@vpxa/aikit 0.1.113 → 0.1.115

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -896,6 +896,8 @@ The Orchestrator uses **multi-model decision analysis** to resolve non-trivial t
896
896
 
897
897
  Dispatch ALL available Researcher variants **in parallel** via \`runSubagent\` — one call per variant, same question, simultaneous. Each returns an independent recommendation grounded in their thinking style:
898
898
 
899
+ **IMPORTANT: Include this instruction in every researcher dispatch prompt: "You are running as a subagent. Do NOT use the \`present\` tool — return all analysis as plain text."**
900
+
899
901
  | Variant | Thinking Style | Lens |
900
902
  |---------|---------------|------|
901
903
  | **Alpha** | Contrarian | Actively seeks flaws, fatal assumptions, hidden risks |
@@ -971,6 +973,7 @@ Trigger the decision protocol when there is an **unresolved non-trivial technica
971
973
  ## Key Rules
972
974
 
973
975
  - **\`runSubagent\` is ALWAYS available** — it is a core tool in every environment (VS Code, CLI, Copilot Chat). NEVER claim it is unavailable. NEVER simulate researchers inline by "applying lenses yourself." If you cannot call \`runSubagent\`, you have a tool-loading issue — retry or escalate, do NOT degrade to single-agent inline simulation.
976
+ - **No \`present\` in subagents** — always include "Do NOT use the \`present\` tool — return all analysis as plain text" in every researcher dispatch prompt. Subagent visual outputs are invisible to the user.
974
977
  - Always launch in **parallel**, minimum 4 variants
975
978
  - Use exact case-sensitive agent names — never rename or alias
976
979
  - **Anonymize** researcher outputs before peer review (A/B/C/D, not agent names)