linshenkx/prompt-optimizer · error · Error

Unable to build model ${configForm.value.modelId}: ${error i

Error message

Unable to build model ${configForm.value.modelId}: ${error instanceof Error ? error.message : String(error)}

What it means

While testing a connection, useImageModelManager needs a model instance. When the model ID isn't in the registry cache it falls back to adapter.buildDefaultModel(modelId); if that builder throws (unknown model ID, malformed ID, adapter limits), the error is rethrown wrapped with context about which model failed.

Source

Thrown at packages/ui/src/composables/model/useImageModelManager.ts:436

        const parts: string[] = []
        if (detail.missing.length) parts.push(t('image.connection.validation.missing', { fields: detail.missing.join(', ') }))
        if (detail.typeErrors.length) {
          parts.push(detail.typeErrors.map(e => t('image.connection.validation.invalidType', e)).join('; '))
        }
        connectionStatus.value = { type: 'error', messageKey: 'image.connection.testFailed', detail: parts.join('; ') }
        toast.error(parts.join('; '))
        return
      }

      // 获取选中的模型信息：优先使用缓存，不存在时通过registry构建
      let selectedModel = models.value.find(m => m.id === configForm.value.modelId)
      if (!selectedModel) {
        // 对于自定义模型ID，使用adapter的buildDefaultModel方法构建
        try {
          const adapter = registry.getAdapter(selectedProviderId.value)
          selectedModel = adapter.buildDefaultModel(configForm.value.modelId)
        } catch (error) {
          throw new Error(
            `Unable to build model ${configForm.value.modelId}: ${error instanceof Error ? error.message : String(error)}`,
            { cause: error }
          )
        }
      }

      // 根据模型能力确定测试类型
      const testType = selectTestType(selectedModel)

      // 构建完整的模型配置
      const completeConfig: ImageModelConfig = {
        id: configForm.value.id || 'test',
        name: configForm.value.name || 'Test Config',
        providerId: selectedProviderId.value,
        modelId: configForm.value.modelId,
        enabled: true,
        connectionConfig: configForm.value.connectionConfig || {},
        paramOverrides: configForm.value.paramOverrides || {},

View on GitHub (pinned to 3e677b1d9f)

Solutions

1. Check the model ID against the provider's model list and correct typos before testing.
2. Update the adapter (or the package) to a version that recognizes the model ID.
3. If the model should be buildable, inspect the cause in the wrapped error's { cause } to see the underlying builder failure.

Example fix

// before
adapter.buildDefaultModel('flux--pro') // throws

// after
adapter.buildDefaultModel('flux-pro') // verify ID against provider docs/model list

const ids = adapter.listModels?.() ?? []
if (!ids.includes(configForm.value.modelId)) { /* warn before test */ }

try { await testConnection() } catch (e) { if (e instanceof Error && e.message.startsWith('Unable to build model')) { console.error(e.cause); showModelIdError(e.message); return } throw e }

When it happens

Trigger: Entering a custom model ID in the image provider config and clicking 'Test Connection' when the provider's adapter cannot construct a default model for that ID — e.g. ID doesn't match any known model pattern or the adapter requires extra parameters.

Common situations: Typos in custom model IDs; using a model name from a newer API version than the adapter supports; provider-specific naming conventions (dashes vs dots) not honored.

Related errors

• Unable to build model ${selectedModelId.value}: ${error inst
• Image understanding service is not available for multimodal
• Image storage service is required to resolve evaluation imag
• Model metadata cannot be empty
• Model provider metadata cannot be empty

AI-assisted analysis of linshenkx/prompt-optimizer@3e677b1d9f (2026-08-27). Data as JSON: /api/errors/50745bb12c214605. Report an issue: GitHub.