feat(ssa): Complete QPER architecture - Query, Planner, Execute, Reflection layers

Implement the full QPER intelligent analysis pipeline:

- Phase E+: Block-based standardization for all 7 R tools, DynamicReport renderer, Word export enhancement

- Phase Q: LLM intent parsing with dynamic Zod validation against real column names, ClarificationCard component, DataProfile is_id_like tagging

- Phase P: ConfigLoader with Zod schema validation and hot-reload API, DecisionTableService (4-dimension matching), FlowTemplateService with EPV protection, PlannedTrace audit output

- Phase R: ReflectionService with statistical slot injection, sensitivity analysis conflict rules, ConclusionReport with section reveal animation, conclusion caching API, graceful R error classification

End-to-end test: 40/40 passed across two complete analysis scenarios.

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

r-statistics-service/tools/descriptive.R

@@ -199,7 +199,83 @@ if (any(categorical_vars)) {{
   
   # ===== 返回结果 =====
   log_add("分析完成")
-  
+
+  # ===== 构建 report_blocks =====
+  blocks <- list()
+
+  # Block 1: 数据概况
+  kv_items <- list(
+    "总样本量" = as.character(summary_stats$n_total),
+    "变量数" = as.character(summary_stats$n_variables),
+    "数值变量数" = as.character(summary_stats$n_numeric),
+    "分类变量数" = as.character(summary_stats$n_categorical)
+  )
+  if (!is.null(groups)) {
+    kv_items$group_var <- group_var
+    kv_items$groups <- paste(sapply(summary_stats$groups, function(g) paste0(g$name, "(n=", g$n, ")")), collapse = ", ")
+  }
+  blocks[[length(blocks) + 1]] <- make_kv_block(kv_items, title = "数据概况")
+
+  # Block 2: 数值变量汇总表
+  numeric_vars <- names(results_list)[sapply(results_list, function(x) {
+    if (is.list(x) && !is.null(x$type)) x$type == "numeric" else FALSE
+  })]
+  if (length(numeric_vars) > 0) {
+    if (is.null(groups)) {
+      num_headers <- c("变量名", "n", "mean", "sd", "median", "Q1", "Q3", "min", "max")
+      num_rows <- lapply(numeric_vars, function(v) {
+        s <- results_list[[v]]
+        c(v, as.character(s$n), as.character(s$mean), as.character(s$sd),
+          as.character(s$median), as.character(s$q1), as.character(s$q3),
+          as.character(s$min), as.character(s$max))
+      })
+    } else {
+      num_headers <- c("变量名", as.character(groups))
+      num_rows <- lapply(numeric_vars, function(v) {
+        s <- results_list[[v]]
+        row <- c(v)
+        for (g in groups) {
+          gs <- s$by_group[[as.character(g)]]
+          row <- c(row, if (!is.null(gs$formatted)) gs$formatted else "-")
+        }
+        row
+      })
+    }
+    blocks[[length(blocks) + 1]] <- make_table_block(num_headers, num_rows, title = "数值变量汇总表")
+  }
+
+  # Block 3: 分类变量汇总表
+  cat_vars <- names(results_list)[sapply(results_list, function(x) {
+    if (is.list(x) && !is.null(x$type)) x$type == "categorical" else FALSE
+  })]
+  if (length(cat_vars) > 0) {
+    cat_headers <- c("变量名", "水平", "n", "百分比")
+    cat_rows <- list()
+    for (v in cat_vars) {
+      s <- results_list[[v]]
+      if (is.null(groups)) {
+        for (lev in s$levels) {
+          cat_rows[[length(cat_rows) + 1]] <- c(v, lev$level, as.character(lev$n), paste0(lev$pct, "%"))
+        }
+      } else {
+        for (g in groups) {
+          gs <- s$by_group[[as.character(g)]]
+          for (lev in gs$levels) {
+            cat_rows[[length(cat_rows) + 1]] <- c(paste0(v, " (", g, ")"), lev$level, as.character(lev$n), paste0(lev$pct, "%"))
+          }
+        }
+      }
+    }
+    if (length(cat_rows) > 0) {
+      blocks[[length(blocks) + 1]] <- make_table_block(cat_headers, cat_rows, title = "分类变量汇总表")
+    }
+  }
+
+  # Block 4+: 各图表
+  for (i in seq_along(plots)) {
+    blocks[[length(blocks) + 1]] <- make_image_block(plots[[i]], title = paste0("图表 ", i), alt = paste0("描述性统计图 ", i))
+  }
+
   return(list(
     status = "success",
     message = "分析完成",
@@ -208,6 +284,7 @@ if (any(categorical_vars)) {{
       summary = summary_stats,
       variables = results_list
     ),
+    report_blocks = blocks,
     plots = plots,
     trace_log = logs,
     reproducible_code = as.character(reproducible_code)