I'm in the middle of test-driving Aider and I'm seeing exactly the same problem, the longer a conversation goes on, the worse the quality of replies... Currently, I'm doing something like this to prevent it from loading previous context:

    rm -r .aider.chat.history.md .aider.tags.cache.v4 || true && aider --architect --model deepseek/deepseek-reasoner --editor-model deepseek/deepseek-chat --no-restore-chat-history

Which clears the history, then I basically re-run that whenever the model gets something wrong (so I can update/improve the prompt and try again).