ARCH: восстановить годовое покрытие MCP discovery помесячными пробами

2026-04-21 08:41:35 +03:00
parent 4baa54fe81
commit cd3315e06d
15 changed files with 834 additions and 94 deletions
@@ -168,6 +168,149 @@ function queryResultToProbeResult(primitiveId, result) {
        limitation: result.error
    };
 }
+function toCoverageAwareQueryResult(result, options = {}) {
+    if (!result) {
+        return null;
+    }
+    return {
+        ...result,
+        coverage_limited_by_probe_limit: options.coverageLimitedByProbeLimit ?? false,
+        coverage_recovered_by_period_chunking: options.coverageRecoveredByPeriodChunking ?? false,
+        period_chunking_granularity: options.periodChunkingGranularity ?? null,
+        period_chunk_count: options.periodChunkCount ?? 0
+    };
+}
+function monthWindowsForYear(year) {
+    const result = [];
+    for (let month = 0; month < 12; month += 1) {
+        const start = new Date(Date.UTC(Number(year), month, 1));
+        const end = new Date(Date.UTC(Number(year), month + 1, 0));
+        result.push({
+            period_from: `${start.getUTCFullYear()}-${String(start.getUTCMonth() + 1).padStart(2, "0")}-${String(start.getUTCDate()).padStart(2, "0")}`,
+            period_to: `${end.getUTCFullYear()}-${String(end.getUTCMonth() + 1).padStart(2, "0")}-${String(end.getUTCDate()).padStart(2, "0")}`
+        });
+    }
+    return result;
+}
+function periodWindowsForDateScope(dateScope) {
+    const yearMatch = dateScope?.match(/^(\d{4})$/);
+    if (yearMatch) {
+        return monthWindowsForYear(yearMatch[1]);
+    }
+    return [];
+}
+function mergeCoverageAwareQueryResults(results, options) {
+    const rawRows = results.flatMap((item) => item.raw_rows);
+    const rows = results.flatMap((item) => item.rows);
+    const errors = results.map((item) => toNonEmptyString(item.error)).filter((item) => Boolean(item));
+    return {
+        fetched_rows: results.reduce((sum, item) => sum + item.fetched_rows, 0),
+        matched_rows: results.reduce((sum, item) => sum + item.matched_rows, 0),
+        raw_rows: rawRows,
+        rows,
+        error: errors[0] ?? null,
+        coverage_limited_by_probe_limit: options.coverageLimitedByProbeLimit,
+        coverage_recovered_by_period_chunking: options.coverageRecoveredByPeriodChunking,
+        period_chunking_granularity: options.periodChunkingGranularity,
+        period_chunk_count: options.periodChunkCount
+    };
+}
+async function executeCoverageAwareValueFlowQuery(input) {
+    const queryLimitations = [];
+    const probeResults = [];
+    let executedProbeCount = 0;
+    const broadRecipePlan = input.recipePlanBuilder(input.baseFilters);
+    const broadResult = await input.deps.executeAddressMcpQuery({
+        query: broadRecipePlan.query,
+        limit: broadRecipePlan.limit,
+        account_scope: broadRecipePlan.account_scope
+    });
+    executedProbeCount += 1;
+    probeResults.push(queryResultToProbeResult(input.primitiveId, broadResult));
+    const broadCoverageLimited = !broadResult.error && broadResult.matched_rows >= input.maxRowsPerProbe;
+    if (broadResult.error) {
+        pushUnique(queryLimitations, broadResult.error);
+        return {
+            result: toCoverageAwareQueryResult(broadResult, {
+                coverageLimitedByProbeLimit: false
+            }),
+            probe_results: probeResults,
+            query_limitations: queryLimitations,
+            executed_probe_count: executedProbeCount
+        };
+    }
+    const periodWindows = periodWindowsForDateScope(input.dateScope);
+    if (!broadCoverageLimited || periodWindows.length === 0) {
+        return {
+            result: toCoverageAwareQueryResult(broadResult, {
+                coverageLimitedByProbeLimit: broadCoverageLimited
+            }),
+            probe_results: probeResults,
+            query_limitations: queryLimitations,
+            executed_probe_count: executedProbeCount
+        };
+    }
+    const requiredChunkProbeCount = periodWindows.length;
+    if (executedProbeCount + requiredChunkProbeCount > input.maxProbeCount) {
+        pushUnique(queryLimitations, "Requested period hit the MCP row limit, but the approved monthly recovery probe budget is smaller than the required subperiod count");
+        return {
+            result: toCoverageAwareQueryResult(broadResult, {
+                coverageLimitedByProbeLimit: true
+            }),
+            probe_results: probeResults,
+            query_limitations: queryLimitations,
+            executed_probe_count: executedProbeCount
+        };
+    }
+    const chunkResults = [];
+    let anyChunkLimited = false;
+    let anyChunkError = false;
+    for (const window of periodWindows) {
+        const chunkFilters = {
+            ...input.baseFilters,
+            period_from: window.period_from,
+            period_to: window.period_to
+        };
+        const chunkPlan = input.recipePlanBuilder(chunkFilters);
+        const chunkResult = await input.deps.executeAddressMcpQuery({
+            query: chunkPlan.query,
+            limit: chunkPlan.limit,
+            account_scope: chunkPlan.account_scope
+        });
+        executedProbeCount += 1;
+        probeResults.push(queryResultToProbeResult(input.primitiveId, chunkResult));
+        if (chunkResult.error) {
+            anyChunkError = true;
+            pushUnique(queryLimitations, chunkResult.error);
+            continue;
+        }
+        if (chunkResult.matched_rows >= input.maxRowsPerProbe) {
+            anyChunkLimited = true;
+        }
+        chunkResults.push(chunkResult);
+    }
+    if (chunkResults.length === 0 && anyChunkError) {
+        return {
+            result: toCoverageAwareQueryResult(broadResult, {
+                coverageLimitedByProbeLimit: true
+            }),
+            probe_results: probeResults,
+            query_limitations: queryLimitations,
+            executed_probe_count: executedProbeCount
+        };
+    }
+    return {
+        result: mergeCoverageAwareQueryResults(chunkResults, {
+            coverageLimitedByProbeLimit: anyChunkLimited || anyChunkError,
+            coverageRecoveredByPeriodChunking: true,
+            periodChunkingGranularity: "month",
+            periodChunkCount: periodWindows.length
+        }),
+        probe_results: probeResults,
+        query_limitations: queryLimitations,
+        executed_probe_count: executedProbeCount
+    };
+}
 function summarizeLifecycleRows(result) {
    if (result.error) {
        return null;
@@ -184,6 +327,9 @@ function summarizeValueFlowRows(result) {
    if (result.fetched_rows <= 0) {
        return "0 MCP value-flow rows fetched";
    }
+    if (result.coverage_recovered_by_period_chunking && result.period_chunking_granularity === "month") {
+        return `${result.period_chunk_count} monthly MCP value-flow probes fetched ${result.fetched_rows} rows total, ${result.matched_rows} matched value-flow scope after the broad probe hit the row limit`;
+    }
    return `${result.fetched_rows} MCP value-flow rows fetched, ${result.matched_rows} matched value-flow scope`;
 }
 function rowDateValue(row) {
@@ -370,7 +516,7 @@ function deriveBidirectionalValueFlowMonthBreakdown(input) {
        };
    });
 }
-function deriveValueFlow(result, counterparty, periodScope, direction, probeLimit, aggregationAxis) {
+function deriveValueFlow(result, counterparty, periodScope, direction, aggregationAxis) {
    if (!result || result.error || result.matched_rows <= 0) {
        return null;
    }
@@ -401,12 +547,14 @@ function deriveValueFlow(result, counterparty, periodScope, direction, probeLimi
        total_amount_human_ru: formatAmountHumanRu(totalAmount),
        first_movement_date: dates[0] ?? null,
        latest_movement_date: dates[dates.length - 1] ?? null,
-        coverage_limited_by_probe_limit: result.matched_rows >= probeLimit,
+        coverage_limited_by_probe_limit: result.coverage_limited_by_probe_limit,
+        coverage_recovered_by_period_chunking: result.coverage_recovered_by_period_chunking,
+        period_chunking_granularity: result.period_chunking_granularity,
        monthly_breakdown: deriveValueFlowMonthBreakdown(result, aggregationAxis),
        inference_basis: "sum_of_confirmed_1c_value_flow_rows"
    };
 }
-function deriveValueFlowSideSummary(result, probeLimit) {
+function deriveValueFlowSideSummary(result) {
    if (!result || result.error || result.matched_rows <= 0) {
        return {
            rows_matched: 0,
@@ -415,7 +563,9 @@ function deriveValueFlowSideSummary(result, probeLimit) {
            total_amount_human_ru: formatAmountHumanRu(0),
            first_movement_date: null,
            latest_movement_date: null,
-            coverage_limited_by_probe_limit: false
+            coverage_limited_by_probe_limit: false,
+            coverage_recovered_by_period_chunking: false,
+            period_chunking_granularity: null
        };
    }
    let totalAmount = 0;
@@ -438,12 +588,14 @@ function deriveValueFlowSideSummary(result, probeLimit) {
        total_amount_human_ru: formatAmountHumanRu(totalAmount),
        first_movement_date: dates[0] ?? null,
        latest_movement_date: dates[dates.length - 1] ?? null,
-        coverage_limited_by_probe_limit: result.matched_rows >= probeLimit
+        coverage_limited_by_probe_limit: result.coverage_limited_by_probe_limit,
+        coverage_recovered_by_period_chunking: result.coverage_recovered_by_period_chunking,
+        period_chunking_granularity: result.period_chunking_granularity
    };
 }
 function deriveBidirectionalValueFlow(input) {
-    const incoming = deriveValueFlowSideSummary(input.incomingResult, input.probeLimit);
-    const outgoing = deriveValueFlowSideSummary(input.outgoingResult, input.probeLimit);
+    const incoming = deriveValueFlowSideSummary(input.incomingResult);
+    const outgoing = deriveValueFlowSideSummary(input.outgoingResult);
    if (incoming.rows_with_amount <= 0 && outgoing.rows_with_amount <= 0) {
        return null;
    }
@@ -458,6 +610,8 @@ function deriveBidirectionalValueFlow(input) {
        net_amount_human_ru: formatAmountHumanRu(Math.abs(netAmount)),
        net_direction: netDirectionFromAmount(netAmount),
        coverage_limited_by_probe_limit: incoming.coverage_limited_by_probe_limit || outgoing.coverage_limited_by_probe_limit,
+        coverage_recovered_by_period_chunking: incoming.coverage_recovered_by_period_chunking || outgoing.coverage_recovered_by_period_chunking,
+        period_chunking_granularity: incoming.period_chunking_granularity ?? outgoing.period_chunking_granularity ?? null,
        monthly_breakdown: deriveBidirectionalValueFlowMonthBreakdown({
            incomingResult: input.incomingResult,
            outgoingResult: input.outgoingResult,
@@ -474,10 +628,14 @@ function summarizeBidirectionalValueFlowRows(input) {
    }
    const incomingSummary = incoming?.error
        ? "incoming value-flow query failed"
-        : `${incoming?.fetched_rows ?? 0} incoming value-flow rows fetched, ${incoming?.matched_rows ?? 0} matched`;
+        : incoming?.coverage_recovered_by_period_chunking && incoming.period_chunking_granularity === "month"
+            ? `${incoming.period_chunk_count} monthly incoming value-flow probes fetched ${incoming.fetched_rows} rows total, ${incoming.matched_rows} matched`
+            : `${incoming?.fetched_rows ?? 0} incoming value-flow rows fetched, ${incoming?.matched_rows ?? 0} matched`;
    const outgoingSummary = outgoing?.error
        ? "outgoing supplier-payout query failed"
-        : `${outgoing?.fetched_rows ?? 0} outgoing supplier-payout rows fetched, ${outgoing?.matched_rows ?? 0} matched`;
+        : outgoing?.coverage_recovered_by_period_chunking && outgoing.period_chunking_granularity === "month"
+            ? `${outgoing.period_chunk_count} monthly outgoing supplier-payout probes fetched ${outgoing.fetched_rows} rows total, ${outgoing.matched_rows} matched`
+            : `${outgoing?.fetched_rows ?? 0} outgoing supplier-payout rows fetched, ${outgoing?.matched_rows ?? 0} matched`;
    return `${incomingSummary}; ${outgoingSummary}`;
 }
 function buildLifecycleConfirmedFacts(result, counterparty) {
@@ -539,6 +697,9 @@ function buildValueFlowInferredFacts(derived) {
    else {
        facts.push("Counterparty value-flow total was calculated from confirmed 1C movement rows");
    }
+    if (derived.coverage_recovered_by_period_chunking && derived.period_chunking_granularity === "month") {
+        facts.push("Requested period coverage was recovered through monthly 1C value-flow probes after the broad probe hit the row limit");
+    }
    if (derived.aggregation_axis === "month" && derived.monthly_breakdown.length > 0) {
        facts.push("Counterparty monthly value-flow breakdown was grouped by month over confirmed 1C movement rows");
    }
@@ -549,6 +710,9 @@ function buildBidirectionalValueFlowInferredFacts(derived) {
        return [];
    }
    const facts = ["Counterparty net value-flow was calculated as incoming confirmed 1C rows minus outgoing confirmed 1C rows"];
+    if (derived.coverage_recovered_by_period_chunking && derived.period_chunking_granularity === "month") {
+        facts.push("Requested period coverage for bidirectional value-flow was recovered through monthly 1C side probes after a broad probe hit the row limit");
+    }
    if (derived.aggregation_axis === "month" && derived.monthly_breakdown.length > 0) {
        facts.push("Counterparty monthly net value-flow breakdown was grouped by month over confirmed incoming and outgoing 1C rows");
    }
@@ -706,36 +870,50 @@ async function executeAssistantMcpDiscoveryPilot(planner, deps = DEFAULT_DEPS) {
                };
            }
            pushReason(reasonCodes, "pilot_bidirectional_value_flow_recipes_selected");
-            const incomingRecipePlan = (0, addressRecipeCatalog_1.buildAddressRecipePlan)(incomingSelection.selected_recipe, filters);
-            const outgoingRecipePlan = (0, addressRecipeCatalog_1.buildAddressRecipePlan)(outgoingSelection.selected_recipe, filters);
            for (const step of dryRun.execution_steps) {
                if (step.primitive_id !== "query_movements") {
                    skippedPrimitives.push(step.primitive_id);
                    probeResults.push(skippedProbeResult(step, "pilot_bidirectional_value_flow_uses_two_query_movements_and_derives_net"));
                    continue;
                }
-                incomingResult = await deps.executeAddressMcpQuery({
-                    query: incomingRecipePlan.query,
-                    limit: incomingRecipePlan.limit,
-                    account_scope: incomingRecipePlan.account_scope
+                const incomingExecution = await executeCoverageAwareValueFlowQuery({
+                    primitiveId: step.primitive_id,
+                    recipePlanBuilder: (scopedFilters) => (0, addressRecipeCatalog_1.buildAddressRecipePlan)(incomingSelection.selected_recipe, scopedFilters),
+                    baseFilters: filters,
+                    dateScope,
+                    maxProbeCount: planner.discovery_plan.execution_budget.max_probe_count,
+                    maxRowsPerProbe: planner.discovery_plan.execution_budget.max_rows_per_probe,
+                    deps
                });
-                outgoingResult = await deps.executeAddressMcpQuery({
-                    query: outgoingRecipePlan.query,
-                    limit: outgoingRecipePlan.limit,
-                    account_scope: outgoingRecipePlan.account_scope
+                const outgoingExecution = await executeCoverageAwareValueFlowQuery({
+                    primitiveId: step.primitive_id,
+                    recipePlanBuilder: (scopedFilters) => (0, addressRecipeCatalog_1.buildAddressRecipePlan)(outgoingSelection.selected_recipe, scopedFilters),
+                    baseFilters: filters,
+                    dateScope,
+                    maxProbeCount: planner.discovery_plan.execution_budget.max_probe_count,
+                    maxRowsPerProbe: planner.discovery_plan.execution_budget.max_rows_per_probe,
+                    deps
                });
+                incomingResult = incomingExecution.result;
+                outgoingResult = outgoingExecution.result;
                pushUnique(executedPrimitives, step.primitive_id);
-                probeResults.push(queryResultToProbeResult(step.primitive_id, incomingResult));
-                probeResults.push(queryResultToProbeResult(step.primitive_id, outgoingResult));
-                if (incomingResult.error) {
-                    pushUnique(queryLimitations, incomingResult.error);
+                probeResults.push(...incomingExecution.probe_results, ...outgoingExecution.probe_results);
+                for (const limitation of [...incomingExecution.query_limitations, ...outgoingExecution.query_limitations]) {
+                    pushUnique(queryLimitations, limitation);
+                }
+                if (incomingResult?.error) {
                    pushReason(reasonCodes, "pilot_bidirectional_incoming_query_movements_mcp_error");
                }
-                if (outgoingResult.error) {
-                    pushUnique(queryLimitations, outgoingResult.error);
+                if (outgoingResult?.error) {
                    pushReason(reasonCodes, "pilot_bidirectional_outgoing_query_movements_mcp_error");
                }
-                if (!incomingResult.error || !outgoingResult.error) {
+                if (incomingResult?.coverage_recovered_by_period_chunking) {
+                    pushReason(reasonCodes, "pilot_bidirectional_incoming_monthly_period_chunking_recovered_coverage");
+                }
+                if (outgoingResult?.coverage_recovered_by_period_chunking) {
+                    pushReason(reasonCodes, "pilot_bidirectional_outgoing_monthly_period_chunking_recovered_coverage");
+                }
+                if (!incomingResult?.error || !outgoingResult?.error) {
                    pushReason(reasonCodes, "pilot_bidirectional_query_movements_mcp_executed");
                }
            }
@@ -745,7 +923,6 @@ async function executeAssistantMcpDiscoveryPilot(planner, deps = DEFAULT_DEPS) {
                outgoingResult,
                counterparty,
                periodScope: dateScope,
-                probeLimit: planner.discovery_plan.execution_budget.max_rows_per_probe,
                aggregationAxis
            });
            if (derivedBidirectionalValueFlow) {
@@ -810,30 +987,39 @@ async function executeAssistantMcpDiscoveryPilot(planner, deps = DEFAULT_DEPS) {
        pushReason(reasonCodes, valueFlowProfile.direction === "outgoing_supplier_payout"
            ? "pilot_supplier_payout_recipe_selected"
            : "pilot_customer_revenue_recipe_selected");
-        const recipePlan = (0, addressRecipeCatalog_1.buildAddressRecipePlan)(selection.selected_recipe, filters);
        for (const step of dryRun.execution_steps) {
            if (step.primitive_id !== "query_movements") {
                skippedPrimitives.push(step.primitive_id);
                probeResults.push(skippedProbeResult(step, "pilot_value_flow_uses_query_movements_and_derives_aggregate"));
                continue;
            }
-            queryResult = await deps.executeAddressMcpQuery({
-                query: recipePlan.query,
-                limit: recipePlan.limit,
-                account_scope: recipePlan.account_scope
+            const execution = await executeCoverageAwareValueFlowQuery({
+                primitiveId: step.primitive_id,
+                recipePlanBuilder: (scopedFilters) => (0, addressRecipeCatalog_1.buildAddressRecipePlan)(selection.selected_recipe, scopedFilters),
+                baseFilters: filters,
+                dateScope,
+                maxProbeCount: planner.discovery_plan.execution_budget.max_probe_count,
+                maxRowsPerProbe: planner.discovery_plan.execution_budget.max_rows_per_probe,
+                deps
            });
-            executedPrimitives.push(step.primitive_id);
-            probeResults.push(queryResultToProbeResult(step.primitive_id, queryResult));
-            if (queryResult.error) {
-                pushUnique(queryLimitations, queryResult.error);
+            queryResult = execution.result;
+            pushUnique(executedPrimitives, step.primitive_id);
+            probeResults.push(...execution.probe_results);
+            for (const limitation of execution.query_limitations) {
+                pushUnique(queryLimitations, limitation);
+            }
+            if (queryResult?.error) {
                pushReason(reasonCodes, "pilot_query_movements_mcp_error");
            }
            else {
                pushReason(reasonCodes, "pilot_query_movements_mcp_executed");
            }
+            if (queryResult?.coverage_recovered_by_period_chunking) {
+                pushReason(reasonCodes, "pilot_monthly_period_chunking_recovered_coverage");
+            }
        }
        const sourceRowsSummary = queryResult ? summarizeValueFlowRows(queryResult) : null;
-        const derivedValueFlow = deriveValueFlow(queryResult, counterparty, dateScope, valueFlowProfile.direction, planner.discovery_plan.execution_budget.max_rows_per_probe, aggregationAxis);
+        const derivedValueFlow = deriveValueFlow(queryResult, counterparty, dateScope, valueFlowProfile.direction, aggregationAxis);
        if (derivedValueFlow) {
            pushReason(reasonCodes, "pilot_derived_value_flow_from_confirmed_rows");
            if (aggregationAxis === "month" && derivedValueFlow.monthly_breakdown.length > 0) {
@@ -55,6 +55,24 @@ function addScopeAxes(axes, meaning) {
 function includesAny(text, tokens) {
    return tokens.some((token) => text.includes(token));
 }
+function isYearDateScope(meaning) {
+    return /^\d{4}$/.test(toNonEmptyString(meaning?.explicit_date_scope) ?? "");
+}
+function budgetOverrideFor(input, recipe) {
+    const meaning = input.turnMeaning ?? null;
+    const requestedAggregationAxis = aggregationAxis(meaning);
+    const isValueFlowRecipe = recipe.semanticDataNeed === "counterparty value-flow evidence" &&
+        recipe.primitives.includes("query_movements");
+    if (!isValueFlowRecipe) {
+        return {};
+    }
+    if (requestedAggregationAxis === "month" || isYearDateScope(meaning)) {
+        return {
+            maxProbeCount: 30
+        };
+    }
+    return {};
+}
 function recipeFor(input) {
    const meaning = input.turnMeaning ?? null;
    const domain = lower(meaning?.asked_domain_family);
@@ -136,14 +154,19 @@ function statusFrom(plan, review) {
 }
 function planAssistantMcpDiscovery(input) {
    const recipe = recipeFor(input);
+    const budgetOverride = budgetOverrideFor(input, recipe);
    const semanticDataNeed = toNonEmptyString(input.semanticDataNeed) ?? recipe.semanticDataNeed;
    const reasonCodes = [];
    pushReason(reasonCodes, recipe.reason);
+    if (budgetOverride.maxProbeCount) {
+        pushReason(reasonCodes, "planner_enabled_chunked_coverage_probe_budget");
+    }
    const plan = (0, assistantMcpDiscoveryPolicy_1.buildAssistantMcpDiscoveryPlan)({
        semanticDataNeed,
        turnMeaning: input.turnMeaning,
        proposedPrimitives: recipe.primitives,
-        requiredAxes: recipe.axes
+        requiredAxes: recipe.axes,
+        maxProbeCount: budgetOverride.maxProbeCount
    });
    const review = (0, assistantMcpCatalogIndex_1.reviewAssistantMcpDiscoveryPlanAgainstCatalog)(plan);
    const plannerStatus = statusFrom(plan, review);
@@ -21,7 +21,7 @@ const DEFAULT_DISCOVERY_BUDGET = {
    max_probe_count: 3,
    max_rows_per_probe: 100
 };
-const MAX_PROBE_COUNT = 6;
+const MAX_PROBE_COUNT = 36;
 const MAX_ROWS_PER_PROBE = 500;
 const ALLOWED_PRIMITIVE_SET = new Set(exports.ASSISTANT_MCP_DISCOVERY_PRIMITIVES);
 function toNonEmptyString(value) {
@@ -139,6 +139,12 @@ function localizeLine(value) {
    if (/^Full all-time bidirectional value-flow is not proven without an explicit checked period$/i.test(value)) {
        return "Полный двусторонний денежный поток за все время без явно проверенного периода не подтвержден.";
    }
+    if (/^Requested period coverage was recovered through monthly 1C value-flow probes after the broad probe hit the row limit$/i.test(value)) {
+        return "Покрытие запрошенного периода восстановлено помесячными проверками 1С после того, как общая выборка уперлась в лимит строк.";
+    }
+    if (/^Requested period coverage for bidirectional value-flow was recovered through monthly 1C side probes after a broad probe hit the row limit$/i.test(value)) {
+        return "Покрытие запрошенного периода по двустороннему денежному потоку восстановлено помесячными проверками 1С после того, как общая выборка уперлась в лимит строк хотя бы по одной стороне.";
+    }
    return value;
 }
 function section(title, lines) {