fix: convert anthropic image content blocks

tests/agent/test_auxiliary_client.py

@@ -169,7 +169,7 @@ class TestGetTextAuxiliaryClient:
         with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
              patch("agent.auxiliary_client.OpenAI") as mock_openai:
             client, model = get_text_auxiliary_client()
-        assert model == "gpt-5.3-codex"
+        assert model == "gpt-5.2-codex"
         # Returns a CodexAuxiliaryClient wrapper, not a raw OpenAI client
         from agent.auxiliary_client import CodexAuxiliaryClient
         assert isinstance(client, CodexAuxiliaryClient)
@@ -202,7 +202,7 @@ class TestVisionClientFallback:
             client, model = get_vision_auxiliary_client()
         from agent.auxiliary_client import CodexAuxiliaryClient
         assert isinstance(client, CodexAuxiliaryClient)
-        assert model == "gpt-5.3-codex"
+        assert model == "gpt-5.2-codex"
 
     def test_vision_auto_falls_back_to_custom_endpoint(self, monkeypatch):
         """Custom endpoint is used as fallback in vision auto mode.
@@ -264,7 +264,7 @@ class TestVisionClientFallback:
             client, model = get_vision_auxiliary_client()
         from agent.auxiliary_client import CodexAuxiliaryClient
         assert isinstance(client, CodexAuxiliaryClient)
-        assert model == "gpt-5.3-codex"
+        assert model == "gpt-5.2-codex"
 
 
 class TestGetAuxiliaryProvider:
@@ -382,7 +382,7 @@ class TestResolveForcedProvider:
             client, model = _resolve_forced_provider("main")
         from agent.auxiliary_client import CodexAuxiliaryClient
         assert isinstance(client, CodexAuxiliaryClient)
-        assert model == "gpt-5.3-codex"
+        assert model == "gpt-5.2-codex"
 
     def test_forced_codex(self, codex_auth_dir, monkeypatch):
         with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
@@ -390,7 +390,7 @@ class TestResolveForcedProvider:
             client, model = _resolve_forced_provider("codex")
         from agent.auxiliary_client import CodexAuxiliaryClient
         assert isinstance(client, CodexAuxiliaryClient)
-        assert model == "gpt-5.3-codex"
+        assert model == "gpt-5.2-codex"
 
     def test_forced_codex_no_token(self, monkeypatch):
         with patch("agent.auxiliary_client._read_codex_access_token", return_value=None):

tests/test_anthropic_adapter.py

@@ -467,6 +467,59 @@ class TestConvertMessages:
         assert len(result) == 1
         assert result[0]["role"] == "user"
 
+    def test_converts_user_image_url_blocks_to_anthropic_image_blocks(self):
+        messages = [
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": "Can you see this?"},
+                    {"type": "image_url", "image_url": {"url": "https://example.com/cat.png"}},
+                ],
+            }
+        ]
+
+        _, result = convert_messages_to_anthropic(messages)
+
+        assert result == [
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": "Can you see this?"},
+                    {"type": "image", "source": {"type": "url", "url": "https://example.com/cat.png"}},
+                ],
+            }
+        ]
+
+    def test_converts_data_url_image_blocks_to_base64_anthropic_image_blocks(self):
+        messages = [
+            {
+                "role": "user",
+                "content": [
+                    {"type": "input_text", "text": "What is in this screenshot?"},
+                    {"type": "input_image", "image_url": "data:image/png;base64,AAAA"},
+                ],
+            }
+        ]
+
+        _, result = convert_messages_to_anthropic(messages)
+
+        assert result == [
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": "What is in this screenshot?"},
+                    {
+                        "type": "image",
+                        "source": {
+                            "type": "base64",
+                            "media_type": "image/png",
+                            "data": "AAAA",
+                        },
+                    },
+                ],
+            }
+        ]
+
     def test_converts_tool_calls(self):
         messages = [
             {

tests/test_provider_parity.py

@@ -543,7 +543,7 @@ class TestAuxiliaryClientProviderPriority:
              patch("agent.auxiliary_client._read_codex_access_token", return_value="codex-tok"), \
              patch("agent.auxiliary_client.OpenAI"):
             client, model = get_text_auxiliary_client()
-        assert model == "gpt-5.3-codex"
+        assert model == "gpt-5.2-codex"
         assert isinstance(client, CodexAuxiliaryClient)
 
 

tests/test_run_agent.py

@@ -12,7 +12,7 @@ import uuid
 from logging.handlers import RotatingFileHandler
 from pathlib import Path
 from types import SimpleNamespace
-from unittest.mock import MagicMock, patch
+from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
@@ -1986,6 +1986,69 @@ class TestBuildApiKwargsAnthropicMaxTokens:
                 assert call_args[0][3] is None
 
 
+class TestAnthropicImageFallback:
+    def test_build_api_kwargs_converts_multimodal_user_image_to_text(self, agent):
+        agent.api_mode = "anthropic_messages"
+        agent.reasoning_config = None
+
+        api_messages = [{
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "Can you see this now?"},
+                {"type": "image_url", "image_url": {"url": "https://example.com/cat.png"}},
+            ],
+        }]
+
+        with (
+            patch("tools.vision_tools.vision_analyze_tool", new=AsyncMock(return_value=json.dumps({"success": True, "analysis": "A cat sitting on a chair."}))),
+            patch("agent.anthropic_adapter.build_anthropic_kwargs") as mock_build,
+        ):
+            mock_build.return_value = {"model": "claude-sonnet-4-20250514", "messages": [], "max_tokens": 4096}
+            agent._build_api_kwargs(api_messages)
+
+        kwargs = mock_build.call_args.kwargs or dict(zip(
+            ["model", "messages", "tools", "max_tokens", "reasoning_config"],
+            mock_build.call_args.args,
+        ))
+        transformed = kwargs["messages"]
+        assert isinstance(transformed[0]["content"], str)
+        assert "A cat sitting on a chair." in transformed[0]["content"]
+        assert "Can you see this now?" in transformed[0]["content"]
+        assert "vision_analyze with image_url: https://example.com/cat.png" in transformed[0]["content"]
+
+    def test_build_api_kwargs_reuses_cached_image_analysis_for_duplicate_images(self, agent):
+        agent.api_mode = "anthropic_messages"
+        agent.reasoning_config = None
+        data_url = "data:image/png;base64,QUFBQQ=="
+
+        api_messages = [
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": "first"},
+                    {"type": "input_image", "image_url": data_url},
+                ],
+            },
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": "second"},
+                    {"type": "input_image", "image_url": data_url},
+                ],
+            },
+        ]
+
+        mock_vision = AsyncMock(return_value=json.dumps({"success": True, "analysis": "A small test image."}))
+        with (
+            patch("tools.vision_tools.vision_analyze_tool", new=mock_vision),
+            patch("agent.anthropic_adapter.build_anthropic_kwargs") as mock_build,
+        ):
+            mock_build.return_value = {"model": "claude-sonnet-4-20250514", "messages": [], "max_tokens": 4096}
+            agent._build_api_kwargs(api_messages)
+
+        assert mock_vision.await_count == 1
+
+
 class TestFallbackAnthropicProvider:
     """Bug fix: _try_activate_fallback had no case for anthropic provider."""