ui: reduce per-token render cost when streaming (#26053)

* performance harness - the empirical root Assisted-by: Claude Opus 4.8 * 210.36ms -> 2.67ms per streamed token Assisted-by: Claude Opus 4.8 * 11.58ms -> 0.62ms per streamed token Assisted-by: Claude Opus 4.8 * 22.02ms -> 3.33ms per streamed token Assisted-by: Claude Opus 4.8 * 3.07ms -> 1.36ms per streamed token at 40 messages Assisted-by: Claude Opus 4.8 --------- Co-authored-by: Zach Winter <dmtommy@icloud.com>
2026-07-24 22:09:46 +02:00
parent 96013c5112
commit 555881ebc8
18 changed files with 1037 additions and 35 deletions
@@ -107,6 +107,15 @@
 		return null;
 	});
 	const liveSvgHtml = $derived(streamingSvgCode !== null ? sanitizeSvg(streamingSvgCode) : '');
+
+	// Derived rather than called inline in the template so it only recomputes when
+	// the block actually changes. Auto-detection is disabled while streaming: it
+	// costs ~38ms a call and re-guesses the language on every chunk.
+	const streamingCodeHtml = $derived(
+		incompleteCodeBlock
+			? highlightCode(incompleteCodeBlock.code, incompleteCodeBlock.language || 'text', false)
+			: ''
+	);
 	let previewDialogOpen = $state(false);
 	let previewCode = $state('');
 	let previewLanguage = $state('text');
@@ -903,10 +912,7 @@
 				>
 					<pre class="streaming-code-pre"><code
 							class="hljs language-{incompleteCodeBlock.language || 'text'}"
-							>{@html highlightCode(
-								incompleteCodeBlock.code,
-								incompleteCodeBlock.language || 'text'
-							)}</code
+							>{@html streamingCodeHtml}</code
 						></pre>
 				</div>
 			</div>