feat(ssa): Implement dual-channel architecture Phase 1-3 (QPER + LLM Agent pipeline)

Completed:
- Phase 1: DB schema (execution_mode + ssa_agent_executions), ModeToggle component, Session PATCH API
- Phase 2: AgentPlannerService + AgentCoderService (streaming) + CodeRunnerService + R Docker /execute-code endpoint
- Phase 3: AgentCodePanel (3-step confirmation UI), SSE event handling (7 agent events), streaming code display
- Three-step confirmation pipeline: plan -> user confirm -> stream code -> user confirm -> execute R code -> results
- R Docker sandbox /execute-code endpoint with 120s timeout + block_helpers preloaded
- E2E dual-channel test script (8 tests)
- Updated R engine architecture doc (v1.5) and SSA module status doc (v4.0)

Technical details:
- AgentCoderService uses LLM streaming (chatStream) for real-time code generation feedback
- ReviewerAgent temporarily disabled, prioritizing Plan -> Code -> Execute flow
- CodeRunnerService wraps user code with auto data loading (df variable injection)
- Frontend handles agent_planning, agent_plan_ready, code_generating, code_generated, code_executing, code_result events
- ask_user mechanism used for plan and code confirmation steps

Files: 24 files (4 new services, 2 new components, 1 migration, 1 E2E test, 16 modified)
Made-with: Cursor

backend/src/modules/ssa/routes/chat.routes.ts

@@ -12,6 +12,7 @@
 
 import { FastifyInstance, FastifyRequest } from 'fastify';
 import { logger } from '../../../common/logging/index.js';
+import { prisma } from '../../../config/database.js';
 import { conversationService } from '../services/ConversationService.js';
 import { intentRouterService } from '../services/IntentRouterService.js';
 import { chatHandlerService } from '../services/ChatHandlerService.js';
@@ -114,6 +115,41 @@ export default async function chatRoutes(app: FastifyInstance) {
       }
       // ── H1 结束 ──
 
+      // 3. 读取 session 的执行模式
+      const session = await (prisma.ssaSession as any).findUnique({
+        where: { id: sessionId },
+        select: { executionMode: true },
+      });
+      const executionMode = (session?.executionMode as string) || 'qper';
+
+      // ── Agent 通道分流 ──
+      if (executionMode === 'agent') {
+        const placeholderMsgId = await conversationService.createAssistantPlaceholder(
+          conversationId, 'chat',
+        );
+
+        const metaEvent = JSON.stringify({
+          type: 'intent_classified',
+          intent: 'analyze',
+          confidence: 1,
+          source: 'agent_mode',
+          guardTriggered: false,
+        });
+        writer.write(`data: ${metaEvent}\n\n`);
+
+        const result = await chatHandlerService.handleAgentMode(
+          sessionId, conversationId, content.trim(), writer, placeholderMsgId,
+        );
+
+        logger.info('[SSA:Chat] Agent mode request completed', {
+          sessionId, success: result.success,
+        });
+
+        writer.end();
+        return;
+      }
+      // ── QPER 通道（现有逻辑） ──
+
       // 3. 意图分类
       const intentResult = await intentRouterService.classify(content.trim(), sessionId);