{"version":"2.1.165","anchor":"extended-thinking-support-in-conversation-summarizer","canonical_anchor":"extended-thinking-support-in-conversation-summarizer","heading":"Extended Thinking Support in Conversation Summarizer","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.165\/e\/extended-thinking-support-in-conversation-summarizer","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.165","markdown":"### Extended Thinking Support in Conversation Summarizer\n\nPreviously the summarizer that compresses long conversations always ran with `thinkingConfig: { type: \"disabled\" }`, regardless of what model was active. In this version a new capability check is evaluated at summarization time: if the current main-loop model is listed in the server-side `cedar_lagoon` capability map, the summarizer now inherits the same thinking configuration used by the main conversation loop. For models that are not in the list, the old behavior (thinking disabled) is unchanged.\n\nIn practice this means users running a model that supports extended thinking may notice more coherent or accurate conversation compaction when context windows fill up, since the summarizer can now reason before producing the summary.\n\n**Evidence**\n\nNew capability gate function (searches `clientDataCache?.cedar_lagoon`); summarization call site changed from hardcoded `{ type: \"disabled\" }` to `hM8(K.options.mainLoopModel) ? K.options.thinkingConfig : { type: \"disabled\" }` \u2014 search for `\"cedar_lagoon\"` to locate the check."}