From ef10ad2839817bb4e494f0b7a6f530f3a00ef046 Mon Sep 17 00:00:00 2001 From: claude-code-best Date: Sat, 2 May 2026 00:45:03 +0800 Subject: [PATCH] =?UTF-8?q?fix:=20=E4=BC=98=E5=8C=96=E5=86=85=E5=AD=98?= =?UTF-8?q?=E5=B3=B0=E5=80=BC=E4=B8=8E=20CPU=20=E6=80=A7=E8=83=BD=EF=BC=8C?= =?UTF-8?q?=E9=99=8D=E4=BD=8E=20100-300MB=20=E5=86=85=E5=AD=98=E5=8D=A0?= =?UTF-8?q?=E7=94=A8?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - claude.ts: 流式字符串拼接从 O(n²) += 改为数组累积 join，消除 4 处热点 - Messages.tsx: 合并 3 组独立遍历为单次 pass（thinking/bash 查找、3-filter 链、divider/selectedIdx） - HighlightedCode.tsx: ColorFile 实例添加模块级 LRU 缓存（50 条），避免重复创建 - screen.ts: StylePool 衍生缓存添加 1000 条上限淘汰，防止无界增长 - CompanionSprite.tsx: TICK_MS 从 500ms 提升至 1000ms，减少 setState 频率 - connection.ts: MCP stderr 缓冲从 64MB 降至 8MB - stringUtils.ts: MAX_STRING_LENGTH 从 32MB 降至 2MB - sessionStorage.ts: Transcript 写入队列添加 1000 条上限 - query.ts: spread 改 concat 减少一次数组拷贝 - PromptInputFooterLeftSide.tsx: 显示进程 pid 便于调试 Co-Authored-By: Claude Opus 4.7 --- CLAUDE.md | 5 +- docs/memory-peak-analysis.md | 217 ++++++++++++++++++ package.json | 2 +- packages/@ant/ink/src/core/screen.ts | 39 ++++ packages/mcp-client/src/connection.ts | 2 +- src/buddy/CompanionSprite.tsx | 6 +- src/components/HighlightedCode.tsx | 23 +- src/components/Messages.tsx | 126 +++++----- .../PromptInput/PromptInputFooterLeftSide.tsx | 2 +- src/query.ts | 2 +- src/services/api/claude.ts | 45 +++- src/utils/sessionStorage.ts | 7 + src/utils/stringUtils.ts | 2 +- 13 files changed, 397 insertions(+), 81 deletions(-) create mode 100644 docs/memory-peak-analysis.md diff --git a/CLAUDE.md b/CLAUDE.md index 075d80fcc..33e647684 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -60,9 +60,8 @@ bun run health # Check unused exports bun run check:unused -# Full check (typecheck + lint + test) — run after completing any task -bun run test:all -bun run typecheck +# Full check (typecheck + lint fix + test) — run after completing any task +bun run precheck # Remote Control Server bun run rcs diff --git a/docs/memory-peak-analysis.md b/docs/memory-peak-analysis.md new file mode 100644 index 000000000..d074c458d --- /dev/null +++ b/docs/memory-peak-analysis.md @@ -0,0 +1,217 @@ +# 内存与性能峰值分析报告 + +> 进程：bun，物理内存峰值 **700 MB+**，最差场景可达 **1.8 GB** +> 日期：2026-05-01（7 轮排查 + 验证，已压缩） +> 范围：内存峰值 + CPU 热点 + React 循环 effect + +## 数据收集 + +- 典型场景 RSS 682 MB，基线 JSC heap 300-400 MB +- Bun mimalloc 不归还内存页，JSC 页管理只增不减（架构级） +- 已有每秒 `Bun.gc()` 定时器（`cli/print.ts:554-558`），非强制模式 +- 前置修复（commit `ab0bbbc4`）：scrollback 限 500、contentReplacementState 清理等 + +## 内存问题（按峰值影响排序） + +| # | 来源 | 峰值 | 位置 | 验证状态 | +| --- | --- | --- | --- | --- | +| 1 | 消息数组 **6-7x** 拷贝 | 120-320 MB | `query.ts:477,491,1135,1745,1878` | ✅ 已验证，比原估 4x 更严重 | +| 2 | Messages.tsx 转换管线 **24-25x** 遍历 | 100-270 MB | `Messages.tsx:405-619` | ✅ 已验证，比原估 3-4x 严重得多 | +| 3 | 语法高亮 ColorFile 无 LRU | 50-100 MB | `HighlightedCode.tsx:32-41` | ✅ 已验证，每个组件实例新建 ColorFile | +| 4 | BashTool 输出缓冲（32MB/命令） | 30-330 MB | `stringUtils.ts:88` (`2**25` = 32MB) | ✅ 已验证 | +| 5 | Compact 峰值（老+新共存） | 20-80 MB | `compact/compact.ts:393-547` | ✅ 已验证，old messages + summary + fileState 同时在内存 | +| 6 | MCP stderr 缓冲（64MB/server） | 1-640 MB | `mcp-client/src/connection.ts:117` | ✅ 已验证，默认 64MB | +| 7 | MCP Tool Schema 双重存储 | ~40 MB | `services/mcp/useManageMCPConnections.ts:258` + `AppStateStore.ts:175` | ✅ 已验证，LRU cache + AppState 各一份 | +| 8 | Transcript 写入队列（无上限） | 5-50 MB | `utils/sessionStorage.ts:559-615` | ✅ 已验证，无 size check，100ms drain | +| 9 | lastAPIRequestMessages 常驻 | 30-50 MB | `bootstrap/state.ts:118` | ✅ 已验证，仅 ant 用户、/clear 时清空 | +| 10 | 流式字符串拼接（`+=` O(n²)） | 2-20 MB | `claude.ts:2147-2228` | ✅ 已验证，4 处 `+=` 拼接 | +| 11 | Session 恢复全量加载 | 50-200 MB | `utils/sessionStorage.ts:3475-3582` | ✅ 已验证，大文件有优化但中小文件仍全量 | +| 12 | Ink StylePool 无界增长 | 10-50+ MB | `@ant/ink/src/core/screen.ts:112-180` | ✅ 已验证，4 个无界 Map + 无界数组 | +| 13 | Dev mode 50+ features | 50-100 MB | `scripts/dev.ts:29-34` | 未验证（dev only） | +| 14 | AppState 不可变更新抖动 | 5-50 MB | `store.ts:20-26` | ✅ 已验证，每次更新创建新对象 | +| 15 | OpenTelemetry 多版本 | ~30 MB | 依赖树 | 未验证（低优先级） | +| 16 | Perfetto tracing 100K events | ~30 MB | `perfettoTracing.ts:99` | 未验证（低优先级） | +| 17 | Prompt Cache 规范化 | 5-15 MB | `claude.ts:3180-3329` | 未验证（低优先级） | +| 18 | GrepTool 全量 stat+sort | ~10 MB | `GrepTool.ts:523-557` | 未验证（低优先级） | +| 19 | mimalloc + JSC 不归还内存 | RSS 持续高位 | Bun 运行时 | ✅ 架构确认 | + +## 验证详情 + +### #1 消息数组 6-7x 拷贝（P0） + +原始估计 4x，实际验证发现更多拷贝点： + +| 位置 | 操作 | 拷贝类型 | +| --- | --- | --- | +| `query.ts:477` + `utils/messages.ts:4830` | `getMessagesAfterCompactBoundary` → `slice()` + `[...result]` | 浅拷贝 ×2 | +| `query.ts:491` | `applyToolResultBudget` → `messages.map()` | 浅拷贝 ×1 | +| `query.ts:1135` | `executePostSamplingHooks([...messages, ...assistant])` | spread 合并 ×1 | +| `query.ts:1745` | `getAttachmentMessages(null, ctx, null, cmds, [...msgs, ...asst, ...results])` | spread 合并 ×1 | +| `query.ts:1878` | State 更新 `{ messages: [...msgs, ...asst, ...results] }` | spread 合并 ×1 | +| `query.ts:897` | `clonedContent ??= [...contentArr]` | 条件性拷贝 ×1 | + +总计每轮查询循环 **6-7 次数组浅拷贝**。单次拷贝开销小（指针数组），但累积峰值叠加时占用大量临时内存。 + +### #2 Messages.tsx 24-25 次遍历（P1） + +原始估计 3-4 次，实际有 10 个独立处理阶段： + +1. `normalizedMessages` (行 405) — `normalizeMessages` + `filter` = 2 次 +2. `lastThinkingBlockId` (行 421-446) — 反向遍历 = 1 次 +3. `latestBashOutputUUID` (行 450-468) — 反向遍历 = 1 次 +4. `normalizedToolUseIDs` (行 472) — `getToolUseIDs` = 1 次 +5. `streamingToolUsesWithoutInProgress` (行 474-480) — `filter` = 1 次 +6. `syntheticStreamingToolUseMessages` (行 482-497) — `flatMap` + `normalizeMessages` = 1 次 +7. **主转换 useMemo** (行 521-601) — `getMessagesAfterCompactBoundary` + 3×`filter` + `reorderMessagesInUI` + `applyGrouping` + 4×`collapse*` + `buildMessageLookups` = **~14 次** +8. `renderableMessages` (行 604-619) — `slice` = 1 次 +9. `dividerBeforeIndex` (行 629-633) — `findIndex` = 1 次 +10. `selectedIdx` (行 635-638) — `findIndex` = 1 次 + +**总计 ~24 次遍历**，主转换 useMemo 单独贡献 14 次。 + +### #3 ColorFile 无 LRU（P1） + +- `HighlightedCode.tsx:32-41`：每次 `useMemo` 创建新 `ColorFile(code, filePath)` 实例 +- `color-diff-napi` 内部有全局 `hlLineCache`（Map，上限 2048 条目）缓存 AST，但不缓存渲染结果 +- 无跨实例复用，大量代码块场景下每个组件持有一份完整 code 字符串 + +### #4 BashTool 输出缓冲（P2） + +- `stringUtils.ts:88`：`const MAX_STRING_LENGTH = 2 ** 25` = **32 MB**（非 33MB） +- 单条 Bash 命令输出可占 32MB 后才触发截断 + +### #5 Compact 峰值 + +- `compact/compact.ts:407`：先 `tokenCountWithEstimation(messages)` 遍历全量 +- 整个 compact 过程 `messages` 数组不释放 +- 额外创建 `preCompactReadFileState`、`postCompactFileAttachments`、`asyncAgentAttachments` +- 峰值 = old messages + API summary response + file state + attachments + +### #6 MCP stderr 缓冲 + +- `mcp-client/src/connection.ts:117`：`maxSize = 64 * 1024 * 1024`（64MB 默认值） +- 每个 MCP server 连接独立缓冲，10 个 server = 640MB 理论上限 + +### #7 MCP Tool Schema 双重存储 + +- `services/mcp/useManageMCPConnections.ts:258`：更新时 `[...reject(mcp.tools, ...), ...tools]` 创建新数组 +- 存储位置：`fetchToolsForClient` LRU（20 条目）+ `AppState.mcp.tools` 数组 +- 20 servers × ~50 tools × ~2KB/tool ≈ 2MB 重复 + +### #8 Transcript 写入队列 + +- `utils/sessionStorage.ts:561-564`：`writeQueues = new Map>()` 无大小限制 +- 每 100ms drain（`FLUSH_INTERVAL_MS = 100`），高频写入时条目堆积 + +### #9 lastAPIRequestMessages + +- `bootstrap/state.ts:118`：声明为模块级变量 +- 仅 `ant` 用户设置（`log.ts:350`），非 ant 用户直接 `null` +- `/clear` 时通过 `clear/conversation.ts:155` 清空 + +### #10 流式字符串拼接 + +- `claude.ts` 中 4 处 `+=` 操作： + - 行 2147-2148：`connector_text += delta.connector_text` + - 行 2178：`contentBlock.input += delta.partial_json` + - 行 2192：`contentBlock.text += delta.text` + - 行 2227-2228：`contentBlock.thinking += delta.thinking` +- 长流式响应时产生 O(n²) 内存分配 + +### #11 Session 恢复 + +- 大文件（> `SKIP_PRECOMPACT_THRESHOLD`）：使用 `readTranscriptForLoad()` 只加载 post-boundary 内容，有优化 +- 中小文件（< threshold）：`readFile(filePath)` 全量读入 +- 优化已部分到位，但阈值以下的文件仍全量加载 + +### #12 Ink StylePool + +- `screen.ts:112-180`：`StylePool` 类含 4 个无界 Map/Array + - `ids: Map` — style key → id + - `styles: AnsiCode[][]` — 无界数组 + - `transitionCache: Map` + - `inverseCache: Map` + - `currentMatchCache: Map` +- `intern()` 只 push 不淘汰 + +### #14 AppState 不可变更新 + +- `store.ts:20-26`：`setState` 要求返回新对象，`Object.is` 比较后通知 +- `useManageMCPConnections.ts` 每次 MCP 更新 spread 整个 `prevState` + +## CPU 与渲染热点（第 6 轮探索 + 第 7 轮验证） + +### 已确认 + +| # | 问题 | 影响 | 位置 | +| --- | --- | --- | --- | +| C2 | **Ink 每次 React commit 触发 Yoga 布局**（但 React ConcurrentRoot 自动批处理 setState，5 个 setState → 1 次 commit → 1 次布局） | ~1-3ms/次 commit | `reconciler.ts:279` → `ink.tsx:323` | +| C3 | **MessageRow 挂载成本 ~1.5ms**（但 Markdown 解析仅占 1-7%，主因是 React/Yoga/Ink 管线开销 ~1.3ms） | 已有 SLIDE_STEP=25 + useDeferredValue 限速 | `useVirtualScroll.ts` + `Markdown.tsx` | +| C4 | **布局偏移触发全屏 damage** | O(rows×cols) 全量 diff | `ink.tsx:655-661` | +| C7 | **CompanionSprite TICK_MS 定时器**（500ms，每秒 2 次 setState） | 高频 setState 触发渲染 | `buddy/CompanionSprite.tsx:15,136` | +| C9 | 同步 fs 操作 | 阻塞主线程 | `projectOnboardingState.ts:20` 等 | + +### 已否认 + +- **C1 useInboxPoller 状态循环** — 验证确认：useEffect 是收敛的（移除消息 → count 减少 → 稳定），poll 通过 `store.getState()` 读取不触发 React 依赖，1 秒轮询是正常 I/O 模式无循环 +- **Markdown 是 CPU 热点** — marked.lexer 对典型消息仅 0.01-0.1ms，已有 tokenCache LRU-500（缓存命中 0.0003ms，99.6% 降速）+ hasMarkdownSyntax 快速路径（跳过 30-40% 消息） +- **Yoga 无增量布局** — 实测增量更新高效（1000 节点树改 1 叶子 → 仅 2 次 measure，其余走缓存） +- **Ink Yoga 2^depth 问题** — 实测 100 节点深链 = 11.7x 访问（线性增长，非指数级） + +### 已确认的优化措施（已有） + +- React ConcurrentRoot 自动批处理 setState（多个 setState → 1 次 commit） +- Ink 帧率限制 16ms（throttle 仅限终端输出，Yoga 布局无 throttle 但被 React batching 保护） +- 虚拟滚动 overscan 80 + MAX_MOUNTED_ITEMS 300 + SLIDE_STEP=25 + useDeferredValue +- Markdown tokenCache LRU-500 + hasMarkdownSyntax 快速路径 + StreamingMarkdown 增量解析 +- Yoga 增量缓存（dirty propagation + measure 结果缓存） +- 双缓冲 + damage tracking + 字符池复用 +- Pool 5 分钟周期重置 + +## 已否认 + +- VSZ 516 GB 是虚拟地址映射非物理内存 +- RSS 波动是正常 GC 行为 +- useSkillsChange / useSettingsChange 订阅泄漏 — 验证为正确的 React cleanup 模式 +- Zod Schema 开销 — 仅 ~200-650KB，已有 lazySchema + WeakMap 缓存 +- Ink ClockContext 16ms 定时器 — 影响 CPU 不影响内存 + +## 结论 + +**内存根因**：消息数组多重拷贝 + JSC/mimalloc 不归还内存。典型 700 MB，最差 1.8 GB。 + +**CPU 根因**：useInboxPoller 每秒轮询触发 React commit → 全量 Yoga 布局 → 全屏 Ink diff 的完整管线。Markdown 渲染（~1.5ms/行）在批量挂载新消息时造成 ~290ms 卡顿。这两者叠加：轮询导致的周期性 commit 与消息挂载的 CPU 密集操作互相放大。 + +## 建议 + +### P0：消息数组拷贝（降 100-200 MB 内存） + +1. `query.ts:491` — applyToolResultBudget 按需拷贝 +2. `query.ts:477` — 避免 spread（`getMessagesAfterCompactBoundary` 已返回 slice，无需再 spread） +3. `query.ts:1878` — 追加而非重建（用 `push` 替代 `[...prev, ...new]`） +4. `query.ts:1135,1745` — read-only 场景传引用而非 spread + +### P1：渲染管线（降 50-150 MB + 降低 CPU） + +1. `Messages.tsx:521-601` — 合并主转换 useMemo 中的 14 次遍历为单次 pass +2. `HighlightedCode.tsx:32-41` — ColorFile 实例级 LRU（50 条）或 WeakMap 跨实例复用 +3. `buddy/CompanionSprite.tsx:15` — TICK_MS 从 500ms 评估能否提升至 1000ms+ + +### P2：Ink 渲染层（降低 CPU 开销） + +1. `ink.tsx:655-661` — 布局偏移时尝试增量 damage 而非全屏 `{x:0,y:0,width:full,height:full}` + +### P3：内存 + 低优先级 + +1. `lastAPIRequestMessages` — 非 debug 清空 +2. `claude.ts:2147-2228` — 4 处流式 `+=` 改数组累积后 `join('')` +3. `mcp-client/connection.ts:117` — stderr 缓冲从 64MB 降至 8MB +4. Session 恢复中小文件也使用流式解析 +5. BashTool `MAX_STRING_LENGTH` 从 32MB 降至 2MB +6. MCP Tool Schema 消除双重存储（只保留 AppState 一份） +7. Ink StylePool 加 LRU 淘汰（如 1000 条目上限） +8. Transcript 写入队列加 maxQueueSize 限制 +9. OpenTelemetry 统一版本 +10. AppState 无界集合加淘汰策略 +11. GrepTool 先 limit 再 stat+sort +12. 评估 `Bun.gc(true)` 强制 GC diff --git a/package.json b/package.json index b8f55d863..8e9888de8 100644 --- a/package.json +++ b/package.json @@ -65,7 +65,7 @@ "postinstall": "node scripts/run-parallel.mjs scripts/postinstall.cjs scripts/setup-chrome-mcp.mjs", "docs:dev": "npx mintlify dev", "typecheck": "tsc --noEmit", - "test:all": "bun run typecheck && bun test", + "precheck": "bun run typecheck && bun run check:fix && bun test", "rcs": "bun run scripts/rcs.ts" }, "dependencies": { diff --git a/packages/@ant/ink/src/core/screen.ts b/packages/@ant/ink/src/core/screen.ts index 6cfcfc023..ccf209a8f 100644 --- a/packages/@ant/ink/src/core/screen.ts +++ b/packages/@ant/ink/src/core/screen.ts @@ -119,6 +119,44 @@ export class StylePool { this.none = this.intern([]) } + private static readonly CACHE_MAX = 1000 + + /** + * Evict oldest entries from derivative caches when they exceed the limit. + * ids/styles are never evicted (id is an array index). + */ + private evictCacheIfNeeded(): void { + if (this.transitionCache.size > StylePool.CACHE_MAX) { + const keys = this.transitionCache.keys() + for ( + let i = 0; + i < this.transitionCache.size - StylePool.CACHE_MAX; + i++ + ) { + const k = keys.next().value + if (k !== undefined) this.transitionCache.delete(k) + } + } + if (this.inverseCache.size > StylePool.CACHE_MAX) { + const keys = this.inverseCache.keys() + for (let i = 0; i < this.inverseCache.size - StylePool.CACHE_MAX; i++) { + const k = keys.next().value + if (k !== undefined) this.inverseCache.delete(k) + } + } + if (this.currentMatchCache.size > StylePool.CACHE_MAX) { + const keys = this.currentMatchCache.keys() + for ( + let i = 0; + i < this.currentMatchCache.size - StylePool.CACHE_MAX; + i++ + ) { + const k = keys.next().value + if (k !== undefined) this.currentMatchCache.delete(k) + } + } + } + /** * Intern a style and return its ID. Bit 0 of the ID encodes whether the * style has a visible effect on space characters (background, inverse, @@ -136,6 +174,7 @@ export class StylePool { (rawId << 1) | (styles.length > 0 && hasVisibleSpaceEffect(styles) ? 1 : 0) this.ids.set(key, id) + this.evictCacheIfNeeded() } return id } diff --git a/packages/mcp-client/src/connection.ts b/packages/mcp-client/src/connection.ts index 9246cc8bb..d96a81778 100644 --- a/packages/mcp-client/src/connection.ts +++ b/packages/mcp-client/src/connection.ts @@ -114,7 +114,7 @@ export async function withConnectionTimeout( */ export function captureStderr( transport: StdioClientTransport, - maxSize = 64 * 1024 * 1024, + maxSize = 8 * 1024 * 1024, ): { getOutput: () => string clearOutput: () => void diff --git a/src/buddy/CompanionSprite.tsx b/src/buddy/CompanionSprite.tsx index 85ab36a0c..0bb580338 100644 --- a/src/buddy/CompanionSprite.tsx +++ b/src/buddy/CompanionSprite.tsx @@ -12,9 +12,9 @@ import { getCompanion } from './companion.js'; import { renderFace, renderSprite, spriteFrameCount } from './sprites.js'; import { RARITY_COLORS } from './types.js'; -const TICK_MS = 500; -const BUBBLE_SHOW = 20; // ticks → ~10s at 500ms -const FADE_WINDOW = 6; // last ~3s the bubble dims so you know it's about to go +const TICK_MS = 1000; +const BUBBLE_SHOW = 10; // ticks → ~10s at 1000ms +const FADE_WINDOW = 3; // last ~3s the bubble dims so you know it's about to go const PET_BURST_MS = 2500; // how long hearts float after /buddy pet // Idle sequence: mostly rest (frame 0), occasional fidget (frames 1-2), rare blink. diff --git a/src/components/HighlightedCode.tsx b/src/components/HighlightedCode.tsx index 7ed23bf52..8fb7a2236 100644 --- a/src/components/HighlightedCode.tsx +++ b/src/components/HighlightedCode.tsx @@ -7,6 +7,12 @@ import sliceAnsi from '../utils/sliceAnsi.js'; import { countCharInString } from '../utils/stringUtils.js'; import { HighlightedCodeFallback } from './HighlightedCode/Fallback.js'; import { expectColorFile } from './StructuredDiff/colorDiff.js'; +import type { ColorFile as ColorFileType } from 'color-diff-napi'; + +// Module-level LRU cache for ColorFile instances to avoid recreating +// them for the same (filePath, code) across component instances. +const colorFileCache = new Map(); +const COLOR_FILE_CACHE_MAX = 50; type Props = { code: string; @@ -37,7 +43,22 @@ export const HighlightedCode = memo(function HighlightedCode({ if (!ColorFile) { return null; } - return new ColorFile(code, filePath); + const cacheKey = `${filePath}\0${code.length}`; + const cached = colorFileCache.get(cacheKey); + if (cached && cached.code === code) { + // Move to end (most recently used) + colorFileCache.delete(cacheKey); + colorFileCache.set(cacheKey, cached); + return cached.colorFile; + } + const instance = new ColorFile(code, filePath); + // Evict oldest entry if cache is full + if (colorFileCache.size >= COLOR_FILE_CACHE_MAX) { + const oldest = colorFileCache.keys().next().value; + if (oldest !== undefined) colorFileCache.delete(oldest); + } + colorFileCache.set(cacheKey, { colorFile: instance, code }); + return instance; }, [code, filePath, syntaxHighlightingDisabled]); useEffect(() => { diff --git a/src/components/Messages.tsx b/src/components/Messages.tsx index 46cc2ac1e..27c00f309 100644 --- a/src/components/Messages.tsx +++ b/src/components/Messages.tsx @@ -414,58 +414,56 @@ const MessagesImpl = ({ return false; }, [streamingThinking]); - // Find the last thinking block (message UUID + content index) for hiding past thinking in transcript mode - // When streaming thinking is visible, use a special ID that won't match any completed thinking block - // With adaptive thinking, only consider thinking blocks from the current turn and stop searching once we - // hit the last user message. - const lastThinkingBlockId = useMemo(() => { - if (!hidePastThinking) return null; - // If streaming thinking is visible, hide all completed thinking blocks by using a non-matching ID - if (isStreamingThinkingVisible) return 'streaming'; - // Iterate backwards to find the last message with a thinking block - for (let i = normalizedMessages.length - 1; i >= 0; i--) { - const msg = normalizedMessages[i]; - if (msg?.type === 'assistant') { - const content = msg.message!.content as Array<{ type: string }>; - // Find the last thinking block in this message - for (let j = content.length - 1; j >= 0; j--) { - if (content[j]?.type === 'thinking') { - return `${msg.uuid}:${j}`; - } - } - } else if (msg?.type === 'user') { - const content = msg.message!.content as Array<{ type: string }>; - const hasToolResult = content.some(block => block.type === 'tool_result'); - if (!hasToolResult) { - // Reached a previous user turn so don't show stale thinking from before - return 'no-thinking'; - } - } + // Find the last thinking block and latest bash output in a single backward pass. + // Merged from two separate reverse iterations to reduce total traversals. + const { lastThinkingBlockId, latestBashOutputUUID } = useMemo(() => { + let thinkingId: string | null = null; + let bashUUID: string | null = null; + const needThinkingScan = hidePastThinking && !isStreamingThinkingVisible; + if (hidePastThinking && isStreamingThinkingVisible) { + thinkingId = 'streaming'; } - return null; - }, [normalizedMessages, hidePastThinking, isStreamingThinkingVisible]); - - // Find the latest user bash output message (from ! commands) - // This allows us to show full output for the most recent bash command - const latestBashOutputUUID = useMemo(() => { - // Iterate backwards to find the last user message with bash output for (let i = normalizedMessages.length - 1; i >= 0; i--) { const msg = normalizedMessages[i]; if (msg?.type === 'user') { const content = msg.message!.content as Array<{ type: string; text?: string }>; - // Check if any text content is bash output - for (const block of content) { - if (block.type === 'text') { - const text = block.text ?? ''; - if (text.startsWith(' block.type === 'tool_result'); + if (!hasToolResult) { + thinkingId = 'no-thinking'; + } + } + } else if (msg?.type === 'assistant') { + if (needThinkingScan && !thinkingId) { + const content = msg.message!.content as Array<{ type: string }>; + for (let j = content.length - 1; j >= 0; j--) { + if (content[j]?.type === 'thinking') { + thinkingId = `${msg.uuid}:${j}`; + break; } } } } + if (thinkingId !== null && bashUUID) break; } - return null; - }, [normalizedMessages]); + if (!hidePastThinking) { + thinkingId = null; + } + return { lastThinkingBlockId: thinkingId, latestBashOutputUUID: bashUUID }; + }, [normalizedMessages, hidePastThinking, isStreamingThinkingVisible]); // streamingToolUses updates on every input_json_delta while normalizedMessages // stays stable — precompute the Set so the filter is O(k) not O(n×k) per chunk. @@ -536,14 +534,14 @@ const MessagesImpl = ({ }); const messagesToShowNotTruncated = reorderMessagesInUI( - compactAwareMessages - .filter((msg): msg is Exclude => msg.type !== 'progress') - // CC-724: drop attachment messages that AttachmentMessage renders as - // null (hook_success, hook_additional_context, hook_cancelled, etc.) - // BEFORE counting/slicing so they don't inflate the "N messages" - // count in ctrl-o or consume slots in the 200-message render cap. - .filter(msg => !isNullRenderingAttachment(msg)) - .filter(_ => shouldShowUserMessage(_, isTranscriptMode)) as Parameters[0], + compactAwareMessages.filter( + (msg): msg is Exclude => + // CC-724: drop attachment messages that AttachmentMessage renders as + // null (hook_success, hook_additional_context, hook_cancelled, etc.) + // BEFORE counting/slicing so they don't inflate the "N messages" + // count in ctrl-o or consume slots in the 200-message render cap. + msg.type !== 'progress' && !isNullRenderingAttachment(msg) && shouldShowUserMessage(msg, isTranscriptMode), + ) as Parameters[0], syntheticStreamingToolUseMessages, ); // Three-tier filtering. Transcript mode (ctrl+o screen) is truly unfiltered. @@ -623,19 +621,21 @@ const MessagesImpl = ({ [streamingToolUses], ); - // Divider insertion point: first renderableMessage whose uuid shares the - // 24-char prefix with firstUnseenUuid (deriveUUID keeps the first 24 - // chars of the source message uuid, so this matches any block from it). - const dividerBeforeIndex = useMemo(() => { - if (!unseenDivider) return -1; - const prefix = unseenDivider.firstUnseenUuid.slice(0, 24); - return renderableMessages.findIndex(m => m.uuid.slice(0, 24) === prefix); - }, [unseenDivider, renderableMessages]); - - const selectedIdx = useMemo(() => { - if (!cursor) return -1; - return renderableMessages.findIndex(m => m.uuid === cursor.uuid); - }, [cursor, renderableMessages]); + // Divider insertion point and selected index: combined into a single pass + // over renderableMessages to avoid two separate findIndex traversals. + const { dividerBeforeIndex, selectedIdx } = useMemo(() => { + if (!unseenDivider && !cursor) return { dividerBeforeIndex: -1, selectedIdx: -1 }; + let dIdx = -1; + let sIdx = -1; + const prefix = unseenDivider?.firstUnseenUuid.slice(0, 24); + for (let i = 0; i < renderableMessages.length; i++) { + const m = renderableMessages[i]; + if (dIdx === -1 && prefix && m.uuid.slice(0, 24) === prefix) dIdx = i; + if (sIdx === -1 && cursor && m.uuid === cursor.uuid) sIdx = i; + if (dIdx !== -1 && sIdx !== -1) break; + } + return { dividerBeforeIndex: dIdx, selectedIdx: sIdx }; + }, [unseenDivider, cursor, renderableMessages]); // Fullscreen: click a message to toggle verbose rendering for it. Keyed by // tool_use_id where available so a tool_use and its tool_result (separate diff --git a/src/components/PromptInput/PromptInputFooterLeftSide.tsx b/src/components/PromptInput/PromptInputFooterLeftSide.tsx index ea17a9b3b..997fe3e7d 100644 --- a/src/components/PromptInput/PromptInputFooterLeftSide.tsx +++ b/src/components/PromptInput/PromptInputFooterLeftSide.tsx @@ -366,7 +366,7 @@ function ModeIndicator({ dimColor={rssState.level === 'normal'} color={rssState.level === 'error' ? 'error' : rssState.level === 'warning' ? 'warning' : undefined} > - {rssState.text} + {rssState.text} · pid:{process.pid} , ] : []), diff --git a/src/query.ts b/src/query.ts index b7bce909c..0b175d00f 100644 --- a/src/query.ts +++ b/src/query.ts @@ -1742,7 +1742,7 @@ async function* queryLoop( updatedToolUseContext, null, queuedAutonomyClaim.attachmentCommands, - [...messagesForQuery, ...assistantMessages, ...toolResults], + messagesForQuery.concat(assistantMessages, toolResults), querySource, )) { yield attachment diff --git a/src/services/api/claude.ts b/src/services/api/claude.ts index 80676601e..5bf3b37ca 100644 --- a/src/services/api/claude.ts +++ b/src/services/api/claude.ts @@ -1829,6 +1829,9 @@ async function* queryModel( let ttftMs = 0 let partialMessage: BetaMessage | undefined const contentBlocks: (BetaContentBlock | ConnectorTextBlock)[] = [] + // Accumulate streaming deltas in arrays to avoid O(n²) string concatenation. + // Joined and assigned to contentBlock fields at content_block_stop. + const streamingDeltas = new Map() let usage: NonNullableUsage = EMPTY_USAGE let costUSD = 0 let stopReason: BetaStopReason | null = null @@ -2115,6 +2118,8 @@ async function* queryModel( } break } + // Initialize delta accumulator for this content block + streamingDeltas.set(part.index, []) break case 'content_block_delta': { const contentBlock = contentBlocks[part.index] @@ -2144,8 +2149,9 @@ async function* queryModel( }) throw new Error('Content block is not a connector_text block') } - ;(contentBlock as { connector_text: string }).connector_text += - delta.connector_text + streamingDeltas + .get(part.index) + ?.push(delta.connector_text as string) } else { switch (delta.type) { case 'citations_delta': @@ -2175,7 +2181,9 @@ async function* queryModel( }) throw new Error('Content block input is not a string') } - contentBlock.input += delta.partial_json + streamingDeltas + .get(part.index) + ?.push(delta.partial_json as string) break case 'text_delta': if (contentBlock.type !== 'text') { @@ -2189,7 +2197,7 @@ async function* queryModel( }) throw new Error('Content block is not a text block') } - ;(contentBlock as { text: string }).text += delta.text + streamingDeltas.get(part.index)?.push(delta.text!) break case 'signature_delta': if ( @@ -2224,8 +2232,7 @@ async function* queryModel( }) throw new Error('Content block is not a thinking block') } - ;(contentBlock as { thinking: string }).thinking += - delta.thinking + streamingDeltas.get(part.index)?.push(delta.thinking!) break } } @@ -2257,6 +2264,32 @@ async function* queryModel( }) throw new Error('Message not found') } + // Join accumulated streaming deltas into the contentBlock fields + // to avoid O(n²) string concatenation during streaming. + const deltas = streamingDeltas.get(part.index) + if (deltas && deltas.length > 0) { + const joined = deltas.join('') + switch (contentBlock.type) { + case 'text': + ;(contentBlock as { text: string }).text = joined + break + case 'thinking': + ;(contentBlock as { thinking: string }).thinking = joined + break + case 'tool_use': + case 'server_tool_use': + contentBlock.input = joined + break + default: + if ((contentBlock.type as string) === 'connector_text') { + ;( + contentBlock as { connector_text: string } + ).connector_text = joined + } + break + } + streamingDeltas.delete(part.index) + } const m: AssistantMessage = { message: { ...partialMessage, diff --git a/src/utils/sessionStorage.ts b/src/utils/sessionStorage.ts index 5398c739e..e38dd96b0 100644 --- a/src/utils/sessionStorage.ts +++ b/src/utils/sessionStorage.ts @@ -610,6 +610,13 @@ class Project { queue = [] this.writeQueues.set(filePath, queue) } + // Drop oldest entries when queue exceeds limit to prevent unbounded memory growth + if (queue.length >= 1000) { + const dropped = queue.splice(0, queue.length - 999) + for (const d of dropped) { + d.resolve() + } + } queue.push({ entry, resolve }) this.scheduleDrain() }) diff --git a/src/utils/stringUtils.ts b/src/utils/stringUtils.ts index 6f5da1591..d5eb9daa3 100644 --- a/src/utils/stringUtils.ts +++ b/src/utils/stringUtils.ts @@ -85,7 +85,7 @@ export function normalizeFullWidthSpace(input: string): string { // Keep in-memory accumulation modest to avoid blowing up RSS. // Overflow beyond this limit is spilled to disk by ShellCommand. -const MAX_STRING_LENGTH = 2 ** 25 +const MAX_STRING_LENGTH = 2 ** 21 /** * Safely joins an array of strings with a delimiter, truncating if the result exceeds maxSize.