SILVER/NODEDC_1C
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

ГЛОБАЛЬНЫЙ РЕФАКТОРИНГ АРХИТЕКТУРЫ - Рефакторинг этапов 3.1 - Добавлен строгий контракт семантического извлечения (валидность, качество, reason-codes, рекомендация применять canonical). Подключен semantic guard в predecompose/runtime: мягкое отклонение плохого canonical: отдельный safe-кейс для сырого полезного raw-фрагмента; fallback теперь выигрывает только когда это оправдано. Подключty semantic arbitration в tool-gate

Browse Source
This commit is contained in:
dctouch
2026-04-11 16:45:43 +03:00
parent 66402439dc
commit a7ccc92a9c
18 changed files with 750 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files
llm_normalizer/backend/src/services/assistantService.ts
+102 -7
View File
@@ -2714,12 +2714,19 @@ function hasSameDateAccountFollowupSignalForPredecompose(text) {
}
function attachAddressPredecomposeContract(meta, sourceMessage) {
const canonicalMessage = toNonEmptyString(meta?.effectiveMessage) ?? String(sourceMessage ?? "");
const predecomposeContract = (0, predecomposeContract_1.buildAddressLlmPredecomposeContractV1)({
sourceMessage: String(sourceMessage ?? ""),
canonicalMessage
});
const semanticExtractionContract = (0, predecomposeContract_1.buildAddressSemanticExtractionContractV1)({
sourceMessage: String(sourceMessage ?? ""),
canonicalMessage,
predecomposeContract
});
return {
...meta,
predecomposeContract: (0, predecomposeContract_1.buildAddressLlmPredecomposeContractV1)({
sourceMessage: String(sourceMessage ?? ""),
canonicalMessage
})
predecomposeContract,
semanticExtractionContract
};
}
async function runAddressLlmPreDecompose(normalizerService, payload, userMessage) {
@@ -2910,6 +2917,63 @@ async function runAddressLlmPreDecompose(normalizerService, payload, userMessage
}, userMessage);
}
}
const semanticContractForCandidate = (0, predecomposeContract_1.buildAddressSemanticExtractionContractV1)({
sourceMessage: String(userMessage ?? ""),
canonicalMessage: candidate
});
if (!semanticContractForCandidate.apply_canonical_recommended) {
const sourceDataSignalDetected = Boolean(semanticContractForCandidate?.guard_hints?.source_data_signal_detected);
const rawFragmentCandidatePreferred = Boolean(sourceDataSignalDetected &&
candidateFromNormalized &&
candidateFromNormalized === candidate &&
toNonEmptyString(candidate));
if (rawFragmentCandidatePreferred) {
return attachAddressPredecomposeContract({
...baseMeta,
attempted: true,
applied: true,
traceId: normalized?.trace_id ?? null,
llmCanonicalCandidateDetected: true,
effectiveMessage: candidate,
reason: "normalized_fragment_semantic_guard_raw_fragment_preferred",
fallbackRuleHit: null,
sanitizedUserMessage
}, userMessage);
}
if (fallbackCandidate) {
const fallbackSemanticContract = (0, predecomposeContract_1.buildAddressSemanticExtractionContractV1)({
sourceMessage: String(userMessage ?? ""),
canonicalMessage: String(fallbackCandidate.candidate ?? "")
});
const fallbackCompact = compactWhitespace(String(fallbackCandidate.candidate ?? "").toLowerCase());
const sourceCompactForFallback = compactWhitespace(String(userMessage ?? "").toLowerCase());
const fallbackApplied = fallbackCompact.length > 0 && fallbackCompact !== sourceCompactForFallback;
if (fallbackApplied && fallbackSemanticContract.apply_canonical_recommended && !sourceDataSignalDetected) {
return attachAddressPredecomposeContract({
...baseMeta,
attempted: true,
applied: true,
traceId: normalized?.trace_id ?? null,
llmCanonicalCandidateDetected: true,
effectiveMessage: String(fallbackCandidate.candidate ?? ""),
reason: "fallback_rule_preferred_over_llm_candidate_semantic_guard",
fallbackRuleHit: fallbackCandidate.rule,
sanitizedUserMessage
}, userMessage);
}
}
return attachAddressPredecomposeContract({
...baseMeta,
attempted: true,
applied: false,
traceId: normalized?.trace_id ?? null,
llmCanonicalCandidateDetected: true,
effectiveMessage: userMessage,
reason: "normalized_fragment_rejected_semantic_guard",
fallbackRuleHit: null,
sanitizedUserMessage
}, userMessage);
}
const sourceCompact = compactWhitespace(String(userMessage ?? "").toLowerCase());
const candidateCompact = compactWhitespace(candidate.toLowerCase());
const applied = sourceCompact !== candidateCompact;
@@ -2986,13 +3050,20 @@ 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 semanticExtractionContract = llmPreDecomposeMeta?.semanticExtractionContract &&
typeof llmPreDecomposeMeta.semanticExtractionContract === "object"
? llmPreDecomposeMeta.semanticExtractionContract
: null;
const semanticCanonicalRecommended = semanticExtractionContract?.apply_canonical_recommended !== false;
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) &&
const hasLlmCanonicalSignal = semanticCanonicalRecommended &&
Boolean(llmPreDecomposeMeta?.llmCanonicalCandidateDetected) &&
((llmContractMode === "address_query" && llmContractModeConfidence !== "low") ||
(llmCanonicalAppliedSignal &&
(hasStrongDataIntentSignal(repairedInputMessage) || llmCanonicalEntitySignal)));
const hasLlmCanonicalDataSignal = Boolean(llmPreDecomposeMeta?.llmCanonicalCandidateDetected) &&
const hasLlmCanonicalDataSignal = semanticCanonicalRecommended &&
Boolean(llmPreDecomposeMeta?.llmCanonicalCandidateDetected) &&
Boolean(llmPreDecomposeMeta?.applied) &&
(llmContractMode === "address_query" || llmContractMode === "unsupported" || llmContractMode === null) &&
hasStrongDataIntentSignal(repairedInputMessage);
@@ -3013,6 +3084,17 @@ function resolveAddressToolGateDecision(addressInputMessage, followupContext, ll
const strongDataSignalFromEffectiveMessage = hasStrongDataIntentSignal(repairedInputMessage) ||
hasAccountingSignal(repairedInputMessage) ||
hasDataRetrievalRequestSignal(repairedInputMessage);
if (!semanticCanonicalRecommended &&
llmContractIntent === "unknown" &&
!followupContext &&
!hasClassifierSignal &&
!strongDataSignalFromRawMessage) {
return {
runAddressLane: false,
decision: "skip_address_lane",
reason: "llm_predecompose_semantic_guard_rejected"
};
}
if (hasUnsupportedLowConfidencePredecomposeSignal && !followupContext &&
!hasAnyAddressSignal &&
!strongDataSignalFromRawMessage &&
@@ -3198,11 +3280,21 @@ export function resolveAssistantOrchestrationDecision(input) {
const modeDetection = (0, addressQueryClassifier_1.detectAddressQuestionMode)(modeSample);
const intentResolution = (0, addressIntentResolver_1.resolveAddressIntent)(modeSample);
const llmContractIntent = toNonEmptyString(llmPreDecomposeMeta?.predecomposeContract?.intent);
const semanticExtractionContract = llmPreDecomposeMeta?.semanticExtractionContract &&
typeof llmPreDecomposeMeta.semanticExtractionContract === "object"
? llmPreDecomposeMeta.semanticExtractionContract
: null;
const semanticContractValid = semanticExtractionContract?.valid !== false;
const semanticApplyCanonicalRecommended = semanticExtractionContract?.apply_canonical_recommended !== false;
const semanticReasonCodes = Array.isArray(semanticExtractionContract?.reason_codes)
? semanticExtractionContract.reason_codes
: [];
const strictDeepInvestigationCueDetected = hasStrictDeepInvestigationCue(rawUserMessage) ||
hasStrictDeepInvestigationCue(repairedRawUserMessage) ||
hasStrictDeepInvestigationCue(effectiveAddressUserMessage) ||
hasStrictDeepInvestigationCue(repairedEffectiveAddressUserMessage);
const keepAddressLaneByIntent = Boolean((intentResolution.intent && ADDRESS_INTENTS_KEEP_ADDRESS_LANE.has(intentResolution.intent)) ||
const keepAddressLaneByIntent = semanticApplyCanonicalRecommended &&
Boolean((intentResolution.intent && ADDRESS_INTENTS_KEEP_ADDRESS_LANE.has(intentResolution.intent)) ||
(llmContractIntent && ADDRESS_INTENTS_KEEP_ADDRESS_LANE.has(llmContractIntent))) &&
!strictDeepInvestigationCueDetected;
const strongDataSignal = hasStrongDataIntentSignal(rawUserMessage) ||
@@ -3402,6 +3494,9 @@ export function resolveAssistantOrchestrationDecision(input) {
address_intent_confidence: intentResolution.confidence,
strong_data_signal_detected: strongDataSignal,
data_retrieval_signal_detected: dataRetrievalSignal,
semantic_contract_valid: semanticContractValid,
semantic_apply_canonical_recommended: semanticApplyCanonicalRecommended,
semantic_reason_codes: semanticReasonCodes,
followup_context_detected: Boolean(followupContext),
unsupported_address_intent_fallback_to_deep: unsupportedAddressIntentFallbackToDeep,
deep_analysis_signal_fallback_to_deep: deepAnalysisSignalFallbackToDeep,