Mintplex-Labs/anything-llm · error · Error

e.message

Error message

e.message

What it means

Same re-wrap anti-pattern: getChatCompletion's .catch flattens any upstream Moonshot API error to a plain Error(e.message). Note Moonshot's getChatCompletion skips the isValidChatCompletionModel pre-check entirely (unlike Minimax/Mistral/Novita) and goes straight to the call, then returns null on a choices-less response. So this catch is the only error boundary for the request.

Source

Thrown at server/utils/AiProviders/moonshotAi/index.js:121

    ];
  }

  async compressMessages(promptArgs = {}, rawHistory = []) {
    const { messageArrayCompressor } = require("../../helpers/chat");
    const messageArray = this.constructPrompt(promptArgs);
    return await messageArrayCompressor(this, messageArray, rawHistory);
  }

  async getChatCompletion(messages = null, { temperature = 0.7 }) {
    const result = await LLMPerformanceMonitor.measureAsyncFunction(
      this.openai.chat.completions
        .create({
          model: this.model,
          messages,
          temperature,
        })
        .catch((e) => {
          throw new Error(e.message);
        })
    );

    if (
      !Object.prototype.hasOwnProperty.call(result.output, "choices") ||
      result.output.choices.length === 0
    )
      return null;

    return {
      textResponse: result.output.choices[0].message.content,
      metrics: {
        prompt_tokens: result.output.usage.prompt_tokens || 0,
        completion_tokens: result.output.usage.completion_tokens || 0,
        total_tokens: result.output.usage.total_tokens || 0,
        outputTps: result.output.usage.completion_tokens / result.duration,
        duration: result.duration,
        model: this.model,

View on GitHub (pinned to 526360e320)

Solutions

1. Read the message for the upstream detail (often includes the real cause).
2. If context-length related, switch to moonshot-v1-32k or 128k, or trim history.
3. If auth-related, verify MOONSHOT_AI_API_KEY.
4. Add backoff/retry for 429/5xx text.

Example fix

// before
.catch((e) => {
  throw new Error(e.message);
})

// after
.catch((e) => {
  const err = new Error(`Moonshot chat failed (${e?.status}): ${e.message}`);
  err.cause = e;
  err.status = e?.status;
  throw err;
})

try {
  await llm.getChatCompletion(messages, { temperature });
} catch (e) {
  const msg = e.message || '';
  if (/context.*(length|window)|too many tokens/i.test(msg)) { /* trim history or use a larger model */ }
  else if (/429|rate/i.test(msg)) { /* backoff */ }
  else if (/401|api key/i.test(msg)) { /* rotate key */ }
}

When it happens

Trigger: Any upstream failure from openai.chat.completions.create against api.moonshot.ai: 401, 429, 400 (e.g. context length exceeded on moonshot-v1-8k/32k), timeout, or 5xx.

Common situations: Invalid Moonshot key; exceeding the model's context window (Moonshot enforces per-model token limits); rate limiting; transient outage; the re-wrap hiding whether it was a context-length error vs auth.

Related errors

• e.message
• e.message
• e.message
• res.statusText
• Could not update agent plugin status.

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/6fb6155478667b8d. Report an issue: GitHub.