fix: highlight 缓存改用 LRUCache 降低内存开销

- Fallback.tsx: 手动 Map LRU 替换为 lru-cache 的 LRUCache
- Markdown.tsx: tokenCache 同样替换为 LRUCache
- color-diff-napi: 新增行级 hljs AST 缓存，避免终端 resize 时重复高亮

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

packages/color-diff-napi/src/index.ts

@@ -502,6 +502,50 @@ function hasRootNode(emitter: unknown): emitter is { rootNode: HljsNode } {
 
 let loggedEmitterShapeError = false
 
+// Per-line hljs AST cache — ColorFile.render re-highlights every line on
+// width change (terminal resize). The AST is theme-independent; flattenHljs
+// applies theme colors separately. Capped at 2048 entries (~1 MB typical).
+const HL_LINE_CACHE_MAX = 2048
+const hlLineCache = new Map<string, HljsNode | null>()
+function cachedHljsAst(
+  lang: string,
+  code: string,
+): HljsNode | null {
+  const key = lang + '\0' + code
+  const hit = hlLineCache.get(key)
+  if (hit !== undefined) return hit
+  let result
+  try {
+    result = hljsApi().highlight(code, {
+      language: lang,
+      ignoreIllegals: true,
+    })
+  } catch {
+    hlLineCache.set(key, null)
+    return null
+  }
+  const emitter = result._emitter || {}
+  if (!hasRootNode(emitter)) {
+    if (!loggedEmitterShapeError) {
+      loggedEmitterShapeError = true
+      logError(
+        new Error(
+          `color-diff: hljs emitter shape mismatch (keys: ${Object.keys(emitter).join(',')}). Syntax highlighting disabled.`,
+        ),
+      )
+    }
+    hlLineCache.set(key, null)
+    return null
+  }
+  const node = emitter.rootNode
+  if (hlLineCache.size >= HL_LINE_CACHE_MAX) {
+    const first = hlLineCache.keys().next().value
+    if (first !== undefined) hlLineCache.delete(first)
+  }
+  hlLineCache.set(key, node)
+  return node
+}
+
 function highlightLine(
   state: { lang: string | null; stack: unknown },
   line: string,
@@ -512,30 +556,12 @@ function highlightLine(
   if (!state.lang) {
     return [[defaultStyle(theme), code]]
   }
-  let result
+  const rootNode = cachedHljsAst(state.lang, code)
-  try {
+  if (!rootNode) {
-    result = hljsApi().highlight(code, {
-      language: state.lang,
-      ignoreIllegals: true,
-    })
-  } catch {
-    // hljs throws on unknown language despite ignoreIllegals
-    return [[defaultStyle(theme), code]]
-  }
-  const emitter = result._emitter || {};
-  if (!hasRootNode(emitter)) {
-    if (!loggedEmitterShapeError) {
-      loggedEmitterShapeError = true
-      logError(
-        new Error(
-          `color-diff: hljs emitter shape mismatch (keys: ${Object.keys(emitter).join(',')}). Syntax highlighting disabled.`,
-        ),
-      )
-    }
     return [[defaultStyle(theme), code]]
   }
   const blocks: Block[] = []
-  flattenHljs(emitter.rootNode, theme, undefined, blocks)
+  flattenHljs(rootNode, theme, undefined, blocks)
   return blocks
 }
 

src/components/HighlightedCode/Fallback.tsx

@@ -1,6 +1,7 @@
 import { extname } from 'path'
 import React, { Suspense, use, useMemo } from 'react'
 import { Ansi, Text } from '@anthropic/ink'
+import { LRUCache } from 'lru-cache'
 import { getCliHighlightPromise } from '../../utils/cliHighlight.js'
 import { logForDebugging } from '../../utils/debug.js'
 import { convertLeadingTabsToSpaces } from '../../utils/file.js'
@@ -16,8 +17,7 @@ type Props = {
 // Module-level highlight cache — hl.highlight() is the hot cost on virtual-
 // scroll remounts. useMemo doesn't survive unmount→remount. Keyed by hash
 // of code+language to avoid retaining full source strings (#24180 RSS fix).
-const HL_CACHE_MAX = 500
+const hlCache = new LRUCache<string, string>({ max: 500 })
-const hlCache = new Map<string, string>()
 function cachedHighlight(
   hl: NonNullable<Awaited<ReturnType<typeof getCliHighlightPromise>>>,
   code: string,
@@ -25,16 +25,8 @@ function cachedHighlight(
 ): string {
   const key = hashPair(language, code)
   const hit = hlCache.get(key)
-  if (hit !== undefined) {
+  if (hit !== undefined) return hit
-    hlCache.delete(key)
-    hlCache.set(key, hit)
-    return hit
-  }
   const out = hl.highlight(code, { language })
-  if (hlCache.size >= HL_CACHE_MAX) {
-    const first = hlCache.keys().next().value
-    if (first !== undefined) hlCache.delete(first)
-  }
   hlCache.set(key, out)
   return out
 }

src/components/Markdown.tsx

@@ -1,5 +1,6 @@
 import { marked, type Token, type Tokens } from 'marked'
 import React, { Suspense, use, useMemo, useRef } from 'react'
+import { LRUCache } from 'lru-cache'
 import { useSettings } from '../hooks/useSettings.js'
 import { Ansi, Box, useTheme } from '@anthropic/ink'
 import {
@@ -22,8 +23,7 @@ type Props = {
 // scrolling back to a previously-visible message re-parses. Messages are
 // immutable in history; same content → same tokens. Keyed by hash to avoid
 // retaining full content strings (turn50→turn99 RSS regression, #24180).
-const TOKEN_CACHE_MAX = 500
+const tokenCache = new LRUCache<string, Token[]>({ max: 500 })
-const tokenCache = new Map<string, Token[]>()
 
 // Characters that indicate markdown syntax. If none are present, skip the
 // ~3ms marked.lexer call entirely — render as a single paragraph. Covers
@@ -55,19 +55,8 @@ function cachedLexer(content: string): Token[] {
   }
   const key = hashContent(content)
   const hit = tokenCache.get(key)
-  if (hit) {
+  if (hit) return hit
-    // Promote to MRU — without this the eviction is FIFO (scrolling back to
-    // an early message evicts the very item you're looking at).
-    tokenCache.delete(key)
-    tokenCache.set(key, hit)
-    return hit
-  }
   const tokens = marked.lexer(content)
-  if (tokenCache.size >= TOKEN_CACHE_MAX) {
-    // LRU-ish: drop oldest. Map preserves insertion order.
-    const first = tokenCache.keys().next().value
-    if (first !== undefined) tokenCache.delete(first)
-  }
   tokenCache.set(key, tokens)
   return tokens
 }