What causes "scan: main_task.messages must not be empty" in alibaba/open-code-review?

Add at least one message (role + content) under main_task.messages in the template

scan: main_task.messages must not be empty

Error message

scan: main_task.messages must not be empty

What it means

ScanTemplate.Validate rejects a template whose MainTask.Messages slice is empty. The main task conversation must contain at least one message (typically the system/user prompt driving the scan); an empty list means the LLM would be invoked with nothing to do. Validation fails fast before any request is made.

Source

Thrown at internal/config/template/template.go:337

	if t.MaxReviewRounds < 0 {
		return fmt.Errorf("max_review_rounds must not be negative")
	}
	if len(t.MainTask.Messages) == 0 {
		return fmt.Errorf("main_task.messages must not be empty")
	}
	return nil
}

// Validate checks that a ScanTemplate has the minimum fields populated.
func (t *ScanTemplate) Validate() error {
	if t.MaxTokens <= 0 {
		return fmt.Errorf("scan: max_tokens must be positive")
	}
	if t.MaxToolRequestTimes <= 0 {
		return fmt.Errorf("scan: max_tool_request_times must be positive")
	}
	if len(t.MainTask.Messages) == 0 {
		return fmt.Errorf("scan: main_task.messages must not be empty")
	}
	return nil
}

// LlmConversation is a preset prompt with settings.
type LlmConversation struct {
	Messages []ChatMessage `json:"messages"`
}

// ChatMessage represents a single message in a conversation.
type ChatMessage struct {
	Role    string `json:"role"`
	Content string `json:"content"`
}

View on GitHub (pinned to 5cf97d0d15)

Solutions

Add at least one message (role + content) under main_task.messages in the template
Check the template file for a misspelled or misplaced messages key so it actually unmarshals
Copy a known-good template and adapt the prompt instead of starting from an empty struct

Example fix

// before
MainTask: LlmTask{ Settings: settings } // no messages
// after
MainTask: LlmTask{ Settings: settings, Messages: []Message{{Role: "user", Content: scanPrompt}} }

Defensive patterns

Strategy: validation

Validate before calling

func hasMessages(t template.ScanTemplate) bool { return len(t.MainTask.Messages) > 0 }

Try / catch

if err := t.Validate(); err != nil { return fmt.Errorf("invalid scan template: %w", err) }

Prevention

Never commit template files with empty main_task.messages
Add a CI check that validates every shipped template with Validate()
Start from a known-good template when authoring new prompts

When it happens

Trigger: Calling Validate() on a ScanTemplate where MainTask is the zero value or where the messages array in the config file is empty ([]) or absent.

Common situations: Template files with main_task section omitted entirely; a prompt refactoring that emptied the messages list; deserializing a template where the messages key is misspelled so nothing is populated.

Understand the failure class

Background: "Invalid value" and "allowed values are" config errors: what your library rejected and how to fix it — this error's family across 41 libraries.

Related errors

AI-assisted analysis of alibaba/open-code-review@5cf97d0d15 (2026-09-02). Data as JSON: /api/errors/8db6af7bd53eea4e. Report an issue: GitHub.