{"version":"2.1.265","anchor":"recently-read-file-reconstruction-from-transcript-is-now-cap","canonical_anchor":"recently-read-file-reconstruction-from-transcript-is-now-cap","heading":"Recently-read file reconstruction from transcript is now capped and marked","tier":"internal","area":"Transcript","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265\/e\/recently-read-file-reconstruction-from-transcript-is-now-cap","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265","markdown":"### Recently-read file reconstruction from transcript is now capped and marked\n\nReconstructing recently-read files from chat history is now capped and marked as coming from history rather than disk\n\n**What**\n\nThe logic that reconstructs which files were recently read, by scanning back through the conversation transcript, now walks the transcript from newest to oldest, stops after finding a fixed maximum number of distinct files, and tags each reconstructed file entry with `contentFromTranscript` so later code can tell it was rebuilt from the conversation history rather than freshly read from disk.\n\n**Why**\n\nThis limits how much work and memory is spent reconstructing file history from a long conversation, and lets other parts of Claude Code distinguish transcript-derived file content from an up-to-date disk read, which matters if the file has changed since it was last read.\n\n- Area: Transcript\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}