docs: clarify config default review risk policy

clawsweeper[bot] · clawsweeper[bot] · commit d0cc9f2e3ebb · 2026-05-25T02:56:50.000Z
diff --git a/AGENTS.md b/AGENTS.md
@@ -23,7 +23,7 @@ Skills own workflows; root owns hard policy and routing.
 - ClawSweeper-owned schema, labels, close reasons, protected-label gates, maintainer-item gates, and mutation rules live in `openclaw/clawsweeper`.
 - Review workers read this full root `AGENTS.md` before judging; no reliance on search snippets, `head`, partial ranges, local excerpts, or truncated copies. Then read every scoped `AGENTS.md` that owns touched paths.
 - Optional integrations, providers, channels, skill bundles, MCP surfaces, and service workflows route to plugins, ClawHub, or owner repos when current seams suffice. Keep core items for missing core/plugin APIs, bundled regressions, security/core hardening, or maintainer product decisions.
-- Plugin APIs, provider routing, auth/session state, persisted preferences, config loading, migrations, setup, startup checks, and fallback behavior are compatibility/upgrade-sensitive. Treat config breaks, removed fallbacks, fail-closed changes, or new operator action as merge risk even with green CI. New or changed config/default additions are `reviewMetrics` and merge-risk material when they can affect existing users, upgrades, provider/plugin behavior, persisted preferences, setup, startup, workflow behavior, fallback behavior, or operator action.
+- Plugin APIs, provider routing, auth/session state, persisted preferences, config loading, migrations, setup, startup checks, and fallback behavior are compatibility/upgrade-sensitive. Treat config breaks, removed fallbacks, fail-closed changes, or new operator action as merge risk even with green CI. New or changed config/default additions are `reviewMetrics` and merge-risk material when they can affect existing users, upgrades, provider/plugin behavior, persisted preferences, setup, startup, workflow behavior, fallback behavior, or operator action. When practical, the metric should name the count and direction (added, changed, removed) of config/default surface changes and why those changes affect review risk.
 - Review whole decision surfaces, not only the touched runtime, provider, channel, harness, plugin seam, or context path. Check sibling Codex/Pi-style runtimes, provider/model routing, channel delivery, gateway/protocol, plugin SDK, and context-management paths when relevant.
 - One-sided fixes need sibling-surface proof, an explanation for why siblings are unaffected, or explicit follow-up work.
 - User-facing `fix`, `feat`, and `perf` changes need `CHANGELOG.md` before landing; contributor PR authors are not blocked solely on maintainer-owned changelog work. Never request thanks for bot/forbidden handles: `@openclaw`, `@clawsweeper`, `@codex`, `@steipete`.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -6,6 +6,8 @@ Docs: https://docs.openclaw.ai
 
 ### Changes
 
+- Maintainers: clarify that config/default `reviewMetrics` should include the count and direction of changed surfaces and why those changes affect review risk. (#86295)
+
 ### Fixes
 
 - Scripts: build CLI startup artifacts before the gateway CPU startup bench so fresh Linux runners do not report false `n/a` readiness and process metrics.
