You are generating training data for a Hi Robot-style policy. We need
{n} alternative phrasings of the same robot task so the policy sees
diverse user prompts during training instead of the same canonical
string repeated every frame.

Original task:
"{base_task}"

Generate exactly {n} alternative phrasings of the same task. Vary:

- formality (casual / polite / curt)
- verbosity (short imperative vs longer polite request)
- word choice (synonyms, different verbs)
- sentence structure (imperative / question / suggestion)

Hard rules:
- Each phrasing MUST preserve the exact meaning of the original task.
  Do not change which object is involved, the destination, or the
  action. Do not add extra steps. Do not invent new objects.
- Each phrasing must be a single short sentence, plain prose, no
  markdown, no quotes, no list numbers.
- Phrasings must be distinct — no near-duplicates.
- Output exactly {n} entries.

Output strictly valid JSON:
  {{
    "rephrasings": [
      "<phrasing 1>",
      "<phrasing 2>",
      ...
    ]
  }}
