veryfront 0.1.876 → 0.1.878
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/esm/deno.d.ts +3 -2
- package/esm/deno.js +4 -3
- package/esm/src/eval/agent-service/durable-run-canaries/cli-runner.d.ts.map +1 -0
- package/esm/src/{agent/testing → eval/agent-service}/durable-run-canaries/environment.d.ts +1 -1
- package/esm/src/eval/agent-service/durable-run-canaries/environment.d.ts.map +1 -0
- package/esm/src/{agent/testing → eval/agent-service}/durable-run-canaries/environment.js +1 -1
- package/esm/src/eval/agent-service/durable-run-canaries/index.d.ts.map +1 -0
- package/esm/src/eval/agent-service/durable-run-canaries/runner.d.ts.map +1 -0
- package/esm/src/eval/agent-service/durable-run-canaries/validation.d.ts.map +1 -0
- package/esm/src/eval/agent-service/live-evals/api-client.d.ts.map +1 -0
- package/esm/src/eval/agent-service/live-evals/cli-runner.d.ts.map +1 -0
- package/esm/src/{agent/testing → eval/agent-service}/live-evals/environment.d.ts +1 -1
- package/esm/src/eval/agent-service/live-evals/environment.d.ts.map +1 -0
- package/esm/src/{agent/testing → eval/agent-service}/live-evals/environment.js +1 -1
- package/esm/src/{agent/testing → eval/agent-service}/live-evals/formatting.d.ts +1 -1
- package/esm/src/eval/agent-service/live-evals/formatting.d.ts.map +1 -0
- package/esm/src/eval/agent-service/live-evals/index.d.ts.map +1 -0
- package/esm/src/eval/agent-service/live-evals/metadata.d.ts.map +1 -0
- package/esm/src/eval/agent-service/live-evals/performance.d.ts.map +1 -0
- package/esm/src/{agent/testing → eval/agent-service}/live-evals/preflight.d.ts +1 -1
- package/esm/src/eval/agent-service/live-evals/preflight.d.ts.map +1 -0
- package/esm/src/{agent/testing → eval/agent-service}/live-evals/preflight.js +1 -1
- package/esm/src/eval/agent-service/live-evals/report.d.ts.map +1 -0
- package/esm/src/eval/agent-service/live-evals/request.d.ts.map +1 -0
- package/esm/src/eval/agent-service/live-evals/result.d.ts.map +1 -0
- package/esm/src/{agent/testing → eval/agent-service}/live-evals/runner.d.ts +1 -1
- package/esm/src/eval/agent-service/live-evals/runner.d.ts.map +1 -0
- package/esm/src/{agent/testing → eval/agent-service}/live-evals/runner.js +1 -1
- package/esm/src/eval/agent-service.d.ts +90 -0
- package/esm/src/eval/agent-service.d.ts.map +1 -0
- package/esm/src/eval/agent-service.js +276 -0
- package/esm/src/eval/index.d.ts +22 -0
- package/esm/src/eval/index.d.ts.map +1 -1
- package/esm/src/eval/index.js +22 -0
- package/esm/src/utils/version-constant.d.ts +1 -1
- package/esm/src/utils/version-constant.js +1 -1
- package/package.json +5 -5
- package/esm/src/agent/testing/agent-tester.d.ts +0 -53
- package/esm/src/agent/testing/agent-tester.d.ts.map +0 -1
- package/esm/src/agent/testing/agent-tester.js +0 -132
- package/esm/src/agent/testing/durable-run-canaries/cli-runner.d.ts.map +0 -1
- package/esm/src/agent/testing/durable-run-canaries/environment.d.ts.map +0 -1
- package/esm/src/agent/testing/durable-run-canaries/index.d.ts.map +0 -1
- package/esm/src/agent/testing/durable-run-canaries/runner.d.ts.map +0 -1
- package/esm/src/agent/testing/durable-run-canaries/validation.d.ts.map +0 -1
- package/esm/src/agent/testing/index.d.ts +0 -10
- package/esm/src/agent/testing/index.d.ts.map +0 -1
- package/esm/src/agent/testing/index.js +0 -9
- package/esm/src/agent/testing/live-evals/api-client.d.ts.map +0 -1
- package/esm/src/agent/testing/live-evals/cli-runner.d.ts.map +0 -1
- package/esm/src/agent/testing/live-evals/environment.d.ts.map +0 -1
- package/esm/src/agent/testing/live-evals/formatting.d.ts.map +0 -1
- package/esm/src/agent/testing/live-evals/index.d.ts.map +0 -1
- package/esm/src/agent/testing/live-evals/metadata.d.ts.map +0 -1
- package/esm/src/agent/testing/live-evals/performance.d.ts.map +0 -1
- package/esm/src/agent/testing/live-evals/preflight.d.ts.map +0 -1
- package/esm/src/agent/testing/live-evals/report.d.ts.map +0 -1
- package/esm/src/agent/testing/live-evals/request.d.ts.map +0 -1
- package/esm/src/agent/testing/live-evals/result.d.ts.map +0 -1
- package/esm/src/agent/testing/live-evals/runner.d.ts.map +0 -1
- /package/esm/src/{agent/testing → eval/agent-service}/durable-run-canaries/cli-runner.d.ts +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/durable-run-canaries/cli-runner.js +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/durable-run-canaries/index.d.ts +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/durable-run-canaries/index.js +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/durable-run-canaries/runner.d.ts +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/durable-run-canaries/runner.js +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/durable-run-canaries/validation.d.ts +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/durable-run-canaries/validation.js +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/api-client.d.ts +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/api-client.js +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/cli-runner.d.ts +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/cli-runner.js +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/formatting.js +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/index.d.ts +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/index.js +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/metadata.d.ts +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/metadata.js +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/performance.d.ts +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/performance.js +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/report.d.ts +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/report.js +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/request.d.ts +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/request.js +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/result.d.ts +0 -0
- /package/esm/src/{agent/testing → eval/agent-service}/live-evals/result.js +0 -0
package/esm/src/eval/index.d.ts
CHANGED
|
@@ -18,6 +18,28 @@
|
|
|
18
18
|
* ],
|
|
19
19
|
* });
|
|
20
20
|
* ```
|
|
21
|
+
*
|
|
22
|
+
* @example Live agent-service eval
|
|
23
|
+
* ```ts
|
|
24
|
+
* import { datasets, evalAgent, metrics, runEval } from "veryfront/eval";
|
|
25
|
+
* import { createAgentServiceEvalAdapter } from "veryfront/eval/agent-service";
|
|
26
|
+
*
|
|
27
|
+
* const definition = evalAgent({
|
|
28
|
+
* target: "agent:veryfront",
|
|
29
|
+
* dataset: datasets.inline([{ id: "smoke", input: "List project files." }]),
|
|
30
|
+
* metrics: [metrics.agent.noFailedTools().gate()],
|
|
31
|
+
* });
|
|
32
|
+
*
|
|
33
|
+
* const report = await runEval(definition, {
|
|
34
|
+
* adapters: {
|
|
35
|
+
* agent: createAgentServiceEvalAdapter({
|
|
36
|
+
* endpoint: "http://127.0.0.1:3001/api/ag-ui",
|
|
37
|
+
* authToken: "<TOKEN>",
|
|
38
|
+
* projectId: "<PROJECT_ID>",
|
|
39
|
+
* }),
|
|
40
|
+
* },
|
|
41
|
+
* });
|
|
42
|
+
* ```
|
|
21
43
|
*/
|
|
22
44
|
import "../../_dnt.polyfills.js";
|
|
23
45
|
export { datasets } from "./datasets.js";
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/src/eval/index.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/src/eval/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA0CG;AACH,OAAO,yBAAyB,CAAC;AAGjC,OAAO,EAAE,QAAQ,EAAE,MAAM,eAAe,CAAC;AACzC,OAAO,EAAE,SAAS,EAAE,gBAAgB,EAAE,MAAM,cAAc,CAAC;AAC3D,OAAO,EAAE,OAAO,EAAE,MAAM,cAAc,CAAC;AACvC,OAAO,EAAE,gBAAgB,EAAE,oBAAoB,EAAE,MAAM,aAAa,CAAC;AACrE,OAAO,EAAE,OAAO,EAAE,MAAM,aAAa,CAAC;AACtC,OAAO,EAAE,YAAY,EAAE,aAAa,EAAE,YAAY,EAAE,MAAM,gBAAgB,CAAC;AAC3E,OAAO,EACL,wBAAwB,EACxB,0BAA0B,EAC1B,gBAAgB,EAChB,2BAA2B,EAC3B,wBAAwB,EACxB,4BAA4B,EAC5B,6BAA6B,GAC9B,MAAM,aAAa,CAAC;AAErB,YAAY,EAAE,cAAc,EAAE,oBAAoB,EAAE,mBAAmB,EAAE,MAAM,gBAAgB,CAAC;AAChG,YAAY,EACV,gBAAgB,EAChB,uBAAuB,EACvB,sBAAsB,EACtB,cAAc,EACd,gBAAgB,EAChB,WAAW,EACX,sBAAsB,EACtB,cAAc,EACd,WAAW,EACX,gBAAgB,EAChB,UAAU,EACV,eAAe,EACf,UAAU,EACV,iBAAiB,EACjB,gBAAgB,EAChB,gBAAgB,EAChB,iBAAiB,EACjB,mBAAmB,EACnB,UAAU,EACV,UAAU,EACV,iBAAiB,EACjB,YAAY,EACZ,UAAU,EACV,cAAc,EACd,YAAY,EACZ,SAAS,EACT,SAAS,EACT,cAAc,GACf,MAAM,YAAY,CAAC;AACpB,YAAY,EACV,+BAA+B,EAC/B,iBAAiB,EACjB,OAAO,EACP,kBAAkB,EAClB,eAAe,EACf,mBAAmB,EACnB,oBAAoB,GACrB,MAAM,aAAa,CAAC"}
|
package/esm/src/eval/index.js
CHANGED
|
@@ -18,6 +18,28 @@
|
|
|
18
18
|
* ],
|
|
19
19
|
* });
|
|
20
20
|
* ```
|
|
21
|
+
*
|
|
22
|
+
* @example Live agent-service eval
|
|
23
|
+
* ```ts
|
|
24
|
+
* import { datasets, evalAgent, metrics, runEval } from "veryfront/eval";
|
|
25
|
+
* import { createAgentServiceEvalAdapter } from "veryfront/eval/agent-service";
|
|
26
|
+
*
|
|
27
|
+
* const definition = evalAgent({
|
|
28
|
+
* target: "agent:veryfront",
|
|
29
|
+
* dataset: datasets.inline([{ id: "smoke", input: "List project files." }]),
|
|
30
|
+
* metrics: [metrics.agent.noFailedTools().gate()],
|
|
31
|
+
* });
|
|
32
|
+
*
|
|
33
|
+
* const report = await runEval(definition, {
|
|
34
|
+
* adapters: {
|
|
35
|
+
* agent: createAgentServiceEvalAdapter({
|
|
36
|
+
* endpoint: "http://127.0.0.1:3001/api/ag-ui",
|
|
37
|
+
* authToken: "<TOKEN>",
|
|
38
|
+
* projectId: "<PROJECT_ID>",
|
|
39
|
+
* }),
|
|
40
|
+
* },
|
|
41
|
+
* });
|
|
42
|
+
* ```
|
|
21
43
|
*/
|
|
22
44
|
import "../../_dnt.polyfills.js";
|
|
23
45
|
export { datasets } from "./datasets.js";
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "veryfront",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.878",
|
|
4
4
|
"description": "The simplest way to build AI-powered apps",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"react",
|
|
@@ -77,14 +77,14 @@
|
|
|
77
77
|
"import": "./esm/src/agent/identity-contracts.js",
|
|
78
78
|
"types": "./esm/src/agent/identity-contracts.d.ts"
|
|
79
79
|
},
|
|
80
|
-
"./agent/testing": {
|
|
81
|
-
"import": "./esm/src/agent/testing/index.js",
|
|
82
|
-
"types": "./esm/src/agent/testing/index.d.ts"
|
|
83
|
-
},
|
|
84
80
|
"./eval": {
|
|
85
81
|
"import": "./esm/src/eval/index.js",
|
|
86
82
|
"types": "./esm/src/eval/index.d.ts"
|
|
87
83
|
},
|
|
84
|
+
"./eval/agent-service": {
|
|
85
|
+
"import": "./esm/src/eval/agent-service.js",
|
|
86
|
+
"types": "./esm/src/eval/agent-service.d.ts"
|
|
87
|
+
},
|
|
88
88
|
"./channels/control-plane": {
|
|
89
89
|
"import": "./esm/src/channels/control-plane.js",
|
|
90
90
|
"types": "./esm/src/channels/control-plane.d.ts"
|
|
@@ -1,53 +0,0 @@
|
|
|
1
|
-
import type { Agent, AgentResponse, Message } from "../types.js";
|
|
2
|
-
/** Public API contract for test case. */
|
|
3
|
-
export interface TestCase {
|
|
4
|
-
/** Test name */
|
|
5
|
-
name: string;
|
|
6
|
-
/** Input to agent */
|
|
7
|
-
input: string | Message[];
|
|
8
|
-
/** Expected output pattern (regex or string) */
|
|
9
|
-
expected?: RegExp | string;
|
|
10
|
-
/** Expected tool calls */
|
|
11
|
-
expectToolCalls?: string[];
|
|
12
|
-
/** Maximum execution time (ms) */
|
|
13
|
-
timeout?: number;
|
|
14
|
-
/** Custom validator */
|
|
15
|
-
validate?: (response: AgentResponse) => boolean | Promise<boolean>;
|
|
16
|
-
}
|
|
17
|
-
/** Result returned from test. */
|
|
18
|
-
export interface TestResult {
|
|
19
|
-
/** Test case name */
|
|
20
|
-
name: string;
|
|
21
|
-
/** Pass/fail */
|
|
22
|
-
passed: boolean;
|
|
23
|
-
/** Response from agent */
|
|
24
|
-
response?: AgentResponse;
|
|
25
|
-
/** Error if test failed */
|
|
26
|
-
error?: string;
|
|
27
|
-
/** Execution time */
|
|
28
|
-
executionTime: number;
|
|
29
|
-
/** Tool calls made */
|
|
30
|
-
toolCalls: string[];
|
|
31
|
-
}
|
|
32
|
-
/** Public API contract for test suite. */
|
|
33
|
-
export interface TestSuite {
|
|
34
|
-
/** Suite name */
|
|
35
|
-
name: string;
|
|
36
|
-
/** Test results */
|
|
37
|
-
results: TestResult[];
|
|
38
|
-
/** Overall pass/fail */
|
|
39
|
-
passed: boolean;
|
|
40
|
-
/** Total execution time */
|
|
41
|
-
totalTime: number;
|
|
42
|
-
}
|
|
43
|
-
/** Test agent helper. */
|
|
44
|
-
export declare function testAgent(agent: Agent, testCases: TestCase[]): Promise<TestSuite>;
|
|
45
|
-
/** Print test results helper. */
|
|
46
|
-
export declare function printTestResults(suite: TestSuite): void;
|
|
47
|
-
/** Assert contains helper. */
|
|
48
|
-
export declare function assertContains(response: AgentResponse, text: string): boolean;
|
|
49
|
-
/** Assert tool called helper. */
|
|
50
|
-
export declare function assertToolCalled(response: AgentResponse, toolName: string): boolean;
|
|
51
|
-
/** Assert completed helper. */
|
|
52
|
-
export declare function assertCompleted(response: AgentResponse): boolean;
|
|
53
|
-
//# sourceMappingURL=agent-tester.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"agent-tester.d.ts","sourceRoot":"","sources":["../../../../src/src/agent/testing/agent-tester.ts"],"names":[],"mappings":"AAUA,OAAO,KAAK,EAAE,KAAK,EAAE,aAAa,EAAE,OAAO,EAAE,MAAM,aAAa,CAAC;AAEjE,yCAAyC;AACzC,MAAM,WAAW,QAAQ;IACvB,gBAAgB;IAChB,IAAI,EAAE,MAAM,CAAC;IAEb,qBAAqB;IACrB,KAAK,EAAE,MAAM,GAAG,OAAO,EAAE,CAAC;IAE1B,gDAAgD;IAChD,QAAQ,CAAC,EAAE,MAAM,GAAG,MAAM,CAAC;IAE3B,0BAA0B;IAC1B,eAAe,CAAC,EAAE,MAAM,EAAE,CAAC;IAE3B,kCAAkC;IAClC,OAAO,CAAC,EAAE,MAAM,CAAC;IAEjB,uBAAuB;IACvB,QAAQ,CAAC,EAAE,CAAC,QAAQ,EAAE,aAAa,KAAK,OAAO,GAAG,OAAO,CAAC,OAAO,CAAC,CAAC;CACpE;AAED,iCAAiC;AACjC,MAAM,WAAW,UAAU;IACzB,qBAAqB;IACrB,IAAI,EAAE,MAAM,CAAC;IAEb,gBAAgB;IAChB,MAAM,EAAE,OAAO,CAAC;IAEhB,0BAA0B;IAC1B,QAAQ,CAAC,EAAE,aAAa,CAAC;IAEzB,2BAA2B;IAC3B,KAAK,CAAC,EAAE,MAAM,CAAC;IAEf,qBAAqB;IACrB,aAAa,EAAE,MAAM,CAAC;IAEtB,sBAAsB;IACtB,SAAS,EAAE,MAAM,EAAE,CAAC;CACrB;AAED,0CAA0C;AAC1C,MAAM,WAAW,SAAS;IACxB,iBAAiB;IACjB,IAAI,EAAE,MAAM,CAAC;IAEb,mBAAmB;IACnB,OAAO,EAAE,UAAU,EAAE,CAAC;IAEtB,wBAAwB;IACxB,MAAM,EAAE,OAAO,CAAC;IAEhB,2BAA2B;IAC3B,SAAS,EAAE,MAAM,CAAC;CACnB;AAED,yBAAyB;AACzB,wBAAsB,SAAS,CAAC,KAAK,EAAE,KAAK,EAAE,SAAS,EAAE,QAAQ,EAAE,GAAG,OAAO,CAAC,SAAS,CAAC,CAWvF;AA6FD,iCAAiC;AACjC,wBAAgB,gBAAgB,CAAC,KAAK,EAAE,SAAS,GAAG,IAAI,CAmBvD;AAED,8BAA8B;AAC9B,wBAAgB,cAAc,CAAC,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,MAAM,GAAG,OAAO,CAE7E;AAED,iCAAiC;AACjC,wBAAgB,gBAAgB,CAAC,QAAQ,EAAE,aAAa,EAAE,QAAQ,EAAE,MAAM,GAAG,OAAO,CAEnF;AAED,+BAA+B;AAC/B,wBAAgB,eAAe,CAAC,QAAQ,EAAE,aAAa,GAAG,OAAO,CAEhE"}
|
|
@@ -1,132 +0,0 @@
|
|
|
1
|
-
/**************************
|
|
2
|
-
* Agent Testing Utilities
|
|
3
|
-
*
|
|
4
|
-
* Utilities for testing agents in development and CI/CD.
|
|
5
|
-
*
|
|
6
|
-
* @module veryfront/agent/testing
|
|
7
|
-
**************************/
|
|
8
|
-
import * as dntShim from "../../../_dnt.shims.js";
|
|
9
|
-
/** Test agent helper. */
|
|
10
|
-
export async function testAgent(agent, testCases) {
|
|
11
|
-
const suiteStartTime = Date.now();
|
|
12
|
-
const results = await Promise.all(testCases.map((testCase) => runTestCase(agent, testCase)));
|
|
13
|
-
const passed = results.every((r) => r.passed);
|
|
14
|
-
return {
|
|
15
|
-
name: agent.id,
|
|
16
|
-
results,
|
|
17
|
-
passed,
|
|
18
|
-
totalTime: Date.now() - suiteStartTime,
|
|
19
|
-
};
|
|
20
|
-
}
|
|
21
|
-
async function runTestCase(agent, testCase) {
|
|
22
|
-
const startTime = Date.now();
|
|
23
|
-
try {
|
|
24
|
-
const timeoutMs = testCase.timeout ?? 30000;
|
|
25
|
-
let timeoutId;
|
|
26
|
-
let response;
|
|
27
|
-
try {
|
|
28
|
-
response = await Promise.race([
|
|
29
|
-
agent.generate({ input: testCase.input }),
|
|
30
|
-
new Promise((_, reject) => {
|
|
31
|
-
timeoutId = dntShim.setTimeout(() => reject(new Error("Test timeout")), timeoutMs);
|
|
32
|
-
}),
|
|
33
|
-
]);
|
|
34
|
-
}
|
|
35
|
-
finally {
|
|
36
|
-
clearTimeout(timeoutId);
|
|
37
|
-
}
|
|
38
|
-
const executionTime = Date.now() - startTime;
|
|
39
|
-
const toolCalls = response.toolCalls.map((tc) => tc.name);
|
|
40
|
-
const { passed, error } = await validateTestCase(testCase, response, toolCalls);
|
|
41
|
-
return {
|
|
42
|
-
name: testCase.name,
|
|
43
|
-
passed,
|
|
44
|
-
response,
|
|
45
|
-
error,
|
|
46
|
-
executionTime,
|
|
47
|
-
toolCalls,
|
|
48
|
-
};
|
|
49
|
-
}
|
|
50
|
-
catch (error) {
|
|
51
|
-
return {
|
|
52
|
-
name: testCase.name,
|
|
53
|
-
passed: false,
|
|
54
|
-
error: error instanceof Error ? error.message : String(error),
|
|
55
|
-
executionTime: Date.now() - startTime,
|
|
56
|
-
toolCalls: [],
|
|
57
|
-
};
|
|
58
|
-
}
|
|
59
|
-
}
|
|
60
|
-
async function validateTestCase(testCase, response, toolCalls) {
|
|
61
|
-
const expected = testCase.expected;
|
|
62
|
-
if (expected instanceof RegExp) {
|
|
63
|
-
if (!expected.test(response.text)) {
|
|
64
|
-
return {
|
|
65
|
-
passed: false,
|
|
66
|
-
error: `Output "${response.text}" does not match pattern ${expected}`,
|
|
67
|
-
};
|
|
68
|
-
}
|
|
69
|
-
}
|
|
70
|
-
else if (typeof expected === "string") {
|
|
71
|
-
if (!response.text.includes(expected)) {
|
|
72
|
-
return {
|
|
73
|
-
passed: false,
|
|
74
|
-
error: `Output does not contain expected text: "${expected}"`,
|
|
75
|
-
};
|
|
76
|
-
}
|
|
77
|
-
}
|
|
78
|
-
const expectedTools = testCase.expectToolCalls;
|
|
79
|
-
if (expectedTools?.length) {
|
|
80
|
-
const missingTools = expectedTools.filter((t) => !toolCalls.includes(t));
|
|
81
|
-
if (missingTools.length) {
|
|
82
|
-
return {
|
|
83
|
-
passed: false,
|
|
84
|
-
error: `Expected tool calls not found: ${missingTools.join(", ")}`,
|
|
85
|
-
};
|
|
86
|
-
}
|
|
87
|
-
}
|
|
88
|
-
if (testCase.validate) {
|
|
89
|
-
try {
|
|
90
|
-
const passed = await testCase.validate(response);
|
|
91
|
-
if (!passed)
|
|
92
|
-
return { passed: false, error: "Custom validation failed" };
|
|
93
|
-
}
|
|
94
|
-
catch (error) {
|
|
95
|
-
return {
|
|
96
|
-
passed: false,
|
|
97
|
-
error: `Custom validation error: ${error instanceof Error ? error.message : String(error)}`,
|
|
98
|
-
};
|
|
99
|
-
}
|
|
100
|
-
}
|
|
101
|
-
return { passed: true };
|
|
102
|
-
}
|
|
103
|
-
/** Print test results helper. */
|
|
104
|
-
export function printTestResults(suite) {
|
|
105
|
-
console.log(`\n=== Test Suite: ${suite.name} ===\n`);
|
|
106
|
-
const passed = suite.results.filter((r) => r.passed).length;
|
|
107
|
-
const total = suite.results.length;
|
|
108
|
-
for (const [index, result] of suite.results.entries()) {
|
|
109
|
-
const icon = result.passed ? "✅" : "❌";
|
|
110
|
-
console.log(`${icon} ${index + 1}. ${result.name}`);
|
|
111
|
-
if (!result.passed && result.error)
|
|
112
|
-
console.log(` Error: ${result.error}`);
|
|
113
|
-
if (result.toolCalls.length)
|
|
114
|
-
console.log(` Tools used: ${result.toolCalls.join(", ")}`);
|
|
115
|
-
console.log(` Time: ${result.executionTime}ms\n`);
|
|
116
|
-
}
|
|
117
|
-
console.log(`Results: ${passed}/${total} passed`);
|
|
118
|
-
console.log(`Total time: ${suite.totalTime}ms`);
|
|
119
|
-
console.log(`Status: ${suite.passed ? "✅ PASSED" : "❌ FAILED"}\n`);
|
|
120
|
-
}
|
|
121
|
-
/** Assert contains helper. */
|
|
122
|
-
export function assertContains(response, text) {
|
|
123
|
-
return response.text.toLowerCase().includes(text.toLowerCase());
|
|
124
|
-
}
|
|
125
|
-
/** Assert tool called helper. */
|
|
126
|
-
export function assertToolCalled(response, toolName) {
|
|
127
|
-
return response.toolCalls.some((tc) => tc.name === toolName);
|
|
128
|
-
}
|
|
129
|
-
/** Assert completed helper. */
|
|
130
|
-
export function assertCompleted(response) {
|
|
131
|
-
return response.status === "completed";
|
|
132
|
-
}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"cli-runner.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/durable-run-canaries/cli-runner.ts"],"names":[],"mappings":"AAGA,OAAO,EAAE,KAAK,kBAAkB,EAAE,MAAM,6BAA6B,CAAC;AAEtE,OAAO,EACL,4BAA4B,EAC5B,KAAK,oBAAoB,EAEzB,KAAK,4BAA4B,EAClC,MAAM,aAAa,CAAC;AAErB,KAAK,SAAS,GAAG,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,SAAS,CAAC,CAAC;AAEpD,6DAA6D;AAC7D,MAAM,WAAW,mCAAmC;IAClD,OAAO,EAAE,kBAAkB,CAAC;IAC5B,gBAAgB,EAAE,MAAM,CAAC;CAC1B;AAED,oDAAoD;AACpD,MAAM,WAAW,2BAA2B;IAC1C,GAAG,EAAE,SAAS,CAAC;IACf,OAAO,EAAE,MAAM,CAAC;IAChB,WAAW,EAAE,CAAC,KAAK,EAAE,mCAAmC,KAAK,oBAAoB,EAAE,CAAC;IACpF,GAAG,CAAC,EAAE,MAAM,CAAC;IACb,GAAG,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,KAAK,IAAI,CAAC;IAChC,YAAY,CAAC,EAAE,CACb,MAAM,EAAE,4BAA4B,KACjC,UAAU,CAAC,OAAO,4BAA4B,CAAC,CAAC;CACtD;AAcD,kCAAkC;AAClC,wBAAsB,sBAAsB,CAC1C,KAAK,EAAE,2BAA2B,GACjC,OAAO,CAAC,MAAM,CAAC,CAwEjB"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"environment.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/durable-run-canaries/environment.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,KAAK,uBAAuB,EAA2B,MAAM,yBAAyB,CAAC;AAEhG,8DAA8D;AAC9D,MAAM,WAAW,2BAA2B;IAC1C,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;IAClB,gBAAgB,EAAE,MAAM,CAAC;IACzB,sBAAsB,EAAE,OAAO,CAAC;CACjC;AAED,uDAAuD;AACvD,eAAO,MAAM,qCAAqC,SAAU,CAAC;AAE7D,+CAA+C;AAC/C,wBAAgB,kCAAkC,CAChD,GAAG,GAAE,uBAA4B,GAChC,2BAA2B,CAY7B"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/durable-run-canaries/index.ts"],"names":[],"mappings":"AAAA,OAAO,EACL,KAAK,mCAAmC,EACxC,sBAAsB,EACtB,KAAK,2BAA2B,GACjC,MAAM,iBAAiB,CAAC;AACzB,OAAO,EACL,qCAAqC,EACrC,KAAK,2BAA2B,EAChC,kCAAkC,GACnC,MAAM,kBAAkB,CAAC;AAC1B,OAAO,EACL,+BAA+B,EAC/B,4BAA4B,EAC5B,KAAK,yBAAyB,EAC9B,KAAK,yBAAyB,EAC9B,KAAK,oBAAoB,EACzB,KAAK,kCAAkC,EACvC,KAAK,uBAAuB,EAC5B,KAAK,4BAA4B,EACjC,KAAK,sBAAsB,EAC3B,KAAK,4BAA4B,EACjC,+BAA+B,EAC/B,KAAK,0BAA0B,EAC/B,KAAK,oCAAoC,EACzC,KAAK,6BAA6B,EAClC,gCAAgC,EAChC,+BAA+B,GAChC,MAAM,aAAa,CAAC;AAErB,OAAO,EACL,eAAe,EACf,oCAAoC,EACpC,oBAAoB,EACpB,oBAAoB,EACpB,gBAAgB,GACjB,MAAM,iBAAiB,CAAC"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"runner.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/durable-run-canaries/runner.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,qCAAqC,CAAC;AAIvE,oDAAoD;AACpD,MAAM,WAAW,yBAAyB;IACxC,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,EAAE,MAAM,CAAC;IAClB,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,EAAE,MAAM,GAAG,IAAI,CAAC;IACzB,QAAQ,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACzB,gBAAgB,EAAE,MAAM,CAAC;IACzB,KAAK,CAAC,EAAE,CAAC,KAAK,EAAE,MAAM,GAAG,GAAG,GAAG,OAAO,EAAE,IAAI,CAAC,EAAE,WAAW,KAAK,OAAO,CAAC,QAAQ,CAAC,CAAC;CAClF;AAED,4DAA4D;AAC5D,MAAM,WAAW,kCAAkC;IACjD,cAAc,EAAE,MAAM,CAAC;IACvB,KAAK,EAAE,MAAM,CAAC;CACf;AAED,8DAA8D;AAC9D,MAAM,WAAW,oCAAoC;IACnD,cAAc,EAAE,MAAM,CAAC;IACvB,MAAM,EAAE,MAAM,CAAC;CAChB;AAED,sDAAsD;AACtD,MAAM,WAAW,6BAA8B,SAAQ,kCAAkC;IACvF,SAAS,EAAE,MAAM,CAAC;IAClB,MAAM,EAAE,MAAM,CAAC;IACf,aAAa,EAAE,MAAM,CAAC;CACvB;AAED,qDAAqD;AACrD,eAAO,MAAM,gCAAgC;;;;;;;;4BAO5C,CAAC;AAEF,4CAA4C;AAC5C,MAAM,MAAM,uBAAuB,GAAG,WAAW,CAC/C,UAAU,CAAC,OAAO,gCAAgC,CAAC,CACpD,CAAC;AAEF,8DAA8D;AAC9D,MAAM,WAAW,0BAA0B;IACzC,KAAK,EAAE,MAAM,CAAC;IACd,cAAc,EAAE,MAAM,CAAC;IACvB,SAAS,EAAE,MAAM,CAAC;IAClB,OAAO,EAAE,MAAM,CAAC;IAChB,MAAM,EAAE,MAAM,CAAC;IACf,aAAa,EAAE,MAAM,CAAC;IACtB,2BAA2B,EAAE,MAAM,GAAG,IAAI,CAAC;IAC3C,iBAAiB,EAAE,MAAM,GAAG,IAAI,CAAC;IACjC,eAAe,EAAE,MAAM,GAAG,IAAI,CAAC;IAC/B,iBAAiB,EAAE,MAAM,GAAG,IAAI,CAAC;IACjC,oBAAoB,EAAE,MAAM,GAAG,IAAI,CAAC;IACpC,SAAS,EAAE,MAAM,GAAG,IAAI,CAAC;IACzB,UAAU,EAAE,MAAM,GAAG,IAAI,CAAC;CAC3B;AA4CD,6CAA6C;AAC7C,wBAAgB,+BAA+B,CAAC,KAAK,EAAE,OAAO,GAAG,0BAA0B,CAoC1F;AAkGD,6DAA6D;AAC7D,MAAM,WAAW,yBAAyB;IACxC,oBAAoB,EAAE,CAAC,KAAK,EAAE,kCAAkC,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;IACnF,aAAa,EAAE,CAAC,KAAK,EAAE,kCAAkC,KAAK,OAAO,CAAC,0BAA0B,CAAC,CAAC;IAClG,qBAAqB,EAAE,CAAC,KAAK,EAAE;QAAE,cAAc,EAAE,MAAM,CAAA;KAAE,KAAK,OAAO,CAAC,uBAAuB,EAAE,CAAC,CAAC;IACjG,wBAAwB,EAAE,CACxB,KAAK,EAAE,oCAAoC,KACxC,OAAO,CAAC,uBAAuB,CAAC,CAAC;IACtC,eAAe,EAAE,CAAC,KAAK,EAAE,6BAA6B,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;CAC1E;AAED,4CAA4C;AAC5C,wBAAgB,+BAA+B,CAC7C,MAAM,EAAE,yBAAyB,GAChC,yBAAyB,CAgF3B;AAED,+CAA+C;AAC/C,MAAM,WAAW,sBAAsB;IACrC,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,MAAM,EAAE,MAAM,GAAG,MAAM,CAAC;IACxB,OAAO,EAAE,MAAM,CAAC;IAChB,UAAU,EAAE,MAAM,CAAC;IACnB,cAAc,EAAE,MAAM,CAAC;IACvB,KAAK,EAAE,MAAM,CAAC;IACd,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;CAC1B;AAED,gEAAgE;AAChE,MAAM,WAAW,4BAA4B;IAC3C,aAAa,CAAC,EAAE,MAAM,EAAE,GAAG,CAAC,CAAC,KAAK,EAAE,MAAM,KAAK,MAAM,EAAE,CAAC,CAAC;IACzD,OAAO,EAAE,CAAC,KAAK,CAAC,EAAE;QAAE,KAAK,EAAE,MAAM,CAAA;KAAE,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;IACtD,cAAc,EAAE,MAAM,CAAC;IACvB,MAAM,EAAE,MAAM,CAAC;IACf,YAAY,CAAC,EAAE,MAAM,OAAO,CAAC,CAAC,MAAM,OAAO,CAAC,IAAI,CAAC,CAAC,GAAG,IAAI,CAAC,CAAC;IAC3D,KAAK,EAAE,MAAM,CAAC;IACd,QAAQ,EAAE,CAAC,KAAK,EAAE;QAChB,QAAQ,EAAE,uBAAuB,EAAE,CAAC;QACpC,GAAG,EAAE,0BAA0B,CAAC;KACjC,KAAK,OAAO,CAAC,IAAI,CAAC,GAAG,IAAI,CAAC;CAC5B;AAED,uDAAuD;AACvD,MAAM,WAAW,oBAAoB;IACnC,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,MAAM,OAAO,CAAC,4BAA4B,CAAC,CAAC;CACtD;AAED,uDAAuD;AACvD,MAAM,WAAW,4BAA6B,SAAQ,yBAAyB;IAC7E,sBAAsB,EAAE,OAAO,CAAC;CACjC;AA0DD,iBAAS,qCAAqC,CAAC,QAAQ,EAAE,uBAAuB,EAAE,GAAG,MAAM,EAAE,CAc5F;AAQD,iBAAS,mBAAmB,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAEpD;AA2CD,wCAAwC;AACxC,wBAAgB,4BAA4B,CAC1C,MAAM,EAAE,4BAA4B,EACpC,SAAS,GAAE,yBAAmE;wBAkB7C,oBAAoB,KAAG,OAAO,CAAC,sBAAsB,CAAC;EAqFxF;AAED,0DAA0D;AAC1D,eAAO,MAAM,+BAA+B;;;CAG3C,CAAC"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"validation.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/durable-run-canaries/validation.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,uBAAuB,EAAE,0BAA0B,EAAE,MAAM,aAAa,CAAC;AA8BvF,+DAA+D;AAC/D,wBAAgB,eAAe,CAAC,GAAG,EAAE,0BAA0B,GAAG,IAAI,CAQrE;AAED,wCAAwC;AACxC,wBAAgB,oBAAoB,CAClC,QAAQ,EAAE,uBAAuB,EAAE,EACnC,SAAS,EAAE,MAAM,GAChB,uBAAuB,CASzB;AAED,gCAAgC;AAChC,wBAAgB,gBAAgB,CAAC,KAAK,EAAE,OAAO,GAAG,MAAM,CAUvD;AAED,qCAAqC;AACrC,wBAAgB,oBAAoB,CAAC,OAAO,EAAE,uBAAuB,GAAG,MAAM,CAK7E;AAED,yDAAyD;AACzD,wBAAgB,oCAAoC,CAAC,QAAQ,EAAE,uBAAuB,EAAE,GAAG,IAAI,CAY9F"}
|
|
@@ -1,10 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* Agent Testing Utilities
|
|
3
|
-
*
|
|
4
|
-
* @module veryfront/agent/testing
|
|
5
|
-
*/
|
|
6
|
-
import "../../../_dnt.polyfills.js";
|
|
7
|
-
export { assertCompleted, assertContains, assertToolCalled, printTestResults, testAgent, type TestCase, type TestResult, type TestSuite, } from "./agent-tester.js";
|
|
8
|
-
export { assertCompleted as assertDurableRunCanaryCompleted, assertNoMalformedCreateFileToolCalls, collectAssistantText, createDurableRunCanaryApiClient, createDurableRunCanaryRunner, DEFAULT_DURABLE_RUN_CANARY_TIMEOUT_MS, type DurableRunCanaryApiClient, type DurableRunCanaryApiConfig, type DurableRunCanaryCase, type DurableRunCanaryCliCaseFactoryInput, type DurableRunCanaryCreateRootRunInput, type DurableRunCanaryEnvironment, type DurableRunCanaryMessage, type DurableRunCanaryPreparedCase, type DurableRunCanaryResult, type DurableRunCanaryRunnerConfig, type DurableRunCanaryRunSummary, type DurableRunCanarySendUserMessageInput, type DurableRunCanaryStartRunInput, findAssistantMessage, getDurableRunCanaryMessageSchema, parseDurableRunCanaryRunSummary, resolveDurableRunCanaryEnvironment, runDurableRunCanaryCli, type RunDurableRunCanaryCliInput, stringifyUnknown, } from "./durable-run-canaries/index.js";
|
|
9
|
-
export { buildFailureSuffix, buildLiveEvalCaseMetadata, type BuildLiveEvalCaseMetadataInput, buildLiveEvalCaseTagSummary, buildLiveEvalRequestBody, type BuildLiveEvalRequestBodyInput, buildLiveEvalRuntimeSummary, buildLiveEvalStatusSummary, buildProgressLine, buildRuntimePerformanceSummary, cancelLiveEvalInputRequest, containsOrderedSubsequence, containsSkillLoad, countStepStartedEvents, createFailedEvalResult, createLiveEvalApiClient, createLiveEvalCaseSupport, createLiveEvalConversation, createLiveEvalProjectUploadFixture, createLiveEvalRelease, createPassedEvalResult, createPlainTextPdf, createSkippedEvalResult, DEFAULT_LIVE_EVAL_AREA_TAG_RULES, DEFAULT_LIVE_EVAL_ENDPOINT, DEFAULT_LIVE_EVAL_OPTIONAL_JUDGE_CASE_PREFIXES, deleteLiveEvalConversation, deleteLiveEvalProjectFile, evaluateRuntimeConfidenceEnv, getLiveEvalProjectFile, hasEveryLiveEvalTag, hasFinished, listOpenLiveEvalInputRequests, type LiveEvalApiClient, type LiveEvalApiContext, type LiveEvalCase, type LiveEvalCaseMetadata, type LiveEvalCaseMetadataOptions, type LiveEvalCaseSelectionInput, type LiveEvalCaseSurface, type LiveEvalCaseTagRule, type LiveEvalCliCaseFactoryInput, type LiveEvalCliCaseGroups, type LiveEvalContext, type LiveEvalConversationInput, type LiveEvalCreateConversationInput, type LiveEvalCreateReleaseInput, type LiveEvalEnvironment, type LiveEvalInputRequestInput, type LiveEvalInputRequestRecord, type LiveEvalInputResponseValues, type LiveEvalProjectFile, type LiveEvalProjectFileInput, type LiveEvalProjectFileReaderInput, type LiveEvalProjectUploadFixtureInput, type LiveEvalRequestBody, type LiveEvalRequestTimeoutInput, type LiveEvalResultForPerformance, type LiveEvalResultForReport, type LiveEvalResultRecord, type LiveEvalRunnerConfig, type LiveEvalRuntime, type LiveEvalSubmitInputResponseInput, type LiveEvalWaitForOpenInputRequestInput, type PreparedLiveEvalInput, printRuntimeConfidencePreflight, resolveLiveEvalEnvironment, resolveLiveEvalRequestedCaseIds, runLiveEvalCli, type RunLiveEvalCliInput, type RuntimeConfidencePreflightResult, type RuntimePerformanceSummary, selectLiveEvalCases, submitLiveEvalInputResponse, waitForOpenLiveEvalInputRequest, withLiveEvalMetadata, } from "./live-evals/index.js";
|
|
10
|
-
//# sourceMappingURL=index.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../../src/src/agent/testing/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH,OAAO,4BAA4B,CAAC;AAGpC,OAAO,EACL,eAAe,EACf,cAAc,EACd,gBAAgB,EAChB,gBAAgB,EAChB,SAAS,EACT,KAAK,QAAQ,EACb,KAAK,UAAU,EACf,KAAK,SAAS,GACf,MAAM,mBAAmB,CAAC;AAE3B,OAAO,EACL,eAAe,IAAI,+BAA+B,EAClD,oCAAoC,EACpC,oBAAoB,EACpB,+BAA+B,EAC/B,4BAA4B,EAC5B,qCAAqC,EACrC,KAAK,yBAAyB,EAC9B,KAAK,yBAAyB,EAC9B,KAAK,oBAAoB,EACzB,KAAK,mCAAmC,EACxC,KAAK,kCAAkC,EACvC,KAAK,2BAA2B,EAChC,KAAK,uBAAuB,EAC5B,KAAK,4BAA4B,EACjC,KAAK,sBAAsB,EAC3B,KAAK,4BAA4B,EACjC,KAAK,0BAA0B,EAC/B,KAAK,oCAAoC,EACzC,KAAK,6BAA6B,EAClC,oBAAoB,EACpB,gCAAgC,EAChC,+BAA+B,EAC/B,kCAAkC,EAClC,sBAAsB,EACtB,KAAK,2BAA2B,EAChC,gBAAgB,GACjB,MAAM,iCAAiC,CAAC;AAEzC,OAAO,EACL,kBAAkB,EAClB,yBAAyB,EACzB,KAAK,8BAA8B,EACnC,2BAA2B,EAC3B,wBAAwB,EACxB,KAAK,6BAA6B,EAClC,2BAA2B,EAC3B,0BAA0B,EAC1B,iBAAiB,EACjB,8BAA8B,EAC9B,0BAA0B,EAC1B,0BAA0B,EAC1B,iBAAiB,EACjB,sBAAsB,EACtB,sBAAsB,EACtB,uBAAuB,EACvB,yBAAyB,EACzB,0BAA0B,EAC1B,kCAAkC,EAClC,qBAAqB,EACrB,sBAAsB,EACtB,kBAAkB,EAClB,uBAAuB,EACvB,gCAAgC,EAChC,0BAA0B,EAC1B,8CAA8C,EAC9C,0BAA0B,EAC1B,yBAAyB,EACzB,4BAA4B,EAC5B,sBAAsB,EACtB,mBAAmB,EACnB,WAAW,EACX,6BAA6B,EAC7B,KAAK,iBAAiB,EACtB,KAAK,kBAAkB,EACvB,KAAK,YAAY,EACjB,KAAK,oBAAoB,EACzB,KAAK,2BAA2B,EAChC,KAAK,0BAA0B,EAC/B,KAAK,mBAAmB,EACxB,KAAK,mBAAmB,EACxB,KAAK,2BAA2B,EAChC,KAAK,qBAAqB,EAC1B,KAAK,eAAe,EACpB,KAAK,yBAAyB,EAC9B,KAAK,+BAA+B,EACpC,KAAK,0BAA0B,EAC/B,KAAK,mBAAmB,EACxB,KAAK,yBAAyB,EAC9B,KAAK,0BAA0B,EAC/B,KAAK,2BAA2B,EAChC,KAAK,mBAAmB,EACxB,KAAK,wBAAwB,EAC7B,KAAK,8BAA8B,EACnC,KAAK,iCAAiC,EACtC,KAAK,mBAAmB,EACxB,KAAK,2BAA2B,EAChC,KAAK,4BAA4B,EACjC,KAAK,uBAAuB,EAC5B,KAAK,oBAAoB,EACzB,KAAK,oBAAoB,EACzB,KAAK,eAAe,EACpB,KAAK,gCAAgC,EACrC,KAAK,oCAAoC,EACzC,KAAK,qBAAqB,EAC1B,+BAA+B,EAC/B,0BAA0B,EAC1B,+BAA+B,EAC/B,cAAc,EACd,KAAK,mBAAmB,EACxB,KAAK,gCAAgC,EACrC,KAAK,yBAAyB,EAC9B,mBAAmB,EACnB,2BAA2B,EAC3B,+BAA+B,EAC/B,oBAAoB,GACrB,MAAM,uBAAuB,CAAC"}
|
|
@@ -1,9 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* Agent Testing Utilities
|
|
3
|
-
*
|
|
4
|
-
* @module veryfront/agent/testing
|
|
5
|
-
*/
|
|
6
|
-
import "../../../_dnt.polyfills.js";
|
|
7
|
-
export { assertCompleted, assertContains, assertToolCalled, printTestResults, testAgent, } from "./agent-tester.js";
|
|
8
|
-
export { assertCompleted as assertDurableRunCanaryCompleted, assertNoMalformedCreateFileToolCalls, collectAssistantText, createDurableRunCanaryApiClient, createDurableRunCanaryRunner, DEFAULT_DURABLE_RUN_CANARY_TIMEOUT_MS, findAssistantMessage, getDurableRunCanaryMessageSchema, parseDurableRunCanaryRunSummary, resolveDurableRunCanaryEnvironment, runDurableRunCanaryCli, stringifyUnknown, } from "./durable-run-canaries/index.js";
|
|
9
|
-
export { buildFailureSuffix, buildLiveEvalCaseMetadata, buildLiveEvalCaseTagSummary, buildLiveEvalRequestBody, buildLiveEvalRuntimeSummary, buildLiveEvalStatusSummary, buildProgressLine, buildRuntimePerformanceSummary, cancelLiveEvalInputRequest, containsOrderedSubsequence, containsSkillLoad, countStepStartedEvents, createFailedEvalResult, createLiveEvalApiClient, createLiveEvalCaseSupport, createLiveEvalConversation, createLiveEvalProjectUploadFixture, createLiveEvalRelease, createPassedEvalResult, createPlainTextPdf, createSkippedEvalResult, DEFAULT_LIVE_EVAL_AREA_TAG_RULES, DEFAULT_LIVE_EVAL_ENDPOINT, DEFAULT_LIVE_EVAL_OPTIONAL_JUDGE_CASE_PREFIXES, deleteLiveEvalConversation, deleteLiveEvalProjectFile, evaluateRuntimeConfidenceEnv, getLiveEvalProjectFile, hasEveryLiveEvalTag, hasFinished, listOpenLiveEvalInputRequests, printRuntimeConfidencePreflight, resolveLiveEvalEnvironment, resolveLiveEvalRequestedCaseIds, runLiveEvalCli, selectLiveEvalCases, submitLiveEvalInputResponse, waitForOpenLiveEvalInputRequest, withLiveEvalMetadata, } from "./live-evals/index.js";
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"api-client.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/live-evals/api-client.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,qCAAqC,CAAC;AAEvE,OAAO,KAAK,EAAE,mBAAmB,EAAE,MAAM,aAAa,CAAC;AAIvD,iCAAiC;AACjC,MAAM,WAAW,kBAAkB;IACjC,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,GAAG,IAAI,CAAC;IACzB,KAAK,CAAC,EAAE,CAAC,KAAK,EAAE,MAAM,GAAG,GAAG,GAAG,OAAO,EAAE,IAAI,CAAC,EAAE,WAAW,KAAK,OAAO,CAAC,QAAQ,CAAC,CAAC;CAClF;AAED,mDAAmD;AACnD,MAAM,WAAW,2BAA2B;IAC1C,gBAAgB,EAAE,MAAM,CAAC;CAC1B;AAED,uDAAuD;AACvD,MAAM,WAAW,+BAAgC,SAAQ,2BAA2B;IAClF,KAAK,EAAE,MAAM,CAAC;CACf;AAED,gDAAgD;AAChD,MAAM,WAAW,yBAA0B,SAAQ,2BAA2B;IAC5E,cAAc,EAAE,MAAM,CAAC;CACxB;AAED,0DAA0D;AAC1D,MAAM,WAAW,iCAAkC,SAAQ,2BAA2B;IACpF,QAAQ,EAAE,MAAM,CAAC;IACjB,WAAW,EAAE,MAAM,CAAC;IACpB,IAAI,EAAE,QAAQ,GAAG,UAAU,CAAC;IAC5B,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,WAAW,CAAC,EAAE,MAAM,CAAC;CACtB;AAED,gDAAgD;AAChD,MAAM,WAAW,wBAAyB,SAAQ,2BAA2B;IAC3E,QAAQ,EAAE,MAAM,CAAC;CAClB;AAED,kDAAkD;AAClD,MAAM,WAAW,0BAA2B,SAAQ,2BAA2B;IAC7E,WAAW,CAAC,EAAE,MAAM,CAAC;CACtB;AAED,+DAA+D;AAC/D,MAAM,WAAW,oCAAqC,SAAQ,yBAAyB;IACrF,WAAW,EAAE,WAAW,CAAC;IACzB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,SAAS,CAAC,EAAE,MAAM,CAAC;CACpB;AAED,+DAA+D;AAC/D,MAAM,WAAW,2BAA2B;IAC1C,CAAC,GAAG,EAAE,MAAM,GAAG,MAAM,GAAG,OAAO,GAAG,MAAM,GAAG,IAAI,CAAC;CACjD;AAED,yDAAyD;AACzD,MAAM,WAAW,gCAAiC,SAAQ,2BAA2B;IACnF,cAAc,EAAE,MAAM,CAAC;IACvB,cAAc,EAAE,MAAM,CAAC;IACvB,MAAM,EAAE,2BAA2B,CAAC;CACrC;AAED,iDAAiD;AACjD,MAAM,WAAW,yBAA0B,SAAQ,2BAA2B;IAC5E,cAAc,EAAE,MAAM,CAAC;IACvB,cAAc,EAAE,MAAM,CAAC;CACxB;AA4BD,QAAA,MAAM,2BAA2B;;;GAKhC,CAAC;AAQF,gDAAgD;AAChD,MAAM,MAAM,0BAA0B,GAAG,WAAW,CAClD,UAAU,CAAC,OAAO,2BAA2B,CAAC,CAC/C,CAAC;AAEF,oDAAoD;AACpD,MAAM,WAAW,iBAAiB;IAChC,kBAAkB,CAAC,KAAK,EAAE,+BAA+B,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;IAC5E,kBAAkB,CAAC,KAAK,EAAE,yBAAyB,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC;IACpE,0BAA0B,CAAC,KAAK,EAAE,iCAAiC,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;IACtF,cAAc,CAAC,KAAK,EAAE,wBAAwB,GAAG,OAAO,CAAC,mBAAmB,GAAG,IAAI,CAAC,CAAC;IACrF,aAAa,CAAC,KAAK,EAAE,0BAA0B,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;IAClE,iBAAiB,CAAC,KAAK,EAAE,wBAAwB,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC;IAClE,qBAAqB,CAAC,KAAK,EAAE,yBAAyB,GAAG,OAAO,CAAC,0BAA0B,EAAE,CAAC,CAAC;IAC/F,uBAAuB,CAAC,KAAK,EAAE,oCAAoC,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;IACtF,mBAAmB,CAAC,KAAK,EAAE,gCAAgC,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC;IAC5E,kBAAkB,CAAC,KAAK,EAAE,yBAAyB,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC;CACrE;AAsID,mCAAmC;AACnC,wBAAgB,uBAAuB,CAAC,OAAO,EAAE,kBAAkB,GAAG,iBAAiB,CAatF;AAED,qCAAqC;AACrC,wBAAsB,0BAA0B,CAC9C,OAAO,EAAE,kBAAkB,EAC3B,KAAK,EAAE,+BAA+B,GACrC,OAAO,CAAC,MAAM,CAAC,CAuBjB;AAED,4CAA4C;AAC5C,wBAAsB,0BAA0B,CAC9C,OAAO,EAAE,kBAAkB,EAC3B,KAAK,EAAE,yBAAyB,GAC/B,OAAO,CAAC,IAAI,CAAC,CAiBf;AAED,+CAA+C;AAC/C,wBAAsB,kCAAkC,CACtD,OAAO,EAAE,kBAAkB,EAC3B,KAAK,EAAE,iCAAiC,GACvC,OAAO,CAAC,MAAM,CAAC,CAuDjB;AAED,qCAAqC;AACrC,wBAAsB,sBAAsB,CAC1C,OAAO,EAAE,kBAAkB,EAC3B,KAAK,EAAE,wBAAwB,GAC9B,OAAO,CAAC,mBAAmB,GAAG,IAAI,CAAC,CA4BrC;AAED,gCAAgC;AAChC,wBAAsB,qBAAqB,CACzC,OAAO,EAAE,kBAAkB,EAC3B,KAAK,EAAE,0BAA0B,GAChC,OAAO,CAAC,MAAM,CAAC,CA6BjB;AAED,4CAA4C;AAC5C,wBAAsB,yBAAyB,CAC7C,OAAO,EAAE,kBAAkB,EAC3B,KAAK,EAAE,wBAAwB,GAC9B,OAAO,CAAC,IAAI,CAAC,CAoBf;AAED,0CAA0C;AAC1C,wBAAsB,6BAA6B,CACjD,OAAO,EAAE,kBAAkB,EAC3B,KAAK,EAAE,yBAAyB,GAC/B,OAAO,CAAC,0BAA0B,EAAE,CAAC,CAoBvC;AAED,yDAAyD;AACzD,wBAAsB,+BAA+B,CACnD,OAAO,EAAE,kBAAkB,EAC3B,KAAK,EAAE,oCAAoC,GAC1C,OAAO,CAAC,MAAM,CAAC,CAsBjB;AAED,mDAAmD;AACnD,wBAAsB,2BAA2B,CAC/C,OAAO,EAAE,kBAAkB,EAC3B,KAAK,EAAE,gCAAgC,GACtC,OAAO,CAAC,IAAI,CAAC,CAmBf;AAED,kDAAkD;AAClD,wBAAsB,0BAA0B,CAC9C,OAAO,EAAE,kBAAkB,EAC3B,KAAK,EAAE,yBAAyB,GAC/B,OAAO,CAAC,IAAI,CAAC,CAkBf"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"cli-runner.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/live-evals/cli-runner.ts"],"names":[],"mappings":"AAGA,OAAO,EAAkC,KAAK,eAAe,EAAE,MAAM,kBAAkB,CAAC;AAQxF,OAAO,EACL,iBAAiB,EACjB,sBAAsB,EACtB,yBAAyB,EACzB,WAAW,EACX,KAAK,YAAY,EACjB,KAAK,oBAAoB,EAC1B,MAAM,aAAa,CAAC;AAKrB,KAAK,SAAS,GAAG,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,SAAS,CAAC,CAAC;AAEpD,yDAAyD;AACzD,MAAM,WAAW,qBAAqB;IACpC,aAAa,EAAE,YAAY,EAAE,CAAC;IAC9B,UAAU,EAAE,YAAY,EAAE,CAAC;IAC3B,sBAAsB,EAAE,YAAY,EAAE,CAAC;CACxC;AAED,oDAAoD;AACpD,MAAM,WAAW,2BAA2B;IAC1C,SAAS,EAAE,MAAM,CAAC;IAClB,QAAQ,EAAE,MAAM,CAAC;IACjB,SAAS,EAAE,MAAM,GAAG,IAAI,CAAC;IACzB,QAAQ,EAAE,MAAM,GAAG,IAAI,CAAC;IACxB,KAAK,EAAE,MAAM,GAAG,IAAI,CAAC;IACrB,gBAAgB,EAAE,MAAM,CAAC;IACzB,cAAc,EAAE,OAAO,CAAC;IACxB,WAAW,EAAE,OAAO,WAAW,CAAC;IAChC,iBAAiB,EAAE,OAAO,iBAAiB,CAAC;IAC5C,sBAAsB,EAAE,OAAO,sBAAsB,CAAC;IACtD,gBAAgB,EAAE,UAAU,CAAC,OAAO,yBAAyB,CAAC,CAAC,kBAAkB,CAAC,CAAC;IACnF,SAAS,EAAE,UAAU,CAAC,OAAO,yBAAyB,CAAC,CAAC,WAAW,CAAC,CAAC;IACrE,QAAQ,EAAE,UAAU,CAAC,OAAO,yBAAyB,CAAC,CAAC,UAAU,CAAC,CAAC;CACpE;AAED,2CAA2C;AAC3C,MAAM,WAAW,mBAAmB;IAClC,GAAG,EAAE,SAAS,CAAC;IACf,QAAQ,EAAE,MAAM,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IAC5C,WAAW,EAAE,CAAC,KAAK,EAAE,2BAA2B,KAAK,qBAAqB,CAAC;IAC3E,QAAQ,CAAC,EAAE,SAAS,eAAe,EAAE,CAAC;IACtC,GAAG,CAAC,EAAE,MAAM,CAAC;IACb,GAAG,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,KAAK,IAAI,CAAC;IAChC,KAAK,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,KAAK,IAAI,CAAC;IAClC,iBAAiB,CAAC,EAAE,CAClB,MAAM,EAAE,oBAAoB,KACzB,UAAU,CAAC,OAAO,yBAAyB,CAAC,CAAC;CACnD;AAuBD,yBAAyB;AACzB,wBAAsB,cAAc,CAAC,KAAK,EAAE,mBAAmB,GAAG,OAAO,CAAC,MAAM,CAAC,CAwJhF"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"environment.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/live-evals/environment.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,KAAK,uBAAuB,EAA2B,MAAM,yBAAyB,CAAC;AAEhG,qDAAqD;AACrD,MAAM,WAAW,mBAAmB;IAClC,QAAQ,EAAE,MAAM,CAAC;IACjB,SAAS,EAAE,MAAM,CAAC;IAClB,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,EAAE,MAAM,GAAG,SAAS,CAAC;IAC9B,QAAQ,EAAE,MAAM,GAAG,SAAS,CAAC;IAC7B,KAAK,EAAE,MAAM,GAAG,SAAS,CAAC;CAC3B;AAED,4CAA4C;AAC5C,eAAO,MAAM,0BAA0B,oCAAoC,CAAC;AAE5E,sCAAsC;AACtC,wBAAgB,0BAA0B,CACxC,GAAG,GAAE,uBAA4B,GAChC,mBAAmB,CAerB"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"formatting.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/live-evals/formatting.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,MAAM,EAAE,MAAM,aAAa,CAAC;AACrC,OAAO,KAAK,EAAE,uBAAuB,IAAI,oBAAoB,EAAE,MAAM,gBAAgB,CAAC;AAStF,6BAA6B;AAC7B,wBAAgB,kBAAkB,CAAC,KAAK,EAAE,MAAM,EAAE,GAAG,MAAM,CA4C1D;AAED,4BAA4B;AAC5B,wBAAgB,iBAAiB,CAAC,KAAK,EAAE;IACvC,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,EAAE,MAAM,CAAC;IAClB,QAAQ,EAAE,oBAAoB,CAAC;CAChC,GAAG,MAAM,CAcT;AAED,6BAA6B;AAC7B,wBAAgB,kBAAkB,CAAC,QAAQ,EAAE,oBAAoB,GAAG,MAAM,CAUzE;AAED,2CAA2C;AAC3C,wBAAgB,0BAA0B,CACxC,QAAQ,EAAE,MAAM,EAAE,EAClB,MAAM,EAAE,MAAM,EAAE,GACf,OAAO,CAcT"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/live-evals/index.ts"],"names":[],"mappings":"AAAA,OAAO,EACL,KAAK,2BAA2B,EAChC,KAAK,qBAAqB,EAC1B,cAAc,EACd,KAAK,mBAAmB,GACzB,MAAM,iBAAiB,CAAC;AACzB,OAAO,EACL,0BAA0B,EAC1B,KAAK,mBAAmB,EACxB,0BAA0B,GAC3B,MAAM,kBAAkB,CAAC;AAC1B,OAAO,EACL,0BAA0B,EAC1B,uBAAuB,EACvB,0BAA0B,EAC1B,kCAAkC,EAClC,qBAAqB,EACrB,0BAA0B,EAC1B,yBAAyB,EACzB,sBAAsB,EACtB,6BAA6B,EAC7B,KAAK,iBAAiB,EACtB,KAAK,kBAAkB,EACvB,KAAK,yBAAyB,EAC9B,KAAK,+BAA+B,EACpC,KAAK,0BAA0B,EAC/B,KAAK,yBAAyB,EAC9B,KAAK,0BAA0B,EAC/B,KAAK,2BAA2B,EAChC,KAAK,wBAAwB,EAC7B,KAAK,iCAAiC,EACtC,KAAK,2BAA2B,EAChC,KAAK,gCAAgC,EACrC,KAAK,oCAAoC,EACzC,2BAA2B,EAC3B,+BAA+B,GAChC,MAAM,iBAAiB,CAAC;AACzB,OAAO,EACL,kBAAkB,EAClB,iBAAiB,EACjB,0BAA0B,EAC1B,kBAAkB,GACnB,MAAM,iBAAiB,CAAC;AACzB,OAAO,EACL,4BAA4B,EAC5B,+BAA+B,EAC/B,KAAK,gCAAgC,GACtC,MAAM,gBAAgB,CAAC;AACxB,OAAO,EACL,8BAA8B,EAC9B,KAAK,4BAA4B,EACjC,KAAK,eAAe,EACpB,KAAK,yBAAyB,GAC/B,MAAM,kBAAkB,CAAC;AAC1B,OAAO,EACL,yBAAyB,EACzB,KAAK,8BAA8B,EACnC,gCAAgC,EAChC,8CAA8C,EAC9C,KAAK,2BAA2B,EAChC,KAAK,mBAAmB,EACxB,KAAK,mBAAmB,EACxB,oBAAoB,GACrB,MAAM,eAAe,CAAC;AACvB,OAAO,EACL,wBAAwB,EACxB,KAAK,6BAA6B,EAClC,KAAK,mBAAmB,GACzB,MAAM,cAAc,CAAC;AACtB,OAAO,EACL,2BAA2B,EAC3B,2BAA2B,EAC3B,0BAA0B,EAC1B,mBAAmB,EACnB,KAAK,oBAAoB,EACzB,KAAK,0BAA0B,EAC/B,KAAK,uBAAuB,EAC5B,+BAA+B,EAC/B,mBAAmB,GACpB,MAAM,aAAa,CAAC;AACrB,OAAO,EACL,sBAAsB,EACtB,sBAAsB,EACtB,uBAAuB,EACvB,KAAK,oBAAoB,GAC1B,MAAM,aAAa,CAAC;AACrB,OAAO,EACL,iBAAiB,EACjB,sBAAsB,EACtB,yBAAyB,EACzB,WAAW,EACX,KAAK,YAAY,EACjB,KAAK,eAAe,EACpB,KAAK,mBAAmB,EACxB,KAAK,8BAA8B,EACnC,KAAK,oBAAoB,EACzB,uBAAuB,EACvB,KAAK,qBAAqB,GAC3B,MAAM,aAAa,CAAC"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"metadata.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/live-evals/metadata.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,oBAAoB,EAAE,MAAM,aAAa,CAAC;AACxD,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,aAAa,CAAC;AAEhD,sDAAsD;AACtD,MAAM,MAAM,mBAAmB,GAAG,WAAW,GAAG,OAAO,GAAG,cAAc,CAAC;AAEzE,uDAAuD;AACvD,MAAM,WAAW,mBAAmB;IAClC,GAAG,EAAE,MAAM,CAAC;IACZ,MAAM,CAAC,EAAE,MAAM,GAAG,SAAS,MAAM,EAAE,CAAC;IACpC,UAAU,CAAC,EAAE,MAAM,GAAG,SAAS,MAAM,EAAE,CAAC;IACxC,QAAQ,CAAC,EAAE,MAAM,GAAG,SAAS,MAAM,EAAE,CAAC;CACvC;AAED,mDAAmD;AACnD,MAAM,WAAW,2BAA2B;IAC1C,kBAAkB,CAAC,EAAE,SAAS,MAAM,EAAE,GAAG,WAAW,CAAC,MAAM,CAAC,CAAC;IAC7D,yBAAyB,CAAC,EAAE,SAAS,MAAM,EAAE,CAAC;IAC9C,YAAY,CAAC,EAAE,SAAS,mBAAmB,EAAE,CAAC;CAC/C;AAED,uDAAuD;AACvD,MAAM,WAAW,8BAA+B,SAAQ,2BAA2B;IACjF,MAAM,EAAE,MAAM,CAAC;IACf,OAAO,EAAE,mBAAmB,CAAC;IAC7B,cAAc,EAAE,OAAO,CAAC;CACzB;AAED,gEAAgE;AAChE,eAAO,MAAM,8CAA8C,EAAE,SAAS,MAAM,EAI3E,CAAC;AAEF,kDAAkD;AAClD,eAAO,MAAM,gCAAgC,EAAE,SAAS,mBAAmB,EAqB1E,CAAC;AA+DF,sCAAsC;AACtC,wBAAgB,yBAAyB,CACvC,KAAK,EAAE,8BAA8B,GACpC,oBAAoB,CAkCtB;AAED,kCAAkC;AAClC,wBAAgB,oBAAoB,CAAC,KAAK,SAAS,YAAY,EAC7D,KAAK,EAAE,SAAS,KAAK,EAAE,EACvB,OAAO,EAAE,mBAAmB,EAC5B,OAAO,GAAE,2BAAgC,GACxC,KAAK,CAAC,KAAK,GAAG;IAAE,QAAQ,EAAE,oBAAoB,CAAA;CAAE,CAAC,CAUnD"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"performance.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/live-evals/performance.ts"],"names":[],"mappings":"AAAA,iDAAiD;AACjD,MAAM,MAAM,eAAe,GAAG,WAAW,CAAC;AAE1C,gEAAgE;AAChE,MAAM,WAAW,4BAA4B;IAC3C,OAAO,EAAE,eAAe,CAAC;IACzB,UAAU,EAAE,MAAM,CAAC;CACpB;AAED,2DAA2D;AAC3D,MAAM,WAAW,yBAAyB;IACxC,KAAK,EAAE,MAAM,CAAC;IACd,aAAa,EAAE,MAAM,CAAC;IACtB,aAAa,EAAE,MAAM,CAAC;IACtB,aAAa,EAAE,MAAM,CAAC;IACtB,aAAa,EAAE,MAAM,CAAC;IACtB,aAAa,EAAE,MAAM,CAAC;CACvB;AAkBD,0CAA0C;AAC1C,wBAAgB,8BAA8B,CAC5C,OAAO,EAAE,4BAA4B,EAAE,GACtC,MAAM,CAAC,eAAe,EAAE,yBAAyB,CAAC,CAiBpD"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"preflight.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/live-evals/preflight.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,KAAK,uBAAuB,EAA2B,MAAM,yBAAyB,CAAC;AAEhG,yDAAyD;AACzD,MAAM,WAAW,gCAAgC;IAC/C,EAAE,EAAE,OAAO,CAAC;IACZ,cAAc,EAAE,MAAM,CAAC;IACvB,QAAQ,EAAE,MAAM,EAAE,CAAC;CACpB;AAED,8CAA8C;AAC9C,wBAAgB,4BAA4B,CAC1C,GAAG,GAAE,uBAA4B,EACjC,cAAc,GAAE,MAAuD,GACtE,gCAAgC,CAoBlC;AAED,iDAAiD;AACjD,wBAAgB,+BAA+B,CAC7C,MAAM,EAAE,gCAAgC,EACxC,MAAM,GAAE,IAAI,CAAC,OAAO,EAAE,OAAO,GAAG,KAAK,CAAW,GAC/C,IAAI,CAKN"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"report.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/live-evals/report.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,kBAAkB,CAAC;AAExD,uDAAuD;AACvD,MAAM,WAAW,oBAAoB;IACnC,IAAI,EAAE,SAAS,MAAM,EAAE,CAAC;CACzB;AAED,2DAA2D;AAC3D,MAAM,WAAW,uBAAuB;IACtC,OAAO,EAAE,eAAe,CAAC;IACzB,MAAM,EAAE,MAAM,GAAG,MAAM,GAAG,MAAM,CAAC;CAClC;AAED,kDAAkD;AAClD,MAAM,WAAW,0BAA0B,CAAC,KAAK,SAAS;IAAE,EAAE,EAAE,MAAM,CAAA;CAAE;IACtE,QAAQ,EAAE,KAAK,EAAE,CAAC;IAClB,aAAa,EAAE,KAAK,EAAE,CAAC;IACvB,UAAU,EAAE,KAAK,EAAE,CAAC;IACpB,sBAAsB,EAAE,KAAK,EAAE,CAAC;IAChC,gBAAgB,EAAE,GAAG,CAAC,MAAM,CAAC,CAAC;IAC9B,iBAAiB,CAAC,EAAE,GAAG,CAAC,MAAM,CAAC,CAAC;IAChC,aAAa,EAAE,OAAO,CAAC;IACvB,yBAAyB,EAAE,OAAO,CAAC;CACpC;AAED,oDAAoD;AACpD,wBAAgB,mBAAmB,CACjC,IAAI,EAAE,SAAS,MAAM,EAAE,EACvB,aAAa,EAAE,GAAG,CAAC,MAAM,CAAC,GACzB,OAAO,CAQT;AAED,yCAAyC;AACzC,wBAAgB,2BAA2B,CACzC,KAAK,EAAE,SAAS;IACd,QAAQ,CAAC,EAAE,oBAAoB,CAAC;CACjC,EAAE,GACF,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAaxB;AAED,qCAAqC;AACrC,wBAAgB,mBAAmB,CACjC,KAAK,SAAS;IAAE,EAAE,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,EAAE,oBAAoB,CAAA;CAAE,EAE7D,KAAK,EAAE,0BAA0B,CAAC,KAAK,CAAC,GACvC,KAAK,EAAE,CAoBT;AAED,6CAA6C;AAC7C,wBAAgB,+BAA+B,CAAC,KAAK,EAAE;IACrD,QAAQ,EAAE,MAAM,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IAC5C,gBAAgB,EAAE,GAAG,CAAC,MAAM,CAAC,CAAC;IAC9B,kBAAkB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;CACpC,GAAG,GAAG,CAAC,MAAM,CAAC,CAsBd;AAED,UAAU,qBAAqB;IAC7B,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,MAAM,CAAC;IACf,OAAO,EAAE,MAAM,CAAC;CACjB;AAgBD,wCAAwC;AACxC,wBAAgB,2BAA2B,CACzC,QAAQ,EAAE,SAAS,eAAe,EAAE,EACpC,OAAO,EAAE,uBAAuB,EAAE,GACjC,MAAM,CAAC,eAAe,EAAE,qBAAqB,CAAC,CAShD;AAED,uCAAuC;AACvC,wBAAgB,0BAA0B,CACxC,OAAO,EAAE,uBAAuB,EAAE,GACjC;IACD,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,MAAM,CAAC;IACf,OAAO,EAAE,MAAM,CAAC;CACjB,CAMA"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"request.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/live-evals/request.ts"],"names":[],"mappings":"AAGA,MAAM,WAAW,mBAAmB;IAClC,QAAQ,EAAE,MAAM,CAAC;IACjB,KAAK,EAAE,MAAM,CAAC;IACd,KAAK,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IAC9B,KAAK,EAAE,OAAO,EAAE,CAAC;IACjB,OAAO,EAAE,OAAO,EAAE,CAAC;IACnB,cAAc,CAAC,EAAE;QACf,SAAS,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;KACpC,CAAC;IACF,QAAQ,EAAE,KAAK,CAAC;QACd,EAAE,EAAE,MAAM,CAAC;QACX,IAAI,EAAE,MAAM,CAAC;QACb,OAAO,EAAE,MAAM,CAAC;KACjB,CAAC,CAAC;CACJ;AAED,sDAAsD;AACtD,MAAM,WAAW,6BAA6B;IAC5C,UAAU,EAAE,MAAM,CAAC;IACnB,MAAM,EAAE,MAAM,CAAC;IACf,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IAClC,SAAS,EAAE,MAAM,GAAG,IAAI,CAAC;IACzB,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,cAAc,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC/B,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;IACxB,qBAAqB,CAAC,EAAE,OAAO,CAAC;IAChC,QAAQ,CAAC,EAAE,MAAM,CAAC;CACnB;AAED,qCAAqC;AACrC,wBAAgB,wBAAwB,CACtC,KAAK,EAAE,6BAA6B,GACnC,mBAAmB,CA6CrB"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"result.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/live-evals/result.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,kBAAkB,CAAC;AAExD,yCAAyC;AACzC,MAAM,WAAW,oBAAoB;IACnC,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,eAAe,CAAC;IACzB,MAAM,EAAE,MAAM,GAAG,MAAM,GAAG,MAAM,CAAC;IACjC,OAAO,EAAE,MAAM,CAAC;IAChB,UAAU,EAAE,MAAM,CAAC;IACnB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;IACzB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,UAAU,CAAC,EAAE,MAAM,EAAE,CAAC;IACtB,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,WAAW,CAAC,EAAE,MAAM,CAAC;CACtB;AA2CD,gDAAgD;AAChD,wBAAgB,uBAAuB,CAAC,KAAK,EAAE;IAC7C,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,eAAe,CAAC;IACzB,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,EAAE,MAAM,CAAC;CACnB,GAAG,oBAAoB,CASvB;AAED,+CAA+C;AAC/C,wBAAgB,sBAAsB,CAAC,KAAK,EAAE;IAC5C,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,eAAe,CAAC;IACzB,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,EAAE,MAAM,CAAC;IAClB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;IACzB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,UAAU,CAAC,EAAE,MAAM,EAAE,CAAC;IACtB,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,WAAW,CAAC,EAAE,MAAM,CAAC;CACtB,GAAG,oBAAoB,CAEvB;AAED,+CAA+C;AAC/C,wBAAgB,sBAAsB,CAAC,KAAK,EAAE;IAC5C,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,eAAe,CAAC;IACzB,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,EAAE,MAAM,CAAC;IAClB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;IACzB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,UAAU,CAAC,EAAE,MAAM,EAAE,CAAC;IACtB,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,WAAW,CAAC,EAAE,MAAM,CAAC;CACtB,GAAG,oBAAoB,CAEvB"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"runner.d.ts","sourceRoot":"","sources":["../../../../../src/src/agent/testing/live-evals/runner.ts"],"names":[],"mappings":"AACA,OAAO,EAEL,KAAK,uBAAuB,IAAI,oBAAoB,EAIpD,KAAK,gBAAgB,IAAI,SAAS,EACnC,MAAM,gBAAgB,CAAC;AAExB,OAAO,EAAE,KAAK,eAAe,EAAE,MAAM,kBAAkB,CAAC;AAExD,OAAO,EAAE,KAAK,oBAAoB,EAAE,MAAM,aAAa,CAAC;AACxD,OAAO,EAIL,KAAK,oBAAoB,EAC1B,MAAM,aAAa,CAAC;AAErB,4CAA4C;AAC5C,MAAM,WAAW,qBAAqB;IACpC,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IAClC,mBAAmB,CAAC,EAAE,eAAe,CAAC;IACtC,OAAO,CAAC,EAAE,MAAM,OAAO,CAAC,IAAI,CAAC,CAAC;IAC9B,YAAY,CAAC,EAAE,MAAM,OAAO,CAAC,CAAC,MAAM,OAAO,CAAC,IAAI,CAAC,CAAC,GAAG,IAAI,CAAC,CAAC;CAC5D;AAED,6BAA6B;AAC7B,MAAM,WAAW,eAAe;IAC9B,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,GAAG,IAAI,CAAC;CAC1B;AAED,8CAA8C;AAC9C,MAAM,WAAW,YAAY;IAC3B,QAAQ,CAAC,EAAE,EAAE,MAAM,CAAC;IACpB,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,QAAQ,CAAC,MAAM,CAAC,EAAE,MAAM,CAAC;IACzB,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;IACxB,qBAAqB,CAAC,EAAE,OAAO,CAAC;IAChC,cAAc,CAAC,EAAE,OAAO,CAAC;IACzB,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,wBAAwB,CAAC,EAAE,MAAM,EAAE,CAAC;IACpC,QAAQ,CAAC,EAAE,oBAAoB,CAAC;IAChC,OAAO,CAAC,EAAE,CAAC,OAAO,EAAE,eAAe,KAAK,OAAO,CAAC,qBAAqB,CAAC,CAAC;IACvE,MAAM,EAAE,CACN,GAAG,EAAE,SAAS,EACd,QAAQ,EAAE,qBAAqB,GAAG,IAAI,KACnC,MAAM,GAAG,IAAI,GAAG,OAAO,CAAC,MAAM,GAAG,IAAI,CAAC,CAAC;CAC7C;AAED,UAAU,cAAc;IACtB,QAAQ,EAAE,MAAM,CAAC;IACjB,eAAe,CAAC,EAAE,MAAM,EAAE,CAAC;IAC3B,WAAW,CAAC,EAAE,MAAM,CAAC;CACtB;AAED,sDAAsD;AACtD,MAAM,WAAW,mBAAmB;IAClC,IAAI,EAAE,MAAM,CAAC;IACb,OAAO,EAAE,MAAM,CAAC;CACjB;AAED,uDAAuD;AACvD,MAAM,WAAW,8BAA8B;IAC7C,QAAQ,EAAE,MAAM,CAAC;IACjB,gBAAgB,EAAE,MAAM,CAAC;CAC1B;AAED,8CAA8C;AAC9C,MAAM,WAAW,oBAAoB;IACnC,QAAQ,EAAE,MAAM,CAAC;IACjB,SAAS,EAAE,MAAM,CAAC;IAClB,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,EAAE,MAAM,GAAG,IAAI,CAAC;IACzB,QAAQ,EAAE,MAAM,GAAG,IAAI,CAAC;IACxB,KAAK,EAAE,MAAM,GAAG,IAAI,CAAC;IACrB,gBAAgB,EAAE,MAAM,CAAC;IACzB,qBAAqB,EAAE,MAAM,CAAC;IAC9B,cAAc,EAAE,OAAO,CAAC;IACxB,KAAK,CAAC,EAAE,CAAC,KAAK,EAAE,MAAM,GAAG,GAAG,GAAG,OAAO,EAAE,IAAI,CAAC,EAAE,WAAW,KAAK,OAAO,CAAC,QAAQ,CAAC,CAAC;IACjF,GAAG,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,KAAK,IAAI,CAAC;IAChC,eAAe,CAAC,EAAE,CAAC,KAAK,EAAE,8BAA8B,KAAK,OAAO,CAAC,mBAAmB,GAAG,IAAI,CAAC,CAAC;CAClG;AAED,UAAU,kBAAkB;IAC1B,QAAQ,EAAE,MAAM,CAAC;IACjB,QAAQ,EAAE,MAAM,CAAC;CAClB;AAED,UAAU,oBAAqB,SAAQ,kBAAkB;IACvD,MAAM,EAAE,MAAM,CAAC;CAChB;AAED,UAAU,mBAAmB;IAC3B,IAAI,EAAE,OAAO,CAAC;IACd,MAAM,EAAE,MAAM,CAAC;CAChB;AAyJD,iBAAS,4BAA4B,CAAC,QAAQ,EAAE,qBAAqB,GAAG,IAAI,GAAG,MAAM,EAAE,CAYtF;AASD,UAAU,qBAAqB;IAC7B,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,eAAe,CAAC;IACzB,SAAS,EAAE,MAAM,CAAC;IAClB,cAAc,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC/B,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;CAC1B;AAED,UAAU,yBAAyB;IACjC,GAAG,EAAE,SAAS,CAAC;IACf,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,cAAc,EAAE,MAAM,CAAC;CACxB;AAED,UAAU,oBAAoB;IAC5B,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,cAAc,EAAE,MAAM,CAAC;IACvB,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,eAAe,EAAE,MAAM,CAAC;IACxB,WAAW,EAAE,MAAM,CAAC;CACrB;AAED,iBAAS,0BAA0B,CAAC,KAAK,EAAE,yBAAyB,GAAG,oBAAoB,CAQ1F;AAED,iBAAS,yBAAyB,CAAC,KAAK,EAAE;IACxC,OAAO,EAAE,MAAM,CAAC;IAChB,OAAO,EAAE,qBAAqB,CAAC;IAC/B,YAAY,EAAE,oBAAoB,CAAC;CACpC,GAAG,oBAAoB,CAevB;AAED,iBAAS,yBAAyB,CAAC,KAAK,EAAE;IACxC,OAAO,EAAE,MAAM,CAAC;IAChB,OAAO,EAAE,qBAAqB,CAAC;IAC/B,YAAY,EAAE,oBAAoB,CAAC;CACpC,GAAG,oBAAoB,CAevB;AAED,iBAAS,gCAAgC,CAAC,KAAK,EAAE;IAC/C,OAAO,EAAE,MAAM,CAAC;IAChB,OAAO,EAAE,qBAAqB,CAAC;IAC/B,QAAQ,EAAE,oBAAoB,CAAC;CAChC,GAAG,oBAAoB,CAcvB;AA+FD,iBAAS,YAAY,CAAC,GAAG,EAAE,SAAS,GAAG,MAAM,GAAG,IAAI,CASnD;AAED,yCAAyC;AACzC,wBAAgB,WAAW,CAAC,GAAG,EAAE,SAAS,GAAG,OAAO,CAEnD;AAED,kCAAkC;AAClC,wBAAgB,iBAAiB,CAAC,GAAG,EAAE,SAAS,EAAE,OAAO,EAAE,MAAM,GAAG,OAAO,CAE1E;AAED,wCAAwC;AACxC,wBAAgB,sBAAsB,CAAC,GAAG,EAAE,SAAS,GAAG,MAAM,CAE7D;AAED,qCAAqC;AACrC,wBAAgB,yBAAyB,CAAC,MAAM,EAAE,oBAAoB,GAAG;IACvE,OAAO,EAAE,CAAC,QAAQ,EAAE,YAAY,EAAE,OAAO,EAAE,eAAe,KAAK,OAAO,CAAC,oBAAoB,CAAC,CAAC;IAC7F,gBAAgB,EAAE,CAAC,KAAK,EAAE,cAAc,KAAK,OAAO,CAAC,MAAM,GAAG,IAAI,CAAC,CAAC;IACpE,SAAS,EAAE,CACT,gBAAgB,EAAE,CAAC,GAAG,EAAE,SAAS,KAAK,MAAM,GAAG,IAAI,EACnD,UAAU,EAAE,kBAAkB,KAC3B,CAAC,GAAG,EAAE,SAAS,KAAK,OAAO,CAAC,MAAM,GAAG,IAAI,CAAC,CAAC;IAChD,QAAQ,EAAE,CAAC,KAAK,EAAE,oBAAoB,KAAK,OAAO,CAAC,mBAAmB,CAAC,CAAC;CACzE,CAoIA;AAED,wDAAwD;AACxD,eAAO,MAAM,uBAAuB;;;;;;;CAOnC,CAAC"}
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|