linshenkx/prompt-optimizer · error · Error

Missing prompt.format

Error message

Missing prompt.format

What it means

The prompt body object (data.prompt) must carry a `format` field that is exactly 'text' or 'messages'. Anything else — including a missing format, null, or a value like 'markdown' — throws this error before content parsing begins.

Source

Thrown at packages/ui/src/composables/app/useAppPromptGardenImport.ts:550

    if (data.schemaVersion !== 1) {
      throw new Error('Unsupported Garden response schemaVersion')
    }

    const optimizerTarget = isPlainObject(data.optimizerTarget) ? data.optimizerTarget : null
    const optimizerTargetKey =
      optimizerTarget && typeof optimizerTarget.subModeKey === 'string'
        ? optimizerTarget.subModeKey.trim()
        : ''
    if (!optimizerTargetKey) {
      throw new Error('Missing optimizerTarget.subModeKey')
    }

    const prompt = isPlainObject(data.prompt) ? data.prompt : null
    const format = prompt && (prompt.format === 'text' || prompt.format === 'messages')
      ? (prompt.format as 'text' | 'messages')
      : null
    if (!format) {
      throw new Error('Missing prompt.format')
    }

    let promptText: string | undefined
    let promptMessages: ConversationMessage[] | undefined
    if (format === 'text') {
      const t = prompt && typeof prompt.text === 'string' ? prompt.text : ''
      if (!t.trim()) {
        throw new Error('Empty prompt.text')
      }
      promptText = t
    } else {
      const msgs = normalizeImportedConversationMessages(prompt?.messages)
      if (!msgs.length) {
        throw new Error('Empty prompt.messages')
      }
      promptMessages = msgs
    }

View on GitHub (pinned to 3e677b1d9f)

Solutions

1. Set prompt.format to exactly 'text' (plain string content) or 'messages' (conversation array)
2. Check for case sensitivity and trailing whitespace in the value
3. If upstream renamed formats, add a mapping in parseV1 or re-export

Example fix

// before
{ "prompt": { "format": "markdown", "text": "hi" } }

// after
{ "prompt": { "format": "text", "text": "hi" } }

const fmt = raw?.prompt?.format
if (fmt !== 'text' && fmt !== 'messages') { /* reject before import */ }

const isPromptFormat = (v: unknown): v is 'text' | 'messages' => v === 'text' || v === 'messages'

catch (e) { if (e.message === 'Missing prompt.format') showImportError('Unsupported prompt format'); else throw e }

When it happens

Trigger: data.prompt is null/not an object, prompt.format is undefined, or prompt.format is a string other than 'text'/'messages' (case-sensitive).

Common situations: New export format names upstream (e.g. 'chat', 'markdown'); truncated payloads; case mismatches like 'Text'; hand-edited JSON where format was deleted.

Understand the failure class

Background: Schema validation failed / invalid input schema: payload rejected because its shape doesn't match the expected schema — this error's family across 28 libraries.

Related errors

• Missing optimizerTarget.subModeKey
• Empty prompt.text
• Empty prompt.messages
• Missing variables
• CONTEXT_ERROR_CODES.STORAGE_ERROR

AI-assisted analysis of linshenkx/prompt-optimizer@3e677b1d9f (2026-08-27). Data as JSON: /api/errors/4d06bd331cc5016b. Report an issue: GitHub.