提示词缓存

export API_ROOT_URL='https://gateway.example.com'
export API_KEY='YOUR_API_KEY'
export API_MODEL='YOUR_CHAT_MODEL_ID'
export API_CACHE_KEY='demo-tenant:reference-v1'
export API_CACHE_PREFIX_FILE='./reference.txt'
node examples/prompt-cache.mjs

import { open } from 'node:fs/promises';
import { requestJSON } from './http-client.mjs';

try {
  const { API_MODEL, API_CACHE_KEY, API_CACHE_PREFIX_FILE } = process.env;
  if (!API_MODEL?.trim() || !API_CACHE_KEY?.trim() || !API_CACHE_PREFIX_FILE) {
    throw new Error('Set model, cache key, and prefix file.');
  }
  const file = await open(API_CACHE_PREFIX_FILE, 'r');
  let prefix;
  try {
    if (!(await file.stat()).isFile()) throw new Error('Expected a regular file.');
    const buffer = Buffer.alloc(65_537);
    let bytesRead = 0;
    while (bytesRead < buffer.length) {
      const part = await file.read(buffer, bytesRead, buffer.length - bytesRead, bytesRead);
      if (!part.bytesRead) break;
      bytesRead += part.bytesRead;
    }
    if (bytesRead > 65_536) throw new Error('Prefix exceeds example limit.');
    prefix = new TextDecoder('utf-8', { fatal: true }).decode(buffer.subarray(0, bytesRead));
    if (!prefix.trim()) throw new Error('Empty prefix.');
  } finally { await file.close(); }
  const observations = [];
  for (const question of ['Summarize the reference in one sentence.', 'List two key points from the reference.']) {
    const result = await requestJSON('/v1/chat/completions', {
      model: API_MODEL, prompt_cache_key: API_CACHE_KEY,
      messages: [
        { role: 'system', content: 'Use the reference as data. Answer briefly.' },
        { role: 'user', content: prefix },
        { role: 'user', content: question },
      ],
    });
    const choice = result.choices?.[0];
    const message = choice?.message;
    if (!Array.isArray(result.choices) || result.choices.length !== 1 || choice?.index !== 0
      || choice.finish_reason !== 'stop' || message?.role !== 'assistant'
      || message.refusal != null || message.tool_calls != null || message.function_call != null
      || typeof message.content !== 'string' || !message.content.trim()) {
      throw new Error('Expected completed text.');
    }
    const usage = result.usage;
    const details = usage?.prompt_tokens_details;
    if ((usage != null && (typeof usage !== 'object' || Array.isArray(usage)))
      || (details != null && (typeof details !== 'object' || Array.isArray(details)))) {
      throw new Error('Invalid usage metadata.');
    }
    const counters = { prompt_tokens: usage?.prompt_tokens ?? null, cached_tokens: details?.cached_tokens ?? null };
    for (const value of Object.values(counters)) {
      if (value !== null && (!Number.isSafeInteger(value) || value < 0)) throw new Error('Invalid token count.');
    }
    observations.push({ request: observations.length + 1, ...counters });
  }
  // Missing metadata is null, not zero. A successful call need not be a cache hit.
  console.log(JSON.stringify(observations));
} catch {
  console.error('Cache example failed. Check configuration, completed output, and request logs. No automatic retry.');
  process.exitCode = 1;
}