Include x-coding-assistant=aider header in litellm calls

Proxies that inspect traffic between the development environment and an
LLM might be interested in whether it's aider or another tool calling in
order to be able to inspect and/or modify the payload.

The most common way of solving this would be to add a `user-agent` header.
However, litellm which aider uses calls into OpenAI libraries directly
when making the request and it seems like the only way to set a custom
`http_client`. This seemed like something that might have unforeseen
consequences (timeouts? retries?). For other LLMs, litellm seems to use
its own httpx wrapper which might presumably be easier to customize, but
I have not tried.

To make things easier, let's just add an aider specific header. I put the
string aider followed by the version there, but the value - and indeed the key
- of the header are not that interesting, what I would like to do is to just
be able to to tell aider calls.

aider/coders/base_coder.py

@@ -1205,6 +1205,7 @@ def warm_cache_worker():
 
                 kwargs = dict(self.main_model.extra_params) or dict()
                 kwargs["max_tokens"] = 1
+                kwargs["headers"] = {"x-coding-assistant": f"aider-{__version__}"}
 
                 try:
                     completion = litellm.completion(

aider/sendchat.py

@@ -3,6 +3,7 @@
 import os
 import time
 
+from aider._version import __version__
 from aider.dump import dump  # noqa: F401
 from aider.exceptions import LiteLLMExceptions
 from aider.llm import litellm
@@ -99,6 +100,7 @@ def send_completion(
         model=model_name,
         messages=messages,
         stream=stream,
+        headers={"x-coding-assistant": f"aider-{__version__}"},
     )
     if temperature is not None:
         kwargs["temperature"] = temperature

tests/basic/test_sendchat.py

@@ -68,6 +68,21 @@ def test_send_completion_with_functions(self, mock_completion):
         assert "tools" in called_kwargs
         assert called_kwargs["tools"][0]["function"] == mock_function
 
+    @patch("litellm.completion")
+    def test_send_completion_aider_specific_header(self, mock_completion):
+        _, _ = send_completion(
+            self.mock_model,
+            self.mock_messages,
+            functions=None,
+            stream=False,
+        )
+
+        # Verify the aider specific header was sent
+        called_kwargs = mock_completion.call_args.kwargs
+        assert "headers" in called_kwargs
+        assert "x-coding-assistant" in called_kwargs["headers"]
+        assert "aider" in called_kwargs["headers"]["x-coding-assistant"]
+
     @patch("litellm.completion")
     def test_simple_send_attribute_error(self, mock_completion):
         # Setup mock to raise AttributeError