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/utils/data_loader.R

@@ -29,23 +29,59 @@ load_input_data <- function(input) {
     
     # 调试：打印原始数据结构
     message(glue("[DataLoader] 原始数据类型: {class(raw_data)}"))
-    message(glue("[DataLoader] 原始数据字段: {paste(names(raw_data), collapse=', ')}"))
+    message(glue("[DataLoader] 原始数据长度: {length(raw_data)}"))
     
     # 安全转换：处理不同的 JSON 解析结果
     if (is.data.frame(raw_data)) {
+      # 已经是 data.frame
       df <- raw_data
-    } else if (is.list(raw_data)) {
-      # JSON 对象 {"col1": [...], "col2": [...]} -> data.frame
-      # JSON 数组可能被解析为 list 而非 vector，需要先 unlist
-      df <- data.frame(
-        lapply(raw_data, function(x) {
-          if (is.list(x)) unlist(x) else x
-        }),
-        stringsAsFactors = FALSE
-      )
+      message("[DataLoader] 数据已是 data.frame")
+      
+    } else if (is.list(raw_data) && length(raw_data) > 0) {
+      # 检查是行格式还是列格式
+      first_elem <- raw_data[[1]]
+      
+      if (is.list(first_elem) && !is.null(names(first_elem))) {
+        # 行格式: [{"col1": val1, "col2": val2}, {...}, ...]
+        # 每个元素是一行数据
+        message("[DataLoader] 检测到行格式数据 (JSON array of objects)")
+        
+        # 使用 jsonlite 的 bind_rows 功能
+        df <- tryCatch({
+          # 方法1：使用 do.call + rbind.data.frame
+          df_list <- lapply(raw_data, function(row) {
+            # 将每一行转为 data.frame
+            as.data.frame(lapply(row, function(val) {
+              if (is.null(val)) NA else val
+            }), stringsAsFactors = FALSE)
+          })
+          do.call(rbind, df_list)
+        }, error = function(e) {
+          # 方法2：如果上面失败，尝试 jsonlite 转换
+          message(glue("[DataLoader] rbind 失败，尝试 jsonlite 转换: {e$message}"))
+          jsonlite::fromJSON(jsonlite::toJSON(raw_data), flatten = TRUE)
+        })
+        
+      } else if (!is.null(names(raw_data))) {
+        # 列格式: {"col1": [...], "col2": [...]}
+        message("[DataLoader] 检测到列格式数据 (JSON object with arrays)")
+        df <- data.frame(
+          lapply(raw_data, function(x) {
+            if (is.list(x)) unlist(x) else x
+          }),
+          stringsAsFactors = FALSE
+        )
+        
+      } else {
+        # 未知格式
+        message(glue("[DataLoader] 未知数据格式，first_elem class: {class(first_elem)}"))
+        stop(make_error(ERROR_CODES$E100_INTERNAL_ERROR,
+                        details = "无法识别的数据格式"))
+      }
+      
     } else {
       stop(make_error(ERROR_CODES$E100_INTERNAL_ERROR,
-                      details = paste("无法解析的数据类型:", class(raw_data))))
+                      details = paste("无法解析的数据类型:", class(raw_data), "或数据为空")))
     }
     
     message(glue("[DataLoader] 转换后: {nrow(df)} 行, {ncol(df)} 列, 列名: {paste(names(df), collapse=', ')}"))

r-statistics-service/utils/guardrails.R

@@ -114,3 +114,129 @@ run_guardrail_chain <- function(guardrail_results) {
     warnings = warnings
   ))
 }
+
+# ========== JIT 护栏接口（Phase 2A） ==========
+# 用于 WorkflowExecutor 在执行核心工具前调用
+
+#' JIT 护栏检查：执行核心统计前检验假设
+#' @param df 数据框
+#' @param tool_code 目标工具代码
+#' @param params 工具参数（group_var, value_var 等）
+#' @return list(checks, suggested_tool, can_proceed)
+run_jit_guardrails <- function(df, tool_code, params) {
+  checks <- list()
+  suggested_tool <- tool_code
+  can_proceed <- TRUE
+  
+  # 根据工具类型执行不同的检验
+  if (tool_code %in% c("ST_T_TEST_IND", "ST_MANN_WHITNEY")) {
+    # 独立样本比较：需要正态性 + 方差齐性检验
+    group_var <- params$group_var
+    value_var <- params$value_var
+    
+    if (!is.null(group_var) && !is.null(value_var)) {
+      groups <- unique(df[[group_var]])
+      
+      # 正态性检验（分组）
+      for (g in groups) {
+        vals <- df[df[[group_var]] == g, value_var]
+        if (length(vals) >= 3) {
+          norm_result <- check_normality(vals, alpha = 0.05)
+          checks <- c(checks, list(list(
+            check_name = glue("正态性检验 (组: {g})"),
+            passed = norm_result$passed,
+            p_value = norm_result$p_value,
+            recommendation = if (norm_result$passed) "满足正态性" else "建议使用非参数方法"
+          )))
+          
+          if (!norm_result$passed && tool_code == "ST_T_TEST_IND") {
+            suggested_tool <- "ST_MANN_WHITNEY"
+          }
+        }
+      }
+      
+      # 方差齐性检验
+      if (length(groups) == 2) {
+        tryCatch({
+          homo_result <- check_homogeneity(df, group_var, value_var, alpha = 0.05)
+          checks <- c(checks, list(list(
+            check_name = "方差齐性检验 (Levene)",
+            passed = homo_result$passed,
+            p_value = homo_result$p_value,
+            recommendation = if (homo_result$passed) "方差齐性满足" else "建议使用 Welch 校正"
+          )))
+        }, error = function(e) {
+          message("方差齐性检验失败: ", e$message)
+        })
+      }
+    }
+    
+  } else if (tool_code == "ST_T_TEST_PAIRED") {
+    # 配对检验：需要差值正态性检验
+    before_var <- params$before_var
+    after_var <- params$after_var
+    
+    if (!is.null(before_var) && !is.null(after_var)) {
+      diff_vals <- df[[after_var]] - df[[before_var]]
+      diff_vals <- diff_vals[!is.na(diff_vals)]
+      
+      if (length(diff_vals) >= 3) {
+        norm_result <- check_normality(diff_vals, alpha = 0.05)
+        checks <- c(checks, list(list(
+          check_name = "差值正态性检验",
+          passed = norm_result$passed,
+          p_value = norm_result$p_value,
+          recommendation = if (norm_result$passed) "差值满足正态性" else "建议使用 Wilcoxon 符号秩检验"
+        )))
+        
+        if (!norm_result$passed) {
+          suggested_tool <- "Wilcoxon signed-rank test"
+        }
+      }
+    }
+    
+  } else if (tool_code == "ST_CORRELATION") {
+    # 相关分析：需要双变量正态性检验
+    var_x <- params$var_x
+    var_y <- params$var_y
+    
+    if (!is.null(var_x) && !is.null(var_y)) {
+      x_vals <- df[[var_x]][!is.na(df[[var_x]])]
+      y_vals <- df[[var_y]][!is.na(df[[var_y]])]
+      
+      if (length(x_vals) >= 3) {
+        norm_x <- check_normality(x_vals, alpha = 0.05)
+        checks <- c(checks, list(list(
+          check_name = glue("正态性检验 ({var_x})"),
+          passed = norm_x$passed,
+          p_value = norm_x$p_value,
+          recommendation = if (norm_x$passed) "满足正态性" else "建议使用 Spearman 秩相关"
+        )))
+      }
+      
+      if (length(y_vals) >= 3) {
+        norm_y <- check_normality(y_vals, alpha = 0.05)
+        checks <- c(checks, list(list(
+          check_name = glue("正态性检验 ({var_y})"),
+          passed = norm_y$passed,
+          p_value = norm_y$p_value,
+          recommendation = if (norm_y$passed) "满足正态性" else "建议使用 Spearman 秩相关"
+        )))
+        
+        if (!norm_x$passed || !norm_y$passed) {
+          suggested_tool <- "ST_CORRELATION (Spearman)"
+        }
+      }
+    }
+  }
+  
+  # 汇总
+  all_passed <- all(sapply(checks, function(c) c$passed))
+  
+  return(list(
+    checks = checks,
+    suggested_tool = suggested_tool,
+    can_proceed = TRUE,  # 即使检验不通过也允许继续，由用户/LLM 决定
+    all_checks_passed = all_passed
+  ))
+}