{"version":"2.1.224","anchor":"memory-index-built-by-scanning-files-rather-than-read-from-d","canonical_anchor":"memory-index-built-by-scanning-files-rather-than-read-from-d","heading":"Memory index built by scanning files rather than read from disk","tier":"soon","area":"Memory","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.224\/e\/memory-index-built-by-scanning-files-rather-than-read-from-d","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.224","markdown":"### Memory index built by scanning files rather than read from disk\n\nA memory index can be generated by scanning recent files rather than read from a stored index.\n\n**What**\n\nNew code builds a memory index at load time by walking the memory directory, taking the most recently modified files and reading each one's `name` and `description` header fields, falling back to the filename and first heading. The result is rendered as markdown and truncated at a byte budget. It runs only for stores that ask for a generated index; stores without that keep using an index file on disk.\n\n**Details**\n\n- The walk skips dotfiles and is capped on depth, number of files and per-file size.\n- Emits `tengu_memdir_index_assembled` with scan counts, how many files needed the filename fallback, whether output was truncated, and whether a disk index was superseded.\n- The consolidation prompt has a matching variant that drops the \"update the index file\" step in favour of keeping each file's header fields accurate.\n\n**Evidence**\n\n`tengu_memdir_index_assembled`\n\n- Area: Memory\n- Tier: Nothing to try yet\n- Useful: 2\/5\n- Signal: 4\/5\n- Present in the build but not switched on"}