Add attempted-retries and timeout values to response headers + more testing (#7926)

* feat(router.py): add retry headers to response

makes it easy to add testing to ensure model-specific retries are respected

* fix(add_retry_headers.py): clarify attempted retries vs. max retries

* test(test_fallbacks.py): add test for checking if max retries set for model is respected

* test(test_fallbacks.py): assert values for attempted retries and max retries are as expected

* fix(utils.py): return timeout in litellm proxy response headers

* test(test_fallbacks.py): add test to assert model specific timeout used on timeout error

* test: add bad model with timeout to proxy

* fix: fix linting error

* fix(router.py): fix get model list from model alias

* test: loosen test restriction - account for other events on proxy

litellm/router_utils/add_retry_headers.py

@@ -0,0 +1,40 @@
+from typing import Any, Optional, Union
+
+from pydantic import BaseModel
+
+from litellm.types.utils import HiddenParams
+
+
+def add_retry_headers_to_response(
+    response: Any,
+    attempted_retries: int,
+    max_retries: Optional[int] = None,
+) -> Any:
+    """
+    Add retry headers to the request
+    """
+
+    if response is None or not isinstance(response, BaseModel):
+        return response
+
+    retry_headers = {
+        "x-litellm-attempted-retries": attempted_retries,
+    }
+    if max_retries is not None:
+        retry_headers["x-litellm-max-retries"] = max_retries
+
+    hidden_params: Optional[Union[dict, HiddenParams]] = getattr(
+        response, "_hidden_params", {}
+    )
+
+    if hidden_params is None:
+        hidden_params = {}
+    elif isinstance(hidden_params, HiddenParams):
+        hidden_params = hidden_params.model_dump()
+
+    hidden_params.setdefault("additional_headers", {})
+    hidden_params["additional_headers"].update(retry_headers)
+
+    setattr(response, "_hidden_params", hidden_params)
+
+    return response