perf: 优化内存与遥测管理，启用 Vite minify

- 禁用 HISTORY_SNIP feature flag 并新增 proactiveTruncate 防止无 compact_boundary 时内存无限增长
- 跳过未启用 telemetry 时的 OTel 初始化，防止长会话 PerformanceMeasure 堆积
- OTel 导出遇 401/403 自动关闭 reader，防止 handle 泄漏
- Vite 构建启用 minify

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

Author: claude-code-best

scripts/defines.ts

@@ -49,7 +49,7 @@ export const DEFAULT_BUILD_FEATURES = [
   'DAEMON', // 守护进程模式，长驻 supervisor 管理后台 worker（非 GB 级主因）
   'ACP', // ACP 代理协议，支持外部 agent 接入
   'WORKFLOW_SCRIPTS', // 工作流脚本（.claude/workflows/ 中的 YAML/MD）
-  'HISTORY_SNIP', // 历史消息裁剪，压缩上下文窗口
+  // 'HISTORY_SNIP', // 历史消息裁剪，压缩上下文窗口
   // 'CONTEXT_COLLAPSE', // 已禁用：实现是空壳 stub，启用后会抑制 auto compact 导致上下文管理完全失效
   'MONITOR_TOOL', // Monitor 工具，流式监控后台进程输出
   // 'FORK_SUBAGENT',            // 已禁用：显式 `fork: true` 参数触发 fork 路径（继承父级上下文和模型），不影响 forceAsync 和探索任务模型选择

src/QueryEngine.ts

@@ -1003,6 +1003,15 @@ export class QueryEngine {
               uuid: msg.uuid,
             }
           }
+          // Proactive truncation: prevent unbounded growth when API doesn't
+          // return compact_boundary (e.g. third-party compat layers).
+          if (feature('HISTORY_SNIP') && snipModule) {
+            const truncated = snipModule.proactiveTruncate(this.mutableMessages)
+            if (truncated !== this.mutableMessages) {
+              this.mutableMessages.length = 0
+              this.mutableMessages.push(...truncated)
+            }
+          }
           // Don't yield other system messages in headless mode
           break
         }

src/entrypoints/init.ts

@@ -320,6 +320,16 @@ async function doInitializeTelemetry(): Promise<void> {
     return
   }
 
+  // Skip entire OTel initialization when telemetry is not enabled.
+  // Prevents PerformanceMeasure accumulation in long-running sessions.
+  if (!isEnvTruthy(process.env.CLAUDE_CODE_ENABLE_TELEMETRY)) {
+    telemetryInitialized = true
+    logForDebugging(
+      '[3P telemetry] Skipped — CLAUDE_CODE_ENABLE_TELEMETRY not set',
+    )
+    return
+  }
+
   // Set flag before init to prevent double initialization
   telemetryInitialized = true
   try {

src/services/compact/snipCompact.ts

@@ -163,3 +163,77 @@ export function isSnipRuntimeEnabled(): boolean {
 export function shouldNudgeForSnips(messages: Message[]): boolean {
   return messages.length >= SNIP_NUDGE_THRESHOLD
 }
+
+/**
+ * Maximum total character length of message content before proactive
+ * truncation kicks in. ~150 MB of string data corresponds to roughly
+ * 1.5x the default 200k-token context window at 4 chars/token — well
+ * beyond what any model can actually use in a single request.
+ */
+const PROACTIVE_TRUNCATE_CHARS = 150_000_000
+
+/**
+ * Minimum number of messages to keep when falling back to tail-only
+ * retention (i.e. when no compact_boundary exists in the array).
+ */
+const PROACTIVE_TRUNCATE_MIN_TAIL = 50
+
+/**
+ * Proactively truncate old messages when the in-memory store grows too
+ * large. Unlike `snipCompactIfNeeded` (which waits for a snip_boundary
+ * from the API), this runs client-side after every push — ensuring
+ * unbounded growth cannot happen even when the API never returns a
+ * compact_boundary (e.g. third-party compat layers).
+ *
+ * Strategy:
+ * 1. If a `compact_boundary` exists, keep it and everything after it.
+ * 2. Otherwise, keep only the last `PROACTIVE_TRUNCATE_MIN_TAIL` messages.
+ *
+ * Returns the same array reference when no truncation is needed.
+ */
+export function proactiveTruncate(messages: Message[]): Message[] {
+  if (messages.length < PROACTIVE_TRUNCATE_MIN_TAIL) return messages
+
+  let totalChars = 0
+  for (const msg of messages) {
+    const content = msg.message?.content
+    if (typeof content === 'string') {
+      totalChars += content.length
+    } else if (Array.isArray(content)) {
+      for (const block of content) {
+        if (typeof block === 'string') {
+          totalChars += (block as string).length
+        } else if (block && typeof block === 'object') {
+          const obj = block as unknown as Record<string, unknown>
+          const text = obj.text ?? obj.content
+          if (typeof text === 'string') {
+            totalChars += text.length
+          }
+        }
+      }
+    }
+  }
+
+  if (totalChars < PROACTIVE_TRUNCATE_CHARS) return messages
+
+  // Find last compact_boundary — the standard anchor point
+  let boundaryIdx = -1
+  for (let i = messages.length - 1; i >= 0; i--) {
+    const msg = messages[i]!
+    if (
+      msg.type === 'system' &&
+      (msg as Record<string, unknown>).subtype === 'compact_boundary'
+    ) {
+      boundaryIdx = i
+      break
+    }
+  }
+
+  const keepFrom =
+    boundaryIdx >= 0
+      ? boundaryIdx
+      : Math.max(0, messages.length - PROACTIVE_TRUNCATE_MIN_TAIL)
+  if (keepFrom === 0) return messages
+
+  return messages.slice(keepFrom)
+}

src/utils/telemetry/instrumentation.ts

@@ -206,10 +206,49 @@ async function getOtlpReaders() {
 
   return exporters.map(exporter => {
     if ('export' in exporter) {
-      return new PeriodicExportingMetricReader({
+      const reader = new PeriodicExportingMetricReader({
         exporter,
         exportIntervalMillis: exportInterval,
       })
+      // Wrap the export callback to auto-shutdown the reader on auth
+      // failures (401/403). Without this the PeriodicExportingMetricReader's
+      // internal setInterval keeps retrying forever, leaking handles.
+      const originalExport = (
+        exporter as unknown as {
+          export: (
+            metrics: unknown,
+            callback: (result: { error?: Error }) => void,
+          ) => unknown
+        }
+      ).export.bind(exporter)
+      ;(
+        exporter as unknown as {
+          export: (
+            metrics: unknown,
+            callback: (result: { error?: Error }) => void,
+          ) => unknown
+        }
+      ).export = (metrics, callback) => {
+        return originalExport(metrics, result => {
+          if (result.error) {
+            const msg = result.error.message || ''
+            if (
+              msg.includes('401') ||
+              msg.includes('403') ||
+              msg.includes('Unauthorized') ||
+              msg.includes('authentication')
+            ) {
+              logForDebugging(
+                `[3P telemetry] Auth error detected, shutting down metric reader`,
+                { level: 'error' },
+              )
+              void reader.shutdown()
+            }
+          }
+          callback(result)
+        })
+      }
+      return reader
     }
     return exporter
   })

vite.config.ts

@@ -83,7 +83,7 @@ export default defineConfig({
     target: 'es2020',
     copyPublicDir: false,
     sourcemap: false,
-    minify: false,
+    minify: true,
 
     // SSR build mode — uses Rollup with Node.js target
     ssr: true,