ГЛОБАЛЬНЫЙ РЕФАКТОРИНГ АРХИТЕКТУРЫ - Рефакторинг этапов 2.2.1 - фикс деградаций по старым доменам + легкая доводка регрессий перед стартом 3его этапа

2026-04-11 16:19:53 +03:00
parent b5bd4fd737
commit 66402439dc
22 changed files with 2640 additions and 61 deletions
@@ -2986,12 +2986,12 @@ function resolveAddressToolGateDecision(addressInputMessage, followupContext, ll
    const llmContractMode = toNonEmptyString(llmPreDecomposeMeta?.predecomposeContract?.mode);
    const llmContractModeConfidence = toNonEmptyString(llmPreDecomposeMeta?.predecomposeContract?.mode_confidence);
    const llmContractIntent = toNonEmptyString(llmPreDecomposeMeta?.predecomposeContract?.intent);
-    const llmCanonicalEntitySignal = /(?:\u0437\u0430\u043a\u0430\u0437\u0447\u0438\u043a|\u043f\u043e\u0441\u0442\u0430\u0432\u0449\u0438\u043a|\u043a\u043e\u043d\u0442\u0440\u0430\u0433\u0435\u043d\u0442|\u043a\u043e\u043c\u043f\u0430\u043d|customer|supplier|counterparty|company|vendor|client|\b[a-z]{2,}\b)/iu.test(compactWhitespace(repairedInputMessage.toLowerCase()));
+    const llmCanonicalEntitySignal = /(?:\u0437\u0430\u043a\u0430\u0437\u0447\u0438\u043a|\u043f\u043e\u0441\u0442\u0430\u0432\u0449\u0438\u043a|\u043a\u043e\u043d\u0442\u0440\u0430\u0433\u0435\u043d\u0442|\u043a\u043e\u043c\u043f\u0430\u043d|customer|supplier|counterparty|company|vendor|client)/iu.test(compactWhitespace(repairedInputMessage.toLowerCase()));
    const llmCanonicalAppliedSignal = Boolean(llmPreDecomposeMeta?.applied) && llmContractMode !== "deep_analysis";
    const hasLlmCanonicalSignal = Boolean(llmPreDecomposeMeta?.llmCanonicalCandidateDetected) &&
        ((llmContractMode === "address_query" && llmContractModeConfidence !== "low") ||
            (llmCanonicalAppliedSignal &&
-                (hasStrongDataIntentSignal(repairedInputMessage) || llmCanonicalEntitySignal || llmContractMode === "unsupported")));
+                (hasStrongDataIntentSignal(repairedInputMessage) || llmCanonicalEntitySignal)));
    const hasLlmCanonicalDataSignal = Boolean(llmPreDecomposeMeta?.llmCanonicalCandidateDetected) &&
        Boolean(llmPreDecomposeMeta?.applied) &&
        (llmContractMode === "address_query" || llmContractMode === "unsupported" || llmContractMode === null) &&
@@ -3133,6 +3133,42 @@ function hasDirectDeepAnalysisSignal(text) {
    }
    return /(?:\u0440\u0430\u0437\u043b\u043e\u0436|\u0446\u0435\u043f\u043e\u0447|lifecycle|\u0440\u0430\u0437\u0440\u044b\u0432|\u043f\u0440\u043e\u0442\u0438\u0432\u043e\u0440\u0435\u0447|\u0430\u043d\u043e\u043c\u0430\u043b|\u043f\u043e\u0447\u0435\u043c\u0443|\u043c\u0435\u0445\u0430\u043d\u0438\u0437\u043c|\u0437\u0430\u043a\u0440\u044b\u0442[\u0430-\u044f]*|state\s+transition|root\s*cause|trace\s*chain)/iu.test(normalized);
 }
+function hasStrictDeepInvestigationCue(text) {
+    const normalized = compactWhitespace(repairAddressMojibake(String(text ?? "")).toLowerCase());
+    if (!normalized) {
+        return false;
+    }
+    const hasInvestigativeVerb = /(?:\u043f\u0440\u043e\u0432\u0435\u0440(?:\u044c|\u0438\u0442\u044c)|\u0440\u0430\u0437\u0431\u0435\u0440(?:\u0438|\u0430\u0442\u044c)|\u0440\u0430\u0437\u043b\u043e\u0436(?:\u0438|\u0438\u0442\u044c)|\u043f\u043e\u0447\u0435\u043c\u0443|\u043c\u0435\u0445\u0430\u043d\u0438\u0437\u043c|root\s*cause|trace\s*chain)/iu.test(normalized);
+    if (!hasInvestigativeVerb) {
+        return false;
+    }
+    return /(?:\u0445\u0432\u043e\u0441\u0442|\u0440\u0430\u0437\u0440\u044b\u0432|\u0446\u0435\u043f\u043e\u0447|\u0430\u043d\u043e\u043c\u0430\u043b|\u043f\u0440\u043e\u0442\u0438\u0432\u043e\u0440\u0435\u0447|\u0437\u0430\u043a\u0440\u044b\u0442\u0438[\u0435\u044f]|\u043e\u0431\u044a\u0435\u043a\u0442(?:\u0443)?\s+\u0440\u0430\u0441\u0447(?:\u0435|\u0451)\u0442|lifecycle|state\s+transition)/iu.test(normalized);
+}
+function hasAggregateBusinessAnalyticsSignal(text) {
+    const normalized = compactWhitespace(repairAddressMojibake(String(text ?? "")).toLowerCase());
+    if (!normalized) {
+        return false;
+    }
+    const hasMetricCue = /(?:\u043e\u0431\u043e\u0440\u043e\u0442|\u0432\u044b\u0440\u0443\u0447|\u0434\u043e\u0445\u043e\u0434|\u043f\u0440\u0438\u0431\u044b\u043b|\u043c\u0430\u0440\u0436|\u0440\u0435\u043d\u0442\u0430\u0431\u0435\u043b|\u043f\u043e\u043a\u0430\u0437\u0430\u0442\u0435\u043b|turnover|revenue|profit|margin)/iu.test(normalized);
+    if (!hasMetricCue) {
+        return false;
+    }
+    const hasRankingOrTrendCue = /(?:\u0441\u0430\u043c(?:\u044b\u0439|\u0430\u044f|\u043e\u0435|\u044b\u0435)|\u0442\u043e\u043f|\u043b\u0443\u0447\u0448|\u0445\u0443\u0434\u0448|\u043c\u0430\u043a\u0441(?:\u0438\u043c\u0443\u043c)?|\u043c\u0438\u043d(?:\u0438\u043c\u0443\u043c)?|\u0434\u0438\u043d\u0430\u043c|\u0442\u0440\u0435\u043d\u0434|\u0441\u0440\u0430\u0432\u043d|ranking|top|best|worst)/iu.test(normalized);
+    const hasPeriodAggregateCue = /(?:\u043f\u043e\s+\u0433\u043e\u0434\u0430\u043c|\u0437\u0430\s+\d{4}\s+\u0433\u043e\u0434|\u0433\u043e\u0434(?:\u0430|\u0443|\u044b)?|year|years|\u043a\u0432\u0430\u0440\u0442\u0430\u043b|\u043c\u0435\u0441\u044f\u0446|\u043f\u0435\u0440\u0438\u043e\u0434)/iu.test(normalized);
+    return hasRankingOrTrendCue || hasPeriodAggregateCue;
+}
+const ADDRESS_INTENTS_KEEP_ADDRESS_LANE = new Set([
+    "list_open_contracts",
+    "open_items_by_counterparty_or_contract",
+    "list_documents_by_contract",
+    "bank_operations_by_contract",
+    "list_documents_by_counterparty",
+    "bank_operations_by_counterparty",
+    "list_contracts_by_counterparty",
+    "contract_usage_overview",
+    "contract_usage_and_value",
+    "vat_payable_forecast"
+]);
 export function resolveAssistantOrchestrationDecision(input) {
    const rawUserMessage = String(input?.rawUserMessage ?? input?.userMessage ?? "");
    const effectiveAddressUserMessage = String(input?.effectiveAddressUserMessage ?? rawUserMessage);
@@ -3154,9 +3190,21 @@ export function resolveAssistantOrchestrationDecision(input) {
        hasDataRetrievalRequestSignal(repairedRawUserMessage) ||
        hasDataRetrievalRequestSignal(effectiveAddressUserMessage) ||
        hasDataRetrievalRequestSignal(repairedEffectiveAddressUserMessage);
+    const aggregateBusinessAnalyticsSignal = hasAggregateBusinessAnalyticsSignal(rawUserMessage) ||
+        hasAggregateBusinessAnalyticsSignal(repairedRawUserMessage) ||
+        hasAggregateBusinessAnalyticsSignal(effectiveAddressUserMessage) ||
+        hasAggregateBusinessAnalyticsSignal(repairedEffectiveAddressUserMessage);
    const modeSample = repairedEffectiveAddressUserMessage || effectiveAddressUserMessage;
    const modeDetection = (0, addressQueryClassifier_1.detectAddressQuestionMode)(modeSample);
    const intentResolution = (0, addressIntentResolver_1.resolveAddressIntent)(modeSample);
+    const llmContractIntent = toNonEmptyString(llmPreDecomposeMeta?.predecomposeContract?.intent);
+    const strictDeepInvestigationCueDetected = hasStrictDeepInvestigationCue(rawUserMessage) ||
+        hasStrictDeepInvestigationCue(repairedRawUserMessage) ||
+        hasStrictDeepInvestigationCue(effectiveAddressUserMessage) ||
+        hasStrictDeepInvestigationCue(repairedEffectiveAddressUserMessage);
+    const keepAddressLaneByIntent = Boolean((intentResolution.intent && ADDRESS_INTENTS_KEEP_ADDRESS_LANE.has(intentResolution.intent)) ||
+        (llmContractIntent && ADDRESS_INTENTS_KEEP_ADDRESS_LANE.has(llmContractIntent))) &&
+        !strictDeepInvestigationCueDetected;
    const strongDataSignal = hasStrongDataIntentSignal(rawUserMessage) ||
        hasStrongDataIntentSignal(repairedRawUserMessage) ||
        hasStrongDataIntentSignal(effectiveAddressUserMessage) ||
@@ -3232,7 +3280,7 @@ export function resolveAssistantOrchestrationDecision(input) {
    const llmContractMode = toNonEmptyString(llmPreDecomposeMeta?.predecomposeContract?.mode);
    const preserveAddressLaneSignal = Boolean((llmPreDecomposeMeta?.llmCanonicalCandidateDetected &&
        llmPreDecomposeMeta?.applied &&
-        (llmContractMode === "address_query" || llmContractMode === "unsupported")) ||
+        llmContractMode === "address_query") ||
        hasSameDateAccountFollowupSignalForPredecompose(rawUserMessage) ||
        hasSameDateAccountFollowupSignalForPredecompose(effectiveAddressUserMessage) ||
        hasSameDateAccountFollowupSignalForPredecompose(repairedRawUserMessage) ||
@@ -3245,10 +3293,11 @@ export function resolveAssistantOrchestrationDecision(input) {
        hasAddressFollowupContextSignal(effectiveAddressUserMessage) ||
        hasAddressFollowupContextSignal(repairedRawUserMessage) ||
        hasAddressFollowupContextSignal(repairedEffectiveAddressUserMessage));
+    const unsupportedIntentOrMode = modeDetection.mode !== "address_query" &&
+        (intentResolution.intent === "unknown" || llmContractMode === "unsupported");
    const unsupportedAddressIntentFallbackToDeep = Boolean(!followupContext &&
        baseToolGate?.runAddressLane &&
-        modeDetection.mode !== "address_query" &&
-        intentResolution.intent === "unknown" &&
+        unsupportedIntentOrMode &&
        strongDataSignal &&
        !preserveAddressLaneSignal);
    const deepAnalysisPreferenceDetected = Boolean(hasDeepAnalysisPreferenceSignal(rawUserMessage) ||
@@ -3264,8 +3313,13 @@ export function resolveAssistantOrchestrationDecision(input) {
        /(?:\u043f\u043e\u0447\u0435\u043c\u0443|why).*(?:\u043f\u0440\u043e\u0433\u043d\u043e\u0437|forecast).*(?:\u0443\u043f\u043b\u0430\u0442|payable|\b0\b)/iu.test(compactWhitespace(`${repairedRawUserMessage} ${repairedEffectiveAddressUserMessage}`)));
    const deepAnalysisSignalFallbackToDeep = Boolean(baseToolGate?.runAddressLane &&
        deepAnalysisPreferenceDetected &&
+        !keepAddressLaneByIntent &&
        !vatExplainFollowupSignal &&
        (!followupContext || !dataRetrievalSignal));
+    const aggregateAnalyticsFallbackToDeep = Boolean(baseToolGate?.runAddressLane &&
+        aggregateBusinessAnalyticsSignal &&
+        !keepAddressLaneByIntent &&
+        !followupContext);
    const deepSessionContinuationFallbackToDeep = Boolean(!followupContext &&
        baseToolGate?.runAddressLane &&
        hasDeepSessionContinuationSignal({
@@ -3288,6 +3342,13 @@ export function resolveAssistantOrchestrationDecision(input) {
        toolGateDecision = "skip_address_lane";
        toolGateReason = "deep_analysis_signal_fallback_to_deep";
    }
+    if (aggregateAnalyticsFallbackToDeep &&
+        !unsupportedAddressIntentFallbackToDeep &&
+        !deepAnalysisSignalFallbackToDeep) {
+        runAddressLane = false;
+        toolGateDecision = "skip_address_lane";
+        toolGateReason = "aggregate_analytics_signal_fallback_to_deep";
+    }
    if (deepSessionContinuationFallbackToDeep) {
        runAddressLane = false;
        toolGateDecision = "skip_address_lane";
@@ -3312,6 +3373,14 @@ export function resolveAssistantOrchestrationDecision(input) {
            reason: "deep_analysis_signal_fallback_to_deep"
        };
    }
+    if (aggregateAnalyticsFallbackToDeep &&
+        !unsupportedAddressIntentFallbackToDeep &&
+        !deepAnalysisSignalFallbackToDeep) {
+        livingDecision = {
+            mode: "deep_analysis",
+            reason: "aggregate_analytics_signal_fallback_to_deep"
+        };
+    }
    if (deepSessionContinuationFallbackToDeep) {
        livingDecision = {
            mode: "deep_analysis",
@@ -3336,6 +3405,7 @@ export function resolveAssistantOrchestrationDecision(input) {
            followup_context_detected: Boolean(followupContext),
            unsupported_address_intent_fallback_to_deep: unsupportedAddressIntentFallbackToDeep,
            deep_analysis_signal_fallback_to_deep: deepAnalysisSignalFallbackToDeep,
+            aggregate_analytics_signal_fallback_to_deep: aggregateAnalyticsFallbackToDeep,
            deep_session_continuation_fallback_to_deep: deepSessionContinuationFallbackToDeep,
            final_decision: {
                run_address_lane: runAddressLane,
@@ -3356,6 +3426,11 @@ function hasDataRetrievalRequestSignal(text) {
    if (!lower) {
        return false;
    }
+    const hasRussianRetrievalAction = /(?:^|\s)(?:\u043f\u043e\u043a\u0430\u0436\u0438|\u043f\u043e\u043a\u0430\u0437\u0430\u0442\u044c|\u043d\u0430\u0439\u0434\u0438|\u0432\u044b\u0432\u0435\u0434\u0438|\u0434\u0430\u0439|\u0440\u0430\u0441\u043a\u0440\u043e\u0439|\u0441\u043f\u0438\u0441\u043e\u043a)(?:$|[\s,.!?;:])/iu.test(lower);
+    const hasRussianRetrievalObject = /(?:\u0434\u043e\u0433\u043e\u0432\u043e\u0440|\u043a\u043e\u043d\u0442\u0440\u0430\u043a\u0442|\u043a\u043e\u043d\u0442\u0440\u0430\u0433\u0435\u043d\u0442|\u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442|\u0441\u0447(?:\u0435|\u0451)\u0442|\u043e\u0441\u0442\u0430\u0442|\u0441\u0430\u043b\u044c\u0434\u043e|\u043e\u0431\u043e\u0440\u043e\u0442|\u043f\u043b\u0430\u0442(?:\u0435|\u0451)\u0436|\u043e\u043f\u0435\u0440\u0430\u0446|\u043f\u043e\u0441\u0442\u0430\u0432\u0449\u0438\u043a|\u043a\u043b\u0438\u0435\u043d\u0442|\u0433\u043e\u0434|\u043f\u0435\u0440\u0438\u043e\u0434|\u043c\u0435\u0441\u044f\u0446)/iu.test(lower);
+    if (hasRussianRetrievalAction && hasRussianRetrievalObject) {
+        return true;
+    }
    const hasExplicitRetrievalAction = /(?:\bпокажи\b|\bпоказать\b|\bвыведи\b|\bнайди\b|\bсписок\b|\bдай\b|\bраскрой\b|\bshow\b|\blist\b|\bfind\b|\bcount\b)/i.test(lower);
    const hasInterrogativeRetrievalAction = /(?:\bсколько\b|\bкакой\b|\bкакая\b|\bкакое\b|\bкакую\b|\bкакие\b|\bкто\b|\bwhich\b|\bwho\b)/i.test(lower);
    if (!hasExplicitRetrievalAction && !hasInterrogativeRetrievalAction) {
@@ -3522,6 +3597,10 @@ function hasAssistantDataScopeMetaQuestionSignal(text) {
    if (!normalized) {
        return false;
    }
+    const hasSlangScopeQuestion = /(?:\u043f\u043e\s+\u043a\u0430\u043a\u0438\u043c\s+(?:\u043a\u043e\u043d\u0442\u043e\u0440(?:\u0430\u043c|\u044b|\u0430)?|\u043a\u043e\u043c\u043f\u0430\u043d(?:\u0438\u044f\u043c|\u0438\u0438|\u0438\u044e|\u0438\u044f)|\u043e\u0440\u0433\u0430\u043d\u0438\u0437\u0430\u0446(?:\u0438\u044f\u043c|\u0438\u0438|\u0438\u044e|\u0438\u044f)|\u0444\u0438\u0440\u043c(?:\u0430\u043c|\u0435|\u0443|\u0430)).*(?:\u043c\u043e\u0436(?:\u0435\u043c|\u043d\u043e)|\u0440\u0430\u0431\u043e\u0442|\u043e\u0431\u0449\u0430\u0442|\u043f\u043e\u0434\u0440\u0443\u0431|\u043f\u043e\u0434\u043a\u043b\u044e\u0447)|(?:\u0431\u0430\u0437\u0430\s+\u043a\u0430\u043a\u043e\u0439\s+(?:\u043a\u043e\u043d\u0442\u043e\u0440|\u043a\u043e\u043c\u043f\u0430\u043d|\u043e\u0440\u0433\u0430\u043d\u0438\u0437\u0430\u0446|\u0444\u0438\u0440\u043c))|(?:\u043a\u0430\u043a\u0430\u044f\s+\u0431\u0430\u0437\u0430\s+(?:\u043f\u043e\u0434\u043a\u043b\u044e\u0447|\u0430\u043a\u0442\u0438\u0432)))/iu.test(normalized);
+    if (hasSlangScopeQuestion) {
+        return true;
+    }
    const hasBaseOrTenantObject = /(?:баз(?:а|е|у|ы)?|тенант|tenant|контур)/i.test(normalized);
    const hasCompanyObject = /(?:компан(?:ия|ии|ию|ией)|компин(?:ия|ии|ию|ией)?|компини(?:я|и|ю|ей)?|компани[яеию]|организац(?:ия|ии|ию|ией)|контор(?:а|ы|у|ой)?|фирм(?:а|ы|у|ой)?)/i.test(normalized);
    const hasConnectionCue = /(?:подключен(?:а|о|ы)?|подруб|воткнут|активн(?:ый|ая)\s+канал|mcp-?канал|канал)/i.test(normalized);