fix(embedding): drop degenerate tiny chunks before embedding (#764) (#768)

Make embedding batch size configurable (#742)

feat: use token-based sizing for embedding chunking (#749)

fix: narrow exception to (ImportError, OSError) and include error in log

fix: handle tiktoken network errors in offline environments (issue #264)

fix: embedding batch sizing and 413 error classification (1.7.4)

fix: resolve merge conflicts and apply extract_text_content to all graphs

fix: restore graceful fallback in get_default_model and truncate error messages

feat: improve error clarity for LLM provider failures (#506)

feat: credential-based API key management (#477) (#540)

fix: handle structured content format in LLM response parsing

feat: add environment variables for chunk size configuration (#520)

fix: use sync get_state() for SqliteSaver compatibility (#519)

Fix re-embedding issues and improve retry strategy (#515)

feat: use standard HTTP_PROXY/HTTPS_PROXY environment variables (#499)

feat: message counting for chat sessions (#430)

feat: add cascade deletion for notebooks with delete preview (#471)

feat: content-type aware chunking and unified embedding (#444)

Feat/localization tests docker (#371)

docs: generate comprehensive CLAUDE.md reference documentation across codebase

fix: strip <think> tags from chat responses

fix: enhance chat reference links and prevent text overflow (#173)

feat: add persistent tiktoken cache to reduce re-downloads (#171)

fix: max tokens max is 8192 now

Version 1 (#160)