Planner Autonomy: выбрать comparison chain для явного bidirectional graph

llm_normalizer/backend/dist/services/assistantMcpDiscoveryPlanner.js

@@ -496,16 +496,19 @@ function recipeFor(input) {
         });
     }
     if (graphFactFamily === "value_flow") {
-        if (dataNeedGraph?.comparison_need === "incoming_vs_outgoing" && !hasSubjectCandidates(dataNeedGraph)) {
+        if (dataNeedGraph?.comparison_need === "incoming_vs_outgoing") {
             pushUnique(axes, "amount");
             pushUnique(axes, "coverage_target");
             if (requestedAggregationAxis === "month" || graphAggregation === "by_month") {
                 pushUnique(axes, "calendar_month");
             }
             const template = (0, assistantMcpCatalogIndex_1.getAssistantMcpCatalogChainTemplate)("value_flow_comparison");
+            const fallbackPrimitives = hasSubjectCandidates(dataNeedGraph)
+                ? ["resolve_entity_reference", ...template.fallback_primitives]
+                : template.fallback_primitives;
             const primitiveSelection = selectPrimitivesFromGraphAndCatalog({
                 dataNeedGraph,
-                fallbackPrimitives: template.fallback_primitives,
+                fallbackPrimitives,
                 requiredAxes: axes,
                 metadataSurface: input.metadataSurface,
                 actionFamily: action,

llm_normalizer/backend/src/services/assistantMcpDiscoveryPlanner.ts

@@ -703,16 +703,19 @@ function recipeFor(input: AssistantMcpDiscoveryPlannerInput): PlannerRecipe {
   }
 
   if (graphFactFamily === "value_flow") {
-    if (dataNeedGraph?.comparison_need === "incoming_vs_outgoing" && !hasSubjectCandidates(dataNeedGraph)) {
+    if (dataNeedGraph?.comparison_need === "incoming_vs_outgoing") {
       pushUnique(axes, "amount");
       pushUnique(axes, "coverage_target");
       if (requestedAggregationAxis === "month" || graphAggregation === "by_month") {
         pushUnique(axes, "calendar_month");
       }
       const template = getAssistantMcpCatalogChainTemplate("value_flow_comparison");
+      const fallbackPrimitives = hasSubjectCandidates(dataNeedGraph)
+        ? (["resolve_entity_reference", ...template.fallback_primitives] as AssistantMcpDiscoveryPrimitive[])
+        : template.fallback_primitives;
       const primitiveSelection = selectPrimitivesFromGraphAndCatalog({
         dataNeedGraph,
-        fallbackPrimitives: template.fallback_primitives,
+        fallbackPrimitives,
         requiredAxes: axes,
         metadataSurface: input.metadataSurface,
         actionFamily: action,

llm_normalizer/backend/tests/assistantMcpDiscoveryPlanner.test.ts

@@ -520,7 +520,7 @@ describe("assistant MCP discovery planner", () => {
     expect(result.reason_codes).not.toContain("planner_selected_movement_from_confirmed_metadata_surface_ref");
   });
 
-  it("can select value-flow chain from data need graph even when turn meaning family is still under-specified", () => {
+  it("can select bidirectional value-flow comparison from data need graph even when turn meaning family is still under-specified", () => {
     const result = planAssistantMcpDiscovery({
       dataNeedGraph: {
         schema_version: "assistant_data_need_graph_v1",
@@ -552,23 +552,18 @@ describe("assistant MCP discovery planner", () => {
     });
 
     expect(result.planner_status).toBe("ready_for_execution");
-    expect(result.selected_chain_id).toBe("value_flow");
-    expect(result.proposed_primitives).toEqual([
-      "resolve_entity_reference",
-      "query_movements",
-      "aggregate_by_axis",
-      "probe_coverage"
-    ]);
+    expect(result.selected_chain_id).toBe("value_flow_comparison");
+    expect(result.proposed_primitives).toEqual(["resolve_entity_reference", "query_movements", "probe_coverage"]);
     expect(result.required_axes).toEqual([
       "counterparty",
       "period",
-      "aggregate_axis",
       "amount",
       "coverage_target",
       "calendar_month"
     ]);
-    expect(result.reason_codes).toContain("planner_selected_monthly_value_flow_from_data_need_graph");
-    expect(result.reason_codes).toContain("planner_instantiated_catalog_chain_template_value_flow");
+    expect(result.reason_codes).toContain("planner_selected_bidirectional_value_flow_comparison_from_data_need_graph");
+    expect(result.reason_codes).toContain("planner_instantiated_catalog_chain_template_value_flow_comparison");
+    expect(result.catalog_chain_template_matches[0]).toBe("value_flow_comparison");
   });
 
   it("does not collapse a ranking-shaped value graph into entity-resolution just because no subject is preselected", () => {