fix(ui): drop the caption from the /permission error text too

Review round: the no-caption rule the Agent Note states applied only to the
success texts, leaving `permission · unknown permission preset "bogus" (…)`.
The error text now reads `unknown preset "bogus" (…)` and its exact wording
is pinned; the fixture mirror drops `JSON.stringify` for the host's own
quoting so the two cannot drift on a quoted argument.

The Note now states the line it draws: the rule bans a caption for the
command's own value, not the vocabulary, so `/plan`'s `Plan mode off.` and
`/goal`'s `Goal cleared.` conform as written — recorded with the broader
name-ban as a rejected alternative. The web row assertions are scoped to the
row so unrelated page text reading `permission` cannot satisfy them.

packages/client/connection/src/client/fixture.ts

@@ -1333,7 +1333,7 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy {
             const current = permissionSelectOf(logOf(id)).currentValue
             append(id, { type: 'command/done', data: { commandId, kind: 'success', text: `current preset ${current} (available: ${Object.keys(PERMISSION_PRESETS).join(', ')})` } })
           } else if (spec === undefined) {
-            append(id, { type: 'command/done', data: { commandId, kind: 'error', text: `unknown permission preset ${JSON.stringify(preset)} (available: ${Object.keys(PERMISSION_PRESETS).join(', ')})` } })
+            append(id, { type: 'command/done', data: { commandId, kind: 'error', text: `unknown preset "${preset}" (available: ${Object.keys(PERMISSION_PRESETS).join(', ')})` } })
           } else {
             if (permissionSelectOf(logOf(id)).currentValue !== preset) append(id, { type: 'permission/preset', data: { preset } })
             append(id, { type: 'sandbox/mode', data: { mode: spec.sandbox } })