Merge branch 'main' into custom-tokenizer

app/MindWork AI Studio/Provider/AlibabaCloud/ProviderAlibabaCloud.cs

@@ -1,7 +1,4 @@
-using System.Net.Http.Headers;
-using System.Runtime.CompilerServices;
-using System.Text;
-using System.Text.Json;
+using System.Runtime.CompilerServices;
 
 using AIStudio.Chat;
 using AIStudio.Provider.OpenAI;
@@ -20,56 +17,37 @@ public sealed class ProviderAlibabaCloud() : BaseProvider(LLMProviders.ALIBABA_C
 
     /// <inheritdoc />
     public override string InstanceName { get; set; } = "AlibabaCloud";
+
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => true;
     
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
-        // Get the API key:
-        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, SecretStoreType.LLM_PROVIDER);
-        if(!requestedSecret.Success)
-            yield break;
-        
-        // Prepare the system prompt:
-        var systemPrompt = new TextMessage
-        {
-            Role = "system",
-            Content = chatThread.PrepareSystemPrompt(settingsManager),
-        };
-        
-        // Parse the API parameters:
-        var apiParameters = this.ParseAdditionalApiParameters();
-        
-        // Build the list of messages:
-        var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
-        
-        // Prepare the AlibabaCloud HTTP chat request:
-        var alibabaCloudChatRequest = JsonSerializer.Serialize(new ChatCompletionAPIRequest
-        {
-            Model = chatModel.Id,
-            
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..messages],
-            
-            Stream = true,
-            AdditionalApiParameters = apiParameters
-        }, JSON_SERIALIZER_OPTIONS);
+        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>(
+                           "AlibabaCloud",
+                           chatModel,
+                           chatThread,
+                           settingsManager,
+                           async (systemPrompt, apiParameters) =>
+                           {
+                               // Build the list of messages:
+                               var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
 
-        async Task<HttpRequestMessage> RequestBuilder()
-        {
-            // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
+                               return new ChatCompletionAPIRequest
+                               {
+                                   Model = chatModel.Id,
 
-            // Set the authorization header:
-            request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
+                                   // Build the messages:
+                                   // - First of all the system prompt
+                                   // - Then none-empty user and AI messages
+                                   Messages = [systemPrompt, ..messages],
 
-            // Set the content:
-            request.Content = new StringContent(alibabaCloudChatRequest, Encoding.UTF8, "application/json");
-            return request;
-        }
-        
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>("AlibabaCloud", RequestBuilder, token))
+                                   Stream = true,
+                                   AdditionalApiParameters = apiParameters
+                               };
+                           },
+                           token: token))
             yield return content;
     }
 
@@ -95,7 +73,7 @@ public sealed class ProviderAlibabaCloud() : BaseProvider(LLMProviders.ALIBABA_C
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         var additionalModels = new[]
         {
@@ -124,17 +102,21 @@ public sealed class ProviderAlibabaCloud() : BaseProvider(LLMProviders.ALIBABA_C
             new Model("qwen2.5-vl-3b-instruct", "Qwen2.5-VL 3b"),  
         };
         
-        return this.LoadModels(["q"], SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional).ContinueWith(t => t.Result.Concat(additionalModels).OrderBy(x => x.Id).AsEnumerable(), token);
+        var result = await this.LoadModels(["q"], SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
+        return result with
+        {
+            Models = [..result.Models.Concat(additionalModels).OrderBy(x => x.Id)]
+        };
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         
         var additionalModels = new[]
@@ -142,45 +124,33 @@ public sealed class ProviderAlibabaCloud() : BaseProvider(LLMProviders.ALIBABA_C
             new Model("text-embedding-v3", "text-embedding-v3"),
         };
         
-        return this.LoadModels(["text-embedding-"], SecretStoreType.EMBEDDING_PROVIDER, token, apiKeyProvisional).ContinueWith(t => t.Result.Concat(additionalModels).OrderBy(x => x.Id).AsEnumerable(), token);
+        var result = await this.LoadModels(["text-embedding-"], SecretStoreType.EMBEDDING_PROVIDER, token, apiKeyProvisional);
+        return result with
+        {
+            Models = [..result.Models.Concat(additionalModels).OrderBy(x => x.Id)]
+        };
     }
 
     #region Overrides of BaseProvider
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
 
     #endregion
 
     #endregion
     
-    private async Task<IEnumerable<Model>> LoadModels(string[] prefixes, SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
+    private Task<ModelLoadResult> LoadModels(string[] prefixes, SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
     {
-        var secretKey = apiKeyProvisional switch
-        {
-            not null => apiKeyProvisional,
-            _ => await RUST_SERVICE.GetAPIKey(this, storeType) switch
-            {
-                { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
-                _ => null,
-            }
-        };
-
-        if (secretKey is null)
-            return [];
-        
-        using var request = new HttpRequestMessage(HttpMethod.Get, "models");
-        request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
-
-        using var response = await this.httpClient.SendAsync(request, token);
-        if(!response.IsSuccessStatusCode)
-            return [];
-        
-        var modelResponse = await response.Content.ReadFromJsonAsync<ModelsResponse>(token);
-        return modelResponse.Data.Where(model => prefixes.Any(prefix => model.Id.StartsWith(prefix, StringComparison.InvariantCulture)));
+        return this.LoadModelsResponse<ModelsResponse>(
+            storeType,
+            "models",
+            modelResponse => modelResponse.Data.Where(model => prefixes.Any(prefix => model.Id.StartsWith(prefix, StringComparison.InvariantCulture))),
+            token,
+            apiKeyProvisional);
     }
     
 }

app/MindWork AI Studio/Provider/Anthropic/ProviderAnthropic.cs

@@ -1,4 +1,3 @@
-using System.Net.Http.Headers;
 using System.Runtime.CompilerServices;
 using System.Text;
 using System.Text.Json;
@@ -15,10 +14,15 @@ public sealed class ProviderAnthropic() : BaseProvider(LLMProviders.ANTHROPIC, "
 
     #region Implementation of IProvider
 
+    /// <inheritdoc />
     public override string Id => LLMProviders.ANTHROPIC.ToName();
 
+    /// <inheritdoc />
     public override string InstanceName { get; set; } = "Anthropic";
 
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => true;
+
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
@@ -124,7 +128,7 @@ public sealed class ProviderAnthropic() : BaseProvider(LLMProviders.ANTHROPIC, "
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         var additionalModels = new[]
         {
@@ -136,59 +140,52 @@ public sealed class ProviderAnthropic() : BaseProvider(LLMProviders.ANTHROPIC, "
             new Model("claude-3-opus-latest", "Claude 3 Opus (Latest)"),
         };
         
-        return this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional).ContinueWith(t => t.Result.Concat(additionalModels).OrderBy(x => x.Id).AsEnumerable(), token);
+        var result = await this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
+        return result with
+        {
+            Models = [..result.Models.Concat(additionalModels).OrderBy(x => x.Id)]
+        };
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     #endregion
     
-    private async Task<IEnumerable<Model>> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
+    private Task<ModelLoadResult> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
     {
-        var secretKey = apiKeyProvisional switch
-        {
-            not null => apiKeyProvisional,
-            _ => await RUST_SERVICE.GetAPIKey(this, storeType) switch
+        return this.LoadModelsResponse<ModelsResponse>(
+            storeType,
+            "models?limit=100",
+            modelResponse => modelResponse.Data,
+            token,
+            apiKeyProvisional,
+            failureReasonSelector: (response, _) => response.StatusCode switch
             {
-                { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
-                _ => null,
-            }
-        };
-
-        if (secretKey is null)
-            return [];
-        
-        using var request = new HttpRequestMessage(HttpMethod.Get, "models?limit=100");
-        
-        // Set the authorization header:
-        request.Headers.Add("x-api-key", secretKey);
-
-        // Set the Anthropic version:
-        request.Headers.Add("anthropic-version", "2023-06-01");
-        
-        request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
-
-        using var response = await this.httpClient.SendAsync(request, token);
-        if(!response.IsSuccessStatusCode)
-            return [];
-
-        var modelResponse = await response.Content.ReadFromJsonAsync<ModelsResponse>(JSON_SERIALIZER_OPTIONS, token);
-        return modelResponse.Data;
+                System.Net.HttpStatusCode.Unauthorized => ModelLoadFailureReason.INVALID_OR_MISSING_API_KEY,
+                System.Net.HttpStatusCode.Forbidden => ModelLoadFailureReason.AUTHENTICATION_OR_PERMISSION_ERROR,
+                _ => ModelLoadFailureReason.PROVIDER_UNAVAILABLE,
+            },
+            requestConfigurator: (request, secretKey) =>
+            {
+                request.Headers.Add("x-api-key", secretKey);
+                request.Headers.Add("anthropic-version", "2023-06-01");
+            },
+            jsonSerializerOptions: JSON_SERIALIZER_OPTIONS);
     }
-}
+}

app/MindWork AI Studio/Provider/BaseProvider.cs

@@ -29,7 +29,7 @@ public abstract class BaseProvider : IProvider, ISecretId
     /// <summary>
     /// The HTTP client to use it for all requests.
     /// </summary>
-    protected readonly HttpClient httpClient = new();
+    protected readonly HttpClient HttpClient = new();
     
     /// <summary>
     /// The logger to use.
@@ -73,7 +73,7 @@ public abstract class BaseProvider : IProvider, ISecretId
         this.Provider = provider;
 
         // Set the base URL:
-        this.httpClient.BaseAddress = new(url);
+        this.HttpClient.BaseAddress = new(url);
     }
     
     #region Handling of IProvider, which all providers must implement
@@ -93,6 +93,9 @@ public abstract class BaseProvider : IProvider, ISecretId
     /// <inheritdoc />
     public string TokenizerPath { get; init; } = string.Empty;
 
+    /// <inheritdoc />
+    public abstract bool HasModelLoadingCapability { get; }
+
     /// <inheritdoc />
     public abstract IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, CancellationToken token = default);
     
@@ -106,16 +109,16 @@ public abstract class BaseProvider : IProvider, ISecretId
     public abstract Task<IReadOnlyList<IReadOnlyList<float>>> EmbedTextAsync(Model embeddingModel, SettingsManager settingsManager, CancellationToken token = default, params List<string> texts);
     
     /// <inheritdoc />
-    public abstract Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default);
+    public abstract Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default);
     
     /// <inheritdoc />
-    public abstract Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default);
+    public abstract Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default);
     
     /// <inheritdoc />
-    public abstract Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default);
+    public abstract Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default);
 
     /// <inheritdoc />
-    public abstract Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default);
+    public abstract Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default);
     
     #endregion
     
@@ -131,6 +134,71 @@ public abstract class BaseProvider : IProvider, ISecretId
     public string SecretName => this.InstanceName;
 
     #endregion
+
+    protected static ModelLoadResult SuccessfulModelLoadResult(IEnumerable<Model> models) => ModelLoadResult.FromModels(models);
+
+    protected static ModelLoadResult FailedModelLoadResult(ModelLoadFailureReason failureReason, string? technicalDetails = null) => ModelLoadResult.Failure(failureReason, technicalDetails);
+
+    protected async Task<string?> GetModelLoadingSecretKey(SecretStoreType storeType, string? apiKeyProvisional = null, bool isTryingSecret = false) => apiKeyProvisional switch
+    {
+        not null => apiKeyProvisional,
+        _ => await RUST_SERVICE.GetAPIKey(this, storeType, isTrying: isTryingSecret) switch
+        {
+            { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
+            _ => null,
+        }
+    };
+
+    protected static ModelLoadFailureReason GetDefaultModelLoadFailureReason(HttpResponseMessage response) => response.StatusCode switch
+    {
+        HttpStatusCode.Unauthorized => ModelLoadFailureReason.INVALID_OR_MISSING_API_KEY,
+        HttpStatusCode.Forbidden => ModelLoadFailureReason.AUTHENTICATION_OR_PERMISSION_ERROR,
+        
+        _ => ModelLoadFailureReason.PROVIDER_UNAVAILABLE,
+    };
+
+    protected async Task<ModelLoadResult> LoadModelsResponse<TResponse>(
+        SecretStoreType storeType,
+        string requestPath,
+        Func<TResponse, IEnumerable<Model>> modelFactory,
+        CancellationToken token,
+        string? apiKeyProvisional = null,
+        Func<HttpResponseMessage, string, ModelLoadFailureReason>? failureReasonSelector = null,
+        Action<HttpRequestMessage, string>? requestConfigurator = null,
+        JsonSerializerOptions? jsonSerializerOptions = null,
+        bool isTryingSecret = false)
+    {
+        var secretKey = await this.GetModelLoadingSecretKey(storeType, apiKeyProvisional, isTryingSecret);
+        if (string.IsNullOrWhiteSpace(secretKey) && !isTryingSecret)
+            return FailedModelLoadResult(ModelLoadFailureReason.INVALID_OR_MISSING_API_KEY, "No API key available for model loading.");
+
+        using var request = new HttpRequestMessage(HttpMethod.Get, requestPath);
+        if (requestConfigurator is not null)
+            requestConfigurator(request, secretKey ?? string.Empty);
+        else if (!string.IsNullOrWhiteSpace(secretKey))
+            request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
+
+        using var response = await this.HttpClient.SendAsync(request, token);
+        var responseBody = await response.Content.ReadAsStringAsync(token);
+        if (!response.IsSuccessStatusCode)
+        {
+            var failureReason = failureReasonSelector?.Invoke(response, responseBody) ?? GetDefaultModelLoadFailureReason(response);
+            return FailedModelLoadResult(failureReason, $"Status={(int)response.StatusCode} {response.ReasonPhrase}; Body='{responseBody}'");
+        }
+
+        try
+        {
+            var parsedResponse = JsonSerializer.Deserialize<TResponse>(responseBody, jsonSerializerOptions ?? JSON_SERIALIZER_OPTIONS);
+            if (parsedResponse is null)
+                return FailedModelLoadResult(ModelLoadFailureReason.INVALID_RESPONSE, "Model list response could not be deserialized.");
+
+            return SuccessfulModelLoadResult(modelFactory(parsedResponse));
+        }
+        catch (Exception e)
+        {
+            return FailedModelLoadResult(ModelLoadFailureReason.INVALID_RESPONSE, e.Message);
+        }
+    }
     
     /// <summary>
     /// Sends a request and handles rate limiting by exponential backoff.
@@ -158,7 +226,7 @@ public abstract class BaseProvider : IProvider, ISecretId
             // Please notice: We do not dispose the response here. The caller is responsible
             // for disposing the response object. This is important because the response
             // object is used to read the stream.
-            var nextResponse = await this.httpClient.SendAsync(request, HttpCompletionOption.ResponseHeadersRead, token);
+            var nextResponse = await this.HttpClient.SendAsync(request, HttpCompletionOption.ResponseHeadersRead, token);
             if (nextResponse.IsSuccessStatusCode)
             {
                 response = nextResponse;
@@ -568,6 +636,78 @@ public abstract class BaseProvider : IProvider, ISecretId
         streamReader.Dispose();
     }
 
+    /// <summary>
+    /// Streams the chat completion from an OpenAI-compatible provider using the Chat Completion API.
+    /// </summary>
+    /// <param name="providerName">The provider name for logging and error reporting.</param>
+    /// <param name="chatModel">The selected chat model.</param>
+    /// <param name="chatThread">The current chat thread.</param>
+    /// <param name="settingsManager">The settings manager.</param>
+    /// <param name="requestFactory">Builds the provider-specific request body.</param>
+    /// <param name="storeType">The secret store type.</param>
+    /// <param name="isTryingSecret">Whether the API key is optional.</param>
+    /// <param name="systemPromptRole">The system prompt role to use.</param>
+    /// <param name="requestPath">The request path, relative to the provider base URL.</param>
+    /// <param name="headersAction">Optional additional headers to add.</param>
+    /// <param name="token">The cancellation token.</param>
+    /// <typeparam name="TRequest">The request DTO type.</typeparam>
+    /// <typeparam name="TDelta">The delta stream line type.</typeparam>
+    /// <typeparam name="TAnnotation">The annotation stream line type.</typeparam>
+    /// <returns>The streamed content chunks.</returns>
+    protected async IAsyncEnumerable<ContentStreamChunk> StreamOpenAICompatibleChatCompletion<TRequest, TDelta, TAnnotation>(
+        string providerName,
+        Model chatModel,
+        ChatThread chatThread,
+        SettingsManager settingsManager,
+        Func<TextMessage, IDictionary<string, object>, Task<TRequest>> requestFactory,
+        SecretStoreType storeType = SecretStoreType.LLM_PROVIDER,
+        bool isTryingSecret = false,
+        string systemPromptRole = "system",
+        string requestPath = "chat/completions",
+        Action<HttpRequestHeaders>? headersAction = null,
+        [EnumeratorCancellation] CancellationToken token = default)
+        where TDelta : IResponseStreamLine
+        where TAnnotation : IAnnotationStreamLine
+    {
+        // Get the API key:
+        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, storeType, isTrying: isTryingSecret);
+        if(!requestedSecret.Success && !isTryingSecret)
+            yield break;
+
+        // Prepare the system prompt:
+        var systemPrompt = new TextMessage
+        {
+            Role = systemPromptRole,
+            Content = chatThread.PrepareSystemPrompt(settingsManager),
+        };
+
+        // Parse the API parameters:
+        var apiParameters = this.ParseAdditionalApiParameters();
+
+        // Prepare the provider HTTP chat request:
+        var providerChatRequest = JsonSerializer.Serialize(await requestFactory(systemPrompt, apiParameters), JSON_SERIALIZER_OPTIONS);
+
+        async Task<HttpRequestMessage> RequestBuilder()
+        {
+            // Build the HTTP post request:
+            var request = new HttpRequestMessage(HttpMethod.Post, requestPath);
+
+            // Set the authorization header:
+            if (requestedSecret.Success)
+                request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
+
+            // Set provider-specific headers:
+            headersAction?.Invoke(request.Headers);
+
+            // Set the content:
+            request.Content = new StringContent(providerChatRequest, Encoding.UTF8, "application/json");
+            return request;
+        }
+
+        await foreach (var content in this.StreamChatCompletionInternal<TDelta, TAnnotation>(providerName, RequestBuilder, token))
+            yield return content;
+    }
+
     protected async Task<string> PerformStandardTranscriptionRequest(RequestedSecret requestedSecret, Model transcriptionModel, string audioFilePath, Host host = Host.NONE, CancellationToken token = default)
     {
         try
@@ -627,7 +767,7 @@ public abstract class BaseProvider : IProvider, ISecretId
                     break;
             }
             
-            using var response = await this.httpClient.SendAsync(request, token);
+            using var response = await this.HttpClient.SendAsync(request, token);
             var responseBody = response.Content.ReadAsStringAsync(token).Result;
         
             if (!response.IsSuccessStatusCode)
@@ -697,7 +837,7 @@ public abstract class BaseProvider : IProvider, ISecretId
             
             // Set the content:
             request.Content = new StringContent(embeddingRequest, Encoding.UTF8, "application/json");
-            using var response = await this.httpClient.SendAsync(request, token);
+            using var response = await this.HttpClient.SendAsync(request, token);
             var responseBody = response.Content.ReadAsStringAsync(token).Result;
         
             if (!response.IsSuccessStatusCode)

app/MindWork AI Studio/Provider/DeepSeek/ProviderDeepSeek.cs

@@ -1,7 +1,4 @@
-using System.Net.Http.Headers;
 using System.Runtime.CompilerServices;
-using System.Text;
-using System.Text.Json;
 
 using AIStudio.Chat;
 using AIStudio.Provider.OpenAI;
@@ -20,56 +17,37 @@ public sealed class ProviderDeepSeek() : BaseProvider(LLMProviders.DEEP_SEEK, "h
 
     /// <inheritdoc />
     public override string InstanceName { get; set; } = "DeepSeek";
+
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => true;
     
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
-        // Get the API key:
-        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, SecretStoreType.LLM_PROVIDER);
-        if(!requestedSecret.Success)
-            yield break;
-        
-        // Prepare the system prompt:
-        var systemPrompt = new TextMessage
-        {
-            Role = "system",
-            Content = chatThread.PrepareSystemPrompt(settingsManager),
-        };
-        
-        // Parse the API parameters:
-        var apiParameters = this.ParseAdditionalApiParameters();
-        
-        // Build the list of messages:
-        var messages = await chatThread.Blocks.BuildMessagesUsingDirectImageUrlAsync(this.Provider, chatModel);
-        
-        // Prepare the DeepSeek HTTP chat request:
-        var deepSeekChatRequest = JsonSerializer.Serialize(new ChatCompletionAPIRequest
-        {
-            Model = chatModel.Id,
-            
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..messages],
-                
-            Stream = true,
-            AdditionalApiParameters = apiParameters
-        }, JSON_SERIALIZER_OPTIONS);
+        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>(
+                           "DeepSeek",
+                           chatModel,
+                           chatThread,
+                           settingsManager,
+                           async (systemPrompt, apiParameters) =>
+                           {
+                               // Build the list of messages:
+                               var messages = await chatThread.Blocks.BuildMessagesUsingDirectImageUrlAsync(this.Provider, chatModel);
 
-        async Task<HttpRequestMessage> RequestBuilder()
-        {
-            // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
+                               return new ChatCompletionAPIRequest
+                               {
+                                   Model = chatModel.Id,
 
-            // Set the authorization header:
-            request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
+                                   // Build the messages:
+                                   // - First of all the system prompt
+                                   // - Then none-empty user and AI messages
+                                   Messages = [systemPrompt, ..messages],
 
-            // Set the content:
-            request.Content = new StringContent(deepSeekChatRequest, Encoding.UTF8, "application/json");
-            return request;
-        }
-        
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>("DeepSeek", RequestBuilder, token))
+                                   Stream = true,
+                                   AdditionalApiParameters = apiParameters
+                               };
+                           },
+                           token: token))
             yield return content;
     }
 
@@ -94,54 +72,38 @@ public sealed class ProviderDeepSeek() : BaseProvider(LLMProviders.DEEP_SEEK, "h
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         return this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
 
     #endregion
 
-    private async Task<IEnumerable<Model>> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
+    private Task<ModelLoadResult> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
     {
-        var secretKey = apiKeyProvisional switch
-        {
-            not null => apiKeyProvisional,
-            _ => await RUST_SERVICE.GetAPIKey(this, storeType) switch
-            {
-                { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
-                _ => null,
-            }
-        };
-
-        if (secretKey is null)
-            return [];
-        
-        using var request = new HttpRequestMessage(HttpMethod.Get, "models");
-        request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
-
-        using var response = await this.httpClient.SendAsync(request, token);
-        if(!response.IsSuccessStatusCode)
-            return [];
-
-        var modelResponse = await response.Content.ReadFromJsonAsync<ModelsResponse>(token);
-        return modelResponse.Data;
+        return this.LoadModelsResponse<ModelsResponse>(
+            storeType,
+            "models",
+            modelResponse => modelResponse.Data,
+            token,
+            apiKeyProvisional);
     }
 }

app/MindWork AI Studio/Provider/Fireworks/ChatRequest.cs

@@ -1,20 +0,0 @@
-using System.Text.Json.Serialization;
-
-namespace AIStudio.Provider.Fireworks;
-
-/// <summary>
-/// The Fireworks chat request model.
-/// </summary>
-/// <param name="Model">Which model to use for chat completion.</param>
-/// <param name="Messages">The chat messages.</param>
-/// <param name="Stream">Whether to stream the chat completion.</param>
-public readonly record struct ChatRequest(
-    string Model,
-    IList<IMessageBase> Messages,
-    bool Stream
-)
-{
-    // Attention: The "required" modifier is not supported for [JsonExtensionData].
-    [JsonExtensionData]
-    public IDictionary<string, object> AdditionalApiParameters { get; init; } = new Dictionary<string, object>();
-}

app/MindWork AI Studio/Provider/Fireworks/ProviderFireworks.cs

@@ -1,7 +1,4 @@
-using System.Net.Http.Headers;
 using System.Runtime.CompilerServices;
-using System.Text;
-using System.Text.Json;
 
 using AIStudio.Chat;
 using AIStudio.Provider.OpenAI;
@@ -21,56 +18,37 @@ public class ProviderFireworks() : BaseProvider(LLMProviders.FIREWORKS, "https:/
     /// <inheritdoc />
     public override string InstanceName { get; set; } = "Fireworks.ai";
 
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => false;
+
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
-        // Get the API key:
-        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, SecretStoreType.LLM_PROVIDER);
-        if(!requestedSecret.Success)
-            yield break;
+        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ResponseStreamLine, ChatCompletionAnnotationStreamLine>(
+                           "Fireworks",
+                           chatModel,
+                           chatThread,
+                           settingsManager,
+                           async (systemPrompt, apiParameters) =>
+                           {
+                               // Build the list of messages:
+                               var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
 
-        // Prepare the system prompt:
-        var systemPrompt = new TextMessage
-        {
-            Role = "system",
-            Content = chatThread.PrepareSystemPrompt(settingsManager),
-        };
-        
-        // Parse the API parameters:
-        var apiParameters = this.ParseAdditionalApiParameters();
-        
-        // Build the list of messages:
-        var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
-        
-        // Prepare the Fireworks HTTP chat request:
-        var fireworksChatRequest = JsonSerializer.Serialize(new ChatRequest
-        {
-            Model = chatModel.Id,
-            
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..messages],
-            
-            // Right now, we only support streaming completions:
-            Stream = true,
-            AdditionalApiParameters = apiParameters
-        }, JSON_SERIALIZER_OPTIONS);
+                               return new ChatCompletionAPIRequest
+                               {
+                                   Model = chatModel.Id,
 
-        async Task<HttpRequestMessage> RequestBuilder()
-        {
-            // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
+                                   // Build the messages:
+                                   // - First of all the system prompt
+                                   // - Then none-empty user and AI messages
+                                   Messages = [systemPrompt, ..messages],
 
-            // Set the authorization header:
-            request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
-
-            // Set the content:
-            request.Content = new StringContent(fireworksChatRequest, Encoding.UTF8, "application/json");
-            return request;
-        }
-        
-        await foreach (var content in this.StreamChatCompletionInternal<ResponseStreamLine, ChatCompletionAnnotationStreamLine>("Fireworks", RequestBuilder, token))
+                                   // Right now, we only support streaming completions:
+                                   Stream = true,
+                                   AdditionalApiParameters = apiParameters
+                               };
+                           },
+                           token: token))
             yield return content;
     }
 
@@ -96,34 +74,33 @@ public class ProviderFireworks() : BaseProvider(LLMProviders.FIREWORKS, "https:/
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         // Source: https://docs.fireworks.ai/api-reference/audio-transcriptions#param-model
-        return Task.FromResult<IEnumerable<Model>>(
-            new List<Model>
-            {
-                new("whisper-v3", "Whisper v3"),
-                // new("whisper-v3-turbo", "Whisper v3 Turbo"), // does not work
-            });
+        return Task.FromResult(ModelLoadResult.FromModels(
+        [
+            new Model("whisper-v3", "Whisper v3"),
+            // new("whisper-v3-turbo", "Whisper v3 Turbo"), // does not work
+        ]));
     }
     
     #endregion
-}
+}

app/MindWork AI Studio/Provider/GWDG/ProviderGWDG.cs

@@ -1,7 +1,4 @@
-using System.Net.Http.Headers;
-using System.Runtime.CompilerServices;
-using System.Text;
-using System.Text.Json;
+using System.Runtime.CompilerServices;
 
 using AIStudio.Chat;
 using AIStudio.Provider.OpenAI;
@@ -20,56 +17,37 @@ public sealed class ProviderGWDG() : BaseProvider(LLMProviders.GWDG, "https://ch
 
     /// <inheritdoc />
     public override string InstanceName { get; set; } = "GWDG SAIA";
+
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => true;
     
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
-        // Get the API key:
-        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, SecretStoreType.LLM_PROVIDER);
-        if(!requestedSecret.Success)
-            yield break;
-        
-        // Prepare the system prompt:
-        var systemPrompt = new TextMessage
-        {
-            Role = "system",
-            Content = chatThread.PrepareSystemPrompt(settingsManager),
-        };
-        
-        // Parse the API parameters:
-        var apiParameters = this.ParseAdditionalApiParameters();
-        
-        // Build the list of messages:
-        var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
-        
-        // Prepare the GWDG HTTP chat request:
-        var gwdgChatRequest = JsonSerializer.Serialize(new ChatCompletionAPIRequest
-        {
-            Model = chatModel.Id,
-            
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..messages],
-                
-            Stream = true,
-            AdditionalApiParameters = apiParameters
-        }, JSON_SERIALIZER_OPTIONS);
+        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>(
+                           "GWDG",
+                           chatModel,
+                           chatThread,
+                           settingsManager,
+                           async (systemPrompt, apiParameters) =>
+                           {
+                               // Build the list of messages:
+                               var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
 
-        async Task<HttpRequestMessage> RequestBuilder()
-        {
-            // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
+                               return new ChatCompletionAPIRequest
+                               {
+                                   Model = chatModel.Id,
 
-            // Set the authorization header:
-            request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
+                                   // Build the messages:
+                                   // - First of all the system prompt
+                                   // - Then none-empty user and AI messages
+                                   Messages = [systemPrompt, ..messages],
 
-            // Set the content:
-            request.Content = new StringContent(gwdgChatRequest, Encoding.UTF8, "application/json");
-            return request;
-        }
-        
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>("GWDG", RequestBuilder, token))
+                                   Stream = true,
+                                   AdditionalApiParameters = apiParameters
+                               };
+                           },
+                           token: token))
             yield return content;
     }
 
@@ -95,61 +73,55 @@ public sealed class ProviderGWDG() : BaseProvider(LLMProviders.GWDG, "https://ch
     }
 
     /// <inheritdoc />
-    public override async Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        var models = await this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
-        return models.Where(model => !model.Id.StartsWith("e5-mistral-7b-instruct", StringComparison.InvariantCultureIgnoreCase));
+        var result = await this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
+        return result with
+        {
+            Models = [..result.Models.Where(model => !model.Id.StartsWith("e5-mistral-7b-instruct", StringComparison.InvariantCultureIgnoreCase))]
+        };
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override async Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        var models = await this.LoadModels(SecretStoreType.EMBEDDING_PROVIDER, token, apiKeyProvisional);
-        return models.Where(model => model.Id.StartsWith("e5-", StringComparison.InvariantCultureIgnoreCase));
+        var result = await this.LoadModels(SecretStoreType.EMBEDDING_PROVIDER, token, apiKeyProvisional);
+        return result with
+        {
+            Models = [..result.Models.Where(model => model.Id.StartsWith("e5-", StringComparison.InvariantCultureIgnoreCase))]
+        };
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         // Source: https://docs.hpc.gwdg.de/services/saia/index.html#voice-to-text
-        return Task.FromResult<IEnumerable<Model>>(
-            new List<Model>
-            {
-                new("whisper-large-v2", "Whisper v2 Large"),
-            });
+        return Task.FromResult(ModelLoadResult.FromModels(
+        [
+            new Model("whisper-large-v2", "Whisper v2 Large"),
+        ]));
     }
     
     #endregion
 
-    private async Task<IEnumerable<Model>> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
+    private async Task<ModelLoadResult> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
     {
-        var secretKey = apiKeyProvisional switch
-        {
-            not null => apiKeyProvisional,
-            _ => await RUST_SERVICE.GetAPIKey(this, storeType) switch
-            {
-                { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
-                _ => null,
-            }
-        };
+        var result = await this.LoadModelsResponse<ModelsResponse>(
+            storeType,
+            "models",
+            modelResponse => modelResponse.Data,
+            token,
+            apiKeyProvisional);
 
-        if (secretKey is null)
-            return [];
-        
-        using var request = new HttpRequestMessage(HttpMethod.Get, "models");
-        request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
+        if (!result.Success)
+            LOGGER.LogWarning("Failed to load models for provider {ProviderId}. FailureReason: {FailureReason}. TechnicalDetails: {TechnicalDetails}", this.Id, result.FailureReason, result.TechnicalDetails);
 
-        using var response = await this.httpClient.SendAsync(request, token);
-        if(!response.IsSuccessStatusCode)
-            return [];
-
-        var modelResponse = await response.Content.ReadFromJsonAsync<ModelsResponse>(token);
-        return modelResponse.Data;
+        return result;
     }
-}
+}

app/MindWork AI Studio/Provider/Google/ChatRequest.cs

@@ -1,20 +0,0 @@
-using System.Text.Json.Serialization;
-
-namespace AIStudio.Provider.Google;
-
-/// <summary>
-/// The Google chat request model.
-/// </summary>
-/// <param name="Model">Which model to use for chat completion.</param>
-/// <param name="Messages">The chat messages.</param>
-/// <param name="Stream">Whether to stream the chat completion.</param>
-public readonly record struct ChatRequest(
-    string Model,
-    IList<IMessageBase> Messages,
-    bool Stream
-)
-{
-    // Attention: The "required" modifier is not supported for [JsonExtensionData].
-    [JsonExtensionData]
-    public IDictionary<string, object> AdditionalApiParameters { get; init; } = new Dictionary<string, object>();
-}

app/MindWork AI Studio/Provider/Google/ProviderGoogle.cs

@@ -1,4 +1,3 @@
-using System.Net.Http.Headers;
 using System.Runtime.CompilerServices;
 using System.Text;
 using System.Text.Json;
@@ -21,56 +20,37 @@ public class ProviderGoogle() : BaseProvider(LLMProviders.GOOGLE, "https://gener
     /// <inheritdoc />
     public override string InstanceName { get; set; } = "Google Gemini";
 
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => true;
+
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
-        // Get the API key:
-        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, SecretStoreType.LLM_PROVIDER);
-        if(!requestedSecret.Success)
-            yield break;
+        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>(
+                           "Google",
+                           chatModel,
+                           chatThread,
+                           settingsManager,
+                           async (systemPrompt, apiParameters) =>
+                           {
+                               // Build the list of messages:
+                               var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
 
-        // Prepare the system prompt:
-        var systemPrompt = new TextMessage
-        {
-            Role = "system",
-            Content = chatThread.PrepareSystemPrompt(settingsManager),
-        };
-        
-        // Parse the API parameters:
-        var apiParameters = this.ParseAdditionalApiParameters();
-        
-        // Build the list of messages:
-        var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
-        
-        // Prepare the Google HTTP chat request:
-        var geminiChatRequest = JsonSerializer.Serialize(new ChatRequest
-        {
-            Model = chatModel.Id,
-            
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..messages],
-            
-            // Right now, we only support streaming completions:
-            Stream = true,
-            AdditionalApiParameters = apiParameters
-        }, JSON_SERIALIZER_OPTIONS);
+                               return new ChatCompletionAPIRequest
+                               {
+                                   Model = chatModel.Id,
 
-        async Task<HttpRequestMessage> RequestBuilder()
-        {
-            // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
+                                   // Build the messages:
+                                   // - First of all the system prompt
+                                   // - Then none-empty user and AI messages
+                                   Messages = [systemPrompt, ..messages],
 
-            // Set the authorization header:
-            request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
-
-            // Set the content:
-            request.Content = new StringContent(geminiChatRequest, Encoding.UTF8, "application/json");
-            return request;
-        }
-        
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>("Google", RequestBuilder, token))
+                                   // Right now, we only support streaming completions:
+                                   Stream = true,
+                                   AdditionalApiParameters = apiParameters
+                               };
+                           },
+                           token: token))
             yield return content;
     }
 
@@ -129,7 +109,7 @@ public class ProviderGoogle() : BaseProvider(LLMProviders.GOOGLE, "https://gener
             // Set the content:
             request.Content = new StringContent(embeddingRequest, Encoding.UTF8, "application/json");
             
-            using var response = await this.httpClient.SendAsync(request, token);
+            using var response = await this.HttpClient.SendAsync(request, token);
             var responseBody = await response.Content.ReadAsStringAsync(token);
         
             if (!response.IsSuccessStatusCode)
@@ -161,80 +141,64 @@ public class ProviderGoogle() : BaseProvider(LLMProviders.GOOGLE, "https://gener
     }
 
     /// <inheritdoc />
-    public override async Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        var models = await this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
-        return models.Where(model =>
-                model.Id.StartsWith("gemini-", StringComparison.OrdinalIgnoreCase) &&
-                !this.IsEmbeddingModel(model.Id))
-            .Select(this.WithDisplayNameFallback);
+        var result = await this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
+        return result with
+        {
+            Models =
+            [
+                ..result.Models.Where(model =>
+                        model.Id.StartsWith("gemini-", StringComparison.OrdinalIgnoreCase) &&
+                        !this.IsEmbeddingModel(model.Id))
+                    .Select(this.WithDisplayNameFallback)
+            ]
+        };
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
 
-    public override async Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        var models = await this.LoadModels(SecretStoreType.EMBEDDING_PROVIDER, token, apiKeyProvisional);
-        return models.Where(model => this.IsEmbeddingModel(model.Id))
-            .Select(this.WithDisplayNameFallback);
+        var result = await this.LoadModels(SecretStoreType.EMBEDDING_PROVIDER, token, apiKeyProvisional);
+        return result with
+        {
+            Models =
+            [
+                ..result.Models.Where(model => this.IsEmbeddingModel(model.Id))
+                    .Select(this.WithDisplayNameFallback)
+            ]
+        };
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     #endregion
 
-    private async Task<IReadOnlyList<Model>> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
+    private Task<ModelLoadResult> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
     {
-        var secretKey = apiKeyProvisional switch
-        {
-            not null => apiKeyProvisional,
-            _ => await RUST_SERVICE.GetAPIKey(this, storeType) switch
-            {
-                { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
-                _ => null,
-            }
-        };
-
-        if (string.IsNullOrWhiteSpace(secretKey))
-            return [];
-
-        using var request = new HttpRequestMessage(HttpMethod.Get, "models");
-        request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
-        
-        using var response = await this.httpClient.SendAsync(request, token);
-        if(!response.IsSuccessStatusCode)
-        {
-            LOGGER.LogError("Failed to load models with status code {ResponseStatusCode} and body: '{ResponseBody}'.", response.StatusCode, await response.Content.ReadAsStringAsync(token));
-            return [];
-        }
-
-        try
-        {
-            var modelResponse = await response.Content.ReadFromJsonAsync<ModelsResponse>(token);
-            if (modelResponse == default || modelResponse.Data.Count is 0)
-            {
-                LOGGER.LogError("Google model list response did not contain a valid data array.");
-                return [];
-            }
-
-            return modelResponse.Data
+        return this.LoadModelsResponse<ModelsResponse>(
+            storeType,
+            "models",
+            modelResponse => modelResponse.Data
                 .Where(model => !string.IsNullOrWhiteSpace(model.Id))
-                .Select(model => new Model(this.NormalizeModelId(model.Id), model.DisplayName))
-                .ToArray();
-        }
-        catch (Exception e)
-        {
-            LOGGER.LogError("Failed to parse Google model list response: '{Message}'.", e.Message);
-            return [];
-        }
+                .Select(model => new Model(this.NormalizeModelId(model.Id), model.DisplayName)),
+            token,
+            apiKeyProvisional,
+            failureReasonSelector: (response, _) => response.StatusCode switch
+            {
+                System.Net.HttpStatusCode.Forbidden => ModelLoadFailureReason.AUTHENTICATION_OR_PERMISSION_ERROR,
+                System.Net.HttpStatusCode.Unauthorized => ModelLoadFailureReason.INVALID_OR_MISSING_API_KEY,
+                _ => ModelLoadFailureReason.PROVIDER_UNAVAILABLE,
+            });
     }
 
     private bool IsEmbeddingModel(string modelId)
@@ -256,4 +220,4 @@ public class ProviderGoogle() : BaseProvider(LLMProviders.GOOGLE, "https://gener
             ? modelId["models/".Length..]
             : modelId;
     }
-}
+}

app/MindWork AI Studio/Provider/Groq/ChatRequest.cs

@@ -1,22 +0,0 @@
-using System.Text.Json.Serialization;
-
-namespace AIStudio.Provider.Groq;
-
-/// <summary>
-/// The Groq chat request model.
-/// </summary>
-/// <param name="Model">Which model to use for chat completion.</param>
-/// <param name="Messages">The chat messages.</param>
-/// <param name="Stream">Whether to stream the chat completion.</param>
-/// <param name="Seed">The seed for the chat completion.</param>
-public readonly record struct ChatRequest(
-    string Model,
-    IList<IMessageBase> Messages,
-    bool Stream,
-    int Seed
-)
-{
-    // Attention: The "required" modifier is not supported for [JsonExtensionData].
-    [JsonExtensionData]
-    public IDictionary<string, object> AdditionalApiParameters { get; init; } = new Dictionary<string, object>();
-}

app/MindWork AI Studio/Provider/Groq/ProviderGroq.cs

@@ -1,7 +1,4 @@
-using System.Net.Http.Headers;
 using System.Runtime.CompilerServices;
-using System.Text;
-using System.Text.Json;
 
 using AIStudio.Chat;
 using AIStudio.Provider.OpenAI;
@@ -21,56 +18,40 @@ public class ProviderGroq() : BaseProvider(LLMProviders.GROQ, "https://api.groq.
     /// <inheritdoc />
     public override string InstanceName { get; set; } = "Groq";
 
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => true;
+
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
-        // Get the API key:
-        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, SecretStoreType.LLM_PROVIDER);
-        if(!requestedSecret.Success)
-            yield break;
+        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>(
+                           "Groq",
+                           chatModel,
+                           chatThread,
+                           settingsManager,
+                           async (systemPrompt, apiParameters) =>
+                           {
+                               if (TryPopIntParameter(apiParameters, "seed", out var parsedSeed))
+                                   apiParameters["seed"] = parsedSeed;
 
-        // Prepare the system prompt:
-        var systemPrompt = new TextMessage
-        {
-            Role = "system",
-            Content = chatThread.PrepareSystemPrompt(settingsManager),
-        };
-        
-        // Parse the API parameters:
-        var apiParameters = this.ParseAdditionalApiParameters();
-        
-        // Build the list of messages:
-        var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
-        
-        // Prepare the OpenAI HTTP chat request:
-        var groqChatRequest = JsonSerializer.Serialize(new ChatRequest
-        {
-            Model = chatModel.Id,
-            
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..messages],
-            
-            // Right now, we only support streaming completions:
-            Stream = true,
-            AdditionalApiParameters = apiParameters
-        }, JSON_SERIALIZER_OPTIONS);
+                               // Build the list of messages:
+                               var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
 
-        async Task<HttpRequestMessage> RequestBuilder()
-        {
-            // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
+                               return new ChatCompletionAPIRequest
+                               {
+                                   Model = chatModel.Id,
 
-            // Set the authorization header:
-            request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
+                                   // Build the messages:
+                                   // - First of all the system prompt
+                                   // - Then none-empty user and AI messages
+                                   Messages = [systemPrompt, ..messages],
 
-            // Set the content:
-            request.Content = new StringContent(groqChatRequest, Encoding.UTF8, "application/json");
-            return request;
-        }
-        
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>("Groq", RequestBuilder, token))
+                                   // Right now, we only support streaming completions:
+                                   Stream = true,
+                                   AdditionalApiParameters = apiParameters
+                               };
+                           },
+                           token: token))
             yield return content;
     }
 
@@ -95,57 +76,41 @@ public class ProviderGroq() : BaseProvider(LLMProviders.GROQ, "https://api.groq.
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         return this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult<IEnumerable<Model>>([]);
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     #endregion
 
-    private async Task<IEnumerable<Model>> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
+    private Task<ModelLoadResult> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
     {
-        var secretKey = apiKeyProvisional switch
-        {
-            not null => apiKeyProvisional,
-            _ => await RUST_SERVICE.GetAPIKey(this, storeType) switch
-            {
-                { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
-                _ => null,
-            }
-        };
-
-        if (secretKey is null)
-            return [];
-        
-        using var request = new HttpRequestMessage(HttpMethod.Get, "models");
-        request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
-
-        using var response = await this.httpClient.SendAsync(request, token);
-        if(!response.IsSuccessStatusCode)
-            return [];
-
-        var modelResponse = await response.Content.ReadFromJsonAsync<ModelsResponse>(token);
-        return modelResponse.Data.Where(n =>
-            !n.Id.StartsWith("whisper-", StringComparison.OrdinalIgnoreCase) &&
-            !n.Id.StartsWith("distil-", StringComparison.OrdinalIgnoreCase) &&
-            !n.Id.Contains("-tts", StringComparison.OrdinalIgnoreCase));
+        return this.LoadModelsResponse<ModelsResponse>(
+            storeType,
+            "models",
+            modelResponse => modelResponse.Data.Where(n =>
+                !n.Id.StartsWith("whisper-", StringComparison.OrdinalIgnoreCase) &&
+                !n.Id.StartsWith("distil-", StringComparison.OrdinalIgnoreCase) &&
+                !n.Id.Contains("-tts", StringComparison.OrdinalIgnoreCase)),
+            token,
+            apiKeyProvisional);
     }
 }

app/MindWork AI Studio/Provider/Helmholtz/ProviderHelmholtz.cs

@@ -1,6 +1,5 @@
 using System.Net.Http.Headers;
 using System.Runtime.CompilerServices;
-using System.Text;
 using System.Text.Json;
 
 using AIStudio.Chat;
@@ -20,56 +19,37 @@ public sealed class ProviderHelmholtz() : BaseProvider(LLMProviders.HELMHOLTZ, "
 
     /// <inheritdoc />
     public override string InstanceName { get; set; } = "Helmholtz Blablador";
+
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => true;
     
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
-        // Get the API key:
-        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, SecretStoreType.LLM_PROVIDER);
-        if(!requestedSecret.Success)
-            yield break;
-        
-        // Prepare the system prompt:
-        var systemPrompt = new TextMessage
-        {
-            Role = "system",
-            Content = chatThread.PrepareSystemPrompt(settingsManager),
-        };
-        
-        // Parse the API parameters:
-        var apiParameters = this.ParseAdditionalApiParameters();
-            
-        // Build the list of messages:
-        var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
-        
-        // Prepare the Helmholtz HTTP chat request:
-        var helmholtzChatRequest = JsonSerializer.Serialize(new ChatCompletionAPIRequest
-        {
-            Model = chatModel.Id,
-            
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..messages],
-                
-            Stream = true,
-            AdditionalApiParameters = apiParameters
-        }, JSON_SERIALIZER_OPTIONS);
+        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>(
+                           "Helmholtz",
+                           chatModel,
+                           chatThread,
+                           settingsManager,
+                           async (systemPrompt, apiParameters) =>
+                           {
+                               // Build the list of messages:
+                               var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
 
-        async Task<HttpRequestMessage> RequestBuilder()
-        {
-            // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
+                               return new ChatCompletionAPIRequest
+                               {
+                                   Model = chatModel.Id,
 
-            // Set the authorization header:
-            request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
+                                   // Build the messages:
+                                   // - First of all the system prompt
+                                   // - Then none-empty user and AI messages
+                                   Messages = [systemPrompt, ..messages],
 
-            // Set the content:
-            request.Content = new StringContent(helmholtzChatRequest, Encoding.UTF8, "application/json");
-            return request;
-        }
-        
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>("Helmholtz", RequestBuilder, token))
+                                   Stream = true,
+                                   AdditionalApiParameters = apiParameters
+                               };
+                           },
+                           token: token))
             yield return content;
     }
 
@@ -95,60 +75,81 @@ public sealed class ProviderHelmholtz() : BaseProvider(LLMProviders.HELMHOLTZ, "
     }
 
     /// <inheritdoc />
-    public override async Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        var models = await this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
-        return models.Where(model => !model.Id.StartsWith("text-", StringComparison.InvariantCultureIgnoreCase) &&
-                                     !model.Id.StartsWith("alias-embedding", StringComparison.InvariantCultureIgnoreCase));
+        var result = await this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
+        return result with
+        {
+            Models =
+            [
+                ..result.Models.Where(model => !model.Id.StartsWith("text-", StringComparison.InvariantCultureIgnoreCase) &&
+                                               !model.Id.Contains("-embedding", StringComparison.InvariantCultureIgnoreCase)
+                                               )
+            ]
+        };
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override async Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        var models = await this.LoadModels(SecretStoreType.EMBEDDING_PROVIDER, token, apiKeyProvisional);
-        return models.Where(model => 
-            model.Id.StartsWith("alias-embedding", StringComparison.InvariantCultureIgnoreCase) ||
-            model.Id.StartsWith("text-", StringComparison.InvariantCultureIgnoreCase) ||
-            model.Id.Contains("gritlm", StringComparison.InvariantCultureIgnoreCase));
+        var result = await this.LoadModels(SecretStoreType.EMBEDDING_PROVIDER, token, apiKeyProvisional);
+        return result with
+        {
+            Models =
+            [
+                ..result.Models.Where(model =>
+                    model.Id.Contains("-embedding", StringComparison.InvariantCultureIgnoreCase) ||
+                    model.Id.StartsWith("text-", StringComparison.InvariantCultureIgnoreCase) ||
+                    model.Id.Contains("gritlm", StringComparison.InvariantCultureIgnoreCase))
+            ]
+        };
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     #endregion
 
-    private async Task<IEnumerable<Model>> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
+    private async Task<ModelLoadResult> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
     {
-        var secretKey = apiKeyProvisional switch
-        {
-            not null => apiKeyProvisional,
-            _ => await RUST_SERVICE.GetAPIKey(this, storeType) switch
-            {
-                { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
-                _ => null,
-            }
-        };
+        var secretKey = await this.GetModelLoadingSecretKey(storeType, apiKeyProvisional);
+        if (string.IsNullOrWhiteSpace(secretKey))
+            return FailedModelLoadResult(ModelLoadFailureReason.INVALID_OR_MISSING_API_KEY, "No API key available for model loading.");
 
-        if (secretKey is null)
-            return [];
-        
         using var request = new HttpRequestMessage(HttpMethod.Get, "models");
         request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
 
-        using var response = await this.httpClient.SendAsync(request, token);
-        if(!response.IsSuccessStatusCode)
-            return [];
+        using var response = await this.HttpClient.SendAsync(request, token);
+        var body = await response.Content.ReadAsStringAsync(token);
+        if (!response.IsSuccessStatusCode)
+            return FailedModelLoadResult(GetDefaultModelLoadFailureReason(response), $"Status={(int)response.StatusCode} {response.ReasonPhrase}; Body='{body}'");
 
-        var modelResponse = await response.Content.ReadFromJsonAsync<ModelsResponse>(token);
-        return modelResponse.Data;
+        try
+        {
+            var modelResponse = JsonSerializer.Deserialize<ModelsResponse>(body, JSON_SERIALIZER_OPTIONS);
+            return SuccessfulModelLoadResult(modelResponse.Data);
+        }
+        catch (JsonException e)
+        {
+            if (body.Contains("API key", StringComparison.InvariantCultureIgnoreCase))
+                return FailedModelLoadResult(ModelLoadFailureReason.INVALID_OR_MISSING_API_KEY, body);
+            
+            LOGGER.LogError(e, "Unexpected error while parsing models from Helmholtz API response. Status Code: {StatusCode}. Reason: {ReasonPhrase}. Response Body: '{ResponseBody}'", response.StatusCode, response.ReasonPhrase, body);
+            return FailedModelLoadResult(ModelLoadFailureReason.INVALID_RESPONSE, body);
+        }
+        catch (Exception e)
+        {
+            LOGGER.LogError(e, "Unexpected error while loading models from Helmholtz API. Status Code: {StatusCode}. Reason: {ReasonPhrase}", response.StatusCode, response.ReasonPhrase);
+            return FailedModelLoadResult(ModelLoadFailureReason.UNKNOWN, e.Message);
+        }
     }
 }

app/MindWork AI Studio/Provider/HuggingFace/ProviderHuggingFace.cs

@@ -1,7 +1,4 @@
-using System.Net.Http.Headers;
-using System.Runtime.CompilerServices;
-using System.Text;
-using System.Text.Json;
+using System.Runtime.CompilerServices;
 
 using AIStudio.Chat;
 using AIStudio.Provider.OpenAI;
@@ -26,55 +23,36 @@ public sealed class ProviderHuggingFace : BaseProvider
     /// <inheritdoc />
     public override string InstanceName { get; set; } = "HuggingFace";
 
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => false;
+
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
-        // Get the API key:
-        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, SecretStoreType.LLM_PROVIDER);
-        if(!requestedSecret.Success)
-            yield break;
+        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>(
+                           "HuggingFace",
+                           chatModel,
+                           chatThread,
+                           settingsManager,
+                           async (systemPrompt, apiParameters) =>
+                           {
+                               // Build the list of messages:
+                               var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
 
-        // Prepare the system prompt:
-        var systemPrompt = new TextMessage
-        {
-            Role = "system",
-            Content = chatThread.PrepareSystemPrompt(settingsManager),
-        };
-        
-        // Parse the API parameters:
-        var apiParameters = this.ParseAdditionalApiParameters();
-        
-        // Build the list of messages:
-        var message = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
-        
-        // Prepare the HuggingFace HTTP chat request:
-        var huggingfaceChatRequest = JsonSerializer.Serialize(new ChatCompletionAPIRequest
-        {
-            Model = chatModel.Id,
-            
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..message],
-                
-            Stream = true,
-            AdditionalApiParameters = apiParameters
-        }, JSON_SERIALIZER_OPTIONS);
+                               return new ChatCompletionAPIRequest
+                               {
+                                   Model = chatModel.Id,
 
-        async Task<HttpRequestMessage> RequestBuilder()
-        {
-            // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
+                                   // Build the messages:
+                                   // - First of all the system prompt
+                                   // - Then none-empty user and AI messages
+                                   Messages = [systemPrompt, ..messages],
 
-            // Set the authorization header:
-            request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
-
-            // Set the content:
-            request.Content = new StringContent(huggingfaceChatRequest, Encoding.UTF8, "application/json");
-            return request;
-        }
-        
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>("HuggingFace", RequestBuilder, token))
+                                   Stream = true,
+                                   AdditionalApiParameters = apiParameters
+                               };
+                           },
+                           token: token))
             yield return content;
     }
 
@@ -99,28 +77,28 @@ public sealed class ProviderHuggingFace : BaseProvider
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     #endregion
-}
+}

app/MindWork AI Studio/Provider/IProvider.cs

@@ -34,6 +34,11 @@ public interface IProvider
     /// </summary>
     public string TokenizerPath { get; }
     
+    /// Whether this provider instance can load available models from the backend/API.
+    /// This capability may differ by provider type, host, or modality.
+    /// </summary>
+    public bool HasModelLoadingCapability { get; }
+    
     /// <summary>
     /// Starts a chat completion stream.
     /// </summary>
@@ -81,7 +86,7 @@ public interface IProvider
     /// <param name="apiKeyProvisional">The provisional API key to use. Useful when the user is adding a new provider. When null, the stored API key is used.</param>
     /// <param name="token">The cancellation token.</param>
     /// <returns>The list of text models.</returns>
-    public Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default);
+    public Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default);
 
     /// <summary>
     /// Load all possible image models that can be used with this provider.
@@ -89,7 +94,7 @@ public interface IProvider
     /// <param name="apiKeyProvisional">The provisional API key to use. Useful when the user is adding a new provider. When null, the stored API key is used.</param>
     /// <param name="token">The cancellation token.</param>
     /// <returns>The list of image models.</returns>
-    public Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default);
+    public Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default);
 
     /// <summary>
     /// Load all possible embedding models that can be used with this provider.
@@ -97,7 +102,7 @@ public interface IProvider
     /// <param name="apiKeyProvisional">The provisional API key to use. Useful when the user is adding a new provider. When null, the stored API key is used.</param>
     /// <param name="token">The cancellation token.</param>
     /// <returns>The list of embedding models.</returns>
-    public Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default);
+    public Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default);
     
     /// <summary>
     /// Load all possible transcription models that can be used with this provider.
@@ -105,5 +110,5 @@ public interface IProvider
     /// <param name="apiKeyProvisional">The provisional API key to use. Useful when the user is adding a new provider. When null, the stored API key is used.</param>
     /// <param name="token">>The cancellation token.</param>
     /// <returns>>The list of transcription models.</returns>
-    public Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default);
+    public Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default);
 }

app/MindWork AI Studio/Provider/Mistral/ChatRequest.cs

@@ -1,25 +0,0 @@
-using System.Text.Json.Serialization;
-
-namespace AIStudio.Provider.Mistral;
-
-/// <summary>
-/// The OpenAI chat request model.
-/// </summary>
-/// <param name="Model">Which model to use for chat completion.</param>
-/// <param name="Messages">The chat messages.</param>
-/// <param name="Stream">Whether to stream the chat completion.</param>
-/// <param name="RandomSeed">The seed for the chat completion.</param>
-/// <param name="SafePrompt">Whether to inject a safety prompt before all conversations.</param>
-public readonly record struct ChatRequest(
-    string Model,
-    IList<IMessageBase> Messages,
-    bool Stream,
-    [property: JsonIgnore(Condition = JsonIgnoreCondition.WhenWritingNull)]
-    int? RandomSeed,
-    bool SafePrompt = false
-)
-{
-    // Attention: The "required" modifier is not supported for [JsonExtensionData].
-    [JsonExtensionData]
-    public IDictionary<string, object> AdditionalApiParameters { get; init; } = new Dictionary<string, object>();
-}

app/MindWork AI Studio/Provider/Mistral/ProviderMistral.cs

@@ -1,7 +1,4 @@
-using System.Net.Http.Headers;
 using System.Runtime.CompilerServices;
-using System.Text;
-using System.Text.Json;
 
 using AIStudio.Chat;
 using AIStudio.Provider.OpenAI;
@@ -15,65 +12,49 @@ public sealed class ProviderMistral() : BaseProvider(LLMProviders.MISTRAL, "http
 
     #region Implementation of IProvider
 
+    /// <inheritdoc />
     public override string Id => LLMProviders.MISTRAL.ToName();
     
+    /// <inheritdoc />
     public override string InstanceName { get; set; } = "Mistral";
+    
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => true;
 
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Provider.Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
-        // Get the API key:
-        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, SecretStoreType.LLM_PROVIDER);
-        if(!requestedSecret.Success)
-            yield break;
+        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>(
+                           "Mistral",
+                           chatModel,
+                           chatThread,
+                           settingsManager,
+                           async (systemPrompt, apiParameters) =>
+                           {
+                               if (TryPopBoolParameter(apiParameters, "safe_prompt", out var parsedSafePrompt))
+                                   apiParameters["safe_prompt"] = parsedSafePrompt;
 
-        // Prepare the system prompt:
-        var systemPrompt = new TextMessage
-        {
-            Role = "system",
-            Content = chatThread.PrepareSystemPrompt(settingsManager),
-        };
-        
-        // Parse the API parameters:
-        var apiParameters = this.ParseAdditionalApiParameters();
-        var safePrompt = TryPopBoolParameter(apiParameters, "safe_prompt", out var parsedSafePrompt) && parsedSafePrompt;
-        var randomSeed = TryPopIntParameter(apiParameters, "random_seed", out var parsedRandomSeed) ? parsedRandomSeed : (int?)null;
+                               if (TryPopIntParameter(apiParameters, "random_seed", out var parsedRandomSeed))
+                                   apiParameters["random_seed"] = parsedRandomSeed;
 
-        // Build the list of messages:
-        var messages = await chatThread.Blocks.BuildMessagesUsingDirectImageUrlAsync(this.Provider, chatModel);
-        
-        // Prepare the Mistral HTTP chat request:
-        var mistralChatRequest = JsonSerializer.Serialize(new ChatRequest
-        {
-            Model = chatModel.Id,
-            
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..messages],
-            
-            // Right now, we only support streaming completions:
-            Stream = true,
-            RandomSeed = randomSeed,
-            SafePrompt = safePrompt,
-            AdditionalApiParameters = apiParameters
-        }, JSON_SERIALIZER_OPTIONS);
+                               // Build the list of messages:
+                               var messages = await chatThread.Blocks.BuildMessagesUsingDirectImageUrlAsync(this.Provider, chatModel);
 
-        
-        async Task<HttpRequestMessage> RequestBuilder()
-        {
-            // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
+                               return new ChatCompletionAPIRequest
+                               {
+                                   Model = chatModel.Id,
 
-            // Set the authorization header:
-            request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
+                                   // Build the messages:
+                                   // - First of all the system prompt
+                                   // - Then none-empty user and AI messages
+                                   Messages = [systemPrompt, ..messages],
 
-            // Set the content:
-            request.Content = new StringContent(mistralChatRequest, Encoding.UTF8, "application/json");
-            return request;
-        }
-        
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>("Mistral", RequestBuilder, token))
+                                   // Right now, we only support streaming completions:
+                                   Stream = true,
+                                   AdditionalApiParameters = apiParameters
+                               };
+                           },
+                           token: token))
             yield return content;
     }
 
@@ -100,72 +81,62 @@ public sealed class ProviderMistral() : BaseProvider(LLMProviders.MISTRAL, "http
     }
 
     /// <inheritdoc />
-    public override async Task<IEnumerable<Provider.Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         var modelResponse = await this.LoadModelList(SecretStoreType.LLM_PROVIDER, apiKeyProvisional, token);
-        if(modelResponse == default)
-            return [];
+        if(!modelResponse.Success)
+            return modelResponse;
         
-        return modelResponse.Data.Where(n => 
-            !n.Id.StartsWith("code", StringComparison.OrdinalIgnoreCase) &&
-            !n.Id.Contains("embed", StringComparison.OrdinalIgnoreCase) &&
-            !n.Id.Contains("moderation", StringComparison.OrdinalIgnoreCase))
-            .Select(n => new Provider.Model(n.Id, null));
+        return modelResponse with
+        {
+            Models =
+            [
+                ..modelResponse.Models.Where(n =>
+                    !n.Id.StartsWith("code", StringComparison.OrdinalIgnoreCase) &&
+                    !n.Id.Contains("embed", StringComparison.OrdinalIgnoreCase) &&
+                    !n.Id.Contains("moderation", StringComparison.OrdinalIgnoreCase))
+            ]
+        };
     }
     
     /// <inheritdoc />
-    public override async Task<IEnumerable<Provider.Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         var modelResponse = await this.LoadModelList(SecretStoreType.EMBEDDING_PROVIDER, apiKeyProvisional, token);
-        if(modelResponse == default)
-            return [];
+        if(!modelResponse.Success)
+            return modelResponse;
         
-        return modelResponse.Data.Where(n => n.Id.Contains("embed", StringComparison.InvariantCulture))
-            .Select(n => new Provider.Model(n.Id, null));
+        return modelResponse with
+        {
+            Models = [..modelResponse.Models.Where(n => n.Id.Contains("embed", StringComparison.InvariantCulture))]
+        };
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Provider.Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Provider.Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Provider.Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         // Source: https://docs.mistral.ai/capabilities/audio_transcription
-        return Task.FromResult<IEnumerable<Provider.Model>>(
-            new List<Provider.Model>
-            {
-                new("voxtral-mini-latest", "Voxtral Mini Latest"),
-            });
+        return Task.FromResult(ModelLoadResult.FromModels(
+        [
+            new Provider.Model("voxtral-mini-latest", "Voxtral Mini Latest"),
+        ]));
     }
     
     #endregion
     
-    private async Task<ModelsResponse> LoadModelList(SecretStoreType storeType, string? apiKeyProvisional, CancellationToken token)
+    private Task<ModelLoadResult> LoadModelList(SecretStoreType storeType, string? apiKeyProvisional, CancellationToken token)
     {
-        var secretKey = apiKeyProvisional switch
-        {
-            not null => apiKeyProvisional,
-            _ => await RUST_SERVICE.GetAPIKey(this, storeType) switch
-            {
-                { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
-                _ => null,
-            }
-        };
-
-        if (secretKey is null)
-            return default;
-        
-        using var request = new HttpRequestMessage(HttpMethod.Get, "models");
-        request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
-
-        using var response = await this.httpClient.SendAsync(request, token);
-        if(!response.IsSuccessStatusCode)
-            return default;
-
-        var modelResponse = await response.Content.ReadFromJsonAsync<ModelsResponse>(token);
-        return modelResponse;
+        return this.LoadModelsResponse<ModelsResponse>(
+            storeType,
+            "models",
+            modelResponse => modelResponse.Data.Select(n => new Provider.Model(n.Id, null)),
+            token,
+            apiKeyProvisional);
     }
-}
+}

app/MindWork AI Studio/Provider/ModelLoadFailureReason.cs

@@ -0,0 +1,11 @@
+namespace AIStudio.Provider;
+
+public enum ModelLoadFailureReason
+{
+    NONE,
+    INVALID_OR_MISSING_API_KEY,
+    AUTHENTICATION_OR_PERMISSION_ERROR,
+    PROVIDER_UNAVAILABLE,
+    INVALID_RESPONSE,
+    UNKNOWN,
+}

app/MindWork AI Studio/Provider/ModelLoadFailureReasonExtensions.cs

@@ -0,0 +1,19 @@
+using AIStudio.Tools.PluginSystem;
+
+namespace AIStudio.Provider;
+
+public static class ModelLoadFailureReasonExtensions
+{
+    private static string TB(string fallbackEN) => I18N.I.T(fallbackEN, typeof(ModelLoadFailureReasonExtensions).Namespace, nameof(ModelLoadFailureReasonExtensions));
+
+    public static string ToUserMessage(this ModelLoadFailureReason failureReason, string providerName) => failureReason switch
+    {
+        ModelLoadFailureReason.INVALID_OR_MISSING_API_KEY => string.Format(TB("We could not load models from '{0}'. The API key is probably missing, invalid, or expired."), providerName),
+        ModelLoadFailureReason.AUTHENTICATION_OR_PERMISSION_ERROR => string.Format(TB("We could not load models from '{0}'. The account or API key does not have the required permissions."), providerName),
+        ModelLoadFailureReason.PROVIDER_UNAVAILABLE => string.Format(TB("We could not load models from '{0}' because the provider is currently unavailable or could not be reached."), providerName),
+        ModelLoadFailureReason.INVALID_RESPONSE => string.Format(TB("We could not load models from '{0}' because the provider returned an unexpected response."), providerName),
+        ModelLoadFailureReason.UNKNOWN => string.Format(TB("We could not load models from '{0}' due to an unknown error."), providerName),
+        
+        _ => string.Empty,
+    };
+}

app/MindWork AI Studio/Provider/ModelLoadResult.cs

@@ -0,0 +1,19 @@
+namespace AIStudio.Provider;
+
+public sealed record ModelLoadResult(
+    IReadOnlyList<Model> Models,
+    ModelLoadFailureReason FailureReason = ModelLoadFailureReason.NONE,
+    string? TechnicalDetails = null)
+{
+    public bool Success => this.FailureReason is ModelLoadFailureReason.NONE;
+
+    public static ModelLoadResult FromModels(IEnumerable<Model> models)
+    {
+        return new([..models]);
+    }
+
+    public static ModelLoadResult Failure(ModelLoadFailureReason failureReason, string? technicalDetails = null)
+    {
+        return new([], failureReason, technicalDetails);
+    }
+}

app/MindWork AI Studio/Provider/NoProvider.cs

@@ -21,13 +21,15 @@ public class NoProvider : IProvider
     /// <inheritdoc />
     public string TokenizerPath { get; init; } = string.Empty;
 
-    public Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default) => Task.FromResult<IEnumerable<Model>>([]);
+    public bool HasModelLoadingCapability => false;
 
-    public Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default) => Task.FromResult<IEnumerable<Model>>([]);
+    public Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default) => Task.FromResult(ModelLoadResult.FromModels([]));
+
+    public Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default) => Task.FromResult(ModelLoadResult.FromModels([]));
     
-    public Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default) => Task.FromResult<IEnumerable<Model>>([]);
+    public Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default) => Task.FromResult(ModelLoadResult.FromModels([]));
     
-    public Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default) => Task.FromResult<IEnumerable<Model>>([]);
+    public Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default) => Task.FromResult(ModelLoadResult.FromModels([]));
 
     public async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatChatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {

app/MindWork AI Studio/Provider/OpenAI/ProviderOpenAI.cs

@@ -23,6 +23,9 @@ public sealed class ProviderOpenAI() : BaseProvider(LLMProviders.OPEN_AI, "https
     /// <inheritdoc />
     public override string InstanceName { get; set; } = "OpenAI";
 
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => true;
+
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
@@ -79,9 +82,9 @@ public sealed class ProviderOpenAI() : BaseProvider(LLMProviders.OPEN_AI, "https
         //
         // Prepare the tools we want to use:
         //
-        IList<Tool> tools = modelCapabilities.Contains(Capability.WEB_SEARCH) switch
+        IList<ProviderTool> providerTools = modelCapabilities.Contains(Capability.WEB_SEARCH) switch
         {
-            true => [ Tools.WEB_SEARCH ],
+            true => [ ProviderTools.WEB_SEARCH ],
             _ => []
         };
         
@@ -178,7 +181,7 @@ public sealed class ProviderOpenAI() : BaseProvider(LLMProviders.OPEN_AI, "https
                 Store = false,
                 
                 // Tools we want to use:
-                Tools = tools,
+                ProviderTools = providerTools,
                 
                 // Additional API parameters:
                 AdditionalApiParameters = apiParameters
@@ -233,61 +236,57 @@ public sealed class ProviderOpenAI() : BaseProvider(LLMProviders.OPEN_AI, "https
     }
 
     /// <inheritdoc />
-    public override async Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        var models = await this.LoadModels(SecretStoreType.LLM_PROVIDER, ["chatgpt-", "gpt-", "o1-", "o3-", "o4-"], token, apiKeyProvisional);
-        return models.Where(model => !model.Id.Contains("image", StringComparison.OrdinalIgnoreCase) &&
-                                     !model.Id.Contains("realtime", StringComparison.OrdinalIgnoreCase) &&
-                                     !model.Id.Contains("audio", StringComparison.OrdinalIgnoreCase) &&
-                                     !model.Id.Contains("tts", StringComparison.OrdinalIgnoreCase) &&
-                                     !model.Id.Contains("transcribe", StringComparison.OrdinalIgnoreCase));
+        var result = await this.LoadModels(SecretStoreType.LLM_PROVIDER, ["chatgpt-", "gpt-", "o1-", "o3-", "o4-"], token, apiKeyProvisional);
+        return result with
+        {
+            Models =
+            [
+                ..result.Models.Where(model => !model.Id.Contains("image", StringComparison.OrdinalIgnoreCase) &&
+                                               !model.Id.Contains("realtime", StringComparison.OrdinalIgnoreCase) &&
+                                               !model.Id.Contains("audio", StringComparison.OrdinalIgnoreCase) &&
+                                               !model.Id.Contains("tts", StringComparison.OrdinalIgnoreCase) &&
+                                               !model.Id.Contains("transcribe", StringComparison.OrdinalIgnoreCase))
+            ]
+        };
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         return this.LoadModels(SecretStoreType.IMAGE_PROVIDER, ["dall-e-", "gpt-image"], token, apiKeyProvisional);
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         return this.LoadModels(SecretStoreType.EMBEDDING_PROVIDER, ["text-embedding-"], token, apiKeyProvisional);
     }
     
     /// <inheritdoc />
-    public override async Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        var models = await this.LoadModels(SecretStoreType.TRANSCRIPTION_PROVIDER, ["whisper-", "gpt-"], token, apiKeyProvisional);
-        return models.Where(model => model.Id.StartsWith("whisper-", StringComparison.InvariantCultureIgnoreCase) ||
-                                     model.Id.Contains("-transcribe", StringComparison.InvariantCultureIgnoreCase));
+        var result = await this.LoadModels(SecretStoreType.TRANSCRIPTION_PROVIDER, ["whisper-", "gpt-"], token, apiKeyProvisional);
+        return result with
+        {
+            Models =
+            [
+                ..result.Models.Where(model => model.Id.StartsWith("whisper-", StringComparison.InvariantCultureIgnoreCase) ||
+                                               model.Id.Contains("-transcribe", StringComparison.InvariantCultureIgnoreCase))
+            ]
+        };
     }
     
     #endregion
 
-    private async Task<IEnumerable<Model>> LoadModels(SecretStoreType storeType, string[] prefixes, CancellationToken token, string? apiKeyProvisional = null)
+    private Task<ModelLoadResult> LoadModels(SecretStoreType storeType, string[] prefixes, CancellationToken token, string? apiKeyProvisional = null)
     {
-        var secretKey = apiKeyProvisional switch
-        {
-            not null => apiKeyProvisional,
-            _ => await RUST_SERVICE.GetAPIKey(this, storeType) switch
-            {
-                { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
-                _ => null,
-            }
-        };
-
-        if (secretKey is null)
-            return [];
-        
-        using var request = new HttpRequestMessage(HttpMethod.Get, "models");
-        request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
-
-        using var response = await this.httpClient.SendAsync(request, token);
-        if(!response.IsSuccessStatusCode)
-            return [];
-
-        var modelResponse = await response.Content.ReadFromJsonAsync<ModelsResponse>(token);
-        return modelResponse.Data.Where(model => prefixes.Any(prefix => model.Id.StartsWith(prefix, StringComparison.InvariantCulture)));
+        return this.LoadModelsResponse<ModelsResponse>(
+            storeType,
+            "models",
+            modelResponse => modelResponse.Data.Where(model => prefixes.Any(prefix => model.Id.StartsWith(prefix, StringComparison.InvariantCulture))),
+            token,
+            apiKeyProvisional);
     }
 }

app/MindWork AI Studio/Provider/OpenAI/ProviderTool.cs

@@ -1,7 +1,7 @@
 namespace AIStudio.Provider.OpenAI;
 
 /// <summary>
-/// Represents a tool used by the AI model.
+/// Represents a tool executed on the provider side.
 /// </summary>
 /// <remarks>
 /// Right now, only our OpenAI provider is using tools. Thus, this class is located in the
@@ -9,4 +9,4 @@ namespace AIStudio.Provider.OpenAI;
 /// be moved into the provider namespace.
 /// </remarks>
 /// <param name="Type">The type of the tool.</param>
-public record Tool(string Type);
+public record ProviderTool(string Type);

app/MindWork AI Studio/Provider/OpenAI/ProviderTools.cs

@@ -1,14 +1,14 @@
 namespace AIStudio.Provider.OpenAI;
 
 /// <summary>
-/// Known tools for LLM providers.
+/// Known provider-side tools for LLM providers.
 /// </summary>
 /// <remarks>
 /// Right now, only our OpenAI provider is using tools. Thus, this class is located in the
 /// OpenAI namespace. In the future, when other providers also support tools, this class can
 /// be moved into the provider namespace.
 /// </remarks>
-public static class Tools
+public static class ProviderTools
 {
-    public static readonly Tool WEB_SEARCH = new("web_search");
-}
+    public static readonly ProviderTool WEB_SEARCH = new("web_search");
+}

app/MindWork AI Studio/Provider/OpenAI/ResponsesAPIRequest.cs

@@ -9,13 +9,13 @@ namespace AIStudio.Provider.OpenAI;
 /// <param name="Input">The chat messages.</param>
 /// <param name="Stream">Whether to stream the response.</param>
 /// <param name="Store">Whether to store the response on the server (usually OpenAI's infrastructure).</param>
-/// <param name="Tools">The tools to use for the request.</param>
+/// <param name="ProviderTools">The provider-side tools to use for the request.</param>
 public record ResponsesAPIRequest(
     string Model,
     IList<IMessageBase> Input,
     bool Stream,
     bool Store,
-    IList<Tool> Tools)
+    [property: JsonPropertyName("tools")] IList<ProviderTool> ProviderTools)
 {
     public ResponsesAPIRequest() : this(string.Empty, [], true, false, [])
     {
@@ -24,4 +24,4 @@ public record ResponsesAPIRequest(
     // Attention: The "required" modifier is not supported for [JsonExtensionData].
     [JsonExtensionData]
     public IDictionary<string, object> AdditionalApiParameters { get; init; } = new Dictionary<string, object>();
-}
+}

app/MindWork AI Studio/Provider/OpenRouter/ProviderOpenRouter.cs

@@ -1,7 +1,5 @@
 using System.Net.Http.Headers;
 using System.Runtime.CompilerServices;
-using System.Text;
-using System.Text.Json;
 
 using AIStudio.Chat;
 using AIStudio.Provider.OpenAI;
@@ -24,60 +22,43 @@ public sealed class ProviderOpenRouter() : BaseProvider(LLMProviders.OPEN_ROUTER
     /// <inheritdoc />
     public override string InstanceName { get; set; } = "OpenRouter";
 
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => true;
+
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
-        // Get the API key:
-        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, SecretStoreType.LLM_PROVIDER);
-        if(!requestedSecret.Success)
-            yield break;
+        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>(
+                           "OpenRouter",
+                           chatModel,
+                           chatThread,
+                           settingsManager,
+                           async (systemPrompt, apiParameters) =>
+                           {
+                               // Build the list of messages:
+                               var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
 
-        // Prepare the system prompt:
-        var systemPrompt = new TextMessage
-        {
-            Role = "system",
-            Content = chatThread.PrepareSystemPrompt(settingsManager),
-        };
+                               return new ChatCompletionAPIRequest
+                               {
+                                   Model = chatModel.Id,
 
-        // Parse the API parameters:
-        var apiParameters = this.ParseAdditionalApiParameters();
-        
-        // Build the list of messages:
-        var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
+                                   // Build the messages:
+                                   // - First of all the system prompt
+                                   // - Then none-empty user and AI messages
+                                   Messages = [systemPrompt, ..messages],
 
-        // Prepare the OpenRouter HTTP chat request:
-        var openRouterChatRequest = JsonSerializer.Serialize(new ChatCompletionAPIRequest
-        {
-            Model = chatModel.Id,
-
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..messages],
-
-            // Right now, we only support streaming completions:
-            Stream = true,
-            AdditionalApiParameters = apiParameters
-        }, JSON_SERIALIZER_OPTIONS);
-
-        async Task<HttpRequestMessage> RequestBuilder()
-        {
-            // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
-
-            // Set the authorization header:
-            request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
-            
-            // Set custom headers for project identification:
-            request.Headers.Add("HTTP-Referer", PROJECT_WEBSITE);
-            request.Headers.Add("X-Title", PROJECT_NAME);
-
-            // Set the content:
-            request.Content = new StringContent(openRouterChatRequest, Encoding.UTF8, "application/json");
-            return request;
-        }
-
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>("OpenRouter", RequestBuilder, token))
+                                   // Right now, we only support streaming completions:
+                                   Stream = true,
+                                   AdditionalApiParameters = apiParameters
+                               };
+                           },
+                           headersAction: headers =>
+                           {
+                               // Set custom headers for project identification:
+                               headers.Add("HTTP-Referer", PROJECT_WEBSITE);
+                               headers.Add("X-Title", PROJECT_NAME);
+                           },
+                           token: token))
             yield return content;
     }
 
@@ -103,102 +84,70 @@ public sealed class ProviderOpenRouter() : BaseProvider(LLMProviders.OPEN_ROUTER
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         return this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         return this.LoadEmbeddingModels(token, apiKeyProvisional);
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
 
     #endregion
 
-    private async Task<IEnumerable<Model>> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
+    private Task<ModelLoadResult> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
     {
-        var secretKey = apiKeyProvisional switch
-        {
-            not null => apiKeyProvisional,
-            _ => await RUST_SERVICE.GetAPIKey(this, storeType) switch
+        return this.LoadModelsResponse<OpenRouterModelsResponse>(
+            storeType,
+            "models",
+            modelResponse => modelResponse.Data
+                .Where(n =>
+                    !n.Id.Contains("whisper", StringComparison.OrdinalIgnoreCase) &&
+                    !n.Id.Contains("dall-e", StringComparison.OrdinalIgnoreCase) &&
+                    !n.Id.Contains("tts", StringComparison.OrdinalIgnoreCase) &&
+                    !n.Id.Contains("embedding", StringComparison.OrdinalIgnoreCase) &&
+                    !n.Id.Contains("moderation", StringComparison.OrdinalIgnoreCase) &&
+                    !n.Id.Contains("stable-diffusion", StringComparison.OrdinalIgnoreCase) &&
+                    !n.Id.Contains("flux", StringComparison.OrdinalIgnoreCase) &&
+                    !n.Id.Contains("midjourney", StringComparison.OrdinalIgnoreCase))
+                .Select(n => new Model(n.Id, n.Name)),
+            token,
+            apiKeyProvisional,
+            requestConfigurator: (request, secretKey) =>
             {
-                { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
-                _ => null,
-            }
-        };
-
-        if (secretKey is null)
-            return [];
-
-        using var request = new HttpRequestMessage(HttpMethod.Get, "models");
-        request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
-        
-        // Set custom headers for project identification:
-        request.Headers.Add("HTTP-Referer", PROJECT_WEBSITE);
-        request.Headers.Add("X-Title", PROJECT_NAME);
-
-        using var response = await this.httpClient.SendAsync(request, token);
-        if(!response.IsSuccessStatusCode)
-            return [];
-
-        var modelResponse = await response.Content.ReadFromJsonAsync<OpenRouterModelsResponse>(token);
-
-        // Filter out non-text models (image, audio, embedding models) and convert to Model
-        return modelResponse.Data
-            .Where(n =>
-                !n.Id.Contains("whisper", StringComparison.OrdinalIgnoreCase) &&
-                !n.Id.Contains("dall-e", StringComparison.OrdinalIgnoreCase) &&
-                !n.Id.Contains("tts", StringComparison.OrdinalIgnoreCase) &&
-                !n.Id.Contains("embedding", StringComparison.OrdinalIgnoreCase) &&
-                !n.Id.Contains("moderation", StringComparison.OrdinalIgnoreCase) &&
-                !n.Id.Contains("stable-diffusion", StringComparison.OrdinalIgnoreCase) &&
-                !n.Id.Contains("flux", StringComparison.OrdinalIgnoreCase) &&
-                !n.Id.Contains("midjourney", StringComparison.OrdinalIgnoreCase))
-            .Select(n => new Model(n.Id, n.Name));
+                request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
+                request.Headers.Add("HTTP-Referer", PROJECT_WEBSITE);
+                request.Headers.Add("X-Title", PROJECT_NAME);
+            });
     }
 
-    private async Task<IEnumerable<Model>> LoadEmbeddingModels(CancellationToken token, string? apiKeyProvisional = null)
+    private Task<ModelLoadResult> LoadEmbeddingModels(CancellationToken token, string? apiKeyProvisional = null)
     {
-        var secretKey = apiKeyProvisional switch
-        {
-            not null => apiKeyProvisional,
-            _ => await RUST_SERVICE.GetAPIKey(this, SecretStoreType.EMBEDDING_PROVIDER) switch
+        return this.LoadModelsResponse<OpenRouterModelsResponse>(
+            SecretStoreType.EMBEDDING_PROVIDER,
+            "embeddings/models",
+            modelResponse => modelResponse.Data.Select(n => new Model(n.Id, n.Name)),
+            token,
+            apiKeyProvisional,
+            requestConfigurator: (request, secretKey) =>
             {
-                { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
-                _ => null,
-            }
-        };
-
-        if (secretKey is null)
-            return [];
-
-        using var request = new HttpRequestMessage(HttpMethod.Get, "embeddings/models");
-        request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
-        
-        // Set custom headers for project identification:
-        request.Headers.Add("HTTP-Referer", PROJECT_WEBSITE);
-        request.Headers.Add("X-Title", PROJECT_NAME);
-
-        using var response = await this.httpClient.SendAsync(request, token);
-        if(!response.IsSuccessStatusCode)
-            return [];
-
-        var modelResponse = await response.Content.ReadFromJsonAsync<OpenRouterModelsResponse>(token);
-
-        // Convert all embedding models to Model
-        return modelResponse.Data.Select(n => new Model(n.Id, n.Name));
+                request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
+                request.Headers.Add("HTTP-Referer", PROJECT_WEBSITE);
+                request.Headers.Add("X-Title", PROJECT_NAME);
+            });
     }
-}
+}

app/MindWork AI Studio/Provider/Perplexity/ProviderPerplexity.cs

@@ -1,7 +1,4 @@
-using System.Net.Http.Headers;
 using System.Runtime.CompilerServices;
-using System.Text;
-using System.Text.Json;
 
 using AIStudio.Chat;
 using AIStudio.Provider.OpenAI;
@@ -29,55 +26,36 @@ public sealed class ProviderPerplexity() : BaseProvider(LLMProviders.PERPLEXITY,
 
     /// <inheritdoc />
     public override string InstanceName { get; set; } = "Perplexity";
+
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => true;
     
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
-        // Get the API key:
-        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, SecretStoreType.LLM_PROVIDER);
-        if(!requestedSecret.Success)
-            yield break;
-        
-        // Prepare the system prompt:
-        var systemPrompt = new TextMessage
-        {
-            Role = "system",
-            Content = chatThread.PrepareSystemPrompt(settingsManager),
-        };
-        
-        // Parse the API parameters:
-        var apiParameters = this.ParseAdditionalApiParameters();
-        
-        // Build the list of messages:
-        var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
-        
-        // Prepare the Perplexity HTTP chat request:
-        var perplexityChatRequest = JsonSerializer.Serialize(new ChatCompletionAPIRequest
-        {
-            Model = chatModel.Id,
-            
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..messages],
-            Stream = true,
-            AdditionalApiParameters = apiParameters
-        }, JSON_SERIALIZER_OPTIONS);
+        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ResponseStreamLine, NoChatCompletionAnnotationStreamLine>(
+                           "Perplexity",
+                           chatModel,
+                           chatThread,
+                           settingsManager,
+                           async (systemPrompt, apiParameters) =>
+                           {
+                               // Build the list of messages:
+                               var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
 
-        async Task<HttpRequestMessage> RequestBuilder()
-        {
-            // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
+                               return new ChatCompletionAPIRequest
+                               {
+                                   Model = chatModel.Id,
 
-            // Set the authorization header:
-            request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
-
-            // Set the content:
-            request.Content = new StringContent(perplexityChatRequest, Encoding.UTF8, "application/json");
-            return request;
-        }
-        
-        await foreach (var content in this.StreamChatCompletionInternal<ResponseStreamLine, NoChatCompletionAnnotationStreamLine>("Perplexity", RequestBuilder, token))
+                                   // Build the messages:
+                                   // - First of all the system prompt
+                                   // - Then none-empty user and AI messages
+                                   Messages = [systemPrompt, ..messages],
+                                   Stream = true,
+                                   AdditionalApiParameters = apiParameters
+                               };
+                           },
+                           token: token))
             yield return content;
     }
 
@@ -102,30 +80,30 @@ public sealed class ProviderPerplexity() : BaseProvider(LLMProviders.PERPLEXITY,
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         return this.LoadModels();
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     #endregion
 
-    private Task<IEnumerable<Model>> LoadModels() => Task.FromResult<IEnumerable<Model>>(KNOWN_MODELS);
+    private Task<ModelLoadResult> LoadModels() => Task.FromResult(ModelLoadResult.FromModels(KNOWN_MODELS));
 }

app/MindWork AI Studio/Provider/SelfHosted/ChatRequest.cs

@@ -1,20 +0,0 @@
-using System.Text.Json.Serialization;
-
-namespace AIStudio.Provider.SelfHosted;
-
-/// <summary>
-/// The chat request model.
-/// </summary>
-/// <param name="Model">Which model to use for chat completion.</param>
-/// <param name="Messages">The chat messages.</param>
-/// <param name="Stream">Whether to stream the chat completion.</param>
-public readonly record struct ChatRequest(
-    string Model,
-    IList<IMessageBase> Messages,
-    bool Stream
-)
-{
-    // Attention: The "required" modifier is not supported for [JsonExtensionData].
-    [JsonExtensionData]
-    public IDictionary<string, object> AdditionalApiParameters { get; init; } = new Dictionary<string, object>();
-}

app/MindWork AI Studio/Provider/SelfHosted/ProviderSelfHosted.cs

@@ -1,7 +1,5 @@
 using System.Net.Http.Headers;
 using System.Runtime.CompilerServices;
-using System.Text;
-using System.Text.Json;
 
 using AIStudio.Chat;
 using AIStudio.Provider.OpenAI;
@@ -18,65 +16,51 @@ public sealed class ProviderSelfHosted(Host host, string hostname) : BaseProvide
 
     #region Implementation of IProvider
 
+    /// <inheritdoc />
     public override string Id => LLMProviders.SELF_HOSTED.ToName();
     
+    /// <inheritdoc />
     public override string InstanceName { get; set; } = "Self-hosted";
+
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => host is Host.OLLAMA or Host.LM_STUDIO or Host.VLLM;
     
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Provider.Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
-        // Get the API key:
-        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, SecretStoreType.LLM_PROVIDER, isTrying: true);
-        
-        // Prepare the system prompt:
-        var systemPrompt = new TextMessage
-        {
-            Role = "system",
-            Content = chatThread.PrepareSystemPrompt(settingsManager),
-        };
-        
-        // Parse the API parameters:
-        var apiParameters = this.ParseAdditionalApiParameters();
+        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>(
+                           "self-hosted provider",
+                           chatModel,
+                           chatThread,
+                           settingsManager,
+                           async (systemPrompt, apiParameters) =>
+                           {
+                               // Build the list of messages. The image format depends on the host:
+                               // - Ollama uses the direct image URL format: { "type": "image_url", "image_url": "data:..." }
+                               // - LM Studio, vLLM, and llama.cpp use the nested image URL format: { "type": "image_url", "image_url": { "url": "data:..." } }
+                               var messages = host switch
+                               {
+                                   Host.OLLAMA => await chatThread.Blocks.BuildMessagesUsingDirectImageUrlAsync(this.Provider, chatModel),
+                                   _ => await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel),
+                               };
 
-        // Build the list of messages. The image format depends on the host:
-        // - Ollama uses the direct image URL format: { "type": "image_url", "image_url": "data:..." }
-        // - LM Studio, vLLM, and llama.cpp use the nested image URL format: { "type": "image_url", "image_url": { "url": "data:..." } }
-        var messages = host switch
-        {
-            Host.OLLAMA => await chatThread.Blocks.BuildMessagesUsingDirectImageUrlAsync(this.Provider, chatModel),
-            _ => await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel),
-        };
-        
-        // Prepare the OpenAI HTTP chat request:
-        var providerChatRequest = JsonSerializer.Serialize(new ChatRequest
-        {
-            Model = chatModel.Id,
-            
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..messages],
-            
-            // Right now, we only support streaming completions:
-            Stream = true,
-            AdditionalApiParameters = apiParameters
-        }, JSON_SERIALIZER_OPTIONS);
+                               return new ChatCompletionAPIRequest
+                               {
+                                   Model = chatModel.Id,
 
-        async Task<HttpRequestMessage> RequestBuilder()
-        {
-            // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, host.ChatURL());
+                                   // Build the messages:
+                                   // - First of all the system prompt
+                                   // - Then none-empty user and AI messages
+                                   Messages = [systemPrompt, ..messages],
 
-            // Set the authorization header:
-            if (requestedSecret.Success)
-                request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
-
-            // Set the content:
-            request.Content = new StringContent(providerChatRequest, Encoding.UTF8, "application/json");
-            return request;
-        }
-        
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>("self-hosted provider", RequestBuilder, token))
+                                   // Right now, we only support streaming completions:
+                                   Stream = true,
+                                   AdditionalApiParameters = apiParameters
+                               };
+                           },
+                           isTryingSecret: true,
+                           requestPath: host.ChatURL(),
+                           token: token))
             yield return content;
     }
 
@@ -102,7 +86,7 @@ public sealed class ProviderSelfHosted(Host host, string hostname) : BaseProvide
         return await this.PerformStandardTextEmbeddingRequest(requestedSecret, embeddingModel, host, token: token, texts: texts);
     }
     
-    public override async Task<IEnumerable<Provider.Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         try
         {
@@ -111,7 +95,7 @@ public sealed class ProviderSelfHosted(Host host, string hostname) : BaseProvide
                 case Host.LLAMA_CPP:
                     // Right now, llama.cpp only supports one model.
                     // There is no API to list the model(s).
-                    return [ new Provider.Model("as configured by llama.cpp", null) ];
+                    return ModelLoadResult.FromModels([ new Provider.Model("as configured by llama.cpp", null) ]);
             
                 case Host.LM_STUDIO:
                 case Host.OLLAMA:
@@ -119,22 +103,22 @@ public sealed class ProviderSelfHosted(Host host, string hostname) : BaseProvide
                     return await this.LoadModels( SecretStoreType.LLM_PROVIDER, ["embed"], [], token, apiKeyProvisional);
             }
 
-            return [];
+            return ModelLoadResult.FromModels([]);
         }
         catch(Exception e)
         {
             LOGGER.LogError($"Failed to load text models from self-hosted provider: {e.Message}");
-            return [];
+            return ModelLoadResult.Failure(ModelLoadFailureReason.UNKNOWN, e.Message);
         }
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Provider.Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Provider.Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
 
-    public override async Task<IEnumerable<Provider.Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         try
         {
@@ -146,69 +130,61 @@ public sealed class ProviderSelfHosted(Host host, string hostname) : BaseProvide
                     return await this.LoadModels( SecretStoreType.EMBEDDING_PROVIDER, [], ["embed"], token, apiKeyProvisional);
             }
 
-            return [];
+            return ModelLoadResult.FromModels([]);
         }
         catch(Exception e)
         {
             LOGGER.LogError($"Failed to load text models from self-hosted provider: {e.Message}");
-            return [];
+            return ModelLoadResult.Failure(ModelLoadFailureReason.UNKNOWN, e.Message);
         }
     }
     
     /// <inheritdoc />
-    public override async Task<IEnumerable<Provider.Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         try
         {
             switch (host)
             {
                 case Host.WHISPER_CPP:
-                    return new List<Provider.Model>
-                    {
-                        new("loaded-model", TB("Model as configured by whisper.cpp")),
-                    };
+                    return ModelLoadResult.FromModels(
+                    [
+                        new Provider.Model("loaded-model", TB("Model as configured by whisper.cpp")),
+                    ]);
                 
                 case Host.OLLAMA:
                 case Host.VLLM:
                     return await this.LoadModels(SecretStoreType.TRANSCRIPTION_PROVIDER, [], [], token, apiKeyProvisional);
                 
                 default:
-                    return [];
+                    return ModelLoadResult.FromModels([]);
             }
         }
         catch (Exception e)
         {
             LOGGER.LogError($"Failed to load transcription models from self-hosted provider: {e.Message}");
-            return [];
+            return ModelLoadResult.Failure(ModelLoadFailureReason.UNKNOWN, e.Message);
         }
     }
     
     #endregion
 
-    private async Task<IEnumerable<Provider.Model>> LoadModels(SecretStoreType storeType, string[] ignorePhrases, string[] filterPhrases, CancellationToken token, string? apiKeyProvisional = null)
+    private async Task<ModelLoadResult> LoadModels(SecretStoreType storeType, string[] ignorePhrases, string[] filterPhrases, CancellationToken token, string? apiKeyProvisional = null)
     {
-        var secretKey = apiKeyProvisional switch
-        {
-            not null => apiKeyProvisional,
-            _ => await RUST_SERVICE.GetAPIKey(this, storeType, isTrying: true) switch
-            {
-                { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
-                _ => null,
-            }
-        };
+        var secretKey = await this.GetModelLoadingSecretKey(storeType, apiKeyProvisional, true);
                     
         using var lmStudioRequest = new HttpRequestMessage(HttpMethod.Get, "models");
         if(secretKey is not null)
-            lmStudioRequest.Headers.Authorization = new AuthenticationHeaderValue("Bearer", apiKeyProvisional);
+            lmStudioRequest.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
                     
-        using var lmStudioResponse = await this.httpClient.SendAsync(lmStudioRequest, token);
+        using var lmStudioResponse = await this.HttpClient.SendAsync(lmStudioRequest, token);
         if(!lmStudioResponse.IsSuccessStatusCode)
-            return [];
+            return FailedModelLoadResult(GetDefaultModelLoadFailureReason(lmStudioResponse), $"Status={(int)lmStudioResponse.StatusCode} {lmStudioResponse.ReasonPhrase}");
 
         var lmStudioModelResponse = await lmStudioResponse.Content.ReadFromJsonAsync<ModelsResponse>(token);
-        return lmStudioModelResponse.Data.
+        return SuccessfulModelLoadResult(lmStudioModelResponse.Data.
             Where(model => !ignorePhrases.Any(ignorePhrase => model.Id.Contains(ignorePhrase, StringComparison.InvariantCulture)) &&
                            filterPhrases.All( filter => model.Id.Contains(filter, StringComparison.InvariantCulture)))
-            .Select(n => new Provider.Model(n.Id, null));
+            .Select(n => new Provider.Model(n.Id, null)));
     }
 }

app/MindWork AI Studio/Provider/X/ProviderX.cs

@@ -1,7 +1,4 @@
-using System.Net.Http.Headers;
 using System.Runtime.CompilerServices;
-using System.Text;
-using System.Text.Json;
 
 using AIStudio.Chat;
 using AIStudio.Provider.OpenAI;
@@ -21,56 +18,37 @@ public sealed class ProviderX() : BaseProvider(LLMProviders.X, "https://api.x.ai
     /// <inheritdoc />
     public override string InstanceName { get; set; } = "xAI";
 
+    /// <inheritdoc />
+    public override bool HasModelLoadingCapability => true;
+
     /// <inheritdoc />
     public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {
-        // Get the API key:
-        var requestedSecret = await RUST_SERVICE.GetAPIKey(this, SecretStoreType.LLM_PROVIDER);
-        if(!requestedSecret.Success)
-            yield break;
-        
-        // Prepare the system prompt:
-        var systemPrompt = new TextMessage
-        {
-            Role = "system",
-            Content = chatThread.PrepareSystemPrompt(settingsManager),
-        };
-        
-        // Parse the API parameters:
-        var apiParameters = this.ParseAdditionalApiParameters();
-        
-        // Build the list of messages:
-        var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
-        
-        // Prepare the xAI HTTP chat request:
-        var xChatRequest = JsonSerializer.Serialize(new ChatCompletionAPIRequest
-        {
-            Model = chatModel.Id,
-            
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..messages],
-            
-            // Right now, we only support streaming completions:
-            Stream = true,
-            AdditionalApiParameters = apiParameters
-        }, JSON_SERIALIZER_OPTIONS);
+        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>(
+                           "xAI",
+                           chatModel,
+                           chatThread,
+                           settingsManager,
+                           async (systemPrompt, apiParameters) =>
+                           {
+                               // Build the list of messages:
+                               var messages = await chatThread.Blocks.BuildMessagesUsingNestedImageUrlAsync(this.Provider, chatModel);
 
-        async Task<HttpRequestMessage> RequestBuilder()
-        {
-            // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
+                               return new ChatCompletionAPIRequest
+                               {
+                                   Model = chatModel.Id,
 
-            // Set the authorization header:
-            request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
+                                   // Build the messages:
+                                   // - First of all the system prompt
+                                   // - Then none-empty user and AI messages
+                                   Messages = [systemPrompt, ..messages],
 
-            // Set the content:
-            request.Content = new StringContent(xChatRequest, Encoding.UTF8, "application/json");
-            return request;
-        }
-        
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>("xAI", RequestBuilder, token))
+                                   // Right now, we only support streaming completions:
+                                   Stream = true,
+                                   AdditionalApiParameters = apiParameters
+                               };
+                           },
+                           token: token))
             yield return content;
     }
 
@@ -95,67 +73,49 @@ public sealed class ProviderX() : BaseProvider(LLMProviders.X, "https://api.x.ai
     }
     
     /// <inheritdoc />
-    public override async Task<IEnumerable<Model>> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        var models = await this.LoadModels(SecretStoreType.LLM_PROVIDER, ["grok-"], token, apiKeyProvisional);
-        return models.Where(n => !n.Id.Contains("-image", StringComparison.OrdinalIgnoreCase));
+        var result = await this.LoadModels(SecretStoreType.LLM_PROVIDER, ["grok-"], token, apiKeyProvisional);
+        return result with
+        {
+            Models = [..result.Models.Where(n => !n.Id.Contains("-image", StringComparison.OrdinalIgnoreCase))]
+        };
     }
 
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult<IEnumerable<Model>>([]);
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult<IEnumerable<Model>>([]);
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     /// <inheritdoc />
-    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(Enumerable.Empty<Model>());
+        return Task.FromResult(ModelLoadResult.FromModels([]));
     }
     
     #endregion
     
-    private async Task<IEnumerable<Model>> LoadModels(SecretStoreType storeType, string[] prefixes, CancellationToken token, string? apiKeyProvisional = null)
+    private Task<ModelLoadResult> LoadModels(SecretStoreType storeType, string[] prefixes, CancellationToken token, string? apiKeyProvisional = null)
     {
-        var secretKey = apiKeyProvisional switch
-        {
-            not null => apiKeyProvisional,
-            _ => await RUST_SERVICE.GetAPIKey(this, storeType) switch
-            {
-                { Success: true } result => await result.Secret.Decrypt(ENCRYPTION),
-                _ => null,
-            }
-        };
-
-        if (secretKey is null)
-            return [];
-        
-        using var request = new HttpRequestMessage(HttpMethod.Get, "models");
-        request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", secretKey);
-
-        using var response = await this.httpClient.SendAsync(request, token);
-        if(!response.IsSuccessStatusCode)
-            return [];
-
-        var modelResponse = await response.Content.ReadFromJsonAsync<ModelsResponse>(token);
-        
-        //
-        // The API does not return the alias model names, so we have to add them manually:
-        // Right now, the only alias to add is `grok-2-latest`.
-        //
-        return modelResponse.Data.Where(model => prefixes.Any(prefix => model.Id.StartsWith(prefix, StringComparison.InvariantCulture)))
-            .Concat([
-                new Model
-                {
-                    Id = "grok-2-latest",
-                    DisplayName = "Grok 2.0 (latest)",
-                }
-            ]);
+        return this.LoadModelsResponse<ModelsResponse>(
+            storeType,
+            "models",
+            modelResponse => modelResponse.Data.Where(model => prefixes.Any(prefix => model.Id.StartsWith(prefix, StringComparison.InvariantCulture)))
+                .Concat([
+                    new Model
+                    {
+                        Id = "grok-2-latest",
+                        DisplayName = "Grok 2.0 (latest)",
+                    }
+                ]),
+            token,
+            apiKeyProvisional);
     }
 }