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/chi_square.R

@@ -213,6 +213,60 @@ cat("Cramer V =", round(cramers_v, 3), "\\n")
 mosaicplot(contingency_table, main = "Mosaic Plot", color = TRUE)
 ')
   
+  # ===== 构建 report_blocks =====
+  # Block 1: 列联表
+  table_headers <- c(var1, as.character(colnames(contingency_table)))
+  table_rows <- lapply(seq_len(nrow(contingency_table)), function(i) {
+    c(as.character(rownames(contingency_table)[i]), as.character(contingency_table[i, ]))
+  })
+  blocks <- list(
+    make_table_block(table_headers, table_rows, title = "列联表")
+  )
+
+  # Block 2: 检验结果键值对
+  if (use_fisher) {
+    kv_items <- list(
+      "方法" = method_used,
+      "P 值" = output_results$p_value_fmt
+    )
+    if (!is.null(output_results$odds_ratio)) {
+      kv_items[["比值比"]] <- as.character(round(as.numeric(output_results$odds_ratio), 4))
+    }
+    if (!is.null(output_results$conf_int)) {
+      kv_items[["95% 置信区间"]] <- sprintf("[%.4f, %.4f]", output_results$conf_int[1], output_results$conf_int[2])
+    }
+  } else {
+    kv_items <- list(
+      "方法" = method_used,
+      "χ² 统计量" = as.character(round(as.numeric(output_results$statistic), 4)),
+      "自由度" = as.character(output_results$df),
+      "P 值" = output_results$p_value_fmt,
+      "Cramér's V" = as.character(output_results$effect_size$cramers_v),
+      "效应量解释" = output_results$effect_size$interpretation
+    )
+  }
+  blocks[[length(blocks) + 1]] <- make_kv_block(kv_items, title = "检验结果")
+
+  # Block 3: 马赛克图（若有）
+  if (!is.null(plot_base64)) {
+    blocks[[length(blocks) + 1]] <- make_image_block(plot_base64, title = "马赛克图")
+  }
+
+  # Block 4: 结论摘要
+  p_val <- as.numeric(output_results$p_value)
+  conclusion <- if (p_val < 0.05) {
+    glue("在 α=0.05 水平下，{var1} 与 {var2} 之间存在显著关联（P {output_results$p_value_fmt}）。")
+  } else {
+    glue("在 α=0.05 水平下，未发现 {var1} 与 {var2} 之间的显著关联（P {output_results$p_value_fmt}）。")
+  }
+  if (!use_fisher) {
+    conclusion <- paste0(conclusion, " 效应量为", output_results$effect_size$interpretation,
+      "（Cramér's V = ", output_results$effect_size$cramers_v, "）。")
+  } else if (!is.null(output_results$odds_ratio)) {
+    conclusion <- paste0(conclusion, " 比值比 = ", round(as.numeric(output_results$odds_ratio), 4), "。")
+  }
+  blocks[[length(blocks) + 1]] <- make_markdown_block(conclusion, title = "结论摘要")
+
   # ===== 返回结果 =====
   log_add("分析完成")
   
@@ -221,6 +275,7 @@ mosaicplot(contingency_table, main = "Mosaic Plot", color = TRUE)
     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)