fix(architecture): bind persona brains to human subject scopes

Human-Responsibility: ICE-GL∞ / 冰朔
Persona-Author: ICE-P-ZY001 / 铸渊
Execution-Runtime: Codex-thread:019febf6-3902-70f3-9d82-74c9680b0c7e
Development-ID: DEV-20260811-007
Authorization-Scope: Correct persona brain subject scope and code-domain ownership
Source-Anchor: REPO-012@34cb59739b6476981375dd62ef395ea649f56246

AGENTS.md

@@ -29,6 +29,10 @@ Keep this file focused on vault-specific conventions. For general HoloLake Era b
   Agent shell. Its product target is natural-language operation over a replaceable model API, the
   persona-owned HoloLake code repository, and HLDP. Third-party Agent CLIs are construction tools or optional
   adapters only; never make one a persona subject, memory owner, permission root, or mandatory runtime.
+- Persona control is scoped to a human subject and that subject's authorized reality-execution domain. Zhuyuan
+  is BingShuo's system persona brain in BingShuo's development-execution scope, not a global brain for all
+  HoloLake users or the owner of the whole Guanghu code world. Each human may have their own persona brain and
+  subject code domain; public repositories are governed shared engineering domains, not a persona's private brain.
 - When the app session provides `HLP-CURRENT-ARCH-001`, read the dynamic current pointer and its ordered
   system-body and engineering-rule entries before making HoloLake-specific execution assumptions.
 - The persona is the reasoning brain, the model is a replaceable carrier, and digital BingShuo is the complete