Kyvvu

Policy · critical

Prevent infinite LLM loops

Block tasks where the agent calls the model more than 5 times consecutively without any other action kind intervening. This catches agents stuck in a reasoning loop.

The policy

A few lines of YAML in your repository.

Part of Internal AI starter. Assign the pack, or copy this policy into a manifest of your own.

Verdict
Critical: the step is blocked before it runs, and an incident is opened.
Checked
Before every step, against everything the agent did earlier in the task.
Rule
max_consecutive_same_type
- name: "Prevent infinite LLM loops"  description: |    Block tasks where the agent calls the model more than 5 times    consecutively without any other action kind intervening. This    catches agents stuck in a reasoning loop.  rule_type: max_consecutive_same_type  params:    kind: step.model    max_consecutive: 5  severity: critical  enforcement_point: step_execution

How the rule works

max_consecutive_same_type: Checks that no run of the same action kind exceeds a limit.

  • kind: step.model. Action kind whose consecutive runs are limited.
  • max_consecutive: 5. Maximum length of a consecutive run.

In these packs

From Kyvvu's open policy library at github.com/Kyvvu/manifests, Apache 2.0.

Next

Watch it decide.

In your browser

Try it in the playground

The policy is loaded. Add the steps your agent takes and watch the engine decide, step by step.

On your machine

Five minutes, no account

kyvvu try runs a demo agent against the bundled baseline. Then assign this pack from the dashboard or the CLI.

For security teams

See it on your agents

A 30-minute demo on the agents you actually run, with the policies that fit them.