langgenius/dify · error · ProviderNotInitializeError

provider_not_initialize

provider_not_initialize

Error message

No valid model provider credentials found. Please go to Settings -> Model Provider to complete your provider credentials.

What it means

HTTP 400 (code=provider_not_initialize) raised in _get_message_suggested_questions (message.py:523) when generating suggested questions throws ProviderTokenNotInitError. Suggested-questions generation calls an LLM, so the tenant must have at least one provider configured; with none, it fails. Catch maps to ProviderNotInitializeError.

Source

Thrown at api/controllers/console/app/message.py:523

def _get_message_suggested_questions(*, session: Session, current_user: Account, app_model: App, message_id: UUID):
    message_id_str = str(message_id)

    try:
        questions = MessageService.get_suggested_questions_after_answer(
            app_model=app_model,
            message_id=message_id_str,
            user=current_user,
            invoke_from=InvokeFrom.DEBUGGER,
            session=session,
        )
    except MessageNotExistsError:
        raise NotFound("Message not found")
    except ConversationNotExistsError:
        raise NotFound("Conversation not found")
    except ProviderTokenNotInitError as ex:
        raise ProviderNotInitializeError(ex.description)
    except QuotaExceededError:
        raise ProviderQuotaExceededError()
    except ModelCurrentlyNotSupportError:
        raise ProviderModelCurrentlyNotSupportError()
    except InvokeError as e:
        raise CompletionRequestError(e.description)
    except SuggestedQuestionsAfterAnswerDisabledError:
        raise AppSuggestedQuestionsAfterAnswerDisabledError()
    except Exception:
        logger.exception("internal server error.")
        raise InternalServerError()

    return dump_response(SuggestedQuestionsResponse, {"data": questions})


def _get_message_detail(*, session: Session, app_model: App, message_id: UUID):
    message_id_str = str(message_id)

View on GitHub (pinned to ef8544b173)

Solutions

1. Configure at least one model provider under Settings -> Model Provider.
2. Disable the 'suggested questions after answer' app feature until a provider is configured.
3. Verify the default tenant model resolves to a configured provider before enabling the feature.

async function ensureProviderReady() {
  const res = await fetch('/console/api/workspaces/current/model-providers');
  const data = await res.json();
  const ok = data.data.some(p => p.is_valid);
  if (!ok) throw new Error('configure a provider first');
}
await ensureProviderReady();

try {
  await getSuggestedQuestions(appId, msgId);
} catch (e) {
  if (e.code === 'provider_not_initialize') {
    // route to Settings -> Model Provider; optionally disable feature
  } else throw e;
}

When it happens

Trigger: GET /console/api/apps/<app_id>/message/<message_id>/suggested-questions on a workspace with no model provider credentials configured.

Common situations: New self-hosted install that never set up a provider; tenant removed all provider configs; suggested-questions-after-answer enabled in app settings without configuring a provider.

Related errors

• provider_quota_exceeded
• model_currently_not_support
• provider_not_initialize
• NotLoggedIn
• completion_request_error

AI-assisted analysis of langgenius/dify@ef8544b173 (2026-08-12). Data as JSON: /api/errors/216d5fbe401f2e9a. Report an issue: GitHub.