Assistants. "Something went wrong. Here's the specific error message we encountered: Illegal model request"

[marcoantonio123456]

What happened?

When a user tries to use an Assistant, any assistant they are met with

"Something went wrong. Here's the specific error message we encountered: Illegal model request"

They will get banned if they try to send messages

Steps to Reproduce

Not 100% sure where this issue started but it was not until I updated Librechat that I am unable to use any of my assistants

What browsers are you seeing the problem on?

No response

Relevant log output

no logging available

Screenshots

Code of Conduct

• I agree to follow this project's Code of Conduct

[danny-avila]

This only happens when the model for the assistant is not "available" in your list of models. This is a security feature to prevent users from using models you have not explicitly or implicitly allowed.

Do you have ASSISTANTS_MODELS set in your .env file? Or is the list of models being fetched from OpenAI?

You can also prevent the behavior of users being banned by setting the following environment variable:

ILLEGAL_MODEL_REQ_SCORE=0

[danny-avila]

Also logs would be helpful to view, those relevant to the issue. In particular, form project root, the debug logs are most relevant and can be found here: logs/debug-currentdate.log

[nicolaslevy]

Same for me, yesterday it was working but today I don't understand why it's failing
In my case I have the models being fetched form OpenAI

Thits is the error.log:
{"level":"error","message":"[/assistants/chat/] Missing thread_id for existing conversation","stack":"Error: Missing thread_id for existing conversation\n at /app/api/server/routes/assistants/chat.js:271:13\n at Layer.handle [as handle_request] (/app/api/node_modules/express/lib/router/layer.js:95:5)\n at next (/app/api/node_modules/express/lib/router/route.js:149:13)\n at setHeaders (/app/api/server/middleware/setHeaders.js:9:3)\n at Layer.handle [as handle_request] (/app/api/node_modules/express/lib/router/layer.js:95:5)\n at next (/app/api/node_modules/express/lib/router/route.js:149:13)\n at buildEndpointOption (/app/api/server/middleware/buildEndpointOption.js:64:3)\n at process.processTicksAndRejections (node:internal/process/task_queues:95:5)"}

This is the debug:
2024-05-03T14:04:56.721Z debug: [/assistants/chat/] req.body
{
text: "testing assistant 2",
sender: "User",
isCreatedByUser: true,
parentMessageId: "70000fef-5339-4d7b-9e04-b30bf24575fb_",
conversationId: "c547d791-0d44-487a-848f-747d29869170",
messageId: "058922b5-5224-48b4-9e0f-e5ebb6f5c2d8",
error: false,
generation: "Illegal model request",
responseMessageId: "70000fef-5339-4d7b-9e04-b30bf24575fb_",
model: "gpt-3.5-turbo-0125",
assistant_id: "asst_MHCSO8doINrVEHWtEiALqJIF",
endpoint: "assistants",
isContinued: false,
endpointOption.endpoint: "assistants",
endpointOption.promptPrefix: null,
endpointOption.assistant_id: "asst_MHCSO8doINrVEHWtEiALqJIF",
endpointOption.iconURL: undefined,
endpointOption.greeting: undefined,
endpointOption.spec: undefined,
modelOptions.model: "gpt-3.5-turbo-0125",
modelOptions.instructions: undefined,
// 1 openAI(s)
modelsConfig.openAI: ["gpt-4-turbo"],
// 12 google(s)
modelsConfig.google: ["gemini-pro","gemini-pro-vision","chat-bison","chat-bison-32k","codechat-bison","codechat-bison-32k","text-bison","text-bison-32k","text-unicorn","code-gecko","code-bison","code-bison-32k"],
// 10 anthropic(s)
modelsConfig.anthropic: ["claude-3-opus-20240229","claude-3-sonnet-20240229","claude-3-haiku-20240307","claude-2.1","claude-2","claude-1.2","claude-1","claude-1-100k","claude-instant-1","claude-instant-1-100k"],
// 18 gptPlugin(s)
modelsConfig.gptPlugins: ["gpt-3.5-turbo-1106","gpt-3.5-turbo-16k","gpt-4-turbo","gpt-4","gpt-4-turbo-2024-04-09","gpt-4-0613","gpt-4-vision-preview","gpt-3.5-turbo","gpt-4-1106-vision-preview","gpt-3.5-turbo-0125","gpt-4-0125-preview","gpt-3.5-turbo-0301","gpt-4-turbo-preview","gpt-4-1106-preview","gpt-3.5-turbo-0613","gpt-3.5-turbo-16k-0613","gpt-3.5-turbo-instruct-0914","gpt-3.5-turbo-instruct"],
// 17 azureOpenAI(s)
modelsConfig.azureOpenAI: ["gpt-3.5-turbo-0125","gpt-3.5-turbo-16k-0613","gpt-3.5-turbo-16k","gpt-4-turbo-preview","gpt-4-0125-preview","gpt-4-1106-preview","gpt-3.5-turbo","gpt-3.5-turbo-1106","gpt-4-vision-preview","gpt-4","gpt-3.5-turbo-instruct-0914","gpt-3.5-turbo-0613","gpt-3.5-turbo-0301","gpt-3.5-turbo-instruct","gpt-4-0613","text-davinci-003","gpt-4-0314"],
// 2 bingAI(s)
modelsConfig.bingAI: ["BingAI","Sydney"],
// 2 chatGPTBrowser(s)
modelsConfig.chatGPTBrowser: ["text-davinci-002-render-sha","gpt-4"],
// 13 assistant(s)
modelsConfig.assistants: ["gpt-3.5-turbo-0125","gpt-4-0125-preview","gpt-4-turbo-preview","gpt-4-1106-preview","gpt-3.5-turbo-1106","gpt-3.5-turbo-16k-0613","gpt-3.5-turbo-16k","gpt-3.5-turbo","gpt-4","gpt-4-0314","gpt-4-32k-0314","gpt-4-0613","gpt-3.5-turbo-0613"],
}
2024-05-03T14:04:56.723Z error: [/assistants/chat/] Missing thread_id for existing conversation

[nicolaslevy]

Update: I tried to set ASSISTANTS_MODELS=gpt-4-turbo and now it's working

[danny-avila]

great, I think I know what's going on now, with the assistants model list not fetching as expected and the default values not including the latest models.

[danny-avila]

Some changes here should prevent the issue highlighted in this discussion: #2611