- 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
When a secondary agent's OAuth token expires and refresh fails, the agent
would error out even if the main agent had fresh, valid credentials for
the same profile.
This fix adds a fallback mechanism that:
1. Detects when OAuth refresh fails for a secondary agent (agentDir is set)
2. Checks if the main agent has fresh credentials for the same profileId
3. If so, copies those credentials to the secondary agent and uses them
4. Logs the inheritance for debugging
This prevents the situation where users have to manually copy auth-profiles.json
between agent directories when tokens expire at different times.
Fixes: Secondary agents failing with 'OAuth token refresh failed' while main
agent continues to work fine.
