2026-08-25 13:29:34 -07:00
|
|
|
# Format: window <role> <agent> <worktree> [task|batch] [extra-cli-args...]
|
|
|
|
|
# The optional receive mode defaults to task. Use batch for roles that should
|
|
|
|
|
# consume all currently queued equal-priority handoffs as one batch.
|
|
|
|
|
# Any fields after the receive mode are passed to the agent CLI, e.g. --yolo.
|
|
|
|
|
#
|
|
|
|
|
# four-pack + pi on Linux: un solo harness (pi), un modelo por rol.
|
|
|
|
|
# - specifier/coder → opencode-go/deepseek-v4-flash (familia DeepSeek, flash)
|
|
|
|
|
# - refactorer → qwen-token-plan/qwen3.7-max (familia Qwen)
|
|
|
|
|
# - architect → qwen-token-plan/glm-5.2 (familia GLM)
|
|
|
|
|
# Verificar ids con: pi --list-models
|
|
|
|
|
window specifier pi master --model deepseek-v4-flash:0731-cloud
|
2026-08-25 18:59:01 -07:00
|
|
|
window coder pi coder --model kimi-k2.7-code:cloud
|
2026-08-25 13:29:34 -07:00
|
|
|
window refactorer pi refactorer batch --model deepseek-v4-flash:0731-cloud
|
|
|
|
|
window architect pi architect batch --model deepseek-v4-flash:0731-cloud
|
