docs: clarify run context, handoffs, and human-in-the-loop guides

[seratch]

This pull request updates five core guides under docs/src/content/docs/guides/ to make advanced run behavior easier to reason about. It clarifies RunContext and serialization in context.mdx, guardrail scope and workflow boundaries in guardrails.mdx, handoff inputType and inputFilter behavior in handoffs.mdx, approval/resume behavior for nested agent.asTool() flows in human-in-the-loop.mdx, and result-surface selection in results.mdx.

The main goal is to remove ambiguity around nested runs, handoffs, approvals, and resumable state. In particular, the docs now spell out which guardrails run where, how handoff metadata differs from destination selection, how interruptions behave across nested agent-tool executions, and when to use history, output, newItems, interruptions, state, and streamed-result fields.

[changeset-bot]

⚠️ No Changeset found

Latest commit: 0fd5d5a

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR