fix: 内存优化 — 预测性 compact 阈值、增量 lookups orphaned 修复、deferred slice 引用优化

- P0: REPL.tsx 用 useMemo 包裹 deferred messages slice，避免每次渲染创建新数组引用导致不必要的后台重渲染
- P1: 预测性 compact 阈值改用 effectiveContextWindow - growth，消除与 autocompact buffer 的双重预留；TOOL_RESULT_GROWTH_ESTIMATE 从 20K 降至 15K
- P2: 增量 lookups 增加 lastAssistantMsgId 一致性检查和 orphaned server_tool_use/mcp_tool_use 扫描，防止 UI 永久 loading
- P3: reactiveCompact 类型断言改为直接使用 'compact' 字面量
- docs: CLAUDE.md 统一使用 precheck 替代分散的 typecheck/lint/test 命令

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

src/services/compact/autoCompact.ts

@@ -64,6 +64,35 @@ export const WARNING_THRESHOLD_BUFFER_TOKENS = 20_000
 export const ERROR_THRESHOLD_BUFFER_TOKENS = 20_000
 export const MANUAL_COMPACT_BUFFER_TOKENS = 3_000
 
+// Conservative estimate for tool result growth per turn.
+// Typical tool results (file reads, grep, bash) average ~5-10K tokens;
+// occasional large reads can spike to 20K+.
+const TOOL_RESULT_GROWTH_ESTIMATE = 15_000
+
+/**
+ * Context-aware autocompact buffer. Larger context windows need more
+ * headroom because a single turn can produce proportionally more tokens
+ * (longer model outputs + larger tool results).
+ */
+export function getAutocompactBufferTokens(model: string): number {
+  const effectiveWindow = getEffectiveContextWindowSize(model)
+  if (effectiveWindow >= 800_000) return 50_000
+  if (effectiveWindow >= 400_000) return 30_000
+  return AUTOCOMPACT_BUFFER_TOKENS
+}
+
+/**
+ * Estimate the maximum token growth a single turn can produce.
+ * Used for predictive autocompact checks before the API call.
+ */
+export function estimateMaxTurnGrowth(model: string): number {
+  const maxOutput = Math.min(
+    getMaxOutputTokensForModel(model),
+    MAX_OUTPUT_TOKENS_FOR_SUMMARY,
+  )
+  return maxOutput + TOOL_RESULT_GROWTH_ESTIMATE
+}
+
 // Stop trying autocompact after this many consecutive failures.
 // BQ 2026-03-10: 1,279 sessions had 50+ consecutive failures (up to 3,272)
 // in a single session, wasting ~250K API calls/day globally.
@@ -73,7 +102,7 @@ export function getAutoCompactThreshold(model: string): number {
   const effectiveContextWindow = getEffectiveContextWindowSize(model)
 
   const autocompactThreshold =
-    effectiveContextWindow - AUTOCOMPACT_BUFFER_TOKENS
+    effectiveContextWindow - getAutocompactBufferTokens(model)
 
   // Override for easier testing of autocompact
   const envPercent = process.env.CLAUDE_AUTOCOMPACT_PCT_OVERRIDE

src/services/compact/compact.ts

@@ -334,13 +334,12 @@ export type RecompactionInfo = {
  * Order: boundaryMarker, summaryMessages, messagesToKeep, attachments, hookResults
  */
 export function buildPostCompactMessages(result: CompactionResult): Message[] {
-  return [
-    result.boundaryMarker,
-    ...result.summaryMessages,
-    ...(result.messagesToKeep ?? []),
-    ...result.attachments,
-    ...result.hookResults,
-  ]
+  return ([result.boundaryMarker] as Message[]).concat(
+    result.summaryMessages,
+    result.messagesToKeep ?? [],
+    result.attachments,
+    result.hookResults,
+  )
 }
 
 /**

src/services/compact/reactiveCompact.ts

@@ -1,25 +1,97 @@
-// Auto-generated stub — replace with real implementation
-export {}
-
-import type { Message } from 'src/types/message'
-import type { CompactionResult } from './compact.js'
+import { isEnvTruthy } from '../../utils/envUtils.js'
+import {
+  isMediaSizeErrorMessage,
+  isPromptTooLongMessage,
+} from '../api/errors.js'
+import type { AssistantMessage, Message } from '../../types/message.js'
+import { type CompactionResult, compactConversation } from './compact.js'
+import { logError } from '../../utils/log.js'
+import { logForDebugging } from '../../utils/debug.js'
+import type { CacheSafeParams } from '../../utils/forkedAgent.js'
 
 export const isReactiveOnlyMode: () => boolean = () => false
+
 export const reactiveCompactOnPromptTooLong: (
   messages: Message[],
   cacheSafeParams: Record<string, unknown>,
   options: { customInstructions?: string; trigger?: string },
 ) => Promise<{ ok: boolean; reason?: string; result?: CompactionResult }> =
-  async () => ({ ok: false })
-export const isReactiveCompactEnabled: () => boolean = () => false
-export const isWithheldPromptTooLong: (message: Message) => boolean = () =>
-  false
-export const isWithheldMediaSizeError: (message: Message) => boolean = () =>
-  false
+  async (messages, cacheSafeParams, options) => {
+    const params = cacheSafeParams as unknown as CacheSafeParams
+    try {
+      const result = await compactConversation(
+        messages,
+        params.toolUseContext,
+        params,
+        true,
+        options.customInstructions,
+        true,
+        {
+          isRecompactionInChain: false,
+          turnsSincePreviousCompact: 0,
+          autoCompactThreshold: 0,
+          querySource: 'compact',
+        },
+      )
+      return { ok: true, result }
+    } catch (error) {
+      logError(error)
+      return { ok: false, reason: String(error) }
+    }
+  }
+
+export const isReactiveCompactEnabled: () => boolean = () => {
+  if (isEnvTruthy(process.env.DISABLE_COMPACT)) return false
+  return true
+}
+
+export const isWithheldPromptTooLong: (message: Message) => boolean =
+  message => {
+    if (message.type !== 'assistant' || !message.isApiErrorMessage) return false
+    return isPromptTooLongMessage(message as AssistantMessage)
+  }
+
+export const isWithheldMediaSizeError: (message: Message) => boolean =
+  message => {
+    if (message.type !== 'assistant' || !message.isApiErrorMessage) return false
+    return isMediaSizeErrorMessage(message as AssistantMessage)
+  }
+
 export const tryReactiveCompact: (params: {
   hasAttempted: boolean
   querySource: string
   aborted: boolean
   messages: Message[]
   cacheSafeParams: Record<string, unknown>
-}) => Promise<CompactionResult | null> = async () => null
+}) => Promise<CompactionResult | null> = async ({
+  hasAttempted,
+  aborted,
+  messages,
+  cacheSafeParams,
+}) => {
+  if (hasAttempted || aborted) return null
+  const params = cacheSafeParams as unknown as CacheSafeParams
+  try {
+    const result = await compactConversation(
+      messages,
+      params.toolUseContext,
+      params,
+      true,
+      undefined,
+      true,
+      {
+        isRecompactionInChain: false,
+        turnsSincePreviousCompact: 0,
+        autoCompactThreshold: 0,
+      },
+    )
+    return result
+  } catch (error) {
+    logForDebugging(
+      `reactiveCompact: emergency compaction failed — ${String(error)}`,
+      { level: 'warn' },
+    )
+    logError(error)
+    return null
+  }
+}