feat(ssa): Complete Phase 2A frontend integration - multi-step workflow end-to-end

Phase 2A: WorkflowPlannerService, WorkflowExecutorService, Python data quality, 6 bug fixes, DescriptiveResultView, multi-step R code/Word export, MVP UI reuse. V11 UI: Gemini-style, multi-task, single-page scroll, Word export. Architecture: Block-based rendering consensus (4 block types). New R tools: chi_square, correlation, descriptive, logistic_binary, mann_whitney, t_test_paired. Docs: dev summary, block-based plan, status updates, task list v2.0.

Co-authored-by: Cursor <cursoragent@cursor.com>

r-statistics-service/plumber.R

@@ -115,6 +115,57 @@ function() {
   )
 }
 
+#* JIT Guardrails Check
+#* @post /api/v1/guardrails/jit
+#* @serializer unboxedJSON
+function(req) {
+  tryCatch({
+    input <- jsonlite::fromJSON(req$postBody, simplifyVector = FALSE)
+    
+    # 必需参数
+    tool_code <- input$tool_code
+    params <- input$params
+    
+    if (is.null(tool_code)) {
+      return(list(
+        status = "error",
+        error_code = "E400",
+        message = "Missing tool_code parameter"
+      ))
+    }
+    
+    # 加载数据
+    df <- tryCatch(
+      load_input_data(input),
+      error = function(e) {
+        return(NULL)
+      }
+    )
+    
+    if (is.null(df)) {
+      return(list(
+        status = "error",
+        error_code = "E100",
+        message = "Failed to load data for guardrail checks"
+      ))
+    }
+    
+    # 执行 JIT 护栏检查
+    result <- run_jit_guardrails(df, tool_code, params)
+    
+    return(list(
+      status = "success",
+      checks = result$checks,
+      suggested_tool = result$suggested_tool,
+      can_proceed = result$can_proceed,
+      all_checks_passed = result$all_checks_passed
+    ))
+    
+  }, error = function(e) {
+    return(map_r_error(e$message))
+  })
+}
+
 #* 执行统计工具
 #* @post /api/v1/skills/<tool_code>
 #* @param tool_code:str 工具代码（如 ST_T_TEST_IND）