NODEDC_1C/llm_normalizer/backend/tests/assistantLifecycleAwareAnsw...

232 lines
7.8 KiB
TypeScript
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import { describe, expect, it } from "vitest";
import { composeAssistantAnswer } from "../src/services/answerComposer";
import type { AnswerGroundingCheck, RequirementCoverageReport, UnifiedRetrievalResult } from "../src/types/assistant";
import type { ProblemUnit, ProblemUnitSummary } from "../src/types/stage2ProblemUnits";
function buildRouteSummary() {
return {
mode: "deterministic_v2" as const,
message_in_scope: true,
scope_confidence: "high" as const,
planner: {
total_fragments: 1,
in_scope_fragments: 1,
out_of_scope_fragments: 0,
discarded_fragments: 0,
contains_multiple_tasks: false
},
decisions: [],
fallback: {
type: "none" as const,
message: null
}
};
}
function buildCoverage(partial = false): RequirementCoverageReport {
return {
requirements_total: 1,
requirements_covered: partial ? 0 : 1,
requirements_uncovered: partial ? ["R1"] : [],
requirements_partially_covered: partial ? ["R1"] : [],
clarification_needed_for: [],
out_of_scope_requirements: []
};
}
function buildGrounding(status: AnswerGroundingCheck["status"]): AnswerGroundingCheck {
return {
status,
route_subject_match: true,
missing_requirements: status === "partial" ? ["R1"] : [],
reasons: status === "partial" ? ["Coverage is partial for lifecycle-focused analysis."] : [],
why_included_summary: ["synthetic-test"],
selection_reason_summary: ["synthetic-test"]
};
}
function buildLifecycleProblemUnit(): ProblemUnit {
return {
schema_version: "problem_unit_v0_1",
problem_unit_id: "pu-lc-1",
problem_unit_type: "lifecycle_anomaly_node",
title: "Lifecycle anomaly node detected",
mechanism_summary: "Mechanism candidate: expected transition is missing.",
business_defect_class: "missing_expected_transition",
severity: {
score: 0.84,
grade: "high"
},
confidence: {
score: 0.68,
grade: "medium"
},
affected_entities: ["Document:DOC-1"],
affected_documents: ["Document:DOC-1"],
affected_postings: [],
affected_accounts: ["51", "60"],
affected_counterparties: ["Counterparty:CP-1"],
affected_contracts: ["Contract:CTR-1"],
expected_state: "settlement_closed",
actual_state: "stale_unlinked_payment",
failed_expected_edge: "payment_to_settlement",
period_impact: {
is_period_sensitive: true,
impact_class: "close_risk"
},
evidence_pack: ["cand-1"],
entity_backlinks: [{ entity: "Document", id: "DOC-1" }],
snapshot_limitations: [],
lifecycle_domain: "bank_settlement",
lifecycle_object_id: "lcobj-pu-lc-1",
current_lifecycle_state: "stale_unlinked_payment",
expected_lifecycle_state: "settlement_closed",
missing_transition: "payment_to_settlement",
lifecycle_defect_type: "stale_active_state",
stale_duration: "period_boundary_exceeded",
lifecycle_confidence: {
score: 0.79,
grade: "high"
},
business_lifecycle_interpretation:
"Текущая стадия: stale_unlinked_payment; ожидаемая стадия: settlement_closed. Объект завис во времени и не дошел до ожидаемого перехода.",
lifecycle_ranking_score: 1.41,
lifecycle_ranking_basis: ["base_problem_severity", "stale_duration_weight", "period_close_impact"]
};
}
function buildSummary(units: ProblemUnit[]): ProblemUnitSummary {
const unitTypes = Array.from(new Set(units.map((item) => item.problem_unit_type)));
return {
schema_version: "problem_unit_summary_v0_1",
units_total: units.length,
duplicate_collapses: 0,
unit_types: unitTypes,
type_distribution: {
lifecycle_anomaly_node: units.length
},
severity_distribution: {
low: 0,
medium: 0,
high: units.length
},
confidence_distribution: {
low: 0,
medium: units.length,
high: 0
},
primary_unit_type: unitTypes[0] ?? null,
lifecycle_enriched_units: units.length,
lifecycle_domain_distribution: {
bank_settlement: units.length
},
lifecycle_defect_distribution: {
stale_active_state: units.length
}
};
}
function buildRetrievalResult(problemUnits: ProblemUnit[]): UnifiedRetrievalResult {
return {
fragment_id: "F1",
requirement_ids: ["R1"],
route: "hybrid_store_plus_live",
status: "ok",
result_type: "chain",
items: [
{
counterparty_id: "CP-1",
operations_count: 5,
document_refs_count: 3
}
],
raw_entities: [],
candidate_evidence: [],
problem_units: problemUnits,
problem_unit_summary: buildSummary(problemUnits),
summary: {
broad_query_detected: true,
broad_result_flag: true,
minimum_evidence_failed: false,
degraded_to: "partial",
narrowing_strength: "weak"
},
evidence: [
{
evidence_id: "ev-1",
claim_ref: "requirement:R1",
source_type: "retrieval_item",
source_ref: {
schema_version: "evidence_source_ref_v1",
namespace: "snapshot_2020",
entity: "Document",
id: "DOC-1",
period: "2020-06",
canonical_ref: "evidence_source_ref_v1|snapshot_2020|document|doc-1|2020-06"
},
pointer: {
fragment_id: "F1",
route: "hybrid_store_plus_live",
source: {
namespace: "snapshot_2020",
entity: "Document",
id: "DOC-1",
period: "2020-06"
},
locator: {
field_path: "risk_score",
item_index: 0
}
},
evidence_kind: "mechanism_link",
mechanism_note: "failed_edge=payment_to_settlement",
confidence: "medium",
limitation: null,
payload: {
risk_score: 5
}
}
],
why_included: ["synthetic-test"],
selection_reason: ["synthetic-test"],
risk_factors: ["broken_chain"],
business_interpretation: ["synthetic-test"],
confidence: "medium",
limitations: [],
errors: []
};
}
describe("assistant lifecycle-aware answer mode v1", () => {
it("promotes stage3 lifecycle mode when lifecycle answer flag is enabled", () => {
const units = [buildLifecycleProblemUnit()];
const output = composeAssistantAnswer({
userMessage: "Проверь, где зависли платежи по 51/60 и какой переход не завершился.",
routeSummary: buildRouteSummary(),
retrievalResults: [buildRetrievalResult(units)],
requirements: [
{
requirement_id: "R1",
source_fragment_id: "F1",
requirement_text: "Проверить lifecycle-переход",
subject_tokens: ["chain", "account_51", "account_60"],
status: "covered",
route: "hybrid_store_plus_live"
}
],
coverageReport: buildCoverage(true),
groundingCheck: buildGrounding("partial"),
enableAnswerPolicyV11: true,
enableProblemCentricAnswerV1: true,
enableLifecycleAnswerV1: true
});
expect(output.problem_centric_answer_applied).toBe(true);
expect(output.problem_answer_mode).toBe("stage3_lifecycle_aware_v1");
expect(output.answer_structure_v11?.answer_summary).toMatch(/lifecycle|Lifecycle|жизненн/i);
expect(String(output.answer_structure_v11?.direct_answer)).toMatch(/не подтвержден|ожидаем|зависл/i);
expect(output.answer_structure_v11?.direct_answer).not.toMatch(/current=|expected=|defect=/i);
});
});