core, openai, standard-tests: improve OpenAI compatibility with Anthropic content blocks (#30128)

- Support thinking blocks in core's `convert_to_openai_messages` (pass
through instead of error)
- Ignore thinking blocks in ChatOpenAI (instead of error)
- Support Anthropic-style image blocks in ChatOpenAI

---

Standard integration tests include a `supports_anthropic_inputs`
property which is currently enabled only for tests on `ChatAnthropic`.
This test enforces compatibility with message histories of the form:
```
- system message
- human message
- AI message with tool calls specified only through `tool_use` content blocks
- human message containing `tool_result` and an additional `text` block
```
It additionally checks support for Anthropic-style image inputs if
`supports_image_inputs` is enabled.

Here we change this test, such that if you enable
`supports_anthropic_inputs`:
- You support AI messages with text and `tool_use` content blocks
- You support Anthropic-style image inputs (if `supports_image_inputs`
is enabled)
- You support thinking content blocks.

That is, we add a test case for thinking content blocks, but we also
remove the requirement of handling tool results within HumanMessages
(motivated by existing agent abstractions, which should all return
ToolMessage). We move that requirement to a ChatAnthropic-specific test.

libs/partners/anthropic/tests/integration_tests/test_chat_models.py

@@ -4,6 +4,7 @@ import json
 from base64 import b64encode
 from typing import List, Optional
 
+import httpx
 import pytest
 import requests
 from anthropic import BadRequestError
@@ -768,3 +769,64 @@ def test_structured_output_thinking_force_tool_use() -> None:
     )
     with pytest.raises(BadRequestError):
         llm.invoke("Generate a username for Sally with green hair")
+
+
+def test_image_tool_calling() -> None:
+    """Test tool calling with image inputs."""
+
+    class color_picker(BaseModel):
+        """Input your fav color and get a random fact about it."""
+
+        fav_color: str
+
+    human_content: List[dict] = [
+        {
+            "type": "text",
+            "text": "what's your favorite color in this image",
+        },
+    ]
+    image_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
+    image_data = b64encode(httpx.get(image_url).content).decode("utf-8")
+    human_content.append(
+        {
+            "type": "image",
+            "source": {
+                "type": "base64",
+                "media_type": "image/jpeg",
+                "data": image_data,
+            },
+        }
+    )
+    messages = [
+        SystemMessage("you're a good assistant"),
+        HumanMessage(human_content),  # type: ignore[arg-type]
+        AIMessage(
+            [
+                {"type": "text", "text": "Hmm let me think about that"},
+                {
+                    "type": "tool_use",
+                    "input": {"fav_color": "green"},
+                    "id": "foo",
+                    "name": "color_picker",
+                },
+            ]
+        ),
+        HumanMessage(
+            [
+                {
+                    "type": "tool_result",
+                    "tool_use_id": "foo",
+                    "content": [
+                        {
+                            "type": "text",
+                            "text": "green is a great pick! that's my sister's favorite color",  # noqa: E501
+                        }
+                    ],
+                    "is_error": False,
+                },
+                {"type": "text", "text": "what's my sister's favorite color"},
+            ]
+        ),
+    ]
+    llm = ChatAnthropic(model="claude-3-5-sonnet-latest")
+    llm.bind_tools([color_picker]).invoke(messages)