When the primary Google Gemini CLI provider hit its rate limits/cooldown, Clawdbot issued a FailoverError: No available auth profile for google-gemini-cli (all in cooldown or unavailable).

Expected behavior: Despite the primary provider's temporary unavailability, Clawdbot should attempt to use subsequent models configured in the fallbacks list, even if they belong to different providers (e.g., OpenRouter models).

Observed behavior: The error message suggests that the entire google-gemini-cli profile being down prevented fallback attempts to other, available providers/models. This indicates a potential logic flaw where provider-level unavailability is not correctly allowing progression to the next provider in the failover chain.

Relevant configuration (from config.get output):

primary: "google-gemini-cli/gemini-2.5-pro"
fallbacks:
  - "openrouter/google/gemini-2.5-flash"
  - "openrouter/openai/gpt-4o-mini"
  - "openrouter/deepseek/deepseek-r1"
  - "openrouter/deepseek/deepseek-v3.2"
  - "openrouter/minimax/minimax-m2.1"

Error observed: FailoverError: No available auth profile for google-gemini-cli (all in cooldown or unavailable).

This impacts resilience and reliability. Requesting investigation and fix.