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/t_test_ind.R

@@ -180,6 +180,66 @@ ggplot(df, aes(x = .data[[group_var]], y = .data[[value_var]])) +
   labs(title = paste("Distribution of", value_var, "by", group_var))
 ')
   
+  # ===== 构建 report_blocks =====
+  log_add("构建 report_blocks")
+
+  blocks <- list()
+
+  # Block 1: 描述统计键值对
+  g1_label <- as.character(groups[1])
+  g2_label <- as.character(groups[2])
+
+  blocks[[length(blocks) + 1]] <- make_kv_block(
+    title = "样本概况",
+    items = list(
+      list(key = paste0(group_var, " = ", g1_label, " (n)"), value = as.character(length(g1_vals))),
+      list(key = paste0(group_var, " = ", g2_label, " (n)"), value = as.character(length(g2_vals))),
+      list(key = paste0(g1_label, " Mean ± SD"),
+           value = paste0(round(mean(g1_vals), 3), " \u00b1 ", round(sd(g1_vals), 3))),
+      list(key = paste0(g2_label, " Mean ± SD"),
+           value = paste0(round(mean(g2_vals), 3), " \u00b1 ", round(sd(g2_vals), 3)))
+    )
+  )
+
+  # Block 2: 检验结果表格
+  blocks[[length(blocks) + 1]] <- make_table_block(
+    title = "独立样本 T 检验结果",
+    headers = c("统计量", "自由度", "P 值", "95% CI 下限", "95% CI 上限", "均值差"),
+    rows = list(
+      list(
+        round(as.numeric(result$statistic), 4),
+        round(as.numeric(result$parameter), 2),
+        format_p_value(result$p.value),
+        round(result$conf.int[1], 4),
+        round(result$conf.int[2], 4),
+        round(diff(result$estimate), 4)
+      )
+    ),
+    footnote = result$method
+  )
+
+  # Block 3: 箱线图
+  if (!is.null(plot_base64)) {
+    blocks[[length(blocks) + 1]] <- make_image_block(
+      base64_data = plot_base64,
+      title = paste0(value_var, " by ", group_var),
+      alt = paste("箱线图：", value_var, "按", group_var, "分组")
+    )
+  }
+
+  # Block 4: 结论摘要
+  sig <- if (result$p.value < 0.05) "存在统计学显著差异" else "差异无统计学意义"
+  blocks[[length(blocks) + 1]] <- make_markdown_block(
+    title = "结果摘要",
+    content = paste0(
+      "两组 **", value_var, "** 的比较（", result$method, "）：",
+      "t = ", round(as.numeric(result$statistic), 3),
+      "，df = ", round(as.numeric(result$parameter), 1),
+      "，P ", format_p_value(result$p.value),
+      "。两组间", sig, "。"
+    )
+  )
+
   # ===== 返回结果 =====
   log_add("分析完成")
   
@@ -196,10 +256,11 @@ ggplot(df, aes(x = .data[[group_var]], y = .data[[value_var]])) +
       conf_int = as.numeric(result$conf.int),
       estimate = as.numeric(result$estimate),
       group_stats = list(
-        list(group = as.character(groups[1]), n = length(g1_vals), mean = mean(g1_vals), sd = sd(g1_vals)),
-        list(group = as.character(groups[2]), n = length(g2_vals), mean = mean(g2_vals), sd = sd(g2_vals))
+        list(group = g1_label, n = length(g1_vals), mean = mean(g1_vals), sd = sd(g1_vals)),
+        list(group = g2_label, n = length(g2_vals), mean = mean(g2_vals), sd = sd(g2_vals))
       )
     ),
+    report_blocks = blocks,
     plots = if (!is.null(plot_base64)) list(plot_base64) else list(),
     trace_log = logs,
     reproducible_code = as.character(reproducible_code)