Hunter
In plain words: Candidate challenger (Hunter)
The planned role (Hunter) that reviews one fixed candidate in a separate run, pointing to unsupported assumptions, missing evidence and rule violations, and naming what observation could settle each.
- 1Returns challenges, evidence requests, boundary findings, withhold recommendations and unresolved uncertainty.
- 2Invents no replacement and gives no score, approval or certification.
- 3Stops where evidence or permission ends; lack of challenges does not certify a candidate.
Designed No simulation config, schema or Hunter path ships.
Words on this page, decoded click one for its card
Where the tracks end, the Hunter kneels.
An attractive candidate promises a clean result, yet one claimed predicate rests on an unsupported assumption. Hunter holds that candidate still, points to the exact gap, and names the observation that could settle it.
Hunter is Designed. No simulation RuneService Config File or schema ships, and no Hunter path runs. State of Work records delivery, while ADR 31 owns the design.
Hold one candidate still
Begin with one candidate whose identity can remain fixed throughout review: either a Dancer alternative or another attributed, named candidate. Its envelope gives Hunter the source IntentRequest, lineage, assumptions, required state, and claimed predicates, together with observations, evidence, artifacts, and the owning policy or contract. Those records let a challenge point to a specific claim under a specific boundary.
The owning Spellweaver Pattern declares the operational Shadow Lens, permitted evidence and tool access, review rounds, budget, and stop conditions. A fresh InvocationJob Request receives no private Dancer generation context and cannot rewrite sibling history. Hunter is not ScoutWeb Fetcher's web-acquisition office; any bounded inquiry proceeds only through Pattern-granted access.
The candidate remains Vikalpa, a possibility awaiting measurement. Hunter's attention does not change its standing.
Return attributed challenges
Hunter returns five typed records, with provenance:
challengestied to the candidate and a named assumption or predicate;evidence_requestsnaming the observation needed;boundary_findingstied to the owning policy or contract;withhold_recommendationsidentifying where further spend lacks present support; and- unresolved uncertainty the evidence cannot settle.
No private reasoning trace or verdict travels with them. The inquiry may expose an unsupported premise, biased framing, missing counterexample, absent evidence, boundary violation, or conclusion extending beyond observation. It may decompose a claim and challenge each dependency. Suspicion alone proves nothing.
Hunter invents no replacement, rewrites no IntentRequest, and supplies no score, rank, certification,
promotion, capability grant, or consent. Each withhold_recommendations item is only input to the
PatternWorkflow's spend decision; it cannot cancel work or deny spending by itself.
End at the evidence boundary
The review ends where its evidence or permission ends. Missing evidence remains unknown; Hunter cannot widen tool access to settle it. Exhausted rounds, budget, tool access, or a stop condition produce an incomplete review with uncertainty preserved. An extra round is never automatic, and reaching the limit establishes neither rejection nor safety.
Review leaves the candidate's identity, provenance, artifacts, and failure evidence intact. Neither an unanswered challenge nor a lack of further challenges certifies it.
Findings may return to SpellweaverWorkflow Engine and its PatternWorkflow, enter deterministic checks, become a Drift trial subject, or reach the MagusYou, the Operator for an owned decision. Repair or renewed expansion requires Dancer or another separate InvocationJob Request.
The parent Shadow page places this review passage within the possibility-lineage Domain.