Add documentation for limiting token usage in AG-UI, conversational, …

[GugaGlonti]

Description

Documents the parameters.max_tokens agent-level token budget for conversational agents, AG-UI agents, plan-execute-reflect agents, and the Execute Agent API.

This update explains that max_tokens limits covered agent-runner LLM calls by applying the remaining budget before each request, preserving lower per-call model limits, and stopping execution when reported usage exhausts the budget. It also clarifies that include_token_usage is not required for token limiting; it only controls whether detailed token usage metrics are returned in the response.

Issues Resolved

Closes #12430

Version

3.7

Frontend features

N/A. This PR documents ML Commons agent API behavior and does not include OpenSearch Dashboards frontend changes.

Checklist

• By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license and subject to the Developers Certificate of Origin.
  For more information on following Developer Certificate of Origin and signing off your commits, please check here.

[github-actions]

Thank you for submitting your PR. The PR states are In progress (or Draft) -> Tech review -> Doc review -> Merged.

Before you submit your PR for doc review, make sure the content is technically accurate. If you need help finding a tech reviewer, tag a maintainer.

When you're ready for doc review, tag the assignee of this PR. The doc reviewer may push edits to the PR directly or leave comments and editorial suggestions for you to address (let us know in a comment if you have a preference).