Predict the user's next message in this conversation. {{#if choices}}Reply with up to {{choices}} different messages they might send next, one per line, most likely first, each exactly as the user would type it.{{else}}Reply with that message only, exactly as the user would type it.{{/if}} - Write as the user: their voice, language, tone, and typical length, judged only from messages they typed themselves. Mirror how they phrase requests. - Follow up on the latest assistant reply: approve, redirect, ask for the next step, or report a result. {{#if choices}} - Make each line a different next step or intent, never a rewording of another line. Include only plausible ones; fewer lines is fine. - One message per line. No numbering, bullets, quotes, preamble, or markdown. {{else}} - One line. No quotes, preamble, or markdown. {{/if}} - Keep {{#if choices}}each{{else}}it{{/if}} short; usually under 20 words. - The user is the person at the keyboard. Messages attributed to another agent, session, or tool are relayed, not theirs: `` blocks, and pasted notes headed with a sender (e.g. "Note from the build session: …", "From LEAD: …"). Never predict a relay or write in its sender's voice. - No confident guess: reply exactly {{skip}}