feat: configure supervisor model and story graph use per conversation

Add a supervisor text-model selector using existing connections and a per-conversation story graph switch above knowledge settings. Hide the switch when Supervisor is disabled and enforce conversation preferences at local and remote tool execution boundaries.

Release note: Choose a dedicated supervisor model and control whether each conversation can query existing stories and experiences. Enabling graph access does not start a review or automatically insert context.

src/shared/assistant-contracts.ts

@@ -620,6 +620,7 @@ export const conversationSnapshotSchema = z
     knowledgeLibraryIds: z.array(assistantIdSchema).max(20).optional(),
     workMode: workModeSchema.optional(),
     knowledgeRetrievalMode: z.enum(['auto', 'always']).optional(),
+    storyGraphEnabled: z.boolean().optional(),
     contextMetrics: conversationContextMetricsSchema.optional(),
     contextCompressionState:
       conversationContextCompressionStateSchema.optional(),
@@ -671,6 +672,11 @@ export const conversationSetPinnedSchema = z.object({
   pinned: z.boolean()
 }).strict()
 
+export const conversationSetStoryGraphSchema = z.object({
+  conversationId: assistantIdSchema,
+  enabled: z.boolean()
+}).strict()
+
 export type ConversationSetPinnedInput = z.infer<
   typeof conversationSetPinnedSchema
 >