jared 242ca84744 os-orchestration: WS4 IRL re-audit + Tier 1/2 wording patch ... First production IRL audit (19 transcripts post-2026-07-08, 3 parallel auditors; run artifacts in autoresearch/improve-260710-1057/, gitignored). Solved: model-param discipline, over-delegation. Patched into ORCHESTRATION.md: settled-design mid-session fan-out trigger, never-sleep-poll rule, own eval/benchmark loops named as mechanical, unfamiliar-tree Explore trigger. SendMessage example skipped (no violations; token budget). One-shot patch — WS4 grids contaminated; acceptance = next IRL audit. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01XknQRvihHDpYE47RTmUR4N		2026-07-10 11:24:59 -04:00
..
adr-system	Add os-adr evaluation harnesses (Eval A and Eval B)	2026-07-03 16:44:42 -04:00
graphify	Complete graphify-ollama-setup OpenSpec change	2026-06-05 11:44:40 -04:00
memory-system	os-vault: add SessionStart git pull for multi-machine vault/memsearch freshness	2026-07-10 10:06:55 -04:00
orchestration-audit	os-orchestration: WS4 eval extension — econ axes, E5 batching pair, fable column, pre-registered E2P/E3P criterion redesign	2026-07-08 09:49:44 -04:00
plans	system-prompt profiles B2 + YAGNI tool deny: overlays shipped, −16k/session total	2026-07-08 14:47:51 -04:00
superpowers/specs	Clarify memsearch spec: install-first, audit-defaults, deviate only if needed	2026-06-09 13:38:10 -04:00
USER-GUIDE.md	Document ADR-015: memsearch episodic sync and resolved commingling design	2026-06-09 15:11:12 -04:00
implementation-status.md	os-orchestration: WS4 IRL re-audit + Tier 1/2 wording patch	2026-07-10 11:24:59 -04:00
issue-workflow.md	Document Forgejo/tea issue workflow	2026-06-30 16:25:29 -04:00