fix(ai): keep gpt-5-codex slugs text-only in the vision gate

The codex vision gate accepted any gpt-5 prefix, which included the gpt-5-codex
specialist slugs that the surrounding contract documents as text-only. Each lab
OCR upload on such a slug burned a doomed image attempt before falling back.
Exclude the -codex slugs from the gate so multimodal gpt-5.x slugs still report
vision while the codex specialists stay on the text path.

src/lib/ai/__tests__/vision-capability.test.ts

@@ -69,6 +69,9 @@ describe("supportsVisionForConfig", () => {
     expect(supportsVisionForConfig("codex", "gpt-4")).toBe(false);
     expect(supportsVisionForConfig("codex", "gpt-3.5-turbo")).toBe(false);
     expect(supportsVisionForConfig("codex", null)).toBe(false);
+    // The `-codex` specialist slugs are text-only despite the gpt-5 prefix.
+    expect(supportsVisionForConfig("codex", "gpt-5-codex")).toBe(false);
+    expect(supportsVisionForConfig("codex", "gpt-5.1-codex-mini")).toBe(false);
   });
 
   it("never reports vision for none", () => {

src/lib/ai/vision-capability.ts

@@ -71,7 +71,10 @@ function openaiSupportsVision(model: string): boolean {
 function codexSupportsVision(model: string): boolean {
   const m = model.toLowerCase();
   return (
-    m.startsWith("gpt-5") || // GPT-5.x line is multimodal (text + vision)
+    // GPT-5.x line is multimodal (text + vision) — but the `-codex` specialist
+    // slugs (e.g. gpt-5-codex) are text-only, so they must not claim vision or
+    // every lab-OCR upload burns a doomed image attempt before falling back.
+    (m.startsWith("gpt-5") && !m.includes("-codex")) ||
     m.startsWith("gpt-4o") ||
     m.startsWith("gpt-4.1") ||
     m.startsWith("gpt-4-turbo") ||