Invalid configured model

Error message

Invalid configured model '{model}' for provider '{}': expected auto or a model ID this provider serves{hint}.

What it means

The config validator checks the configured model against the model ID namespace of the *active* provider via `model_completion_names_for_provider(provider)`. Only `auto` or a model ID that provider actually serves is accepted; anything else is rejected with a hint listing example valid IDs.

Solutions

Set `model = "auto"` in the config to let the provider resolver pick the model.
Pick a model ID from the hint list in the error message (examples come from `model_completion_names_for_provider` for your active provider).
If you switched providers, also update `api_provider` so the model is validated against the intended namespace.
Verify the model ID is one the provider currently serves (provider may have deprecated it).

Example fix

// before (config.toml)
model = "gpt-4o"   # active provider is openrouter

// after
model = "auto"
# or
model = "openai/gpt-4o"

Defensive patterns

Strategy: validation

Validate before calling

use codewhale::tui::config::model_completion_names_for_provider;
let known = model_completion_names_for_provider(provider);
let ok = model == "auto" || known.iter().any(|m| *m == model);
assert!(ok, "model '{model}' not served by {}; valid: {known:?}", provider.as_str());

Prevention

Use `model = "auto"` unless you specifically need a pinned model.
After switching providers, always update the model ID in the same edit.
Pick model IDs from the completion list the CLI offers, not from memory or other tools.

When it happens

Trigger: `Config::validate` runs and the configured `model` value is neither the literal `auto` nor one of the completion names returned by `model_completion_names_for_provider` for the currently selected provider.

Common situations: Switching providers (e.g. from DeepSeek to OpenRouter) but keeping the old provider's model ID; typos in the model string; using a model name that the provider retired or never served; copying a model ID from another tool's config.

Understand the failure class

Background: "Invalid value" and "allowed values are" config errors: what your library rejected and how to fix it — this error's family across 41 libraries.

Related errors

AI-assisted analysis of Hmbown/CodeWhale@73e0f67d83 (2026-09-22). Data as JSON: /api/errors/99a9eac356b327c3. Report an issue: GitHub.

Appendix: source

Thrown at crates/tui/src/config.rs:5155

            && !self.active_provider_preserves_custom_base_url_model()
            && crate::provider_lake::configured_model_for_route(
                self,
                active_provider,
                &self.provider_identity_for(active_provider),
                &self.base_url_for_route(active_provider),
                model,
            )
            .is_none()
            && canonical_model_id_for_provider(self.api_provider(), model).is_none()
        {
            let provider = self.api_provider();
            let known = model_completion_names_for_provider(provider);
            let hint = if known.is_empty() {
                String::new()
            } else {
                format!(" (for example: {})", known.join(", "))
            };
            anyhow::bail!(
                "Invalid configured model '{model}' for provider '{}': expected auto or a model ID this provider serves{hint}.",
                provider.as_str()
            );
        }
        if let Some(policy) = self.approval_policy.as_deref() {
            let normalized = policy.trim().to_ascii_lowercase();
            if !matches!(
                normalized.as_str(),
                "on-request" | "untrusted" | "never" | "auto" | "suggest"
            ) {
                anyhow::bail!(
                    "Invalid approval_policy '{policy}': expected on-request, untrusted, never, auto, or suggest."
                );
            }
        }
        if let Some(v) = self.verbosity.as_deref() {
            let normalized = v.trim().to_ascii_lowercase();
            if !matches!(normalized.as_str(), "normal" | "concise") {

View on GitHub (pinned to 73e0f67d83)