安全修复： - 开启 webSecurity（CORS 改为 webRequest 允许清单精确放行 Ollama 地址） - 新增 net-guard SSRF 防护：web_fetch/download_file/browser_open 拦截环回/内网/链路本地地址（DNS 解析后校验） - browser_open 协议白名单（仅 http/https，阻止 file:// 绕过路径安全层） - git 参数注入防护（用户可控参数禁止 - 开头；git add 强制 -- 分隔） - 身份文件保护：SOUL.md/AGENT.md/USER.md 工具只读（防提示注入持久化劫持） - 系统目录硬红线 + 工作空间/白名单不可豁免系统目录 - spawn_task 权限只降不升（封顶于用户设置 subAgentMaxPermission） - 子代理写类工具接入主 Agent 确认管线 + 完整路径沙箱 - toast 改 textContent、HTML 导出 escapeHtml（XSS 修复） - Agent 浏览器改用 memory: 内存分区（退出清空 cookie/storage） 数据层重构： - sql.js 写入改防抖批量落盘（300ms 合并快照 + temp 原子替换 + 退出刷盘） - Schema 迁移改 PRAGMA user_version 顺序迁移数组 - 消息/设置/轨迹批量写（单事务）；SearXNG 配置 13 次写合并为 1 次 - 会话摘要查询（getSessionSummaries/searchSessions 单条 SQL）消除 N+1 - 导出改 getAllSessionsData 一次 IPC 取回全部行 Bug 修复： - edit_file 替换符污染（$&/$1 被特殊解释导致文件写坏） - truncateToolResult 暴力截断拼接非法 JSON 必然崩溃 - diff 算法 100MB dp 数组 → 前缀/后缀裁剪 + LCS 限额 + 回退 - move_file 跨盘 rename 失败回退 copy+delete - Ctrl+K 快捷键冲突（双注册）；全局错误处理器双注册 - ffmpeg stderr 无限累积 + 帧进度 O(n²) 正则 - 搜索可达性预检只取响应头（Range: bytes=0-0） - 备份导出逐字节 base64 拼接（O(n²)）改 FileReader - MCP clientInfo 版本硬编码 5.0.0 改真实版本；tools/list 支持 nextCursor 分页 - 看门狗默认值统一为 30 分钟；download_file 超时跟随用户配置 架构改进： - 主进程工具分发注册表 tool-dispatch.ts（消除 switch 硬编码） - agent-engine 拆分 result-formatter.ts / tool-parsing.ts（纯函数） - 文本兜底解析白名单改从注册表派生（补齐 browser_*/diff/spawn_task/mcp_*） - diff 工具默认启用；MODE_TOOLS 单一事实来源（tools-modal 复用） - 记忆系统：条目缓存 + 访问统计(hits/last)持久化 + removeById 按 ID 删除 - 度量历史启动恢复 + Metrics 仪表盘接入 JSON/Prometheus 导出 - 子代理模型下拉框打开设置时刷新（此前从未填充） 死代码清理（约 1400 行）： - 删除 context-indexer 整模块、agent-safety 震荡检测/性能报告/依赖图/记忆调优/归档取回 - 删除 context-manager 水印/跳过压缩/自适应窗口/趋势分析/预算分配等未接线函数 - 删除 sanitizeToolArgs（污染 write_file 内容，防注入职责移交主进程安全层） - infra-service 裁剪为全局错误处理器唯一定义 文档对齐： - 新增内置 AGENT.md（工作空间同名文件可覆盖） - README/帮助面板/DEVELOPMENT 移除失实描述（WAL/内部URL拦截/5层防御/并行白名单/Hook 数量） - 工具数量口径统一 33；安全机制表新增 SSRF/身份保护/子代理权限等 9 项 工程化： - Vitest + 34 个单元测试（myers-diff/calculator/net-guard/MEMORY.md 格式） - Gitea Actions CI（typecheck + test + build） - package.json 新增 typecheck/test 脚本
This commit is contained in:
@@ -155,27 +155,17 @@ export function predictContextOverflow(numCtx: number): ContextPrediction {
|
||||
return { level, currentUsage, predictedUsage, turnsToOverflow, message };
|
||||
}
|
||||
|
||||
/** R18: 获取 token 使用趋势数据（供调试用） */
|
||||
export function getTokenUsageTrend(): TokenUsagePoint[] {
|
||||
return [..._tokenUsageTrend];
|
||||
}
|
||||
|
||||
// ── Token 校准系统 ──
|
||||
|
||||
/** 校准比例：actualTokens / estimatedTokens，基于 Ollama 返回的实际计数动态修正 */
|
||||
// ── Token 估算校准状态 ──
|
||||
let _calibrationModel = '';
|
||||
let _tokenCalibrationRatio = 1.0;
|
||||
let _calibrationSamples = 0;
|
||||
let _calibrationModel = ''; // C8: 记录校准时的模型名
|
||||
const MIN_CALIBRATION_SAMPLES = 3;
|
||||
const MIN_CALIBRATION_SAMPLES = 5;
|
||||
|
||||
/** 自动压缩触发阈值（占上下文窗口比例） */
|
||||
export const AUTO_COMPRESS_THRESHOLD = 0.5;
|
||||
|
||||
/**
|
||||
* 记录 Ollama 返回的实际 token 计数，用于校准估算器。
|
||||
* 在 agent-engine.ts 每轮流式完成后调用。
|
||||
* C8: 模型切换时自动重置校准比例，避免不同 tokenizer 导致估算失真
|
||||
* @param actualInputTokens Ollama 返回的 prompt_eval_count
|
||||
* @param actualOutputTokens Ollama 返回的 eval_count
|
||||
* @param estimatedTokens 本轮消息调用 estimateTokens 的合计值
|
||||
* @param modelName 当前使用的模型名
|
||||
*/
|
||||
export function recordActualTokens(actualInputTokens: number, actualOutputTokens: number, estimatedCount: number, modelName?: string): void {
|
||||
// C8: 模型切换时重置校准
|
||||
@@ -212,19 +202,7 @@ export function estimateTokens(text: string): number {
|
||||
return raw;
|
||||
}
|
||||
|
||||
/** 获取当前校准比例（供调试用） */
|
||||
export function getTokenCalibration(): { ratio: number; samples: number } {
|
||||
return { ratio: _tokenCalibrationRatio, samples: _calibrationSamples };
|
||||
}
|
||||
|
||||
/** 自动压缩阈值：当消息 token 占 context window 比例超过此值时触发自动压缩
|
||||
* P2 #7 修复：从 0.3 提高到 0.5，避免过于频繁的压缩导致信息丢失
|
||||
*/
|
||||
export const AUTO_COMPRESS_THRESHOLD = 0.5;
|
||||
|
||||
/** R14: 自适应压缩阈值 — 根据模型上下文长度动态调整
|
||||
* P2 #7 修复：提高各档位阈值，减少不必要的压缩
|
||||
*/
|
||||
/** 自适应压缩阈值 — 根据模型上下文长度动态调整 */
|
||||
export function getAdaptiveCompressThreshold(numCtx: number): number {
|
||||
// 小上下文模型（<8K）：更早触发压缩（55%），留余量
|
||||
// 中等上下文（8K-32K）：标准阈值（50%）
|
||||
@@ -1580,235 +1558,6 @@ export function chooseCompressionStrategy(
|
||||
};
|
||||
}
|
||||
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
// R115: 上下文水印 — 标记不可压缩的关键信息
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
|
||||
/** 水印标记：带有此标记的消息在压缩时会被保留 */
|
||||
const WATERMARK_PREFIX = '[PRESERVE]';
|
||||
const _watermarkedIndices = new Set<number>();
|
||||
|
||||
/** R115: 标记消息为不可压缩 */
|
||||
export function watermarkMessage(index: number): void {
|
||||
_watermarkedIndices.add(index);
|
||||
}
|
||||
|
||||
/** R115: 检查消息是否被水印保护 */
|
||||
export function isWatermarked(index: number): boolean {
|
||||
return _watermarkedIndices.has(index);
|
||||
}
|
||||
|
||||
/** R115: 自动为关键消息添加水印 */
|
||||
export function autoWatermarkCritical(messages: OllamaMessage[]): number[] {
|
||||
const protectedIndices: number[] = [];
|
||||
|
||||
for (let i = 0; i < messages.length; i++) {
|
||||
const msg = messages[i];
|
||||
const content = msg.content || '';
|
||||
|
||||
// 系统消息始终保护
|
||||
if (msg.role === 'system') {
|
||||
watermarkMessage(i);
|
||||
protectedIndices.push(i);
|
||||
continue;
|
||||
}
|
||||
|
||||
// 包含错误信息的用户消息保护
|
||||
if (msg.role === 'user' && (content.includes('错误') || content.includes('error') || content.includes('失败'))) {
|
||||
watermarkMessage(i);
|
||||
protectedIndices.push(i);
|
||||
continue;
|
||||
}
|
||||
|
||||
// 最近 5 条消息保护
|
||||
if (i >= messages.length - 5) {
|
||||
watermarkMessage(i);
|
||||
protectedIndices.push(i);
|
||||
}
|
||||
}
|
||||
|
||||
return protectedIndices;
|
||||
}
|
||||
|
||||
/** R115: 清除水印 */
|
||||
export function clearWatermarks(): void {
|
||||
_watermarkedIndices.clear();
|
||||
}
|
||||
|
||||
/** R115: 获取受保护的消息索引列表 */
|
||||
export function getWatermarkedIndices(): number[] {
|
||||
return Array.from(_watermarkedIndices).sort((a, b) => a - b);
|
||||
}
|
||||
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
// R120: 上下文压缩跳过逻辑 — 不值得压缩时跳过
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
|
||||
/** R120: 判断是否应该跳过压缩 */
|
||||
export function shouldSkipCompression(
|
||||
messages: OllamaMessage[],
|
||||
numCtx: number,
|
||||
recentCompressionRatio: number
|
||||
): { skip: boolean; reason: string } {
|
||||
const totalTokens = estimateTokens(messages.map(m => m.content || '').join(''));
|
||||
const usageRatio = numCtx > 0 ? totalTokens / numCtx : 0;
|
||||
|
||||
// 如果使用率很低，跳过
|
||||
if (usageRatio < 0.2) {
|
||||
return { skip: true, reason: `上下文使用率极低 (${(usageRatio * 100).toFixed(0)}%)，无需压缩` };
|
||||
}
|
||||
|
||||
// 如果消息数太少，跳过
|
||||
if (messages.length < 10) {
|
||||
return { skip: true, reason: `消息数过少 (${messages.length} 条)，无需压缩` };
|
||||
}
|
||||
|
||||
// 如果最近压缩收益很低（压缩比 < 10%），跳过
|
||||
if (recentCompressionRatio > 0.9) {
|
||||
return { skip: true, reason: `最近压缩收益低 (压缩比 ${(recentCompressionRatio * 100).toFixed(0)}%)，跳过` };
|
||||
}
|
||||
|
||||
// 如果大部分消息已经被归档/压缩过，跳过
|
||||
const archivedCount = messages.filter(m =>
|
||||
m.content?.includes('[工具结果已归档]') || m.content?.includes('[PRESERVE]')
|
||||
).length;
|
||||
if (archivedCount / messages.length > 0.6) {
|
||||
return { skip: true, reason: `大部分消息已归档 (${(archivedCount / messages.length * 100).toFixed(0)}%)，跳过` };
|
||||
}
|
||||
|
||||
return { skip: false, reason: '' };
|
||||
}
|
||||
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
// R121: 滑动窗口自适应大小 — 根据上下文压力动态调整窗口大小
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
|
||||
/** R121: 根据上下文压力获取自适应滑动窗口大小 */
|
||||
export function getAdaptiveWindowSize(
|
||||
totalMessages: number,
|
||||
pressureLevel: string,
|
||||
numCtx: number
|
||||
): { keepRecent: number; keepSystem: number; reason: string } {
|
||||
const baseWindow = Math.min(totalMessages, 40);
|
||||
|
||||
switch (pressureLevel) {
|
||||
case 'critical':
|
||||
return {
|
||||
keepRecent: Math.min(baseWindow, 15),
|
||||
keepSystem: 2,
|
||||
reason: '关键压力：保留最近 15 条 + 系统 2 条',
|
||||
};
|
||||
case 'high':
|
||||
return {
|
||||
keepRecent: Math.min(baseWindow, 25),
|
||||
keepSystem: 3,
|
||||
reason: '高压力：保留最近 25 条 + 系统 3 条',
|
||||
};
|
||||
case 'medium':
|
||||
return {
|
||||
keepRecent: Math.min(baseWindow, 35),
|
||||
keepSystem: 5,
|
||||
reason: '中等压力：保留最近 35 条 + 系统 5 条',
|
||||
};
|
||||
case 'low':
|
||||
default:
|
||||
return {
|
||||
keepRecent: Math.min(baseWindow, 50),
|
||||
keepSystem: 5,
|
||||
reason: '低压力：保留最近 50 条 + 系统 5 条',
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
// R122: Token 趋势分析 — 深度分析 token 使用趋势用于预测性压缩
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
|
||||
export interface TrendAnalysis {
|
||||
trend: 'increasing' | 'decreasing' | 'stable';
|
||||
avgGrowthRate: number; // 每轮平均 token 增长量
|
||||
projectedOverflow: number; // 预计几轮后溢出（-1=不会）
|
||||
recommendedAction: string;
|
||||
confidence: number; // 0-1
|
||||
}
|
||||
|
||||
/** R122: 分析 token 使用趋势 */
|
||||
export function analyzeTokenTrend(numCtx: number): TrendAnalysis {
|
||||
if (_tokenUsageTrend.length < 3) {
|
||||
return {
|
||||
trend: 'stable',
|
||||
avgGrowthRate: 0,
|
||||
projectedOverflow: -1,
|
||||
recommendedAction: '数据不足，暂不推荐操作',
|
||||
confidence: 0,
|
||||
};
|
||||
}
|
||||
|
||||
const points = _tokenUsageTrend;
|
||||
const n = points.length;
|
||||
|
||||
// 计算平均增长率
|
||||
let totalGrowth = 0;
|
||||
let growthCount = 0;
|
||||
for (let i = 1; i < n; i++) {
|
||||
const growth = points[i].tokens - points[i - 1].tokens;
|
||||
totalGrowth += growth;
|
||||
growthCount++;
|
||||
}
|
||||
const avgGrowthRate = growthCount > 0 ? totalGrowth / growthCount : 0;
|
||||
|
||||
// 线性回归确定趋势
|
||||
const xs = points.map(p => p.turn);
|
||||
const ys = points.map(p => p.tokens);
|
||||
const xMean = xs.reduce((s, x) => s + x, 0) / n;
|
||||
const yMean = ys.reduce((s, y) => s + y, 0) / n;
|
||||
let num = 0, den = 0;
|
||||
for (let i = 0; i < n; i++) {
|
||||
num += (xs[i] - xMean) * (ys[i] - yMean);
|
||||
den += (xs[i] - xMean) ** 2;
|
||||
}
|
||||
const slope = den !== 0 ? num / den : 0;
|
||||
|
||||
// 判断趋势
|
||||
let trend: TrendAnalysis['trend'];
|
||||
if (slope > 100) trend = 'increasing';
|
||||
else if (slope < -50) trend = 'decreasing';
|
||||
else trend = 'stable';
|
||||
|
||||
// 预测溢出
|
||||
let projectedOverflow = -1;
|
||||
if (slope > 0) {
|
||||
const currentTokens = points[n - 1].tokens;
|
||||
const remaining = numCtx - currentTokens;
|
||||
projectedOverflow = Math.ceil(remaining / slope);
|
||||
if (projectedOverflow < 0) projectedOverflow = 0;
|
||||
}
|
||||
|
||||
// 推荐操作
|
||||
let recommendedAction = '';
|
||||
if (trend === 'increasing' && projectedOverflow >= 0 && projectedOverflow <= 5) {
|
||||
recommendedAction = `⚠️ 预计 ${projectedOverflow} 轮后上下文溢出，建议立即压缩`;
|
||||
} else if (trend === 'increasing' && projectedOverflow > 5 && projectedOverflow <= 10) {
|
||||
recommendedAction = `建议在接下来 2-3 轮内进行压缩（${projectedOverflow} 轮后溢出）`;
|
||||
} else if (trend === 'stable') {
|
||||
recommendedAction = 'Token 使用趋势稳定，无需额外操作';
|
||||
} else if (trend === 'decreasing') {
|
||||
recommendedAction = 'Token 使用量在下降，压缩策略生效';
|
||||
}
|
||||
|
||||
// 置信度：基于数据点数量和趋势一致性
|
||||
let confidence = Math.min(1, n / 10);
|
||||
if (trend === 'stable') confidence *= 0.7;
|
||||
|
||||
return {
|
||||
trend,
|
||||
avgGrowthRate: Math.round(avgGrowthRate),
|
||||
projectedOverflow,
|
||||
recommendedAction,
|
||||
confidence,
|
||||
};
|
||||
}
|
||||
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
// R123: 会话摘要持久化 — 跨会话引用
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
@@ -1862,7 +1611,7 @@ export function generateSessionSummary(
|
||||
const toolsUsed = [...new Set(toolRecords.map(t => t.name))];
|
||||
const assistantMessages = messages.filter(m => m.role === 'assistant');
|
||||
const lastAssistant = assistantMessages[assistantMessages.length - 1];
|
||||
|
||||
|
||||
return {
|
||||
id: `session_${Date.now()}_${Math.random().toString(36).slice(2, 8)}`,
|
||||
createdAt: Date.now(),
|
||||
@@ -1886,7 +1635,7 @@ export function formatSessionSummariesForContext(summaries: SessionSummary[]): s
|
||||
}
|
||||
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
// R125: Agent 状态检查点 — 保存和恢复 Agent 状态
|
||||
// R125: Agent 状态检查点 — 保存 Agent 运行状态（恢复 API 见后续迭代）
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
|
||||
export interface AgentCheckpoint {
|
||||
@@ -1919,138 +1668,18 @@ export function createCheckpoint(
|
||||
toolRecordsCount,
|
||||
goal,
|
||||
};
|
||||
|
||||
|
||||
_checkpoints.push(checkpoint);
|
||||
if (_checkpoints.length > MAX_CHECKPOINTS) {
|
||||
_checkpoints.shift();
|
||||
}
|
||||
|
||||
|
||||
logInfo(`R125: 检查点已创建 (loop=${loopCount}, state=${agentState})`);
|
||||
return checkpoint;
|
||||
}
|
||||
|
||||
/** R125: 获取最近的检查点 */
|
||||
export function getLatestCheckpoint(): AgentCheckpoint | null {
|
||||
return _checkpoints.length > 0 ? _checkpoints[_checkpoints.length - 1] : null;
|
||||
}
|
||||
|
||||
/** R125: 恢复到指定检查点 */
|
||||
export function restoreCheckpoint(id: string): AgentCheckpoint | null {
|
||||
const cp = _checkpoints.find(c => c.id === id);
|
||||
if (!cp) {
|
||||
logWarn(`R125: 检查点 ${id} 不存在`);
|
||||
return null;
|
||||
}
|
||||
logInfo(`R125: 恢复到检查点 ${id} (loop=${cp.loopCount})`);
|
||||
return cp;
|
||||
}
|
||||
|
||||
/** R125: 获取所有检查点 */
|
||||
export function getAllCheckpoints(): AgentCheckpoint[] {
|
||||
return [..._checkpoints];
|
||||
}
|
||||
|
||||
/** R125: 清除所有检查点 */
|
||||
export function clearCheckpoints(): void {
|
||||
_checkpoints.length = 0;
|
||||
}
|
||||
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
// R126: 上下文预算分配 — 按消息类型分配上下文 token 预算
|
||||
// ═══════════════════════════════════════════════════════════════
|
||||
|
||||
export interface ContextBudgetAllocation {
|
||||
system: number; // 系统消息预算
|
||||
user: number; // 用户消息预算
|
||||
assistant: number; // 助手消息预算
|
||||
tool: number; // 工具结果预算
|
||||
memory: number; // 记忆注入预算
|
||||
total: number; // 总预算
|
||||
}
|
||||
|
||||
/** R126: 默认预算分配比例 */
|
||||
const DEFAULT_BUDGET_RATIOS = {
|
||||
system: 0.05, // 5%
|
||||
user: 0.15, // 15%
|
||||
assistant: 0.25, // 25%
|
||||
tool: 0.45, // 45%
|
||||
memory: 0.10, // 10%
|
||||
};
|
||||
|
||||
/** R126: 根据消息分布动态调整预算分配 */
|
||||
export function allocateContextBudget(
|
||||
messages: OllamaMessage[],
|
||||
numCtx: number
|
||||
): ContextBudgetAllocation {
|
||||
const total = numCtx;
|
||||
|
||||
// 统计各类型消息当前占比
|
||||
const counts = { system: 0, user: 0, assistant: 0, tool: 0 };
|
||||
let memorySize = 0;
|
||||
|
||||
for (const msg of messages) {
|
||||
if (msg.role in counts) {
|
||||
counts[msg.role as keyof typeof counts]++;
|
||||
}
|
||||
if (msg.content?.includes('[记忆注入]')) {
|
||||
memorySize += estimateTokens(msg.content);
|
||||
}
|
||||
}
|
||||
|
||||
const totalMsgs = messages.length || 1;
|
||||
|
||||
// 动态调整：如果工具结果占比过高，增加工具预算
|
||||
const toolRatio = counts.tool / totalMsgs;
|
||||
const ratios = { ...DEFAULT_BUDGET_RATIOS };
|
||||
|
||||
if (toolRatio > 0.5) {
|
||||
// 工具结果过多，从助手预算中转移一部分给工具
|
||||
const shift = Math.min(0.1, (toolRatio - 0.5) * 0.3);
|
||||
ratios.assistant -= shift;
|
||||
ratios.tool += shift;
|
||||
}
|
||||
|
||||
// 如果记忆注入很大，增加记忆预算
|
||||
if (memorySize > numCtx * 0.1) {
|
||||
const shift = Math.min(0.05, (memorySize / numCtx - 0.1) * 0.2);
|
||||
ratios.tool -= shift;
|
||||
ratios.memory += shift;
|
||||
}
|
||||
|
||||
return {
|
||||
system: Math.floor(total * ratios.system),
|
||||
user: Math.floor(total * ratios.user),
|
||||
assistant: Math.floor(total * ratios.assistant),
|
||||
tool: Math.floor(total * ratios.tool),
|
||||
memory: Math.floor(total * ratios.memory),
|
||||
total,
|
||||
};
|
||||
}
|
||||
|
||||
/** R126: 检查消息是否超出预算 */
|
||||
export function checkBudgetOverflow(
|
||||
messages: OllamaMessage[],
|
||||
budget: ContextBudgetAllocation
|
||||
): { role: string; current: number; budget: number; overflow: number }[] {
|
||||
const tokensByRole: Record<string, number> = {};
|
||||
for (const msg of messages) {
|
||||
tokensByRole[msg.role] = (tokensByRole[msg.role] || 0) + estimateTokens(msg.content || '');
|
||||
}
|
||||
|
||||
const overflows: { role: string; current: number; budget: number; overflow: number }[] = [];
|
||||
const budgetMap: Record<string, number> = {
|
||||
system: budget.system,
|
||||
user: budget.user,
|
||||
assistant: budget.assistant,
|
||||
tool: budget.tool,
|
||||
};
|
||||
|
||||
for (const [role, current] of Object.entries(tokensByRole)) {
|
||||
const bud = budgetMap[role] || Infinity;
|
||||
if (current > bud) {
|
||||
overflows.push({ role, current, budget: bud, overflow: current - bud });
|
||||
}
|
||||
}
|
||||
|
||||
return overflows;
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user