🛂 ci: Grant Multi-Convo Permission in E2E Mock Config (#14839)

`agent-skills-added.spec.ts` drives the composer's `+` command, which opens the
added-model popover. That path is gated on MULTI_CONVO.USE:

    if (!hasMultiConvoAccess || !plusCommandEnabled || isAssistantsEndpoint(endpoint)) return;

The mock config never sets `interface.multiConvo`, so the permission falls
through to the seeded role default and `handlePlusCommand` returns before
opening the popover. The spec then fails on a popover that is absent from the
DOM entirely, which reads as a selector or timing problem rather than a missing
permission.

Set it explicitly, the same way `contextCost` is set just above for the usage
gauge — the mock config's job is to make each exercised feature's gate explicit
rather than inherit a default.

e2e/config/librechat.e2e.yaml

@@ -8,6 +8,11 @@ interface:
   # Exercises the cost row in the context usage gauge (off by default).
   # Mock models price at the default rate, so synthetic usage yields a value.
   contextCost: true
+  # Grants MULTI_CONVO.USE so the composer's `+` command opens the added-model
+  # popover. agent-skills-added.spec.ts drives that flow; without an explicit
+  # value the permission falls through to the seeded role default and
+  # `handlePlusCommand` returns before opening the popover.
+  multiConvo: true
 
 # Enables the memory feature so the MEMORIES.USE permission is granted and the
 # ephemeral memory badge (inline set_memory/delete_memory tools) is available.