omh-autopilot

OMH Autopilot — End-to-End Autonomous Pipeline

When to Use

• End-to-end feature implementation from idea to verified, reviewed code
• The user says: "autopilot", "build me", "handle it all", "e2e this"

When NOT to Use

• Single-file changes or trivial tasks (just do them)
• You want to stay in one continuous session (autopilot is multi-session)
• You only need planning (omh-ralplan) or execution (omh-ralph)

Prerequisites

• The omh plugin must be installed (~/.hermes/plugins/omh/)

Architecture: One Phase Step Per Invocation

Each autopilot invocation reads state, does ONE unit of work, exits. The caller re-invokes. This preserves fresh context at every level — including during the ralph loop.

Invocation 1:   Phase 0 — requirements (or skip)
Invocation 2:   Phase 1 — planning (or skip)
Invocations 3-N: Phase 2 — ralph iterations (one per call)
Invocation N+1: Phase 3 — QA cycle         [FRESH SESSION]
Invocation M:   Phase 4 — validation round  [FRESH SESSION]
Final:          Phase 5 — cleanup → complete

See references/caller-examples.md for how to drive the loop.

Procedure

Step 0: Resolve Instance and Acquire Lock

Autopilot drives a goal through spec → plan → ralph → QA → validation. Two autopilot sessions on the same goal would race on autopilot, ralph, and ralph-tasks state simultaneously. Use per-instance state

• advisory lock.

1. Resolve instance_id in this order:
   • If a confirmed spec exists at .omh/specs/{name}-spec.md, use instance_id = "{name}".
   • Else if a plan exists at .omh/plans/ralplan-{slug}.md, use instance_id = "{slug}".
   • Else derive from the goal: instance_id = kebab(goal)[:60].
2. Acquire the autopilot lock:

   lock = omh_state(action="lock", mode="autopilot",
                    lock_key="{instance_id}",
                    session_id="{HERMES_SESSION_ID or uuid}",
                    holder_note="autopilot driving {goal_or_plan}")
   

   On acquired=false, report held_by, offer wait/cancel/different goal. Stale-pid auto-release applies.
3. Pass instance_id to every omh_state call in this invocation (autopilot, ralph, ralph-tasks).
4. When dispatching to ralph in Phase 2, pass the same instance_id in the delegation context so the ralph subagent acquires mode="ralph" lock on the same slug.
5. Release the autopilot lock at every exit point (paused, blocked, complete, exception):

   omh_state(action="unlock", mode="autopilot",
             lock_key="{instance_id}",
             session_id="{HERMES_SESSION_ID or uuid}")