docs(ai): trim listModels return value and AI overview per review

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

src/docs/src/AI.md

@@ -7,8 +7,6 @@ The Puter.js AI feature allows you to integrate artificial intelligence capabili
 
 You can use AI models from various providers to perform tasks such as chat, text-to-image, image-to-text, text-to-video, and text-to-speech conversion. And with the [User-Pays Model](/user-pays-model/), you don't have to set up your own API keys and top up credits, because users cover their own AI costs.
 
-Chat supports cancellation through an `AbortSignal`; see [chat()](/AI/chat/#stopping-a-stream). [listModels()](/AI/listModels/) caches successful catalogues for 60 seconds and rejects failed requests.
-
 ## Features
 
 <div style="overflow:hidden; margin-bottom: 30px;">

src/docs/src/AI/listModels.md

@@ -20,17 +20,6 @@ A string containing the provider you want to list the models for.
 
 ## Return value
 
-Successful results are cached for 60 seconds per SDK instance, provider, API origin
-and authentication token. Concurrent identical calls share one request. Each call
-receives an independent copy of the result. Provider filtering happens on the server;
-older servers are filtered locally. The SDK falls back to the legacy driver only
-when the endpoint is unavailable (404 or 501).
-
-Network and server failures reject the promise; they do not resolve to an empty
-catalogue. Network failures use `{ message, code: "network_error" }`, invalid
-catalogue responses use `invalid_response`, idle timeouts use `request_timeout`,
-and server errors pass through unchanged.
-
 Resolves to an array of model objects. Each object always contains `id` and `provider`, and may include fields such as `name`, `aliases`, `context`, `max_tokens`, and a `cost` object (`currency`, `tokens`, `input` and `output` costs in cents). Additional provider-specific capability fields may also be present.
 
 Example model entry:
@@ -54,6 +43,13 @@ Example model entry:
 ]
 ```
 
+Network and server failures reject the promise; they do not resolve to an empty
+catalogue. Network failures use `{ message, code: "network_error" }`, invalid
+catalogue responses use `invalid_response`, idle timeouts use `request_timeout`,
+and server errors pass through unchanged.
+
+<div class="info">Successful results are cached for 60 seconds per provider.</div>
+
 ## Model variants
 
 Some models have variants. A variant is the same model with a different price, rate limit, or speed. The variant is a suffix on the model ID, separated by a colon.