Skip to content

Garry's Opinionated OpenClaw/Hermes Agent Brain

TypeScript

docs: name the reads #8367 quotes and point the rest to #8377

garrytan80cef5c3622a
diff --git a/CHANGELOG.md b/CHANGELOG.md
index b3d40e7849..65abea3e07 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -14,7 +14,7 @@ identifiers and attribution are available in the pre-removal Git revision
**Agents connected over MCP now see agent-written, ingested and unverified-origin text quoted as source material on search, recall, page, chunk, timeline, version and write-receipt reads, and conversation tool calls come back summarized on the reads that still returned them verbatim.**
-Before, the quote fence (#8066) covered chat page types and conversation-derived facts only. A note an agent wrote over MCP, a fact saved with `remember`, a chat message saved into a member source, and every placement read through `get_timeline`, `search_exact`, `get_chunks`, `think`'s extractive answer or a write receipt reached a remote reader as plain text, and a conversation page's tool-call JSON came back verbatim through `get_page`, `fetch`, `search_exact`, `get_chunks` and `think`. Now any text whose stored trust tier is below "your notes" (`operator_curated`) is quoted for a remote reader: written by an agent, tool data, external, or unverified origin.
+Before, the quote fence (#8066) covered chat page types and conversation-derived facts only. A note an agent wrote over MCP, a fact saved with `remember`, a chat message saved into a member source, and every placement read through `get_timeline`, `search_exact`, `get_chunks`, `think`'s extractive answer or a write receipt reached a remote reader as plain text, and a conversation page's tool-call JSON came back verbatim through `get_page`, `fetch`, `search_exact`, `get_chunks` and `think`. Now any text whose stored trust tier is below "your notes" (`operator_curated`) is quoted for a remote reader on those reads: written by an agent, tool data, external, or unverified origin. The `chronicle_*` reads, `takes_search` and `takes_list`, and a quoted page's title and frontmatter still return stored text unquoted; #8377 tracks them.
**Remote MCP readers now see unverified-origin text quoted until you run trust backfill.** A note saved before gbrain tracked trust has no recorded origin, so it reads as unverified and is quoted for agents connected over MCP. Claim the sources that hold your own notes with `gbrain trust claim-sources` and run `gbrain trust backfill`; `gbrain doctor` (`trust_tiers`, `trust_sources_unclaimed`) names how many pages are affected and verifies the fix. Local reads are unchanged, nothing stored changes, and no trust tier is raised or lowered.
@@ -22,12 +22,13 @@ Before, the quote fence (#8066) covered chat page types and conversation-derived
- `src/core/search/transcript-quote.ts`: `quotesTier` / `quotesStored` (a missing tier reads as `unknown`, so it fails closed); `quoteFacts` reads each fact's stored tier from the database for a remote reader.
- Search, query, recall, assemble_evidence, saved facts, context_pack, delta, `_meta.brain_hot_memory` (its cache key carries the quoting), `get_page` (body, timeline, windows), `fetch`, `get_timeline`, `get_chunks`, `search_exact`, `think`'s extractive fallback, `get_versions` and `known_as_of` reads (by the version's tier snapshot; a version without one reads as unverified) and `list_write_requests` / `get_write_request` outcome text quote by tier for remote readers.
-- Tool-call blocks in conversation pages are summarized on `get_page`'s reading shape and `view: read` windows, `fetch`, `search_exact`, `get_chunks` and `think`; `include_content`, `view: markdown` and gbrain's thin client keep the stored bytes inside the fence. A remote `put_page` that would write a summarized tool call back over a conversation page refuses with `invalid_params` and stores nothing.
+- Tool-call blocks in conversation pages are summarized on `get_page`'s reading shape and `view: read` windows, `fetch`, `search_exact`, `get_chunks` and `think`; `include_content`, `view: markdown` and gbrain's thin client keep the stored bytes inside the fence. A remote `put_page` whose content keeps a tool call's summary but fewer of that call than the stored conversation page holds refuses with `invalid_params` and stores nothing.
- A remote `put_page` round trip of any quoted page stores the body, never the fence; a forged fence in stored text stays inside the quote.
- Rendered context_pack/delta lines put a quoted fact's label on the marker line and close its fence on its own line.
- `gbrain doctor`: `trust_tiers` and `trust_sources_unclaimed` say remote readers see unverified pages quoted and name the claim and backfill commands.
- BrainBench poisoning: a payload inside a closed quote fence is judged by its fence's marker line, where its label is rendered.
- Tests: `test/search-transcript-quote-tiers.test.ts` (every placement and read surface, red on master), `test/search-transcript-quote-legacy-claim.test.ts` (legacy note quoted, raw again after claim and backfill), both on PGLite and Postgres; existing fixtures that stand for the owner's own notes now write at the owner tier (`test/helpers/owner-tier.ts`).
+
## [0.60.534.0] - 2026-11-01
**Merge train S: five sync, refresh and maintenance fixes land in one release.** Page writes create a missing source folder and name a missing checkout (#8106). A diverged managed checkout can publish itself on opt-in, and every refresh fetch is logged (#8102). Sync-lane wave 2 repairs quoted fence markers, releases agreeing file-drift holds, syncs plain directories and retires former-binding effects (#8077). The `synthesize` phase survives a local writer replace (#8111). A door commit during a refresh is waited out instead of failing the refresh as `refresh_dirty` (#8117).
diff --git a/src/core/behavior-change-notice.ts b/src/core/behavior-change-notice.ts
index d13d17778b..3d59359501 100644
--- a/src/core/behavior-change-notice.ts
+++ b/src/core/behavior-change-notice.ts
@@ -1391,7 +1391,7 @@ export const BEHAVIOR_CHANGES: ReadonlyArray<{ since: string; text: ChangeText;
{ since: '0.60.516.0', id: 'settle_effects_retire_7985', text: '`gbrain sources writer settle-effects --retire` settles a parked Git effect of a former binding that nothing current owes, on evidence: its source was archived, removed or re-created, or each target\'s page moved to a later revision, was deleted or lost its slug to another page. It is previewed, bound to its plan hash, applied only after the user agrees, never retried, and `--unsettle` reverses it. The parked group for a replaced source now names that preview, and plain settle\'s `source_replaced` refusal points to it.' },
{ since: '0.60.516.0', id: 'managed_marker_own_directory_7988', text: 'Managed persistence now marks a root that no Git checkout tracks (a connector clone or plain directory under a dotfiles home) in its own directory instead of in the enclosing repository, so legacy writers elsewhere in that repository are no longer refused, and the autopilot HEAD probe no longer reads the enclosing repository\'s HEAD for it. A marker an older release already wrote there stays until `gbrain sources writer deactivate` removes it (preview with `--dry-run --json`; activate again afterwards), and a write it refuses now says so.' },
// GST-687 (GBRA-269) quote fence by trust tier. since stamped at the merge slot.
- { since: '0.60.535.0', id: 'remote_quotes_unverified_text_gst687', text: 'Agents connected over MCP now get text quoted as source material (a line naming its page or fact, then a code fence) wherever its stored trust tier is below "your notes": text written by an agent, tool data, external text and text of unverified origin. This covers search, query, recall, assemble_evidence, get_page, fetch, get_timeline, get_chunks, search_exact, think\'s extractive answer, get_versions and known_as_of reads, context_pack, delta, hot memory and write receipts. A note saved before gbrain tracked trust reads as unverified origin, so it is quoted until the owner claims its source (`gbrain trust claim-sources`) or `gbrain trust backfill` classifies it; `gbrain doctor` names how many pages that is. Conversation pages also come back with tool-call blocks summarized on get_page, fetch, search_exact, get_chunks and think; `get_page` with `include_content` and the markdown view keep the stored text. Local reads, stored text and trust tiers are unchanged.' },
+ { since: '0.60.535.0', id: 'remote_quotes_unverified_text_gst687', text: 'Agents connected over MCP now get text quoted as source material (a line naming its page or fact, then a code fence) when its stored trust tier is below "your notes": text written by an agent, tool data, external text and text of unverified origin. This covers search, query, recall, assemble_evidence, get_page, fetch, get_timeline, get_chunks, search_exact, think\'s extractive answer, get_versions and known_as_of reads, context_pack, delta, hot memory and write receipts; chronicle, takes and page title reads are not quoted yet. A note saved before gbrain tracked trust reads as unverified origin, so it is quoted until the owner claims its source (`gbrain trust claim-sources`) or `gbrain trust backfill` classifies it; `gbrain doctor` names how many pages that is. Conversation pages also come back with tool-call blocks summarized on get_page, fetch, search_exact, get_chunks and think; `get_page` with `include_content` and the markdown view keep the stored text. Local reads, stored text and trust tiers are unchanged.' },
];
/** The newest disclosed change's release: the notice id moves only when a release adds rows. */