fix(inference): fail-fast on empty model for cloud providers, demote nvidia-nim Sentry noise (#2811)

Co-authored-by: Taimoor <astikkosapparel009@gmail.com>

src/openhuman/inference/provider/config_rejection.rs

@@ -171,17 +171,44 @@ pub fn is_provider_config_rejection_message(body: &str) -> bool {
         // this is the `type` field used by litellm/Anthropic-style
         // envelopes for the same class of user-state error.
         "not_found_error",
-        // TAURI-RUST-4K7 — Ollama models that don't support tool calling
-        // (e.g. gemma3:1b-it-qat, huihui_ai/deepseek-r1-abliterated:8b)
-        // return HTTP 400 with one of these phrases. The compatible
-        // provider (`compatible.rs`) detects the error and retries
-        // without tools, so the 400 is expected capability-discovery
-        // rather than a product bug. Suppress Sentry to avoid noise from
-        // the first-attempt rejection that precedes the successful retry.
+        // TAURI-RUST-4NM — nvidia-nim (and some other providers) return
+        // `{"error":{"message":"model field is required","type":"invalid_request_error","code":"missing_required_field"}}`
+        // when the `model` key is absent or empty in the request body.
+        // This is a user-configuration error (provider string has no model
+        // component, e.g. `nvidia-nim:` with empty model), not a product
+        // regression. Demote from Sentry; the factory now validates this
+        // up-front so in practice this phrase should no longer appear.
+        "model field is required",
+        // TAURI-RUST-4XK — Ollama 403 when the requested model requires a
+        // paid Ollama subscription. Body carries the upgrade URL. User must
+        // switch to a free model or upgrade their Ollama account.
+        "requires a subscription",
+        // TAURI-RUST-2G / TAURI-RUST-2F — DeepSeek / compatible providers
+        // that use extended thinking reject tool-call turns when the
+        // `reasoning_content` block from a prior assistant turn is not
+        // threaded back. This is user-config state (model requires the
+        // caller to replay the thinking block; the frontend replay logic in
+        // `turn.rs` handles it for subsequent turns, so the first-turn 400
+        // is expected capability-discovery, not a regression).
+        "in the thinking mode must be passed back",
+        // TAURI-RUST-35 / TAURI-RUST-4K7 / TAURI-RUST-4Z0 — Ollama models
+        // (e.g. gemma3, phi3, deepseek-r1) that do not support function
+        // calling return HTTP 400 with this phrase. The compatible provider
+        // retries without tools on 400, so the initial rejection is expected
+        // capability-discovery. Sentry noise suppressed here.
         "does not support tools",
+        // TAURI-RUST-4K7-d — alternative phrasing used by some Ollama model
+        // versions for the same tool-unsupported condition.
         "function calling is not supported",
+        // TAURI-RUST-4K7-e — litellm / OpenAI-compatible proxies reject the
+        // `tools` key in the request body when the backing model does not
+        // support tool use (e.g. local Ollama via LiteLLM gateway).
         "unknown parameter: tools",
+        // TAURI-RUST-4K7-f — Ollama native API surface rejects the field
+        // outright when the model has no function-calling capability.
         "unrecognized field `tools`",
+        // TAURI-RUST-4K7-g — another litellm / proxy variant of the same
+        // tool-unsupported condition.
         "unsupported parameter: tools",
         // TAURI-RUST-4NM — nvidia-nim (and compatible providers) return
         // `{"error":{"message":"model field is required","code":"missing_required_field"}}`
@@ -565,6 +592,21 @@ mod tests {
         }
     }
 
+    #[test]
+    fn detects_nvidia_nim_missing_model_body() {
+        // TAURI-RUST-4NM — nvidia-nim rejects requests with model="" with
+        // `{"error":{"message":"model field is required",...}}`.
+        let body = r#"nvidia-nim API error (400 Bad Request): {"error":{"message":"model field is required","type":"invalid_request_error","code":"missing_required_field"}}"#;
+        assert!(
+            is_provider_config_rejection_message(body),
+            "TAURI-RUST-4NM body must classify as provider config-rejection: {body:?}"
+        );
+        // Also verify the bare phrase on its own (defense-in-depth path).
+        assert!(is_provider_config_rejection_message(
+            "model field is required"
+        ));
+    }
+
     #[test]
     fn unknown_model_helper_rejects_other_config_rejection_phrases() {
         // Polarity exception must stay narrow: other config-rejection

src/openhuman/inference/provider/factory.rs

@@ -788,7 +788,7 @@ fn make_cloud_provider_by_slug(
             slug,
         );
         anyhow::bail!(
-            "[chat-factory] role '{}' resolved to an empty model id for slug '{}'. \
+            "[chat-factory] no model configured: role '{}' resolved to an empty model id for slug '{}'. \
              Include a model in the provider string (e.g. '{slug}:<model-id>') or \
              set default_model on the cloud_providers entry for slug '{slug}'.",
             role,

src/openhuman/inference/provider/factory_test.rs

@@ -369,6 +369,57 @@ fn empty_model_in_ollama_rejected() {
     assert!(err.to_string().contains("empty model"), "{err}");
 }
 
+#[test]
+fn cloud_provider_with_no_model_and_no_default_rejected() {
+    // TAURI-RUST-4NM — nvidia-nim (and others) reject `model=""` with
+    // "model field is required". The factory must catch this up-front with
+    // a clear, actionable message instead of leaking an empty model to the API.
+    let mut config = Config::default();
+    config.cloud_providers.push(CloudProviderCreds {
+        id: "p_nim".to_string(),
+        slug: "nvidia-nim".to_string(),
+        label: "NVIDIA NIM".to_string(),
+        endpoint: "https://integrate.api.nvidia.com/v1".to_string(),
+        auth_style: AuthStyle::Bearer,
+        default_model: None, // no fallback model configured
+        ..Default::default()
+    });
+
+    let err = match create_chat_provider_from_string("reasoning", "nvidia-nim:", &config) {
+        Ok(_) => panic!("empty model must fail"),
+        Err(e) => e,
+    };
+    let msg = err.to_string();
+    assert!(
+        msg.contains("no model configured"),
+        "expected 'no model configured' in error, got: {msg}"
+    );
+    assert!(
+        msg.contains("nvidia-nim"),
+        "error must name the slug; got: {msg}"
+    );
+}
+
+#[test]
+fn cloud_provider_default_model_used_when_model_part_is_empty() {
+    // When provider string is "nvidia-nim:" (empty model) but the entry
+    // has a default_model, the factory must use the default — not error.
+    let mut config = Config::default();
+    config.cloud_providers.push(CloudProviderCreds {
+        id: "p_nim".to_string(),
+        slug: "nvidia-nim".to_string(),
+        label: "NVIDIA NIM".to_string(),
+        endpoint: "https://integrate.api.nvidia.com/v1".to_string(),
+        auth_style: AuthStyle::Bearer,
+        default_model: Some("meta/llama-3.1-8b-instruct".to_string()),
+        ..Default::default()
+    });
+
+    let (_, model) = create_chat_provider_from_string("reasoning", "nvidia-nim:", &config)
+        .expect("empty model with default_model must succeed");
+    assert_eq!(model, "meta/llama-3.1-8b-instruct");
+}
+
 #[test]
 fn missing_slug_for_openai_gives_clear_error() {
     let config = Config::default();