feat(ssa): Complete Phase I-IV intelligent dialogue and tool system development

Phase I - Session Blackboard + READ Layer:
- SessionBlackboardService with Postgres-Only cache
- DataProfileService for data overview generation
- PicoInferenceService for LLM-driven PICO extraction
- Frontend DataContextCard and VariableDictionaryPanel
- E2E tests: 31/31 passed

Phase II - Conversation Layer LLM + Intent Router:
- ConversationService with SSE streaming
- IntentRouterService (rule-first + LLM fallback, 6 intents)
- SystemPromptService with 6-segment dynamic assembly
- TokenTruncationService for context management
- ChatHandlerService as unified chat entry
- Frontend SSAChatPane and useSSAChat hook
- E2E tests: 38/38 passed

Phase III - Method Consultation + AskUser Standardization:
- ToolRegistryService with Repository Pattern
- MethodConsultService with DecisionTable + LLM enhancement
- AskUserService with global interrupt handling
- Frontend AskUserCard component
- E2E tests: 13/13 passed

Phase IV - Dialogue-Driven Analysis + QPER Integration:
- ToolOrchestratorService (plan/execute/report)
- analysis_plan SSE event for WorkflowPlan transmission
- Dual-channel confirmation (ask_user card + workspace button)
- PICO as optional hint for LLM parsing
- E2E tests: 25/25 passed

R Statistics Service:
- 5 new R tools: anova_one, baseline_table, fisher, linear_reg, wilcoxon
- Enhanced guardrails and block helpers
- Comprehensive test suite (run_all_tools_test.js)

Documentation:
- Updated system status document (v5.9)
- Updated SSA module status and development plan (v1.8)

Total E2E: 107/107 passed (Phase I: 31, Phase II: 38, Phase III: 13, Phase IV: 25)

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

r-statistics-service/utils/block_helpers.R

@@ -21,7 +21,7 @@ make_markdown_block <- function(content, title = NULL) {
 #' @param title 可选表格标题
 #' @param footnote 可选脚注（如方法说明）
 #' @return block list
-make_table_block <- function(headers, rows, title = NULL, footnote = NULL) {
+make_table_block <- function(headers, rows, title = NULL, footnote = NULL, metadata = NULL) {
   block <- list(
     type = "table",
     headers = as.list(headers),
@@ -29,6 +29,7 @@ make_table_block <- function(headers, rows, title = NULL, footnote = NULL) {
   )
   if (!is.null(title)) block$title <- title
   if (!is.null(footnote)) block$footnote <- footnote
+  if (!is.null(metadata)) block$metadata <- metadata
   block
 }
 

r-statistics-service/utils/guardrails.R

@@ -228,6 +228,98 @@ run_jit_guardrails <- function(df, tool_code, params) {
         }
       }
     }
+
+  } else if (tool_code == "ST_ANOVA_ONE") {
+    group_var <- params$group_var
+    value_var <- params$value_var
+
+    if (!is.null(group_var) && !is.null(value_var)) {
+      groups <- unique(df[[group_var]])
+
+      for (g in groups) {
+        vals <- df[df[[group_var]] == g, value_var]
+        vals <- vals[!is.na(vals)]
+        if (length(vals) >= 3) {
+          norm_result <- check_normality(vals, alpha = 0.05)
+          checks <- c(checks, list(list(
+            check_name = glue("正态性检验 (组: {g})"),
+            passed = norm_result$passed,
+            p_value = norm_result$p_value,
+            recommendation = if (norm_result$passed) "满足正态性" else "建议使用 Kruskal-Wallis"
+          )))
+
+          if (!norm_result$passed) {
+            suggested_tool <- "Kruskal-Wallis (内置于 ST_ANOVA_ONE)"
+          }
+        }
+      }
+
+      tryCatch({
+        homo_result <- check_homogeneity(df, group_var, value_var, alpha = 0.05)
+        checks <- c(checks, list(list(
+          check_name = "方差齐性检验 (Levene)",
+          passed = homo_result$passed,
+          p_value = homo_result$p_value,
+          recommendation = if (homo_result$passed) "方差齐性满足" else "建议使用 Welch ANOVA"
+        )))
+      }, error = function(e) {
+        message("方差齐性检验失败: ", e$message)
+      })
+    }
+
+  } else if (tool_code == "ST_WILCOXON") {
+    before_var <- params$before_var
+    after_var <- params$after_var
+
+    if (!is.null(before_var) && !is.null(after_var)) {
+      diff_vals <- df[[after_var]] - df[[before_var]]
+      diff_vals <- diff_vals[!is.na(diff_vals)]
+
+      checks <- c(checks, list(list(
+        check_name = "配对样本量检查",
+        passed = length(diff_vals) >= 5,
+        recommendation = if (length(diff_vals) >= 5) "样本量充足" else "配对样本量不足"
+      )))
+    }
+
+  } else if (tool_code %in% c("ST_FISHER", "ST_CHI_SQUARE")) {
+    var1 <- params$var1
+    var2 <- params$var2
+
+    if (!is.null(var1) && !is.null(var2)) {
+      ct <- table(df[[var1]], df[[var2]])
+      expected <- tryCatch(chisq.test(ct)$expected, error = function(e) NULL)
+
+      if (!is.null(expected)) {
+        low_pct <- sum(expected < 5) / length(expected)
+        checks <- c(checks, list(list(
+          check_name = "期望频数检查",
+          passed = low_pct <= 0.2,
+          recommendation = if (low_pct <= 0.2) "期望频数满足卡方检验条件" else "建议使用 Fisher 精确检验"
+        )))
+
+        if (low_pct > 0.2 && tool_code == "ST_CHI_SQUARE") {
+          suggested_tool <- "ST_FISHER"
+        }
+      }
+    }
+
+  } else if (tool_code == "ST_LINEAR_REG") {
+    outcome_var <- params$outcome_var
+    predictors <- params$predictors
+
+    if (!is.null(outcome_var)) {
+      vals <- df[[outcome_var]][!is.na(df[[outcome_var]])]
+      if (length(vals) >= 3) {
+        norm_result <- check_normality(vals, alpha = 0.05)
+        checks <- c(checks, list(list(
+          check_name = glue("结局变量正态性 ({outcome_var})"),
+          passed = norm_result$passed,
+          p_value = norm_result$p_value,
+          recommendation = if (norm_result$passed) "满足正态性" else "结局变量分布偏态，结果需谨慎解读"
+        )))
+      }
+    }
   }
   
   # 汇总