feat(ai,coding-agent): add OpenCode Go provider support closes #1757

packages/ai/README.md

@@ -63,6 +63,8 @@ Unified LLM API with automatic model discovery, provider configuration, token an
 - **Google Gemini CLI** (requires OAuth, see below)
 - **Antigravity** (requires OAuth, see below)
 - **Amazon Bedrock**
+- **OpenCode Zen**
+- **OpenCode Go**
 - **Kimi For Coding** (Moonshot AI, uses Anthropic-compatible API)
 - **Any OpenAI-compatible API**: Ollama, vLLM, LM Studio, etc.
 
@@ -905,6 +907,7 @@ In Node.js environments, you can set environment variables to avoid passing API
 | Vercel AI Gateway | `AI_GATEWAY_API_KEY` |
 | zAI | `ZAI_API_KEY` |
 | MiniMax | `MINIMAX_API_KEY` |
+| OpenCode Zen / OpenCode Go | `OPENCODE_API_KEY` |
 | Kimi For Coding | `KIMI_API_KEY` |
 | GitHub Copilot | `COPILOT_GITHUB_TOKEN` or `GH_TOKEN` or `GITHUB_TOKEN` |
 

packages/ai/scripts/generate-models.ts

@@ -460,14 +460,21 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 			}
 		}
 
-		// Process OpenCode Zen models
+		// Process OpenCode models (Zen and Go)
 		// API mapping based on provider.npm field:
 		// - @ai-sdk/openai → openai-responses
 		// - @ai-sdk/anthropic → anthropic-messages
 		// - @ai-sdk/google → google-generative-ai
 		// - null/undefined/@ai-sdk/openai-compatible → openai-completions
-		if (data.opencode?.models) {
-			for (const [modelId, model] of Object.entries(data.opencode.models)) {
+		const opencodeVariants = [
+			{ key: "opencode", provider: "opencode", basePath: "https://opencode.ai/zen" },
+			{ key: "opencode-go", provider: "opencode-go", basePath: "https://opencode.ai/zen/go" },
+		] as const;
+
+		for (const variant of opencodeVariants) {
+			if (!data[variant.key]?.models) continue;
+
+			for (const [modelId, model] of Object.entries(data[variant.key].models)) {
 				const m = model as ModelsDevModel & { status?: string };
 				if (m.tool_call !== true) continue;
 				if (m.status === "deprecated") continue;
@@ -478,25 +485,25 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 
 				if (npm === "@ai-sdk/openai") {
 					api = "openai-responses";
-					baseUrl = "https://opencode.ai/zen/v1";
+					baseUrl = `${variant.basePath}/v1`;
 				} else if (npm === "@ai-sdk/anthropic") {
 					api = "anthropic-messages";
 					// Anthropic SDK appends /v1/messages to baseURL
-					baseUrl = "https://opencode.ai/zen";
+					baseUrl = variant.basePath;
 				} else if (npm === "@ai-sdk/google") {
 					api = "google-generative-ai";
-					baseUrl = "https://opencode.ai/zen/v1";
+					baseUrl = `${variant.basePath}/v1`;
 				} else {
 					// null, undefined, or @ai-sdk/openai-compatible
 					api = "openai-completions";
-					baseUrl = "https://opencode.ai/zen/v1";
+					baseUrl = `${variant.basePath}/v1`;
 				}
 
 				models.push({
 					id: modelId,
 					name: m.name || modelId,
 					api,
-					provider: "opencode",
+					provider: variant.provider,
 					baseUrl,
 					reasoning: m.reasoning === true,
 					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
@@ -657,11 +664,17 @@ async function generateModels() {
 			candidate.cost.cacheWrite = 6.25;
 			candidate.contextWindow = 200000;
 		}
-		if ((candidate.provider === "anthropic" || candidate.provider === "opencode") && candidate.id === "claude-opus-4-6") {
+		if (
+			(candidate.provider === "anthropic" || candidate.provider === "opencode" || candidate.provider === "opencode-go") &&
+			candidate.id === "claude-opus-4-6"
+		) {
 			candidate.contextWindow = 200000;
 		}
-		// opencode lists Claude Sonnet 4/4.5 with 1M context, actual limit is 200K
-		if (candidate.provider === "opencode" && (candidate.id === "claude-sonnet-4-5" || candidate.id === "claude-sonnet-4")) {
+		// OpenCode variants list Claude Sonnet 4/4.5 with 1M context, actual limit is 200K
+		if (
+			(candidate.provider === "opencode" || candidate.provider === "opencode-go") &&
+			(candidate.id === "claude-sonnet-4-5" || candidate.id === "claude-sonnet-4")
+		) {
 			candidate.contextWindow = 200000;
 		}
 	}

packages/ai/src/env-api-keys.ts

@@ -113,6 +113,7 @@ export function getEnvApiKey(provider: any): string | undefined {
 		"minimax-cn": "MINIMAX_CN_API_KEY",
 		huggingface: "HF_TOKEN",
 		opencode: "OPENCODE_API_KEY",
+		"opencode-go": "OPENCODE_API_KEY",
 		"kimi-coding": "KIMI_API_KEY",
 	};
 

packages/ai/src/models.generated.ts

@@ -6155,6 +6155,59 @@ export const MODELS = {
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
 	},
+	"opencode-go": {
+		"glm-5": {
+			id: "glm-5",
+			name: "GLM-5",
+			api: "openai-completions",
+			provider: "opencode-go",
+			baseUrl: "https://opencode.ai/zen/go/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1,
+				output: 3.2,
+				cacheRead: 0.2,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"kimi-k2.5": {
+			id: "kimi-k2.5",
+			name: "Kimi K2.5",
+			api: "openai-completions",
+			provider: "opencode-go",
+			baseUrl: "https://opencode.ai/zen/go/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.6,
+				output: 3,
+				cacheRead: 0.1,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"minimax-m2.5": {
+			id: "minimax-m2.5",
+			name: "MiniMax M2.5",
+			api: "anthropic-messages",
+			provider: "opencode-go",
+			baseUrl: "https://opencode.ai/zen/go",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0.03,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"anthropic-messages">,
+	},
 	"openrouter": {
 		"ai21/jamba-large-1.7": {
 			id: "ai21/jamba-large-1.7",

packages/ai/src/types.ts

@@ -37,6 +37,7 @@ export type KnownProvider =
 	| "minimax-cn"
 	| "huggingface"
 	| "opencode"
+	| "opencode-go"
 	| "kimi-coding";
 export type Provider = KnownProvider | string;
 

packages/ai/test/cross-provider-handoff.test.ts

@@ -101,6 +101,9 @@ const PROVIDER_MODEL_PAIRS: ProviderModelPair[] = [
 	{ provider: "opencode", model: "glm-4.7-free", label: "zen-glm-4.7-free" },
 	{ provider: "opencode", model: "gpt-5.2-codex", label: "zen-gpt-5.2-codex" },
 	{ provider: "opencode", model: "minimax-m2.1-free", label: "zen-minimax-m2.1-free" },
+	// OpenCode Go
+	{ provider: "opencode-go", model: "kimi-k2.5", label: "go-kimi-k2.5" },
+	{ provider: "opencode-go", model: "minimax-m2.5", label: "go-minimax-m2.5" },
 ];
 
 // Cached context structure

packages/ai/test/zen.test.ts

@@ -3,17 +3,23 @@ import { MODELS } from "../src/models.generated.js";
 import { complete } from "../src/stream.js";
 import type { Model } from "../src/types.js";
 
-describe.skipIf(!process.env.OPENCODE_API_KEY)("OpenCode Zen Models Smoke Test", () => {
-	const zenModels = Object.values(MODELS.opencode);
+describe.skipIf(!process.env.OPENCODE_API_KEY)("OpenCode Models Smoke Test", () => {
+	const providers = [
+		{ key: "opencode", label: "OpenCode Zen" },
+		{ key: "opencode-go", label: "OpenCode Go" },
+	] as const;
 
-	zenModels.forEach((model) => {
-		it(`${model.id}`, async () => {
-			const response = await complete(model as Model<any>, {
-				messages: [{ role: "user", content: "Say hello.", timestamp: Date.now() }],
-			});
+	providers.forEach(({ key, label }) => {
+		const providerModels = Object.values(MODELS[key]);
+		providerModels.forEach((model) => {
+			it(`${label}: ${model.id}`, async () => {
+				const response = await complete(model as Model<any>, {
+					messages: [{ role: "user", content: "Say hello.", timestamp: Date.now() }],
+				});
 
-			expect(response.content).toBeTruthy();
-			expect(response.stopReason).toBe("stop");
-		}, 60000);
+				expect(response.content).toBeTruthy();
+				expect(response.stopReason).toBe("stop");
+			}, 60000);
+		});
 	});
 });

packages/coding-agent/README.md

@@ -98,6 +98,7 @@ For each built-in provider, pi maintains a list of tool-capable models, updated
 - Vercel AI Gateway
 - ZAI
 - OpenCode Zen
+- OpenCode Go
 - Hugging Face
 - Kimi For Coding
 - MiniMax

packages/coding-agent/docs/providers.md

@@ -65,6 +65,7 @@ pi
 | Vercel AI Gateway | `AI_GATEWAY_API_KEY` | `vercel-ai-gateway` |
 | ZAI | `ZAI_API_KEY` | `zai` |
 | OpenCode Zen | `OPENCODE_API_KEY` | `opencode` |
+| OpenCode Go | `OPENCODE_API_KEY` | `opencode-go` |
 | Hugging Face | `HF_TOKEN` | `huggingface` |
 | Kimi For Coding | `KIMI_API_KEY` | `kimi-coding` |
 | MiniMax | `MINIMAX_API_KEY` | `minimax` |
@@ -81,7 +82,8 @@ Store credentials in `~/.pi/agent/auth.json`:
   "anthropic": { "type": "api_key", "key": "sk-ant-..." },
   "openai": { "type": "api_key", "key": "sk-..." },
   "google": { "type": "api_key", "key": "..." },
-  "opencode": { "type": "api_key", "key": "..." }
+  "opencode": { "type": "api_key", "key": "..." },
+  "opencode-go": { "type": "api_key", "key": "..." }
 }
 ```
 

packages/coding-agent/src/cli/args.ts

@@ -291,6 +291,7 @@ ${chalk.bold("Environment Variables:")}
   ZAI_API_KEY                      - ZAI API key
   MISTRAL_API_KEY                  - Mistral API key
   MINIMAX_API_KEY                  - MiniMax API key
+  OPENCODE_API_KEY                 - OpenCode Zen/OpenCode Go API key
   KIMI_API_KEY                     - Kimi For Coding API key
   AWS_PROFILE                      - AWS profile for Amazon Bedrock
   AWS_ACCESS_KEY_ID                - AWS access key for Amazon Bedrock

packages/coding-agent/src/core/model-resolver.ts

@@ -33,6 +33,7 @@ export const defaultModelPerProvider: Record<KnownProvider, string> = {
 	"minimax-cn": "MiniMax-M2.1",
 	huggingface: "moonshotai/Kimi-K2.5",
 	opencode: "claude-opus-4-6",
+	"opencode-go": "kimi-k2.5",
 	"kimi-coding": "kimi-k2-thinking",
 };