Skip to main content
Kronos audits the reasoning prompt SERV generates from your system prompt. If the audit finds a semantic problem, SERV repairs the generated prompt and checks it again. It repeats this loop up to its configured internal repair limit, then uses the latest generated prompt.

​
Add Kronos to a model ID

Add -serv-kronos to a supported base model ID. The suffix is a model feature, not an application tool, so you do not add a function definition or implement a handler for it.
SERV removes the feature suffix before routing to the upstream provider. Use a real base model from the model catalog, then append -serv-kronos exactly once.

​
When to use Kronos

Use Kronos for system prompts with procedural rules, multiple conditions, or consequences that must remain consistent. Add it when ambiguity in the generated reasoning prompt could change the model’s decision. Kronos does not replace application authorization, tool-argument validation, or testing. Keep those checks in your application.

​
Cost and behavior

On a cache miss, Kronos adds at least one audit call and may add repair and re-audit calls. Those calls increase cost and latency. A matching cache hit reuses the previously audited reasoning prompt, but the requested upstream model still runs for every request. See Monitor usage and billing. You can combine Kronos with Multipath by using -serv-kronos-multipath. See Use Multipath for branching instructions.