Gemini is way too hot right now (quota exceeded on Free tier) does not respect given time

Description

While the extended message shows the following, Opencode attempts with the normal exponential backoff starting at 1s, instead of, well, 45.

You exceeded your current quota, please check your plan and
billing details. For more information on this error, head to:
https://ai.google.dev/gemini-api/docs/rate-limits.

To monitor your current usage, head to: https://ai.dev/rate-limit.

* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_input_token_count
  limit: 250000, model: gemini-3.5-flash. Please retry in 45.14551691s.

Plugins

1.18.16

OpenCode version

No response

Steps to reproduce

1. Use Gemini, preferably on Free tier
2. Ask it to do loads of tool calls etc to waste tokens/requests
3. Notice that its not respecting the provided rate limit reset timer

Screenshot and/or share link

No response

Operating System

Arch Linux (btw)

Terminal

Zed (not the agents panel, but using the TUI inside the Terminal)