What causes "${e.message}" in Mintplex-Labs/anything-llm?

Inspect the raw e.message — CometAPI errors typically include the HTTP status and a reason string.

Mintplex-Labs/anything-llm · error · Error

${e.message}

Error message

${e.message}

What it means

Re-throws the OpenAI SDK error message when the CometAPI OpenAI-compatible chat completions request fails. The .catch wraps the SDK error into a generic Error, stripping the original error object's status code, type, and response metadata. Any transport-layer or API-layer failure from the OpenAI client collapses into this single message string.

Source

Thrown at server/utils/AiProviders/cometapi/index.js:210

      },
    ];
  }

  async getChatCompletion(messages = null, { temperature = 0.7 }) {
    if (!(await this.isValidChatCompletionModel(this.model)))
      throw new Error(
        `CometAPI chat: ${this.model} is not valid for chat completion!`
      );

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

    if (
      !result.output.hasOwnProperty("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

Inspect the raw e.message — CometAPI errors typically include the HTTP status and a reason string.
Check the CometAPI dashboard for remaining quota/credits and API key status.
If the error is a transient 5xx, retry the request with exponential backoff.
Patch the catch to preserve the SDK error object rather than rewrapping into a plain Error.

Example fix

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

// after
.catch((e) => {
  throw e; // preserve status code and structured error

Defensive patterns

Strategy: retry

Type guard

/** OpenAI SDK errors carry numeric `status` and an `error` object. */
function isOpenAiSdkError(e) {
  return e instanceof Error && typeof e.status === 'number';
}

Try / catch

try {
  return await comet.getChatCompletion(messages, { temperature });
} catch (e) {
  if (/429|rate|quota|insufficient/i.test(e.message)) {
    await sleep(2000 * attempt);
    return retry();
  }
  if (/401|403|unauthorized/i.test(e.message))
    throw new Error('CometAPI key invalid — check COMETAPI_LLM_API_KEY and account credits');
  throw e;
}

Prevention

Monitor CometAPI credit balance and set up low-balance alerts.
Implement exponential backoff for transient 5xx/429 errors.
Log the full error object during development since e.message alone may omit the status code.

When it happens

Trigger: CometAPI rejecting the request due to an invalid model, insufficient credits/quota, malformed message payload, API key authentication failure, or a network timeout; CometAPI returning a non-OpenAI-schema error body that the SDK cannot parse.

Common situations: Exhausted CometAPI credit balance producing a 402/403; transient CometAPI gateway errors (502/503) during peak load; the model being valid per the cache but disabled server-side; proxies or firewalls intercepting the request to api.cometapi.com.

Related errors

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/981cbaab5da4258f. Report an issue: GitHub.