tinyhumansai/openhuman · error

Your local inference server (e.g. LM Studio) is running but

Error message

Your local inference server (e.g. LM Studio) is running but has no model loaded. Load a model — in LM Studio use the developer page or the `lms load` command — then try again.

What it means

Error "Your local inference server (e.g. LM Studio) is running but has no model loaded. Load a model — in LM Studio use the developer page or the `lms load` command — then try again." thrown in tinyhumansai/openhuman.

Source

Thrown at src/openhuman/inference/provider/ops/http_error.rs:1136

            "llm_provider",
            "api_error",
            &[
                ("provider", provider),
                ("status", status_str.as_str()),
                ("failure", "non_2xx"),
            ],
        );
    }
    // Replace the opaque `Internal Server Error (ref: <uuid>)` body with
    // actionable guidance; the prefix anchors the higher-layer re-report
    // demotion (`is_ollama_cloud_internal_500_message`).
    if is_ollama_cloud_internal_500 {
        return anyhow::anyhow!(ollama_cloud_internal_500_user_message(None, status));
    }
    // Replace the raw `No models loaded` body with actionable guidance so the
    // surfaced chat error tells the user how to recover (TAURI-RUST-DMQ).
    if is_local_provider_no_model_loaded {
        return anyhow::anyhow!(local_provider_no_model_loaded_user_message());
    }
    anyhow::anyhow!(message)
}

#[cfg(test)]
mod tests {
    use super::*;
    use reqwest::StatusCode;

    /// Verbatim TAURI-RUST-DMQ LM Studio body — the local server is running but
    /// has no model loaded. The matcher keys on this prose, so coupling the test
    /// to the exact string makes a wording drift fail CI rather than silently
    /// leak events back to Sentry.
    const DMQ_BODY: &str = "lm_studio API error (400 Bad Request): {\"error\":\
        {\"message\":\"No models loaded. Please load a model in the developer page \
        or via `lms load`.\",\"type\":\"invalid_request_error\",\"param\":\"model\"}}";

    #[test]

View on GitHub (pinned to 7491200858)

Solutions

1. Load a model in the local server — in LM Studio use the developer page or run `lms load <model>`
2. Verify the local server's base URL points at the intended instance
3. Confirm the loaded model name matches what the provider string requests

When it happens

Trigger: Thrown at src/openhuman/inference/provider/ops/http_error.rs:1136 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of tinyhumansai/openhuman@7491200858 (2026-08-17). Data as JSON: /api/errors/fcee3157a10349d0. Report an issue: GitHub.