Model Lifecycle Management
LLM providers regularly deprecate and retire models. MeetLoyd's Model Lifecycle Manager ensures your agents stay operational by providing advance warnings, automatic upgrade paths, and full control over how your organization responds to model changes.
How It Works
Every LLM model in MeetLoyd has a lifecycle state:
| State | Meaning |
|---|---|
| Active | Model is fully operational |
| Preview | New model available for early testing |
| Deprecated | Still works, but a better successor exists |
| Retiring | Will stop working on a specific date |
| Retired | No longer available - API calls will fail |
When a model's state changes, MeetLoyd can automatically notify you, upgrade your agents, or pause them - depending on your settings.
Lifecycle Indicators
In the Model Selector dropdown (when creating or editing agents), you'll see visual indicators:
- Amber "Deprecated" badge - Model still works but you should plan to upgrade
- Red "Retiring" badge with date - Model will stop working soon
- Red "Retired" badge - Model is disabled and cannot be selected
- Blue "Preview" badge - New model available for testing
If you have an agent using a deprecated or retiring model, you'll see a warning banner with upgrade recommendations.
Configuring Lifecycle Settings
Navigate to Settings > Model Lifecycle to configure how your organization handles model changes.
On Deprecation
What happens when a model is marked as deprecated:
| Option | Behavior |
|---|---|
| Notify & Warn (default) | Sends notification + shows warning in dashboard |
| Notify Only | Sends notification, no UI warnings |
| Auto-Upgrade | Automatically switches agents to the successor model |
| Ignore | No action taken |
On Retirement
What happens when a model is fully retired:
| Option | Behavior |
|---|---|
| Pause Agents (default) | Pauses affected agents and notifies you |
| Auto-Upgrade | Automatically upgrades to successor model |
| Notify Only | Sends notification but agents will fail on next run |
Reminder Frequency
How often you receive reminders about affected agents:
- Daily - One reminder per day
- Weekly (default) - One reminder per week
- Once - Single notification, no reminders
Who Gets Notified
Choose which roles receive lifecycle notifications:
- Owner (default)
- Admin (default)
- Agent Creator - The user who originally created the agent
Notifications
MeetLoyd sends lifecycle notifications through your configured channels:
| Event | Priority | Channels |
|---|---|---|
| Model deprecated | Normal | In-app, Email |
| Model retiring soon | High | In-app, Email, Slack |
| Model retired | Urgent | In-app, Email, Slack |
| Agents auto-upgraded | Normal | In-app, Email |
Each notification includes:
- Which model is affected
- How many of your agents use it
- The recommended successor model (if available)
- A direct link to update your agents
Viewing Deprecations
To see which of your agents are affected by model changes:
- Go to Settings > Model Lifecycle
- Or call
GET /api/models/deprecationsvia the API
This shows all deprecated/retiring/retired models with a list of your affected agents.
Auto-Upgrade
When auto-upgrade is enabled and a successor model is defined:
- MeetLoyd updates the agent's model configuration to the successor
- The agent continues running on the new model
- You receive a notification listing all upgraded agents
- No downtime - the switch happens at the next execution
Auto-upgrade works best for standard workloads. If you have agents with model-specific prompt tuning, consider using Notify & Warn instead and upgrading manually after testing.
API Reference
Get Deprecation Info
GET /api/models/deprecations
Returns models affecting your agents with their lifecycle state and affected agent list.
Update Lifecycle Settings
PUT /api/settings/model-lifecycle
Content-Type: application/json
{
"onDeprecation": "notify_and_warn",
"onRetirement": "suspend_agent",
"reminderFrequency": "weekly",
"notifyRoles": ["owner", "admin"]
}
Models Endpoint Enhancement
The existing GET /api/models endpoint now includes a lifecycle field with the current state of each model:
{
"providers": { ... },
"available": [ ... ],
"all": [ ... ],
"lifecycle": {
"gpt-4o": {
"lifecycleState": "retiring",
"retirementDate": "2026-02-16T00:00:00.000Z",
"successorModelId": "gpt-5-mini"
}
}
}
Execution Guard
As an additional safety net, MeetLoyd checks the model lifecycle state before every agent execution:
- Retired models are blocked - the execution returns an error with the recommended successor
- Deprecated models log a warning but continue executing normally
This ensures agents never silently fail due to a retired model.