Skip to content

Garry's Opinionated OpenClaw/Hermes Agent Brain

TypeScript

docs(changelog): W-H2 harness fixes (Hermes, Windows, request_tools, schema show, claude-cli)

garrytana2c47b652815
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8cadb056cf..9882b0af36 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,6 +10,18 @@ credits are retained; no result has been reassigned to another provider. Origina
identifiers and attribution are available in the pre-removal Git revision
`6040075c6cb95be5881cc2e1b76ef7d71f4e5d29` (retained on 2026-09-23).
+## [Unreleased]
+
+**Five harness fixes: Hermes, Windows, request_tools, schema show and claude-cli.** A per-turn hook you paste into Hermes by hand now counts, Windows Claude Code installs get the per-turn rule hook, `request_tools` stops promising tools a stdio session cannot call, `gbrain schema show --source` reads that source's pack, and claude-cli calls no longer carry your personal Claude Code instructions.
+
+### Itemized changes
+
+- **Hermes:** when your `config.yaml` already has a `hooks:` section, `gbrain setup hermes` prints the `pre_llm_call` entry for you to add. Once you paste it, `gbrain doctor` now sees it (and still reports it untrusted until Hermes approves it) instead of calling it missing (reported by @Masashi-Ono0611, #8857).
+- **Windows:** `gbrain setup claude-code` and the other install paths now write the per-turn rule hook for a Windows gbrain binary (`C:\...\gbrain.exe`) instead of skipping it with "no absolute gbrain binary was found". The hook names its paths in Git Bash's `/c/...` form, which is how Claude Code runs hooks on Windows. Codex runs hooks on Windows without a POSIX shell, so it still gets the printed step, now with that reason (reported by @Masashi-Ono0611, #8451).
+- **request_tools:** on a stdio session started at a narrower surface (`gbrain serve --surface starter`), `request_tools {tools: [...]}` lists only the tools the session can call. A tool outside it comes back with its schema, `listed: false` and a note to call `request_tools {"surface":"full"}` first, instead of a promise that it is in your tool list (reported by @Masashi-Ono0611, #8734).
+- **Schema packs:** `gbrain schema show --source <id>` shows that source's own pack (its per-source override, else the brain-wide pack) instead of failing with `Unknown pack: <id>`. A pack you name still wins (reported by @Masashi-Ono0611, #8900).
+- **claude-cli provider:** on Claude Code 2.1.314 or newer, gbrain's background `claude-cli` calls run with `--setting-sources ""`, so your `~/.claude/CLAUDE.md`, memory and `settings.json` no longer steer them, and your subscription login is kept. gbrain reads `claude --version` once per binary; older CLIs are unchanged (reported by @Masashi-Ono0611, #8350).
+
## [0.60.620.0] - 2026-11-09
**A diverged managed checkout now publishes its local commits on refresh by default when Git durability is on, after a secret scan of those commits.** Commits a script made with plain `git commit` in a managed checkout used to strand there whenever the remote moved: every `gbrain sources refresh` refused `refresh_diverged` and asked the user, unless `sources.refresh_publish_diverged` was set to `true`. With the setting unset, a worktree whose Git durability is on (`gbrain sources writer git-durability <source> --enable`, or the legacy hook) now publishes them itself: the local commits merged with the upstream in memory, never a rebase or force-push, then the fast-forward. The publish child scans, under its publish lock and for the exact commits it pushes, what they add: commit messages, added lines (including a value a later commit removed) and merge-commit conflict resolutions. A value that looks like a secret, added text too large to scan, or a commit that changes `.gbrain-scan-allow` or a `.gitattributes` refuses the new `publish_secret_found` naming the file, line, rule and commit, never the value, with nothing pushed; commits the scan cannot read in full refuse `publish_scan_unreadable` instead. The rewritten-upstream refusal and the `--expect-remote` bound are unchanged. `false` turns it off; `true` still publishes with durability off.