Keep delegated-agent notifications alive through permission prompts (#3177)

* fix(agents): preserve permission notification callbacks

Permission requests consumed the one-shot completion watcher, so callers never heard about later approvals or the final result. Keep the watcher alive across permission checkpoints and include the actionable request payload in each notification.

* fix(agents): notify concurrent permission requests

docs/agent-lifecycle.md

@@ -49,6 +49,8 @@ Runtime ownership is resolved from explicit workspace ID and caller context, nev
 Users can also detach an existing subagent from the subagents track. Detach is deliberately a manual lifecycle gesture, not an agent-facing MCP tool. It removes the `paseo.parent-agent-id` label only: it does not stop, archive, move, or restart the agent. The agent keeps its current `cwd` and `workspaceId`, leaves the former parent's track, and behaves like a root agent for tab close, workspace activity, and future parent archive.
 
 `notifyOnFinish` defaults to `true` for agent-scoped creation and background prompt follow-ups because most delegated work needs to report back to the creating agent. Set it to `false` only for truly fire-and-forget agents or prompts.
+Permission requests are notification checkpoints, not the end of that subscription. The caller is notified again after a permission response when the child finishes, errors, or requests another permission.
+The permission notification includes the normalized request plus the child and request IDs, so the caller can inspect it and respond without fetching agent status.
 
 ## Provider-managed child agents