HEART ai.output-rejected H-07006
AI output rejected. AI suggestions keep failing the HEART's checks.
| Code | HEART ai.output-rejected; inside a message "code": "ai.output-rejected" |
|---|---|
| H-number | H-07006: area 07, code 006 |
| 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 model proposes actions outside what the product allows.
- It names parts, settings or values that do not exist.
- The model or its instructions changed.
- A poor prompt, or missing data in what the model is given.
How to fix or prevent it
- Look at the rejected suggestions and the reason for each.
- Check the model version and its instructions.
- Use a better model, or give it the data it lacks.
What the HEART does by itself
It refuses each suggestion that fails its checks, so nothing unsafe is done, records why, and raises a warning when this keeps happening. It may stop asking the model until a person looks.
When to call service
Not usually: the HEART has already refused the bad suggestions.
Related codes
ai.model-driftH-07005: AI model driftai.answer-rejectedH-07009: Brain answer rejectedai.disagreementH-07010: Brain disagrees with the system's checks
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)