@tangle-network/agent-knowledge 4.0.0 → 4.0.1

package/CHANGELOG.md

@@ -1,5 +1,17 @@
 # Changelog
 
+## 4.0.1
+
+### Changed
+
+- Split benchmark, memory experiment, and memory improvement internals into focused modules while preserving every public export and signature.
+- Split memory and benchmark tests by behavior, with shared controller and adapter fixtures kept in one test-support module.
+- Moved retrieval holdout contracts into the memory type layer to remove the holdout/types import cycle.
+
+### Fixed
+
+- Made the Mem0 deletion-convergence test deterministic under file-level parallel execution.
+
 ## 4.0.0
 
 ### Breaking Changes

package/dist/benchmarks/index.d.ts

@@ -1,4 +1,52 @@
-import '@tangle-network/agent-eval/campaign';
-export { B as BuildRetrievalBenchmarkCasesFromQrelsOptions, I as INDUSTRY_MEMORY_BENCHMARKS, o as INDUSTRY_RAG_BENCHMARKS, K as KnowledgeAnswerBenchmarkCase, p as KnowledgeAnswerBenchmarkTaskKind, q as KnowledgeBenchmarkArtifact, r as KnowledgeBenchmarkCase, s as KnowledgeBenchmarkCaseBase, t as KnowledgeBenchmarkDistribution, u as KnowledgeBenchmarkEvaluation, v as KnowledgeBenchmarkFamily, w as KnowledgeBenchmarkReport, x as KnowledgeBenchmarkResponder, y as KnowledgeBenchmarkScenario, z as KnowledgeBenchmarkSliceSummary, C as KnowledgeBenchmarkSource, D as KnowledgeBenchmarkSpec, E as KnowledgeBenchmarkSplit, F as KnowledgeBenchmarkTaskKind, G as KnowledgeClaimMatcher, H as KnowledgeMemoryBenchmarkCase, J as KnowledgeMemoryBenchmarkTaskKind, L as KnowledgeMemoryEvent, M as KnowledgeMemoryFactMatcher, N as KnowledgeRetrievalBenchmarkCase, O as KnowledgeRetrievalBenchmarkQrel, P as KnowledgeRetrievalBenchmarkQuery, Q as MemoryAdapterBenchmarkCandidate, S as MemoryAdapterBenchmarkRankingRow, ag as RunKnowledgeBenchmarkSuiteOptions, ah as RunKnowledgeBenchmarkSuiteResult, ai as RunMemoryAdapterBenchmarkOptions, aj as RunMemoryAdapterBenchmarkResult, an as buildFirstPartyMemoryLifecycleBenchmarkCases, ao as buildIndustryMemoryBenchmarkSmokeCases, ap as buildIndustryRagBenchmarkSmokeCases, aq as buildKnowledgeBenchmarkScenarios, ar as buildRetrievalBenchmarkCasesFromQrels, au as createInMemoryBenchmarkAdapter, av as createNoopMemoryBenchmarkAdapter, ay as isKnowledgeMemoryBenchmarkCase, az as knowledgeBenchmarkJudge, aA as parseKnowledgeBenchmarkJsonl, aB as parseKnowledgeBenchmarkQrels, aC as renderKnowledgeBenchmarkReportMarkdown, aE as respondToIndustryMemoryBenchmarkSmokeCase, aF as respondToIndustryRagBenchmarkSmokeCase, aL as runKnowledgeBenchmarkSuite, aM as runMemoryAdapterBenchmark, aO as scoreKnowledgeBenchmarkArtifact, aP as scoreMemoryBenchmarkArtifact, aR as summarizeKnowledgeBenchmarkCampaign } from '../index-Bqg1mBPt.js';
+import { b as AgentMemoryAdapter, C as KnowledgeBenchmarkSpec, H as KnowledgeMemoryBenchmarkTaskKind, o as KnowledgeAnswerBenchmarkTaskKind, G as KnowledgeMemoryBenchmarkCase, q as KnowledgeBenchmarkCase, p as KnowledgeBenchmarkArtifact, ad as RunMemoryAdapterBenchmarkOptions, ae as RunMemoryAdapterBenchmarkResult, x as KnowledgeBenchmarkScenario, v as KnowledgeBenchmarkReport, B as BuildRetrievalBenchmarkCasesFromQrelsOptions, L as KnowledgeRetrievalBenchmarkCase, M as KnowledgeRetrievalBenchmarkQrel, t as KnowledgeBenchmarkEvaluation, D as KnowledgeBenchmarkSplit, ab as RunKnowledgeBenchmarkSuiteOptions, ac as RunKnowledgeBenchmarkSuiteResult } from '../types-ZzY_x0r7.js';
+export { K as KnowledgeAnswerBenchmarkCase, r as KnowledgeBenchmarkCaseBase, s as KnowledgeBenchmarkDistribution, u as KnowledgeBenchmarkFamily, w as KnowledgeBenchmarkResponder, y as KnowledgeBenchmarkSliceSummary, z as KnowledgeBenchmarkSource, E as KnowledgeBenchmarkTaskKind, F as KnowledgeClaimMatcher, I as KnowledgeMemoryEvent, J as KnowledgeMemoryFactMatcher, N as KnowledgeRetrievalBenchmarkQuery, O as MemoryAdapterBenchmarkCandidate, P as MemoryAdapterBenchmarkRankingRow } from '../types-ZzY_x0r7.js';
+import { CampaignResult, JudgeConfig } from '@tangle-network/agent-eval/campaign';
 import '../types-6x0OpfW6.js';
-import '@tangle-network/agent-eval/rl';
+
+declare function createNoopMemoryBenchmarkAdapter(id?: string): AgentMemoryAdapter;
+declare function createInMemoryBenchmarkAdapter(options?: {
+    id?: string;
+}): AgentMemoryAdapter;
+
+declare const INDUSTRY_RAG_BENCHMARKS: readonly (KnowledgeBenchmarkSpec & {
+    taskKind: 'retrieval' | KnowledgeAnswerBenchmarkTaskKind;
+})[];
+declare const INDUSTRY_MEMORY_BENCHMARKS: readonly (KnowledgeBenchmarkSpec & {
+    taskKind: KnowledgeMemoryBenchmarkTaskKind;
+})[];
+declare function buildIndustryRagBenchmarkSmokeCases(specs?: readonly (KnowledgeBenchmarkSpec & {
+    taskKind: 'retrieval' | KnowledgeAnswerBenchmarkTaskKind;
+})[]): KnowledgeBenchmarkCase[];
+declare function respondToIndustryRagBenchmarkSmokeCase(input: {
+    case: KnowledgeBenchmarkCase;
+}): KnowledgeBenchmarkArtifact;
+declare function buildIndustryMemoryBenchmarkSmokeCases(specs?: readonly (KnowledgeBenchmarkSpec & {
+    taskKind: KnowledgeMemoryBenchmarkTaskKind;
+})[]): KnowledgeMemoryBenchmarkCase[];
+declare function respondToIndustryMemoryBenchmarkSmokeCase(input: {
+    case: KnowledgeMemoryBenchmarkCase;
+}): KnowledgeBenchmarkArtifact;
+declare function buildFirstPartyMemoryLifecycleBenchmarkCases(): KnowledgeMemoryBenchmarkCase[];
+
+declare function runMemoryAdapterBenchmark(options: RunMemoryAdapterBenchmarkOptions): Promise<RunMemoryAdapterBenchmarkResult>;
+
+declare function summarizeKnowledgeBenchmarkCampaign<TArtifact>(input: {
+    scenarios: readonly KnowledgeBenchmarkScenario[];
+    campaign: CampaignResult<TArtifact, KnowledgeBenchmarkScenario>;
+}): KnowledgeBenchmarkReport;
+
+declare function parseKnowledgeBenchmarkJsonl<T = unknown>(text: string): T[];
+declare function parseKnowledgeBenchmarkQrels(text: string): KnowledgeRetrievalBenchmarkQrel[];
+declare function buildRetrievalBenchmarkCasesFromQrels(options: BuildRetrievalBenchmarkCasesFromQrelsOptions): KnowledgeRetrievalBenchmarkCase[];
+
+declare function scoreKnowledgeBenchmarkArtifact<TArtifact>(testCase: KnowledgeBenchmarkCase, artifact: TArtifact): KnowledgeBenchmarkEvaluation;
+declare function scoreMemoryBenchmarkArtifact<TArtifact>(testCase: KnowledgeMemoryBenchmarkCase, artifact: TArtifact): KnowledgeBenchmarkEvaluation;
+
+declare function runKnowledgeBenchmarkSuite<TArtifact = KnowledgeBenchmarkArtifact>(options: RunKnowledgeBenchmarkSuiteOptions<TArtifact>): Promise<RunKnowledgeBenchmarkSuiteResult<TArtifact>>;
+declare function renderKnowledgeBenchmarkReportMarkdown(report: KnowledgeBenchmarkReport): string;
+declare function buildKnowledgeBenchmarkScenarios(cases: readonly KnowledgeBenchmarkCase[], splits?: readonly KnowledgeBenchmarkSplit[]): KnowledgeBenchmarkScenario[];
+declare function knowledgeBenchmarkJudge<TArtifact = KnowledgeBenchmarkArtifact>(): JudgeConfig<TArtifact, KnowledgeBenchmarkScenario>;
+
+declare function isKnowledgeMemoryBenchmarkCase(testCase: KnowledgeBenchmarkCase): testCase is KnowledgeMemoryBenchmarkCase;
+
+export { BuildRetrievalBenchmarkCasesFromQrelsOptions, INDUSTRY_MEMORY_BENCHMARKS, INDUSTRY_RAG_BENCHMARKS, KnowledgeAnswerBenchmarkTaskKind, KnowledgeBenchmarkArtifact, KnowledgeBenchmarkCase, KnowledgeBenchmarkEvaluation, KnowledgeBenchmarkReport, KnowledgeBenchmarkScenario, KnowledgeBenchmarkSpec, KnowledgeBenchmarkSplit, KnowledgeMemoryBenchmarkCase, KnowledgeMemoryBenchmarkTaskKind, KnowledgeRetrievalBenchmarkCase, KnowledgeRetrievalBenchmarkQrel, RunKnowledgeBenchmarkSuiteOptions, RunKnowledgeBenchmarkSuiteResult, RunMemoryAdapterBenchmarkOptions, RunMemoryAdapterBenchmarkResult, buildFirstPartyMemoryLifecycleBenchmarkCases, buildIndustryMemoryBenchmarkSmokeCases, buildIndustryRagBenchmarkSmokeCases, buildKnowledgeBenchmarkScenarios, buildRetrievalBenchmarkCasesFromQrels, createInMemoryBenchmarkAdapter, createNoopMemoryBenchmarkAdapter, isKnowledgeMemoryBenchmarkCase, knowledgeBenchmarkJudge, parseKnowledgeBenchmarkJsonl, parseKnowledgeBenchmarkQrels, renderKnowledgeBenchmarkReportMarkdown, respondToIndustryMemoryBenchmarkSmokeCase, respondToIndustryRagBenchmarkSmokeCase, runKnowledgeBenchmarkSuite, runMemoryAdapterBenchmark, scoreKnowledgeBenchmarkArtifact, scoreMemoryBenchmarkArtifact, summarizeKnowledgeBenchmarkCampaign };

package/dist/benchmarks/index.js

@@ -20,7 +20,7 @@ import {
   scoreKnowledgeBenchmarkArtifact,
   scoreMemoryBenchmarkArtifact,
   summarizeKnowledgeBenchmarkCampaign
-} from "../chunk-DW6APRTX.js";
+} from "../chunk-BBCIB4UL.js";
 import "../chunk-DQ3PDMDP.js";
 import "../chunk-YMKHCTS2.js";
 export {