Add provider model and token limit overrides to ProviderConfig

dotnet/src/Types.cs

@@ -1528,6 +1528,43 @@ public class ProviderConfig
     /// </summary>
     [JsonPropertyName("headers")]
     public IDictionary<string, string>? Headers { get; set; }
+
+    /// <summary>
+    /// Well-known model ID used to look up agent configuration (tools, prompts,
+    /// reasoning behavior) and default token limits from the capability catalog.
+    /// Useful for fine-tuned models that should inherit the configuration of a
+    /// known base model.
+    /// Defaults to the session's configured model (see <see cref="SessionConfig.Model"/>)
+    /// when not explicitly set.
+    /// </summary>
+    [JsonPropertyName("modelId")]
+    public string? ModelId { get; set; }
+
+    /// <summary>
+    /// Model identifier sent to the provider API for inference.
+    /// Use this when the name your provider knows (e.g. an Azure deployment name
+    /// or a custom fine-tune name) differs from the well-known model ID used for
+    /// configuration lookup.
+    /// Defaults to the session's configured model (see <see cref="SessionConfig.Model"/>)
+    /// when not explicitly set.
+    /// </summary>
+    [JsonPropertyName("wireModel")]
+    public string? WireModel { get; set; }
+
+    /// <summary>
+    /// Maximum number of tokens allowed in the prompt for a single LLM API request.
+    /// Used by the runtime to trigger conversation compaction before sending a request
+    /// when the prompt (system message, history, tool definitions, user message) exceeds this limit.
+    /// </summary>
+    [JsonPropertyName("maxPromptTokens")]
+    public int? MaxPromptTokens { get; set; }
+
+    /// <summary>
+    /// Maximum number of tokens the model can generate in a single response.
+    /// When hit, the model stops generating and returns a truncated response.
+    /// </summary>
+    [JsonPropertyName("maxOutputTokens")]
+    public int? MaxOutputTokens { get; set; }
 }
 
 /// <summary>

dotnet/test/Unit/SerializationTests.cs

@@ -20,19 +20,31 @@ public void ProviderConfig_CanSerializeHeaders_WithSdkOptions()
         var original = new ProviderConfig
         {
             BaseUrl = "https://example.com/provider",
-            Headers = new Dictionary<string, string> { ["Authorization"] = "Bearer provider-token" }
+            Headers = new Dictionary<string, string> { ["Authorization"] = "Bearer provider-token" },
+            ModelId = "gpt-4o",
+            WireModel = "my-finetune-v3",
+            MaxPromptTokens = 100_000,
+            MaxOutputTokens = 4096
         };
 
         var json = JsonSerializer.Serialize(original, options);
         using var document = JsonDocument.Parse(json);
         var root = document.RootElement;
         Assert.Equal("https://example.com/provider", root.GetProperty("baseUrl").GetString());
         Assert.Equal("Bearer provider-token", root.GetProperty("headers").GetProperty("Authorization").GetString());
+        Assert.Equal("gpt-4o", root.GetProperty("modelId").GetString());
+        Assert.Equal("my-finetune-v3", root.GetProperty("wireModel").GetString());
+        Assert.Equal(100_000, root.GetProperty("maxPromptTokens").GetInt32());
+        Assert.Equal(4096, root.GetProperty("maxOutputTokens").GetInt32());
 
         var deserialized = JsonSerializer.Deserialize<ProviderConfig>(json, options);
         Assert.NotNull(deserialized);
         Assert.Equal("https://example.com/provider", deserialized.BaseUrl);
         Assert.Equal("Bearer provider-token", deserialized.Headers!["Authorization"]);
+        Assert.Equal("gpt-4o", deserialized.ModelId);
+        Assert.Equal("my-finetune-v3", deserialized.WireModel);
+        Assert.Equal(100_000, deserialized.MaxPromptTokens);
+        Assert.Equal(4096, deserialized.MaxOutputTokens);
     }
 
     [Fact]

go/types.go

@@ -859,6 +859,29 @@ type ProviderConfig struct {
 	Azure *AzureProviderOptions `json:"azure,omitempty"`
 	// Headers are custom HTTP headers included in outbound provider requests.
 	Headers map[string]string `json:"headers,omitempty"`
+	// ModelID is the well-known model ID used to look up agent configuration
+	// (tools, prompts, reasoning behavior) and default token limits from the
+	// capability catalog. Useful for fine-tuned models that should inherit the
+	// configuration of a known base model.
+	// Defaults to the session's configured model (SessionConfig.Model) when
+	// not explicitly set.
+	ModelID string `json:"modelId,omitempty"`
+	// WireModel is the model identifier sent to the provider API for inference.
+	// Use this when the name your provider knows (e.g. an Azure deployment name
+	// or a custom fine-tune name) differs from the well-known model ID used for
+	// configuration lookup.
+	// Defaults to the session's configured model (SessionConfig.Model) when
+	// not explicitly set.
+	WireModel string `json:"wireModel,omitempty"`
+	// MaxPromptTokens is the maximum number of tokens allowed in the prompt for
+	// a single LLM API request. Used by the runtime to trigger conversation
+	// compaction before sending a request when the prompt (system message,
+	// history, tool definitions, user message) exceeds this limit.
+	MaxPromptTokens int `json:"maxPromptTokens,omitempty"`
+	// MaxOutputTokens is the maximum number of tokens the model can generate in
+	// a single response. When hit, the model stops generating and returns a
+	// truncated response.
+	MaxOutputTokens int `json:"maxOutputTokens,omitempty"`
 }
 
 // AzureProviderOptions contains Azure-specific provider configuration

go/types_test.go

@@ -151,3 +151,68 @@ func TestSessionSendRequest_JSONIncludesRequestHeaders(t *testing.T) {
 		t.Fatalf("expected Authorization header, got %v", headers["Authorization"])
 	}
 }
+
+func TestProviderConfig_JSONIncludesAllFields(t *testing.T) {
+	cfg := ProviderConfig{
+		BaseURL:         "https://example.com/provider",
+		APIKey:          "test-key",
+		Headers:         map[string]string{"Authorization": "Bearer provider-token"},
+		ModelID:         "gpt-4o",
+		WireModel:       "my-finetune-v3",
+		MaxPromptTokens: 100000,
+		MaxOutputTokens: 4096,
+	}
+
+	data, err := json.Marshal(cfg)
+	if err != nil {
+		t.Fatalf("failed to marshal ProviderConfig: %v", err)
+	}
+
+	var decoded map[string]any
+	if err := json.Unmarshal(data, &decoded); err != nil {
+		t.Fatalf("failed to unmarshal ProviderConfig: %v", err)
+	}
+
+	if decoded["baseUrl"] != "https://example.com/provider" {
+		t.Errorf("expected baseUrl to round-trip, got %v", decoded["baseUrl"])
+	}
+	if decoded["modelId"] != "gpt-4o" {
+		t.Errorf("expected modelId 'gpt-4o', got %v", decoded["modelId"])
+	}
+	if decoded["wireModel"] != "my-finetune-v3" {
+		t.Errorf("expected wireModel 'my-finetune-v3', got %v", decoded["wireModel"])
+	}
+	if decoded["maxPromptTokens"] != float64(100000) {
+		t.Errorf("expected maxPromptTokens 100000, got %v", decoded["maxPromptTokens"])
+	}
+	if decoded["maxOutputTokens"] != float64(4096) {
+		t.Errorf("expected maxOutputTokens 4096, got %v", decoded["maxOutputTokens"])
+	}
+	headers, ok := decoded["headers"].(map[string]any)
+	if !ok {
+		t.Fatalf("expected headers object, got %T", decoded["headers"])
+	}
+	if headers["Authorization"] != "Bearer provider-token" {
+		t.Errorf("expected Authorization header, got %v", headers["Authorization"])
+	}
+}
+
+func TestProviderConfig_JSONOmitsUnsetTokenFields(t *testing.T) {
+	cfg := ProviderConfig{BaseURL: "https://example.com/provider"}
+
+	data, err := json.Marshal(cfg)
+	if err != nil {
+		t.Fatalf("failed to marshal ProviderConfig: %v", err)
+	}
+
+	var decoded map[string]any
+	if err := json.Unmarshal(data, &decoded); err != nil {
+		t.Fatalf("failed to unmarshal ProviderConfig: %v", err)
+	}
+
+	for _, field := range []string{"modelId", "wireModel", "maxPromptTokens", "maxOutputTokens", "headers"} {
+		if _, present := decoded[field]; present {
+			t.Errorf("expected %q to be omitted when unset, got %v", field, decoded[field])
+		}
+	}
+}

nodejs/src/types.ts

@@ -1503,6 +1503,39 @@ export interface ProviderConfig {
      * Custom HTTP headers to include in outbound provider requests.
      */
     headers?: Record<string, string>;
+
+    /**
+     * Well-known model ID used to look up agent configuration (tools, prompts,
+     * reasoning behavior) and default token limits from the capability catalog.
+     * Useful for fine-tuned models that should inherit the configuration of a
+     * known base model.
+     * Defaults to the session's configured model (see {@link SessionConfig.model})
+     * when not explicitly set.
+     */
+    modelId?: string;
+
+    /**
+     * Model identifier sent to the provider API for inference.
+     * Use this when the name your provider knows (e.g. an Azure deployment name
+     * or a custom fine-tune name) differs from the well-known model ID used
+     * for configuration lookup.
+     * Defaults to the session's configured model (see {@link SessionConfig.model})
+     * when not explicitly set.
+     */
+    wireModel?: string;
+
+    /**
+     * Maximum number of tokens allowed in the prompt for a single LLM API request.
+     * Used by the runtime to trigger conversation compaction before sending a request
+     * when the prompt (system message, history, tool definitions, user message) exceeds this limit.
+     */
+    maxPromptTokens?: number;
+
+    /**
+     * Maximum number of tokens the model can generate in a single response.
+     * When hit, the model stops generating and returns a truncated response.
+     */
+    maxOutputTokens?: number;
 }
 
 /**

nodejs/test/client.test.ts

@@ -224,6 +224,10 @@ describe("CopilotClient", () => {
             provider: {
                 baseUrl: "https://example.com/provider",
                 headers: { Authorization: "Bearer provider-token" },
+                modelId: "gpt-4o",
+                wireModel: "my-finetune-v3",
+                maxPromptTokens: 100_000,
+                maxOutputTokens: 4096,
             },
         });
 
@@ -232,6 +236,10 @@ describe("CopilotClient", () => {
             expect.objectContaining({
                 baseUrl: "https://example.com/provider",
                 headers: { Authorization: "Bearer provider-token" },
+                modelId: "gpt-4o",
+                wireModel: "my-finetune-v3",
+                maxPromptTokens: 100_000,
+                maxOutputTokens: 4096,
             })
         );
         spy.mockRestore();
@@ -255,6 +263,10 @@ describe("CopilotClient", () => {
             provider: {
                 baseUrl: "https://example.com/provider",
                 headers: { Authorization: "Bearer resume-token" },
+                modelId: "gpt-4o",
+                wireModel: "my-finetune-v3",
+                maxPromptTokens: 100_000,
+                maxOutputTokens: 4096,
             },
         });
 
@@ -263,6 +275,10 @@ describe("CopilotClient", () => {
             expect.objectContaining({
                 baseUrl: "https://example.com/provider",
                 headers: { Authorization: "Bearer resume-token" },
+                modelId: "gpt-4o",
+                wireModel: "my-finetune-v3",
+                maxPromptTokens: 100_000,
+                maxOutputTokens: 4096,
             })
         );
         spy.mockRestore();

python/copilot/client.py

@@ -2275,6 +2275,14 @@ def _convert_provider_to_wire_format(
             wire_provider["bearerToken"] = provider["bearer_token"]
         if "headers" in provider:
             wire_provider["headers"] = provider["headers"]
+        if "model_id" in provider:
+            wire_provider["modelId"] = provider["model_id"]
+        if "wire_model" in provider:
+            wire_provider["wireModel"] = provider["wire_model"]
+        if "max_prompt_tokens" in provider:
+            wire_provider["maxPromptTokens"] = provider["max_prompt_tokens"]
+        if "max_output_tokens" in provider:
+            wire_provider["maxOutputTokens"] = provider["max_output_tokens"]
         if "azure" in provider:
             azure = provider["azure"]
             wire_azure: dict[str, Any] = {}

python/copilot/session.py

@@ -832,6 +832,28 @@ class ProviderConfig(TypedDict, total=False):
     bearer_token: str
     azure: AzureProviderOptions  # Azure-specific options
     headers: dict[str, str]
+    # Well-known model ID used to look up agent configuration (tools, prompts,
+    # reasoning behavior) and default token limits from the capability catalog.
+    # Useful for fine-tuned models that should inherit the configuration of a
+    # known base model.
+    # Defaults to the session's configured model (SessionConfig.model) when
+    # not explicitly set.
+    model_id: str
+    # Model identifier sent to the provider API for inference. Use this when the
+    # name your provider knows (e.g. an Azure deployment name or a custom
+    # fine-tune name) differs from the well-known model ID used for
+    # configuration lookup.
+    # Defaults to the session's configured model (SessionConfig.model) when
+    # not explicitly set.
+    wire_model: str
+    # Maximum number of tokens allowed in the prompt for a single LLM API
+    # request. Used by the runtime to trigger conversation compaction before
+    # sending a request when the prompt (system message, history, tool
+    # definitions, user message) exceeds this limit.
+    max_prompt_tokens: int
+    # Maximum number of tokens the model can generate in a single response.
+    # When hit, the model stops generating and returns a truncated response.
+    max_output_tokens: int
 
 
 class SessionConfig(TypedDict, total=False):

python/test_client.py

@@ -564,12 +564,20 @@ async def mock_request(method, params):
                 provider={
                     "base_url": "https://example.com/provider",
                     "headers": {"Authorization": "Bearer provider-token"},
+                    "model_id": "gpt-4o",
+                    "wire_model": "my-finetune-v3",
+                    "max_prompt_tokens": 100_000,
+                    "max_output_tokens": 4096,
                 },
             )
 
             provider = captured["session.create"]["provider"]
             assert provider["baseUrl"] == "https://example.com/provider"
             assert provider["headers"] == {"Authorization": "Bearer provider-token"}
+            assert provider["modelId"] == "gpt-4o"
+            assert provider["wireModel"] == "my-finetune-v3"
+            assert provider["maxPromptTokens"] == 100_000
+            assert provider["maxOutputTokens"] == 4096
         finally:
             await client.force_stop()
 
@@ -599,12 +607,20 @@ async def mock_request(method, params):
                 provider={
                     "base_url": "https://example.com/provider",
                     "headers": {"Authorization": "Bearer resume-token"},
+                    "model_id": "gpt-4o",
+                    "wire_model": "my-finetune-v3",
+                    "max_prompt_tokens": 100_000,
+                    "max_output_tokens": 4096,
                 },
             )
 
             provider = captured["session.resume"]["provider"]
             assert provider["baseUrl"] == "https://example.com/provider"
             assert provider["headers"] == {"Authorization": "Bearer resume-token"}
+            assert provider["modelId"] == "gpt-4o"
+            assert provider["wireModel"] == "my-finetune-v3"
+            assert provider["maxPromptTokens"] == 100_000
+            assert provider["maxOutputTokens"] == 4096
         finally:
             await client.force_stop()