Skip to content

Garry's Opinionated OpenClaw/Hermes Agent Brain

TypeScript

docs: CHANGELOG voice fixes and TODOS follow-ups for the memory train

garrytan732f48800294
diff --git a/CHANGELOG.md b/CHANGELOG.md
index d03b8dc657..14dcb06ecb 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -18,7 +18,7 @@ This release folds seven approved memory PRs into one: #7616, #7791, #7797, #780
### Forget writes the page files first (#7616)
-Git stays the parent: a withdrawal is now a page write, published to Git before the database changes.
+Git stays the parent. A withdrawal is now a page write, published to Git before the database changes.
| Situation | Before | Now |
|---|---|---|
@@ -27,7 +27,7 @@ Git stays the parent: a withdrawal is now a page write, published to Git before
| Remembering that claim again with an entity | two copies | the entity row is written and the unattributed row struck in the same publication |
| A member forgets a fact on their own member page | withdrawn for that page | unchanged: the withdrawal stays on that page, and other members' copies stay active |
-A forget now waits for the source's writer the way `remember` does: with the writer unavailable it returns the pending-write receipt, and the fact is still recalled until it publishes. With `sync.write_through` off, from a sandboxed subagent, or on a source with no canonical owner, a forget of a claim a page file carries is refused (`sync_write_through_off`, `subagent_sandbox`, `unbound_source`) instead of withdrawing it in the database only; a claim only database-only pages carry is still withdrawn. Migration v287 adds the multi-page recovery record (one record restores every file of an interrupted publication); it rewrites no data.
+A forget now waits for the source's writer the way `remember` does. With the writer unavailable it returns the pending-write receipt, and the fact is still recalled until it publishes. With `sync.write_through` off, from a sandboxed subagent, or on a source with no canonical owner, a forget of a claim a page file carries is refused (`sync_write_through_off`, `subagent_sandbox`, `unbound_source`) instead of withdrawing it in the database only; a claim only database-only pages carry is still withdrawn. Migration v287 adds the multi-page recovery record (one record restores every file of an interrupted publication); it rewrites no data.
### Review lists and review decisions through the page door (#7791, #7797)
@@ -95,7 +95,7 @@ A page can now say when its text takes effect, with `valid_from` and `valid_unti
- The answer is the edition with the latest `valid_from` on or before the date, picked across the current page and every version gbrain kept. Its `valid_time` block says whether that edition was `in_force`, `not_in_force`, `not_yet_in_force` or `before_recorded_history`, and whether gbrain held enough history to be sure. Only an `in_force` answer returns the text at the top level, so an agent that skips the status cannot quote expired text as current.
- When history is missing (pruned versions, a sync that imported several commits at once, a page that came from a file) or the dates look ambiguous (a corrected date and a renewal leave the same trace), the answer says `uncertain: true`, why, and how to recover: the file's `git log`, or asking the user for a backup. It never guesses.
- Works the same on a brain with no Git repository, the default keyless install.
-- Over MCP, an `as_of` read follows the plain read's rules: a quarantined page's body is omitted, and an edition's `introduced_because` is shown only when the edition it replaced is one the caller may read.
+- Over MCP, an `as_of` read follows the plain read's rules. A quarantined page's body is omitted, and an edition's `introduced_because` is shown only when the edition it replaced is one the caller may read.
- `gbrain get --as-of` exits 15 when no edition was in force, and 16 (`host_upgrade_required`) when the brain host is too old to answer by date, printing nothing historical.
- Writes say when they keep or change an edition's date (`valid_time_correction`, `valid_time_date_only`, `valid_from_unparsed`), and `get_versions` rows carry each version's `valid_from` and `valid_until`.
- Behavior change: a plain `get_page` of a page whose own `valid_from` is in the future, or whose `valid_until` has passed, now also carries a `valid_time` status. Pages without those dates read exactly as before.
diff --git a/TODOS.md b/TODOS.md
index 8ba66936e9..a1b70418dd 100644
--- a/TODOS.md
+++ b/TODOS.md
@@ -1,5 +1,12 @@
# TODOS
+## Memory train follow-ups (filed 2026-11-04, GBRA-286, #8481)
+
+- [ ] **P3 — `extraction_pending`'s local relink argv can carry fenced fact text (#8597).** **What:** running the owner's relink action stores the quote fence as fact text. **Fix:** unquote before building the argv. **Effort:** S. **Priority:** P3.
+- [ ] **P3 — The `sync_write_through_off` forget refusal has no typed fix and reads as transient (#8599).** **What:** an agent may retry instead of asking the user. **Fix:** an `ask_user` fix naming the config change. **Effort:** S. **Priority:** P3.
+- [ ] **P3 — `forget_fact`'s description still says a withdrawal stays in the database when write-through is off (#8600).** **Fix:** reword to the refusal. **Effort:** S. **Priority:** P3.
+- [ ] **P3 — `checkFactAgainstSaved` is exported with no caller after the #7809 removal (#8601).** **Fix:** delete it. **Effort:** S. **Priority:** P3.
+
## SkillOpt E1/B1 follow-ups (filed 2026-11-01, GBRA-274, #8408)
- [ ] **P2 — SkillOpt review follow-ups (#8415).** **What:** held-out deferral on abort and the receipt's pending-champion score; final test eval on an unchanged skill; preflight prices the test eval at 2 runs per task instead of 6; resume does not pin the hook, criteria or cost scope; `--resume` with an unloadable checkpoint starts fresh; the one-shot output-cap check runs after baseline spend; one accepted one-shot step can replace the whole body; cat31 config C changed meaning; stale docs and comments. **Fix:** per item in #8415. **Effort:** S-M each. **Priority:** P2.