### What happened?

Router is failing to updated the litellm_deployment_cooled_down prometheus metric due to a "incorrect label count" error. As a result, we have no data for this metric at all.

Looks like the set of labels is coming from https://github.com/BerriAI/litellm/blob/v1.78.5-stable/litellm/types/integrations/prometheus.py#L352-L357 (four of them) whereas the call is providing 5 labels. The `exception_status` is the one that is presumably not supported.

Happy to make a PR to fix this. This appears to still be an issue on `main` branch, see https://github.com/BerriAI/litellm/blob/4dbbec233cebd126c6286d574839e4922bff4ff4/litellm/router_utils/cooldown_callbacks.py#L79

Similar to #7611

### Relevant log output

```shell Task exception was never retrieved future: <Task finished name='Task-13231120' coro=<router_cooldown_event_callback() done, defined at /usr/lib/python3.13/site-packages/litellm/router_utils/cooldown_callbacks.py:24> exception=ValueError('Incorrect label count')>

Traceback (most recent call last): File "/usr/lib/python3.13/site-packages/litellm/router_utils/cooldown_callbacks.py", line 77, in router_cooldown_event_callback prometheusLogger.increment_d…