Read the context window from a provider's model list

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

@@ -1,3 +1,23 @@
+using System.Text.Json.Serialization;
+
 namespace AIStudio.Provider.SelfHosted;
 
-public readonly record struct Model(string Id, string? Object, string? OwnedBy, ModelArchitecture? Architecture);
+/// <summary>
+/// One model as an OpenAI-compatible engine lists it.
+/// </summary>
+/// <remarks>
+/// The context window is vLLM's addition to that route: it reports the window the operator started
+/// the engine with, which is the one number no rule about the weights could ever know. Ollama,
+/// LM Studio, and llama.cpp answer the same route without it, so it stays unknown there instead of
+/// being guessed.
+///
+/// vLLM calls that field max_model_len, which reads like a limit on the model rather than on a
+/// conversation. The wire keeps their spelling, and this record says what the number means, so that
+/// nobody has to remember the translation while reading the code that uses it.
+/// </remarks>
+/// <param name="Id">The model's ID.</param>
+/// <param name="Object">What kind of thing the entry is. Known value: "model".</param>
+/// <param name="OwnedBy">Who the engine names as the owner of the model.</param>
+/// <param name="Architecture">Which kinds of input and output the model takes, where the engine says.</param>
+/// <param name="ContextWindowTokens">The context window the engine was started with, in tokens, where it says.</param>
+public readonly record struct Model(string Id, string? Object, string? OwnedBy, ModelArchitecture? Architecture, [property: JsonPropertyName("max_model_len")] int? ContextWindowTokens);

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

@@ -3,6 +3,8 @@ using System.Runtime.CompilerServices;
 using System.Text.Json;
 
 using AIStudio.Chat;
+using AIStudio.Models;
+using AIStudio.Models.Live;
 using AIStudio.Provider.OpenAI;
 using AIStudio.Settings;
 using AIStudio.Tools.PluginSystem;
@@ -188,8 +190,23 @@ public sealed class ProviderSelfHosted(Host host, string hostname) : BaseProvide
                 return FailedModelLoadResult(this.GetModelLoadFailureReason(lmStudioResponse, responseBody), $"Status={(int)lmStudioResponse.StatusCode} {lmStudioResponse.ReasonPhrase}; Body='{responseBody}'");
             }
 
-            var lmStudioModelResponse = await lmStudioResponse.Content.ReadFromJsonAsync<ModelsResponse>(token);
+            //
+            // Read with the shared options, the way every other model list of this app is read.
+            // This one route did without them, which quietly cost it every field an engine spells
+            // in snake case: owned_by has been arriving as nothing all along, and the next field
+            // somebody adds here would have gone the same way without anything failing.
+            //
+            var lmStudioModelResponse = await lmStudioResponse.Content.ReadFromJsonAsync<ModelsResponse>(JSON_SERIALIZER_OPTIONS, token);
             var models = lmStudioModelResponse.Data ?? [];
+
+            //
+            // What the engine said about its own models, taken from the whole list rather than
+            // from what is offered below: a model filtered out here as an embedding model is still
+            // a model somebody may have configured this instance with, and this list is the only
+            // place its window is ever stated.
+            //
+            ListedModels.Shared.Report(this.ConfiguredProviderId, ListingsOf(models));
+
             return SuccessfulModelLoadResult(models.
                 Where(model => !string.IsNullOrWhiteSpace(model.Id) &&
                                !ignorePhrases.Any(ignorePhrase => model.Id.Contains(ignorePhrase, StringComparison.InvariantCulture)) &&
@@ -302,6 +319,27 @@ public sealed class ProviderSelfHosted(Host host, string hostname) : BaseProvide
         }
     }
 
+    /// <summary>
+    /// What an engine stated about the models it serves.
+    /// </summary>
+    /// <remarks>
+    /// A window of zero or less is dropped rather than repaired. An engine answering that way is
+    /// telling us something we cannot interpret, and falling back to what the rules say about the
+    /// weights is the one answer nobody has to invent.
+    /// </remarks>
+    /// <param name="models">The models exactly as the engine listed them.</param>
+    /// <returns>One listing per model the engine said something usable about.</returns>
+    private static IEnumerable<ModelListing> ListingsOf(IEnumerable<Model> models)
+    {
+        foreach (var model in models)
+        {
+            if (string.IsNullOrWhiteSpace(model.Id) || model.ContextWindowTokens is not > 0)
+                continue;
+
+            yield return new(model.Id, ContextWindow.Of(model.ContextWindowTokens.Value));
+        }
+    }
+
     private static bool IsMatchingLlamaCppTextModel(Model model, string[] ignorePhrases, string[] filterPhrases)
     {
         if (string.IsNullOrWhiteSpace(model.Id))