feat(server): inference state-graph + supervisor, memory tools, MCP client, schema, routes

- Add state-graph.ts: typed state machine for inference lifecycle
- Add supervisor.ts: agent supervisor pattern for multi-agent coordination
- Add export-formatter.ts: structured export formatting
- Add manage_memory.ts: memory CRUD tool for agent persistence
- Add get_wiki_article.ts: codecontext wiki article retrieval
- Extend memory/index.ts: 3-tier memory (context/daily/core)
- Extend MCP client: mcp-config.ts env-var substitution
- Update schema.sql: agent_sessions, tasks, pending_changes extensions
- Update API types: MessageMetadata, ErrorReason, AgentSessionConfig
- Update routes: chats, messages, sessions — column renames and agent_session_id
- Update inference: error handler, payload builder, stream phase, turn orchestrator

apps/server/src/services/inference/stream-phase.ts

@@ -56,6 +56,7 @@ export async function executeStreamPhase(
     message_id: assistantMessageId,
     chat_id: chatId,
     role: 'assistant',
+    ...(args.compareGroupId ? { compare_group_id: args.compareGroupId } : {}),
   });
 
   const flusher = createContentFlusher(ctx.sql, assistantMessageId, () => state.accumulated);
@@ -119,6 +120,7 @@ export async function executeStreamPhase(
           message_id: assistantMessageId,
           chat_id: chatId,
           content: delta,
+          ...(args.compareGroupId ? { compare_group_id: args.compareGroupId } : {}),
         });
         ctx.log.debug({ sessionId, delta }, 'inference delta');
         flusher.scheduleFlush();