Skip to content

fix: clarify single-page toc detection#264

Draft
Bortlesboat wants to merge 1 commit intoVectifyAI:mainfrom
Bortlesboat:codex/single-page-toc-guard
Draft

fix: clarify single-page toc detection#264
Bortlesboat wants to merge 1 commit intoVectifyAI:mainfrom
Bortlesboat:codex/single-page-toc-guard

Conversation

@Bortlesboat
Copy link
Copy Markdown

Summary

  • clarify the single-page TOC detector prompt so structured document content is not treated as a table of contents just because it has numbered sections
  • call out that a true table of contents should reference content elsewhere in the document
  • add a regression test that captures the prompt sent to the detector

Verification

  • RED: python -m pytest tests/test_toc_detector.py -q failed before the prompt guidance was added
  • GREEN: python -m pytest tests/test_toc_detector.py -q
  • python -m compileall -q pageindex tests
  • git diff --check -- pageindex/page_index.py tests/test_toc_detector.py

Closes #203

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Single-page documents incorrectly identified as TOC, skipping all content

1 participant