Mintplex-Labs/anything-llm · critical · Error

LMStudio must have a valid model set.

Error message

LMStudio must have a valid model set.

What it means

LMStudioProvider's constructor (lmstudio.js:21-27) requires a model id from either config.model or the LMSTUDIO_MODEL_PREF environment variable and throws this if neither is set. LM Studio is a local OpenAI-compatible server, so the agent must be told which loaded model to target.

Source

Thrown at server/utils/agents/aibitat/providers/lmstudio.js:27

  parseLMStudioBasePath,
} = require("../../../AiProviders/lmStudio/index.js");

/**
 * The agent provider for the LMStudio.
 * Supports true OpenAI-compatible tool calling when the model supports it,
 * falling back to the UnTooled prompt-based approach otherwise.
 */
class LMStudioProvider extends InheritMultiple([Provider, UnTooled]) {
  model;

  /**
   * @param {{model?: string}} config
   */
  constructor(config = {}) {
    super();
    this.providerTag = "lmstudio";
    const model = config?.model || process.env.LMSTUDIO_MODEL_PREF;
    if (!model) throw new Error("LMStudio must have a valid model set.");

    const apiKey = process.env.LMSTUDIO_AUTH_TOKEN ?? null;
    const client = new OpenAI({
      baseURL: parseLMStudioBasePath(process.env.LMSTUDIO_BASE_PATH),
      apiKey,
    });

    this._client = client;
    this.model = model;
    this.verbose = true;
    this._supportsToolCalling = null;
  }

  get client() {
    return this._client;
  }

  get supportsAgentStreaming() {

View on GitHub (pinned to 526360e320)

Solutions

1. Set LMSTUDIO_MODEL_PREF in .env to a model loaded in LM Studio (exact id).
2. Or pass { model: "<id>" } in the provider config at construction time.
3. Start the LM Studio local server and load the target model before sending requests.
4. Confirm LMSTUDIO_BASE_PATH points at the running server.

Example fix

// before (env missing)
// LMSTUDIO_MODEL_PREF=
const p = new LMStudioProvider();

// after (.env)
// LMSTUDIO_MODEL_PREF=meta-llama/Meta-Llama-3-8B-Instruct
const p = new LMStudioProvider();

// Resolve the model BEFORE constructing the provider.
const model = config?.model || process.env.LMSTUDIO_MODEL_PREF;
if (!model)
  throw new Error(
    "Set LMSTUDIO_MODEL_PREF (or pass config.model) before creating LMStudioProvider."
  );

/** @param {unknown} v @returns {v is string} */
function isNonEmptyString(v) {
  return typeof v === "string" && v.trim().length > 0;
}

try {
  return new LMStudioProvider(config);
} catch (e) {
  if (/valid model set/.test(e.message)) {
    // prompt the user for a model id, then retry construction
    throw new Error("Please choose an LM Studio model before starting the agent.");
  }
  throw e;
}

When it happens

Trigger: Instantiating LMStudioProvider with an empty/undefined config.model while LMSTUDIO_MODEL_PREF is unset, or starting the server with a .env that is missing that variable.

Common situations: Fresh install where the model preference was never set, an env-var rename/removal, or the model id in LMSTUDIO_MODEL_PREF not matching a model loaded in the LM Studio GUI.

Related errors

• OMLX must have a valid model set.
• LMStudio base path must be provided to use agents.
• GenericOpenAI must have a valid base path to use for the api
• No Lemonade API Base Path was set.
• No embedding base path was set.

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/0141f34d773089cb. Report an issue: GitHub.