Rongsong Shen 164c9a9d2e docs(ha-entity-snapshots): record hybrid execution-mode decision for remaining tasks ... Split remaining tasks by risk after a mid-session spend-limit hit: small/ isolated tasks (4.2, 4.3, 7.1, 8.1) execute directly with self-review; load_snapshot restore (5.1/5.2, the exact function that caused task 2.2's rejection) and the production wiring (6.1) keep the full implementer + independent-reviewer subagent cycle, since that's where adversarial review already proved its worth and where the remaining risk is concentrated. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JDYFbrgyDHbvNYcxApKhrX		2026-07-01 07:30:15 +00:00
..
settings	finalize configuration replication	2026-06-09 16:40:13 +08:00
specs	docs(ha-entity-snapshots): record hybrid execution-mode decision for remaining tasks	2026-07-01 07:30:15 +00:00
steering	docs(steering): sync HA protocol with ha-term-safety — per-entry term, (term,lsn) reconcile, commit-source ownership, bug-828 truncate rule	2026-06-23 04:48:06 +00:00