Garry's Opinionated OpenClaw/Hermes Agent Brain
TypeScript
Merge remote-tracking branch 'origin/gbra247-holds' into gbra247-sync-wave2
garrytan00328b82bdd1
diff --cc src/core/behavior-change-notice.tsindex 578e61c529,adf285776c..892794afd6--- a/src/core/behavior-change-notice.ts+++ b/src/core/behavior-change-notice.ts@@@ -1372,7 -1372,12 +1372,13 @@@ export const BEHAVIOR_CHANGES: Readonly{ since: '0.60.514.0', id: 'storage_ignored_dirs_8015', text: 'When gbrain.yml lists a deprecated `supabase_only` next to canonical keys (which ignores it), a managed sync now holds only the missing-file pages under the ignored directories `db_only` does not already cover, and deletes other missing-file pages as usual; it used to hold every missing-file page of the source. `gbrain storage status` now names those directories, and the deprecation warning no longer points to a `gbrain doctor --fix` rename that does not exist. A `db_only` or `supabase_only` line whose inline value the parser refuses (a missing comma, a nested list, a bare scalar) now counts as unresolved even when another key resolves, so missing-file pages are held rather than deleted.' },{ since: '0.60.514.0', id: 'company_db_only_keep_8014', text: 'A company-brain source now keeps a live page under a declared `storage.db_only` directory when its file is not in the approved manifest, and keeps every such page while its gbrain.yml storage section is invalid, as other managed sources do; it used to delete them. The decision reads gbrain.yml at the approved commit, never the working tree.' },{ since: '0.60.514.0', id: 'redaction_marker_not_credential_7997', text: 'The transcript `labeled_credential` detector no longer reads an importer redaction marker (`login **<REDACTED:user-pattern>**`) as a typed user/password pair, so a correctly redacted page clears `gbrain transcripts audit-secrets`; a password written beside a marker is still found. The audit detector version moves to 3, so `gbrain doctor` asks for a fresh audit once.' },+ { since: '0.60.516.0', id: 'quoted_fence_marker_8059', text: 'A page that quotes a facts or takes fence marker in prose (text after the marker on its line, or a blockquote line) is now held or refused with the fence reason `quoted_marker` instead of `repeated_marker` or `unclosed_ambiguous_tail`, and `gbrain repair fences`, `gbrain repair content`, `gbrain sync unblock --apply` and the maintenance run repair it by wrapping each mention in backticks, with a receipt per file; readers count fence lines exactly as before. The edit is kept only when every fence row stays where it was and nothing the privacy boundary hid becomes visible. Existing `invalid_fence` holds are screened once more on the next sync. `forget` now locates the facts fence it rewrites with the parser\'s code-aware search, so a marker quoted in code above the fence no longer moves the rewrite.' },+ // #7199 (re-port of #7228). since is stamped at the merge slot.+ { since: '0.60.516.0', id: 'classic_drift_rescreen_7199', text: 'A `file_drift` hold with side `unknown` that an older gbrain wrote before sync compared a record-less page with its file at the last synced commit is now compared once more, also with the file\'s last three earlier committed versions, and imports when the page equals one of them; otherwise it stays held and is not re-screened again. Such a hold now names what the page was compared with, and `gbrain sync status` lists it under its own verdict (`file_drift_unknown`, needs a person). A managed sync that holds files a person must decide now reports `reason: held_needs_human` with `held_needs_human: <count>` (JSON) and prints `Synced; N file(s) held for a person (gbrain sync status --source <id>).`; the source still syncs and its status stays `synced`.' },+ // #7931 parts 2 and 3. since is stamped at the merge slot.+ { since: '0.60.516.0', id: 'file_drift_agrees_7931', text: 'A managed sync no longer holds a file as `file_drift` when its page agrees with it as `gbrain repair file-drift` reads them (they differ only in how the file writes the page, such as YAML quoting, or in a reserved key an older import kept in the database copy): the file imports. A held file someone asks to re-screen (`gbrain sources retry-held`, or the apply of a `release_hold` preview) whose page has no import record is now screened again instead of staying held, so an agreeing page is released. A `gbrain repair file-drift --apply` refused before it published no longer makes the apply after a fresh preview with the same `--expect` answer `idempotency_conflict`.' },+ { since: '0.60.516.0', id: 'file_drift_slug_release_7950', text: '`gbrain repair file-drift --slug <s>` now lists a held page whose file agrees with it as `release_hold` (it was `no_drift`, and its printed apply always refused `preview_changed`); the apply releases only the hold the preview observed and answers `changed_since_preview` when that hold was replaced. A preview that finds nothing to apply prints an apply command that now applies nothing instead of refusing `preview_changed`.' },+ { since: '0.60.516.0', id: 'file_drift_followups_7974', text: 'A page a read-only mirror stored database-only is compared with the file at its slug path the way `gbrain sources reconcile` reads it: one that agrees is listed `release_hold` instead of drifted, and one whose slug path has several spellings is listed unknown (`slug_path_ambiguous`) instead of aborting `gbrain repair file-drift` and the conflict audit. A held file whose page agrees with a different file than the held one is listed unknown instead of `release_hold`. The slug path of a page with no recorded file follows the source\'s slug-root mode and never resolves through a symlink.' },];/** The newest disclosed change's release: the notice id moves only when a release adds rows. */