Read the context window from a provider's model list

app/MindWork AI Studio/Dialogs/ProviderDialog.razor.cs

@@ -853,10 +853,15 @@ public partial class ProviderDialog : MSGComponentBase, ISecretId
     private ModelProfile GetCurrentModelProfile() => this.CreateProviderSettings().GetModelProfile();
 
     /// <summary>
-    /// What the rules alone say about the model, which is what each switch shows as its automatic answer.
+    /// What holds without anybody switching anything, which is what each field shows as its automatic answer.
     /// </summary>
+    /// <remarks>
+    /// The rules, plus whatever the provider itself stated when the model list was loaded a moment
+    /// ago. A self-hosted engine is the case this matters for: it reports the window it was started
+    /// with, and that is the number a person gets by leaving the field below empty.
+    /// </remarks>
     /// <returns>The profile.</returns>
-    private ModelProfile GetAutomaticModelProfile() => this.DataLLMProvider.GetModelProfile(this.GetSelectedModel());
+    private ModelProfile GetAutomaticModelProfile() => this.CreateProviderSettings().GetAutomaticModelProfile();
 
     private string GetCurrentModelApiLabel()
     {

app/MindWork AI Studio/Models/Live/ListedModels.cs

@@ -0,0 +1,86 @@
+using System.Collections.Concurrent;
+using System.Collections.Frozen;
+
+namespace AIStudio.Models.Live;
+
+/// <summary>
+/// What the configured providers last said about the models they serve.
+/// </summary>
+/// <remarks>
+/// One snapshot per configured provider instance, and reporting replaces the snapshot rather than
+/// adding to it. That is the same reason the registry replaces what the plugins declare: a model an
+/// installation no longer serves has to stop answering, and a window somebody halved by restarting
+/// their engine must not go on being reported alongside its correction.
+///
+/// Nothing here is written to disk. These are statements about a machine as it is running right
+/// now, and the app asks that machine again before every chat round anyway. An instance somebody
+/// deleted keeps its snapshot until the app is closed -- a few dozen kilobytes at the very worst,
+/// which is not worth a second mechanism to watch the settings for.
+/// </remarks>
+public sealed class ListedModels
+{
+    /// <summary>
+    /// The one the app reports into and asks.
+    /// </summary>
+    public static ListedModels Shared { get; } = new();
+
+    /// <summary>
+    /// Per configured provider instance, what its model list said about each model.
+    /// </summary>
+    /// <remarks>
+    /// Both keys ignore case. The IDs come back from the same list they were stored under, so
+    /// ordinal would do -- but a model an organization wrote into a configuration plugin by hand
+    /// was typed by a person, and the availability check already treats such a name as the same
+    /// model regardless of case. Being stricter here would leave exactly those people without the
+    /// numbers.
+    /// </remarks>
+    private readonly ConcurrentDictionary<string, FrozenDictionary<string, ModelListing>> byProvider = new(StringComparer.OrdinalIgnoreCase);
+
+    /// <summary>
+    /// Takes over what one provider instance said about its models, replacing what it said before.
+    /// </summary>
+    /// <remarks>
+    /// Only ever call this with a whole list in hand. Reporting a filtered part of one would tell
+    /// this instance that everything left out has stopped existing.
+    /// </remarks>
+    /// <param name="configuredProviderId">The instance that was asked. Nothing happens without one.</param>
+    /// <param name="listings">What its list stated, with the models it stated nothing about left in or out as convenient.</param>
+    public void Report(string configuredProviderId, IEnumerable<ModelListing> listings)
+    {
+        //
+        // A provider instance nobody has configured yet is not a machine we could ask again later,
+        // so there is nothing to remember it by. The provider dialog is not such a case: it works
+        // on a fully built instance from the moment it opens, ID included.
+        //
+        if (string.IsNullOrWhiteSpace(configuredProviderId))
+            return;
+
+        var stated = new Dictionary<string, ModelListing>(StringComparer.OrdinalIgnoreCase);
+        foreach (var listing in listings)
+        {
+            if (string.IsNullOrWhiteSpace(listing.ModelId) || !listing.IsKnown)
+                continue;
+
+            stated[listing.ModelId] = listing;
+        }
+
+        this.byProvider[configuredProviderId] = stated.ToFrozenDictionary(StringComparer.OrdinalIgnoreCase);
+    }
+
+    /// <summary>
+    /// What one provider instance said about one of its models.
+    /// </summary>
+    /// <param name="configuredProviderId">The instance serving the model.</param>
+    /// <param name="modelId">The model, named the way that instance names it.</param>
+    /// <returns>What it stated, which is nothing when it was never asked or said nothing.</returns>
+    public ModelListing Of(string configuredProviderId, string modelId)
+    {
+        if (string.IsNullOrWhiteSpace(configuredProviderId) || string.IsNullOrWhiteSpace(modelId))
+            return ModelListing.NOTHING;
+
+        if (!this.byProvider.TryGetValue(configuredProviderId, out var stated))
+            return ModelListing.NOTHING;
+
+        return stated.TryGetValue(modelId, out var listing) ? listing : ModelListing.NOTHING;
+    }
+}

app/MindWork AI Studio/Models/Live/ModelListing.cs

@@ -0,0 +1,44 @@
+namespace AIStudio.Models.Live;
+
+/// <summary>
+/// What a provider's own model list says about one of the models it serves.
+/// </summary>
+/// <remarks>
+/// That list is fetched anyway: before every chat round, before every assistant run, and whenever
+/// somebody opens the provider dialog. Reading what it already carries therefore costs no request
+/// of its own, which is the whole reason these numbers are taken from here and not asked for.
+///
+/// This describes one installation, never the model as such. Two machines may serve the same
+/// weights behind different settings, and a statement about one of them says nothing about the
+/// other -- which is why a listing is kept per configured provider instance and is gone with the
+/// process. It is also the only source for a self-hosted model: a rule can say what the weights
+/// were trained for, but only the engine knows what its operator started it with.
+/// </remarks>
+/// <param name="ModelId">The model, named the way the provider names it in its list.</param>
+/// <param name="Context">The window the provider states for it, or unknown where it states none.</param>
+public readonly record struct ModelListing(string ModelId, ContextWindow Context)
+{
+    /// <summary>
+    /// What we have about a model nobody has reported anything about.
+    /// </summary>
+    public static readonly ModelListing NOTHING = new(string.Empty, ContextWindow.UNKNOWN);
+
+    /// <summary>
+    /// Whether this listing states anything at all.
+    /// </summary>
+    public bool IsKnown => this.Context.IsKnown;
+
+    /// <summary>
+    /// Puts what the provider stated over what the rules worked out.
+    /// </summary>
+    /// <remarks>
+    /// A stated window replaces the whole window, the ceiling included, for the same reason the
+    /// expert settings do: what a model card says it could be raised to is a statement about the
+    /// model, while this is a statement about the installation serving it. Whoever started that
+    /// engine has already decided, and a ceiling nobody can reach without restarting it is not a
+    /// number to keep showing.
+    /// </remarks>
+    /// <param name="profile">What is known about the model without this listing.</param>
+    /// <returns>The profile, with what the provider stated in it.</returns>
+    public ModelProfile ApplyTo(in ModelProfile profile) => this.IsKnown ? profile with { Context = this.Context } : profile;
+}

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))

app/MindWork AI Studio/Settings/ProviderExtensions.cs

@@ -1,4 +1,5 @@
 using AIStudio.Models;
+using AIStudio.Models.Live;
 using AIStudio.Models.Registry;
 using AIStudio.Provider;
 
@@ -11,23 +12,42 @@ public static partial class ProviderExtensions
     /// </summary>
     /// <remarks>
     /// The one door to that question. Behind it stand the links of the chain, in the order they
-    /// win: what the person said about their own installation, then what the rules worked out from
-    /// the name, then what the app assumes when nothing else said anything.
+    /// win: what the person said about their own installation, then what the installation itself
+    /// reported, then what the rules worked out from the name, and last what the app assumes when
+    /// nothing else said anything.
     /// </remarks>
     /// <param name="provider">The configured provider.</param>
     /// <returns>The profile of the configured model.</returns>
     public static ModelProfile GetModelProfile(this Provider provider)
     {
-        var stated = provider.UsedLLMProvider.GetModelProfile(provider.Model);
-        return provider.CapabilityOverrides?.ApplyTo(stated) ?? stated;
+        var automatic = provider.GetAutomaticModelProfile();
+        return provider.CapabilityOverrides?.ApplyTo(automatic) ?? automatic;
     }
 
     /// <summary>
-    /// Everything the rules know about a model at a provider, without anybody's own settings.
+    /// Everything known about the configured model except what the person themselves switched.
     /// </summary>
     /// <remarks>
-    /// What the expert dialog shows next to each switch as the automatic answer, so that a person
-    /// can see what they are overriding.
+    /// This is what happens when somebody fills in nothing, which is why the expert dialog shows it
+    /// as the automatic answer. It has to include what the provider reported: a person who leaves
+    /// the window empty gets the number their own engine stated, and a placeholder showing them a
+    /// different one would be a promise the app does not keep.
+    /// </remarks>
+    /// <param name="provider">The configured provider.</param>
+    /// <returns>The profile of the configured model, without that provider's overrides.</returns>
+    public static ModelProfile GetAutomaticModelProfile(this Provider provider)
+    {
+        var stated = provider.UsedLLMProvider.GetModelProfile(provider.Model);
+        return ListedModels.Shared.Of(provider.Id, provider.Model.Id).ApplyTo(stated);
+    }
+
+    /// <summary>
+    /// Everything the rules know about a model at a provider, without anybody's own installation.
+    /// </summary>
+    /// <remarks>
+    /// The answer to the model as such, which is the same for everybody who uses that name at that
+    /// provider -- and therefore the answer the registry caches. What one particular installation
+    /// says about it is asked one link further up, where the instance is known.
     ///
     /// The assumed profile fills in where no rule stated a single capability. It fills in the
     /// capabilities only: a modifier may well have said what the model is made for without any rule