{"version":"2.1.323","anchor":"document-and-pdf-tool-results-gain-page-images-and-text-laye","canonical_anchor":"document-and-pdf-tool-results-gain-page-images-and-text-laye","heading":"PDF and document results can include page images and page text","tier":"notice","area":"PDF Reading","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323\/e\/document-and-pdf-tool-results-gain-page-images-and-text-laye","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323","markdown":"### PDF and document results can include page images and page text\n\nDocument search results can now include page images, and large PDFs can come back with each page's text layer\n\n**Unclear.** It is unclear which tool returns these results, so it is not known where a reader would see them.\n\n**What**\n\nResults that Claude Code returns from documents and PDFs can now carry more:\n\n- Search results can say whether an image is attached and which page it is from. Page images for the hits are sent to the model as images after the main result.\n\n- A PDF page can carry its text layer, the text stored in the page. This only happens when no page range was asked for and the PDF was too large to read whole.\n\n- Pages taken from a PDF now also return a \"Text layer of page N\" block when the page has text.\n\n**Why**\n\nPDFs that are too large to read whole may now come back as text rather than failing.\n\n- Area: PDF Reading\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}