craft-goal

# Craft Goal Craft the autonomy contract above AgentOps RPI. A goal is a persistent Mayor over a bead-shaped experiment graph. Each RPI is one scientific trial; the goal selects the next useful trial, preserves what was learned, and ratchets toward a larger outcome. ```text Goal / Mayor: observe graph → choose bounded wave → consume verdicts → ratchet └─ Bead: durable experiment intent, context, scratch, evidence, and links └─ RPI: plan → implement → fresh validate → verdict → report and stop └─ Implementation: one RED → GREEN → refactor experiment ``` The number of RPIs need not be known in advance. The goal is safe when success is decidable, every experiment is bounded, knowledge is monotonic, and the authorization envelope cannot silently renew itself. **Insight:** bounded waves shorten the feedback loop; one hard, non-renewing campaign envelope prevents those waves from becoming infinite continuation. Named failure mode — **completion treadmill**: discoveries recursively become requirements and activity continues without new information. Its opposite is **first-red abandonment**: one falsified hypothesis ends a viable campaign. Anti-pattern: choose endless retries or stop on the first red. Corrective: continue while experiments produce a defined ratchet and remain inside the envelope; invoke an andon on churn, judgment, or exhaustion. Stop when the goal reports `ACHIEVED`, `NOT_ACHIEVED`, or `NEEDS_OPERATOR`. ## Modes | Caller wording | Mode | ...