Checkpoint-scoped execution for an existing AFlow plan. Use when an agent should implement exactly one checkpoint, verify it, synchronize plan state, and then stop instead of continuing into the next checkpoint.
Lightweight execution reinforcement for an existing AFlow plan. Use when an agent must resume from the first unchecked checkpoint and keep the plan synchronized with verified progress.
Create a strict AFlow checkpoint handoff plan for coding work that will be implemented by another model, tool, or later session. Use when the user explicitly wants the aflow pattern or a checkpoint-based handoff plan.
Checkpoint-scoped review for AFlow plans. Use when an agent should review the latest checkpoint attempt, compare it against the original plan, and either approve that checkpoint or create a focused fix plan for that checkpoint only.
Final no-squash review for a completed checkpointed AFlow handoff. Use when the original plan is complete and the reviewer must either approve the whole result or create one focused follow-up fix plan.
Review a completed autonomous AFlow plan, compare the full accumulated implementation against the original plan, and either squash the whole handoff into one final commit or create a focused fix plan for the remaining failed checkpoints or behaviors.
Decide how aflow should recover from harness throttling, quota, and other repeatable runtime failures. Return one strict JSON object only.
Investigate aflow setup problems, failed or confusing workflow runs, run-log evidence, plan parsing and retry issues, lifecycle/bootstrap/merge failures, and questions about aflow concepts or interface behavior. Use when an agent needs to explain what happened in an aflow run, gather high-signal evidence from `.aflow/runs/` efficiently, or reason about the engine from bundled references when a source checkout is unavailable.