v0.4.8

What's Changed

• Improve citation mapping with systematic algorithm and confidence scoring by @agamm in #37

Full Changelog: v0.4.6...v0.4.8

v0.4.6

What's Changed

• Fix JSON serialization issue with date fields by @agamm in #36

Full Changelog: v0.4.5...v0.4.6

v0.4.5

What's Changed

• Add save_to_json() convenience method to JobResult by @agamm in #35

Full Changelog: v0.4.4...v0.4.5

v0.4.4

What's Changed

• Fix Citation serialization issue causing truncated JSON files by @agamm in #34

Full Changelog: v0.4.3...v0.4.4

v0.4.3

What's Changed

• Bug/fix citation mapping by @agamm in #33

Full Changelog: v0.4.2...v0.4.3

v0.4.2

What's Changed

• Fix progress bar threading, status display, and PDF token estimation by @agamm in #32

Full Changelog: v0.4.1...v0.4.2

v0.4.1

PDF Cost Estimation Fix & Dry Run Feature

Major Improvements

• Fixed PDF cost estimation - Previously overestimated by ~50x (e.g. $18.70 → $0.32)
• Added dry run feature - Preview costs before execution with batch.run(dry_run=True)
• Intelligent PDF processing - Uses text extraction for accurate token counting

New Features

• PDF text extraction with pypdf library
• Configurable token coefficient (1.5x default for PDF overhead)
• Smart classification of textual vs image-based PDFs
• Comprehensive test coverage for PDF features

Improvements

• Reduced logging verbosity for cleaner output
• Better error handling for PDF processing
• Fallback to page-based estimation for image PDFs

No breaking changes

All existing code continues to work unchanged.

v0.4.0

What's Changed

• Add Google Gemini support with async processing by @Copilot in #29

New Contributors

• @Copilot made their first contribution in #29

Full Changelog: v0.3.8...v0.4.0

v0.3.8

What's Changed

• Add tests by @agamm in #28

Full Changelog: v0.3.7...v0.3.8

v0.3.7

What's Changed

• Move file content to be a reference in state file by @agamm in #27

Full Changelog: v0.3.6...v0.3.7