上下文修剪器

专为DeepSeek的64k上下文窗口优化的高级上下文管理工具。提供智能修剪、压缩和词元优化，防止上下文溢出，同时保留重要信息。

核心功能

• 专为DeepSeek优化: 专门针对64k上下文窗口调优
• 自适应修剪: 基于上下文使用情况的多策略修剪
• 语义去重: 移除冗余信息
• 优先级感知: 保留高价值消息
• 词元高效: 最小化词元开销
• 实时监控: 持续追踪上下文健康状态

快速开始

动态上下文自动压缩：

import { createContextPruner } from './lib/index.js';

const pruner = createContextPruner({
  contextLimit: 64000, // DeepSeek's limit
  autoCompact: true,    // Enable automatic compaction
  dynamicContext: true, // Enable dynamic relevance-based context
  strategies: ['semantic', 'temporal', 'extractive', 'adaptive'],
  queryAwareCompaction: true, // Compact based on current query relevance
});

await pruner.initialize();

// Process messages with auto-compaction and dynamic context
const processed = await pruner.processMessages(messages, currentQuery);

// Get context health status
const status = pruner.getStatus();
console.log(`Context health: ${status.health}, Relevance scores: ${status.relevanceScores}`);

// Manual compaction when needed
const compacted = await pruner.autoCompact(messages, currentQuery);

归档检索（分层记忆）：

// When something isn't in current context, search archive
const archiveResult = await pruner.retrieveFromArchive('query about previous conversation', {
  maxContextTokens: 1000,
  minRelevance: 0.4,
});

if (archiveResult.found) {
  // Add relevant snippets to current context
  const archiveContext = archiveResult.snippets.join('\n\n');
  // Use archiveContext in your prompt
  console.log(`Found ${archiveResult.sources.length} relevant sources`);
  console.log(`Retrieved ${archiveResult.totalTokens} tokens from archive`);
}

自动压缩策略

1. 语义压缩合并相似消息而非直接删除
2. 时序压缩：按时间窗口汇总历史对话
3. 提取式压缩：从冗长消息中提取关键信息
4. 自适应压缩：根据消息特征选择最佳策略
5. 动态上下文：根据与当前查询的相关性筛选消息

动态上下文管理

• 查询感知相关性：根据与当前查询的相似度对消息评分
• 相关性衰减：历史对话的相关性评分随时间衰减
• 自适应过滤：自动过滤低相关性消息
• 优先级整合：结合消息优先级与语义相关性

分层记忆系统

上下文归档采用类似内存与存储的架构设计：

• 当前上下文（内存）：有限（64k tokens），访问快速，自动压缩
• 存档（存储）：容量更大（100MB），速度较慢但可搜索
• 智能检索：当信息不在当前上下文中时，高效搜索存档
• 选择性加载：仅提取相关片段，而非整个文档
• 自动存储：压缩后的内容自动存入存档

配置

{
  contextLimit: 64000, // DeepSeek's context window
  autoCompact: true, // Enable automatic compaction
  compactThreshold: 0.75, // Start compacting at 75% usage
  aggressiveCompactThreshold: 0.9, // Aggressive compaction at 90%
  
  dynamicContext: true, // Enable dynamic context management
  relevanceDecay: 0.95, // Relevance decays 5% per time step
  minRelevanceScore: 0.3, // Minimum relevance to keep
  queryAwareCompaction: true, // Compact based on current query relevance
  
  strategies: ['semantic', 'temporal', 'extractive', 'adaptive'],
  preserveRecent: 10, // Always keep last N messages
  preserveSystem: true, // Always keep system messages
  minSimilarity: 0.85, // Semantic similarity threshold
  
  // Archive settings
  enableArchive: true, // Enable hierarchical memory system
  archivePath: './context-archive',
  archiveSearchLimit: 10,
  archiveMaxSize: 100 * 1024 * 1024, // 100MB
  archiveIndexing: true,
  
  // Chat logging
  logToChat: true, // Log optimization events to chat
  chatLogLevel: 'brief', // 'brief', 'detailed', or 'none'
  chatLogFormat: '📊 {action}: {details}', // Format for chat messages
  
  // Performance
  batchSize: 5, // Messages to process in batch
  maxCompactionRatio: 0.5, // Maximum 50% compaction in one pass
}

聊天日志记录

上下文优化器可以直接将事件记录到聊天中：

// Example chat log messages:
// 📊 Context optimized: Compacted 15 messages → 8 (47% reduction)
// 📊 Archive search: Found 3 relevant snippets (42% similarity)
// 📊 Dynamic context: Filtered 12 low-relevance messages

// Configure logging:
const pruner = createContextPruner({
  logToChat: true,
  chatLogLevel: 'brief', // Options: 'brief', 'detailed', 'none'
  chatLogFormat: '📊 {action}: {details}',
  
  // Custom log handler (optional)
  onLog: (level, message, data) => {
    if (level === 'info' && data.action === 'compaction') {
      // Send to chat
      console.log(`🧠 Context optimized: ${message}`);
    }
  }
});

与Clawdbot集成

添加到您的Clawdbot配置中：

skills:
  context-pruner:
    enabled: true
    config:
      contextLimit: 64000
      autoPrune: true

修剪器将自动监控上下文使用情况，并应用适当的修剪策略，以保持在DeepSeek的64k限制内。