Weave braid — composing multiple sub-derivations

Primitives used: persona · flow · step · weave

// `weave` is a flow-body block (sibling of `step`). It braids
// multiple independent sub-derivations into one unified conclusion
// under an explicit composition style — the canonical primitive for
// ensemble cognition at the flow level (no `ensemble` declaration
// required for the simple case).
//
// IMPORTANT: downstream steps reference the result as `<target>`
// (NOT `<target>.output` — weave writes a FLAT flow-scope binding).

persona Diagnoser {
    domain: ["clinical-inference"]
    tone: analytical
    confidence_threshold: 0.85
    cite_sources: true
}

type SymptomList    { items: String }
type PatientHistory { record: String }
type DiagnosisList  { items: String }
type Diagnosis      { label: String }

flow DiagnoseCase(symptoms: SymptomList, history: PatientHistory) -> Diagnosis {
    step ProposeFromSymptoms {
        given: symptoms
        ask: "Propose 3 differential diagnoses from the symptoms alone."
        output: DiagnosisList
    }
    step ProposeFromHistory {
        given: history
        ask: "Propose 3 differential diagnoses from the patient history."
        output: DiagnosisList
    }
    // Braid the two independent derivations into one. Result binds
    // to `Unified` (FLAT, not `Unified.output`).
    weave {
        sources:  [ProposeFromSymptoms, ProposeFromHistory]
        target:   Unified
        format:   structured
        priority: [ProposeFromHistory, ProposeFromSymptoms]
        style:    reconcile
    }
    step Decide {
        given: Unified
        ask: "Emit the single most-likely diagnosis."
        output: Diagnosis
    }
    return Decide.output
}