HEART ai.provider-unavailable H-07001
AI provider unavailable. The AI model or provider cannot be reached.
| Code | HEART ai.provider-unavailable; inside a message "code": "ai.provider-unavailable" |
|---|---|
| H-number | H-07001: area 07, code 001 |
| 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
- The AI provider has an outage, or limits the product's requests.
- The network link to the provider is down.
- An API key that expired or was revoked.
- A local model that did not load, for lack of memory or a missing file.
How to fix or prevent it
- Check the provider's status page.
- Check the network and the API key.
- For a local model: check memory and the model file.
- Set a second provider or a local model, so the product can fall back.
What the HEART does by itself
It falls back to its next way of thinking (from cloud to local, or to rules only), records ai.tier.changed, and keeps doing its job without the model. A Playbook may switch providers (switch_provider). It raises a warning, and resolves it when the provider answers again.
When to call service
Rarely: a HEART must work without its model. Only if the fallback does not work.
Related codes
ai.lease-expiredH-07007: Brain lease expiredconnectivity.dependency-unreachableH-03003: A service it relies on cannot be reachedai.budget-exceededH-07004: AI budget used up
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)