From 1c6a0e75c8b7e3a8c8c4d81f347d155107c13466 Mon Sep 17 00:00:00 2001 From: Cuzyoung Date: Wed, 10 Jun 2026 13:19:27 +0000 Subject: [PATCH] docs(guide): document skill-aware reflection options in the configuration guide Co-Authored-By: Claude Fable 5 --- docs/guide/configuration.md | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/docs/guide/configuration.md b/docs/guide/configuration.md index 55a3a86..57fffae 100644 --- a/docs/guide/configuration.md +++ b/docs/guide/configuration.md @@ -61,6 +61,36 @@ optimizer: use_meta_skill: true # Cross-epoch strategy memory ``` +### Skill-Aware Reflection (optional, off by default) + +EmbodiSkill-style failure routing: the failure analyst classifies each +failure pattern as **SKILL_DEFECT** (the rule is wrong or missing → normal +gated body edit) or **EXECUTION_LAPSE** (a valid rule exists but was not +followed → a short reminder appended to a protected appendix region inside +the skill that step-level edits can never modify). + +```yaml +optimizer: + use_skill_aware_reflection: false # Master switch (default off = baseline-identical) + skill_aware_appendix_source: both # both | failure_only (paper-faithful S_app) + skill_aware_consolidate_threshold: 0 # >0: LLM-compact the appendix past N notes (experimental) +``` + +Notes: + +- The switch is resolved process-wide from the config + (`configure_skill_aware_reflection`), so it applies to every benchmark + with no per-adapter wiring. +- `failure_only` restricts appendix notes to the failure analyst, matching + the original S_app formulation; `both` additionally lets the success + analyst re-emphasize existing rules. +- Appendix notes bypass the validation gate by design and accumulate with + order-preserving dedup; lapse-only steps (no body edits) still flush + their notes. +- Not supported together with `skill_update_mode=rewrite_from_suggestions` + or the full-rewrite modes: whole-document rewrites can drop the appendix + region. + ### Evaluation ```yaml