Files
DocsGPT/docs/content/Models
Alex 1f86139b9c fix(compression,llm): address review — exact point dedupe, marked summary rows, opaque cache key
- append_compression_point only skips a point when both query_index and
  compressed_summary are present and match the last one; points without
  those fields (as in the repository tests) were all being treated as
  duplicates.
- The incremental compression tail and the orchestrator's "anything new
  since the last point" check exclude the visible summary row, which the
  prompt already receives through existing_compressions.
- Summary rows carry a persisted metadata marker; replay filters on the
  marker, and falls back to the label only for rows written before it that
  have no tool calls and no per-turn metadata, so a user who types the
  label text keeps their turn.
- The prompt_cache_key is a hash of the user id, never the id itself.
- Describe truncation="auto" as dropping the oldest items.
2026-09-05 09:30:13 +01:00
..