Skip to content

Garry's Opinionated OpenClaw/Hermes Agent Brain

TypeScript

chore: stamp v0.60.654.0

garrytanf9b2072e3ef7
diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
index 213b6f5956..60af0a83be 100644
--- a/.claude-plugin/plugin.json
+++ b/.claude-plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "gbrain",
- "version": "0.60.653.0",
+ "version": "0.60.654.0",
"description": "Personal knowledge brain for your coding agent — hybrid search, synthesis, graph traversal, and durable cross-session memory over Postgres/PGLite with pgvector, plus a curated brain-first skill set.",
"author": {
"name": "Garry Tan",
diff --git a/.codex-plugin/plugin.json b/.codex-plugin/plugin.json
index 573f67431a..c969caed24 100644
--- a/.codex-plugin/plugin.json
+++ b/.codex-plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "gbrain",
- "version": "0.60.653.0",
+ "version": "0.60.654.0",
"description": "Personal knowledge brain for your coding agent — hybrid search, synthesis, graph traversal, and durable cross-session memory over Postgres/PGLite with pgvector, plus a curated brain-first skill set.",
"author": {
"name": "Garry Tan",
diff --git a/BOOTSTRAP_FOR_AGENTS.md b/BOOTSTRAP_FOR_AGENTS.md
index 60ccc8c17e..091e5106b9 100644
--- a/BOOTSTRAP_FOR_AGENTS.md
+++ b/BOOTSTRAP_FOR_AGENTS.md
@@ -1,4 +1,4 @@
-<!-- gbrain-runbook-stamp: 0.60.653.0 -->
+<!-- gbrain-runbook-stamp: 0.60.654.0 -->
<!-- This stamp must equal the VERSION file at every release; CI enforces it
(scripts/check-bootstrap-tag.sh). `gbrain bootstrap status` compares it to
the installed binary and warns on skew. -->
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 9094110a4b..757188ab8f 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,7 +10,7 @@ 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]
+## [0.60.654.0] - 2026-11-10
**A managed sync no longer fetches Git objects in a partial clone (`git clone --filter`).** Every Git read a managed sync makes now runs with Git's transports and lazy fetching switched off. A file whose blob the clone never fetched is imported from your checkout when the checkout holds exactly that blob, and otherwise held alone as `git_object_missing`, with a message that names the partial clone and the `git cat-file -p <blob>` that fetches it. A blobless clone with a normal checkout syncs every file as before; an older object it never fetched (an earlier version of a renamed file or of the folder rules) is read only once you fetch it. A treeless clone (`--filter=tree:0`) that lacks a tree of the commit being synced stops the run with `git_object_missing`, naming the partial clone and the `git ls-tree -r -d <commit>` that fetches the trees; nothing is synced or deleted until then. The folder rules in `.gbrain/access.yml` are read the same way. A rule file or rule history the clone has not fetched makes the source read as nobody to remote members, as a shallow checkout already does, with a message that names the exact `git` command that fetches it. Run that command in the checkout and the next sync applies the rules and clears the mark.
diff --git a/VERSION b/VERSION
index 2d891489f7..42dd617870 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-0.60.653.0
+0.60.654.0
diff --git a/openclaw.plugin.json b/openclaw.plugin.json
index 973cca7443..dc7234fbf6 100644
--- a/openclaw.plugin.json
+++ b/openclaw.plugin.json
@@ -1,7 +1,7 @@
{
"id": "gbrain-context-engine",
"name": "gbrain",
- "version": "0.60.653.0",
+ "version": "0.60.654.0",
"description": "Personal knowledge brain with Postgres + pgvector hybrid search",
"family": "bundle-plugin",
"kind": "context-engine",
diff --git a/package.json b/package.json
index fd9b45dac0..57b747ac60 100644
--- a/package.json
+++ b/package.json
@@ -254,7 +254,7 @@
"bun": ">=1.4.4"
},
"license": "MIT",
- "version": "0.60.653.0",
+ "version": "0.60.654.0",
"overrides": {
"@aws-sdk/util-format-url": "3.972.9",
"@ai-sdk/provider-utils": "4.0.56",
diff --git a/plugin-variants/gbrain-coding/.claude-plugin/plugin.json b/plugin-variants/gbrain-coding/.claude-plugin/plugin.json
index 30332cdfa1..29a554e4c2 100644
--- a/plugin-variants/gbrain-coding/.claude-plugin/plugin.json
+++ b/plugin-variants/gbrain-coding/.claude-plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "gbrain-coding",
- "version": "0.60.653.0",
+ "version": "0.60.654.0",
"description": "Brain-first coding agent working inside a repo: retrieval, routing, ingest discipline, correction hygiene. Default persona for the claude-code harness bridge; also published as the gbrain-coding marketplace variant. (persona variant of the gbrain plugin — 21 skills)",
"author": {
"name": "Garry Tan",
diff --git a/plugin-variants/gbrain-coding/.codex-plugin/plugin.json b/plugin-variants/gbrain-coding/.codex-plugin/plugin.json
index dc1e4b8112..65cf3505c3 100644
--- a/plugin-variants/gbrain-coding/.codex-plugin/plugin.json
+++ b/plugin-variants/gbrain-coding/.codex-plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "gbrain-coding",
- "version": "0.60.653.0",
+ "version": "0.60.654.0",
"description": "Brain-first coding agent working inside a repo: retrieval, routing, ingest discipline, correction hygiene. Default persona for the claude-code harness bridge; also published as the gbrain-coding marketplace variant. (persona variant of the gbrain plugin — 21 skills)",
"author": {
"name": "Garry Tan",
diff --git a/plugin-variants/gbrain-coding/README.md b/plugin-variants/gbrain-coding/README.md
index 698a56c2ce..fd7b088b22 100644
--- a/plugin-variants/gbrain-coding/README.md
+++ b/plugin-variants/gbrain-coding/README.md
@@ -1,4 +1,4 @@
-<!-- gbrain-plugin-tree-stamp: 0.60.653.0 -->
+<!-- gbrain-plugin-tree-stamp: 0.60.654.0 -->
# gbrain-coding (generated persona variant — do not hand-edit)
Brain-first coding agent working inside a repo: retrieval, routing, ingest discipline, correction hygiene. Default persona for the claude-code harness bridge; also published as the gbrain-coding marketplace variant.
diff --git a/plugin-variants/gbrain-daily/.claude-plugin/plugin.json b/plugin-variants/gbrain-daily/.claude-plugin/plugin.json
index fd4160a107..29de1a79c4 100644
--- a/plugin-variants/gbrain-daily/.claude-plugin/plugin.json
+++ b/plugin-variants/gbrain-daily/.claude-plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "gbrain-daily",
- "version": "0.60.653.0",
+ "version": "0.60.654.0",
"description": "Personal knowledge-brain daily use: meetings, tasks, briefings, reading, research. Published as the gbrain-daily marketplace variant. (persona variant of the gbrain plugin — 20 skills)",
"author": {
"name": "Garry Tan",
diff --git a/plugin-variants/gbrain-daily/.codex-plugin/plugin.json b/plugin-variants/gbrain-daily/.codex-plugin/plugin.json
index a87f0f1478..395946eb71 100644
--- a/plugin-variants/gbrain-daily/.codex-plugin/plugin.json
+++ b/plugin-variants/gbrain-daily/.codex-plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "gbrain-daily",
- "version": "0.60.653.0",
+ "version": "0.60.654.0",
"description": "Personal knowledge-brain daily use: meetings, tasks, briefings, reading, research. Published as the gbrain-daily marketplace variant. (persona variant of the gbrain plugin — 20 skills)",
"author": {
"name": "Garry Tan",
diff --git a/plugin-variants/gbrain-daily/README.md b/plugin-variants/gbrain-daily/README.md
index 0b523c69b7..05752ad490 100644
--- a/plugin-variants/gbrain-daily/README.md
+++ b/plugin-variants/gbrain-daily/README.md
@@ -1,4 +1,4 @@
-<!-- gbrain-plugin-tree-stamp: 0.60.653.0 -->
+<!-- gbrain-plugin-tree-stamp: 0.60.654.0 -->
# gbrain-daily (generated persona variant — do not hand-edit)
Personal knowledge-brain daily use: meetings, tasks, briefings, reading, research. Published as the gbrain-daily marketplace variant.
diff --git a/plugin/README.md b/plugin/README.md
index 8bf6d51a1f..5fb574316b 100644
--- a/plugin/README.md
+++ b/plugin/README.md
@@ -1,4 +1,4 @@
-<!-- gbrain-plugin-tree-stamp: 0.60.653.0 -->
+<!-- gbrain-plugin-tree-stamp: 0.60.654.0 -->
# gbrain plugin skill tree (generated — do not hand-edit)
This tree is the curated skill set for the gbrain Codex and Claude Code
diff --git a/src/core/behavior-change-notice.ts b/src/core/behavior-change-notice.ts
index 1475069b60..0737fb5d5a 100644
--- a/src/core/behavior-change-notice.ts
+++ b/src/core/behavior-change-notice.ts
@@ -1507,7 +1507,7 @@ export const BEHAVIOR_CHANGES: ReadonlyArray<{ since: string; text: ChangeText;
{ since: '0.60.649.0', id: 'private_labels_write_ahead_gst2092', text: '`gbrain repair private-labels` writes its undo ledger ahead of each page: an `intent` line before the write and a `committed` line after it, so a run that stops between them can still be undone with `--class restore`, and a ledger that cannot take the intent line refuses the apply (`storage_error`) before anything changes. Restore re-adds only `access` and `visibility: private` from well-formed ledger lines (others are counted unreadable) and no longer lists a page whose label was removed after a restore landed (`removed_after_restore`). The preview counts the derived_from pages and life-chronicle events each window would expose along with its pages; on a brain without managed persistence a page whose file sits in its source\'s checkout is held (`file_backed`) instead of being cleared in the database only; and an apply that ends with a failure keeps its approved preview, so the same `--apply --expect` resumes it.' },
{ since: '0.60.650.0', id: 'private_labels_batch_exit_gbra443', text: '`gbrain repair private-labels --apply --expect` on a brain with managed persistence admits a window\'s pages together and publishes them in groups instead of one page and one wait at a time; a page whose write is declined fails alone. `gbrain repair <kind> --apply --expect <hash>` (every preview-bound kind) now exits 0 when the run is complete, nothing stopped, and every failed item is its page declining the write (`source_changed`, `page_body_segmented`); the result counts them in `declined` by reason, and any other failure or a stop still exits 1. An apply bound to no preview keeps exit 1 for them. The private-labels preview lists pages an earlier apply tried and that did not change after every page not tried yet (`details.window.tried_before`), no longer claims a re-embed for every page (only pages stored under per-chunk synopsis, or with a chunk that has no vector yet, count), and an apply result carries `details.ledger`, `details.ledger_rows_written` and `details.ledger_rows`. A page an earlier apply tried that declines again no longer counts toward `item_failures_systemic`, so a window of carried declines completes; pages not tried yet still trip it. A preview-bound repair apply waits out a `gbrain sources refresh` for up to 10 minutes per step instead of 10 s, and past that ends with `worktree_refreshing` (exit 1) naming the refresh and its running time; rerunning the same apply resumes. Other interactive writes keep 10 s.' },
{ since: '0.60.653.0', id: 'postgres_tls_default', text: 'Postgres connections to a host that is not on this machine now require TLS (sslmode=require) unless the database URL names an sslmode; localhost, 127.0.0.0/8, ::1 and Unix sockets are unchanged. A private address or a Docker service name counts as not on this machine. A database server without TLS now fails to connect with `postgres_tls_required` instead of connecting in plaintext: turn TLS on at the server, or add `sslmode=disable` to the database URL to keep the old plaintext connection on a network you trust. `sslmode=require` encrypts but does not verify the server certificate; `sslmode=verify-full` (with the provider CA in `NODE_EXTRA_CA_CERTS`) verifies it too. `gbrain doctor --only postgres_tls` shows whether this brain\'s connection is encrypted.' },
- { since: 'TBD', id: 'sync_reads_fetch_nothing_gst2331', text: 'A managed sync now makes no object fetches in a partial clone (`git clone --filter`): every Git read it makes runs with Git\'s transports and lazy fetching switched off. A committed file whose blob the partial clone never fetched imports from the working tree when those bytes are the committed blob, and is otherwise held `git_object_missing` with a message that names the partial clone and the `git cat-file -p <blob>` that fetches it; a partial clone with no checkout holds every committed file this way. A blobless clone with a normal checkout syncs its files as before, but an older object it never fetched is read only once it is fetched: when rename detection needs an older blob the partial clone lacks, the sync compares the whole tree instead (the new path imports as a new page and the old page is deleted, so that rename does not keep its page), and folder rules wait as below. A treeless clone (`--filter=tree:0`) that lacks a tree of the synced commit stops the run with `git_object_missing`, naming the partial clone and the `git ls-tree -r -d <commit>` that fetches the trees, and syncs or deletes nothing until then. A source whose commit names a folder-rule file (`.gbrain/access.yml`, `.gbrain/access.approved`) this clone has not fetched, or whose rule history a rebuild cannot read (a first sync replays every earlier version of `access.yml`), reads as nobody to remote members until the objects are fetched, the same as the shallow-checkout rule; its problem names the exact command that fetches them (`git -C <root> cat-file -p <rev>:./<path>` for a file, `git -C <root> log --first-parent -p <rev> -- .gbrain/access.yml` for the history), and the next sync after that command applies the rules and clears the mark with no other step. Before, the sync fetched a missing object from the partial clone\'s remote.' },
+ { since: '0.60.654.0', id: 'sync_reads_fetch_nothing_gst2331', text: 'A managed sync now makes no object fetches in a partial clone (`git clone --filter`): every Git read it makes runs with Git\'s transports and lazy fetching switched off. A committed file whose blob the partial clone never fetched imports from the working tree when those bytes are the committed blob, and is otherwise held `git_object_missing` with a message that names the partial clone and the `git cat-file -p <blob>` that fetches it; a partial clone with no checkout holds every committed file this way. A blobless clone with a normal checkout syncs its files as before, but an older object it never fetched is read only once it is fetched: when rename detection needs an older blob the partial clone lacks, the sync compares the whole tree instead (the new path imports as a new page and the old page is deleted, so that rename does not keep its page), and folder rules wait as below. A treeless clone (`--filter=tree:0`) that lacks a tree of the synced commit stops the run with `git_object_missing`, naming the partial clone and the `git ls-tree -r -d <commit>` that fetches the trees, and syncs or deletes nothing until then. A source whose commit names a folder-rule file (`.gbrain/access.yml`, `.gbrain/access.approved`) this clone has not fetched, or whose rule history a rebuild cannot read (a first sync replays every earlier version of `access.yml`), reads as nobody to remote members until the objects are fetched, the same as the shallow-checkout rule; its problem names the exact command that fetches them (`git -C <root> cat-file -p <rev>:./<path>` for a file, `git -C <root> log --first-parent -p <rev> -- .gbrain/access.yml` for the history), and the next sync after that command applies the rules and clears the mark with no other step. Before, the sync fetched a missing object from the partial clone\'s remote.' },
];
/** The newest disclosed change's release: the notice id moves only when a release adds rows. */
diff --git a/templates/bootstrap/template-repo/README.md b/templates/bootstrap/template-repo/README.md
index 243354d74a..ef5f0686cf 100644
--- a/templates/bootstrap/template-repo/README.md
+++ b/templates/bootstrap/template-repo/README.md
@@ -1,6 +1,6 @@
# gbrain agent workspace — template
-<!-- gbrain-template-stamp: 0.60.653.0 -->
+<!-- gbrain-template-stamp: 0.60.654.0 -->
This repository is the **"Use this template"** distribution artifact for a
[gbrain](https://github.com/garrytan/gbrain) personal-agent workspace — the same