Skip to content

Garry's Opinionated OpenClaw/Hermes Agent Brain

TypeScript

Merge remote-tracking branch 'origin/capy/gbra283-wave-a-engine-caches' into ship-ga-8458

garrytan281705a80c4c
diff --cc CHANGELOG.md
index 31178f8da4,9b2f7c92fa..94e81f90ce
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@@ -10,19 -10,9 +10,19 @@@ credits are retained; no result has bee
identifiers and attribution are available in the pre-removal Git revision
`6040075c6cb95be5881cc2e1b76ef7d71f4e5d29` (retained on 2026-09-23).
+## [Unreleased]
+
+**SkillOpt rollouts now see the same tool errors MCP callers get.** When a read tool refused or failed during a SkillOpt rollout, the model saw only the error's one-line message. MCP callers get the full error for the same call: its code, the suggestion and a runnable `fix`. So skills were tuned against a weaker error surface than real callers read. Both SkillOpt registries (the read-only rollout registry and write-capture) now hand the model the exact error text an HTTP MCP caller receives, and they keep `code` for callers that branch on it. MCP output is unchanged. Write ops keep refusing as before.
+
+### Itemized changes
+
+- `src/mcp/dispatch.ts` (`asAgentToolError`): turns a failed read into an error whose message is the MCP error text for the same call. An AI invocation policy stop passes through unchanged, because the tool loop rethrows it.
+- `src/core/skillopt/rollout.ts`, `src/core/skillopt/write-capture.ts`: read handlers throw that error.
+- `test/skillopt-rollout-agent-errors.test.ts`: on both registries, a two-selector refusal and a missing-page error read exactly as MCP returns them, including the suggestion and the fix argv. All four cases fail on master.
+
## [0.60.556.0] - 2026-11-02
- **Mounted brains stop sharing settings and search telemetry.** In a process that serves several brains, search telemetry for every brain was written into the first brain's database, and a handful of per-brain settings were read once from whichever brain asked first and then applied to all of them. Each of those caches now belongs to its engine, and each engine gets its own telemetry writer, which retires when the engine disconnects. A process with one brain behaves exactly as before. Contributed by @bradgessler (#8454).
+ **Mounted brains stop sharing settings and search telemetry.** In a process that serves several brains, search telemetry for every brain was written into the first brain's database, and a handful of per-brain settings were read once from whichever brain asked first and then applied to all of them. Each of those caches now belongs to its engine, and each engine gets its own telemetry writer, which stops its timer when the engine disconnects and keeps its buffer for a reconnect. A process with one brain behaves exactly as before. Contributed by @bradgessler (#8454).
### Itemized changes