can choose the most appropriate completion method for each situation. ### Description Create comprehensive CLI commands that integrate all template filling capabilities, offering multiple modes (auto, interactive, guided) and advanced options for different use cases. ### Technical Implementation - **New Files**: - `markitect/template/fill_commands.py` - `tests/test_template_fill_commands.py` - **Modified Files**: - `markitect/cli.py` - **Dependencies**: Issues 7, 9 ### Acceptance Criteria - [ ] Command: `markitect template-fill