@oh-my-pi/pi-ai 9.2.0 → 9.2.2

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@oh-my-pi/pi-ai",
-	"version": "9.2.0",
+	"version": "9.2.2",
 	"description": "Unified LLM API with automatic model discovery and provider configuration",
 	"type": "module",
 	"main": "./src/index.ts",
@@ -63,7 +63,7 @@
 		"@connectrpc/connect-node": "^2.1.1",
 		"@google/genai": "^1.38.0",
 		"@mistralai/mistralai": "^1.13.0",
-		"@oh-my-pi/pi-utils": "9.2.0",
+		"@oh-my-pi/pi-utils": "9.2.2",
 		"@sinclair/typebox": "^0.34.48",
 		"@smithy/node-http-handler": "^4.4.8",
 		"ajv": "^8.17.1",

package/src/models.generated.ts

@@ -3102,8 +3102,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0,
-				output: 0,
+				input: 0.4,
+				output: 2,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -4357,6 +4357,23 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"glm-4.7-free": {
+			id: "glm-4.7-free",
+			name: "GLM-4.7 Free",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 		"gpt-5": {
 			id: "gpt-5",
 			name: "GPT-5",
@@ -4555,7 +4572,24 @@ export const MODELS = {
 			cost: {
 				input: 0.6,
 				output: 3,
-				cacheRead: 0.1,
+				cacheRead: 0.08,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"kimi-k2.5-free": {
+			id: "kimi-k2.5-free",
+			name: "Kimi K2.5 Free",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -4578,6 +4612,23 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"minimax-m2.1-free": {
+			id: "minimax-m2.1-free",
+			name: "MiniMax M2.1 Free",
+			api: "anthropic-messages",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"anthropic-messages">,
 		"qwen3-coder": {
 			id: "qwen3-coder",
 			name: "Qwen3 Coder",
@@ -4595,6 +4646,23 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
+		"trinity-large-preview-free": {
+			id: "trinity-large-preview-free",
+			name: "Trinity Large Preview",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 	},
 	"openrouter": {
 		"ai21/jamba-large-1.7": {
@@ -5350,23 +5418,6 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
-		"google/gemini-2.0-flash-exp:free": {
-			id: "google/gemini-2.0-flash-exp:free",
-			name: "Google: Gemini 2.0 Flash Experimental (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
 		"google/gemini-2.0-flash-lite-001": {
 			id: "google/gemini-2.0-flash-lite-001",
 			name: "Google: Gemini 2.0 Flash Lite",
@@ -6362,13 +6413,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.6,
-				output: 3,
+				input: 0.5,
+				output: 2.8,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 262144,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"nex-agi/deepseek-v3.1-nex-n1": {
 			id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -6464,13 +6515,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.06,
-				output: 0.24,
+				input: 0.049999999999999996,
+				output: 0.19999999999999998,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 262144,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"nvidia/nemotron-3-nano-30b-a3b:free": {
 			id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -8699,7 +8750,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 256000,
-			maxTokens: 256000,
+			maxTokens: 65536,
 		} satisfies Model<"anthropic-messages">,
 		"anthropic/claude-3-haiku": {
 			id: "anthropic/claude-3-haiku",
@@ -9611,9 +9662,9 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 1.2,
-				output: 1.2,
-				cacheRead: 0.6,
+				input: 0.6,
+				output: 3,
+				cacheRead: 0.09999999999999999,
 				cacheWrite: 0,
 			},
 			contextWindow: 256000,
@@ -9732,7 +9783,7 @@ export const MODELS = {
 			cost: {
 				input: 0.09999999999999999,
 				output: 0.39999999999999997,
-				cacheRead: 0.024999999999999998,
+				cacheRead: 0.03,
 				cacheWrite: 0,
 			},
 			contextWindow: 1047576,
@@ -9936,7 +9987,7 @@ export const MODELS = {
 			cost: {
 				input: 1.25,
 				output: 10,
-				cacheRead: 0.125,
+				cacheRead: 0.13,
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
@@ -9953,7 +10004,7 @@ export const MODELS = {
 			cost: {
 				input: 1.25,
 				output: 10,
-				cacheRead: 0.125,
+				cacheRead: 0.13,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -9961,7 +10012,7 @@ export const MODELS = {
 		} satisfies Model<"anthropic-messages">,
 		"openai/gpt-5.2": {
 			id: "openai/gpt-5.2",
-			name: "GPT-5.2",
+			name: "GPT 5.2",
 			api: "anthropic-messages",
 			provider: "vercel-ai-gateway",
 			baseUrl: "https://ai-gateway.vercel.sh",
@@ -9970,7 +10021,7 @@ export const MODELS = {
 			cost: {
 				input: 1.75,
 				output: 14,
-				cacheRead: 0.175,
+				cacheRead: 0.18,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -10231,40 +10282,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 131072,
 		} satisfies Model<"anthropic-messages">,
-		"stealth/sonoma-dusk-alpha": {
-			id: "stealth/sonoma-dusk-alpha",
-			name: "Sonoma Dusk Alpha",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.19999999999999998,
-				output: 0.5,
-				cacheRead: 0.049999999999999996,
-				cacheWrite: 0,
-			},
-			contextWindow: 2000000,
-			maxTokens: 131072,
-		} satisfies Model<"anthropic-messages">,
-		"stealth/sonoma-sky-alpha": {
-			id: "stealth/sonoma-sky-alpha",
-			name: "Sonoma Sky Alpha",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.19999999999999998,
-				output: 0.5,
-				cacheRead: 0.049999999999999996,
-				cacheWrite: 0,
-			},
-			contextWindow: 2000000,
-			maxTokens: 131072,
-		} satisfies Model<"anthropic-messages">,
 		"vercel/v0-1.0-md": {
 			id: "vercel/v0-1.0-md",
 			name: "v0-1.0-md",
@@ -10552,7 +10569,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 65536,
-			maxTokens: 66000,
+			maxTokens: 16384,
 		} satisfies Model<"anthropic-messages">,
 		"zai/glm-4.6": {
 			id: "zai/glm-4.6",
@@ -11143,5 +11160,23 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"glm-4.7-flash": {
+			id: "glm-4.7-flash",
+			name: "GLM-4.7-Flash",
+			api: "openai-completions",
+			provider: "zai",
+			baseUrl: "https://api.z.ai/api/coding/paas/v4",
+			compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai"},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 	},
 } as const;

package/src/utils/oauth/index.ts

@@ -48,6 +48,8 @@ export { loginKimi, refreshKimiToken } from "./kimi";
 export type { OpenAICodexLoginOptions } from "./openai-codex";
 // OpenAI Codex (ChatGPT OAuth)
 export { loginOpenAICodex, refreshOpenAICodexToken } from "./openai-codex";
+// OpenCode (API key)
+export { loginOpenCode } from "./opencode";
 
 export * from "./types";
 
@@ -93,6 +95,10 @@ export async function refreshOAuthToken(
 		case "cursor":
 			newCredentials = await refreshCursorToken(credentials.refresh);
 			break;
+		case "opencode":
+			// API keys don't expire, return as-is
+			newCredentials = credentials;
+			break;
 		default:
 			throw new Error(`Unknown OAuth provider: ${provider}`);
 	}
@@ -173,5 +179,10 @@ export function getOAuthProviders(): OAuthProviderInfo[] {
 			name: "Cursor (Claude, GPT, etc.)",
 			available: true,
 		},
+		{
+			id: "opencode",
+			name: "OpenCode Zen",
+			available: true,
+		},
 	];
 }

package/src/utils/oauth/opencode.ts

@@ -0,0 +1,50 @@
+/**
+ * OpenCode Zen login flow.
+ *
+ * OpenCode Zen is a subscription service that provides access to various AI models
+ * (GPT-5.x, Claude 4.x, Gemini 3, etc.) through a unified API at opencode.ai/zen.
+ *
+ * This is not OAuth - it's a simple API key flow:
+ * 1. Open browser to https://opencode.ai/auth
+ * 2. User logs in and copies their API key
+ * 3. User pastes the API key back into the CLI
+ */
+
+import type { OAuthController } from "./types";
+
+const AUTH_URL = "https://opencode.ai/auth";
+
+/**
+ * Login to OpenCode Zen.
+ *
+ * Opens browser to auth page, prompts user to paste their API key.
+ * Returns the API key directly (not OAuthCredentials - this isn't OAuth).
+ */
+export async function loginOpenCode(options: OAuthController): Promise<string> {
+	if (!options.onPrompt) {
+		throw new Error("OpenCode Zen login requires onPrompt callback");
+	}
+
+	// Open browser to auth page
+	options.onAuth?.({
+		url: AUTH_URL,
+		instructions: "Log in and copy your API key",
+	});
+
+	// Prompt user to paste their API key
+	const apiKey = await options.onPrompt({
+		message: "Paste your OpenCode Zen API key",
+		placeholder: "sk-...",
+	});
+
+	if (options.signal?.aborted) {
+		throw new Error("Login cancelled");
+	}
+
+	const trimmed = apiKey.trim();
+	if (!trimmed) {
+		throw new Error("API key is required");
+	}
+
+	return trimmed;
+}

package/src/utils/oauth/types.ts

@@ -15,6 +15,7 @@ export type OAuthProvider =
 	| "google-antigravity"
 	| "kimi-code"
 	| "openai-codex"
+	| "opencode"
 	| "cursor";
 
 export type OAuthPrompt = {