@tangle-network/agent-eval 0.183.0 → 0.185.0

package/dist/{benchmark-command-NBrqNwgy.js → benchmark-command-kvq7yFY4.js}

@@ -1,19 +1,22 @@
 import { s as ValidationError, t as AgentEvalError } from "./errors-Dngq5h35.js";
-import { a as hashCanonical, i as compareCodeUnits, o as jsonDocument, r as canonicalString } from "./canonical-DPyQ_rpt.js";
+import { a as hashCanonical, i as compareCodeUnits, o as jsonDocument, r as canonicalString } from "./canonical-BsZVgBhW.js";
 import { r as pairedBootstrap } from "./paired-tests-C8iCsioC.js";
 import { a as resolveModelPricing } from "./metrics-DOMpkoeb.js";
 import { a as CostLedgerPersistenceError, i as CostLedger, n as CostCallConflictError, o as CostReceiptCaptureError, r as CostCeilingReachedError, s as CostReservationExceededError, t as CostAccountingIncompleteError } from "./cost-ledger-_IbkejCF.js";
-import { c as withLedgerFileLock, l as writeLedgerFileAtomically } from "./journal-Cs9f7385.js";
+import { c as withLedgerFileLock, l as writeLedgerFileAtomically } from "./journal-BuRLm6ho.js";
 import "./ledger-core/index.js";
-import { S as fsCampaignStorage, i as startExternalOptimizerModelProxy, r as runWithCleanup, x as createRunCostLedger, y as resolveExternalOptimizerProcessLimits } from "./external-optimizer-subprocess-CjguXN2e.js";
-import { r as makeFinding, s as usageReceiptFromCostLedger } from "./types-DQ0e2E7y.js";
-import { M as RawAnalystFindingSchema, N as evidenceRefsFromRawFinding, h as TRACE_ANALYSIS_LIMITS, j as RAW_FINDING_SCHEMA_PROMPT, r as runTraceAnalyst } from "./kind-factory-DxTzg32u.js";
+import { S as fsCampaignStorage, i as startExternalOptimizerModelProxy, r as runWithCleanup, x as createRunCostLedger, y as resolveExternalOptimizerProcessLimits } from "./external-optimizer-subprocess-DMgmqTB6.js";
+import { r as makeFinding } from "./types-C8VBbiw6.js";
+import { M as RawAnalystFindingSchema, N as evidenceRefsFromRawFinding, h as TRACE_ANALYSIS_LIMITS, j as RAW_FINDING_SCHEMA_PROMPT, r as runTraceAnalyst } from "./kind-factory-V79Hw0AU.js";
+import { r as usageReceiptFromCostLedger } from "./usage-receipt-Cx3xNeyB.js";
 import { a as callLlmJson, r as LlmResponseError, t as LlmCallError } from "./llm-client-DDhZ29Vm.js";
-import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-8pgBSiy7.js";
-import { i as otlpTextToTraceAnalysisStore, r as createOtlpBufferTraceStore, t as DEFAULT_MAX_TRACE_FILE_BYTES } from "./store-otlp-DAaEbMLf.js";
-import { i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver } from "./benchmark-DQKzykkO.js";
-import { n as acquireSingleRunLock } from "./external-optimizer-process-DIB4YWEe.js";
-import { c as primeProtocolSha256, d as runPrimeExchange, f as decodeReplyRows, n as buildPrimePrompt, p as assertEqualDeclarativeTerms, t as analystUsageReceiptFromPrimeUsage, u as projectPrimeTrajectory } from "./prime-protocol-6tZTVsWm.js";
+import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-BE9lCzzL.js";
+import { i as otlpTextToTraceAnalysisStore, r as createOtlpBufferTraceStore, t as DEFAULT_MAX_TRACE_FILE_BYTES } from "./store-otlp-2gYCy-v0.js";
+import { i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver } from "./benchmark-BeQJyrRC.js";
+import { n as acquireSingleRunLock } from "./external-optimizer-process-BbhvXTFx.js";
+import { t as assertEqualDeclarativeTerms } from "./equal-terms-Blx9Zk5I.js";
+import { c as primeProtocolSha256, d as runPrimeExchange, f as decodeReplyRows, n as buildPrimePrompt, t as analystUsageReceiptFromPrimeUsage, u as projectPrimeTrajectory } from "./prime-protocol-DcAK9pC8.js";
+import { t as nodeHttpPrimeBridgeTransport } from "./prime-bridge-transport-Z3cpKGoV.js";
 import { createHash, randomUUID } from "node:crypto";
 import { constants, existsSync, lstatSync, readFileSync } from "node:fs";
 import { z } from "zod";
@@ -22,9 +25,7 @@ import { dirname, isAbsolute, relative, resolve, sep } from "node:path";
 import { arch, platform } from "node:os";
 import { pathToFileURL } from "node:url";
 import { link, lstat, mkdir, open, readFile, readdir, realpath, stat, unlink } from "node:fs/promises";
-import { request } from "node:http";
 import { TextDecoder as TextDecoder$1 } from "node:util";
-import { request as request$1 } from "node:https";
 //#region src/analyst/benchmark-dataset-utils.ts
 function normalizeBenchmarkLabel(value) {
 	const normalized = nonEmpty$1(value, "benchmark label").toLowerCase().replace(/[^a-z0-9]+/g, "-").replace(/^-|-$/g, "");
@@ -1413,7 +1414,7 @@ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
 	"package.json",
 	"pnpm-lock.yaml"
 ]);
-const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "fe80b5a69feb434921d2508b57d93c1da2448771224bec07bf81f65921db78f9";
+const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "3c2fc1a6a3cb07b2c285736ef071f0d2cf02aaffe02d827bd69d3051f65262a9";
 const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
 const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
 const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
@@ -1526,7 +1527,7 @@ const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
 	"src/trace/raw-provider-sink.ts",
 	"src/verdict-cache.ts"
 ]);
-const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "956a7205aae4110a7b3dd927bef2c1098986e16cd89a17276791083219ade3fc";
+const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "dd54cb34dafbb0cab915e4223a387fbd1093ad8daa44b1230979bdeca71bf5ce";
 function analystBenchmarkImplementationDigest() {
 	return ANALYST_BENCHMARK_IMPLEMENTATION_SHA256;
 }
@@ -5203,44 +5204,6 @@ function rootAgent(row) {
 	return scalarDistributionValue(row.failures.find((failure) => String(failure.failure_id) === String(rootCauseId))?.failed_agent);
 }
 //#endregion
-//#region src/analyst/prime-bridge-transport.ts
-/**
-* Default transport on node:http/node:https rather than fetch: undici's fixed
-* response-header timeout kills prime calls that legitimately run past five
-* minutes, so the request's AbortSignal is the only deadline.
-*/
-function nodeHttpPrimeBridgeTransport() {
-	return ({ url, body, signal }) => {
-		const target = new URL(url);
-		if (target.protocol !== "http:" && target.protocol !== "https:") throw new TypeError(`bridge URL must be http: or https:, got ${target.protocol}`);
-		const send = target.protocol === "https:" ? request$1 : request;
-		const encoded = JSON.stringify(body);
-		return new Promise((resolvePromise, rejectPromise) => {
-			const req = send({
-				hostname: target.hostname,
-				port: target.port,
-				path: `${target.pathname}${target.search}`,
-				method: "POST",
-				headers: {
-					"content-type": "application/json",
-					"content-length": Buffer.byteLength(encoded)
-				},
-				signal
-			}, (res) => {
-				const chunks = [];
-				res.on("data", (chunk) => chunks.push(chunk));
-				res.on("end", () => resolvePromise({
-					status: res.statusCode ?? 0,
-					text: Buffer.concat(chunks).toString("utf8")
-				}));
-				res.on("error", rejectPromise);
-			});
-			req.on("error", rejectPromise);
-			req.end(encoded);
-		});
-	};
-}
-//#endregion
 //#region src/analyst/benchmark-runner-prime.ts
 /**
 * Prime analyst arm: the RLM coding agent reached through an OpenAI-compatible
@@ -6350,6 +6313,6 @@ function shellQuote(value) {
 	return /^[a-zA-Z0-9_./:@%+=,-]+$/.test(value) ? value : `'${value.replaceAll("'", "'\\''")}'`;
 }
 //#endregion
-export { ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE as $, effectiveAnalystProtocolSha256 as A, loadCodeTraceVerificationArtifacts as B, adaptPublicBenchmarkFindings as C, renderCodeTraceCalibrationMarkdown as D, readAnalystBenchmarkArtifact as E, publicBenchmarkProtocolSha256 as F, ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 as G, ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM as H, publicBenchmarkRlmInstructions as I, ANALYST_BENCHMARK_IMPLEMENTATION_FILES as J, ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 as K, publicBenchmarkSystemPrompt as L, CODE_TRACE_BENCH_ANALYST_PROMPT as M, MAX_INCORRECT_BLOCKS as N, summarizeCodeTraceCalibration as O, MAX_INCORRECT_BLOCK_STEPS as P, ANALYST_BENCHMARK_COST_LEDGER_FILE as Q, DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES as R, analystDefinitionProtocolSha256 as S, expandCodeTraceFailureBlocks as T, ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES as U, parseVerificationOutcome as V, ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 as W, analystBenchmarkDependencyLockDigest as X, ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 as Y, analystBenchmarkImplementationDigest as Z, createPublicBenchmarkDirectRunner as _, primeCodeTraceAnalystDefinition as a, summarizeAgentRxCalibration as at, AnalystExpressivenessError as b, loadPublicBenchmarkRows as c, agentRxBenchmarkCase as ct, publicBenchmarkSelectionReport as d, roundAgentRxStep as dt, ANALYST_BENCHMARK_MANIFEST_FILE as et, selectPublicBenchmarkRows as f, normalizeBenchmarkLabel as ft, runReplVariableAnalystDefinition as g, rlmEngineLimits as h, primeAnalystProtocolSha256 as i, renderAgentRxCalibrationMarkdown as it, readAnalystInstructionsOverride as j, analystInstructionsOverrideFromText as k, preparePublicAnalystBenchmark as l, agentRxPredictionsToFindings as lt, publicRlmAnalystDefinition as m, renderAnalystBenchmarkMarkdown as n, compareAnalystRunners as nt, runInlineAnalystDefinition as o, codeTraceBenchCase as ot, createPublicBenchmarkRlmRunner as p, ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM as q, createPrimeBenchmarkRunner as r, AGENT_RX_UPSTREAM_REVISION as rt, nodeHttpPrimeBridgeTransport as s, codeTracerPredictionsToFindings as st, runAnalystBenchmarkCommand as t, ANALYST_BENCHMARK_OBSERVATIONS_FILE as tt, publicBenchmarkDistributions as u, normalizeAgentRxCategory as ut, publicDirectAnalystDefinition as v, emptyPublicBenchmarkRunner as w, analystDefinitionAsymmetries as x, runChunkedAnalystDefinition as y, appendVerificationArtifactsToOtlp as z };
+export { ANALYST_BENCHMARK_MANIFEST_FILE as $, readAnalystInstructionsOverride as A, parseVerificationOutcome as B, emptyPublicBenchmarkRunner as C, summarizeCodeTraceCalibration as D, renderCodeTraceCalibrationMarkdown as E, publicBenchmarkRlmInstructions as F, ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 as G, ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES as H, publicBenchmarkSystemPrompt as I, ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 as J, ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM as K, DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES as L, MAX_INCORRECT_BLOCKS as M, MAX_INCORRECT_BLOCK_STEPS as N, analystInstructionsOverrideFromText as O, publicBenchmarkProtocolSha256 as P, ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE as Q, appendVerificationArtifactsToOtlp as R, adaptPublicBenchmarkFindings as S, readAnalystBenchmarkArtifact as T, ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 as U, ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM as V, ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 as W, analystBenchmarkImplementationDigest as X, analystBenchmarkDependencyLockDigest as Y, ANALYST_BENCHMARK_COST_LEDGER_FILE as Z, publicDirectAnalystDefinition as _, primeCodeTraceAnalystDefinition as a, codeTraceBenchCase as at, analystDefinitionAsymmetries as b, preparePublicAnalystBenchmark as c, agentRxPredictionsToFindings as ct, selectPublicBenchmarkRows as d, normalizeBenchmarkLabel as dt, ANALYST_BENCHMARK_OBSERVATIONS_FILE as et, createPublicBenchmarkRlmRunner as f, createPublicBenchmarkDirectRunner as g, runReplVariableAnalystDefinition as h, primeAnalystProtocolSha256 as i, summarizeAgentRxCalibration as it, CODE_TRACE_BENCH_ANALYST_PROMPT as j, effectiveAnalystProtocolSha256 as k, publicBenchmarkDistributions as l, normalizeAgentRxCategory as lt, rlmEngineLimits as m, renderAnalystBenchmarkMarkdown as n, AGENT_RX_UPSTREAM_REVISION as nt, runInlineAnalystDefinition as o, codeTracerPredictionsToFindings as ot, publicRlmAnalystDefinition as p, ANALYST_BENCHMARK_IMPLEMENTATION_FILES as q, createPrimeBenchmarkRunner as r, renderAgentRxCalibrationMarkdown as rt, loadPublicBenchmarkRows as s, agentRxBenchmarkCase as st, runAnalystBenchmarkCommand as t, compareAnalystRunners as tt, publicBenchmarkSelectionReport as u, roundAgentRxStep as ut, runChunkedAnalystDefinition as v, expandCodeTraceFailureBlocks as w, analystDefinitionProtocolSha256 as x, AnalystExpressivenessError as y, loadCodeTraceVerificationArtifacts as z };
 
-//# sourceMappingURL=benchmark-command-NBrqNwgy.js.map
+//# sourceMappingURL=benchmark-command-kvq7yFY4.js.map