agentv 4.40.1 → 4.41.0-next.1
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/dist/{artifact-writer-GIAIMGPQ.js → artifact-writer-AMV64TWV.js} +4 -4
- package/dist/{chunk-B7CT3J2W.js → chunk-6FXICR66.js} +899 -300
- package/dist/chunk-6FXICR66.js.map +1 -0
- package/dist/{chunk-TWQP7JYQ.js → chunk-A4J456KS.js} +2 -2
- package/dist/{chunk-A36XLUI5.js → chunk-CF5RCUWH.js} +12 -10
- package/dist/chunk-CF5RCUWH.js.map +1 -0
- package/dist/{chunk-BLXYBUU4.js → chunk-ENHX2CCS.js} +1485 -943
- package/dist/chunk-ENHX2CCS.js.map +1 -0
- package/dist/{chunk-I3SC4FOT.js → chunk-Z45FKRMJ.js} +212 -58
- package/dist/chunk-Z45FKRMJ.js.map +1 -0
- package/dist/cli.js +5 -5
- package/dist/{dist-6Z4OSITR.js → dist-X5P5IR65.js} +7 -3
- package/dist/index.js +5 -5
- package/dist/{interactive-Q575M3A7.js → interactive-4JKJTY3G.js} +5 -5
- package/dist/skills/agentv-bench/references/eval-yaml-spec.md +4 -4
- package/dist/skills/agentv-eval-writer/references/custom-evaluators.md +14 -14
- package/dist/skills/agentv-eval-writer/references/python-helpers.md +47 -0
- package/dist/{ts-eval-loader-NWH3B4HG-UXXCZKLP.js → ts-eval-loader-ZVL6CGTE-TZYZX3QS.js} +2 -2
- package/package.json +1 -1
- package/dist/chunk-A36XLUI5.js.map +0 -1
- package/dist/chunk-B7CT3J2W.js.map +0 -1
- package/dist/chunk-BLXYBUU4.js.map +0 -1
- package/dist/chunk-I3SC4FOT.js.map +0 -1
- /package/dist/{artifact-writer-GIAIMGPQ.js.map → artifact-writer-AMV64TWV.js.map} +0 -0
- /package/dist/{chunk-TWQP7JYQ.js.map → chunk-A4J456KS.js.map} +0 -0
- /package/dist/{dist-6Z4OSITR.js.map → dist-X5P5IR65.js.map} +0 -0
- /package/dist/{interactive-Q575M3A7.js.map → interactive-4JKJTY3G.js.map} +0 -0
- /package/dist/{ts-eval-loader-NWH3B4HG-UXXCZKLP.js.map → ts-eval-loader-ZVL6CGTE-TZYZX3QS.js.map} +0 -0
|
@@ -5,7 +5,7 @@ import {
|
|
|
5
5
|
parseYamlValue,
|
|
6
6
|
writeArtifactsFromResults,
|
|
7
7
|
writePerTestArtifacts
|
|
8
|
-
} from "./chunk-
|
|
8
|
+
} from "./chunk-ENHX2CCS.js";
|
|
9
9
|
|
|
10
10
|
// src/commands/eval/artifact-writer.ts
|
|
11
11
|
import path2 from "node:path";
|
|
@@ -491,4 +491,4 @@ export {
|
|
|
491
491
|
writePerTestArtifacts2 as writePerTestArtifacts,
|
|
492
492
|
writeArtifactsFromResults2 as writeArtifactsFromResults
|
|
493
493
|
};
|
|
494
|
-
//# sourceMappingURL=chunk-
|
|
494
|
+
//# sourceMappingURL=chunk-A4J456KS.js.map
|
|
@@ -2,7 +2,7 @@ import { createRequire } from 'node:module'; const require = createRequire(impor
|
|
|
2
2
|
import {
|
|
3
3
|
toSnakeCaseDeep as toSnakeCaseDeep2,
|
|
4
4
|
writeArtifactsFromResults
|
|
5
|
-
} from "./chunk-
|
|
5
|
+
} from "./chunk-A4J456KS.js";
|
|
6
6
|
import {
|
|
7
7
|
RunBudgetTracker,
|
|
8
8
|
buildWipBranchName,
|
|
@@ -19,7 +19,7 @@ import {
|
|
|
19
19
|
resolveResultsRepoRunsDir,
|
|
20
20
|
setupWipWorktree,
|
|
21
21
|
syncResultsRepoForProject
|
|
22
|
-
} from "./chunk-
|
|
22
|
+
} from "./chunk-Z45FKRMJ.js";
|
|
23
23
|
import {
|
|
24
24
|
CLI_PLACEHOLDERS,
|
|
25
25
|
COMMON_TARGET_SETTINGS,
|
|
@@ -67,7 +67,7 @@ import {
|
|
|
67
67
|
toSnakeCaseDeep,
|
|
68
68
|
traceFromTranscriptJsonLines,
|
|
69
69
|
writeInitialBenchmarkArtifact
|
|
70
|
-
} from "./chunk-
|
|
70
|
+
} from "./chunk-ENHX2CCS.js";
|
|
71
71
|
|
|
72
72
|
// src/commands/eval/shared.ts
|
|
73
73
|
import { constants } from "node:fs";
|
|
@@ -183,7 +183,7 @@ async function findRepoRoot(start) {
|
|
|
183
183
|
// package.json
|
|
184
184
|
var package_default = {
|
|
185
185
|
name: "agentv",
|
|
186
|
-
version: "4.
|
|
186
|
+
version: "4.41.0-next.1",
|
|
187
187
|
description: "CLI entry point for AgentV",
|
|
188
188
|
type: "module",
|
|
189
189
|
repository: {
|
|
@@ -3526,7 +3526,7 @@ var COPILOT_SDK_SETTINGS = /* @__PURE__ */ new Set([
|
|
|
3526
3526
|
"api_key",
|
|
3527
3527
|
"bearer_token",
|
|
3528
3528
|
"api_version",
|
|
3529
|
-
"
|
|
3529
|
+
"api_format"
|
|
3530
3530
|
]);
|
|
3531
3531
|
var COPILOT_CLI_SETTINGS = /* @__PURE__ */ new Set([
|
|
3532
3532
|
...COMMON_SETTINGS,
|
|
@@ -3547,7 +3547,7 @@ var COPILOT_CLI_SETTINGS = /* @__PURE__ */ new Set([
|
|
|
3547
3547
|
"api_key",
|
|
3548
3548
|
"bearer_token",
|
|
3549
3549
|
"api_version",
|
|
3550
|
-
"
|
|
3550
|
+
"api_format"
|
|
3551
3551
|
]);
|
|
3552
3552
|
var VSCODE_SETTINGS = /* @__PURE__ */ new Set([
|
|
3553
3553
|
...COMMON_SETTINGS,
|
|
@@ -5775,7 +5775,7 @@ async function runEvalCommand(input) {
|
|
|
5775
5775
|
const useFileExport = !!options.otelFile;
|
|
5776
5776
|
if (options.exportOtel || useFileExport) {
|
|
5777
5777
|
try {
|
|
5778
|
-
const { OtelTraceExporter } = await import("./dist-
|
|
5778
|
+
const { OtelTraceExporter } = await import("./dist-X5P5IR65.js");
|
|
5779
5779
|
let endpoint = process.env.OTEL_EXPORTER_OTLP_ENDPOINT;
|
|
5780
5780
|
let headers = {};
|
|
5781
5781
|
let resourceAttributes = {};
|
|
@@ -5980,7 +5980,7 @@ async function runEvalCommand(input) {
|
|
|
5980
5980
|
const activeTestFiles = resolvedTestFiles.filter((f) => fileMetadata.has(f));
|
|
5981
5981
|
let transcriptProviderFactory;
|
|
5982
5982
|
if (options.transcript) {
|
|
5983
|
-
const { TranscriptProvider } = await import("./dist-
|
|
5983
|
+
const { TranscriptProvider } = await import("./dist-X5P5IR65.js");
|
|
5984
5984
|
const transcriptProvider = await TranscriptProvider.fromFile(options.transcript);
|
|
5985
5985
|
const totalTests = [...fileMetadata.values()].reduce(
|
|
5986
5986
|
(sum, meta) => sum + meta.testCases.length,
|
|
@@ -6204,7 +6204,7 @@ ${formatRequiredVersionFailureNote(requiredVersionCheck)}`);
|
|
|
6204
6204
|
);
|
|
6205
6205
|
const taskBundleTargets = buildTaskBundleTargetSelections(activeTestFiles, fileMetadata);
|
|
6206
6206
|
if (isResumeAppend) {
|
|
6207
|
-
const { writePerTestArtifacts } = await import("./artifact-writer-
|
|
6207
|
+
const { writePerTestArtifacts } = await import("./artifact-writer-AMV64TWV.js");
|
|
6208
6208
|
await writePerTestArtifacts(allResults, runDir, {
|
|
6209
6209
|
experiment: normalizeExperimentName(options.experiment),
|
|
6210
6210
|
cwd,
|
|
@@ -6422,6 +6422,7 @@ export {
|
|
|
6422
6422
|
setRemoteRunTags,
|
|
6423
6423
|
clearRemoteRunTags,
|
|
6424
6424
|
maybeAutoExportRunArtifacts,
|
|
6425
|
+
loadEnvFromHierarchy,
|
|
6425
6426
|
resolveRunCacheFile,
|
|
6426
6427
|
loadRunCache,
|
|
6427
6428
|
detectFileType,
|
|
@@ -6434,9 +6435,10 @@ export {
|
|
|
6434
6435
|
TARGET_FILE_CANDIDATES,
|
|
6435
6436
|
fileExists,
|
|
6436
6437
|
selectTarget,
|
|
6438
|
+
selectMultipleTargets,
|
|
6437
6439
|
runEvalCommand,
|
|
6438
6440
|
discoverEvalFiles,
|
|
6439
6441
|
getCategories,
|
|
6440
6442
|
filterByCategory
|
|
6441
6443
|
};
|
|
6442
|
-
//# sourceMappingURL=chunk-
|
|
6444
|
+
//# sourceMappingURL=chunk-CF5RCUWH.js.map
|