feat(llm): per-provider unsupported parameter filtering (#749, #728) (#809)

Add declarative `unsupported_params` field to provider definitions in
providers.json. Parameters listed are stripped from requests before
sending, preventing 400 errors from providers that reject them (e.g.
gpt-5 family and kimi-k2.5 rejecting custom temperature values).

- Add `unsupported_params` to ProviderDefinition and RegistryProviderConfig
- Propagate from registry through config resolution
- Generic strip helpers handle temperature, max_tokens, stop_sequences
- Apply filtering in RigAdapter and AnthropicOAuthProvider
- Mark openai and tinfoil providers as unsupporting temperature
- Update openai default model to gpt-5-mini

Co-authored-by: Claude Opus 4.6 <[email protected]>

providers.json

@@ -9,8 +9,9 @@
     "api_key_required": true,
     "base_url_env": "OPENAI_BASE_URL",
     "model_env": "OPENAI_MODEL",
-    "default_model": "gpt-4o",
+    "default_model": "gpt-5-mini",
     "description": "OpenAI GPT models (direct API)",
+    "unsupported_params": ["temperature"],
     "setup": {
       "kind": "api_key",
       "secret_name": "llm_openai_api_key",
@@ -86,6 +87,7 @@
     "model_env": "TINFOIL_MODEL",
     "default_model": "kimi-k2-5",
     "description": "Tinfoil private inference (hardware-attested TEE)",
+    "unsupported_params": ["temperature"],
     "setup": {
       "kind": "api_key",
       "secret_name": "llm_tinfoil_api_key",

src/config/llm.rs

@@ -209,6 +209,7 @@ impl LlmConfig {
             extra_headers_env,
             api_key_required,
             base_url_required,
+            unsupported_params,
         ) = if let Some(def) = def {
             (
                 def.id.as_str(),
@@ -221,6 +222,7 @@ impl LlmConfig {
                 def.extra_headers_env.as_deref(),
                 def.api_key_required,
                 def.base_url_required,
+                def.unsupported_params.clone(),
             )
         } else {
             // Absolute fallback: treat as generic openai_completions
@@ -235,6 +237,7 @@ impl LlmConfig {
                 Some("LLM_EXTRA_HEADERS"),
                 false,
                 true,
+                Vec::new(),
             )
         };
 
@@ -338,6 +341,7 @@ impl LlmConfig {
             extra_headers,
             oauth_token,
             cache_retention,
+            unsupported_params,
         })
     }
 }
@@ -624,6 +628,12 @@ mod tests {
         let provider = cfg.provider.expect("provider config should be present");
         assert_eq!(provider.base_url, "https://inference.tinfoil.sh/v1");
         assert_eq!(provider.model, "kimi-k2-5");
+        assert!(
+            provider
+                .unsupported_params
+                .contains(&"temperature".to_string()),
+            "tinfoil should propagate unsupported_params from registry"
+        );
     }
 
     #[test]

src/llm/anthropic_oauth.rs

@@ -6,6 +6,8 @@
 //!
 //! Pattern follows `nearai_chat.rs`: direct HTTP calls via `reqwest::Client`.
 
+use std::collections::HashSet;
+
 use async_trait::async_trait;
 use reqwest::Client;
 use rust_decimal::Decimal;
@@ -35,6 +37,8 @@ pub struct AnthropicOAuthProvider {
     model: String,
     base_url: Option<String>,
     active_model: std::sync::RwLock<String>,
+    /// Parameter names that this provider does not support.
+    unsupported_params: HashSet<String>,
 }
 
 impl AnthropicOAuthProvider {
@@ -61,15 +65,45 @@ impl AnthropicOAuthProvider {
             Some(config.base_url.clone())
         };
 
+        let unsupported_params: HashSet<String> =
+            config.unsupported_params.iter().cloned().collect();
+
         Ok(Self {
             client,
             token,
             model: config.model.clone(),
             base_url,
             active_model,
+            unsupported_params,
         })
     }
 
+    /// Strip unsupported fields from a `CompletionRequest` in place.
+    fn strip_unsupported_completion_params(&self, req: &mut CompletionRequest) {
+        if self.unsupported_params.is_empty() {
+            return;
+        }
+        if self.unsupported_params.contains("temperature") {
+            req.temperature = None;
+        }
+        if self.unsupported_params.contains("max_tokens") {
+            req.max_tokens = None;
+        }
+    }
+
+    /// Strip unsupported fields from a `ToolCompletionRequest` in place.
+    fn strip_unsupported_tool_params(&self, req: &mut ToolCompletionRequest) {
+        if self.unsupported_params.is_empty() {
+            return;
+        }
+        if self.unsupported_params.contains("temperature") {
+            req.temperature = None;
+        }
+        if self.unsupported_params.contains("max_tokens") {
+            req.max_tokens = None;
+        }
+    }
+
     fn api_url(&self) -> String {
         if let Some(ref base) = self.base_url {
             let base = base.trim_end_matches('/');
@@ -197,8 +231,9 @@ impl AnthropicOAuthProvider {
 
 #[async_trait]
 impl LlmProvider for AnthropicOAuthProvider {
-    async fn complete(&self, req: CompletionRequest) -> Result<CompletionResponse, LlmError> {
-        let model = req.model.unwrap_or_else(|| self.active_model_name());
+    async fn complete(&self, mut req: CompletionRequest) -> Result<CompletionResponse, LlmError> {
+        let model = req.model.take().unwrap_or_else(|| self.active_model_name());
+        self.strip_unsupported_completion_params(&mut req);
         let (system, messages) = convert_messages(req.messages);
 
         let request = AnthropicRequest {
@@ -233,9 +268,10 @@ impl LlmProvider for AnthropicOAuthProvider {
 
     async fn complete_with_tools(
         &self,
-        req: ToolCompletionRequest,
+        mut req: ToolCompletionRequest,
     ) -> Result<ToolCompletionResponse, LlmError> {
-        let model = req.model.unwrap_or_else(|| self.active_model_name());
+        let model = req.model.take().unwrap_or_else(|| self.active_model_name());
+        self.strip_unsupported_tool_params(&mut req);
         let (system, messages) = convert_messages(req.messages);
 
         let tools: Vec<AnthropicTool> = req

src/llm/config.rs

@@ -87,6 +87,10 @@ pub struct RegistryProviderConfig {
     pub oauth_token: Option<SecretString>,
     /// Prompt cache retention (Anthropic-specific).
     pub cache_retention: CacheRetention,
+    /// Parameter names that this provider does not support (e.g., `["temperature"]`).
+    /// Supported keys: `"temperature"`, `"max_tokens"`, `"stop_sequences"`.
+    /// Listed parameters are stripped from requests before sending to avoid 400 errors.
+    pub unsupported_params: Vec<String>,
 }
 
 /// Configuration for AWS Bedrock (native Converse API).

src/llm/mod.rs

@@ -228,7 +228,9 @@ fn create_openai_compat_from_registry(
         "Using OpenAI-compatible provider"
     );
 
-    Ok(Arc::new(RigAdapter::new(model, &config.model)))
+    let adapter = RigAdapter::new(model, &config.model)
+        .with_unsupported_params(config.unsupported_params.clone());
+    Ok(Arc::new(adapter))
 }
 
 fn create_anthropic_from_registry(
@@ -296,7 +298,9 @@ fn create_anthropic_from_registry(
     );
 
     Ok(Arc::new(
-        RigAdapter::new(model, &config.model).with_cache_retention(cache_retention),
+        RigAdapter::new(model, &config.model)
+            .with_cache_retention(cache_retention)
+            .with_unsupported_params(config.unsupported_params.clone()),
     ))
 }
 
@@ -324,7 +328,9 @@ fn create_ollama_from_registry(
         "Using Ollama provider"
     );
 
-    Ok(Arc::new(RigAdapter::new(model, &config.model)))
+    let adapter = RigAdapter::new(model, &config.model)
+        .with_unsupported_params(config.unsupported_params.clone());
+    Ok(Arc::new(adapter))
 }
 
 /// Create a cheap/fast LLM provider for lightweight tasks (heartbeat, routing, evaluation).

src/llm/registry.rs

@@ -152,6 +152,11 @@ pub struct ProviderDefinition {
     /// Setup wizard hints.
     #[serde(default)]
     pub setup: Option<SetupHint>,
+    /// Parameter names that this provider does not support (e.g., `["temperature"]`).
+    /// Supported keys: `"temperature"`, `"max_tokens"`, `"stop_sequences"`.
+    /// Listed parameters are stripped from requests before sending to avoid 400 errors.
+    #[serde(default)]
+    pub unsupported_params: Vec<String>,
 }
 
 /// Registry of known LLM providers.
@@ -378,6 +383,7 @@ mod tests {
             description: "Custom tinfoil".to_string(),
             extra_headers_env: None,
             setup: None,
+            unsupported_params: vec![],
         });
         let registry = ProviderRegistry::new(all);
         let tf = registry.find("tinfoil").expect("tinfoil should exist");
@@ -517,6 +523,7 @@ mod tests {
             description: "No setup".to_string(),
             extra_headers_env: None,
             setup: None, // no setup hint
+            unsupported_params: vec![],
         }];
 
         let registry = ProviderRegistry::new(providers.clone());
@@ -546,6 +553,7 @@ mod tests {
                 can_list_models: false,
                 models_filter: None,
             }),
+            unsupported_params: vec![],
         });
 
         let registry = ProviderRegistry::new(providers);
@@ -587,6 +595,7 @@ mod tests {
                     can_list_models: false,
                     models_filter: None,
                 }),
+                unsupported_params: vec![],
             },
             // User override removes setup
             ProviderDefinition {
@@ -603,6 +612,7 @@ mod tests {
                 description: "No setup now".to_string(),
                 extra_headers_env: None,
                 setup: None,
+                unsupported_params: vec![],
             },
         ];
 
@@ -640,6 +650,7 @@ mod tests {
                     display_name: "A".to_string(),
                     can_list_models: false,
                 }),
+                unsupported_params: vec![],
             },
             ProviderDefinition {
                 id: "bbb".to_string(),
@@ -658,6 +669,7 @@ mod tests {
                     display_name: "B".to_string(),
                     can_list_models: false,
                 }),
+                unsupported_params: vec![],
             },
             ProviderDefinition {
                 id: "ccc".to_string(),
@@ -676,6 +688,7 @@ mod tests {
                     display_name: "C".to_string(),
                     can_list_models: false,
                 }),
+                unsupported_params: vec![],
             },
             // User override for B
             ProviderDefinition {
@@ -695,6 +708,7 @@ mod tests {
                     display_name: "B".to_string(),
                     can_list_models: false,
                 }),
+                unsupported_params: vec![],
             },
         ];
 
@@ -708,6 +722,48 @@ mod tests {
         );
     }
 
+    #[test]
+    fn test_unsupported_params_deserialized() {
+        let providers: Vec<ProviderDefinition> =
+            serde_json::from_str(include_str!("../../providers.json")).unwrap();
+
+        // Tinfoil should have temperature in unsupported_params
+        let tinfoil = providers.iter().find(|p| p.id == "tinfoil").unwrap();
+        assert!(
+            tinfoil
+                .unsupported_params
+                .contains(&"temperature".to_string()),
+            "tinfoil should have 'temperature' in unsupported_params"
+        );
+
+        // OpenAI should also have temperature in unsupported_params
+        let openai = providers.iter().find(|p| p.id == "openai").unwrap();
+        assert!(
+            openai
+                .unsupported_params
+                .contains(&"temperature".to_string()),
+            "openai should have 'temperature' in unsupported_params"
+        );
+
+        // Providers without the field in JSON should deserialize to empty vec
+        let groq = providers.iter().find(|p| p.id == "groq").unwrap();
+        assert!(
+            groq.unsupported_params.is_empty(),
+            "groq should have empty unsupported_params (field absent in JSON)"
+        );
+
+        // Every non-empty entry should contain valid param names
+        for def in &providers {
+            for param in &def.unsupported_params {
+                assert!(
+                    !param.is_empty(),
+                    "{}: unsupported_params contains empty string",
+                    def.id
+                );
+            }
+        }
+    }
+
     #[test]
     fn test_all_builtin_api_key_providers_have_api_key_env() {
         // Every built-in provider with SetupHint::ApiKey must have api_key_env

src/llm/rig_adapter.rs

@@ -42,6 +42,9 @@ pub struct RigAdapter<M: CompletionModel> {
     /// via `additional_params` for Anthropic automatic caching. Also controls
     /// the cost multiplier for cache-creation tokens.
     cache_retention: CacheRetention,
+    /// Parameter names that this provider does not support (e.g., `"temperature"`).
+    /// These are stripped from requests before sending to avoid 400 errors.
+    unsupported_params: HashSet<String>,
 }
 
 impl<M: CompletionModel> RigAdapter<M> {
@@ -56,6 +59,7 @@ impl<M: CompletionModel> RigAdapter<M> {
             input_cost,
             output_cost,
             cache_retention: CacheRetention::None,
+            unsupported_params: HashSet::new(),
         }
     }
 
@@ -84,6 +88,44 @@ impl<M: CompletionModel> RigAdapter<M> {
         }
         self
     }
+
+    /// Set the list of unsupported parameter names for this provider.
+    ///
+    /// Parameters in this set are stripped from requests before sending.
+    /// Supported parameter names: `"temperature"`, `"max_tokens"`, `"stop_sequences"`.
+    pub fn with_unsupported_params(mut self, params: Vec<String>) -> Self {
+        self.unsupported_params = params.into_iter().collect();
+        self
+    }
+
+    /// Strip unsupported fields from a `CompletionRequest` in place.
+    fn strip_unsupported_completion_params(&self, req: &mut CompletionRequest) {
+        if self.unsupported_params.is_empty() {
+            return;
+        }
+        if self.unsupported_params.contains("temperature") {
+            req.temperature = None;
+        }
+        if self.unsupported_params.contains("max_tokens") {
+            req.max_tokens = None;
+        }
+        if self.unsupported_params.contains("stop_sequences") {
+            req.stop_sequences = None;
+        }
+    }
+
+    /// Strip unsupported fields from a `ToolCompletionRequest` in place.
+    fn strip_unsupported_tool_params(&self, req: &mut ToolCompletionRequest) {
+        if self.unsupported_params.is_empty() {
+            return;
+        }
+        if self.unsupported_params.contains("temperature") {
+            req.temperature = None;
+        }
+        if self.unsupported_params.contains("max_tokens") {
+            req.max_tokens = None;
+        }
+    }
 }
 
 // -- Type conversion helpers --
@@ -539,7 +581,10 @@ where
         }
     }
 
-    async fn complete(&self, request: CompletionRequest) -> Result<CompletionResponse, LlmError> {
+    async fn complete(
+        &self,
+        mut request: CompletionRequest,
+    ) -> Result<CompletionResponse, LlmError> {
         if let Some(requested_model) = request.model.as_deref()
             && requested_model != self.model_name.as_str()
         {
@@ -550,6 +595,8 @@ where
             );
         }
 
+        self.strip_unsupported_completion_params(&mut request);
+
         let mut messages = request.messages;
         crate::llm::provider::sanitize_tool_messages(&mut messages);
         let (preamble, history) = convert_messages(&messages);
@@ -599,7 +646,7 @@ where
 
     async fn complete_with_tools(
         &self,
-        request: ToolCompletionRequest,
+        mut request: ToolCompletionRequest,
     ) -> Result<ToolCompletionResponse, LlmError> {
         if let Some(requested_model) = request.model.as_deref()
             && requested_model != self.model_name.as_str()
@@ -611,6 +658,8 @@ where
             );
         }
 
+        self.strip_unsupported_tool_params(&mut request);
+
         let known_tool_names: HashSet<String> =
             request.tools.iter().map(|t| t.name.clone()).collect();
 
@@ -1156,4 +1205,97 @@ mod tests {
         assert!(!supports_prompt_cache("gpt-4o"));
         assert!(!supports_prompt_cache("llama3"));
     }
+
+    #[test]
+    fn test_with_unsupported_params_populates_set() {
+        use rig::client::CompletionClient;
+        use rig::providers::openai;
+
+        let client: openai::Client = openai::Client::builder()
+            .api_key("test-key")
+            .base_url("http://localhost:0")
+            .build()
+            .unwrap();
+        let client = client.completions_api();
+        let model = client.completion_model("test-model");
+        let adapter = RigAdapter::new(model, "test-model")
+            .with_unsupported_params(vec!["temperature".to_string()]);
+
+        assert!(adapter.unsupported_params.contains("temperature"));
+        assert!(!adapter.unsupported_params.contains("max_tokens"));
+    }
+
+    #[test]
+    fn test_strip_unsupported_completion_params() {
+        use rig::client::CompletionClient;
+        use rig::providers::openai;
+
+        let client: openai::Client = openai::Client::builder()
+            .api_key("test-key")
+            .base_url("http://localhost:0")
+            .build()
+            .unwrap();
+        let client = client.completions_api();
+        let model = client.completion_model("test-model");
+        let adapter = RigAdapter::new(model, "test-model").with_unsupported_params(vec![
+            "temperature".to_string(),
+            "stop_sequences".to_string(),
+        ]);
+
+        let mut req = CompletionRequest::new(vec![ChatMessage::user("hi")]);
+        req.temperature = Some(0.7);
+        req.max_tokens = Some(100);
+        req.stop_sequences = Some(vec!["STOP".to_string()]);
+
+        adapter.strip_unsupported_completion_params(&mut req);
+
+        assert!(req.temperature.is_none(), "temperature should be stripped");
+        assert_eq!(req.max_tokens, Some(100), "max_tokens should be preserved");
+        assert!(
+            req.stop_sequences.is_none(),
+            "stop_sequences should be stripped"
+        );
+    }
+
+    #[test]
+    fn test_strip_unsupported_tool_params() {
+        use rig::client::CompletionClient;
+        use rig::providers::openai;
+
+        let client: openai::Client = openai::Client::builder()
+            .api_key("test-key")
+            .base_url("http://localhost:0")
+            .build()
+            .unwrap();
+        let client = client.completions_api();
+        let model = client.completion_model("test-model");
+        let adapter = RigAdapter::new(model, "test-model")
+            .with_unsupported_params(vec!["temperature".to_string(), "max_tokens".to_string()]);
+
+        let mut req = ToolCompletionRequest::new(vec![ChatMessage::user("hi")], vec![]);
+        req.temperature = Some(0.5);
+        req.max_tokens = Some(200);
+
+        adapter.strip_unsupported_tool_params(&mut req);
+
+        assert!(req.temperature.is_none(), "temperature should be stripped");
+        assert!(req.max_tokens.is_none(), "max_tokens should be stripped");
+    }
+
+    #[test]
+    fn test_unsupported_params_empty_by_default() {
+        use rig::client::CompletionClient;
+        use rig::providers::openai;
+
+        let client: openai::Client = openai::Client::builder()
+            .api_key("test-key")
+            .base_url("http://localhost:0")
+            .build()
+            .unwrap();
+        let client = client.completions_api();
+        let model = client.completion_model("test-model");
+        let adapter = RigAdapter::new(model, "test-model");
+
+        assert!(adapter.unsupported_params.is_empty());
+    }
 }

src/setup/wizard.rs

@@ -3787,6 +3787,7 @@ mod tests {
             description: "Custom provider with no setup wizard".to_string(),
             extra_headers_env: None,
             setup: None,
+            unsupported_params: vec![],
         });
         let registry = crate::llm::ProviderRegistry::new(providers);