📖About

Seed and wire the chat actions themselves, for all agents in one arc. UNIVERSAL (every agent, within its realm): start/pause/resume a droid; trigger one run of a scheduled droid now; restart an owned app through Radagast; request an initiative through Elrond's Creator; read its own health, runs and spend. All through the framework's boundary with receipts.

⚖️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)
• [HYGIENE GATE apps_registered] skip: work_type=G does not require app registration (orion.bypass)
• [HYGIENE GATE design_filed] pass: design 483: Agent Chat Actions: mandatory boundary, authority realms, employees (CAROL-INI-3513) (orion.bypass)
• [HYGIENE GATE architecture_compliance] pass: references architecture design #146 (agent-centric modular architecture) (orion.bypass)
• [HYGIENE GATE policy_check] pass: considered: P.01.03.09.01,P.01.03.09.02,P.01.03.09.05 (orion.bypass)
• [HYGIENE GATE constitution_aligned] pass: soft-default pass; caller responsible for asserting via decision row (orion.bypass)
• [HYGIENE GATE cookbook_entry] fail: no cookbook_id provided — bypass should leave a recipe or explicitly waive (orion.bypass)
• [HYGIENE GATE logbook_entry] pass: logbook session 306: (orion.bypass)
• [status-router] executing -> reviewing | event=bypass_reviewing | bypass transition (or-bx-01)
• Parallel-session note (CLI-185): a concurrent Orion session (CLI-186) rewrote regression/test_ini3514.py at 15:29 UTC with an equivalent 22-check hermetic suite covering the same contracts; CLI-185s original 29-check version was superseded, not restored (CLI-177 no-clobber-back rule). All suites green against the merged live state (3513: 34/0, 3514: 22/0, 3515: 15/0). The framework files from 14:14 and the 15:22 core-install are intact. — Two sessions built on the same initiative; the live merged state is coherent and green, so the record notes the merge instead of racing writes. (orion)
• [agt_042.mind] dispatched my droid var-privacy-gate-01 (sequence 1): Run my privacy review gate over CAROL-INI-3514-00: verify whether the 'every agent's chat actions: universal set' introduces any read-by-default or write channels that can reach private records (wishes, agent memories, user PII); enumerate data categories exposed, require explicit carve-outs for private records, confirm lawful bases, retention and deletion rules, supervisor-visibility reconciliation, mechanical non-inheritance, and produce blockers and required wording changes. Also flag sibling initiatives (3513, 3515) for a combined sweep if the gate finds composing channels. — My standing goals are to enforce user-memory isolation and prevent default-read channels from becoming permanent cross-agent pathways. 3514's 'universal set' of chat actions is a textbook place where a default could grant broad read access; I must run the privacy gate now and sweep siblings if the gate finds composition risks. (agt_042.mind)
• [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

• Every agent can start or pause its own droids, trigger a run, restart an owned app, request an initiative, and report its own health from its chat, each producing a receipt (must_have)
• Elrond can start, pause and stop the build pipeline from his chat, and the switch records that he did it (must_have)
• Each agent with a specific control can trigger it from its own chat within its authority and nothing outside that authority (must_have)
• A chat-triggered action that runs a process bills that process's own service, visible in the cost records (must_have)