micro/go-micro · error

no response from API

Error message

no response from API

What it means

Thrown after a successful JSON parse when the Mistral chat completion response contains zero choices. The library guarantees at least one choice to return a Reply, so an empty choices array is treated as 'no response from API'.

Source

Thrown at ai/mistral/mistral.go:203

		Choices []struct {
			Message struct {
				Content   string `json:"content"`
				ToolCalls []struct {
					ID       string `json:"id"`
					Function struct {
						Name      string `json:"name"`
						Arguments string `json:"arguments"`
					} `json:"function"`
				} `json:"tool_calls"`
			} `json:"message"`
		} `json:"choices"`
	}

	if err := json.Unmarshal(respBody, &chatResp); err != nil {
		return nil, nil, fmt.Errorf("failed to parse response: %w", err)
	}
	if len(chatResp.Choices) == 0 {
		return nil, nil, fmt.Errorf("no response from API")
	}

	choice := chatResp.Choices[0]
	response := &ai.Response{Reply: choice.Message.Content}

	for _, tc := range choice.Message.ToolCalls {
		var input map[string]any
		if err := json.Unmarshal([]byte(tc.Function.Arguments), &input); err != nil {
			input = map[string]any{}
		}
		response.ToolCalls = append(response.ToolCalls, ai.ToolCall{
			ID:    tc.ID,
			Name:  tc.Function.Name,
			Input: input,
		})
	}

	rawMessage := map[string]any{

View on GitHub (pinned to 24529f1404)

Solutions

1. Log the full response body when choices is empty to inspect any error/metadata fields
2. Verify the model name and prompt are valid for the Mistral API
3. Add an error/message field to the response struct and surface it instead of the generic message
4. Retry the request once; transient empty responses are often intermittent

Example fix

// before
if len(chatResp.Choices) == 0 {
    return nil, nil, fmt.Errorf("no response from API")
}
// after
if len(chatResp.Choices) == 0 {
    return nil, nil, fmt.Errorf("no response from API (status %s): %s", httpResp.Status, string(respBody))
}

if req.Model == "" {
    return fmt.Errorf("model name is required")
}

func hasChoices(c *chatCompletionResponse) bool {
    return c != nil && len(c.Choices) > 0
}

resp, err := provider.Generate(ctx, req)
if err != nil {
    if strings.Contains(err.Error(), "no response from API") {
        // retry once with backoff, or surface prompt/model issue to user
    }
    return err
}

When it happens

Trigger: len(chatResp.Choices) == 0 in callAPI — the API responded 200 with an empty choices array, e.g. the prompt was filtered, the model produced no content, or an error payload still returned HTTP 200 with choices omitted.

Common situations: Content-filtered prompts; a model name that returns an odd empty completion; API returning {"choices":[]} during partial outages; error responses that happen to parse but carry no choices.

Understand the failure class

Background: "empty response", "returned no data", "empty embeddings": what HTTP 200-with-empty-body errors mean across libraries — this error's family across 36 libraries.

Related errors

• no response from API
• no response from API
• ${rsp.Status}: ${body} (dynamic HTTP status and body)
• video completed but no outputs returned
• failed to parse response: %w

AI-assisted analysis of micro/go-micro@24529f1404 (2026-09-01). Data as JSON: /api/errors/1252893d042543ba. Report an issue: GitHub.