📖About

Forge, Argus, and Radagast currently execute commands locally on carol-vm. They need a mode where they SSH into the target project's VM and run the work there instead. The vault carries the per-project SSH key. Carol's project always means local execution.

⚖️Decisions

• Part of the Carol→Glover multi-tenancy programme. Mode = bypass for foundation/bootstrap work; mode = planner for the final validation initiative. (Ninad)
• requester rewritten ninad -> orion per CAROL-INI-744: orion is the only human-CLI requester — Backfill of historical rows after INI744 added API-level refusal of requester=ninad. Orion is Ninads CLI agent; all human-originated initiatives are filed with requester=orion. (orion)
• [status-router] planned -> dispatched | event=dispatch | Backfilled into the 3-deep dispatch queue (CAROL-INI-1972); queued for operator push, not auto-executed. (spb-01)
• Gap J (CAROL-INI-771): stuck-dispatched with queue.status='no-queue-row'; flipped to blocked so Escalation card surfaces it. Reason: (elrond.handover_watchdog)
• Gap J (CAROL-INI-771): stuck-dispatched with queue.status='no-queue-row'; flipped to blocked so Escalation card surfaces it. Reason: (elrond.handover_watchdog)
• [status-router] dispatched -> executing | event=dispatcher_transition | dispatcher state change (ds-s1)
• [status-router] executing -> reviewing | event=review_inferred | review row present (el-review-inferer)
• [status-router] reviewing -> blocked | event=stuck_10min_no_activity | Elrond safety net: initiative has had no activity for 10+ minutes. Blocking under the parallel safety mechanism. (el-watchdog)
• Elrond safety net blocked initiative: no activity for 10+ minutes. Parallel mechanism (twin of handshake). (el-watchdog)
• Elrond blocked initiative under the CAROL-INI-2162 dead-Albus protocol. Albus was supposed to wake for step 0 (cause=albus_no_show) but did not respond. Cause: albus_no_show. Reason: Elrond safety net: initiative stranded 10+ min. Albus wake failed or produced no useful result. (el-s1)
• RSI diagnosed: 2026-07-01 07:05:13 -> improvement #(none). ({'_raw': 'ROOT CAUSE: The initiative was blocked because Albus did not respond for step 0 (albus_no_show), and the Elrond safety net then blocked it after 10 minutes of inactivity via the parallel watchdog mechanism.\n\nIMPROVEMENT: Implement a proactive health check and retry mechanism for Albus b (el-rsi-eng-01)
• Orion remediated: Albus RSI group diagnosis (via INI 999900430): [procedural, confidence high] Albus executor did not wake to execute step 0 of the initiative (albus_no_show), as evidenced by the Elrond safety net decision and the prior RSI diagnosis for the same cause group. The initiative remained idle for over 10 minutes, triggering the parallel safety mechanism. No actual work was attempted; the single execution history entry shows 'Idle close — no activity in window.' (orion)
• [status-router] blocked -> closed | event=operator_put | PUT /api/initiatives (operator)
• [rsi-group-cure] Cured by the group diagnosis on INI 999900430 (shared cause stuck_10min_no_activity); retriggered as INI 999900602. Root cause: [procedural, confidence high] Albus executor did not wake to execute step 0 of the initiative (albus_no_show), as evidenced by the Elrond safety net decision and the prior RSI diagnosis for the same cause group. The initiative remained idle for over 10 minutes, triggering the parallel safety mechanism. No actual work was attempted; the single execution history entry shows 'Idle close — no activity (elrond.rsi_loop)

✅Success criteria

• A pipeline droid called with project=glover runs its shell commands on glover-vm via SSH, not on carol-vm; with project=carol it runs locally. (must_have)