Fabric Fusion

Use one fabric_exec call for a 2–8 model panel and a judge when at least two responses complete. The judge compares rather than merges responses; return a compact status/coverage/analysis envelope so the caller writes the final answer. Use fusion for model-diverse research or critique, not tactical work or a lookup.

Pass every key: strings.task; JSON strings.panel as Array<{ model, label? }>; and optional strings.judge, strings.tools, and strings.thinking as empty strings when unset. Labels are attribution only. Tools default to read, grep, find, ls, and bash; thinking defaults to configured agent thinking.

type FusionAnalysis = {
  consensus: string[];
  contradictions: string[];
  partial_coverage: string[];
  unique_insights: string[];
  blind_spots: string[];
};