diff --git a/packages/ai/scripts/generate-models.ts b/packages/ai/scripts/generate-models.ts
index 4b8e508c..79b22e60 100644
--- a/packages/ai/scripts/generate-models.ts
+++ b/packages/ai/scripts/generate-models.ts
@@ -317,10 +317,13 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 				if (m.tool_call !== true) continue;
 				if (m.status === "deprecated") continue;
 
+				// gpt-5 models require responses API, others use completions
+				const needsResponsesApi = modelId.startsWith("gpt-5");
+
 				const copilotModel: Model<any> = {
 					id: modelId,
 					name: m.name || modelId,
-					api: "openai-completions",
+					api: needsResponsesApi ? "openai-responses" : "openai-completions",
 					provider: "github-copilot",
 					baseUrl: "https://api.individual.githubcopilot.com",
 					reasoning: m.reasoning === true,
@@ -334,11 +337,14 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 					contextWindow: m.limit?.context || 128000,
 					maxTokens: m.limit?.output || 8192,
 					headers: { ...COPILOT_STATIC_HEADERS },
-					compat: {
-						supportsStore: false,
-						supportsDeveloperRole: false,
-						supportsReasoningEffort: false,
-					},
+					// compat only applies to openai-completions
+					...(needsResponsesApi ? {} : {
+						compat: {
+							supportsStore: false,
+							supportsDeveloperRole: false,
+							supportsReasoningEffort: false,
+						},
+					}),
 				};
 
 				models.push(copilotModel);
diff --git a/packages/ai/src/models.generated.ts b/packages/ai/src/models.generated.ts
index d285ace5..bdd6490f 100644
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -2496,7 +2496,7 @@ export const MODELS = {
 		"gpt-5.1-codex": {
 			id: "gpt-5.1-codex",
 			name: "GPT-5.1-Codex",
-			api: "openai-completions",
+			api: "openai-responses",
 			provider: "github-copilot",
 			baseUrl: "https://api.individual.githubcopilot.com",
 			headers: {
@@ -2505,7 +2505,6 @@ export const MODELS = {
 				"Editor-Plugin-Version": "copilot-chat/0.35.0",
 				"Copilot-Integration-Id": "vscode-chat",
 			},
-			compat: { supportsStore: false, supportsDeveloperRole: false, supportsReasoningEffort: false },
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -2516,7 +2515,7 @@ export const MODELS = {
 			},
 			contextWindow: 128000,
 			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"openai-responses">,
 		"claude-haiku-4.5": {
 			id: "claude-haiku-4.5",
 			name: "Claude Haiku 4.5",
@@ -2592,7 +2591,7 @@ export const MODELS = {
 		"gpt-5.1-codex-mini": {
 			id: "gpt-5.1-codex-mini",
 			name: "GPT-5.1-Codex-mini",
-			api: "openai-completions",
+			api: "openai-responses",
 			provider: "github-copilot",
 			baseUrl: "https://api.individual.githubcopilot.com",
 			headers: {
@@ -2601,7 +2600,6 @@ export const MODELS = {
 				"Editor-Plugin-Version": "copilot-chat/0.35.0",
 				"Copilot-Integration-Id": "vscode-chat",
 			},
-			compat: { supportsStore: false, supportsDeveloperRole: false, supportsReasoningEffort: false },
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -2612,11 +2610,11 @@ export const MODELS = {
 			},
 			contextWindow: 128000,
 			maxTokens: 100000,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"openai-responses">,
 		"gpt-5.1": {
 			id: "gpt-5.1",
 			name: "GPT-5.1",
-			api: "openai-completions",
+			api: "openai-responses",
 			provider: "github-copilot",
 			baseUrl: "https://api.individual.githubcopilot.com",
 			headers: {
@@ -2625,7 +2623,6 @@ export const MODELS = {
 				"Editor-Plugin-Version": "copilot-chat/0.35.0",
 				"Copilot-Integration-Id": "vscode-chat",
 			},
-			compat: { supportsStore: false, supportsDeveloperRole: false, supportsReasoningEffort: false },
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -2636,11 +2633,11 @@ export const MODELS = {
 			},
 			contextWindow: 128000,
 			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"openai-responses">,
 		"gpt-5-codex": {
 			id: "gpt-5-codex",
 			name: "GPT-5-Codex",
-			api: "openai-completions",
+			api: "openai-responses",
 			provider: "github-copilot",
 			baseUrl: "https://api.individual.githubcopilot.com",
 			headers: {
@@ -2649,7 +2646,6 @@ export const MODELS = {
 				"Editor-Plugin-Version": "copilot-chat/0.35.0",
 				"Copilot-Integration-Id": "vscode-chat",
 			},
-			compat: { supportsStore: false, supportsDeveloperRole: false, supportsReasoningEffort: false },
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -2660,7 +2656,7 @@ export const MODELS = {
 			},
 			contextWindow: 128000,
 			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"openai-responses">,
 		"gpt-4o": {
 			id: "gpt-4o",
 			name: "GPT-4o",
@@ -2712,7 +2708,7 @@ export const MODELS = {
 		"gpt-5-mini": {
 			id: "gpt-5-mini",
 			name: "GPT-5-mini",
-			api: "openai-completions",
+			api: "openai-responses",
 			provider: "github-copilot",
 			baseUrl: "https://api.individual.githubcopilot.com",
 			headers: {
@@ -2721,7 +2717,6 @@ export const MODELS = {
 				"Editor-Plugin-Version": "copilot-chat/0.35.0",
 				"Copilot-Integration-Id": "vscode-chat",
 			},
-			compat: { supportsStore: false, supportsDeveloperRole: false, supportsReasoningEffort: false },
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -2732,7 +2727,7 @@ export const MODELS = {
 			},
 			contextWindow: 128000,
 			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"openai-responses">,
 		"gemini-2.5-pro": {
 			id: "gemini-2.5-pro",
 			name: "Gemini 2.5 Pro",
@@ -2760,7 +2755,7 @@ export const MODELS = {
 		"gpt-5.1-codex-max": {
 			id: "gpt-5.1-codex-max",
 			name: "GPT-5.1-Codex-max",
-			api: "openai-completions",
+			api: "openai-responses",
 			provider: "github-copilot",
 			baseUrl: "https://api.individual.githubcopilot.com",
 			headers: {
@@ -2769,7 +2764,6 @@ export const MODELS = {
 				"Editor-Plugin-Version": "copilot-chat/0.35.0",
 				"Copilot-Integration-Id": "vscode-chat",
 			},
-			compat: { supportsStore: false, supportsDeveloperRole: false, supportsReasoningEffort: false },
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -2780,7 +2774,7 @@ export const MODELS = {
 			},
 			contextWindow: 128000,
 			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"openai-responses">,
 		"claude-sonnet-4": {
 			id: "claude-sonnet-4",
 			name: "Claude Sonnet 4",
@@ -2808,7 +2802,7 @@ export const MODELS = {
 		"gpt-5": {
 			id: "gpt-5",
 			name: "GPT-5",
-			api: "openai-completions",
+			api: "openai-responses",
 			provider: "github-copilot",
 			baseUrl: "https://api.individual.githubcopilot.com",
 			headers: {
@@ -2817,7 +2811,6 @@ export const MODELS = {
 				"Editor-Plugin-Version": "copilot-chat/0.35.0",
 				"Copilot-Integration-Id": "vscode-chat",
 			},
-			compat: { supportsStore: false, supportsDeveloperRole: false, supportsReasoningEffort: false },
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -2828,7 +2821,7 @@ export const MODELS = {
 			},
 			contextWindow: 128000,
 			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"openai-responses">,
 		"claude-opus-4.5": {
 			id: "claude-opus-4.5",
 			name: "Claude Opus 4.5",
@@ -2856,7 +2849,7 @@ export const MODELS = {
 		"gpt-5.2": {
 			id: "gpt-5.2",
 			name: "GPT-5.2",
-			api: "openai-completions",
+			api: "openai-responses",
 			provider: "github-copilot",
 			baseUrl: "https://api.individual.githubcopilot.com",
 			headers: {
@@ -2865,7 +2858,6 @@ export const MODELS = {
 				"Editor-Plugin-Version": "copilot-chat/0.35.0",
 				"Copilot-Integration-Id": "vscode-chat",
 			},
-			compat: { supportsStore: false, supportsDeveloperRole: false, supportsReasoningEffort: false },
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -2876,7 +2868,7 @@ export const MODELS = {
 			},
 			contextWindow: 128000,
 			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"openai-responses">,
 		"claude-sonnet-4.5": {
 			id: "claude-sonnet-4.5",
 			name: "Claude Sonnet 4.5",
@@ -6031,9 +6023,9 @@ export const MODELS = {
 			contextWindow: 32768,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"anthropic/claude-3.5-haiku": {
-			id: "anthropic/claude-3.5-haiku",
-			name: "Anthropic: Claude 3.5 Haiku",
+		"anthropic/claude-3.5-haiku-20241022": {
+			id: "anthropic/claude-3.5-haiku-20241022",
+			name: "Anthropic: Claude 3.5 Haiku (2024-10-22)",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
@@ -6048,9 +6040,9 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
-		"anthropic/claude-3.5-haiku-20241022": {
-			id: "anthropic/claude-3.5-haiku-20241022",
-			name: "Anthropic: Claude 3.5 Haiku (2024-10-22)",
+		"anthropic/claude-3.5-haiku": {
+			id: "anthropic/claude-3.5-haiku",
+			name: "Anthropic: Claude 3.5 Haiku",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
@@ -6082,23 +6074,6 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
-		"mistralai/ministral-3b": {
-			id: "mistralai/ministral-3b",
-			name: "Mistral: Ministral 3B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.04,
-				output: 0.04,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 		"mistralai/ministral-8b": {
 			id: "mistralai/ministral-8b",
 			name: "Mistral: Ministral 8B",
@@ -6116,6 +6091,23 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"mistralai/ministral-3b": {
+			id: "mistralai/ministral-3b",
+			name: "Mistral: Ministral 3B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.04,
+				output: 0.04,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"nvidia/llama-3.1-nemotron-70b-instruct": {
 			id: "nvidia/llama-3.1-nemotron-70b-instruct",
 			name: "NVIDIA: Llama 3.1 Nemotron 70B Instruct",
@@ -6303,23 +6295,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-3.1-70b-instruct": {
-			id: "meta-llama/llama-3.1-70b-instruct",
-			name: "Meta: Llama 3.1 70B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.39999999999999997,
-				output: 0.39999999999999997,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 		"meta-llama/llama-3.1-405b-instruct": {
 			id: "meta-llama/llama-3.1-405b-instruct",
 			name: "Meta: Llama 3.1 405B Instruct",
@@ -6337,6 +6312,23 @@ export const MODELS = {
 			contextWindow: 130815,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-3.1-70b-instruct": {
+			id: "meta-llama/llama-3.1-70b-instruct",
+			name: "Meta: Llama 3.1 70B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.39999999999999997,
+				output: 0.39999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"mistralai/mistral-nemo": {
 			id: "mistralai/mistral-nemo",
 			name: "Mistral: Mistral Nemo",
@@ -6473,6 +6465,23 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"openai/gpt-4o-2024-05-13": {
+			id: "openai/gpt-4o-2024-05-13",
+			name: "OpenAI: GPT-4o (2024-05-13)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 5,
+				output: 15,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"openai/gpt-4o": {
 			id: "openai/gpt-4o",
 			name: "OpenAI: GPT-4o",
@@ -6507,22 +6516,22 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 64000,
 		} satisfies Model<"openai-completions">,
-		"openai/gpt-4o-2024-05-13": {
-			id: "openai/gpt-4o-2024-05-13",
-			name: "OpenAI: GPT-4o (2024-05-13)",
+		"meta-llama/llama-3-70b-instruct": {
+			id: "meta-llama/llama-3-70b-instruct",
+			name: "Meta: Llama 3 70B Instruct",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: false,
-			input: ["text", "image"],
+			input: ["text"],
 			cost: {
-				input: 5,
-				output: 15,
+				input: 0.3,
+				output: 0.39999999999999997,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
-			maxTokens: 4096,
+			contextWindow: 8192,
+			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
 		"meta-llama/llama-3-8b-instruct": {
 			id: "meta-llama/llama-3-8b-instruct",
@@ -6541,23 +6550,6 @@ export const MODELS = {
 			contextWindow: 8192,
 			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-3-70b-instruct": {
-			id: "meta-llama/llama-3-70b-instruct",
-			name: "Meta: Llama 3 70B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 0.39999999999999997,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
 		"mistralai/mixtral-8x22b-instruct": {
 			id: "mistralai/mixtral-8x22b-instruct",
 			name: "Mistral: Mixtral 8x22B Instruct",
@@ -6762,23 +6754,6 @@ export const MODELS = {
 			contextWindow: 8191,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"openai/gpt-3.5-turbo": {
-			id: "openai/gpt-3.5-turbo",
-			name: "OpenAI: GPT-3.5 Turbo",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.5,
-				output: 1.5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 16385,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 		"openai/gpt-4": {
 			id: "openai/gpt-4",
 			name: "OpenAI: GPT-4",
@@ -6796,6 +6771,23 @@ export const MODELS = {
 			contextWindow: 8191,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"openai/gpt-3.5-turbo": {
+			id: "openai/gpt-3.5-turbo",
+			name: "OpenAI: GPT-3.5 Turbo",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.5,
+				output: 1.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 16385,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"openrouter/auto": {
 			id: "openrouter/auto",
 			name: "OpenRouter: Auto Router",
diff --git a/packages/ai/src/providers/transorm-messages.ts b/packages/ai/src/providers/transorm-messages.ts
index 72f32ba7..c1c047f6 100644
--- a/packages/ai/src/providers/transorm-messages.ts
+++ b/packages/ai/src/providers/transorm-messages.ts
@@ -1,10 +1,31 @@
-import type { Api, AssistantMessage, Message, Model } from "../types.js";
+import type { Api, AssistantMessage, Message, Model, ToolCall } from "../types.js";
+
+/**
+ * Normalize tool call ID for GitHub Copilot cross-API compatibility.
+ * OpenAI Responses API generates IDs that are 450+ chars with special characters like `|`.
+ * Other APIs (Claude, etc.) require max 40 chars and only alphanumeric + underscore + hyphen.
+ */
+function normalizeCopilotToolCallId(id: string): string {
+	return id.replace(/[^a-zA-Z0-9_-]/g, "").slice(0, 40);
+}
 
 export function transformMessages<TApi extends Api>(messages: Message[], model: Model<TApi>): Message[] {
+	// Build a map of original tool call IDs to normalized IDs for github-copilot cross-API switches
+	const toolCallIdMap = new Map<string, string>();
+
 	return messages
 		.map((msg) => {
-			// User and toolResult messages pass through unchanged
-			if (msg.role === "user" || msg.role === "toolResult") {
+			// User messages pass through unchanged
+			if (msg.role === "user") {
+				return msg;
+			}
+
+			// Handle toolResult messages - normalize toolCallId if we have a mapping
+			if (msg.role === "toolResult") {
+				const normalizedId = toolCallIdMap.get(msg.toolCallId);
+				if (normalizedId && normalizedId !== msg.toolCallId) {
+					return { ...msg, toolCallId: normalizedId };
+				}
 				return msg;
 			}
 
@@ -17,6 +38,12 @@ export function transformMessages<TApi extends Api>(messages: Message[], model:
 					return msg;
 				}
 
+				// Check if we need to normalize tool call IDs (github-copilot cross-API)
+				const needsToolCallIdNormalization =
+					assistantMsg.provider === "github-copilot" &&
+					model.provider === "github-copilot" &&
+					assistantMsg.api !== model.api;
+
 				// Transform message from different provider/model
 				const transformedContent = assistantMsg.content.map((block) => {
 					if (block.type === "thinking") {
@@ -26,7 +53,16 @@ export function transformMessages<TApi extends Api>(messages: Message[], model:
 							text: `<thinking>\n${block.thinking}\n</thinking>`,
 						};
 					}
-					// All other blocks (text, toolCall) pass through unchanged
+					// Normalize tool call IDs for github-copilot cross-API switches
+					if (block.type === "toolCall" && needsToolCallIdNormalization) {
+						const toolCall = block as ToolCall;
+						const normalizedId = normalizeCopilotToolCallId(toolCall.id);
+						if (normalizedId !== toolCall.id) {
+							toolCallIdMap.set(toolCall.id, normalizedId);
+							return { ...toolCall, id: normalizedId };
+						}
+					}
+					// All other blocks pass through unchanged
 					return block;
 				});
 
diff --git a/packages/coding-agent/README.md b/packages/coding-agent/README.md
index 1878998b..2675cfde 100644
--- a/packages/coding-agent/README.md
+++ b/packages/coding-agent/README.md
@@ -132,18 +132,11 @@ pi
 /login  # Select "GitHub Copilot", authorize in browser
 ```
 
-During login, you'll be prompted for an enterprise domain. Press Enter to use github.com, or enter your GitHub Enterprise Server domain (e.g., `github.mycompany.com`).
+During login, you'll be prompted for an enterprise domain. Press Enter to use github.com, or enter your GitHub Enterprise Server domain (e.g., `github.mycompany.com`). All models are automatically enabled after login.
 
-Some models require explicit enablement before use. If you get "The requested model is not supported" error:
+If you get "The requested model is not supported" error, enable the model manually in VS Code: open Copilot Chat, click the model selector, select the model (warning icon), and click "Enable".
 
-1. Open VS Code with GitHub Copilot Chat extension
-2. Open the Copilot Chat panel and click the model selector
-3. Select the model (marked with a warning icon)
-4. Click "Enable" to accept the terms
-
-For enterprise users, check with your organization's Copilot administrator for model availability and policies.
-
-Note: Enabling some models (e.g., Grok from xAI) may involve sharing usage data with the provider. Review the terms before enabling.
+For enterprise users, check with your organization's Copilot administrator for model availability.
 
 Tokens stored in `~/.pi/agent/oauth.json` (mode 0600). Use `/logout` to clear.
 
diff --git a/packages/coding-agent/src/core/oauth/github-copilot.ts b/packages/coding-agent/src/core/oauth/github-copilot.ts
index 600d9f2a..0530c3e5 100644
--- a/packages/coding-agent/src/core/oauth/github-copilot.ts
+++ b/packages/coding-agent/src/core/oauth/github-copilot.ts
@@ -1,3 +1,4 @@
+import { getModels } from "@mariozechner/pi-ai";
 import type { OAuthCredentials } from "./storage.js";
 
 const CLIENT_ID = "Iv1.b507a08c87ecfe98";
@@ -216,9 +217,58 @@ export async function refreshGitHubCopilotToken(
 	} satisfies OAuthCredentials;
 }
 
+/**
+ * Enable a model for the user's GitHub Copilot account.
+ * This is required for some models (like Claude, Grok) before they can be used.
+ */
+export async function enableGitHubCopilotModel(
+	token: string,
+	modelId: string,
+	enterpriseDomain?: string,
+): Promise<boolean> {
+	const baseUrl = getGitHubCopilotBaseUrl(token, enterpriseDomain);
+	const url = `${baseUrl}/models/${modelId}/policy`;
+
+	try {
+		const response = await fetch(url, {
+			method: "POST",
+			headers: {
+				"Content-Type": "application/json",
+				Authorization: `Bearer ${token}`,
+				...COPILOT_HEADERS,
+				"openai-intent": "chat-policy",
+				"x-interaction-type": "chat-policy",
+			},
+			body: JSON.stringify({ state: "enabled" }),
+		});
+		return response.ok;
+	} catch {
+		return false;
+	}
+}
+
+/**
+ * Enable all known GitHub Copilot models that may require policy acceptance.
+ * Called after successful login to ensure all models are available.
+ */
+export async function enableAllGitHubCopilotModels(
+	token: string,
+	enterpriseDomain?: string,
+	onProgress?: (model: string, success: boolean) => void,
+): Promise<void> {
+	const models = getModels("github-copilot");
+	await Promise.all(
+		models.map(async (model) => {
+			const success = await enableGitHubCopilotModel(token, model.id, enterpriseDomain);
+			onProgress?.(model.id, success);
+		}),
+	);
+}
+
 export async function loginGitHubCopilot(options: {
 	onAuth: (url: string, instructions?: string) => void;
 	onPrompt: (prompt: { message: string; placeholder?: string; allowEmpty?: boolean }) => Promise<string>;
+	onProgress?: (message: string) => void;
 }): Promise<OAuthCredentials> {
 	const input = await options.onPrompt({
 		message: "GitHub Enterprise URL/domain (blank for github.com)",
@@ -242,5 +292,11 @@ export async function loginGitHubCopilot(options: {
 		device.interval,
 		device.expires_in,
 	);
-	return await refreshGitHubCopilotToken(githubAccessToken, enterpriseDomain ?? undefined);
+	const credentials = await refreshGitHubCopilotToken(githubAccessToken, enterpriseDomain ?? undefined);
+
+	// Enable all models after successful login
+	options.onProgress?.("Enabling models...");
+	await enableAllGitHubCopilotModels(credentials.access, enterpriseDomain ?? undefined);
+
+	return credentials;
 }
diff --git a/packages/coding-agent/src/core/oauth/index.ts b/packages/coding-agent/src/core/oauth/index.ts
index 2069b00a..a5951bc3 100644
--- a/packages/coding-agent/src/core/oauth/index.ts
+++ b/packages/coding-agent/src/core/oauth/index.ts
@@ -55,6 +55,7 @@ export async function login(
 	provider: SupportedOAuthProvider,
 	onAuth: (info: OAuthAuthInfo) => void,
 	onPrompt: (prompt: OAuthPrompt) => Promise<string>,
+	onProgress?: (message: string) => void,
 ): Promise<void> {
 	switch (provider) {
 		case "anthropic":
@@ -67,6 +68,7 @@ export async function login(
 			const creds = await loginGitHubCopilot({
 				onAuth: (url, instructions) => onAuth({ url, instructions }),
 				onPrompt,
+				onProgress,
 			});
 			saveOAuthCredentials("github-copilot", creds);
 			break;
diff --git a/packages/coding-agent/src/modes/interactive/interactive-mode.ts b/packages/coding-agent/src/modes/interactive/interactive-mode.ts
index ea7dd100..1d6c92c1 100644
--- a/packages/coding-agent/src/modes/interactive/interactive-mode.ts
+++ b/packages/coding-agent/src/modes/interactive/interactive-mode.ts
@@ -1419,6 +1419,10 @@ export class InteractiveMode {
 										this.ui.requestRender();
 									});
 								},
+								(message) => {
+									this.chatContainer.addChild(new Text(theme.fg("dim", message), 1, 0));
+									this.ui.requestRender();
+								},
 							);
 
 							invalidateOAuthCache();