@tangle-network/agent-eval 0.144.1 → 0.144.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +30 -0
- package/dist/analyst/index.d.ts +9 -9
- package/dist/analyst/index.js +3 -3
- package/dist/{analyze-runs-BScZvqMV.js → analyze-runs-DWIvOAGk.js} +2 -2
- package/dist/{analyze-runs-BScZvqMV.js.map → analyze-runs-DWIvOAGk.js.map} +1 -1
- package/dist/{benchmark-DxaZfy0w.d.ts → benchmark-CP6kWfj8.d.ts} +3 -3
- package/dist/{benchmark-DxaZfy0w.d.ts.map → benchmark-CP6kWfj8.d.ts.map} +1 -1
- package/dist/{benchmark-command-95Zqd1e8.js → benchmark-command-9FTgq6Fg.js} +6 -6
- package/dist/{benchmark-command-95Zqd1e8.js.map → benchmark-command-9FTgq6Fg.js.map} +1 -1
- package/dist/benchmarks/index.d.ts +1 -1
- package/dist/benchmarks/index.js +1 -1
- package/dist/{benchmarks-CRT4ScEA.js → benchmarks-CkG1bWFa.js} +4 -4
- package/dist/{benchmarks-CRT4ScEA.js.map → benchmarks-CkG1bWFa.js.map} +1 -1
- package/dist/campaign/index.d.ts +4 -4
- package/dist/campaign/index.js +3 -3
- package/dist/{campaign-CefP3fPS.js → campaign-DjGFyPxH.js} +73 -39
- package/dist/campaign-DjGFyPxH.js.map +1 -0
- package/dist/cli.js +1 -1
- package/dist/{client-Cgl6KasJ.d.ts → client-Bbht4xxl.d.ts} +4 -4
- package/dist/{client-Cgl6KasJ.d.ts.map → client-Bbht4xxl.d.ts.map} +1 -1
- package/dist/{completion-verifier-D15NHYSk.d.ts → completion-verifier-EJERfFwF.d.ts} +3 -3
- package/dist/{completion-verifier-D15NHYSk.d.ts.map → completion-verifier-EJERfFwF.d.ts.map} +1 -1
- package/dist/contract/index.d.ts +8 -8
- package/dist/contract/index.js +9 -7
- package/dist/contract/index.js.map +1 -1
- package/dist/control.d.ts +2 -2
- package/dist/control.js +1 -1
- package/dist/{default-registry-D3uqKbo6.d.ts → default-registry-iXfu2trt.d.ts} +5 -5
- package/dist/{default-registry-D3uqKbo6.d.ts.map → default-registry-iXfu2trt.d.ts.map} +1 -1
- package/dist/{dspy-rlm-engine-BR7TtB0o.js → dspy-rlm-engine-IRCG8kdi.js} +2 -2
- package/dist/{dspy-rlm-engine-BR7TtB0o.js.map → dspy-rlm-engine-IRCG8kdi.js.map} +1 -1
- package/dist/{eval-campaign-lI7wB9DH.js → eval-campaign-lZcDIwQM.js} +2 -2
- package/dist/{eval-campaign-lI7wB9DH.js.map → eval-campaign-lZcDIwQM.js.map} +1 -1
- package/dist/{exact-types-B0lJV3tu.d.ts → exact-types-BygCBR4L.d.ts} +2 -2
- package/dist/{exact-types-B0lJV3tu.d.ts.map → exact-types-BygCBR4L.d.ts.map} +1 -1
- package/dist/{feedback-trajectory-BCHqzLh3.d.ts → feedback-trajectory-CSIkRLQX.d.ts} +3 -3
- package/dist/{feedback-trajectory-BCHqzLh3.d.ts.map → feedback-trajectory-CSIkRLQX.d.ts.map} +1 -1
- package/dist/hosted/index.d.ts +3 -3
- package/dist/{index-BrpxwELi.d.ts → index-BuHs_OnD.d.ts} +17 -12
- package/dist/{index-BrpxwELi.d.ts.map → index-BuHs_OnD.d.ts.map} +1 -1
- package/dist/{index-D2enbqA0.d.ts → index-CNOCxBLh.d.ts} +2 -2
- package/dist/{index-D2enbqA0.d.ts.map → index-CNOCxBLh.d.ts.map} +1 -1
- package/dist/{index-DFLVtPZ9.d.ts → index-DGIzNtRv.d.ts} +2 -2
- package/dist/{index-DFLVtPZ9.d.ts.map → index-DGIzNtRv.d.ts.map} +1 -1
- package/dist/{index-DRI1DU5z.d.ts → index-D_qTihaQ.d.ts} +5 -5
- package/dist/{index-DRI1DU5z.d.ts.map → index-D_qTihaQ.d.ts.map} +1 -1
- package/dist/index.d.ts +20 -20
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +15 -15
- package/dist/{insight-report-Bh_8ksel.d.ts → insight-report-D5m1z0_n.d.ts} +3 -3
- package/dist/{insight-report-Bh_8ksel.d.ts.map → insight-report-D5m1z0_n.d.ts.map} +1 -1
- package/dist/ledger-core/index.js +1 -1
- package/dist/{ledger-core-Dxz0Rkwa.js → ledger-core-DXZIqu17.js} +3 -3
- package/dist/ledger-core-DXZIqu17.js.map +1 -0
- package/dist/meta-eval/index.d.ts +1 -1
- package/dist/{mint-Ctwk079K.js → mint-DD-0oQTA.js} +2 -2
- package/dist/{mint-Ctwk079K.js.map → mint-DD-0oQTA.js.map} +1 -1
- package/dist/multishot/index.d.ts +1 -1
- package/dist/openapi.json +1 -1
- package/dist/{propose-review-control-DLXz4FCX.js → propose-review-control-BciUCZoh.js} +2 -2
- package/dist/{propose-review-control-DLXz4FCX.js.map → propose-review-control-BciUCZoh.js.map} +1 -1
- package/dist/{release-report-B_bQOHM-.d.ts → release-report-BZRWdq_t.d.ts} +3 -3
- package/dist/{release-report-B_bQOHM-.d.ts.map → release-report-BZRWdq_t.d.ts.map} +1 -1
- package/dist/{release-report-B5XPBvAU.js → release-report-Sl0xfkFv.js} +2 -2
- package/dist/{release-report-B5XPBvAU.js.map → release-report-Sl0xfkFv.js.map} +1 -1
- package/dist/{replay-DjUfTrHD.js → replay-CqOsGjzU.js} +2 -9
- package/dist/replay-CqOsGjzU.js.map +1 -0
- package/dist/{replay-BuJM6kLh.d.ts → replay-DQ-55DC_.d.ts} +4 -4
- package/dist/{replay-BuJM6kLh.d.ts.map → replay-DQ-55DC_.d.ts.map} +1 -1
- package/dist/reporting.d.ts +3 -3
- package/dist/reporting.js +1 -1
- package/dist/{researcher-C6lzl-rP.d.ts → researcher-BSiCoM1s.d.ts} +3 -3
- package/dist/{researcher-C6lzl-rP.d.ts.map → researcher-BSiCoM1s.d.ts.map} +1 -1
- package/dist/{reward-hacking-DjTi9HLb.js → reward-hacking-CyuzxKly.js} +2 -2
- package/dist/{reward-hacking-DjTi9HLb.js.map → reward-hacking-CyuzxKly.js.map} +1 -1
- package/dist/{reward-hacking-CEVVmy3h.d.ts → reward-hacking-DFgkEY4p.d.ts} +2 -2
- package/dist/{reward-hacking-CEVVmy3h.d.ts.map → reward-hacking-DFgkEY4p.d.ts.map} +1 -1
- package/dist/rl.d.ts +5 -5
- package/dist/rl.js +4 -4
- package/dist/rollout/index.d.ts +1 -1
- package/dist/rollout/index.js +2 -2
- package/dist/{rollout-8nj3mYvx.js → rollout-C2fD1cf4.js} +2 -2
- package/dist/{rollout-8nj3mYvx.js.map → rollout-C2fD1cf4.js.map} +1 -1
- package/dist/{rubric-predictive-validity-C2CthIfY.d.ts → rubric-predictive-validity-C4r4Y-q8.d.ts} +2 -2
- package/dist/{rubric-predictive-validity-C2CthIfY.d.ts.map → rubric-predictive-validity-C4r4Y-q8.d.ts.map} +1 -1
- package/dist/{run-evidence-8Ou28QSa.d.ts → run-evidence-H1vRpIdT.d.ts} +3 -3
- package/dist/{run-evidence-8Ou28QSa.d.ts.map → run-evidence-H1vRpIdT.d.ts.map} +1 -1
- package/dist/{run-record-vRgqWmJw.js → run-record-CWN8-VsV.js} +40 -14
- package/dist/{run-record-vRgqWmJw.js.map → run-record-CWN8-VsV.js.map} +1 -1
- package/dist/{run-record-Tb3TTtUn.d.ts → run-record-ooo9FWns.d.ts} +5 -9
- package/dist/{run-record-Tb3TTtUn.d.ts.map → run-record-ooo9FWns.d.ts.map} +1 -1
- package/dist/{semantic-concept-judge-l8Lb3Kqz.js → semantic-concept-judge-Do5aM9wP.js} +2 -2
- package/dist/{semantic-concept-judge-l8Lb3Kqz.js.map → semantic-concept-judge-Do5aM9wP.js.map} +1 -1
- package/dist/{single-run-lock-B-cFnnNn.js → single-run-lock-D5iN0Xzb.js} +2 -2
- package/dist/{single-run-lock-B-cFnnNn.js.map → single-run-lock-D5iN0Xzb.js.map} +1 -1
- package/dist/{skill-usage-3vUWdZ9n.d.ts → skill-usage-DtpLou9L.d.ts} +6 -6
- package/dist/{skill-usage-3vUWdZ9n.d.ts.map → skill-usage-DtpLou9L.d.ts.map} +1 -1
- package/dist/{skillopt-optimization-method-DA5mJmFE.js → skillopt-optimization-method-C4FX42dy.js} +29 -8
- package/dist/skillopt-optimization-method-C4FX42dy.js.map +1 -0
- package/dist/{skillopt-optimization-method-DNniakI5.d.ts → skillopt-optimization-method-CvSJGdm3.d.ts} +7 -7
- package/dist/{skillopt-optimization-method-DNniakI5.d.ts.map → skillopt-optimization-method-CvSJGdm3.d.ts.map} +1 -1
- package/dist/{summary-report-o3eJ3gxG.d.ts → summary-report-BOM6dfP7.d.ts} +2 -2
- package/dist/{summary-report-o3eJ3gxG.d.ts.map → summary-report-BOM6dfP7.d.ts.map} +1 -1
- package/dist/{tool-groups-Bqy4A3QB.d.ts → tool-groups-CMmsgTzj.d.ts} +7 -7
- package/dist/{tool-groups-Bqy4A3QB.d.ts.map → tool-groups-CMmsgTzj.d.ts.map} +1 -1
- package/dist/traces.d.ts +4 -4
- package/dist/traces.js +1 -1
- package/dist/{types-KEqL1pZc.d.ts → types-DcJxgsLy.d.ts} +8 -6
- package/dist/{types-KEqL1pZc.d.ts.map → types-DcJxgsLy.d.ts.map} +1 -1
- package/dist/{types-D3jh6F98.d.ts → types-y8jrxXWd.d.ts} +2 -2
- package/dist/{types-D3jh6F98.d.ts.map → types-y8jrxXWd.d.ts.map} +1 -1
- package/dist/wire/index.d.ts +1 -1
- package/docs/eval-surface-map.md +4 -0
- package/package.json +3 -3
- package/dist/campaign-CefP3fPS.js.map +0 -1
- package/dist/ledger-core-Dxz0Rkwa.js.map +0 -1
- package/dist/replay-DjUfTrHD.js.map +0 -1
- package/dist/skillopt-optimization-method-DA5mJmFE.js.map +0 -1
|
@@ -5,9 +5,9 @@ import { c as callLlmJson, r as LlmResponseError, t as LlmCallError } from "./ll
|
|
|
5
5
|
import { O as evidenceRefsFromRawFinding, h as TRACE_ANALYSIS_LIMITS, i as runTraceAnalyst } from "./kind-factory-Bvwe3pup.js";
|
|
6
6
|
import { o as makeFinding, r as usageReceiptFromCostLedger } from "./usage-receipt-CgxMEBZq.js";
|
|
7
7
|
import { i as hashCanonical, r as canonicalString } from "./canonical-D011XM8r.js";
|
|
8
|
-
import { M as resolveExternalOptimizerProcessLimits, f as runWithCleanup, n as createRunCostLedger, p as startExternalOptimizerModelProxy, r as fsCampaignStorage, t as acquireSingleRunLock } from "./single-run-lock-
|
|
9
|
-
import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-
|
|
10
|
-
import { c as writeLedgerFileAtomically, s as withLedgerFileLock } from "./ledger-core-
|
|
8
|
+
import { M as resolveExternalOptimizerProcessLimits, f as runWithCleanup, n as createRunCostLedger, p as startExternalOptimizerModelProxy, r as fsCampaignStorage, t as acquireSingleRunLock } from "./single-run-lock-D5iN0Xzb.js";
|
|
9
|
+
import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-IRCG8kdi.js";
|
|
10
|
+
import { c as writeLedgerFileAtomically, s as withLedgerFileLock } from "./ledger-core-DXZIqu17.js";
|
|
11
11
|
import { E as pairedBootstrap } from "./statistics-ByxzSiOM.js";
|
|
12
12
|
import { i as otlpTextToTraceAnalysisStore, r as createOtlpBufferTraceStore, t as DEFAULT_MAX_TRACE_FILE_BYTES } from "./store-otlp-D4I90_vR.js";
|
|
13
13
|
import { i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver } from "./benchmark-CYtcIF2V.js";
|
|
@@ -1200,7 +1200,7 @@ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
|
|
|
1200
1200
|
"package.json",
|
|
1201
1201
|
"pnpm-lock.yaml"
|
|
1202
1202
|
]);
|
|
1203
|
-
const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "
|
|
1203
|
+
const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "6d84e54943016e204ddfca4ac7a3cb17508913f3a43201d09c13a82f1f07a318";
|
|
1204
1204
|
/** The published benchmark evidence was produced at this package version, by
|
|
1205
1205
|
* the retired one-shot direct runner, before trace analysts moved to the
|
|
1206
1206
|
* recursive DSPy RLM engine. Both evidence digests below are historical facts
|
|
@@ -1299,7 +1299,7 @@ const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
|
|
|
1299
1299
|
"src/trace/raw-provider-sink.ts",
|
|
1300
1300
|
"src/verdict-cache.ts"
|
|
1301
1301
|
]);
|
|
1302
|
-
const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "
|
|
1302
|
+
const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "67cd83aaaa158d44a9fa32e172cbe68fa97f01ae673ccb117469688b628bb9b1";
|
|
1303
1303
|
function analystBenchmarkImplementationDigest() {
|
|
1304
1304
|
return ANALYST_BENCHMARK_IMPLEMENTATION_SHA256;
|
|
1305
1305
|
}
|
|
@@ -5469,4 +5469,4 @@ function shellQuote(value) {
|
|
|
5469
5469
|
//#endregion
|
|
5470
5470
|
export { normalizeAgentRxCategory as $, parseVerificationOutcome as A, analystBenchmarkDependencyLockDigest as B, MAX_INCORRECT_BLOCK_STEPS as C, DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES as D, publicBenchmarkSystemPrompt as E, ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 as F, ANALYST_BENCHMARK_OBSERVATIONS_FILE as G, ANALYST_BENCHMARK_COST_LEDGER_FILE as H, ANALYST_BENCHMARK_EVIDENCE_PACKAGE_VERSION as I, summarizeAgentRxCalibration as J, AGENT_RX_UPSTREAM_REVISION as K, ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM as L, ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES as M, ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 as N, appendVerificationArtifactsToOtlp as O, ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 as P, agentRxPredictionsToFindings as Q, ANALYST_BENCHMARK_IMPLEMENTATION_FILES as R, MAX_INCORRECT_BLOCKS as S, publicBenchmarkRlmInstructions as T, ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE as U, analystBenchmarkImplementationDigest as V, ANALYST_BENCHMARK_MANIFEST_FILE as W, codeTracerPredictionsToFindings as X, codeTraceBenchCase as Y, agentRxBenchmarkCase as Z, compareAnalystRunners as _, preparePublicAnalystBenchmark as a, readAnalystInstructionsOverride as b, selectPublicBenchmarkRows as c, adaptPublicBenchmarkFindings as d, roundAgentRxStep as et, emptyPublicBenchmarkRunner as f, summarizeCodeTraceCalibration as g, renderCodeTraceCalibrationMarkdown as h, loadPublicBenchmarkRows as i, ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM as j, loadCodeTraceVerificationArtifacts as k, createPublicBenchmarkRlmRunner as l, readAnalystBenchmarkArtifact as m, runAnalystBenchmarkCommand as n, publicBenchmarkDistributions as o, expandCodeTraceFailureBlocks as p, renderAgentRxCalibrationMarkdown as q, renderAnalystBenchmarkMarkdown as r, publicBenchmarkSelectionReport as s, ANALYST_BENCHMARK_HELP as t, normalizeBenchmarkLabel as tt, createPublicBenchmarkDirectRunner as u, analystInstructionsOverrideFromText as v, publicBenchmarkProtocolSha256 as w, CODE_TRACE_BENCH_ANALYST_PROMPT as x, effectiveAnalystProtocolSha256 as y, ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 as z };
|
|
5471
5471
|
|
|
5472
|
-
//# sourceMappingURL=benchmark-command-
|
|
5472
|
+
//# sourceMappingURL=benchmark-command-9FTgq6Fg.js.map
|