agentv 3.9.2 → 3.10.1
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/{chunk-OIVGGWJ3.js → chunk-GWHHM6X2.js} +25 -14
- package/dist/chunk-GWHHM6X2.js.map +1 -0
- package/dist/{chunk-6ZAFWUBT.js → chunk-JLFFYTZA.js} +4 -4
- package/dist/{chunk-JGMJL2LV.js → chunk-TXCVDTEE.js} +8 -7
- package/dist/{chunk-JGMJL2LV.js.map → chunk-TXCVDTEE.js.map} +1 -1
- package/dist/cli.js +3 -3
- package/dist/{dist-PUPHGVKL.js → dist-FPC7J7KQ.js} +2 -2
- package/dist/index.js +3 -3
- package/dist/{interactive-BD56NB23.js → interactive-N463HRIL.js} +3 -3
- package/dist/templates/.agents/skills/agentv-chat-to-eval/README.md +84 -0
- package/dist/templates/.agents/skills/agentv-chat-to-eval/SKILL.md +144 -0
- package/dist/templates/.agents/skills/agentv-chat-to-eval/examples/transcript-json.md +67 -0
- package/dist/templates/.agents/skills/agentv-chat-to-eval/examples/transcript-markdown.md +101 -0
- package/dist/templates/.agents/skills/agentv-eval-builder/SKILL.md +458 -0
- package/dist/templates/.agents/skills/agentv-eval-builder/references/config-schema.json +36 -0
- package/dist/templates/.agents/skills/agentv-eval-builder/references/custom-evaluators.md +118 -0
- package/dist/templates/.agents/skills/agentv-eval-builder/references/eval-schema.json +12753 -0
- package/dist/templates/.agents/skills/agentv-eval-builder/references/rubric-evaluator.md +77 -0
- package/dist/templates/.agents/skills/agentv-eval-orchestrator/SKILL.md +50 -0
- package/dist/templates/.agents/skills/agentv-prompt-optimizer/SKILL.md +78 -0
- package/dist/templates/.agentv/.env.example +25 -0
- package/dist/templates/.claude/skills/agentv-eval-builder/SKILL.md +177 -0
- package/dist/templates/.claude/skills/agentv-eval-builder/references/batch-cli-evaluator.md +316 -0
- package/dist/templates/.claude/skills/agentv-eval-builder/references/compare-command.md +137 -0
- package/dist/templates/.claude/skills/agentv-eval-builder/references/composite-evaluator.md +215 -0
- package/dist/templates/.claude/skills/agentv-eval-builder/references/config-schema.json +27 -0
- package/dist/templates/.claude/skills/agentv-eval-builder/references/custom-evaluators.md +115 -0
- package/dist/templates/.claude/skills/agentv-eval-builder/references/eval-schema.json +278 -0
- package/dist/templates/.claude/skills/agentv-eval-builder/references/example-evals.md +333 -0
- package/dist/templates/.claude/skills/agentv-eval-builder/references/rubric-evaluator.md +79 -0
- package/dist/templates/.claude/skills/agentv-eval-builder/references/structured-data-evaluators.md +121 -0
- package/dist/templates/.claude/skills/agentv-eval-builder/references/tool-trajectory-evaluator.md +298 -0
- package/dist/templates/.claude/skills/agentv-prompt-optimizer/SKILL.md +78 -0
- package/dist/templates/.github/prompts/agentv-eval-build.prompt.md +5 -0
- package/dist/templates/.github/prompts/agentv-optimize.prompt.md +4 -0
- package/package.json +3 -3
- package/dist/chunk-OIVGGWJ3.js.map +0 -1
- /package/dist/{chunk-6ZAFWUBT.js.map → chunk-JLFFYTZA.js.map} +0 -0
- /package/dist/{dist-PUPHGVKL.js.map → dist-FPC7J7KQ.js.map} +0 -0
- /package/dist/{interactive-BD56NB23.js.map → interactive-N463HRIL.js.map} +0 -0
|
@@ -301,7 +301,7 @@ var require_dist = __commonJS({
|
|
|
301
301
|
}
|
|
302
302
|
});
|
|
303
303
|
|
|
304
|
-
// ../../packages/core/dist/chunk-
|
|
304
|
+
// ../../packages/core/dist/chunk-VCFYWLFV.js
|
|
305
305
|
import { constants } from "node:fs";
|
|
306
306
|
import { access, readFile } from "node:fs/promises";
|
|
307
307
|
import path from "node:path";
|
|
@@ -419,7 +419,7 @@ __export(external_exports2, {
|
|
|
419
419
|
void: () => voidType
|
|
420
420
|
});
|
|
421
421
|
|
|
422
|
-
// ../../packages/core/dist/chunk-
|
|
422
|
+
// ../../packages/core/dist/chunk-VCFYWLFV.js
|
|
423
423
|
import { readFile as readFile2 } from "node:fs/promises";
|
|
424
424
|
import path3 from "node:path";
|
|
425
425
|
import fg from "fast-glob";
|
|
@@ -840,7 +840,12 @@ function resolveTargetDefinition(definition, env = process.env, evalFilePath) {
|
|
|
840
840
|
`${parsed.name}: target-level workspace_template has been removed. Use eval-level workspace.template.`
|
|
841
841
|
);
|
|
842
842
|
}
|
|
843
|
-
const provider =
|
|
843
|
+
const provider = resolveString(
|
|
844
|
+
parsed.provider,
|
|
845
|
+
env,
|
|
846
|
+
`${parsed.name} provider`,
|
|
847
|
+
true
|
|
848
|
+
).toLowerCase();
|
|
844
849
|
const providerBatching = resolveOptionalBoolean(
|
|
845
850
|
parsed.provider_batching ?? parsed.providerBatching
|
|
846
851
|
);
|
|
@@ -20057,11 +20062,7 @@ var CopilotCliProvider = class {
|
|
|
20057
20062
|
}
|
|
20058
20063
|
}
|
|
20059
20064
|
if (sessionUpdate === "usage_update") {
|
|
20060
|
-
|
|
20061
|
-
tokenUsage = { input: update.used, output: tokenUsage.output };
|
|
20062
|
-
} else {
|
|
20063
|
-
tokenUsage = { input: update.used, output: 0 };
|
|
20064
|
-
}
|
|
20065
|
+
tokenUsage = { input: update.used, output: 0 };
|
|
20065
20066
|
if (update.cost && update.cost.currency === "USD") {
|
|
20066
20067
|
costUsd = (costUsd ?? 0) + update.cost.amount;
|
|
20067
20068
|
}
|
|
@@ -20095,21 +20096,32 @@ var CopilotCliProvider = class {
|
|
|
20095
20096
|
sessionId: session.sessionId,
|
|
20096
20097
|
prompt: promptMessages
|
|
20097
20098
|
});
|
|
20099
|
+
let promptResponse;
|
|
20098
20100
|
if (request.signal) {
|
|
20099
20101
|
const abortHandler = () => {
|
|
20100
20102
|
killProcess(agentProcess);
|
|
20101
20103
|
};
|
|
20102
20104
|
request.signal.addEventListener("abort", abortHandler, { once: true });
|
|
20103
20105
|
try {
|
|
20104
|
-
await this.raceWithTimeout(sendPromise, agentProcess);
|
|
20106
|
+
promptResponse = await this.raceWithTimeout(sendPromise, agentProcess);
|
|
20105
20107
|
} finally {
|
|
20106
20108
|
request.signal.removeEventListener("abort", abortHandler);
|
|
20107
20109
|
}
|
|
20108
20110
|
} else {
|
|
20109
|
-
await this.raceWithTimeout(sendPromise, agentProcess);
|
|
20111
|
+
promptResponse = await this.raceWithTimeout(sendPromise, agentProcess);
|
|
20110
20112
|
}
|
|
20111
20113
|
const endTime = (/* @__PURE__ */ new Date()).toISOString();
|
|
20112
20114
|
const durationMs = Date.now() - startMs;
|
|
20115
|
+
const responseUsage = promptResponse.usage;
|
|
20116
|
+
if (responseUsage && responseUsage.totalTokens > 0) {
|
|
20117
|
+
tokenUsage = {
|
|
20118
|
+
input: responseUsage.inputTokens,
|
|
20119
|
+
output: responseUsage.outputTokens,
|
|
20120
|
+
...responseUsage.thoughtTokens != null ? { reasoning: responseUsage.thoughtTokens } : {},
|
|
20121
|
+
...responseUsage.cachedReadTokens != null ? { cached: responseUsage.cachedReadTokens } : {}
|
|
20122
|
+
};
|
|
20123
|
+
request.streamCallbacks?.onLlmCallEnd?.("copilot", tokenUsage);
|
|
20124
|
+
}
|
|
20113
20125
|
const rejectedCalls = completedToolCalls.filter((tc) => {
|
|
20114
20126
|
const out = tc.output;
|
|
20115
20127
|
return out && (out.code === "rejected" || out.code === "denied");
|
|
@@ -20167,8 +20179,7 @@ var CopilotCliProvider = class {
|
|
|
20167
20179
|
async raceWithTimeout(sendPromise, agentProcess) {
|
|
20168
20180
|
const timeoutMs = this.config.timeoutMs;
|
|
20169
20181
|
if (!timeoutMs) {
|
|
20170
|
-
|
|
20171
|
-
return;
|
|
20182
|
+
return sendPromise;
|
|
20172
20183
|
}
|
|
20173
20184
|
let timer;
|
|
20174
20185
|
const timeoutPromise = new Promise((_, reject) => {
|
|
@@ -20179,7 +20190,7 @@ var CopilotCliProvider = class {
|
|
|
20179
20190
|
timer.unref?.();
|
|
20180
20191
|
});
|
|
20181
20192
|
try {
|
|
20182
|
-
await Promise.race([sendPromise, timeoutPromise]);
|
|
20193
|
+
return await Promise.race([sendPromise, timeoutPromise]);
|
|
20183
20194
|
} finally {
|
|
20184
20195
|
if (timer) clearTimeout(timer);
|
|
20185
20196
|
}
|
|
@@ -31051,4 +31062,4 @@ export {
|
|
|
31051
31062
|
OtelStreamingObserver,
|
|
31052
31063
|
createAgentKernel
|
|
31053
31064
|
};
|
|
31054
|
-
//# sourceMappingURL=chunk-
|
|
31065
|
+
//# sourceMappingURL=chunk-GWHHM6X2.js.map
|