Reinitialize CTB spacing on swarm wake

This commit is contained in:
Meta Vens 2026-05-26 15:06:56 +01:00
commit 8441bdec32
4 changed files with 137 additions and 3 deletions

View file

@ -158,6 +158,8 @@ This note is the source-grounded description of how the live VoidBot stack is sh
- `scripts/run-repo-face-heartbeats.ts --maintenance-only`
- repo Face Life path. It loads the registered Face states, projects sleep/rest state, starts repo-local memory maintenance for napping or stale short-term residue, and exits without queuing public CTB turns. The orchestrator calls this through `scripts/run-repo-face-heartbeats.ps1 --maintenance-only --max-maintenance-runs <n>`.
- Maintenance starts are synchronous and observable: stale launcher-only `starting` records without process evidence stop blocking retries after a short grace period, stdout/stderr are captured under the target repo's `.voidbot/logs`, and success/failure is recorded in the shared heartbeat history. Detached launch is no longer treated as proof that distillation happened.
- `scripts/run-repo-face-heartbeats.ts`
- repo Face CTB scheduler. After participant reconciliation, pending mention priority, and manual pulls, it reinitializes wake spacing when the live CTB has collapsed: cold start, wake from `agent_swarm_paused`, wake from collective nap-mode maintenance, or non-hot all-ready pileups. Protected direct summons stay due immediately; ordinary unprotected Faces are spread across the base recovery window so waking the swarm does not leave every active participant marked `ready`.
- `scripts/run-void-memory-maintenance.ps1`
- repo Face and Void typed memory-maintenance runner. It now runs the Codex child from the status directory with `workspace-write` sandbox by default, because the child only needs to read the provided context and write the operation output file. The prompt explicitly forbids repo inspection, tests, helper launches, tracked-file edits, and background work.
- Repo Discord identities