test: update replay harness default to Claude Sonnet 5 (#2472)

* test: update replay harness default to Claude Sonnet 5

Preserve explicit legacy-model replay while advertising a supported default in historical catalogs. Update synthetic C# catalogs, model-list expectations, and the model-specific rate-limit fixture.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

* test: preserve legacy selection in catalog and vision fixtures

Advertise Sonnet 4.5 alongside the current default when no capture exists, and explicitly pin capability-toggle tests to their existing model so they do not switch model families mid-test.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

* test: use Sonnet 5 for both vision capability turns

Migrate session creation and capability updates together across Node, Python, Go, and C#. Update the shared fixture catalogs without changing conversation captures.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

Copilot-Session: 79d231f3-b08c-460b-89ec-c2abbd554368

* test: migrate all Sonnet 4.5 fixtures to Sonnet 5

Use Sonnet 5 consistently in test sessions, fake providers, assertions, and replay catalogs. Remove the legacy catalog compatibility shim and retain model-independent replay coverage using an arbitrary provider model. Conversation captures are not regenerated.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

Copilot-Session: 79d231f3-b08c-460b-89ec-c2abbd554368

* test: fix migration formatting and fixture-authoring examples

Apply Ruff and Spotless reflow after model identifiers shortened, and update Java snapshot-authoring templates to Sonnet 5 so new tests do not reintroduce the retired model.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

Copilot-Session: 79d231f3-b08c-460b-89ec-c2abbd554368

* test: trim replay coverage to the Sonnet 5 default

Keep missing and empty catalog default coverage and the existing cached catalog test; remove tests added for the deleted compatibility shim.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

Copilot-Session: 79d231f3-b08c-460b-89ec-c2abbd554368

---------

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 79d231f3-b08c-460b-89ec-c2abbd554368

Author: dereklegenzoff

.github/skills/new-java-e2e-test-yaml-and-test/SKILL.md

@@ -33,7 +33,7 @@ The format is:
 
 ```yaml
 models:
-  - claude-sonnet-4.5
+  - claude-sonnet-5
 conversations:
   - messages:
       - role: system

.github/skills/new-java-e2e-test-yaml-and-test/examples.md

@@ -8,7 +8,7 @@ File: `test/snapshots/system_message_sections/should_use_replaced_identity_secti
 
 ```yaml
 models:
-  - claude-sonnet-4.5
+  - claude-sonnet-5
 conversations:
   - messages:
       - role: system
@@ -73,7 +73,7 @@ File: `test/snapshots/system_message_transform/should_invoke_transform_callbacks
 
 ```yaml
 models:
-  - claude-sonnet-4.5
+  - claude-sonnet-5
 conversations:
   # First exchange: model decides to call tools
   - messages:

dotnet/test/E2E/ClientOptionsE2ETests.cs

@@ -296,7 +296,7 @@ public async Task Should_Forward_Advanced_Session_Options_In_Create_Wire_Request
         var session = await Ctx.CreateSessionAsync(client, new SessionConfig
         {
             ClientName = "advanced-create-client",
-            Model = "claude-sonnet-4.5",
+            Model = "claude-sonnet-5",
             ReasoningEffort = "medium",
             ReasoningSummary = ReasoningSummary.Detailed,
             ContextTier = ContextTier.LongContext,
@@ -379,7 +379,7 @@ public async Task Should_Forward_Advanced_Session_Options_In_Create_Wire_Request
                     Provider = "create-provider",
                     Id = "create-model",
                     Name = "Create Model",
-                    ModelId = "claude-sonnet-4.5",
+                    ModelId = "claude-sonnet-5",
                     WireModel = "create-wire-model",
                     MaxContextWindowTokens = 12_000,
                     MaxPromptTokens = 10_000,
@@ -392,7 +392,7 @@ public async Task Should_Forward_Advanced_Session_Options_In_Create_Wire_Request
         using var capture = JsonDocument.Parse(await File.ReadAllTextAsync(capturePath));
         var createRequest = GetCapturedRequestParams(capture.RootElement, "session.create");
         Assert.Equal("advanced-create-client", createRequest.GetProperty("clientName").GetString());
-        Assert.Equal("claude-sonnet-4.5", createRequest.GetProperty("model").GetString());
+        Assert.Equal("claude-sonnet-5", createRequest.GetProperty("model").GetString());
         Assert.Equal("medium", createRequest.GetProperty("reasoningEffort").GetString());
         Assert.Equal("detailed", createRequest.GetProperty("reasoningSummary").GetString());
         Assert.Equal("long_context", createRequest.GetProperty("contextTier").GetString());
@@ -442,7 +442,7 @@ public async Task Should_Forward_Singular_Provider_Options_In_Create_Wire_Reques
 
         var session = await Ctx.CreateSessionAsync(client, new SessionConfig
         {
-            Model = "claude-sonnet-4.5",
+            Model = "claude-sonnet-5",
             Provider = new ProviderConfig
             {
                 Type = "azure",
@@ -453,7 +453,7 @@ public async Task Should_Forward_Singular_Provider_Options_In_Create_Wire_Reques
                 BearerToken = "provider-bearer-token",
                 Azure = new AzureOptions { ApiVersion = "2024-02-15-preview" },
                 Headers = new Dictionary<string, string> { ["X-Provider-Wire"] = "yes" },
-                ModelId = "claude-sonnet-4.5",
+                ModelId = "claude-sonnet-5",
                 WireModel = "azure-deployment",
                 MaxPromptTokens = 8192,
                 MaxOutputTokens = 1024,
@@ -471,7 +471,7 @@ public async Task Should_Forward_Singular_Provider_Options_In_Create_Wire_Reques
         Assert.Equal("provider-bearer-token", provider.GetProperty("bearerToken").GetString());
         Assert.Equal("2024-02-15-preview", provider.GetProperty("azure").GetProperty("apiVersion").GetString());
         Assert.Equal("yes", provider.GetProperty("headers").GetProperty("X-Provider-Wire").GetString());
-        Assert.Equal("claude-sonnet-4.5", provider.GetProperty("modelId").GetString());
+        Assert.Equal("claude-sonnet-5", provider.GetProperty("modelId").GetString());
         Assert.Equal("azure-deployment", provider.GetProperty("wireModel").GetString());
         Assert.Equal(8192, provider.GetProperty("maxPromptTokens").GetInt32());
         Assert.Equal(1024, provider.GetProperty("maxOutputTokens").GetInt32());

dotnet/test/E2E/CopilotRequestE2EProvider.cs

@@ -160,9 +160,9 @@ internal static HttpResponseMessage BuildNonInferenceResponse(string url)
 
     private static readonly string[] ChatCompletionStreamEvents =
     [
-        "data: {\"id\":\"chatcmpl-stub-1\",\"object\":\"chat.completion.chunk\",\"created\":1,\"model\":\"claude-sonnet-4.5\",\"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\",\"content\":\"\"},\"finish_reason\":null}]}\n\n",
-        "data: {\"id\":\"chatcmpl-stub-1\",\"object\":\"chat.completion.chunk\",\"created\":1,\"model\":\"claude-sonnet-4.5\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"" + SyntheticText + "\"},\"finish_reason\":null}]}\n\n",
-        "data: {\"id\":\"chatcmpl-stub-1\",\"object\":\"chat.completion.chunk\",\"created\":1,\"model\":\"claude-sonnet-4.5\",\"choices\":[{\"index\":0,\"delta\":{},\"finish_reason\":\"stop\"}],\"usage\":{\"prompt_tokens\":5,\"completion_tokens\":7,\"total_tokens\":12}}\n\n",
+        "data: {\"id\":\"chatcmpl-stub-1\",\"object\":\"chat.completion.chunk\",\"created\":1,\"model\":\"claude-sonnet-5\",\"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\",\"content\":\"\"},\"finish_reason\":null}]}\n\n",
+        "data: {\"id\":\"chatcmpl-stub-1\",\"object\":\"chat.completion.chunk\",\"created\":1,\"model\":\"claude-sonnet-5\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"" + SyntheticText + "\"},\"finish_reason\":null}]}\n\n",
+        "data: {\"id\":\"chatcmpl-stub-1\",\"object\":\"chat.completion.chunk\",\"created\":1,\"model\":\"claude-sonnet-5\",\"choices\":[{\"index\":0,\"delta\":{},\"finish_reason\":\"stop\"}],\"usage\":{\"prompt_tokens\":5,\"completion_tokens\":7,\"total_tokens\":12}}\n\n",
         "data: [DONE]\n\n",
     ];
 
@@ -172,7 +172,7 @@ internal static HttpResponseMessage BuildNonInferenceResponse(string url)
     // runtime's Anthropic client fail with "stream ended without producing a Message".
     private static readonly string[] AnthropicStreamEvents =
     [
-        "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"msg_stub_1\",\"type\":\"message\",\"role\":\"assistant\",\"model\":\"claude-sonnet-4.5\",\"content\":[],\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":5,\"output_tokens\":1}}}\n\n",
+        "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"msg_stub_1\",\"type\":\"message\",\"role\":\"assistant\",\"model\":\"claude-sonnet-5\",\"content\":[],\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":5,\"output_tokens\":1}}}\n\n",
         "event: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"}}\n\n",
         "event: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"" + SyntheticText + "\"}}\n\n",
         "event: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\n",
@@ -184,13 +184,13 @@ internal static HttpResponseMessage BuildNonInferenceResponse(string url)
         "{\"id\":\"resp_stub_1\",\"object\":\"response\",\"status\":\"completed\",\"output\":[{\"id\":\"msg_1\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"" + SyntheticText + "\"}]}],\"usage\":{\"input_tokens\":5,\"output_tokens\":7,\"total_tokens\":12}}";
 
     private static readonly string BufferedChatCompletionJson =
-        "{\"id\":\"chatcmpl-stub-1\",\"object\":\"chat.completion\",\"created\":1,\"model\":\"claude-sonnet-4.5\",\"choices\":[{\"index\":0,\"message\":{\"role\":\"assistant\",\"content\":\"" + SyntheticText + "\"},\"finish_reason\":\"stop\"}],\"usage\":{\"prompt_tokens\":5,\"completion_tokens\":7,\"total_tokens\":12}}";
+        "{\"id\":\"chatcmpl-stub-1\",\"object\":\"chat.completion\",\"created\":1,\"model\":\"claude-sonnet-5\",\"choices\":[{\"index\":0,\"message\":{\"role\":\"assistant\",\"content\":\"" + SyntheticText + "\"},\"finish_reason\":\"stop\"}],\"usage\":{\"prompt_tokens\":5,\"completion_tokens\":7,\"total_tokens\":12}}";
 
     private static readonly string BufferedAnthropicMessageJson =
-        "{\"id\":\"msg_stub_1\",\"type\":\"message\",\"role\":\"assistant\",\"model\":\"claude-sonnet-4.5\",\"content\":[{\"type\":\"text\",\"text\":\"" + SyntheticText + "\"}],\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"usage\":{\"input_tokens\":5,\"output_tokens\":7}}";
+        "{\"id\":\"msg_stub_1\",\"type\":\"message\",\"role\":\"assistant\",\"model\":\"claude-sonnet-5\",\"content\":[{\"type\":\"text\",\"text\":\"" + SyntheticText + "\"}],\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"usage\":{\"input_tokens\":5,\"output_tokens\":7}}";
 
     private const string ModelCatalogJson =
-        "{\"data\":[{\"id\":\"claude-sonnet-4.5\",\"name\":\"Claude Sonnet 4.5\",\"object\":\"model\",\"vendor\":\"Anthropic\",\"version\":\"1\",\"preview\":false,\"model_picker_enabled\":true,\"capabilities\":{\"type\":\"chat\",\"family\":\"claude-sonnet-4.5\",\"tokenizer\":\"o200k_base\",\"limits\":{\"max_context_window_tokens\":200000,\"max_output_tokens\":8192},\"supports\":{\"streaming\":true,\"tool_calls\":true,\"parallel_tool_calls\":true,\"vision\":true}}}]}";
+        "{\"data\":[{\"id\":\"claude-sonnet-5\",\"name\":\"Claude Sonnet 5\",\"object\":\"model\",\"vendor\":\"Anthropic\",\"version\":\"1\",\"preview\":false,\"model_picker_enabled\":true,\"capabilities\":{\"type\":\"chat\",\"family\":\"claude-sonnet-5\",\"tokenizer\":\"o200k_base\",\"limits\":{\"max_context_window_tokens\":200000,\"max_output_tokens\":8192},\"supports\":{\"streaming\":true,\"tool_calls\":true,\"parallel_tool_calls\":true,\"vision\":true}}}]}";
 }
 
 /// <summary>A single request the callback intercepted.</summary>

dotnet/test/E2E/CopilotRequestSessionIdE2ETests.cs

@@ -76,15 +76,15 @@ public async Task Threads_The_Session_Id_Into_A_Byok_Session_Inference_Request()
         {
             OnPermissionRequest = PermissionHandler.ApproveAll,
             // BYOK providers require an explicit model id.
-            Model = "claude-sonnet-4.5",
+            Model = "claude-sonnet-5",
             Provider = new ProviderConfig
             {
                 Type = "openai",
                 WireApi = "responses",
                 BaseUrl = "https://byok.invalid/v1",
                 ApiKey = "byok-secret",
-                ModelId = "claude-sonnet-4.5",
-                WireModel = "claude-sonnet-4.5",
+                ModelId = "claude-sonnet-5",
+                WireModel = "claude-sonnet-5",
             },
         });
         var byokSessionId = session.SessionId;

dotnet/test/E2E/CopilotRequestWebSocketE2ETests.cs

@@ -349,7 +349,7 @@ private static (string Type, string Json)[] ResponseEvents(string text, string i
     ];
 
     private const string ModelCatalogJson =
-        "{\"data\":[{\"id\":\"claude-sonnet-4.5\",\"name\":\"Claude Sonnet 4.5\",\"object\":\"model\",\"vendor\":\"Anthropic\",\"version\":\"1\",\"preview\":false,\"model_picker_enabled\":true,\"supported_endpoints\":[\"/responses\",\"ws:/responses\"],\"capabilities\":{\"type\":\"chat\",\"family\":\"claude-sonnet-4.5\",\"tokenizer\":\"o200k_base\",\"limits\":{\"max_context_window_tokens\":200000,\"max_output_tokens\":8192},\"supports\":{\"streaming\":true,\"tool_calls\":true,\"parallel_tool_calls\":true,\"vision\":true}}}]}";
+        "{\"data\":[{\"id\":\"claude-sonnet-5\",\"name\":\"Claude Sonnet 5\",\"object\":\"model\",\"vendor\":\"Anthropic\",\"version\":\"1\",\"preview\":false,\"model_picker_enabled\":true,\"supported_endpoints\":[\"/responses\",\"ws:/responses\"],\"capabilities\":{\"type\":\"chat\",\"family\":\"claude-sonnet-5\",\"tokenizer\":\"o200k_base\",\"limits\":{\"max_context_window_tokens\":200000,\"max_output_tokens\":8192},\"supports\":{\"streaming\":true,\"tool_calls\":true,\"parallel_tool_calls\":true,\"vision\":true}}}]}";
 
     private static int GetFreePort()
     {

dotnet/test/E2E/RewindE2ETests.cs

@@ -24,7 +24,7 @@ public async Task Should_Restore_Tracked_File_And_Conversation()
         await File.WriteAllTextAsync(filePath, OriginalFileContent);
         await using var session = await CreateSessionAsync(new SessionConfig
         {
-            Model = "claude-sonnet-4.5",
+            Model = "claude-sonnet-5",
             EnableFileChangeTracking = true,
         });
 

dotnet/test/E2E/RpcServerE2ETests.cs

@@ -171,7 +171,7 @@ public async Task Should_Call_Rpc_Models_List_With_Typed_Result()
         var result = await client.Rpc.Models.ListAsync();
 
         Assert.NotNull(result.Models);
-        Assert.Contains(result.Models, model => model.Id == "claude-sonnet-4.5");
+        Assert.Contains(result.Models, model => model.Id == "claude-sonnet-5");
         Assert.All(result.Models, model => Assert.False(string.IsNullOrWhiteSpace(model.Name)));
     }
 

dotnet/test/E2E/RpcSessionStateE2ETests.cs

@@ -22,14 +22,14 @@ private static async Task<Exception> AssertImplementedFailureAsync(Func<Task> ac
     [Fact]
     public async Task Should_Call_Session_Rpc_Model_GetCurrent()
     {
-        await using var session = await CreateSessionAsync(new SessionConfig { Model = "claude-sonnet-4.5" });
+        await using var session = await CreateSessionAsync(new SessionConfig { Model = "claude-sonnet-5" });
 
         var result = await session.Rpc.Model.GetCurrentAsync();
 
         Assert.NotNull(result.ModelId);
         Assert.NotEmpty(result.ModelId);
         // Strengthen: verify the configured model is actually in effect, not just any model
-        Assert.Equal("claude-sonnet-4.5", result.ModelId);
+        Assert.Equal("claude-sonnet-5", result.ModelId);
     }
 
     [Fact]
@@ -48,12 +48,12 @@ public async Task Should_Call_Session_Rpc_Model_SwitchTo()
 
         await using var session = await isolatedCtx.CreateSessionAsync(isolatedClient, new SessionConfig
         {
-            Model = "claude-sonnet-4.5",
+            Model = "claude-sonnet-5",
             OnPermissionRequest = PermissionHandler.ApproveAll,
         });
 
         var before = await session.Rpc.Model.GetCurrentAsync();
-        Assert.Equal("claude-sonnet-4.5", before.ModelId);
+        Assert.Equal("claude-sonnet-5", before.ModelId);
 
         var result = await session.Rpc.Model.SwitchToAsync(modelId: "gpt-5.4", reasoningEffort: "high");
         Assert.Equal("gpt-5.4", result.ModelId);
@@ -281,14 +281,14 @@ public async Task Should_Call_Metadata_Snapshot_SetWorkingDirectory_And_RecordCo
         var branch = $"rpc-context-{Guid.NewGuid():N}";
         await using var session = await CreateSessionAsync(new SessionConfig
         {
-            Model = "claude-sonnet-4.5",
+            Model = "claude-sonnet-5",
             WorkingDirectory = firstDirectory,
         });
 
         var initialSnapshot = await session.Rpc.Metadata.SnapshotAsync();
         Assert.Equal(session.SessionId, initialSnapshot.SessionId);
         Assert.Equal(MetadataSnapshotCurrentMode.Interactive, initialSnapshot.CurrentMode);
-        Assert.Equal("claude-sonnet-4.5", initialSnapshot.SelectedModel);
+        Assert.Equal("claude-sonnet-5", initialSnapshot.SelectedModel);
         Assert.False(initialSnapshot.IsRemote);
         Assert.False(initialSnapshot.AlreadyInUse);
         Assert.NotEqual(default, initialSnapshot.StartTime);
@@ -405,14 +405,14 @@ public async Task Should_Set_ReasoningEffort_And_Auto_Name()
     {
         await using var session = await CreateSessionAsync(new SessionConfig
         {
-            Model = "claude-sonnet-4.5",
+            Model = "claude-sonnet-5",
         });
 
         var reasoning = await session.Rpc.Model.SetReasoningEffortAsync("high");
         Assert.Equal("high", reasoning.ReasoningEffort);
 
         var currentModel = await session.Rpc.Model.GetCurrentAsync();
-        Assert.Equal("claude-sonnet-4.5", currentModel.ModelId);
+        Assert.Equal("claude-sonnet-5", currentModel.ModelId);
         Assert.Equal("high", currentModel.ReasoningEffort);
 
         var autoName = $"Auto Session {Guid.NewGuid():N}";
@@ -653,9 +653,9 @@ public async Task Should_Compact_Session_History_After_Messages()
         var contextInfo = await session.Rpc.Metadata.ContextInfoAsync(
             promptTokenLimit: 128_000,
             outputTokenLimit: 4_096,
-            selectedModel: "claude-sonnet-4.5");
+            selectedModel: "claude-sonnet-5");
         var context = Assert.IsType<MetadataContextInfoResultContextInfo>(contextInfo.ContextInfo);
-        Assert.Equal("claude-sonnet-4.5", context.ModelName);
+        Assert.Equal("claude-sonnet-5", context.ModelName);
         Assert.Equal(128_000, context.PromptTokenLimit);
         Assert.True(context.Limit >= context.PromptTokenLimit);
         Assert.True(context.TotalTokens > 0);
@@ -666,7 +666,7 @@ public async Task Should_Compact_Session_History_After_Messages()
             context.SystemTokens + context.ConversationTokens + context.ToolDefinitionsTokens,
             context.TotalTokens);
 
-        var recomputed = await session.Rpc.Metadata.RecomputeContextTokensAsync("claude-sonnet-4.5");
+        var recomputed = await session.Rpc.Metadata.RecomputeContextTokensAsync("claude-sonnet-5");
         Assert.True(recomputed.SystemTokenCount > 0);
         Assert.True(recomputed.MessagesTokenCount > 0);
         Assert.Equal(recomputed.SystemTokenCount + recomputed.MessagesTokenCount, recomputed.TotalTokens);

dotnet/test/E2E/RpcSessionStateExtrasE2ETests.cs

@@ -32,7 +32,7 @@ public async Task Should_List_Models_For_Session()
         await using var client = CreateAuthenticatedClient(token);
         await using var session = await Ctx.CreateSessionAsync(client, new SessionConfig
         {
-            Model = "claude-sonnet-4.5",
+            Model = "claude-sonnet-5",
             OnPermissionRequest = PermissionHandler.ApproveAll,
         });
 
@@ -41,7 +41,7 @@ public async Task Should_List_Models_For_Session()
         Assert.NotNull(result.List);
         Assert.NotEmpty(result.List);
         // The configured model must be present in the returned catalog.
-        Assert.Contains(result.List, model => model.GetRawText().Contains("claude-sonnet-4.5", StringComparison.Ordinal));
+        Assert.Contains(result.List, model => model.GetRawText().Contains("claude-sonnet-5", StringComparison.Ordinal));
     }
 
     [Fact]
@@ -73,7 +73,7 @@ public async Task Should_Add_Byok_Provider_And_Model_At_Runtime()
                     Provider = providerName,
                     Id = modelId,
                     Name = "SDK Runtime Model",
-                    ModelId = "claude-sonnet-4.5",
+                    ModelId = "claude-sonnet-5",
                     WireModel = "wire-sdk-runtime-model",
                     MaxContextWindowTokens = 4_096,
                     MaxPromptTokens = 3_072,
@@ -277,7 +277,7 @@ public async Task Should_Update_And_Clear_Live_Subagent_Settings()
             {
                 ["general-purpose"] = new()
                 {
-                    Model = "claude-sonnet-4.5",
+                    Model = "claude-sonnet-5",
                     EffortLevel = "high",
                     ContextTier = SubagentSettingsEntryContextTier.Default,
                 },