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/prisma/schema.prisma

@@ -2480,13 +2480,15 @@ model SsaSession {
   dataPayload   Json?    @map("data_payload")   /// 真实数据（仅R可见）
   dataOssKey    String?  @map("data_oss_key")   /// OSS 存储 key（大数据）
   dataProfile   Json?    @map("data_profile")   /// 🆕 Python 生成的 DataProfile（Phase 2A）
+  executionMode String   @default("qper") @map("execution_mode") /// qper | agent
   status        String   @default("active")     /// active | consult | completed | error
   createdAt     DateTime @default(now()) @map("created_at")
   updatedAt     DateTime @updatedAt @map("updated_at")
   
-  messages      SsaMessage[]
-  executionLogs SsaExecutionLog[]
-  workflows     SsaWorkflow[]                   /// 🆕 多步骤流程（Phase 2A）
+  messages        SsaMessage[]
+  executionLogs   SsaExecutionLog[]
+  workflows       SsaWorkflow[]                   /// 🆕 多步骤流程（Phase 2A）
+  agentExecutions SsaAgentExecution[]              /// Agent 模式执行记录
   
   @@index([userId], map: "idx_ssa_session_user")
   @@index([status], map: "idx_ssa_session_status")
@@ -2494,6 +2496,30 @@ model SsaSession {
   @@schema("ssa_schema")
 }
 
+/// SSA Agent 执行记录（LLM 代码生成通道）
+model SsaAgentExecution {
+  id              String   @id @default(uuid())
+  sessionId       String   @map("session_id")
+  query           String
+  planText        String?  @map("plan_text")
+  generatedCode   String?  @map("generated_code")
+  reviewResult    Json?    @map("review_result")
+  executionResult Json?    @map("execution_result")
+  reportBlocks    Json?    @map("report_blocks")
+  retryCount      Int      @default(0) @map("retry_count")
+  status          String   @default("pending")      /// pending | planning | coding | reviewing | executing | completed | error
+  errorMessage    String?  @map("error_message")
+  durationMs      Int?     @map("duration_ms")
+  createdAt       DateTime @default(now()) @map("created_at")
+  updatedAt       DateTime @updatedAt @map("updated_at")
+
+  session         SsaSession @relation(fields: [sessionId], references: [id], onDelete: Cascade)
+
+  @@index([sessionId], map: "idx_ssa_agent_exec_session")
+  @@map("ssa_agent_executions")
+  @@schema("ssa_schema")
+}
+
 /// SSA 消息记录
 model SsaMessage {
   id            String   @id @default(uuid())