Files
hermes-agent/tests/agent
Zheqing Zeng 9b003f201f fix(curator): seed shared read-marks store in the LLM consolidation fork
The read-before-write guard requires a skill_view mark from the SAME review
run before any skill_manage write. mark_background_review_skill_read
auto-creates a store when the ContextVar is unset, but tool workers run on
copied contexts, so marks recorded in one worker stayed invisible to the
others: every patch was refused with "current SKILL.md content has not been
loaded in this review turn" even after fresh full reads, and the
consolidation pass burned its iterations retrying a dead-end write.

The background-review fork already seeds a shared store before
run_conversation (agent/background_review.py); do the same in the curator
fork so every copied worker context shares one store.
2026-09-15 19:01:11 -07:00
..
2026-08-28 08:28:21 -04:00