{"version":"2.1.207","anchor":"streaming-markdown-renderer-long-output-chunking","canonical_anchor":"streaming-markdown-renderer-long-output-chunking","heading":"Streaming Markdown Renderer: Long-Output Chunking","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.207\/e\/streaming-markdown-renderer-long-output-chunking","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.207","markdown":"### Streaming Markdown Renderer: Long-Output Chunking\n\nThe streaming markdown renderer (`StreamingMarkdown`) was rewritten to chunk large outputs into frozen segments rather than keeping everything in a single growing string. Open code fences are tracked across chunks so streaming inside a code block is handled correctly. This improves rendering performance and token-cache efficiency for very long streamed responses.\n\n**Evidence**\n\nChunked streaming renderer (search for `\"openFence\"` and `\"gapAfterChunks\"` in the renderer)"}