Remove allowDuringStreaming flag - commands always run immediately

Hook commands now always execute immediately, even during streaming.
If a command needs to interact with the LLM, it uses pi.sendMessage()
which handles queueing automatically.

This simplifies the API and eliminates the issue of queued slash
commands being sent to the LLM instead of executing.

.pi/hooks/test-command.ts

@@ -29,14 +29,6 @@ export default function (pi: HookAPI) {
 		return box;
 	});
 
-	pi.registerCommand("no-stream", {
-		description: "Send a message without streaming",
-		handler: async (ctx) => {
-			ctx.ui.notify("Sending message after streaming is done...");
-		},
-		allowDuringStreaming: true,
-	})
-
 	// Register /test-msg command
 	pi.registerCommand("test-msg", {
 		description: "Send a test custom message",

packages/ai/src/models.generated.ts

@@ -6104,9 +6104,9 @@ export const MODELS = {
 			contextWindow: 32768,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"anthropic/claude-3.5-haiku": {
+		"anthropic/claude-3.5-haiku-20241022": {
-			id: "anthropic/claude-3.5-haiku",
+			id: "anthropic/claude-3.5-haiku-20241022",
-			name: "Anthropic: Claude 3.5 Haiku",
+			name: "Anthropic: Claude 3.5 Haiku (2024-10-22)",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
@@ -6121,9 +6121,9 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
-		"anthropic/claude-3.5-haiku-20241022": {
+		"anthropic/claude-3.5-haiku": {
-			id: "anthropic/claude-3.5-haiku-20241022",
+			id: "anthropic/claude-3.5-haiku",
-			name: "Anthropic: Claude 3.5 Haiku (2024-10-22)",
+			name: "Anthropic: Claude 3.5 Haiku",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
@@ -6359,6 +6359,23 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-3.1-8b-instruct": {
+			id: "meta-llama/llama-3.1-8b-instruct",
+			name: "Meta: Llama 3.1 8B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.02,
+				output: 0.03,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 16384,
+		} 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",
@@ -6393,23 +6410,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-3.1-8b-instruct": {
-			id: "meta-llama/llama-3.1-8b-instruct",
-			name: "Meta: Llama 3.1 8B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.02,
-				output: 0.03,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
 		"mistralai/mistral-nemo": {
 			id: "mistralai/mistral-nemo",
 			name: "Mistral: Mistral Nemo",
@@ -6546,6 +6546,23 @@ 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",
@@ -6580,23 +6597,6 @@ 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)",
-			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">,
 		"meta-llama/llama-3-70b-instruct": {
 			id: "meta-llama/llama-3-70b-instruct",
 			name: "Meta: Llama 3 70B Instruct",
@@ -6835,23 +6835,6 @@ 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",
@@ -6869,6 +6852,23 @@ 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",

packages/coding-agent/examples/hooks/snake.ts

@@ -309,7 +309,7 @@ const SNAKE_SAVE_TYPE = "snake-save";
 export default function (pi: HookAPI) {
 	pi.registerCommand("snake", {
 		description: "Play Snake!",
-		allowDuringStreaming: true, // Run even during streaming, not queued
+
 		handler: async (ctx) => {
 			if (!ctx.hasUI) {
 				ctx.ui.notify("Snake requires interactive mode", "error");

packages/coding-agent/src/core/hooks/types.ts

@@ -442,8 +442,7 @@ export interface HookCommandContext {
 export interface RegisteredCommand {
 	name: string;
 	description?: string;
-	/** If true, command runs during streaming instead of being queued */
+
-	allowDuringStreaming?: boolean;
 	handler: (ctx: HookCommandContext) => Promise<void>;
 }
 
@@ -456,9 +455,9 @@ export interface HookAPI {
 	on(event: "session", handler: HookHandler<SessionEvent, SessionEventResult | void>): void;
 	// biome-ignore lint/suspicious/noConfusingVoidType: void allows handlers to not return anything
 	on(event: "context", handler: HookHandler<ContextEvent, ContextEventResult | void>): void;
-	// biome-ignore lint/suspicious/noConfusingVoidType: void allows handlers to not return anything
 	on(
 		event: "before_agent_start",
+		// biome-ignore lint/suspicious/noConfusingVoidType: void allows handlers to not return anything
 		handler: HookHandler<BeforeAgentStartEvent, BeforeAgentStartEventResult | void>,
 	): void;
 	on(event: "agent_start", handler: HookHandler<AgentStartEvent>): void;
@@ -527,10 +526,7 @@ export interface HookAPI {
 	 * Register a custom slash command.
 	 * Handler receives HookCommandContext.
 	 */
-	registerCommand(
+	registerCommand(name: string, options: { description?: string; handler: RegisteredCommand["handler"] }): void;
-		name: string,
-		options: { description?: string; allowDuringStreaming?: boolean; handler: RegisteredCommand["handler"] },
-	): void;
 
 	/**
 	 * Execute a shell command and return stdout/stderr/code.

packages/coding-agent/src/modes/interactive/interactive-mode.ts

@@ -744,13 +744,13 @@ export class InteractiveMode {
 				return;
 			}
 
-			// Check if this hook command can run during streaming (not queued)
+			// Hook commands always run immediately, even during streaming
-			if (text.startsWith("/") && this.session.hookRunner && this.session.isStreaming) {
+			// (if they need to interact with LLM, they use pi.sendMessage which handles queueing)
+			if (text.startsWith("/") && this.session.hookRunner) {
 				const spaceIndex = text.indexOf(" ");
 				const commandName = spaceIndex === -1 ? text.slice(1) : text.slice(1, spaceIndex);
 				const command = this.session.hookRunner.getCommand(commandName);
-				if (command?.allowDuringStreaming) {
+				if (command) {
-					// Execute hook command right away
 					this.editor.addToHistory(text);
 					this.editor.setText("");
 					await this.session.prompt(text);
@@ -758,7 +758,7 @@ export class InteractiveMode {
 				}
 			}
 
-			// Queue message if agent is streaming
+			// Queue regular messages if agent is streaming
 			if (this.session.isStreaming) {
 				await this.session.queueMessage(text);
 				this.updatePendingMessagesDisplay();