P1 修复面收口: - 超时三态区分(aborted→USER_INTERRUPT / ETIMEDOUT→TIMEOUT / 其余→ERROR), 根治"真实网络超时被误报为用户中断" - 流空闲超时统一(SSE/Ollama/Anthropic 读循环 60s 无数据抛 504 进重试通道) - 同会话并发 sendMessage 防重入(isRunning 守卫)+ 会话存在性预检 + 前置调用移入 try(ERROR+DONE 双事件保证,根治 isStreaming 假死) - 清空审计后 resetChainCache(根治 verifyChain 误报 TAMPERED) - DONE 不再提前清理 TRACE(TERMINATED 统一收尾,补全最终迭代录制) - IME 合成回车不发送(普通 Enter + Cmd/Ctrl+Enter 双分支)+ handleSend 闭包修复 P2 安全纵深: - preload 移除原始 electronAPI 暴露(渲染层零使用,关掉 XSS invoke 任意通道单点风险) - CORS 同源回显根治(仅当前浏览页面 Origin,did-navigate 同步) - MEMORY.md 命令保护正则扩展(括号/$/反引号/< 重定向边界 + 前导路径) - write_file append TOCTOU 统一(open 后 realpath 校验,新文件分支补漏) - 敏感键归一化(authKey 驼峰/连字符命中)+ MCP headers 鉴权值加密落库 - ReDoS 检测共享化(search_files/file_editor 统一拦截) - run_tests/lint_code 升风险 + 需确认 + npx --no-install(执行边界对齐 run_command) - MCP/SearXNG/llm.baseURL/updateFeedUrl 配置类 URL 高危目标校验(IPv6 去括号 + 十六进制映射解析 + 尾点剥离) P3 架构还债: - temperature/maxTokens 热生效(引擎/编排器/SubAgent 三处接线)+ setBatch 单事务落盘 - SessionRecorder flush 竞态根治(flushPromise 等待 + 超限内联落盘 + stopRecording async) - 内存收口(lastConsolidationBySession LRU / subTraces 清理 / 会话删除 disposeEngine) - i18n 全量收口(28 组件 + 353 key 双字典,状态标签改渲染时函数) - 死代码清理(updateTraceStep/HEADER_HEIGHT/void preA/失实注释) - 斜杠菜单 MUI 化 + 删除逻辑收敛 resetSessionState + Blob URL 统一释放 + 用户消息"仅保存"落库(saveMessage 透传前端 id 修复 id 错位) P4 能力演进: - 死循环检测拆分(驻留前置 + 乒乓后置带进度信号,合法交替不误报) - run-lock 30s 超时强制 abort(旧 run 卡死不无限排队) - RETRY 双通道 stream_reset(前端按 run 归属精确清空,根治重试文本重复) - FTS5 trigram 中文子串搜索(迁移 9 版本化 SCHEMA_VERSION=2,≤2 字符 LIKE 回退) - getContextWindow 兜底 1M→128K(未知模型防 413) 测试: - 855 → 2406 用例(+1551,2.8 倍):服务层 +325(含 MemoryManager 51 新用例)、 工具实体 +483、IPC/适配器 +390(含 OpenAI/Anthropic/Ollama 独立套件)、 纯函数表格化 +330;引入 jsdom + @testing-library(14 组件测试文件 249 用例) - 修复 R1(saveMessage id 透传)/ R2(stream_reset 精确归属)两个回归缺陷 - 遗留低危项清零:git-tools 顺序耦合 / web-fetch 真实时间退避 / slo 内存断言 / mcp-security 多余 skipIf / deepseek-balance 命名误导 / 组件 mock 注入脆弱性 版本: 0.7.4; README 同步(工具风险表/版本徽章); 依赖: 移除 @electron-toolkit/preload, 新增 jsdom/@testing-library(devDependencies 不打包) 回归: typecheck 双端 0 错误; ESLint 0/0; Electron ABI 全量 2406/2406 零跳过; 系统 Node 2110 通过 296 跳过(better-sqlite3 ABI)
407 lines
13 KiB
TypeScript
407 lines
13 KiB
TypeScript
/**
|
||
* 网络工具共享模块
|
||
*
|
||
* 提供 UA 轮换池、反爬请求头、HTML 转文本、拦截检测、超时 fetch、LRU 缓存等通用能力。
|
||
* web_search 和 web_fetch 共享此模块。
|
||
*
|
||
* @see docs/Agent网络工具通用设计-v2.md — 第 3 章 web_fetch 抓取设计
|
||
*/
|
||
|
||
import { LRUCache } from 'lru-cache';
|
||
import log from 'electron-log';
|
||
|
||
// ===== LRU 缓存 =====
|
||
|
||
/** 搜索结果缓存(200 条,5 分钟 TTL) */
|
||
export const searchCache = new LRUCache<string, Record<string, unknown>>({
|
||
max: 200,
|
||
ttl: 300_000,
|
||
});
|
||
|
||
/** 浏览器回退缓存(100 条,10 分钟 TTL) */
|
||
export const fetchCache = new LRUCache<string, string>({
|
||
max: 100,
|
||
ttl: 600_000,
|
||
});
|
||
|
||
// ===== UA 轮换池 =====
|
||
|
||
export const UA_POOL = [
|
||
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
|
||
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Edg/131.0.0.0 Safari/537.36',
|
||
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
|
||
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/18.1 Safari/605.1.15',
|
||
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:133.0) Gecko/20100101 Firefox/133.0',
|
||
];
|
||
|
||
export const MOBILE_UA =
|
||
'Mozilla/5.0 (iPhone; CPU iPhone OS 17_5 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.5 Mobile/15E148 Safari/604.1';
|
||
|
||
export const ACCEPT_LANGUAGE_POOL = [
|
||
'zh-CN,zh;q=0.9,en;q=0.8',
|
||
'zh-CN,zh;q=0.9',
|
||
'en-US,en;q=0.9,zh-CN;q=0.8',
|
||
];
|
||
|
||
// ===== 反爬请求头构建 =====
|
||
|
||
export function buildAntiCrawlHeaders(
|
||
url: string,
|
||
attempt: number,
|
||
mobileUA = false,
|
||
): Record<string, string> {
|
||
const uaIdx = attempt % UA_POOL.length;
|
||
const langIdx = attempt % ACCEPT_LANGUAGE_POOL.length;
|
||
const userAgent = mobileUA ? MOBILE_UA : UA_POOL[uaIdx];
|
||
|
||
let origin = '';
|
||
try {
|
||
origin = new URL(url).origin;
|
||
} catch {
|
||
/* ignore */
|
||
}
|
||
|
||
return {
|
||
'User-Agent': userAgent,
|
||
Accept: 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
|
||
'Accept-Language': ACCEPT_LANGUAGE_POOL[langIdx],
|
||
'Accept-Encoding': 'gzip, deflate, br',
|
||
'Cache-Control': 'no-cache',
|
||
DNT: '1',
|
||
Referer: origin || '',
|
||
'Sec-Fetch-Dest': 'document',
|
||
'Sec-Fetch-Mode': 'navigate',
|
||
'Sec-Fetch-Site': 'none',
|
||
'Sec-Fetch-User': '?1',
|
||
Pragma: 'no-cache',
|
||
};
|
||
}
|
||
|
||
// ===== 超时 fetch =====
|
||
|
||
export async function fetchWithTimeout(
|
||
url: string,
|
||
options: RequestInit = {},
|
||
timeoutMs = 20_000,
|
||
): Promise<Response> {
|
||
const controller = new AbortController();
|
||
const timer = setTimeout(() => controller.abort(), timeoutMs);
|
||
try {
|
||
return await fetch(url, { ...options, signal: controller.signal });
|
||
} finally {
|
||
clearTimeout(timer);
|
||
}
|
||
}
|
||
|
||
// ===== URL 标准化(去重用) =====
|
||
|
||
/**
|
||
* H-6 增强: URL 标准化用于搜索结果去重
|
||
*
|
||
* 规范推荐使用 normalize-url 库(@see docs/Agent网络工具通用设计-v2.md §6.1.3),
|
||
* 但当前实现已覆盖核心场景,且避免 ESM-only 依赖兼容性风险,
|
||
* 故在现有基础上增强以下能力(对标 normalize-url 默认行为):
|
||
* 1. 去除追踪参数(utm_*, gclid, fbclid)
|
||
* 2. 强制小写 host
|
||
* 3. 去除尾部斜杠(根路径除外)
|
||
* 4. H-6 新增: 去除默认端口(http→:80, https→:443)
|
||
* 5. H-6 新增: 排序查询参数(避免 ?a=1&b=2 vs ?b=2&a=1 被视为不同 URL)
|
||
*/
|
||
export function normalizeUrl(url: string): string {
|
||
try {
|
||
const u = new URL(url);
|
||
|
||
// 去除追踪参数
|
||
const trackingParams = [
|
||
'utm_source',
|
||
'utm_medium',
|
||
'utm_campaign',
|
||
'utm_term',
|
||
'utm_content',
|
||
'gclid',
|
||
'fbclid',
|
||
];
|
||
for (const p of trackingParams) u.searchParams.delete(p);
|
||
|
||
// H-6 增强: 排序查询参数(确保参数顺序一致,便于去重)
|
||
// searchParams.sort() 原地排序,URLSearchParams 按码点顺序
|
||
u.searchParams.sort();
|
||
|
||
// 去除尾部斜杠(根路径除外)
|
||
let path = u.pathname;
|
||
if (path.length > 1 && path.endsWith('/')) path = path.slice(0, -1);
|
||
|
||
// H-6 增强: 去除默认端口
|
||
// http 默认 :80, https 默认 :443, ws 默认 :80, wss 默认 :443
|
||
const isDefaultPort =
|
||
(u.protocol === 'http:' && u.port === '80') ||
|
||
(u.protocol === 'https:' && u.port === '443') ||
|
||
(u.protocol === 'ws:' && u.port === '80') ||
|
||
(u.protocol === 'wss:' && u.port === '443');
|
||
const portSuffix = isDefaultPort ? '' : u.port ? `:${u.port}` : '';
|
||
|
||
// 强制小写 host
|
||
return `${u.protocol}//${u.hostname.toLowerCase()}${portSuffix}${path}${u.search}${u.hash}`;
|
||
} catch {
|
||
return url;
|
||
}
|
||
}
|
||
|
||
// ===== 拦截页面检测 =====
|
||
|
||
const INTERCEPTION_PATTERNS = [
|
||
/just a moment/i,
|
||
/attention required/i,
|
||
/challenge-platform/i,
|
||
/\.cf-challenge-/i,
|
||
/access denied/i,
|
||
/403 forbidden/i,
|
||
/请启用\s*javascript/i,
|
||
/please enable javascript/i,
|
||
/checking your browser/i,
|
||
/ddos protection/i,
|
||
];
|
||
|
||
export function isInterceptedPage(html: string): boolean {
|
||
if (html.length < 80) return true;
|
||
const lower = html.toLowerCase();
|
||
return INTERCEPTION_PATTERNS.some((p) => p.test(lower));
|
||
}
|
||
|
||
// ===== HTML → 纯文本转换 =====
|
||
|
||
const HTML_ENTITY_MAP: Record<string, string> = {
|
||
' ': ' ',
|
||
'<': '<',
|
||
'>': '>',
|
||
'&': '&',
|
||
'"': '"',
|
||
''': "'",
|
||
'…': '…',
|
||
'—': '—',
|
||
'–': '–',
|
||
'«': '«',
|
||
'»': '»',
|
||
'×': '×',
|
||
'÷': '÷',
|
||
'©': '©',
|
||
'®': '®',
|
||
'™': '™',
|
||
'€': '€',
|
||
'£': '£',
|
||
'¥': '¥',
|
||
'¢': '¢',
|
||
'°': '°',
|
||
};
|
||
|
||
export function htmlToText(html: string): string {
|
||
return (
|
||
html
|
||
// 移除噪声标签及内容
|
||
.replace(/<script[^>]*>[\s\S]*?<\/script>/gi, '')
|
||
.replace(/<style[^>]*>[\s\S]*?<\/style>/gi, '')
|
||
.replace(/<noscript[^>]*>[\s\S]*?<\/noscript>/gi, '')
|
||
.replace(/<nav[^>]*>[\s\S]*?<\/nav>/gi, '')
|
||
.replace(/<header[^>]*>[\s\S]*?<\/header>/gi, '')
|
||
.replace(/<footer[^>]*>[\s\S]*?<\/footer>/gi, '')
|
||
.replace(/<aside[^>]*>[\s\S]*?<\/aside>/gi, '')
|
||
.replace(/<iframe[^>]*>[\s\S]*?<\/iframe>/gi, '')
|
||
.replace(/<svg[^>]*>[\s\S]*?<\/svg>/gi, '')
|
||
// 移除 HTML 注释
|
||
.replace(/<!--[\s\S]*?-->/g, '')
|
||
// 块级标签转换行
|
||
.replace(/<\/?(p|div|h[1-6]|li|tr|blockquote|section|article|pre|br|hr)[^>]*>/gi, '\n')
|
||
// 表格单元格转制表符
|
||
.replace(/<\/?(td|th)[^>]*>/gi, '\t')
|
||
// 移除剩余标签
|
||
.replace(/<[^>]+>/g, '')
|
||
// 解码 HTML 实体
|
||
.replace(/&#(\d+);/g, (_, n) => String.fromCharCode(Number(n)))
|
||
.replace(/&#x([0-9a-f]+);/gi, (_, h) => String.fromCharCode(parseInt(h, 16)))
|
||
.replace(/&[a-z]+;/gi, (m) => HTML_ENTITY_MAP[m.toLowerCase()] ?? m)
|
||
// 清理空白
|
||
.replace(/\n{3,}/g, '\n\n')
|
||
.replace(/[ \t]+/g, ' ')
|
||
.replace(/^[ \t]+/gm, '')
|
||
.trim()
|
||
);
|
||
}
|
||
|
||
// ===== 流式读取(大文件保护,10MB 上限) =====
|
||
|
||
export async function readBodyWithLimit(
|
||
response: Response,
|
||
maxBytes = 10 * 1024 * 1024,
|
||
): Promise<string> {
|
||
const contentLength = response.headers.get('content-length');
|
||
if (contentLength && parseInt(contentLength) > maxBytes) {
|
||
throw new Error(`Response too large: ${contentLength} bytes (limit: ${maxBytes})`);
|
||
}
|
||
|
||
const reader = response.body?.getReader();
|
||
if (!reader) return '';
|
||
|
||
const chunks: Uint8Array[] = [];
|
||
let totalBytes = 0;
|
||
|
||
try {
|
||
while (true) {
|
||
const { done, value } = await reader.read();
|
||
if (done) break;
|
||
if (value) {
|
||
totalBytes += value.byteLength;
|
||
if (totalBytes > maxBytes) {
|
||
throw new Error(`Response exceeded ${maxBytes} bytes limit`);
|
||
}
|
||
chunks.push(value);
|
||
}
|
||
}
|
||
} finally {
|
||
reader.releaseLock();
|
||
}
|
||
|
||
const decoder = new TextDecoder('utf-8', { fatal: false });
|
||
return decoder.decode(Buffer.concat(chunks));
|
||
}
|
||
|
||
// ===== SearXNG 认证头构建 =====
|
||
|
||
export function buildSearXNGAuthHeaders(authKey: string, authType: string): Record<string, string> {
|
||
if (!authKey) return {};
|
||
if (authType === 'bearer') {
|
||
return { Authorization: `Bearer ${authKey}` };
|
||
}
|
||
if (authType === 'basic') {
|
||
return { Authorization: `Basic ${Buffer.from(authKey).toString('base64')}` };
|
||
}
|
||
return {};
|
||
}
|
||
|
||
// ===== 日志辅助 =====
|
||
|
||
export function logTool(toolName: string, message: string): void {
|
||
log.info(`[Tool:${toolName}] ${message}`);
|
||
}
|
||
|
||
// ===== v0.7.3 P2-2: Agent 浏览器 CORS Origin 回显 =====
|
||
|
||
/**
|
||
* v0.7.4 P2-2 根治: Agent 浏览器 CORS 放行的唯一事实来源。
|
||
*
|
||
* 背景(v0.7.3 P2-2 仍不彻底):旧实现回显任意请求 Origin —— 等价 ACAO:* 且
|
||
* 允许凭据(回显值非 '*' 时浏览器会携带 cookies/localStorage 跨域读取),第三方
|
||
* 页面可借该分区的凭据读取任何被浏览过的跨域资源,比通配 '*' 更宽松。
|
||
*
|
||
* 根治:仅当请求 Origin 与「当前 Agent 正在浏览的页面 Origin」完全一致时才回显。
|
||
* 同源请求本就不需要 CORS(放行无副作用);跨域 Origin(第三方页面借道)一律
|
||
* 返回 null —— 不加 ACAO 头,浏览器保持默认同源策略阻止读取。无 Origin(同源
|
||
* 导航/资源子请求)同样返回 null(原回退 '*' 的语义一并移除——同源请求无需
|
||
* CORS 头即可读取)。
|
||
*
|
||
* @param requestOrigin 请求头 Origin(可能为 undefined / 任意字符串)
|
||
* @param allowedOrigin 当前浏览页面的 origin(如 'https://example.com');null 表示未知
|
||
* @returns 应写入响应的 ACAO 值(单元素数组);null 表示不加 ACAO 头(默认阻止跨域)
|
||
*/
|
||
export function corsAllowOrigin(
|
||
requestOrigin: string | undefined | null,
|
||
allowedOrigin: string | null | undefined,
|
||
): string[] | null {
|
||
const origin = requestOrigin?.trim();
|
||
const allowed = allowedOrigin?.trim();
|
||
if (!origin || !allowed) return null;
|
||
// 大小写不敏感 + 去尾斜杠比较(origin 规范无尾斜杠,防御性处理)
|
||
const normalize = (o: string): string => o.toLowerCase().replace(/\/+$/, '');
|
||
if (normalize(origin) === normalize(allowed)) {
|
||
return [origin];
|
||
}
|
||
return null;
|
||
}
|
||
|
||
/** 从请求头集合中大小写不敏感地提取 Origin 值 */
|
||
export function extractOriginHeader(
|
||
requestHeaders: Record<string, string | string[] | undefined> | undefined,
|
||
): string | undefined {
|
||
if (!requestHeaders) return undefined;
|
||
for (const [key, value] of Object.entries(requestHeaders)) {
|
||
if (key.toLowerCase() === 'origin') {
|
||
return Array.isArray(value) ? value[0] : value;
|
||
}
|
||
}
|
||
return undefined;
|
||
}
|
||
|
||
// ===== v0.6.4 P4-4: HTML → Markdown 转换(web_fetch extract_mode='markdown') =====
|
||
//
|
||
// v0.6.4 收尾:私有 npm 凭据解锁后,按开发规范第一铁律把第一轮的临时自写实现
|
||
// 替换为 turndown(成熟库)。对外函数签名与行为契约保持不变:
|
||
// h1-h6(atx) / 段落 / 链接 / 图片 / strong+em+code 行内 / pre 围栏代码块 /
|
||
// ul('-') 与 ol(数字) 列表(跨空行合并为紧凑形态) / blockquote / hr('---') /
|
||
// 表格等未知块降级为纯文本、<script/style/svg/noscript/iframe> 整体剔除。
|
||
|
||
import TurndownService from 'turndown';
|
||
|
||
const turndown = new TurndownService({
|
||
headingStyle: 'atx',
|
||
bulletListMarker: '-',
|
||
codeBlockStyle: 'fenced',
|
||
emDelimiter: '*',
|
||
});
|
||
|
||
// 噪声节点显式剔除(与 htmlToText 的剥离口径一致)
|
||
turndown.remove(['script', 'style', 'noscript', 'iframe', 'svg']);
|
||
|
||
// hr 输出 GitHub 风格 '---'(turndown 默认 '* * *')
|
||
turndown.addRule('hr-rule', {
|
||
filter: ['hr'],
|
||
replacement: () => '\n\n---\n\n',
|
||
});
|
||
|
||
/** 列表项行判定:'- xxx' 或 '1. xxx'(允许前导空白) */
|
||
const LIST_LINE = /^\s*(?:- |\d+\. )/;
|
||
|
||
/**
|
||
* 紧凑化 + 规范化列表 —— turndown 对松散列表(li 之间带空白文本节点的常见书写)
|
||
* 输出条目间空行,且标记为 '- ' / '1. ' 多空格形态。这里做单趟扫描:
|
||
* 1. 归一化条目标记为紧凑形态('- ' / 'N. ');
|
||
* 2. 仅当"空行两侧都是同一列表的条目行"时移除该空行(绝不吞条目、不影响段落间距)。
|
||
*/
|
||
function collapseListGaps(markdown: string): string {
|
||
const lines = markdown
|
||
.split('\n')
|
||
.map((line) => line.replace(/^(\s*)- {2,}/, '$1- ').replace(/^(\s*\d+\.)\s{2,}/, '$1 '));
|
||
|
||
const isListItem = (l: string | undefined): boolean => (l ?? '').length > 0 && LIST_LINE.test(l!);
|
||
|
||
const out: string[] = [];
|
||
for (let i = 0; i < lines.length; i++) {
|
||
const line = lines[i];
|
||
if (line.trim() === '') {
|
||
const prev = out.length > 0 ? out[out.length - 1] : undefined;
|
||
const next = i + 1 < lines.length ? lines[i + 1] : undefined;
|
||
// 空行夹在两个列表项之间 → 移除;否则保留原始段落间隔
|
||
if (isListItem(prev) && isListItem(next)) continue;
|
||
out.push(line);
|
||
continue;
|
||
}
|
||
out.push(line);
|
||
}
|
||
return out.join('\n');
|
||
}
|
||
|
||
export function htmlToMarkdown(html: string): string {
|
||
if (!html || !html.trim()) return '';
|
||
|
||
let md: string;
|
||
try {
|
||
md = turndown.turndown(html);
|
||
} catch {
|
||
// 极端畸形输入时降级为空串(调用方已具备 Phase1 文本回退能力)
|
||
logTool?.('htmlToMarkdown', 'turndown conversion failed');
|
||
return '';
|
||
}
|
||
|
||
return collapseListGaps(md)
|
||
.replace(/\n{3,}/g, '\n\n')
|
||
.trim();
|
||
}
|