Tianyi Cui
78d60366ec
The seed-boundary change made fork-child replay route correctly but shipped with no recorded fork scenario — the seedLength slice was exercised only by llm-replay unit tests and a persistence round-trip, never by the full-transcript snapshot tier. Add two recorded scenarios that drive a real fork child through it: - subagent-fork: parent completes a turn, then forks one child (child fixture carries a non-zero seedLength, the boundary the replay slice consumes). - subagent-mixed: parent completes a turn, then delegates once via spawn (seedLength 0) and once via fork (non-zero seedLength) in one transcript — the first scenario to drive two subagent backends at once, exercising both branches of the slice. Both need a completed turn-1 so the fork seed is a non-empty completed-turn prefix (a turn-1 fork seeds empty = spawn, which would not exercise the slice). Removing the slice turns both scenarios red (the fork child receives the parent's recorded chunks), proving the guard bites. ACP (out-of-process) subagent replay remains a different shape, still tracked as TODO(acp-subagent-replay).
9 lines
762 B
JSON
9 lines
762 B
JSON
{
|
|
"steps": [
|
|
{ "op": "initialize" },
|
|
{ "op": "newSession" },
|
|
{ "op": "prompt", "text": "Remember this fact for later: the project codeword is SAFFRON. Reply with the single word OK and stop. Do not use any tools." },
|
|
{ "op": "prompt", "text": "Do these two delegations, once at a time. First, use the subagent tool (fresh child) exactly once: 'Reply with exactly the word ALPHA and nothing else.' Then, after it returns, use the subagent_fork tool (forked child that inherits this conversation) exactly once: 'What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.' After both subagents return, reply with the single word PARENT_DONE and stop. Do not use the bash tool." }
|
|
]
|
|
}
|