Skip to content

v1.0.0 — the self-improvement release

Latest

Choose a tag to compare

@anianroid anianroid released this 07 Jul 03:41
· 114 commits to main since this release
81c0ce5

The first tagged release. session-warden graduates from a session lifeguard to a full self-improvement harness for persistent OpenClaw agent fleets.

Fixed

  • Recovery delivery restored (#16): OpenClaw 2026.6.x requires --channel with multi-channel gateways and --session-key for session keys; both were breaking every post-rotation recovery silently. Failure counters now reset on rotation completion, not delivery success — the mechanism that permanently wedged sessions in BACKOFF.
  • BACKOFF now escalates once via Telegram and throttles log spam to hourly (#19).
  • Delivery errors surface stderr in logs; channel-less sessions skip --deliver (#19).
  • update-openclaw.sh recognizes retired dist patches on OpenClaw ≥ 2026.6.5 (#19).
  • Portable stat helpers for macOS/BSD (#19, closes the #2 proposal with GNU-first ordering).

Added

  • Reflector (#17): nightly per-agent lesson distillation — Sonnet maker + independent Haiku skeptic, ACE-style append-only bullets staged for human approval, apply-lessons.sh mirrors approved lessons to GBrain with provenance.
  • Skill harvester (#18): weekly mining of repeated workflows into staged SKILL.md drafts + promote-skill.sh.
  • Model scorecard (#20): weekly blind-judged benchmark across experimental agents, results to GBrain + Telegram.
  • Memory evals (#20): monthly regression eval of each agent's memory quality with per-run deltas.
  • Rotation summaries link GBrain page slugs instead of restating facts, and stage lesson candidates for the Reflector (#19).
  • GBrain graceful degradation, weekly logrotate policy (#19).

Requires

bash, jq, flock, the claude CLI, an OpenClaw gateway, and optionally GBrain + a Telegram bot for notifications.