5 Commits

Author SHA1 Message Date
CharlesYang030
e4ea6a6771 chore(release): v0.2.0
Highlights since v0.1.0:
- feat: SkillOpt-Sleep engine — nightly offline self-evolution
  (harvest -> mine -> replay -> consolidate behind a validation gate),
  with multi-objective reward, experience replay + dream rollouts,
  slow-update long-term memory, and secret redaction in cycle diagnostics.
  Shipped as the `skillopt-sleep` CLI.
- feat: cross-tool backends & plugin shells — Claude, Codex (+Desktop
  harvest), Copilot, Devin, and OpenClaw.
- feat: SearchQA split materialization + rollout fail-fast.
- fix: Windows robustness for claude/codex backends, hardened JSON
  fallback, Qwen timeout/thinking gating, Codex failure surfacing.

Packaging:
- Bump pyproject / skillopt / skillopt_sleep to 0.2.0.
- Restore skillopt_webui to the packaged wheel.

See CHANGELOG.md for the full changelog and contributor acknowledgements.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-02 22:11:10 +08:00
Yifan Yang
46b3207b96 docs(sleep): trim RESULTS to the headline results (remove the full grid)
Remove the per-cell full deployment grid section; keep the gate-safety stress
test, experience-replay scaling + night-by-night climb, the dream-diversity
ablation, the gbrain end-to-end result, and the scope/limitations. Renumber
sections; update the README pointer accordingly.
2026-06-15 17:08:51 +00:00
Yifan Yang
d02098ffc4 docs(sleep): add full Results & Analysis (RESULTS.md); link from README
Adds docs/sleep/RESULTS.md — the complete deployment-scale study behind
SkillOpt-Sleep, presented rigorously (named benchmarks, test sizes, metrics,
baseline->after, single shared protocol):
  1. Gate-safety stress test: ungated nano SearchQA collapses 0.554->0.026
     (-52.8); the gated twin holds 0.570 — the core argument for the design.
  2. Full 18-cell deployment grid (3 benchmarks x 3 targets x gate/free),
     shipped config: mean +0.5, range [-2.4, +5.1], nothing hidden.
  3. Experience-replay scaling (recall_k 10->20->full: +3.1->+4.5->+5.6) and
     the night-by-night climb (0.798->...->0.858, gate accepts as late as N5).
  4. Dream-diversity fix as defense-in-depth: 3-config grid comparison
     (-2.66/-52.8 -> +0.24/-4.0 -> +0.53/-2.4); the -52.8 cell becomes +2.7
     from the dream fix alone.
  5. gbrain end-to-end 0.00->1.00 on real Claude + Codex.
  6. Honest scope: where it helps vs flat-in-noise, single-seed caveat with a
     seed-robustness spot check, keep-the-gate-on.
README Results section now links prominently to it. Docs only; numbers are
self-contained with reproduce commands (no raw run dumps committed).
2026-06-15 16:49:13 +00:00
Yifan Yang
ea4ff459d7 docs(sleep): make the results section rigorous (named benchmarks, baseline→after)
Label each result with its benchmark, test size, metric, target model, and gate
mode; show absolute baseline→after (not just Δ); state the single shared protocol
once. SearchQA recall-scaling table (1400-item test, SQuAD-EM, GPT-5.5, gated) +
SpreadsheetBench confirmation (280-item, cell-value compare, nano, gate-free) +
the gbrain end-to-end line. Keeps the single-seed / flat-on-noisy caveats.
2026-06-15 16:42:43 +00:00
Yifan Yang
de3be75bac docs(sleep): add a SkillOpt-Sleep module readme + News mention
Adds docs/sleep/README.md — a concise intro to the SkillOpt-Sleep plugin (what
it is, how to use it across the three agents, the opt-in experience-replay /
dream-rollout knobs, and headline results), linking to the full guide section.
Adds a News bullet pointing to it. No code changes.
2026-06-15 16:31:15 +00:00