app-server: expose image-context tri-state

codex-rs/app-server-protocol/schema/json/v2/ThreadStartResponse.json

@@ -382,6 +382,25 @@
       },
       "type": "object"
     },
+    "InputModality": {
+      "description": "Canonical user-input modality tags advertised by a model.",
+      "oneOf": [
+        {
+          "description": "Plain text turns and tool payloads.",
+          "enum": [
+            "text"
+          ],
+          "type": "string"
+        },
+        {
+          "description": "Image attachments included in user turns.",
+          "enum": [
+            "image"
+          ],
+          "type": "string"
+        }
+      ]
+    },
     "McpToolCallError": {
       "properties": {
         "message": {
@@ -701,6 +720,17 @@
           "description": "Version of the CLI that created the thread.",
           "type": "string"
         },
+        "conversationModalities": {
+          "default": null,
+          "description": "Tri-state conversation modalities signal: - `None`: unknown / not yet determined - `Some([Text])`: known to be text-only - `Some([Text, Image])`: images are known to exist in context",
+          "items": {
+            "$ref": "#/definitions/InputModality"
+          },
+          "type": [
+            "array",
+            "null"
+          ]
+        },
         "createdAt": {
           "description": "Unix timestamp (in seconds) when the thread was created.",
           "format": "int64",