📖About

Ninad (2026-08-15): Clara truncated the 139-task list because grounding is ONE SQL with LIMIT 50. Build a bounded loop in the grounding engine: after the first result the model may ask up to 2 follow-up read-only queries (same fenced surface, same bans), evidence aggregates under a total size cap, and when evidence is cut the block SAYS truncated (an empty page passes every check about what is on it - truncation must be stated, never silent). Chat-lane worst case stays inside the proxy window: measured turn 23s + max 2 extra lane calls ~18s = ~41s < 60s.

--- Resequenced 2026-08-16 (Ninad): the rich-chat arc is FIVE phases. 1 rich replies (3864/3865/3866) - 2 live stages + named threads (3867) - 3 the self-correcting turn + WhatsApp full-turn convergence (3873) - 4 files, charts, canvas (3868) - 5 get-back-to-me (3869; voice removed 2026-08-16, parked separately). The self-correcting turn moved AHEAD of files/canvas: it rebuilds the turn machinery and completes the one-engine convergence, and file grounding plus canvas state plug INTO that turn - building them first wires them to a seam about to be rebuilt. Voice was removed from the arc on 2026-08-16 and parked on its own record.

⚖️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] 4 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)
• [arc] Rich-chat arc resequenced into FIVE phases (Ninad, 2026-08-16): 1 rich replies (3864/3865/3866) | 2 live stages + named threads (3867) | 3 the self-correcting turn + WhatsApp full-turn convergence (3873) | 4 files, charts, canvas (3868) | 5 voice + get-back-to-me (3869). — The self-correcting turn moved ahead of files/charts/canvas because it rebuilds the turn machinery and finishes the one-engine convergence (3872/3877); file grounding and canvas state plug into that turn, so building them first would wire them to a seam about to be rebuilt. Voice remains last per Ninad's standing ruling. (orion)
• [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 question needing >50 rows (list all estate tasks) is answered completely or with a STATED truncation, never a silent partial (must_have)
• The loop is capped at 3 queries per turn and the evidence block at a fixed size; both caps stated in the block when hit (must_have)
• All existing grounding fences hold in every round (read-only, banned tables, confidential rows) - test proves a banned query in round 2 is refused (must_have)
• A full turn with a 3-round grounding stays under 60s measured (must_have)