docs(kilo-docs): note that kilo-auto underlying models can change

packages/kilo-docs/pages/code-with-ai/agents/auto-model.md

@@ -23,6 +23,10 @@ That's it. No configuration needed.
 
 You can see which underlying models are used, as well as the cost, in the expanded model picker. Model mapping information is also available on the [Gateway Model page](/docs/gateway/models-and-providers#kilo-autofrontier).
 
+{% callout type="info" title="Models can change" %}
+The underlying models behind each Auto Model tier are updated server-side as better options become available or as providers change pricing and availability. The tier you select stays the same; the model it routes to may change over time.
+{% /callout %}
+
 ## Tiers
 
 - **Frontier** — Routes to the latest and most capable paid models. Uses different models for reasoning-heavy tasks (planning, architecture, debugging) versus implementation tasks (coding, building, exploring), pairing the right capability to each type of work.

packages/kilo-docs/pages/gateway/models-and-providers.md

@@ -76,6 +76,10 @@ Provided under the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia
 
 Kilo Auto virtual models automatically select the best underlying model based on the task type. The selection is controlled by the `x-kilocode-mode` request header.
 
+{% callout type="info" title="Underlying models can change" %}
+The mappings below reflect the current routing. The underlying models behind each `kilo-auto/*` tier are updated server-side as better options become available or as providers change pricing and availability — the tier IDs themselves remain stable.
+{% /callout %}
+
 ### `kilo-auto/frontier`
 
 Highest performance and capability for any task. Frontier requests are sent with medium reasoning effort and medium verbosity.