ضغط السياق

import { createAgent } from '@lousho/build-ai-agent';

const simple = createAgent({ model: 'openai/gpt-4o', compaction: true });

const agent = createAgent({
  model: 'openai/gpt-4o',
  compaction: {
    thresholdPercent: 0.8, // compact above 80% of the context window (default 0.9)
    protectedTokens: 20_000, // never change the newest 20K tokens (default 40_000)
    summarizer: 'openai/gpt-4o-mini', // prune, then summarize if still too big
  },
});

for await (const event of agent.stream('Audit the repository.')) {
  if (event.type === 'compaction.done') console.log(`${event.tokensBefore} -> ${event.tokensAfter} tokens`);
}

import { AgentExecutor, HookRegistry, createCompactionHook, twoPhaseStrategy } from '@lousho/build-ai-agent';

const hooks = new HookRegistry();
hooks.register(
  createCompactionHook({
    strategy: twoPhaseStrategy({ model: 'openai/gpt-4o-mini' }), // prune, then summarize if still too big
    thresholdPercent: 0.9, // compact above 90% of the context window (the default)
    protectedTokens: 40_000, // never change the newest 40K tokens (the default)
    onCompaction: ({ tokensBefore, tokensAfter, prunedToolCallIds, summary, error }) => {
      console.log(`compacted ${tokensBefore} -> ${tokensAfter} tokens (${prunedToolCallIds.length} results pruned)`);
      if (summary) console.log('summary:', summary);
      if (error) console.warn('summarizer failed, kept the pruned conversation:', error.message);
    },
  })
);

const result = await AgentExecutor.execute({ agent, input, provider, toolRegistry, hooks });

[Conversation summary]
<the summary>

import { pinMessage, isPinned, type Message } from '@lousho/build-ai-agent';

const messages: Message[] = [
  { role: 'system', content: 'You are a research assistant.' },
  pinMessage({ role: 'user', content: 'Goal: compare the three vendors on price and support.' }),
];
console.log(isPinned(messages[1])); // true

import { compactMessages, summarizeStrategy, type Message } from '@lousho/build-ai-agent';

declare const history: Message[];

const { messages, tokensBefore, tokensAfter, prunedToolCallIds } = await compactMessages(history, {
  protectedTokens: 8_000,
  model: 'gpt-4o-mini', // for the context-window lookup and the token estimator
});
console.log(`${tokensBefore} -> ${tokensAfter} tokens, pruned ${prunedToolCallIds.length} results`);

const summarized = await compactMessages(history, {
  protectedTokens: 8_000,
  strategy: summarizeStrategy({ model: 'openai/gpt-4o-mini' }),
});
console.log(summarized.summary ?? summarized.error?.message);

import { createAgent, twoPhaseStrategy } from '@lousho/build-ai-agent';
import { mockModel } from '@lousho/build-ai-agent/testing';

const agent = createAgent({ provider: mockModel(['ok']) });
const session = agent.session({ compaction: { strategy: twoPhaseStrategy({ model: 'openai/gpt-4o-mini' }) } });
session.on((event) => {
  if (event.type === 'compaction.done') console.log(event.trigger, event.tokensBefore, '->', event.tokensAfter);
});
await session.send('hello');
const { tokensBefore, tokensAfter } = await session.compact({ protectedTokens: 2_000 });
console.log(`${tokensBefore} -> ${tokensAfter} tokens`);
await session.clear();
console.log(session.messages.length); // 0

import { createCompactionHook, isPinned, type CompactionStrategy } from '@lousho/build-ai-agent';

// Keep the system prompt, pinned messages and the last 20 messages.
const keepRecent: CompactionStrategy = {
  name: 'keep-recent',
  compact({ messages, estimateTokens }) {
    const tokensBefore = estimateTokens(messages);
    if (messages.length <= 22) return { messages, tokensBefore, tokensAfter: tokensBefore, prunedToolCallIds: [] };
    // A real strategy must not split a tool call from its result.
    const older = messages.slice(0, -20).filter((m) => m.role === 'system' || isPinned(m));
    const kept = [...older, ...messages.slice(-20)];
    return { messages: kept, tokensBefore, tokensAfter: estimateTokens(kept), prunedToolCallIds: [] };
  },
};

const hook = createCompactionHook({ strategy: keepRecent });