Skip to content

Garry's Opinionated OpenClaw/Hermes Agent Brain

TypeScript

Release 0.60.694.0

garrytan4a8bbab54bd3
diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
index 062c2d7636..40d1b49537 100644
--- a/.claude-plugin/plugin.json
+++ b/.claude-plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "gbrain",
- "version": "0.60.693.0",
+ "version": "0.60.694.0",
"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 0e2415188e..09e9288447 100644
--- a/.codex-plugin/plugin.json
+++ b/.codex-plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "gbrain",
- "version": "0.60.693.0",
+ "version": "0.60.694.0",
"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 5e74deae6e..9515ad8063 100644
--- a/BOOTSTRAP_FOR_AGENTS.md
+++ b/BOOTSTRAP_FOR_AGENTS.md
@@ -1,4 +1,4 @@
-<!-- gbrain-runbook-stamp: 0.60.693.0 -->
+<!-- gbrain-runbook-stamp: 0.60.694.0 -->
<!-- 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 43e759fb0f..082f09405b 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]
+## [0.60.694.0] - 2026-11-12
**Labels you set on an agent's page now hold, and an agent can no longer take you out of a page's readers.** When you made an agent-written page private with `gbrain repair visibility` (or set its readers with `--readers`), the page kept its agent tier, so a later agent write at that tier could drop the label again with nothing held. Your label repairs now raise the page's label guard to your tier, so that write is held the same way as one over a page you wrote: it publishes with your labels kept and waits for you in `gbrain trust review`. Separately, a local write below your tier whose `readable_by` would leave you, the brain owner, out of a page you read now keeps you in the list (the rest of the narrowing still applies), and its `lower_page` item records the readers it asked for, which `gbrain trust confirm tp<id>` applies. Confirming such an item on a page whose own tier is an agent's changes only its labels and leaves the page at the agent's tier, so saying yes to a label change never vouches for the body; on a page of yours, confirm still endorses the edit at your tier. Your own readers changes, synced edits, agent narrowing that keeps you, and brains with the owner opt-in to read restricted pages are unaffected. The guard lives in a new database table and is set only by label repairs run after the upgrade, so labels you set earlier, and a managed Git brain rebuilt from a clone, start unguarded: running `gbrain repair visibility --slug <page>` or `--readers <list>` again on a page that already has those labels raises the guard without changing the labels or writing the page (GST-2521).
diff --git a/VERSION b/VERSION
index 03a627bb20..fbb897b994 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-0.60.693.0
+0.60.694.0
diff --git a/openclaw.plugin.json b/openclaw.plugin.json
index 102ea0548d..5b7881e517 100644
--- a/openclaw.plugin.json
+++ b/openclaw.plugin.json
@@ -1,7 +1,7 @@
{
"id": "gbrain-context-engine",
"name": "gbrain",
- "version": "0.60.693.0",
+ "version": "0.60.694.0",
"description": "Personal knowledge brain with Postgres + pgvector hybrid search",
"family": "bundle-plugin",
"kind": "context-engine",
diff --git a/package.json b/package.json
index cca1c8633c..5cc00e2953 100644
--- a/package.json
+++ b/package.json
@@ -255,7 +255,7 @@
"bun": ">=1.4.4"
},
"license": "MIT",
- "version": "0.60.693.0",
+ "version": "0.60.694.0",
"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 96383efdd8..327c92869c 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": "0.60.693.0",
+ "version": "0.60.694.0",
"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 19399146d8..2d9009cb7b 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": "0.60.693.0",
+ "version": "0.60.694.0",
"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 0cc3b4da63..316854871d 100644
--- a/plugin-variants/gbrain-coding/README.md
+++ b/plugin-variants/gbrain-coding/README.md
@@ -1,4 +1,4 @@
-<!-- gbrain-plugin-tree-stamp: 0.60.693.0 -->
+<!-- gbrain-plugin-tree-stamp: 0.60.694.0 -->
# 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 5ebe912bca..50ccbc2450 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": "0.60.693.0",
+ "version": "0.60.694.0",
"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 76b4b86bbc..d3d7eeb94a 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": "0.60.693.0",
+ "version": "0.60.694.0",
"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 d431f315fe..3d62f242db 100644
--- a/plugin-variants/gbrain-daily/README.md
+++ b/plugin-variants/gbrain-daily/README.md
@@ -1,4 +1,4 @@
-<!-- gbrain-plugin-tree-stamp: 0.60.693.0 -->
+<!-- gbrain-plugin-tree-stamp: 0.60.694.0 -->
# 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 f727ca2e82..e86cf03cfe 100644
--- a/plugin/README.md
+++ b/plugin/README.md
@@ -1,4 +1,4 @@
-<!-- gbrain-plugin-tree-stamp: 0.60.693.0 -->
+<!-- gbrain-plugin-tree-stamp: 0.60.694.0 -->
# 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 e735b0e76b..243c45a0de 100644
--- a/src/core/behavior-change-notice.ts
+++ b/src/core/behavior-change-notice.ts
@@ -1537,7 +1537,7 @@ export const BEHAVIOR_CHANGES: ReadonlyArray<{ since: string; text: ChangeText;
{ since: '0.60.676.0', id: 'write_capacity_low_saved_gst2107', text: 'The `write_capacity_low` notice a write receipt carries now opens with "This write was saved" and its fix is the read-only `gbrain doctor --only persistence_capacity --json` (actor agent) instead of a `gbrain config set` cap raise for the user, so an agent reading the end of a successful write no longer reports it as refused. The one-more-year value doctor, the notice snapshot and `/metrics` recommend now uses the 7-day mean rate, so one bulk day is no longer projected for a year; days-to-exhaustion still uses the larger of the mean and the last 24 hours. A `write_quota_exhausted`, `write_quota_insufficient` or background-pause refusal names the same value doctor does instead of sizing the year from the latest 1,000 admissions.' },
{ since: '0.60.676.0', id: 'ingest_backfill_409_recovery_gst2112', text: 'A `revision_backfill_pending` refusal (a write to a page the revision backfill has not reached, including the 409 a webhook capture to such a page gets from `POST /ingest`) now names the command that resumes the backfill, `gbrain apply-migrations --force-schema` on the brain host, instead of `gbrain apply-migrations --yes`, which does not resume it once the schema is current. A capture answered 409 stores and queues nothing, so its sender sends it again after the backfill; an `ingest_capture` job already queued for such a page goes straight to dead and is re-run with `gbrain jobs retry <id>`.' },
{ since: '0.60.683.0', id: 'label_only_operator_repairs_gst2468', text: '`gbrain repair visibility` and `gbrain repair private-labels` now write a page through a label-only door: the page keeps its trust tier, files no `lower_page` proposal, and its file changes only on the label lines (other keys, their order and the body are kept). Before, `repair visibility` wrote through `put_page`, which lowered the page to agent_written and re-rendered its frontmatter. On a brain without managed persistence, `repair visibility` edits the label lines of a page\'s file in its source checkout and imports it with the tier kept (`private-labels` still holds such a page as `file_backed`). New `gbrain repair visibility --slug <page>` makes named pages private, preview first. New read-only `gbrain trust backfill --label-lowerings` lists `lower_page` proposals as label-only or content by proposer. A plain `put_page` still lowers as an agent edit.' },
- { since: 'TBD', id: 'fence_fact_widening_held_gst2511', text: 'A page write by a writer less trusted than a private `## Facts` row that makes it world (the same claim at its row number or any other, or a different claim at its row number) no longer stores a world copy before the owner decides. The writer\'s row is stored private and contested, the trusted row stays private, and the `supersede_fact` proposal records the widening: `gbrain trust confirm tp<id>` applies it while the page\'s fence row still asks for world (the claim becomes world, confirmed), `gbrain trust drop tp<id>` keeps it private, and later writes of the same fence by such a writer, and the background facts reconcile, keep the contested row private. The `remember` route is not covered. Before, the writer\'s world row was live at once, so remote recall and other fact reads returned the private claim while the proposal waited, and accepting the proposal failed as stale (`scope_changed`). The page text keeps the visibility the writer wrote.' },
+ { since: '0.60.694.0', id: 'fence_fact_widening_held_gst2511', text: 'A page write by a writer less trusted than a private `## Facts` row that makes it world (the same claim at its row number or any other, or a different claim at its row number) no longer stores a world copy before the owner decides. The writer\'s row is stored private and contested, the trusted row stays private, and the `supersede_fact` proposal records the widening: `gbrain trust confirm tp<id>` applies it while the page\'s fence row still asks for world (the claim becomes world, confirmed), `gbrain trust drop tp<id>` keeps it private, and later writes of the same fence by such a writer, and the background facts reconcile, keep the contested row private. The `remember` route is not covered. Before, the writer\'s world row was live at once, so remote recall and other fact reads returned the private claim while the proposal waited, and accepting the proposal failed as stale (`scope_changed`). The page text keeps the visibility the writer wrote.' },
{ since: '0.60.678.0', id: 'unmanaged_push_history_scan_8902', text: 'Four pushes from a checkout that is not a managed worktree now scan every local commit they publish for secrets, not only what they just wrote: the access-policy commit (`gbrain access rule` and the other policy writers), the durability-scaffolding commit of `gbrain sources harden`, `gbrain sources push`, and the first push of `gbrain bootstrap repo` (the whole history, since the remote has no such branch yet). A credential that a commit made with plain `git commit` added, even one a later commit removed, or one in a commit message, now refuses `publish_secret_found` naming the file, line, rule and commit (never the value), and nothing is pushed; history the scan cannot read in full refuses `publish_scan_unreadable`. The local commits stay where they are. `gbrain sources push` now pushes the exact commit it scanned, leased on the remote tip it read, and an allowlist (`.gbrain-scan-allow`) edit it commits itself still publishes; one a script committed is left for the user to review and push. Remove the value from the unpublished commits, or allowlist a false positive by fingerprint, then rerun.' },
{ since: '0.60.680.0', id: 'privacy_label_ignored_gst2462', text: 'A page write (put_page, `gbrain import`, `gbrain sync`) that stores a page with an `access` or `confidentiality` value gbrain does not read as private (for example `access: personal`) and no `visibility` now carries one `privacy_label_ignored` safety notice: it names the key and value (a bulk run counts pages by value and names no page), says remote callers read the page like an unlabelled one and, on a source with a git checkout, that the label does not keep it out of git, and asks before adding `visibility: private`. `gbrain doctor --only privacy_label_ignored` counts such pages by value (a warning when the value plainly means private). Who can read a page is unchanged: the recognized values and `visibility.honor_aliases` are as before.' },
{ since: '0.60.680.0', id: 'access_page_rules_gst2462', text: 'A folder rule can now name one exact page: `gbrain access rule add --slug <page> --readers <list>` (`slug:` in `.gbrain/access.yml`) restricts that page alone, never a folder of the same name, without writing the page, so a page at the source root or one whose file left git can be narrowed. A write refused because the page\'s file is missing now names this route beside the ghost-page repair. Upgrade every gbrain host that shares the brain before adding a page rule. Reads are decided in the database, so an older host still keeps the page restricted, but it refuses its own `gbrain access rule` commands and, on a git-backed source, stops syncing that source with `stored rulebook holds a malformed rule` until it is upgraded.' },
@@ -1558,8 +1558,8 @@ export const BEHAVIOR_CHANGES: ReadonlyArray<{ since: string; text: ChangeText;
{ since: '0.60.693.0', id: 'owner_forget_private_gst2346', text: 'A credential bound to the brain owner (`gbrain access owner set`), or a stdio server started with `--stdio-member <owner>`, speaking for itself, now withdraws with `forget` or `forget_fact` a private fact it reads on a page its credential can write (one the brain host saved with `visibility: "private"`), where it used to be told only the brain host could. A fact on a `visibility: private` page, on a page whose readers leave the owner out or on another member\'s page is still withdrawn on the brain host, and a fact the owner confirmed or curated still files a `forget_requires_owner` proposal. Member credentials, attested QM calls (`x-qm-actor`), audiences (`X-Gbrain-On-Behalf-Of`), subagent jobs, slug-fenced clients and unbound connections are unchanged.' },
{ since: '0.60.693.0', id: 'owner_forget_readers_page_gst2346', text: 'The brain owner\'s own credential speaking for itself now withdraws with `forget` or `forget_fact` a fact, private or shared, on a page whose `readable_by` names the owner, where it answered `not_found`, when that credential may also write the page and reads the fact\'s entity page the same way. The owner opt-in `access.owner_reads_restricted` does not extend to `forget`. Every other caller is unchanged.' },
{ since: '0.60.693.0', id: 'member_save_withdrawn_scope_gst2346', text: 'A remote `remember` onto a member\'s own page (`memory/members/<id>`) is refused `fact_withdrawn` only when that member could read what was withdrawn: a fact on its own page, its own copy withdrawn by the brain host, or for the brain owner a fact it reads. A claim withdrawn by the brain host or the owner that the member never read no longer refuses its save: the fact saves as the member\'s own active row with the same reply as a new claim. A schema migration makes the database insert guards mark a row on a member page only by that page\'s own withdrawals; a withdrawal still expires matching rows on member pages when it is made, and strikes them in the page\'s file, so an import of a member page\'s file no longer marks a row withdrawn by a withdrawal of another subject. The same holds for each item of a `remember` batch (`items`), a replay with the same `request_id`, a `replaces` and the write receipt (`get_write_request`). Trusted local saves keep the check they had.' },
- { since: 'TBD', id: 'owner_labels_guarded_gst2521', text: 'Labels the owner sets with `gbrain repair visibility` (or its `--readers` setter, or `gbrain repair private-labels`) now raise the page\'s label guard to operator_curated, so a later local agent write at the page\'s own tier that drops or widens them is held like a write over an owner page, with a `lower_page` item. A local write below operator_curated whose `readable_by` would leave the brain owner out of a page the owner reads now publishes with the owner kept in the readers (the rest of the narrowing applies), and its item records the requested readers. Accepting such an item (`gbrain trust confirm tp<id>`) on a page whose own tier is an agent\'s writes only the labels and keeps the agent\'s tier; on an owner page it still endorses the edit at the owner\'s tier. The guard is stored in the database (`page_label_guards`) and set only by label repairs run after the upgrade, so labels set earlier, and a managed Git brain rebuilt from a clone, start unguarded; re-running `gbrain repair visibility --slug` or `--readers` on a page that already has those labels raises the guard without changing them. The owner\'s own label writes, synced owner edits, agent narrowing that keeps the owner, and brains with `access.owner_reads_restricted` on are unchanged.' },
- { since: 'TBD', id: 'page_label_widening_held_gst2518', text: 'A local agent write (`put_page`, `capture`, `edit_page`, `append_page`, `revert_version`, `restore_page`) less trusted than a page that drops or widens its `visibility`, `access`, `confidentiality` or `readable_by` now publishes with the page\'s earlier labels kept, in the database and in the committed file, and its receipt lists them under `privacy_labels_kept`; so does a maintenance job\'s derived page publication, and a page whose tier is still `unknown` counts as the owner\'s. A soft delete no longer lowers the page\'s tier. Before, the page became readable to remote callers and other members at once, and only a `lower_page` item waited for the owner. That item now records the requested labels: `gbrain trust confirm tp<id>` applies them if the page has not changed since, `gbrain trust drop tp<id>` keeps the earlier ones, and undoing a confirm restores them while the page is unchanged since. Narrowing writes, label-neutral writes, writers at or above the page\'s tier, synced owner edits and `gbrain repair visibility` are unchanged.' },
+ { since: '0.60.694.0', id: 'owner_labels_guarded_gst2521', text: 'Labels the owner sets with `gbrain repair visibility` (or its `--readers` setter, or `gbrain repair private-labels`) now raise the page\'s label guard to operator_curated, so a later local agent write at the page\'s own tier that drops or widens them is held like a write over an owner page, with a `lower_page` item. A local write below operator_curated whose `readable_by` would leave the brain owner out of a page the owner reads now publishes with the owner kept in the readers (the rest of the narrowing applies), and its item records the requested readers. Accepting such an item (`gbrain trust confirm tp<id>`) on a page whose own tier is an agent\'s writes only the labels and keeps the agent\'s tier; on an owner page it still endorses the edit at the owner\'s tier. The guard is stored in the database (`page_label_guards`) and set only by label repairs run after the upgrade, so labels set earlier, and a managed Git brain rebuilt from a clone, start unguarded; re-running `gbrain repair visibility --slug` or `--readers` on a page that already has those labels raises the guard without changing them. The owner\'s own label writes, synced owner edits, agent narrowing that keeps the owner, and brains with `access.owner_reads_restricted` on are unchanged.' },
+ { since: '0.60.694.0', id: 'page_label_widening_held_gst2518', text: 'A local agent write (`put_page`, `capture`, `edit_page`, `append_page`, `revert_version`, `restore_page`) less trusted than a page that drops or widens its `visibility`, `access`, `confidentiality` or `readable_by` now publishes with the page\'s earlier labels kept, in the database and in the committed file, and its receipt lists them under `privacy_labels_kept`; so does a maintenance job\'s derived page publication, and a page whose tier is still `unknown` counts as the owner\'s. A soft delete no longer lowers the page\'s tier. Before, the page became readable to remote callers and other members at once, and only a `lower_page` item waited for the owner. That item now records the requested labels: `gbrain trust confirm tp<id>` applies them if the page has not changed since, `gbrain trust drop tp<id>` keeps the earlier ones, and undoing a confirm restores them while the page is unchanged since. Narrowing writes, label-neutral writes, writers at or above the page\'s tier, synced owner edits and `gbrain repair visibility` are unchanged.' },
];
/** 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 334b46c52b..3060350413 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: 0.60.693.0 -->
+<!-- gbrain-template-stamp: 0.60.694.0 -->
This repository is the **"Use this template"** distribution artifact for a
[gbrain](https://github.com/garrytan/gbrain) personal-agent workspace — the same