3-stage plan: decouple (RunConfig/LLMResponse move + app name parameterization) → extract to standalone package → adopt in first consumer. Registered as workstream in Custodian State Hub. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| 260210-llm-integration | ||
| eat-the-frog | ||
| helper-command | ||
| infospace-tooling | ||
| llm-shared-library | ||
| prompt-dependency-resolution | ||
| README.md | ||
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