@tangle-network/agent-knowledge 19.1.1 → 19.1.5

package/CHANGELOG.md

@@ -1,3 +1,27 @@
+## 19.1.5
+
+Publish the Eval 0.208 qualification. The play-memory tests gave their fixture Hindsight a 10 ms ingestion deadline on every path; on a loaded self-hosted runner a write that completes at once missed it and the 19.1.4 publish failed. Success paths now get 10 s; only the unresolved-path test keeps 10 ms.
+
+## 19.1.4
+
+Publish 19.1.3's Eval 0.208 qualification. The version-bump check no longer compares a tag push in CI against the `origin/main` a reused self-hosted workspace kept from an earlier job, which refused the 19.1.3 publish (`origin/main shares no history with HEAD`).
+
+## 19.1.3
+
+Qualify Eval 0.208 for packed consumers and official GEPA/SkillOpt integration, and develop against 0.208.2.
+Eval 0.208.1 gives the optimizer bridge its interpreter's loader path, which a shared-library Python needs.
+
+## 19.1.2
+
+Make knowledge tools fast when many directors share one process and one store.
+Same-process writers queue in arrival order in front of the cross-process file lock, and reads share that admission, so a same-process write never restarts a read and no writer polls with backoff.
+Searches persist content-addressed visibility snapshots without the mutation lock and without moving the epoch.
+Tool views re-read and re-hash only page files whose identity changed, concurrent calls share one refresh, and the stores of the current view stay cached regardless of size.
+Transactions sync independent files concurrently and drop a repeated directory sync.
+Every tool result reports `timing`: `viewMs`, `visibilityMs`, `lockWaitMs` and `lockHoldMs`.
+A mutation started inside a read of the same store now fails instead of livelocking the read.
+Tool names, inputs, receipts, snapshot bytes, transactions and storage formats are unchanged.
+
 ## 19.1.1
 
 Qualify Eval 0.206 and 0.207 for packed consumers and official GEPA/SkillOpt integration.

package/README.md

@@ -9,13 +9,13 @@ Supply application callbacks for those decisions, or use `@tangle-network/agent-
 ## Install
 
 ```bash
-pnpm add @tangle-network/agent-knowledge@19.1.1 @tangle-network/agent-eval@0.207.0 @tangle-network/agent-interface@2.16.0
+pnpm add @tangle-network/agent-knowledge@19.1.5 @tangle-network/agent-eval@0.208.2 @tangle-network/agent-interface@2.16.0
 ```
 
 Requires Node.js 22.12 or later and Interface 2.16 or later within v2, matching the Sandbox dependency.
 
-Eval 0.201 through 0.207 are supported.
-Package and official optimizer checks exercise each supported minor; development uses 0.207.0.
+Eval 0.201 through 0.208 are supported.
+Package and official optimizer checks exercise each supported minor; development uses 0.208.2.
 These releases use Core 0.10, Trace Contract 2, and Zod 4.6.5.
 Knowledge 19 requires TCloud 0.8 with Sandbox 0.58.4 or later in that minor.
 Use Knowledge 17 with older Eval releases.
@@ -213,6 +213,8 @@ Retrying an identical completed write is safe.
 It does not report a partial write as tool success.
 The lower-level `applyKnowledgeWriteBlocks` API retains its explicit `written` and `warnings` result for callers that inspect partial proposals.
 `knowledge_resolve` returns the resolution status of each reference.
+Every tool result carries `timing` in milliseconds: `viewMs` to obtain the current page view for search, read and resolve, `visibilityMs` to persist a search's snapshot, and `lockWaitMs` and `lockHoldMs` for a record.
+Tools re-read only the page files whose identity changed since the previous call, and concurrent calls share one refresh.
 
 Knowledge tools retain write history by default.
 Each transaction records the host actorId, runId, and exact prior and new bytes.

package/dist/benchmarks/index.js

@@ -1,2 +1,2 @@
-import { F as buildIndustryRagBenchmarkSmokeCases, H as createNoopMemoryBenchmarkAdapter, I as respondToIndustryMemoryBenchmarkSmokeCase, L as respondToIndustryRagBenchmarkSmokeCase, M as INDUSTRY_RAG_BENCHMARKS, N as buildFirstPartyMemoryLifecycleBenchmarkCases, P as buildIndustryMemoryBenchmarkSmokeCases, R as isKnowledgeMemoryBenchmarkCase, V as createInMemoryBenchmarkAdapter, a as buildKnowledgeBenchmarkScenarios, c as runKnowledgeBenchmarkSuite, d as summarizeKnowledgeBenchmarkCampaign, i as runMemoryAdapterBenchmark, j as INDUSTRY_MEMORY_BENCHMARKS, l as scoreKnowledgeBenchmarkArtifact, n as parseKnowledgeBenchmarkJsonl, o as knowledgeBenchmarkJudge, r as parseKnowledgeBenchmarkQrels, s as renderKnowledgeBenchmarkReportMarkdown, t as buildRetrievalBenchmarkCasesFromQrels, u as scoreMemoryBenchmarkArtifact } from "../benchmarks-B3kU-Yxz.js";
+import { F as buildIndustryRagBenchmarkSmokeCases, H as createNoopMemoryBenchmarkAdapter, I as respondToIndustryMemoryBenchmarkSmokeCase, L as respondToIndustryRagBenchmarkSmokeCase, M as INDUSTRY_RAG_BENCHMARKS, N as buildFirstPartyMemoryLifecycleBenchmarkCases, P as buildIndustryMemoryBenchmarkSmokeCases, R as isKnowledgeMemoryBenchmarkCase, V as createInMemoryBenchmarkAdapter, a as buildKnowledgeBenchmarkScenarios, c as runKnowledgeBenchmarkSuite, d as summarizeKnowledgeBenchmarkCampaign, i as runMemoryAdapterBenchmark, j as INDUSTRY_MEMORY_BENCHMARKS, l as scoreKnowledgeBenchmarkArtifact, n as parseKnowledgeBenchmarkJsonl, o as knowledgeBenchmarkJudge, r as parseKnowledgeBenchmarkQrels, s as renderKnowledgeBenchmarkReportMarkdown, t as buildRetrievalBenchmarkCasesFromQrels, u as scoreMemoryBenchmarkArtifact } from "../benchmarks-BjXxjAke.js";
 export { INDUSTRY_MEMORY_BENCHMARKS, INDUSTRY_RAG_BENCHMARKS, buildFirstPartyMemoryLifecycleBenchmarkCases, buildIndustryMemoryBenchmarkSmokeCases, buildIndustryRagBenchmarkSmokeCases, buildKnowledgeBenchmarkScenarios, buildRetrievalBenchmarkCasesFromQrels, createInMemoryBenchmarkAdapter, createNoopMemoryBenchmarkAdapter, isKnowledgeMemoryBenchmarkCase, knowledgeBenchmarkJudge, parseKnowledgeBenchmarkJsonl, parseKnowledgeBenchmarkQrels, renderKnowledgeBenchmarkReportMarkdown, respondToIndustryMemoryBenchmarkSmokeCase, respondToIndustryRagBenchmarkSmokeCase, runKnowledgeBenchmarkSuite, runMemoryAdapterBenchmark, scoreKnowledgeBenchmarkArtifact, scoreMemoryBenchmarkArtifact, summarizeKnowledgeBenchmarkCampaign };

package/dist/{benchmarks-B3kU-Yxz.js → benchmarks-BjXxjAke.js}

@@ -1,5 +1,5 @@
 import { r as stableId, t as sha256 } from "./ids-Bevz_pXV.js";
-import { r as searchKnowledge } from "./search-Cbyj2shJ.js";
+import { r as searchKnowledge } from "./search-BBr5eUyT.js";
 import { randomUUID } from "node:crypto";
 import { join } from "node:path";
 import { canonicalJson } from "@tangle-network/agent-eval";
@@ -2821,4 +2821,4 @@ function defaultDocumentTarget(documentId, targetKind) {
 //#endregion
 export { reserveRecoveryAttempts as A, rankCandidates as B, sleepForMemoryRecovery as C, hasSettledPaidCall as D, assertNoInterruptedPaidCalls as E, buildIndustryRagBenchmarkSmokeCases as F, buildRetrievalEvalDispatch as G, createNoopMemoryBenchmarkAdapter as H, respondToIndustryMemoryBenchmarkSmokeCase as I, retrievalConfigSurface as J, partitionRetrievalScenarios as K, respondToIndustryRagBenchmarkSmokeCase as L, INDUSTRY_RAG_BENCHMARKS as M, buildFirstPartyMemoryLifecycleBenchmarkCases as N, readActiveAttemptJournal as O, buildIndustryMemoryBenchmarkSmokeCases as P, isKnowledgeMemoryBenchmarkCase as R, runBoundedMemoryLifecycle as S, appendDurableJournalEvent as T, memoryHitToSourceRecord as U, createInMemoryBenchmarkAdapter as V, memoryWriteResultToSourceRecord as W, scoreRetrievalArtifact as X, retrievalRecallJudge as Y, mean as Z, MEMORY_OPERATION_CANCELLATION_TIMEOUT_MS as _, buildKnowledgeBenchmarkScenarios as a, memoryRecoveryDelayMs as b, runKnowledgeBenchmarkSuite as c, summarizeKnowledgeBenchmarkCampaign as d, acquireAgentMemoryRunLease as f, MEMORY_CAMPAIGN_DISPATCH_SHUTDOWN_TIMEOUT_MS as g, DEFAULT_MEMORY_CLEANUP_TIMEOUT_MS as h, runMemoryAdapterBenchmark as i, INDUSTRY_MEMORY_BENCHMARKS as j, reconcileInterruptedMemoryPaidCalls as k, scoreKnowledgeBenchmarkArtifact as l, AgentMemoryLifecycleUnsafeError as m, parseKnowledgeBenchmarkJsonl as n, knowledgeBenchmarkJudge as o, AgentMemoryLifecycleTimeoutError as p, retrievalConfigFromSurface as q, parseKnowledgeBenchmarkQrels as r, renderKnowledgeBenchmarkReportMarkdown as s, buildRetrievalBenchmarkCasesFromQrels as t, scoreMemoryBenchmarkArtifact as u, createBoundedMemoryAdapter as v, appendAttemptJournalEvent as w, resolveMemoryCleanupTimeoutMs as x, createMemoryExecutionPool as y, normalizeUsd as z };
 
-//# sourceMappingURL=benchmarks-B3kU-Yxz.js.map
+//# sourceMappingURL=benchmarks-BjXxjAke.js.map