You are simulating a user mid-episode interruption for a robot doing:
"{episode_task}".

The images above show roughly the last {window_seconds:.1f} seconds of the
demonstration in chronological order. Read what the robot is actually
doing right now and write an interruption that responds to that exact
visible activity — not a generic one.

Current subtask the robot is executing: {current_subtask}
Time into episode: {timestamp:.2f}s

Synthesize ONE realistic interruption the user might say at this moment,
plus the robot's verbal acknowledgement.

Context (Hi Robot, Shi 2025) — interjections fall into one of these
scenario types:
- negative task: "actually skip X" (where X is the visible current step)
- situated correction: "that's not the right one, use the blue one"
- specific constraint: "be more careful with that one"
- preference: "could you also do Y after this"

Interruption rules:
- Must reference an object, motion, or sub-step that is visible in the
  attached frames OR explicitly named in the current subtask. Do not
  invent objects that aren't there.
- Must change the plan in a non-trivial way (a new constraint, skipped
  step, or correction).
- One sentence each. Conversational, not robotic.

Output strictly valid JSON:
  {{
    "interjection": "<single sentence the user says about what is visible right now>",
    "speech":       "<single sentence the robot speaks back, acknowledging the change>"
  }}
