review: the persona becomes the system-prompt plugin's deployment config

Review round 2 (tianyicui inline comments):

- dsh-system-prompt itself registers the harness:identity (-100) and
  deployment:persona (0) sections — they must survive a swapped loop
  plugin, so they leave dsh-agent-loop; the persona text is the plugin's
  own validated 'persona' config. The model/cwd variables STAY on the
  loop: runtime facts of the agents it drives.
- AgentOptions.systemPrompt is deleted with all its forwarding plumbing:
  the app configs' systemPrompt keys become 'persona' routed through
  dsh-agent-core (schema = z.intersect of the owners'), the ACP bridge
  and tool-subagent stop carrying persona configuration, and subagent
  children now render the deployment persona like every other agent.
- Example personas drop transport/interface trivia (ACP, CLI) — facts
  irrelevant to the model.
- Root CONTEXT.md removed (not idiomatic); its persona definition was
  wrong under the new ownership anyway.
- Docs, READMEs, the prompt-variables RFC, and generated catalogs
  updated; new loop test pins the assemble-waterfall escape valve
  (an emptied assembly sends NO system field).

packages/core/agent/src/index.ts

@@ -49,7 +49,7 @@ export interface CreateAgentOptions {
    * for a fresh (spawn) child.
    */
   seed?: SessionEvent[]
-  /** Per-agent options (model, system prompt). */
+  /** Per-agent options (model, …). */
   agentOptions?: AgentOptions
 }
 
@@ -62,7 +62,7 @@ export interface ResumeAgentOptions {
   agentId: AgentId
   /** The persisted session id to load and resume on. */
   resumeSessionId: SessionId
-  /** Per-agent options (model, system prompt). */
+  /** Per-agent options (model, …). */
   agentOptions?: AgentOptions
 }
 

packages/core/agent/src/types.ts

@@ -60,9 +60,8 @@ declare module '@deepseek-ai/dsh-system-prompt' {
   interface AssembleContext {
     /**
      * The agent this assembly is for. The agent loop passes it on every
-     * per-step `assemble({ agent })`; section text and variable providers
-     * project per-agent facts from it (`options.systemPrompt` → the persona
-     * section, `options.model` → `{{model}}`, `session.header.cwd` →
+     * per-step `assemble({ agent })`; variable providers project per-agent
+     * facts from it (`options.model` → `{{model}}`, `session.header.cwd` →
      * `{{cwd}}`). Optional because a bare `assemble()` (tests, diagnostics)
      * has no agent — providers must tolerate its absence.
      */
@@ -71,23 +70,14 @@ declare module '@deepseek-ai/dsh-system-prompt' {
 }
 
 /**
- * Options an agent is created with.
+ * Options an agent is created with. The persona is NOT here — it is the
+ * deployment's `persona` config on the dsh-system-prompt plugin, shared by
+ * every agent in the context.
  * Merge-extensible: plugins declare extra fields via declaration merging.
  */
 export interface AgentOptions {
   /** Model name (must have a registered adapter at call time). */
   model?: string
-  /**
-   * The agent's persona: a deployment-authored prompt-TEMPLATE fragment,
-   * rendered as the order-0 section of the assembled system prompt (before
-   * all tool guidance). It may reference registered `{{variables}}` (e.g.
-   * `{{model}}`, `{{cwd}}`); it is one section of the full prompt, never the
-   * whole. Template, not free-form text: every complete `{{…}}` group IS
-   * interpreted, strictly — an unknown or malformed reference fails the turn
-   * loudly — and there is no escape syntax for literal `{{…}}` prose yet (a
-   * deliberate deferral; see the prompt-variables RFC).
-   */
-  systemPrompt?: string
 }
 
 export interface SendOptions {