fix(ai): exclude text-only o-series variants from vision capability

The o1/o3/o4 prefix match also caught o1-mini, o1-preview and o3-mini,
which have no image input. A user pinned to one was told OCR works, then
the provider rejected the image block. Treat an o1/o3/o4 slug as
vision-capable only when it is not a -mini or -preview variant, applied
to both the OpenAI and Codex gates.

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

@@ -39,7 +39,10 @@ describe("supportsVisionForConfig", () => {
       expect(supportsVisionForConfig(providerType, "gpt-4o-mini")).toBe(true);
       expect(supportsVisionForConfig(providerType, "gpt-4.1")).toBe(true);
       expect(supportsVisionForConfig(providerType, "gpt-4-turbo")).toBe(true);
+      // Full o-series reasoning models read images.
       expect(supportsVisionForConfig(providerType, "o1")).toBe(true);
+      expect(supportsVisionForConfig(providerType, "o3")).toBe(true);
+      expect(supportsVisionForConfig(providerType, "o4")).toBe(true);
     }
   });
 
@@ -49,6 +52,20 @@ describe("supportsVisionForConfig", () => {
     expect(supportsVisionForConfig("openai", null)).toBe(false);
   });
 
+  it("rejects text-only o-series variants (-mini / -preview) for openai", () => {
+    // o1-mini / o1-preview / o3-mini accept the `o*` prefix but have no image
+    // input — claiming vision here 400s the user at the image block.
+    for (const providerType of [
+      "openai",
+      "admin-openai",
+      "admin-key",
+    ] as const) {
+      expect(supportsVisionForConfig(providerType, "o1-mini")).toBe(false);
+      expect(supportsVisionForConfig(providerType, "o1-preview")).toBe(false);
+      expect(supportsVisionForConfig(providerType, "o3-mini")).toBe(false);
+    }
+  });
+
   it("trusts local (operator opted in) regardless of model string", () => {
     expect(supportsVisionForConfig("local", "llava")).toBe(true);
     expect(supportsVisionForConfig("local", null)).toBe(true);
@@ -72,6 +89,12 @@ describe("supportsVisionForConfig", () => {
     // 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);
+    // Text-only o-series variants are excluded for codex too.
+    expect(supportsVisionForConfig("codex", "o1-mini")).toBe(false);
+    expect(supportsVisionForConfig("codex", "o3-mini")).toBe(false);
+    expect(supportsVisionForConfig("codex", "o1-preview")).toBe(false);
+    // Full o-series stays vision-capable.
+    expect(supportsVisionForConfig("codex", "o3")).toBe(true);
   });
 
   it("never reports vision for none", () => {

src/lib/ai/vision-capability.ts

@@ -41,18 +41,32 @@ function anthropicSupportsVision(model: string): boolean {
 /**
  * OpenAI vision models (also covers the operator's admin key + Codex when it
  * runs an OpenAI model — though Codex is excluded by `providerType`). `gpt-4o`,
- * `gpt-4.1`, `gpt-4-turbo`, and the `o*` reasoning models read image content;
- * `gpt-3.5*` and the legacy `gpt-4` (non-turbo) 400 on an image block.
+ * `gpt-4.1`, `gpt-4-turbo`, and the full `o1` / `o3` / `o4` reasoning models
+ * read image content; `gpt-3.5*` and the legacy `gpt-4` (non-turbo) 400 on an
+ * image block.
+ *
+ * The `o*` reasoning line has text-only variants that DO accept the `o*` prefix
+ * but reject an image block: `o1-mini` / `o1-preview` and `o3-mini` have no
+ * vision input (only the full `o1` / `o3` are multimodal). They must be
+ * excluded or a user pinned to one is told OCR works, then the provider 400s at
+ * the image block. We treat an `o1` / `o3` / `o4` slug as vision-capable only
+ * when it is NOT a `-mini` / `-preview` variant — the conservative default for
+ * any unverified narrow slug.
  */
+function isVisionReasoningSlug(m: string): boolean {
+  if (!(m.startsWith("o1") || m.startsWith("o3") || m.startsWith("o4"))) {
+    return false;
+  }
+  return !m.includes("-mini") && !m.includes("-preview");
+}
+
 function openaiSupportsVision(model: string): boolean {
   const m = model.toLowerCase();
   return (
     m.startsWith("gpt-4o") ||
     m.startsWith("gpt-4.1") ||
     m.startsWith("gpt-4-turbo") ||
-    m.startsWith("o1") ||
-    m.startsWith("o3") ||
-    m.startsWith("o4")
+    isVisionReasoningSlug(m)
   );
 }
 
@@ -78,9 +92,9 @@ function codexSupportsVision(model: string): boolean {
     m.startsWith("gpt-4o") ||
     m.startsWith("gpt-4.1") ||
     m.startsWith("gpt-4-turbo") ||
-    m.startsWith("o1") ||
-    m.startsWith("o3") ||
-    m.startsWith("o4")
+    // Same `-mini` / `-preview` text-only exclusion as the OpenAI gate: a
+    // future codex slug rotation onto e.g. `o3-mini` must not claim vision.
+    isVisionReasoningSlug(m)
   );
 }