Files

T

Yifan Yang 86bad36ffe feat(sleep): SkillOpt-Sleep plugin update (preview) — engine robustness + scheduling

Updates the SkillOpt-Sleep plugin on top of the current main. User-facing and
engine improvements since the initial drop:

* Command renamed /sleep -> /skillopt-sleep across Claude Code + Codex shells;
  refreshed plugin READMEs and install scripts.
* Built-in scheduling (skillopt_sleep/scheduler.py + __main__): schedule /
  unschedule the nightly cycle without external cron wiring.
* Backend robustness: bounded retry with backoff (no more silent empty-string
  on transient 429/timeout), content-filter-safe rollout prompt, an
  output-contract guardrail that rejects edits violating the task's required
  format, and a per-sample cache key so repeated dream rollouts are independent
  samples (fixes degenerate single-sample reflection).
* consolidate / rollout / replay: parallel multi-rollout dreaming, gate-mode
  controls, TaskRecord.system framing field.

Scope: this commit ships only the plugin engine + shells. Research/benchmark
harnesses and their data are intentionally not included; the public package
has no dependency on them (the one research-evaluator import is now guarded).
Marked as an early preview in the README; we'll keep iterating.

99/99 unit tests pass.

Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>

2026-06-14 16:12:00 +00:00

2.0 KiB

Raw Blame History

name, description

name	description
skillopt-sleep	Nightly offline self-evolution for a Codex agent. Reviews past sessions, replays recurring tasks, and consolidates validated memory + skills behind a held-out gate. Use when the user wants Codex to learn from past usage, run a "sleep"/"dream" cycle, or schedule offline self-optimization.

SkillOpt-Sleep (Codex skill)

This skill drives the skillopt_sleep engine — an offline "sleep cycle" that makes a Codex agent better at the user's recurring work without retraining.

When to use

Trigger when the user wants to: review past sessions, learn their preferences, consolidate feedback into long-term memory/skills, run a nightly/offline self-improvement cycle, or adopt a staged proposal.

How to run it

Invoke the bundled runner via shell (Codex exec has shell access). The runner finds the engine and a Python ≥ 3.10 automatically:

# point at the repo if it isn't auto-detected from CWD:
export SKILLOPT_SLEEP_REPO=/path/to/SkillOpt-Sleep
bash "$SKILLOPT_SLEEP_REPO/plugins/run-sleep.sh" <action> --project "$(pwd)"

<action> ∈ status | dry-run | run | adopt | harvest. Use --backend codex for real improvement on the user's own Codex budget (default mock = no spend).

Steps

Run the requested action; capture stdout.
For run/dry-run: read the staged report.md it prints and show the user the held-out baseline → candidate score and the exact proposed edits.
run only stages a proposal under <project>/.skillopt-sleep/staging/; nothing live changes until adopt. Offer /skillopt-sleep adopt.
Never hand-edit the user's AGENTS.md / skills yourself — only adopt does, and it backs up first.

Validate

python -m skillopt_sleep.experiments.run_gbrain --backend codex \
  --seeds brief-writer --data-root /path/to/gbrain-evals/eval/data/skillopt-v1 \
  --nights 2 --limit-replay 3 --limit-holdout 3

A deficient skill goes 0.00 → 1.00 on a held-out set; the optimizer's edits are gated on real-task performance.

2.0 KiB Raw Blame History