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
651 B
JSON
9 lines
651 B
JSON
{
|
|
"steps": [
|
|
{ "op": "initialize" },
|
|
{ "op": "newSession" },
|
|
{ "op": "prompt", "text": "Remember this fact for later: the project codeword is MARMALADE. Reply with the single word OK and stop. Do not use any tools." },
|
|
{ "op": "prompt", "text": "Use the subagent_fork tool exactly once to delegate this subtask to a forked child agent: 'What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.' The forked child inherits this conversation, so it can answer. After the subagent returns, reply with the single word PARENT_DONE and stop. Do not use the bash tool." }
|
|
]
|
|
}
|