HEART ai.cost-spike H-07002
AI cost spike. AI spending is rising much faster than normal.
| Code | HEART ai.cost-spike; inside a message "code": "ai.cost-spike" |
|---|---|
| H-number | H-07002: area 07, code 002 |
| Area | ai: AI providers, models, budgets |
| Typical severity | warning. A product may set another for its own case. |
| Applies to | Products that use an AI model |
Likely causes
- A loop that calls the model again and again.
- Much more use than normal, or a new feature that calls the model often.
- A change to a larger, more expensive model.
- Someone else using the product's API key.
How to fix or prevent it
- Look at which calls grew, and since when.
- Fix loops, and cache answers that repeat.
- Check that the key is not leaked; rotate it if in doubt.
- Set or lower the budget.
What the HEART does by itself
It raises a warning when spending rises much faster than normal. It may throttle model calls or move to a cheaper way of thinking, if a Playbook allows it. It resolves when spending is back to its normal rate.
When to call service
If the key may have leaked, or the cost cannot be explained.
Related codes
ai.budget-near-limitH-07003: AI budget near its limitai.budget-exceededH-07004: AI budget used upsecurity.anomalyH-11007: Security anomaly
Inside a message a code is written bare, "code": "storage.full". In logs, tickets, documents and searches it is written
HEART storage.full. Things that simply happen, such as system.started, are event types, not faults.
The codes are defined in Part 3, Section 5.4, and their H-numbers in Section 5.7.
All of it, as data: fault-codes.json.
All fault codes, by area · All fault codes, by H-number · Problem types (API errors)