What happened?
Gemini CLI is encountering persistent 429 Resource Exhausted errors immediately upon execution due to a critical inefficiency in how the system prompt is handled.
The full text of the system instruction (4,375 tokens) is re-uploading with every single API request. This causes the application to hit the Tokens Per Minute quota almost instantly, even if Requests Per Minute count is low.
What did you expect to happen?
System prompts cached
Client information
Client Information
Run gemini to enter the interactive CLI, then run the /about command.
> /about
# paste output here
Login information
API key Pro account
Anything else we need to know?
No response