{"version":"1.0.77","anchor":"token-aware-conversation-summarization","canonical_anchor":"token-aware-conversation-summarization","heading":"Token-Aware Conversation Summarization","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/1.0.77\/e\/token-aware-conversation-summarization","release_url":"https:\/\/changelogs.core-directive.com\/v\/1.0.77","markdown":"### Token-Aware Conversation Summarization\n\n**What:** Intelligent conversation summarization that respects model token limits **How to use:** Conversation summaries are generated automatically when saving conversations. The system will indicate if summarizing partial conversations:\n\n`Summarizing last 5 of 10 messages (~2500 tokens)` **Details:**\n\n- Dynamically calculates available tokens based on model context window\n- Prioritizes recent messages when full conversation exceeds token budget\n- Transparently indicates when summaries are based on partial context\n- Uses efficient Haiku model with prompt caching for fast summarization\n- Generates concise 5-10 word titles for easy conversation browsing"}