fix(ai): use OpenCode protocol-specific endpoints (#11434)

closes #11132

pi sends every opencode and opencode-go request to the shared base
(`https://opencode.ai/inference/v1`, `/inference/go/v1`), Jev included.
this switches them to the documented protocol-specific endpoints, which
is also what models.dev lists per model:

| api | before | after |
|---|---|---|
| openai-completions / openai-responses | `/inference/v1` |
`/inference/openai/v1` |
| anthropic-messages | `/inference` | `/inference/anthropic` (SDK
appends `/v1/messages`) |
| google-generative-ai | `/inference/v1` | `/inference/google/v1beta` |
| jev-1.13 / jev-1.13-free | `/inference/v1` | `/inference/systemone/v1`
|

go uses the same paths under `/inference/go/...`.

changes: base URLs in `generate-models.ts`, the jev URL expectations in
`test/classifier-models.test.ts`, and a stale comment in
`providers/opencode.ts`. `models.generated.ts` has no diff since the
catalog data is gitignored.

verified with the regenerated catalog:
- all 111 opencode/opencode-go models hit their new URL, none 404
- real requests with an OpenCode key returned replies on
anthropic-messages, google-generative-ai, openai-responses,
openai-completions and jev
- go returned 403 "subscription required" from the new paths (my key has
no Go sub), so routing works there too

`npm run check` passes. `./test.sh` passes for ai and coding-agent; the
only remaining failures were timeouts that pass in isolation and pi-env
tests that need cargo locally.

---

_Drafted with AI assistance, reviewed by me._

packages/ai/scripts/generate-models.ts

@@ -2272,23 +2272,23 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 
 				if (npm === "@ai-sdk/openai") {
 					api = "openai-responses";
-					baseUrl = `${variant.basePath}/v1`;
+					baseUrl = `${variant.basePath}/openai/v1`;
 					compat = { sessionAffinityFormat: "openai-nosession" };
 				} else if (npm === "@ai-sdk/anthropic") {
 					api = "anthropic-messages";
 					// Anthropic SDK appends /v1/messages to baseURL
-					baseUrl = variant.basePath;
+					baseUrl = `${variant.basePath}/anthropic`;
 				} else if (npm === "@ai-sdk/google") {
 					api = "google-generative-ai";
-					baseUrl = `${variant.basePath}/v1`;
+					baseUrl = `${variant.basePath}/google/v1beta`;
 				} else if (npm === "@ai-sdk/alibaba") {
 					api = "openai-completions";
-					baseUrl = `${variant.basePath}/v1`;
+					baseUrl = `${variant.basePath}/openai/v1`;
 					compat = { cacheControlFormat: "anthropic" };
 				} else {
 					// null, undefined, or @ai-sdk/openai-compatible
 					api = "openai-completions";
-					baseUrl = `${variant.basePath}/v1`;
+					baseUrl = `${variant.basePath}/openai/v1`;
 				}
 
 				if (variant.provider === "opencode" && modelId === "grok-build-0.1") {
@@ -2304,11 +2304,11 @@ 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 OpenCode Go serves them through the
-				// OpenAI-compatible /v1/chat/completions path.
+				// OpenAI-compatible /openai/v1/chat/completions path.
 				if (variant.provider === "opencode-go") {
 					if (modelId === "qwen3.5-plus" || modelId === "qwen3.6-plus") {
 						api = "openai-completions";
-						baseUrl = `${variant.basePath}/v1`;
+						baseUrl = `${variant.basePath}/openai/v1`;
 						// Qwen/DashScope uses enable_thinking at the top level.
 						compat = { ...(compat ?? {}), thinkingFormat: "qwen" };
 					}
@@ -2681,7 +2681,7 @@ const OPENCODE_CLASSIFIER_MODELS: ClassifierModel<"typesafe-system-one">[] = [
 		name: "Jev 1.13",
 		api: "typesafe-system-one",
 		provider: "opencode",
-		baseUrl: "https://opencode.ai/inference/v1",
+		baseUrl: "https://opencode.ai/inference/systemone/v1",
 		input: ["text"],
 		cost: { input: 0.042, output: 0, cacheRead: 0, cacheWrite: 0 },
 		contextWindow: 32000,
@@ -2692,7 +2692,7 @@ const OPENCODE_CLASSIFIER_MODELS: ClassifierModel<"typesafe-system-one">[] = [
 		name: "Jev 1.13 Free",
 		api: "typesafe-system-one",
 		provider: "opencode",
-		baseUrl: "https://opencode.ai/inference/v1",
+		baseUrl: "https://opencode.ai/inference/systemone/v1",
 		input: ["text"],
 		cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
 		contextWindow: 32000,

packages/ai/src/providers/opencode.ts

@@ -22,7 +22,7 @@ export function opencodeProvider(): Provider<OpenCodeApi> {
 			"openai-completions": withOpenCodeSessionHeader(openAICompletionsApi()),
 			"openai-responses": withOpenCodeSessionHeader(openAIResponsesApi()),
 		},
-		// OpenCode Zen serves TypeSafe's System One protocol at /zen/v1/systemone.
+		// OpenCode Zen serves TypeSafe's System One protocol at /inference/systemone/v1/systemone.
 		classifiers: { "typesafe-system-one": typesafeSystemOneApi() },
 	});
 }

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/inference/v1/systemone"],
-		["opencode", "jev-1.13-free", "https://opencode.ai/inference/v1/systemone"],
+		["opencode", "jev-1.13", "https://opencode.ai/inference/systemone/v1/systemone"],
+		["opencode", "jev-1.13-free", "https://opencode.ai/inference/systemone/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);