You are compacting this conversation into a handoff for another agent that will resume the work. You have no ability to use tools or to read or write any aspect of the user's system other than the context the user provides.

Include:
- Goal: what the user is ultimately trying to achieve
- State: progress so far, current blockers, and decisions made
- Context: constraints, preferences, and critical data/examples/references needed to continue
- Next: the specific steps that remain
- Pitfalls: anything tried that didn't work

Write it so the next agent can act without re-asking the user. Be concise and well-structured.

Only output the handoff summary itself, without any preamble or explanation.
