feat(opencode-go): register 4 missing models from upstream catalog

Add qwen3.7-max, mimo-v2-pro, mimo-v2-omni, hy3-preview to the
opencode-go provider. Extend executor tests and model specs.

- Registry now matches live https://opencode.ai/zen/go/v1/models response
  (16 models). Previously, four models returned by the upstream API were
  absent from the static registry, so requests to them failed model
  resolution before reaching the executor.
- qwen3.7-max: inherits defaultContextLength 200000; model spec mirrors
  qwen3.6-plus (Bailian multimodal, thinking + tools + vision).
- mimo-v2-pro: spec mirrors mimo-v2-omni (262144 ctx, 131072 maxOut,
  tools + vision).
- mimo-v2-omni: registry entry only (spec already present upstream).
- hy3-preview: registry entry only; falls back to __default__ spec.
- All four route to /chat/completions (default openai format), matching
  the existing opencode-go executor behavior.

open-sse/config/providerRegistry.ts

@@ -1288,10 +1288,14 @@ export const REGISTRY: Record<string, RegistryEntry> = {
       { id: "kimi-k2.5", name: "Kimi K2.5" },
       { id: "mimo-v2.5-pro", name: "MiMo-V2.5-Pro" },
       { id: "mimo-v2.5", name: "MiMo-V2.5" },
+      { id: "mimo-v2-pro", name: "MiMo-V2-Pro" },
+      { id: "mimo-v2-omni", name: "MiMo-V2-Omni" },
       { id: "minimax-m2.7", name: "MiniMax M2.7", targetFormat: "claude" },
       { id: "minimax-m2.5", name: "MiniMax M2.5", targetFormat: "claude" },
+      { id: "qwen3.7-max", name: "Qwen3.7 Max" },
       { id: "qwen3.6-plus", name: "Qwen3.6 Plus" },
       { id: "qwen3.5-plus", name: "Qwen3.5 Plus" },
+      { id: "hy3-preview", name: "Hunyuan3 Preview" },
       { id: "deepseek-v4-pro", name: "DeepSeek V4 Pro", supportsReasoning: true },
       { id: "deepseek-v4-flash", name: "DeepSeek V4 Flash", supportsReasoning: true },
     ],

src/shared/constants/modelSpecs.ts

@@ -217,6 +217,15 @@ export const MODEL_SPECS: Record<string, ModelSpec> = {
     aliases: ["kimi-k2.6-thinking", "kimi-for-coding"],
   },
 
+  // ── Qwen3.7 Max (Bailian multimodal — text/image/video) ─────────
+  "qwen3.7-max": {
+    maxOutputTokens: 8192,
+    contextWindow: 200000,
+    supportsThinking: true,
+    supportsTools: true,
+    supportsVision: true,
+  },
+
   // ── Xiaomi MiMo V2.5 (1M context, consensus across 7+ sync sources) ──
   "mimo-v2.5-pro": {
     maxOutputTokens: 131072,
@@ -230,6 +239,12 @@ export const MODEL_SPECS: Record<string, ModelSpec> = {
     supportsTools: true,
     supportsVision: true,
   },
+  "mimo-v2-pro": {
+    maxOutputTokens: 131072,
+    contextWindow: 262144,
+    supportsTools: true,
+    supportsVision: true,
+  },
   "mimo-v2-omni": {
     maxOutputTokens: 131072,
     contextWindow: 262144,

tests/unit/opencode-executor.test.ts

@@ -253,6 +253,30 @@ describe("OpencodeExecutor", () => {
       });
       assert.deepEqual(fetchCalls[0].options.headers, result.headers);
     });
+
+    it("routes opencode-go catalog-only models to chat completions", async () => {
+      // Register new models
+      registerModel("opencode-go", { id: "qwen3.7-max", name: "Qwen3.7 Max" });
+      registerModel("opencode-go", { id: "mimo-v2-pro", name: "MiMo-V2-Pro" });
+      registerModel("opencode-go", { id: "mimo-v2-omni", name: "MiMo-V2-Omni" });
+      registerModel("opencode-go", { id: "hy3-preview", name: "Hunyuan3 Preview" });
+
+      // qwen3.7-max
+      const qwen37 = await goExecutor.execute(createInput("qwen3.7-max"));
+      assert.equal(qwen37.url, "https://opencode.ai/zen/go/v1/chat/completions");
+
+      // mimo-v2-pro
+      const mimoPro = await goExecutor.execute(createInput("mimo-v2-pro"));
+      assert.equal(mimoPro.url, "https://opencode.ai/zen/go/v1/chat/completions");
+
+      // mimo-v2-omni
+      const mimoOmni = await goExecutor.execute(createInput("mimo-v2-omni"));
+      assert.equal(mimoOmni.url, "https://opencode.ai/zen/go/v1/chat/completions");
+
+      // hy3-preview
+      const hy3 = await goExecutor.execute(createInput("hy3-preview"));
+      assert.equal(hy3.url, "https://opencode.ai/zen/go/v1/chat/completions");
+    });
   });
 
   describe("user-agent forwarding", () => {