fix(ai): move OpenCode providers to inference endpoints

- Use opencode.ai/inference and opencode.ai/inference/go base URLs; /zen/go has no Gemini route (404)
- Add google-generative-ai support to the OpenCode Go provider
- Use Anthropic Messages for OpenCode Go minimax-m2.7; openai-completions now returns ModelProtocolUnsupported
- Remove test for opencode-go deepseek-v4-flash, which is no longer listed

packages/ai/CHANGELOG.md

@@ -6,6 +6,8 @@
 
 - Fixed tool-call argument parsing dropping fields when a string contains an invalid `\u` escape such as `\usepackage` ([#10868](https://github.com/earendil-works/pi/issues/10868))
 - Fixed Anthropic requests failing with a 400 when an error tool result contains images; the images are now replaced with a text note ([#10794](https://github.com/earendil-works/pi/issues/10794))
+- Fixed OpenCode Go Gemini models failing with a 404 by moving OpenCode Zen and OpenCode Go to the `opencode.ai/inference` endpoints, and added Google Generative AI support to the OpenCode Go provider
+- Fixed OpenCode Go MiniMax M2.7 failing with "Model does not support this protocol" by using the Anthropic Messages API
 
 ## [1.2.0] - 2026-10-12
 

packages/ai/scripts/generate-models.ts

@@ -2159,8 +2159,8 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 		// - @ai-sdk/google → google-generative-ai
 		// - null/undefined/@ai-sdk/openai-compatible → openai-completions
 		const opencodeVariants = [
-			{ key: "opencode", provider: "opencode", basePath: "https://opencode.ai/zen" },
-			{ key: "opencode-go", provider: "opencode-go", basePath: "https://opencode.ai/zen/go" },
+			{ key: "opencode", provider: "opencode", basePath: "https://opencode.ai/inference" },
+			{ key: "opencode-go", provider: "opencode-go", basePath: "https://opencode.ai/inference/go" },
 		] as const;
 
 		for (const variant of opencodeVariants) {
@@ -2209,16 +2209,9 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 
 				// Fix known mismatches between models.dev npm data and actual
 				// OpenCode Go endpoint behaviour. models.dev reports these models
-				// as @ai-sdk/anthropic, but the OpenCode Go endpoints either don't
-				// accept Anthropic SDK auth (MiniMax M2.7) or are served through
-				// the OpenAI-compatible /v1/chat/completions path (Qwen 3.5/3.6).
-				// Switch them to openai-completions so requests use Bearer auth
-				// and the standard /v1/chat/completions endpoint.
+				// as @ai-sdk/anthropic, but OpenCode Go serves them through the
+				// OpenAI-compatible /v1/chat/completions path.
 				if (variant.provider === "opencode-go") {
-					if (modelId === "minimax-m2.7") {
-						api = "openai-completions";
-						baseUrl = `${variant.basePath}/v1`;
-					}
 					if (modelId === "qwen3.5-plus" || modelId === "qwen3.6-plus") {
 						api = "openai-completions";
 						baseUrl = `${variant.basePath}/v1`;
@@ -2619,7 +2612,7 @@ async function loadModelsDevClassifierModels(): Promise<ClassifierModel<"typesaf
 // System One models yet. Cloudflare publishes pricing only in the dashboard.
 // https://developers.cloudflare.com/ai/models/typesafe/jev/
 // OpenCode Zen serves Jev through its TypeSafe-compatible System One endpoint.
-// Neither its /zen/v1/models listing nor models.dev carries metadata for it.
+// Neither its /inference/v1/models listing nor models.dev carries metadata for it.
 // https://opencode.ai/docs/zen
 const OPENCODE_CLASSIFIER_MODELS: ClassifierModel<"typesafe-system-one">[] = [
 	{
@@ -2628,7 +2621,7 @@ const OPENCODE_CLASSIFIER_MODELS: ClassifierModel<"typesafe-system-one">[] = [
 		name: "Jev 1.13",
 		api: "typesafe-system-one",
 		provider: "opencode",
-		baseUrl: "https://opencode.ai/zen/v1",
+		baseUrl: "https://opencode.ai/inference/v1",
 		input: ["text"],
 		cost: { input: 0.042, output: 0, cacheRead: 0, cacheWrite: 0 },
 		contextWindow: 32000,
@@ -2639,7 +2632,7 @@ const OPENCODE_CLASSIFIER_MODELS: ClassifierModel<"typesafe-system-one">[] = [
 		name: "Jev 1.13 Free",
 		api: "typesafe-system-one",
 		provider: "opencode",
-		baseUrl: "https://opencode.ai/zen/v1",
+		baseUrl: "https://opencode.ai/inference/v1",
 		input: ["text"],
 		cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
 		contextWindow: 32000,

packages/ai/src/providers/opencode-go.ts

@@ -1,4 +1,5 @@
 import { anthropicMessagesApi } from "../api/anthropic-messages.lazy.ts";
+import { googleGenerativeAIApi } from "../api/google-generative-ai.lazy.ts";
 import { openAICompletionsApi } from "../api/openai-completions.lazy.ts";
 import { openAIResponsesApi } from "../api/openai-responses.lazy.ts";
 import { envApiKeyAuth } from "../auth/helpers.ts";
@@ -6,14 +7,17 @@ import { createProvider, type Provider } from "../models.ts";
 import { OPENCODE_GO_MODELS } from "./opencode-go.models.ts";
 import { withOpenCodeSessionHeader } from "./opencode-headers.ts";
 
-export function opencodeGoProvider(): Provider<"anthropic-messages" | "openai-completions" | "openai-responses"> {
-	return createProvider<"anthropic-messages" | "openai-completions" | "openai-responses">({
+type OpenCodeGoApi = "anthropic-messages" | "google-generative-ai" | "openai-completions" | "openai-responses";
+
+export function opencodeGoProvider(): Provider<OpenCodeGoApi> {
+	return createProvider<OpenCodeGoApi>({
 		id: "opencode-go",
 		name: "OpenCode Go",
 		auth: { apiKey: envApiKeyAuth("OpenCode API key", ["OPENCODE_API_KEY"]) },
 		models: Object.values(OPENCODE_GO_MODELS),
 		api: {
 			"anthropic-messages": withOpenCodeSessionHeader(anthropicMessagesApi()),
+			"google-generative-ai": withOpenCodeSessionHeader(googleGenerativeAIApi()),
 			"openai-completions": withOpenCodeSessionHeader(openAICompletionsApi()),
 			"openai-responses": withOpenCodeSessionHeader(openAIResponsesApi()),
 		},

packages/ai/test/classifier-models.test.ts

@@ -130,8 +130,8 @@ describe("Models with classifier models", () => {
 
 	it.each([
 		["vercel-ai-gateway", "typesafe-ai/jev", "https://ai-gateway.vercel.sh/typesafe/v1/systemone"],
-		["opencode", "jev-1.13", "https://opencode.ai/zen/v1/systemone"],
-		["opencode", "jev-1.13-free", "https://opencode.ai/zen/v1/systemone"],
+		["opencode", "jev-1.13", "https://opencode.ai/inference/v1/systemone"],
+		["opencode", "jev-1.13-free", "https://opencode.ai/inference/v1/systemone"],
 	])("routes %s Jev (%s) to its TypeSafe-compatible endpoint", async (provider, id, url) => {
 		const models = builtinModels();
 		const jev = models.getModelOfType("classifier", provider, id);

packages/ai/test/supports-xhigh.test.ts

@@ -175,12 +175,6 @@ describe("getSupportedThinkingLevels", () => {
 		expect(getSupportedThinkingLevels(model!)).toEqual(["off", "low", "high", "max"]);
 	});
 
-	it("includes low/high/max plus off for DeepSeek V4 Flash on opencode-go", () => {
-		const model = getModel("opencode-go", "deepseek-v4-flash");
-		expect(model).toBeDefined();
-		expect(getSupportedThinkingLevels(model!)).toEqual(["off", "low", "high", "max"]);
-	});
-
 	it("preserves low/high/max metadata for DeepSeek V4.1 Flash on OpenRouter", () => {
 		const model = getModel("openrouter", "deepseek/deepseek-v4.1-flash");
 		expect(model).toBeDefined();