swarm

Swarm

Fan out N parallel workers, each in its own Paseo worktree. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report.

Start

Open a todolist with one entry per phase before launching anything.

1. Frame
2. Fan out
3. Aggregate
4. Report

Phase A: Frame

1. State the done predicate and the artifact or report the swarm must return.
2. Choose the shape. Partition into slices, race N workers on identical briefs, or mix both. For a race or mixed shape, declare first pass, rank all, or best-of before spawning.
3. Set N from the user or derive it from the shape. N is total workers, not a concurrency limit.
4. Pick the worker model from the pstack Agent profiles (read them with list_profiles): pstack-worker, default codex/gpt-6.1-sol xhigh. Copy the profile's provider/model, thinkingOptionId, modeId, and featureValues into create_agent. If create_agent rejects a model, use the default and say so. If it rejects the default, use the closest valid model of the same provider from list_models. For a model race, name each arm's model up front.
5. Give each worker its own writable output when it writes. When workers verify or measure commits, each brief names the exact SHAs. A measurement brief also names the method (sample count, what one sample is, order). The worker records both in its result.

Phase B: Fan out

Spawn all N workers in one message with create_agent, each in its own Paseo worktree (create_workspace with isolation worktree, then pass its workspaceId), notifyOnFinish: true, and the step 4 model. Run a worker in the current workspace only when it needs access to something outside a fresh worktree.

When a worker must start from a non-default pushed branch, pass it as baseBranch to create_workspace.

Every brief stands alone. Include the goal, scope, exact slice or race arm, how to verify, and what to report. Reports use PASS, ISSUES, or BLOCKED with evidence. A worker that can prove a defect reports ISSUES and lists every issue it can prove, not only the first.

If a worker drops out, proceed with N-1 and note it.

Phase C: Aggregate

Read the terminal results. Drop a result that does not record the SHAs and method its brief names, and rerun that worker once. After a second miss, record a gap. A gap does not count as a pass. For coverage, every required slice needs a result. For a race, apply the selection rule declared up front. Use first pass, rank all, or best-of. Do not paste raw worker dumps.

Keep a compact result table, one-line evidenced issues, and explicit gaps or dropouts.

Phase D: Report

Return one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.