tegwick
c0615c2d50
Some checks failed
Test Suite / code-quality (push) Has been cancelled
Test Suite / security-scan (push) Has been cancelled
Test Suite / unit-tests (3.11) (push) Has been cancelled
Test Suite / unit-tests (3.12) (push) Has been cancelled
Test Suite / integration-tests (push) Has been cancelled
Test Suite / e2e-tests (push) Has been cancelled
Test Suite / performance-tests (push) Has been cancelled
Test Suite / test-summary (push) Has been cancelled
Five improvements that eliminate most of the agent-in-the-loop friction
observed while closing out the 988-entity WoN evaluation (C.1):
1. Gemini adapter now retries on 429 + 5xx with exponential backoff
(same pattern already used by OpenRouter/OpenAI). Removes the need
for shell-level retry wrappers when hitting free-tier rate limits.
2. evaluate CLI prints the underlying error ("ERROR — HTTP 503 …")
instead of a bare "ERROR", so agents don't have to drop into Python
to diagnose transient failures.
3. --entity/--chapter now respect existing evaluation files by default
(previously only the full-collection pass did). New --force flag
opts into re-evaluation. Stops silently burning free-tier quota on
re-runs of the same slug.
4. --entity accepts hyphenated slugs (matching entity filenames) and
normalizes them to the underscore form used on disk. On a miss the
CLI suggests near matches instead of a bare "not found".
5. eval-summary --update-metrics is no longer destructive:
read_metrics_file/write_metrics_file preserve structured values
(type_distribution) and don't flatten ints to floats. Fixes a
silent data loss observed on every run.
Bonus: the evaluator field in written evaluation frontmatter now
falls back from run_config.model_name to the adapter's resolved model
(or the model echoed back in the API response), so rows no longer
show `evaluator: null` when --model is omitted.
Tests: new tests/unit/llm/test_gemini.py covers retry behavior;
tests/unit/infospace/test_history.py gains a round-trip test that
pins the type_distribution / int-preservation invariants.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
MarkiTect Documentation
Welcome to the MarkiTect documentation. This directory contains comprehensive documentation for developers, users, and contributors.
Documentation Structure
📐 Architecture Documentation (architecture/)
Deep technical documentation about system design, performance, and implementation details.
- Capabilities Architecture - Critical: How capabilities work as independent git submodules and separation of concerns
- Caching System - Why and how MarkiTect's AST caching delivers 60-85% performance improvements
- Coming soon: Database Schema, CLI Architecture
👥 User Guides (user-guides/)
End-user documentation for working with MarkiTect CLI and features.
- Coming soon: Getting Started, Command Reference, Best Practices
🔧 Development Documentation (development/)
Documentation for contributors and developers extending MarkiTect.
- Coming soon: Contributing Guide, Testing Strategy, Release Process
Quick Links
For Users
- Installation & Setup
- Command Reference (coming soon)
- Performance Guide (coming soon)
For Developers
- Architecture Overview - System design and component relationships
- Development Setup - Local development environment
- API Documentation (coming soon)
Project Management
- Project Status - Current development status
- Roadmap - Strategic development plan
- Current Tasks - Task management using Keep a Todofile format
Key Concepts
Core Architecture Principles
- Parse Once, Use Many Times - AST caching for 60-85% performance improvement
- Convention Over Configuration - Sensible defaults with minimal setup
- Schema-Driven Processing - Structured markdown with validation
- Relational Metadata - Database-powered document relationships
Performance Philosophy
MarkiTect treats markdown documents as structured, queryable data rather than plain text. This approach enables:
- Lightning-fast document processing through intelligent caching
- Complex querying and relationship management
- Schema validation and consistency enforcement
- Scalable performance that grows with your content
Contributing to Documentation
Documentation follows the same quality standards as code:
- Clear Structure - Logical organization and navigation
- Practical Examples - Real-world usage patterns
- Performance Context - Why architectural decisions matter
- User-Focused - Written for the intended audience
Documentation Standards
- Use clear, concise language
- Include practical examples
- Explain the "why" behind design decisions
- Keep technical accuracy as the highest priority
- Update docs when changing functionality
This documentation is maintained alongside the codebase. For the most current information, always refer to the latest version in the repository.