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_paired.R

@@ -226,7 +226,98 @@ ggplot(df_long, aes(x = time, y = value, group = id)) +
   theme_minimal() +
   labs(title = "Paired Comparison")
 ')
-  
+
+  # ===== 构建 report_blocks =====
+  d <- output_results$descriptive
+  blocks <- list()
+
+  # Block 1: 样本概况
+  blocks[[length(blocks) + 1]] <- make_kv_block(
+    title = "样本概况",
+    items = list(
+      list(key = paste0(before_var, " (n)"), value = as.character(d$before$n)),
+      list(key = paste0(before_var, " Mean"), value = as.character(d$before$mean)),
+      list(key = paste0(before_var, " SD"), value = as.character(d$before$sd)),
+      list(key = paste0(before_var, " Median"), value = as.character(d$before$median)),
+      list(key = paste0(after_var, " (n)"), value = as.character(d$after$n)),
+      list(key = paste0(after_var, " Mean"), value = as.character(d$after$mean)),
+      list(key = paste0(after_var, " SD"), value = as.character(d$after$sd)),
+      list(key = paste0(after_var, " Median"), value = as.character(d$after$median)),
+      list(key = "差值 Mean", value = as.character(d$difference$mean)),
+      list(key = "差值 SD", value = as.character(d$difference$sd))
+    )
+  )
+
+  # Block 2: 检验结果表格（根据 use_wilcoxon 区分）
+  if (use_wilcoxon) {
+    blocks[[length(blocks) + 1]] <- make_table_block(
+      title = "Wilcoxon 符号秩检验结果",
+      headers = c("统计量 V", "P 值", "效应量 r", "效应量解释"),
+      rows = list(list(
+        round(as.numeric(output_results$statistic), 4),
+        format_p_value(output_results$p_value),
+        round(output_results$effect_size$r, 4),
+        output_results$effect_size$interpretation
+      )),
+      footnote = method_used
+    )
+  } else {
+    ci_str <- if (length(output_results$conf_int) >= 2) {
+      sprintf("[%.4f, %.4f]", output_results$conf_int[1], output_results$conf_int[2])
+    } else {
+      "—"
+    }
+    blocks[[length(blocks) + 1]] <- make_table_block(
+      title = "配对 T 检验结果",
+      headers = c("t", "df", "P 值", "95% CI", "Cohen's d", "效应量解释"),
+      rows = list(list(
+        round(as.numeric(output_results$statistic), 4),
+        round(as.numeric(output_results$df), 2),
+        format_p_value(output_results$p_value),
+        ci_str,
+        round(output_results$effect_size$cohens_d, 4),
+        output_results$effect_size$interpretation
+      )),
+      footnote = method_used
+    )
+  }
+
+  # Block 3: 配对比较图
+  if (!is.null(plot_base64)) {
+    blocks[[length(blocks) + 1]] <- make_image_block(
+      base64_data = plot_base64,
+      title = paste0("配对比较: ", before_var, " vs ", after_var),
+      alt = paste("配对比较图：", before_var, "与", after_var)
+    )
+  }
+
+  # Block 4: 结论摘要
+  sig <- if (output_results$p_value < 0.05) "存在统计学显著差异" else "差异无统计学意义"
+  if (use_wilcoxon) {
+    concl <- paste0(
+      "配对样本 **", before_var, "** 与 **", after_var, "** 的比较（", method_used, "）：",
+      "V = ", round(as.numeric(output_results$statistic), 3),
+      "，P ", format_p_value(output_results$p_value),
+      "，效应量 r = ", round(output_results$effect_size$r, 3),
+      "（", output_results$effect_size$interpretation, "）。",
+      sig, "。"
+    )
+  } else {
+    concl <- paste0(
+      "配对样本 **", before_var, "** 与 **", after_var, "** 的比较（", method_used, "）：",
+      "t = ", round(as.numeric(output_results$statistic), 3),
+      "，df = ", round(as.numeric(output_results$df), 1),
+      "，P ", format_p_value(output_results$p_value),
+      "，Cohen's d = ", round(output_results$effect_size$cohens_d, 3),
+      "（", output_results$effect_size$interpretation, "）。",
+      sig, "。"
+    )
+  }
+  blocks[[length(blocks) + 1]] <- make_markdown_block(
+    title = "结果摘要",
+    content = concl
+  )
+
   # ===== 返回结果 =====
   log_add("分析完成")
   
@@ -235,6 +326,7 @@ ggplot(df_long, aes(x = time, y = value, group = id)) +
     message = "分析完成",
     warnings = if (length(warnings_list) > 0) warnings_list else NULL,
     results = output_results,
+    report_blocks = blocks,
     plots = if (!is.null(plot_base64)) list(plot_base64) else list(),
     trace_log = logs,
     reproducible_code = as.character(reproducible_code)