Garry's Opinionated OpenClaw/Hermes Agent Brain
TypeScript
chore(release): stamp v0.60.569.0
garrytan3b13556eefba
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex cbd2da93d3..40676e05de 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -10,7 +10,7 @@ credits are retained; no result has been reassigned to another provider. Originaidentifiers and attribution are available in the pre-removal Git revision`6040075c6cb95be5881cc2e1b76ef7d71f4e5d29` (retained on 2026-09-23).-## [Unreleased]+## [0.60.569.0] - 2026-11-03**A brain opened from settings no longer leaks into the process, or into another brain, when a call forgets its scope.** While an embedded engine is open, an embed, chat, expansion or rerank call that entered no scope now refuses `engine_scope_required` and sends nothing, even if the host configured a process gateway; it decides by scope presence alone. `withLocalScope(fn)` marks a call that belongs to the process gateway, and the CLI, `gbrain serve` and `gbrain jobs` enter it, so they behave exactly as before. `hybridSearch`, the import paths, minion jobs and `POST /mcp` enter their engine's scope themselves. Each embedded engine keeps its own chat-usage sink (it survives `reconnect()`), batch-shrink, no-key and structured-output memory, and alias and remote-privacy policy, and a closed per-call engine is no longer held by the policy sets. A host that reopens a brain per call can pass `settings.cache_namespace` to keep its query embeddings warm. `openEngine` now refuses a settings key it does not know. Everything here is behind `embedded_core`, which is off by default.diff --git a/VERSION b/VERSIONindex 0019b70d32..e6122bb879 100644--- a/VERSION+++ b/VERSION@@ -1 +1 @@-0.60.568.0+0.60.569.0diff --git a/package.json b/package.jsonindex abc61acf0d..f9a1ae740b 100644--- a/package.json+++ b/package.json@@ -249,7 +249,7 @@"bun": ">=1.4.4"},"license": "MIT",- "version": "0.60.568.0",+ "version": "0.60.569.0","overrides": {"@ai-sdk/provider-utils": "4.0.56","@hono/node-server": "^2.0.5",