feat: add 'get' command to CLI and getDocument helper function

refactor: check only first metadata entry for processed_at timestamp

refactor: use collection ID directly and return true when processed_at is missing

refactor: move chunk ID creation to needsUpdate and pass document ID instead of chunk IDs

refactor: rename checkDocumentNeedsUpdate to needsUpdate

refactor: combine checkDocument and checkDocumentNeedsUpdate functions

feat: add timestamp-based document update checking functionality

feat: add timestamp to chunk metadata for processing tracking

fix: keep only metadatas in checkDocument method

feat: add limit parameter to checkDocument method

feat: include documents in checkDocument method response

fix: remove "documents" from include array in checkDocument method

feat: add include parameter with metadatas and documents to checkDocument method

refactor: rename getDocuments to checkDocument for clarity

fix: change "Original ID" to "Document ID" in output message

feat: skip files with no valid chunks and no embeddings created

chore: remove debug echo statement for document existence check

fix: check first 3 chunk numbers to detect existing documents in ChromaDB

feat: add document existence check before processing files in ChromaDB

feat: skip files starting with underscore when sending to chromadb

feat: implement title-based tagging for document chunks in chromadb_cli

fix: update default values for think and use_tools configuration options

chore: disable think and use_tools features by default

refactor: update AI thinking content extraction to use XML tags instead of backticks

refactor: remove redundant action check for showing thinking content modal