#31887 [Bug]: Toggeling on Cache Control Injection Points for anthropic break litellm for anthropic
### Check for existing issues
- [x] I have searched the existing issues and checked that my issue is not a duplicate.
### What happened?
After I toggle `Cache Control Injection Points` on I got following error. Once i saved the model, I am no longer able to add the same anthropic model again with different public name and get same error. ``` prompt_id is required for Prompt Management Base class Traceback (most recent call last): File "/app/.venv/lib/python3.13/site-packages/litellm/main.py", line 632, in acompletion init_response = await loop.run_in_executor(None, func_with_context) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3.13/concurrent/futures/thread.py", line 59, in run result = self.fn(*self.args, **self.kwargs) File "/app/.venv/lib/python3.13/site-packages/litellm/utils.py", line 1448, in wrapper result = original_function(*args, **kwargs) File "/app/.venv/lib/python3.13/site-packages/litellm/main.py", line 1366, in completion ) = litellm_logging_obj.get_chat_completion_prompt( ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^ model=model, ^^^^^^^^^^^^ ...<5 lines>... prompt_version=kwargs.get("prompt_version", None), ^^^^^^^^^^^^^^^^^^^^^^^^…