Initial Checks

• I confirm that I'm using the latest version of Pydantic AI
• I confirm that I searched for my issue inhttps://github.com/pydantic/pydantic-ai/issues before opening this issue

Description

As mentioned in the title, the documentation implies that dynamic prompts are always evaluated even if message_history is present. So far, logging all_messages() and putting a bunch of print statemetns all over the place seems to imply that they don't get included

The LLM model responses also suggest that the content from dynamic system prompts is not being included
(I use Gemini models)

Example Code

Python, Pydantic AI & LLM client version

pydantic-ai 0.1.9Gemini 2.0