Aleksandr Prilipko 0a2609d538 fix(tools): file_read binary file support — PDF extraction + lossy fallback ... Add cascading fallback to file_read tool: UTF-8 → PDF text extraction (via pdf-extract) → lossy UTF-8 conversion. Binary files no longer produce errors; PDFs return extracted text, other binaries get lossy output with U+FFFD replacement characters. Changes: - Cargo.toml: add rag-pdf to default features - file_read.rs: cascading fallback logic + try_extract_pdf_text helper - file_read.rs: update tool description - test_document.pdf: replace empty fixture with PDF containing "Hello PDF" - Tests: remove file_read_rejects_binary_pdf, add unit + e2e tests for PDF extraction and lossy binary reads (including live OpenAI Codex e2e) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-02-21 13:03:13 +08:00
..
hello.mp3	test(channel): add live e2e test for voice transcription + reply cache	2026-02-21 12:57:32 +08:00
test_document.pdf	fix(tools): file_read binary file support — PDF extraction + lossy fallback	2026-02-21 13:03:13 +08:00
test_photo.jpg	fix(channel): use [IMAGE:] marker for photo attachments, add e2e vision tests	2026-02-21 12:57:32 +08:00