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/correlation.R

@@ -195,12 +195,50 @@ ggplot(df, aes(x = .data[[var_x]], y = .data[[var_y]])) +
   if (final_method == "pearson" && !is.null(result$conf.int)) {
     output_results$conf_int <- as.numeric(result$conf.int)
   }
-  
+
+  # ===== 构建 report_blocks =====
+  blocks <- list()
+
+  # Block 1: 分析概况
+  blocks[[length(blocks) + 1]] <- make_kv_block(list(
+    "变量 X" = var_x,
+    "变量 Y" = var_y,
+    "样本量" = as.character(n),
+    "分析方法" = final_method
+  ), title = "分析概况")
+
+  # Block 2: 相关分析结果表
+  ci_str <- if (final_method == "pearson" && !is.null(result$conf.int)) {
+    sprintf("[%.3f, %.3f]", result$conf.int[1], result$conf.int[2])
+  } else {
+    "-"
+  }
+  corr_headers <- c("r 值", "P 值", "95% CI", "相关强度")
+  corr_rows <- list(c(
+    as.character(round(r_value, 4)),
+    format_p_value(p_value),
+    ci_str,
+    r_interpretation
+  ))
+  blocks[[length(blocks) + 1]] <- make_table_block(corr_headers, corr_rows, title = "相关分析结果")
+
+  # Block 3: 散点图
+  if (!is.null(plot_base64)) {
+    blocks[[length(blocks) + 1]] <- make_image_block(plot_base64, title = "散点图", alt = paste(var_x, "vs", var_y))
+  }
+
+  # Block 4: 结论摘要
+  conclusion_text <- glue(
+    "**{var_x}** 与 **{var_y}** 的 {final_method} 相关系数为 r = {round(r_value, 3)} (P {format_p_value(p_value)})，相关强度为 **{r_interpretation}**。"
+  )
+  blocks[[length(blocks) + 1]] <- make_markdown_block(conclusion_text, title = "结论摘要")
+
   return(list(
     status = "success",
     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)