diff --git a/plugins/model-providers/meta-ai/__init__.py b/plugins/model-providers/meta-ai/__init__.py
index d6c3851961..e54b1f4f54 100644
--- a/plugins/model-providers/meta-ai/__init__.py
+++ b/plugins/model-providers/meta-ai/__init__.py
@@ -121,6 +121,9 @@ meta_ai = MetaAIProfile(
     api_mode="codex_responses",
     # Muse Spark is natively multimodal (image/video/pdf/audio in, text out).
     supports_vision=True,
+    # ...but only on user turns: an image envelope inside a role:tool message
+    # 400s "messages[N].content did not match any supported type" (#101668).
+    supports_vision_tool_messages=False,
     # Cheap contributor tier is a good default for auxiliary tasks
     # (compaction, title generation, vision) when this is the main provider.
     default_aux_model="muse-spark-1.2-contributor",
diff --git a/tests/providers/test_meta_ai_profile.py b/tests/providers/test_meta_ai_profile.py
index 8fe41cd6e2..5a0ea074ce 100644
--- a/tests/providers/test_meta_ai_profile.py
+++ b/tests/providers/test_meta_ai_profile.py
@@ -28,6 +28,8 @@ class TestMetaAIProfile:
         assert p.api_mode == "codex_responses"
         assert "MODEL_API_KEY" in p.env_vars
         assert p.supports_vision is True
+        # Images are accepted on user turns only; tool-result envelopes 400 (#101668).
+        assert p.supports_vision_tool_messages is False
         assert p.default_aux_model == "muse-spark-1.2-contributor"
         assert p.default_max_tokens == 16384
         assert p.fallback_models == ("muse-spark-1.2",)