Autopilot

$deep-interview -> $ralplan -> $ultragoal (+ $team if needed) -> $code-review -> $ultraqa

If $code-review or $ultraqa is not clean, Autopilot returns to $ralplan with the findings as the next planning input, then continues again through $ultragoal, $code-review, and $ultraqa until the gates are clean or a hard blocker is reported. Ralph is a legacy/explicit alternate execution loop only; do not advertise Ralph as the default Autopilot path.

1. Phase deep-interview — Socratic requirements clarification gate

   • Run or resume $deep-interview to clarify intent, scope, non-goals, constraints, and decision boundaries.
   • Deep-interview is a structured question chain, not a one-question gate; max_rounds is a cap, not a target.
   • After a user answers an omx question, re-score ambiguity against the active profile threshold. Ask another question only when a readiness gate is still unresolved and the answer would materially change execution; otherwise crystallize the spec and hand off.
   • Required handoff artifact: a clarified spec or concise requirements summary suitable for $ralplan, including an explicit interview-complete rationale when leaving deep-interview.

2. Phase ralplan — consensus planning gate

   • Ground the task with pre-context intake and the deep-interview artifact.
   • Current ownership rule: Autopilot records planning_routing in state before heavy planning. When the Autopilot/main model resolves to a cheap/mini lane (for example o4-mini, *-mini, *spark*, or an explicitly cheap/economy/lite model name), the initial planning/decomposition owner is dedicated [planner]; otherwise [main] may keep ownership for backward compatibility. A configured agentModels.planner is an explicit opt-in that forces dedicated [planner] ownership even when [main] is not cheap/mini.
   • Run or resume $ralplan to produce/update PRD and test-spec artifacts. If planning_routing.owner is planner, use the dedicated [planner] role for the initial Planner draft/decomposition before the Architect→Critic consensus gates.
   • PRD/test-spec files alone are not completion evidence. Ralplan may hand off only after durable consensus evidence records a subsequent Architect approval first and a subsequent Critic approval second.
   • When returning from a non-clean review or QA pass, include return_to_ralplan_reason and the findings as first-class planning input.
   • If either review is missing, blocked, out of order, or non-approving, remain in ralplan or report an explicit blocker/max-iteration outcome; do not progress to $ultragoal, $team, $ralph, or implementation.
   • Required handoff artifact: an approved plan/test spec plus ralplan_consensus_gate evidence suitable for $ultragoal.

3. Phase ultragoal — durable implementation + verification loop

   • Run $ultragoal from the approved ralplan artifacts.
   • Ultragoal owns durable Codex goal handoffs, .omx/ultragoal ledger checkpoints, implementation, tests, build/lint/typecheck evidence, cleanup, and final review gate discipline.
   • Use $team only inside an active Ultragoal story when the story clearly benefits from coordinated parallel execution (for example independent file/module lanes, broad test matrix work, or multi-domain implementation). Team remains explicit and leader-owned; Ultragoal keeps the goal/ledger state.
   • Required handoff artifact: implementation evidence, changed-file summary, verification evidence, and Ultragoal ledger/checkpoint references suitable for $code-review.

4. Phase code-review — merge-readiness gate

   • Run $code-review on the diff/artifacts produced by $ultragoal.
   • A clean review means final recommendation APPROVE with architectural status CLEAR.
   • COMMENT, REQUEST CHANGES, any architectural WATCH/BLOCK, or any unresolved finding is not clean.
   • If not clean because the implementation must be repaired, increment the review cycle, persist review_verdict, set current_phase:"rework", and carry the findings as the sanctioned execution-fix input. Return to Phase ralplan only when the review shows the plan/requirements are wrong or incomplete.

5. Phase ultraqa — adversarial QA gate

   • Run $ultraqa after a clean code review when user-facing behavior, workflows, CLI/runtime behavior, integration surfaces, or regression risk warrant adversarial QA.
   • For docs-only or trivially non-runtime changes, record ultraqa as skipped with an explicit condition and evidence.
   • If UltraQA finds issues, persist the QA verdict/evidence, set return_to_ralplan_reason, and transition back to Phase ralplan.

The only normal terminal state is complete after clean code review and a passed or explicitly skipped UltraQA gate. Cancellation, blocked credentials, unrecoverable repeated failures, or explicit user stop may terminate earlier with preserved state.

Before Phase deep-interview or ralplan starts or resumes:

1. Derive a task slug from the request.
2. Reuse the latest relevant .omx/context/{slug}-*.md snapshot when available.
3. If none exists, create .omx/context/{slug}-{timestamp}.md (UTC YYYYMMDDTHHMMSSZ) with:
   • activation prompt / task seed
   • original task status (activation-prompt, legacy-unverified, or unavailable)
   • desired outcome
   • known facts/evidence
   • constraints
   • unknowns/open questions
   • likely codebase touchpoints
   • a scope note that the seed is the Autopilot activation prompt, not guaranteed prior conversation context
4. If brownfield facts are missing, run explore first before or during $deep-interview ($deep-interview --quick <task> remains acceptable for bounded low-ambiguity intake); do not skip the clarification gate merely because the task sounds actionable.
5. Carry the snapshot path in Autopilot state and all handoff artifacts. </Pre-context Intake>

Inside active Autopilot, named child phases such as $ralplan are supervised phases, not peer workflow activations: keep mode:"autopilot" active and update current_phase:"ralplan" rather than starting standalone mode:"ralplan" over Autopilot.

Required fields:

{
  "mode": "autopilot",
  "active": true,
  "current_phase": "deep-interview",
  "iteration": 1,
  "review_cycle": 0,
  "max_iterations": 10,
  "phase_cycle": ["deep-interview", "ralplan", "ultragoal", "code-review", "ultraqa"],
  "handoff_artifacts": {
    "context_snapshot_path": ".omx/context/<slug>-<timestamp>.md",
    "deep_interview": null,
    "ralplan": null,
    "ralplan_consensus_gate": {
      "required": true,
      "sequence": ["architect-review", "critic-review"],
      "planning_artifacts_are_not_consensus": true,
      "required_review_roles": ["architect", "critic"],
      "ralplan_architect_review": null,
      "ralplan_critic_review": null,
      "complete": false
    },
    "ultragoal": null,
    "code_review": null,
    "ultraqa": null
  },
  "review_verdict": null,
  "qa_verdict": null,
  "return_to_ralplan_reason": null
}

• On start: omx state write --input '{"mode":"autopilot","active":true,"current_phase":"deep-interview","iteration":1,"review_cycle":0,"state":{"phase_cycle":["deep-interview","ralplan","ultragoal","code-review","ultraqa"],"handoff_artifacts":{"context_snapshot_path":"<snapshot-path>","deep_interview":null,"ralplan":null,"ralplan_consensus_gate":{"required":true,"sequence":["architect-review","critic-review"],"planning_artifacts_are_not_consensus":true,"required_review_roles":["architect","critic"],"ralplan_architect_review":null,"ralplan_critic_review":null,"complete":false},"ultragoal":null,"code_review":null,"ultraqa":null},"review_verdict":null,"qa_verdict":null,"return_to_ralplan_reason":null}}' --json
• On deep-interview -> ralplan: only after a separate gate proves the interview chain is explicitly complete or the user explicitly authorized a skip. For completion, persist deep_interview_gate:{"status":"complete","rationale":"<why requirements are complete>","handoff_summary":"<summary>"} (or equivalent non-empty rationale/summary) plus the clarified spec/requirements under handoff_artifacts.deep_interview; if a final omx question was involved, keep its same-session answered record linked by question_id/satisfied_at. For skip, persist deep_interview_gate:{"status":"skipped","skip_authorized_by_user":true,"skip_reason":"<user-authorized reason>","skipped_at":"<timestamp>","source":"user","session_id":"<session>"}. Do not leave deep-interview merely because the first omx question was answered or cleared.
  • Optional execution contract foundation: when a downstream handoff explicitly sets execution_contract_required:true, persist a complete structured execution_contract under handoff_artifacts.deep_interview before leaving deep-interview. The canonical schema is version:1, execution_stride:"task"|"deliverable"|"milestone", source:"deep-interview", selected_by:"user"|"default", allow_task_shrink:<boolean>, non-empty completion_unit, non-empty stop_condition, acceptance_coverage_scope:"task"|"deliverable"|"milestone", and shrink_policy:"allowed"|"ask_before_shrink"|"deny_unless_blocked".
  • Stride semantics are binding only when execution_contract_required:true: task means allow_task_shrink:true, acceptance_coverage_scope:"task", shrink_policy:"allowed"; deliverable means allow_task_shrink:false, acceptance_coverage_scope:"deliverable", shrink_policy:"ask_before_shrink"; milestone means allow_task_shrink:false, acceptance_coverage_scope:"milestone", shrink_policy:"deny_unless_blocked".
  • Preserve legacy behavior when execution_contract_required is absent or false. Do not infer stride from prose, broadness, phase names, snapshots, or task size; this foundation only validates an explicit structured contract and deliberately uses milestone rather than phase. New artifacts must write canonical snake_case keys under handoff_artifacts.deep_interview; the runtime may read legacy camelCase field/marker aliases and direct/nested execution_contract locations only as compatibility input.
• On ralplan -> ultragoal: only after ralplan_consensus_gate.complete:true, with tracker-backed native-subagent ralplan_architect_review.agent_role:"architect" and ralplan_architect_review.verdict:"approve" recorded before tracker-backed native-subagent ralplan_critic_review.agent_role:"critic" and ralplan_critic_review.verdict:"approve"; codex_exec or artifact-only approvals are trace evidence but not native lane proof. Set current_phase:"ultragoal" and persist the plan/test-spec paths under handoff_artifacts.ralplan.
• On missing ralplan consensus evidence: keep current_phase:"ralplan", persist ralplan_consensus_gate.complete:false with blocked_reason, and report an explicit blocker or max-iteration outcome instead of handing off to execution.
• On ultragoal -> code-review: set current_phase:"code-review", persist implementation/test/ledger evidence under handoff_artifacts.ultragoal.
• On code-review -> ultraqa: set current_phase:"ultraqa" only after a real $code-review stage/subagent has produced durable evidence; persist the clean review under handoff_artifacts.code_review with its source thread/tool/stage reference. Do not author review_verdict:{clean:true} from the leader's own summary.
• On non-clean code-review requiring implementation repair: increment review_cycle, set current_phase:"rework", persist review_verdict, persist the phase handoff under handoff_artifacts.code_review, and keep the fix scoped to the review findings before returning to code-review.
• On clean review + passed/skipped QA: set active:false, current_phase:"complete", persist review_verdict:{recommendation:"APPROVE", architectural_status:"CLEAR", clean:true}, qa_verdict:{clean:true, skipped:<boolean>, reason:<string|null>}, and completed_at only when both gates have durable source evidence. Required evidence is either (a) actual $code-review/$ultraqa stage or native-subagent/thread/tool records, or (b) for QA only, an explicit persisted skip reason for a documented docs-only/trivially non-runtime condition. If that evidence is missing, keep the active phase at code-review or ultraqa and record a blocker instead of self-attesting a clean gate.
• On non-clean review requiring plan changes or failed QA: increment iteration and review_cycle, set current_phase:"ralplan", persist review_verdict or qa_verdict, persist the phase handoff, and set return_to_ralplan_reason to a concise findings-driven reason.
• Legacy Ralph state: if a user explicitly selected the legacy Ralph execution lane, phase names and handoff keys may include ralph; preserve and resume them rather than rewriting history to Ultragoal.
• On cancellation: run $cancel; preserve progress for resume rather than deleting handoff artifacts.

Do not restart discovery or discard handoff artifacts on continuation.

deep-interview -> ralplan -> ultragoal -> code-review -> ultraqa

Pipeline state should use current_phase values that match the same phase names (deep-interview, ralplan, ultragoal, rework, code-review, ultraqa, complete, failed) and should carry iteration, review_cycle, handoff_artifacts, review_verdict, qa_verdict, and return_to_ralplan_reason alongside stage results. $team is not a default pipeline stage; it is an explicit conditional execution engine inside an Ultragoal story.