- Primary: Detect sections via Heading 1 styles (structured)
- Fallback: Detect chapters via "Chapter X" text patterns
- Add text_patterns_only flag to skip heading styles (for messy docs)
This handles both well-structured business documents (manuals, PRDs)
and narrative content (books with explicit chapter headings).
New tools for easier document navigation:
- get_document_outline: Structured view of headings with chapter detection
- check_style_consistency: Find formatting issues and missing chapters
- search_document: Search with context and chapter location
All tools tested with 200+ page manuscript. Detects issues like
Chapter 3 being styled as "normal" instead of "Heading 1".
python-docx elements don't support xpath() with namespaces kwarg.
The calls silently failed in try/except blocks, causing chapter search
and heading detection to never find matches.
Fixed by replacing xpath(..., namespaces={...}) with:
- findall('.//' + qn('w:t')) for text elements
- find(qn('w:pPr')) + find(qn('w:pStyle')) for style detection
- get(qn('w:val')) for attribute values
Also fixed logic bug where elif prevented short-text fallback from
running when a non-heading style existed on the paragraph.
Links README to Ryan's AI discernment article, which discusses
the documentation rewrite process and connects to the model's
perspective in the collaborations archive.
- Self-contained HTML dashboard with MS Office 365 design
- pytest plugin captures inputs, outputs, and errors per test
- Unified orchestrator runs pytest + torture tests together
- Test files persisted in reports/test_files/ with relative links
- GitHub Actions workflow with PR comments and job summaries
- Makefile with convenient commands (test, view-dashboard, etc.)
- Works offline with embedded JSON data (no CORS issues)
