📖About

Ninad direction (2026-08-15): make agent chats intelligent - focus on intelligence and presentation; voice (3869) explicitly LATER. Ruling to bind as a DESIGN before any build: (1) ONE chat engine serves every door - Clara/org directory chats, Carol, Leo, Sam; internal vs external is a matter of fences (access policies, subscriptions, stranger identity), never separate brains. (2) The estate fences - spend gate, receipts, access, SST grounding - sit OUTSIDE the runtime and bind whatever runs inside. (3) Where the lane has an agentic runtime (Codex CLI, Claude Code) the turn uses the runtime's OWN loop; the hand-stitched text path stays as the fallback so a subscription change is a lane swap, never a rebuild, and a lane without a loop degrades gracefully and VISIBLY. Design record via Albus's design register; supersedes-per-design where it touches design 255's chat model.

⚖️Decisions

• Elrond's bypass methodology checklist (a reminder, not a gate -- you've got this): 0. File it requested_mode='bypass' (planner-vs-bypass is a deliberate choice). bypass_start REFUSES a non-bypass initiative (CAROL-INI-1846), and the dispatcher only skips the bypass lane when the mode says bypass -- a 'planner' mistag lets Merlin's pipeline grab the placeholder step and block your finished work. 1. Filed as planned status -- let the bypass claim/activate it; never file active. 2. Open the bypass (bypass_start) with your droid id + the remediation answer (remediates_initiative_id=NNN, or remediates_nothing=True). 3. Work the blocks for your work-type: template -> design -> code -> test -> review. Do the real work; record decisions on the initiative as you make them. 4. Reality is recorded for you at close -- code (files changed), each decision, and the twin-review verdict become real activities tied to this initiative and show in the Activity Tracker like a planner run (CAROL-INI-1840). No dummy rows. 5. Keep the initiative status moving; it parks in 'reviewing' and is tagged uat-pending for you at close (CAROL-INI-1836), so the stuck-watchdog leaves it alone until UAT. 6. Close runs the gates (design/architecture compliance + caller-audit). If a gate flags something pre-existing or unrelated to your change, waive it with a clear written rationale -- audit, don't skip. 7. Bypass skips the planner's auto-orchestration, NOT the standards. Same template checklist, same review, same observability as a planner run. (elrond)
• [status-router] planned -> executing | event=bypass_executing | bypass transition (or-bx-01)
• [delivery-check] 3 must-have criteria remain pending at bypass_end — delivery has no mechanical re-performance lane; UAT must grade on live evidence, not checklist silence (CAROL-INI-3020): (no detail) (orion)
• [status-router] executing -> reviewing | event=bypass_reviewing | bypass transition (or-bx-01)
• [status-router] reviewing -> closed | event=operator_signoff | Auto-accepted (CAROL-INI-1859): Orion-initiated, >2 days in reviewing with no objection. (el-srac-01)

✅Success criteria

• A ratified design record states the one-engine rule, the fences-outside rule, the runtime-loop-inside rule and the text-fallback rule, each citing the standing rulings it builds on (must_have)
• The design names the seams (engine, adapter, fence layer) and which existing initiative records own each (must_have)
• Build initiatives in this arc cite the design and are refused review without it (must_have)