- Remove duplicate JSDoc blocks left from iterative editing
- Add @example annotations to cooldownKey() for clarity
- Handle empty/whitespace model strings in cooldownKey()
- Improve isProfileInCooldown() documentation to explain dual-check behavior
- Clarify markAuthProfileCooldown() is a convenience wrapper
When a model succeeds, also clear its per-model cooldown key so
the system doesn't think it's still rate-limited.
- Add optional `model` param to markAuthProfileUsed
- Pass modelId when marking profile used in agent runner
- Add tests for per-model cooldown clearing behavior
Allow different models from the same provider to have independent
cooldowns. When a model hits rate limit, only that specific model
is blocked, not all models using the same auth profile.
- Add cooldownKey() helper for composite key generation
- Update isProfileInCooldown to check both per-model and profile-level
- Update markAuthProfileFailure/Cooldown with optional model param
- Pass model to cooldown checks in model-fallback and agent runner
- Add comprehensive tests for per-model cooldown behavior
Ref: #3417
