docs: align agent and voice agent guides with current SDK behavior

[seratch]

This pull request updates the Agents, Running Agents, Tools, and Voice Agents guides to match the current SDK behavior and improve how the docs route readers between related topics. It also refreshes the docs-backed voice examples to reflect the current Realtime defaults and adds markdown formatting configuration so MD/MDX prose stays intentionally unwrapped.

Key updates in this change:

• Clarify agent, tool, handoff, and run-loop guidance with better cross-links, decision tables, and more accurate parameter descriptions across the core guides.
• Rework the Voice Agents overview, quickstart, build, and transport docs around current WebRTC/WebSocket/SIP behavior, ephemeral token flow, session configuration, interruptions, history handling, and low-level transport access.
• Refresh the voice-agent snippets to use gpt-realtime, prefer audio-first session examples, and add a new image-input example with session.addImage(...).
• Update .prettierrc and AGENTS.md so markdown and MDX prose are not manually hard-wrapped and repository guidance matches that formatting policy.

This is a docs-and-examples alignment pass rather than a runtime SDK change, so the main user-facing impact is clearer, more accurate guidance for integrating the current Agents and Realtime APIs.

[changeset-bot]

⚠️ No Changeset found

Latest commit: f40d954

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