feat(models): add GLM-5.3-Flash, DeepSeek V4 Vision, Grok 4.5/4.6

Vendors shipped four multimodal models the registry did not carry:

- glm-5.3-flash — z.ai's first natively multimodal GLM-5, 1M context,
  image + video + pdf input (glm, glm-cn, opencode-go)
- deepseek-v4-flash-vision-exp — image input at V4-Flash text parity,
  1M context / 384k output (deepseek, opencode-go)
- grok-4.6, grok-4.5 — 500k context; 4.6 has no text output limit (xai)

Capabilities needed hand entries because the existing globs mis-matched:
*glm-5* and *deepseek-v4* carry no vision, and *grok-4* would have capped
grok-4.6 at 256k instead of 500k. The grok-4.6 pattern sits above the
generic *grok-4* so it wins the first-match lookup.

Also corrects glm-4.6v / glm-4.5v, which were missing video input and
declared no maxOutput, and backfills glm-4.6v on glm-cn — zhipuai serves
it and the sibling provider already listed it.

tests/unit/opencode-go-models.test.js pins the opencode-go model list, so
its expected array moves with the registry.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

tests/unit/opencode-go-models.test.js

@@ -22,8 +22,8 @@ describe("OpenCode Go model catalog", () => {
   it("matches the documented model IDs", () => {
     const ids = (PROVIDER_MODELS["opencode-go"] || []).map((m) => m.id);
     expect(ids).toEqual([
-      "glm-5.2", "glm-5.1", "kimi-k2.7-code", "kimi-k2.6",
-      "deepseek-v4-pro", "deepseek-v4-flash",
+      "glm-5.3-flash", "glm-5.2", "glm-5.1", "kimi-k2.7-code", "kimi-k2.6",
+      "deepseek-v4-pro", "deepseek-v4-flash", "deepseek-v4-flash-vision-exp",
       "mimo-v2.5", "mimo-v2.5-pro",
       "minimax-m3", "minimax-m2.7", "minimax-m2.5",
       "qwen3.7-max", "qwen3.7-plus", "qwen3.6-plus",