Add z.ai/GLM provider via per-process Claude CLI env injection

Route glm:-prefixed models through the CLI/Anthropic path: ResolveModelId
strips the glm: prefix, and CreateCliStartInfo activates the z.ai
Anthropic-compatible endpoint (ANTHROPIC_BASE_URL/AUTH_TOKEN) only for that
process when IsZaiModel matches, leaving every other request's OAuth login
untouched. GLM model list is loaded through the existing model cache and
exposed via /api/models/glm with a "GLM (z.ai)" optgroup in the agent form.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Endpoints/ModelsEndpoint.cs

@@ -16,6 +16,7 @@ public static class ModelsEndpoint
         app.MapGet("/api/models/gemini",       HandleGeminiModels);
         app.MapGet("/api/models/openai",       HandleOpenAiModels);
         app.MapGet("/api/models/minimax",      HandleMinimaxModels);
+        app.MapGet("/api/models/glm",          HandleGlmModels);
         app.MapPost("/api/models/refresh",     HandleRefresh);
     }
 
@@ -59,6 +60,14 @@ public static class ModelsEndpoint
         return Results.Json(new { models });
     }
 
+    private static IResult HandleGlmModels(OpenAiService openAiService)
+    {
+        var models = openAiService.GetGlmModels()
+            .Select(m => new { id = m.Id, displayName = m.DisplayName })
+            .ToList();
+        return Results.Json(new { models });
+    }
+
     private static async Task<IResult> HandleRefresh(OpenAiService openAiService)
     {
         await openAiService.RefreshModelsFromApis();