feat: Support the merging of custom user-defined models on clients configured in the global configuration file with the built in models

assets/config-template.yaml

@@ -277,6 +277,7 @@ sync_models_ttl_hours: 24        # Hours before the synced model catalog is cons
 # All clients have the following configuration:
 # - type: xxxx
 #   name: xxxx                                      # Only use it to distinguish clients with the same client type. Optional
+#   extend_models: true                             # Merge the models below on top of the catalog models for this client instead of replacing them. Optional, default false
 #   models:
 #     - name: xxxx                                  # Chat model
 #       max_input_tokens: 100000

src/client/azure_openai.rs

@@ -4,13 +4,15 @@ use super::*;
 use anyhow::Result;
 use serde::Deserialize;
 
-#[derive(Debug, Clone, Deserialize)]
+#[derive(Debug, Clone, Deserialize, Default)]
 pub struct AzureOpenAIConfig {
     pub name: Option<String>,
     pub api_base: Option<String>,
     pub api_key: Option<String>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
 }

src/client/bedrock.rs

@@ -16,7 +16,7 @@ use reqwest::{Client as ReqwestClient, Method, RequestBuilder};
 use serde::Deserialize;
 use serde_json::{Value, json};
 
-#[derive(Debug, Clone, Deserialize)]
+#[derive(Debug, Clone, Deserialize, Default)]
 pub struct BedrockConfig {
     pub name: Option<String>,
     pub access_key_id: Option<String>,
@@ -25,6 +25,8 @@ pub struct BedrockConfig {
     pub session_token: Option<String>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub prompt_cache: Option<bool>,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,

src/client/catalog.rs

@@ -572,7 +572,7 @@ pub(crate) fn name_overlap(old: &[String], new: &[String]) -> f64 {
     kept as f64 / old.len() as f64
 }
 
-fn overlay_hand_owned(hand: ModelData, api: ModelData) -> ModelData {
+pub(crate) fn overlay_hand_owned(hand: ModelData, api: ModelData) -> ModelData {
     ModelData {
         name: hand.name,
         model_type: hand.model_type,
@@ -604,6 +604,23 @@ fn overlay_hand_owned(hand: ModelData, api: ModelData) -> ModelData {
     }
 }
 
+pub(crate) fn extend_catalog_models(
+    catalog: &[ModelData],
+    overrides: &[ModelData],
+) -> Vec<ModelData> {
+    let mut models = catalog.to_vec();
+    for override_model in overrides {
+        match models.iter_mut().find(|model| {
+            model.name == override_model.name && model.model_type == override_model.model_type
+        }) {
+            Some(model) => *model = overlay_hand_owned(override_model.clone(), model.clone()),
+            None => models.push(override_model.clone()),
+        }
+    }
+
+    models
+}
+
 #[derive(Debug, Clone, Serialize, Deserialize)]
 #[serde(deny_unknown_fields)]
 pub struct ProviderQuirks {
@@ -1724,4 +1741,47 @@ rules:
             );
         }
     }
+
+    fn typed_model(name: &str, model_type: &str) -> ModelData {
+        ModelData {
+            name: name.to_string(),
+            model_type: model_type.to_string(),
+            ..Default::default()
+        }
+    }
+
+    #[test]
+    fn extend_catalog_models_merges_collisions_field_wise() {
+        let mut catalog_model = ModelData::new("m");
+        catalog_model.max_input_tokens = Some(100_000);
+        catalog_model.input_price = Some(1.0);
+        catalog_model.supports_vision = true;
+        let mut override_model = ModelData::new("m");
+        override_model.input_price = Some(9.0);
+
+        let merged = extend_catalog_models(&[catalog_model], &[override_model]);
+        assert_eq!(merged.len(), 1);
+        assert_eq!(merged[0].input_price, Some(9.0));
+        assert_eq!(merged[0].max_input_tokens, Some(100_000));
+        assert!(merged[0].supports_vision);
+    }
+
+    #[test]
+    fn extend_catalog_models_appends_net_new_after_catalog() {
+        let catalog = [ModelData::new("a"), ModelData::new("b")];
+        let merged = extend_catalog_models(&catalog, &[ModelData::new("c")]);
+        let names: Vec<&str> = merged.iter().map(|model| model.name.as_str()).collect();
+        assert_eq!(names, ["a", "b", "c"]);
+    }
+
+    #[test]
+    fn extend_catalog_models_collides_on_name_and_type() {
+        let mut catalog_model = typed_model("m", "embedding");
+        catalog_model.default_chunk_size = Some(1500);
+        let merged = extend_catalog_models(&[catalog_model], &[typed_model("m", "reranker")]);
+        assert_eq!(merged.len(), 2);
+        assert_eq!(merged[0].model_type, "embedding");
+        assert_eq!(merged[0].default_chunk_size, Some(1500));
+        assert_eq!(merged[1].model_type, "reranker");
+    }
 }

src/client/claude.rs

@@ -15,7 +15,7 @@ use serde_json::{Value, json};
 const API_BASE: &str = "https://api.anthropic.com/v1";
 const CLAUDE_CODE_PREFIX: &str = "You are Claude Code, Anthropic's official CLI for Claude.";
 
-#[derive(Debug, Clone, Deserialize)]
+#[derive(Debug, Clone, Deserialize, Default)]
 pub struct ClaudeConfig {
     pub name: Option<String>,
     pub api_key: Option<String>,
@@ -24,6 +24,8 @@ pub struct ClaudeConfig {
     pub oauth: Option<Box<OAuthConfig>>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub prompt_cache: Option<bool>,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
@@ -1122,16 +1124,12 @@ mod tests {
     fn claude_config(name: &str, auth: Option<&str>, oauth: Option<OAuthConfig>) -> ClaudeConfig {
         ClaudeConfig {
             name: Some(name.into()),
-            api_key: None,
             api_base: oauth
                 .as_ref()
                 .map(|_| "https://gateway.example/v1".to_string()),
             auth: auth.map(str::to_string),
             oauth: oauth.map(Box::new),
-            models: vec![],
+            ..Default::default()
-            prompt_cache: None,
-            patch: None,
-            extra: None,
         }
     }
 

src/client/cohere.rs

@@ -16,6 +16,8 @@ pub struct CohereConfig {
     pub api_base: Option<String>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
 }

src/client/gemini.rs

@@ -20,6 +20,8 @@ pub struct GeminiConfig {
     pub oauth: Option<Box<OAuthConfig>>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
 }

src/client/macros.rs

@@ -51,15 +51,24 @@ macro_rules! register_client {
 
                 pub fn list_models(local_config: &$config) -> Vec<Model> {
                     let client_name = Self::name(local_config);
-                    if local_config.models.is_empty() {
+                    let find_catalog = || $crate::client::ALL_PROVIDER_MODELS.iter().find(|v| {
-                        if let Some(v) = $crate::client::ALL_PROVIDER_MODELS.iter().find(|v| {
                         v.provider == $name ||
                             ($name == OpenAICompatibleClient::NAME
                                 && local_config.name.as_ref().map(|name| name.starts_with(&v.provider)).unwrap_or_default())
-                        }) {
+                    });
-                            return Model::from_config(client_name, &v.models);
+                    if local_config.models.is_empty() {
+                        match find_catalog() {
+                            Some(v) => Model::from_config(client_name, &v.models),
+                            None => vec![],
+                        }
+                    } else if local_config.extend_models {
+                        match find_catalog() {
+                            Some(v) => Model::from_config(
+                                client_name,
+                                &$crate::client::catalog::extend_catalog_models(&v.models, &local_config.models),
+                            ),
+                            None => Model::from_config(client_name, &local_config.models),
                         }
-                        vec![]
                     } else {
                         Model::from_config(client_name, &local_config.models)
                     }

src/client/model.rs

@@ -557,4 +557,96 @@ reasoning_levels: [none, low, medium, high]
             "oauth blocks in the shipped models.yaml are limited to providers with no built-in stock oauth path (currently only xai's bundled defaults); adding one for claude/openai/gemini would silently swap stock oauth users onto a non-stock provider"
         );
     }
+
+    #[test]
+    fn config_models_replace_catalog_by_default() {
+        let ClientConfig::ClaudeConfig(config) = serde_yaml::from_str::<ClientConfig>(
+            "type: claude\nmodels:\n  - name: test-replace-model\n",
+        )
+        .unwrap() else {
+            panic!("expected a claude config");
+        };
+        assert!(!config.extend_models);
+
+        let models = crate::client::ClaudeClient::list_models(&config);
+        assert_eq!(models.len(), 1);
+        assert_eq!(models[0].name(), "test-replace-model");
+    }
+
+    #[test]
+    fn config_models_extend_catalog_when_flag_set() {
+        let ClientConfig::ClaudeConfig(config) = serde_yaml::from_str::<ClientConfig>(
+            "type: claude\nextend_models: true\nmodels:\n  - name: test-extra-model\n",
+        )
+        .unwrap() else {
+            panic!("expected a claude config");
+        };
+
+        let catalog_len = crate::client::ALL_PROVIDER_MODELS
+            .iter()
+            .find(|v| v.provider == "claude")
+            .map(|v| v.models.len())
+            .unwrap();
+        let models = crate::client::ClaudeClient::list_models(&config);
+        assert_eq!(models.len(), catalog_len + 1);
+        assert_eq!(models.last().unwrap().name(), "test-extra-model");
+    }
+
+    #[test]
+    fn extend_models_with_empty_models_returns_catalog_exactly() {
+        let ClientConfig::ClaudeConfig(config) =
+            serde_yaml::from_str::<ClientConfig>("type: claude\nextend_models: true\n").unwrap()
+        else {
+            panic!("expected a claude config");
+        };
+
+        let catalog = crate::client::ALL_PROVIDER_MODELS
+            .iter()
+            .find(|v| v.provider == "claude")
+            .unwrap();
+        let models = crate::client::ClaudeClient::list_models(&config);
+        assert_eq!(models.len(), catalog.models.len());
+        for (model, catalog_model) in models.iter().zip(catalog.models.iter()) {
+            assert_eq!(model.name(), catalog_model.name);
+        }
+    }
+
+    #[test]
+    fn extend_models_without_catalog_match_returns_config_models_only() {
+        let ClientConfig::OpenAICompatibleConfig(config) = serde_yaml::from_str::<ClientConfig>(
+            "type: openai-compatible\nname: no-such-provider-xyz\nextend_models: true\nmodels:\n  - name: test-only-model\n",
+        )
+        .unwrap() else {
+            panic!("expected an openai-compatible config");
+        };
+
+        assert!(
+            !crate::client::ALL_PROVIDER_MODELS
+                .iter()
+                .any(|v| "no-such-provider-xyz".starts_with(v.provider.as_str())),
+            "test premise: the client name must not prefix-match any catalog provider"
+        );
+        let models = crate::client::OpenAICompatibleClient::list_models(&config);
+        assert_eq!(models.len(), 1);
+        assert_eq!(models[0].name(), "test-only-model");
+    }
+
+    #[test]
+    fn extend_models_extends_catalog_via_provider_name_prefix_match() {
+        let ClientConfig::OpenAICompatibleConfig(config) = serde_yaml::from_str::<ClientConfig>(
+            "type: openai-compatible\nname: openrouter-custom\nextend_models: true\nmodels:\n  - name: test-net-new-model\n",
+        )
+        .unwrap() else {
+            panic!("expected an openai-compatible config");
+        };
+
+        let catalog_len = crate::client::ALL_PROVIDER_MODELS
+            .iter()
+            .find(|v| v.provider == "openrouter")
+            .map(|v| v.models.len())
+            .unwrap();
+        let models = crate::client::OpenAICompatibleClient::list_models(&config);
+        assert_eq!(models.len(), catalog_len + 1);
+        assert_eq!(models.last().unwrap().name(), "test-net-new-model");
+    }
 }

src/client/oauth.rs

@@ -1457,13 +1457,9 @@ echo_pkce_in_token_exchange: true
         ClientConfig::OpenAICompatibleConfig(OpenAICompatibleConfig {
             name: Some(name.into()),
             api_base: Some("https://api.example/v1".into()),
-            api_key: None,
             auth: auth.map(str::to_string),
             oauth: oauth.map(Box::new),
-            wire_api: None,
+            ..Default::default()
-            models: vec![],
-            patch: None,
-            extra: None,
         })
     }
 
@@ -1474,14 +1470,9 @@ echo_pkce_in_token_exchange: true
     ) -> ClientConfig {
         ClientConfig::ClaudeConfig(ClaudeConfig {
             name: Some(name.into()),
-            api_key: None,
-            api_base: None,
             auth: auth.map(str::to_string),
             oauth: oauth.map(Box::new),
-            models: vec![],
+            ..Default::default()
-            prompt_cache: None,
-            patch: None,
-            extra: None,
         })
     }
 
@@ -1492,15 +1483,9 @@ echo_pkce_in_token_exchange: true
     ) -> ClientConfig {
         ClientConfig::OpenAIConfig(OpenAIConfig {
             name: Some(name.into()),
-            api_key: None,
-            api_base: None,
-            organization_id: None,
             auth: auth.map(str::to_string),
             oauth: oauth.map(Box::new),
-            wire_api: None,
+            ..Default::default()
-            models: vec![],
-            patch: None,
-            extra: None,
         })
     }
 
@@ -1511,13 +1496,9 @@ echo_pkce_in_token_exchange: true
     ) -> ClientConfig {
         ClientConfig::GeminiConfig(GeminiConfig {
             name: Some(name.into()),
-            api_key: None,
-            api_base: None,
             auth: auth.map(str::to_string),
             oauth: oauth.map(Box::new),
-            models: vec![],
+            ..Default::default()
-            patch: None,
-            extra: None,
         })
     }
 

src/client/openai.rs

@@ -24,6 +24,8 @@ pub struct OpenAIConfig {
     pub wire_api: Option<WireApi>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
 }

src/client/openai_compatible.rs

@@ -9,7 +9,7 @@ use serde::Deserialize;
 use serde_json::{Value, json};
 use oauth::OAuthConfig;
 
-#[derive(Debug, Clone, Deserialize)]
+#[derive(Debug, Clone, Deserialize, Default)]
 pub struct OpenAICompatibleConfig {
     pub name: Option<String>,
     pub api_base: Option<String>,
@@ -19,6 +19,8 @@ pub struct OpenAICompatibleConfig {
     pub wire_api: Option<WireApi>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
 }
@@ -274,12 +276,8 @@ mod tests {
             name: Some("compat-test".into()),
             api_base: Some("https://compat.example/v1".into()),
             api_key: Some("sk-test".into()),
-            auth: None,
-            oauth: None,
             wire_api,
-            models: vec![],
+            ..Default::default()
-            patch: None,
-            extra: None,
         }
     }
 

src/client/vertexai.rs

@@ -18,6 +18,8 @@ pub struct VertexAIConfig {
     pub adc_file: Option<String>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub prompt_cache: Option<bool>,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,