Two root causes of metric fragmentation observed in collection checks:
1. Schema's Economic Domain used free-form examples ("labour economics,
trade theory") which overrode the enum in extraction-rules.md, causing
the LLM to produce multi-domain strings and non-canonical values.
Fix: schema now specifies the exact 7-value enum with descriptions.
2. Source Chapter had no format constraint, producing 9 different formats
for 7 chapters (full titles, mixed Roman/Arabic numerals, asterisks).
Fix: extraction-rules now mandate "Book [Roman], Chapter [n]" exactly.
These fixes are prerequisites for clean reprocessing (S3.2 continuation).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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>
