tegwick
fecc2fd4fa
Implements markitect/llm/ package with concrete LLMAdapter implementations:
- OpenRouterAdapter: HTTP via urllib with retry/backoff on 429/5xx
- ClaudeCodeAdapter: subprocess-based Claude CLI with stdin piping
- Factory pattern: create_adapter("openrouter") or create_adapter("claude-code")
- API key resolution chain: constructor > env var > project-root key file
- 42 unit tests, 2 integration tests (gated on API key / CLI availability)
Also adds the infospace-with-history example with Wealth of Nations VSM
analysis pipeline, templates, schemas, source chapters, and processed
output for chapters 1-2. process_chapters.py now supports --provider
and --model flags for automatic LLM-driven processing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
MarkiTect Project Roadmap
This roadmap directory contains planning directories for roadmap topics.
- When starting to implement a topic its directory will be timestamped
- If implementing multiple topics in parallel use branches
- Keep current state of what's next to implement in TODO.md
- See ../history directory for closed topics
Naming Convention
Directory Format: yymmdd-topic-name
- Use 2-digit year prefix (e.g.,
260106-for 2026-01-06) - Lowercase topic names with hyphens
- Examples:
260106-semantic-document-validation,260105-schema-evolution
This convention keeps names concise while maintaining chronological sorting.
Purpose
This planning documentation serves multiple purposes:
- Implementation State Awareness: Allow for recovery after breaks or breakdowns
- Minimal Plan-Implement Loop: Don't complicate agentic coding with issue tracking if unnecessary
- Planning Info Analysis: Keeping the planning info allows for retrospective analyses to optimize
- Clean Repo Structure: Using roadmap/ for planning and TODO.md as current state helps stay organized
xxx