Skip to content

Garry's Opinionated OpenClaw/Hermes Agent Brain

TypeScript

docs: maintain skill names per-source synthesize routing and the held-session fix (#7805)

garrytan3746665ffaa4
diff --git a/skills/maintain/SKILL.md b/skills/maintain/SKILL.md
index 31effe2cc7..fd0ffc7d77 100644
--- a/skills/maintain/SKILL.md
+++ b/skills/maintain/SKILL.md
@@ -166,8 +166,10 @@ or a third of the remaining time. Pause both with
The two new phases consolidate yesterday's conversations into long-term memory:
-**Synthesize phase (two-stage cascade):** reads transcripts from
-`dream.synthesize.session_corpus_dir`, then triages before it spends: a cheap
+**Synthesize phase (two-stage cascade):** reads the cycle source's transcripts from
+`dream.synthesize.session_corpus_dir` (another source's sessions wait for their own
+`gbrain dream --source <id> --phase synthesize`; unresolved or legacy files are held,
+already-extracted ones included, until `gbrain sweep --assign-corpus <source>`), then triages before it spends: a cheap
utility-tier judge (`models.dream.triage`) scores every new file 0–1 for
salience and pre-extracts candidate quotes + entities, cached in
`dream_verdicts` with the judging model + prompt version (bounded per cycle