Skip to content

feat: connect FileAnalyzerAgent to real PDF extraction#7

Draft
khasinski wants to merge 1 commit intoactiveagents:mainfrom
khasinski:fix/file-analyzer-pdf-extraction
Draft

feat: connect FileAnalyzerAgent to real PDF extraction#7
khasinski wants to merge 1 commit intoactiveagents:mainfrom
khasinski:fix/file-analyzer-pdf-extraction

Conversation

@khasinski
Copy link
Contributor

Summary

  • Replace stubbed extract_pdf_content placeholder in FileAnalyzerAgent with actual PdfTextExtractor integration (the pdf-reader gem was already installed but unused by the agent)
  • Replace raw File.read in extract_text/summarize_document with DocumentTextExtractor for format-aware extraction, with fallback for unsupported types
  • Write real prompt templates for analyze_pdf, extract_text, and summarize_document (were scaffold placeholders)
  • Handle PdfTextExtractor::ExtractionError gracefully

Test plan

  • Full suite: 293 runs, 744 assertions, 0 failures, 0 errors

- Replace stubbed extract_pdf_content with PdfTextExtractor integration
  (pdf-reader gem was already installed but unused by the agent)
- Replace raw File.read in extract_text/summarize_document with
  DocumentTextExtractor for format-aware extraction with fallback
- Write real prompt templates for analyze_pdf, extract_text, and
  summarize_document (were scaffold placeholders)
- Handle PdfTextExtractor::ExtractionError gracefully
- Update tests to match new extract_document_content method
@superconductor-for-github
Copy link

superconductor-for-github bot commented Feb 26, 2026

@khasinskiSuperconductor finishedView implementation


Standing by for instructions.

@khasinski khasinski marked this pull request as draft February 26, 2026 23:52
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.

1 participant