drew
b4ebf6a2bd
Document the two known gaps that need operator intervention for an
end-to-end trial:
1. MCP-to-OpenCode transport: response-builder MCPs aren't yet
registered in opencode.json. Agents use the FALLBACK file-write
path (``{workspace_dir}/{role}_output.json``) per the prompt
instructions. The agent_runner polls both channels.
2. CI status polling not wired: AWAITING_CI exits only via
ci_polling_exhausted timeout (default 2h → STUCK). To advance
during the trial, the operator runs a SQL UPDATE to manually
transition AWAITING_CI → REVIEWING (snippet in the RUNBOOK).
Added a step-by-step Trial checklist covering: env vars, label
the PR, expected log timeline, the manual SQL to advance past
AWAITING_CI, and the verification query.
Both gaps have follow-up phases queued (1m for MCP wiring, 1n for
CI poller). The trial as described validates the full controller
state machine + most of the worker substrate; only the CI poll +
the MCP transport are operator-intervention paths.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Controller deployment
Contents:
RUNBOOK.md— operator guide: setup, day-to-day, incident response, migration playbook, tunables.systemd/cleveragents-controller-master.service— master singleton unit (one per owner/repo).systemd/cleveragents-controller-worker@.service— worker template unit (systemctl enable cleveragents-controller-worker@implementer-1).systemd/master.env.example— env vars the master reads (copy to/etc/cleveragents/master.env).systemd/worker.env.example— env vars the workers read (copy to/etc/cleveragents/worker.env).
Start with the RUNBOOK.