moeru-ai/airi · error · Error

Vision provider/model not configured

Error message

Vision provider/model not configured

What it means

runVisionInference throws this pre-flight check before any provider instance is created: the vision store must have both activeProvider and activeModel set. It is a configuration error, not a network one — image inference cannot run until a vision provider and model have been selected in settings.

Solutions

1. Open vision settings and select a provider and a model, then retry
2. If invoking programmatically, seed visionStore activeProvider and activeModel before running
3. Guard the call site so the UI routes to settings instead of surfacing a raw error
4. Re-select the vision provider after any settings reset

Example fix

// before
await runVisionInference({ workloadId, imageDataUrl }) // throws: not configured

// after
if (!visionStore.activeProvider || !visionStore.activeModel) {
  openSettingsPage('vision')
  return
}
await runVisionInference({ workloadId, imageDataUrl })

const ready = Boolean(visionStore.activeProvider && visionStore.activeModel)
if (!ready)
  openSettingsPage('vision')

try {
  await runVisionInference(input)
}
catch (err) {
  if (err instanceof Error && err.message === 'Vision provider/model not configured')
    openSettingsPage('vision')
}

When it happens

Trigger: Fresh install where vision settings were never configured; after resetSettingsState() cleared the persisted stores; calling runVisionInference programmatically (devtool, automation, or test) without seeding the store first.

Common situations: Onboarding not completed; user switched devices so settings storage is empty; a script or test invokes the composable without selecting a provider.

Related errors

• Failed to initialize speech provider
• Failed to initialize speech provider
• Failed to resolve chat provider
• Missing LLM configuration
• No active chat provider or model configured

AI-assisted analysis of moeru-ai/airi@438a067dde (2026-09-17). Data as JSON: /api/errors/a87567c8f7d905aa. Report an issue: GitHub.

Appendix: source

Thrown at packages/stage-ui/src/composables/vision/use-vision-inference.ts:47

  const base64 = meta?.includes('base64') ? data : btoa(data)
  return {
    mimeType,
    base64,
    url: `data:${mimeType};base64,${base64}`,
  }
}

export function useVisionInference() {
  const llmStore = useLLM()
  const providersStore = useProviderStore()
  const visionStore = useVisionStore()
  const { activeProvider, activeModel, ollamaThinkingEnabled } = storeToRefs(visionStore)

  const lastText = ref('')

  async function runVisionInference(input: VisionInferenceInput) {
    if (!activeProvider.value || !activeModel.value)
      throw new Error('Vision provider/model not configured')

    const provider = await providersStore.getChatProviderInstance(activeProvider.value)
    const workload = getVisionWorkload(input.workloadId)
    const prompt = input.promptOverride ?? workload.prompt
    const { url } = parseDataUrl(input.imageDataUrl)
    const visionProvider: GenerationProvider = activeProvider.value === 'vision-ollama'
      ? {
          generation(model) {
            const request = provider.generation(model)
            if (request.protocol !== 'chat-completions')
              return request
            return { ...request, config: { ...request.config, think: ollamaThinkingEnabled.value } }
          },
        }
      : provider

    const context: Conversation = { turns: [{
      id: 'vision-input',

View on GitHub (pinned to 438a067dde)