agentv 4.42.4 → 4.43.0-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.
Files changed (43) hide show
  1. package/README.md +2 -2
  2. package/dist/{artifact-writer-7PXSB6LM.js → artifact-writer-STR7E5UO.js} +4 -4
  3. package/dist/{chunk-RBOP5X36.js → chunk-5NDSGGMJ.js} +2605 -171
  4. package/dist/chunk-5NDSGGMJ.js.map +1 -0
  5. package/dist/{chunk-6SQDBXT7.js → chunk-E2NL57MZ.js} +2 -2
  6. package/dist/chunk-E2NL57MZ.js.map +1 -0
  7. package/dist/{chunk-ISPJY2AX.js → chunk-IFQXBQSY.js} +2454 -415
  8. package/dist/chunk-IFQXBQSY.js.map +1 -0
  9. package/dist/{chunk-ZPFM52HV.js → chunk-RFJM2UBD.js} +2321 -630
  10. package/dist/chunk-RFJM2UBD.js.map +1 -0
  11. package/dist/{chunk-N6U3GXMF.js → chunk-ROLNQBYU.js} +620 -342
  12. package/dist/chunk-ROLNQBYU.js.map +1 -0
  13. package/dist/cli.js +5 -5
  14. package/dist/dashboard/assets/index-1Hvy8sBy.js +119 -0
  15. package/dist/dashboard/assets/{index-uXJsSG83.js → index-DitffAxS.js} +1 -1
  16. package/dist/dashboard/assets/index-J5sPcQO3.css +1 -0
  17. package/dist/dashboard/index.html +2 -2
  18. package/dist/{dist-VQWTETNY.js → dist-FTTL5IOY.js} +67 -3
  19. package/dist/index.js +9 -5
  20. package/dist/{interactive-TNRJEFA2.js → interactive-RE4DXH4A.js} +5 -5
  21. package/dist/skills/agentv-bench/SKILL.md +2 -2
  22. package/dist/skills/agentv-bench/agents/executor.md +1 -1
  23. package/dist/skills/agentv-bench/agents/grader.md +1 -1
  24. package/dist/skills/agentv-bench/references/autoresearch.md +4 -4
  25. package/dist/skills/agentv-bench/references/eval-yaml-spec.md +2 -1
  26. package/dist/skills/agentv-bench/references/schemas.md +1 -1
  27. package/dist/skills/agentv-bench/references/subagent-pipeline.md +4 -4
  28. package/dist/skills/agentv-eval-writer/SKILL.md +23 -16
  29. package/dist/skills/agentv-eval-writer/references/config-schema.json +114 -0
  30. package/dist/skills/agentv-eval-writer/references/eval-schema.json +192 -0
  31. package/dist/{ts-eval-loader-PYEU2PMP-YLXIQTEQ.js → ts-eval-loader-HQDMXQQV-LBW3N3W6.js} +2 -2
  32. package/package.json +6 -5
  33. package/dist/chunk-6SQDBXT7.js.map +0 -1
  34. package/dist/chunk-ISPJY2AX.js.map +0 -1
  35. package/dist/chunk-N6U3GXMF.js.map +0 -1
  36. package/dist/chunk-RBOP5X36.js.map +0 -1
  37. package/dist/chunk-ZPFM52HV.js.map +0 -1
  38. package/dist/dashboard/assets/index-BwBJwHp4.js +0 -118
  39. package/dist/dashboard/assets/index-C5v6_zhR.css +0 -1
  40. /package/dist/{artifact-writer-7PXSB6LM.js.map → artifact-writer-STR7E5UO.js.map} +0 -0
  41. /package/dist/{dist-VQWTETNY.js.map → dist-FTTL5IOY.js.map} +0 -0
  42. /package/dist/{interactive-TNRJEFA2.js.map → interactive-RE4DXH4A.js.map} +0 -0
  43. /package/dist/{ts-eval-loader-PYEU2PMP-YLXIQTEQ.js.map → ts-eval-loader-HQDMXQQV-LBW3N3W6.js.map} +0 -0
package/README.md CHANGED
@@ -73,7 +73,7 @@ agentv eval evals/my-eval.yaml
73
73
 
74
74
  **5. Compare results across targets:**
75
75
  ```bash
76
- agentv compare .agentv/results/runs/<timestamp>/index.jsonl
76
+ agentv compare .agentv/results/default/<timestamp>/index.jsonl
77
77
  ```
78
78
 
79
79
  ## Output formats
@@ -88,7 +88,7 @@ cat ./run/index.jsonl # JSONL results for scripts/CI
88
88
  Use AgentV programmatically:
89
89
 
90
90
  ```typescript
91
- import { evaluate } from '@agentv/core';
91
+ import { evaluate } from '@agentv/sdk';
92
92
 
93
93
  const { results, summary } = await evaluate({
94
94
  tests: [
@@ -4,8 +4,8 @@ import {
4
4
  buildResultIndexArtifact,
5
5
  writeArtifactsFromResults,
6
6
  writePerTestArtifacts
7
- } from "./chunk-6SQDBXT7.js";
8
- import "./chunk-RBOP5X36.js";
7
+ } from "./chunk-E2NL57MZ.js";
8
+ import "./chunk-5NDSGGMJ.js";
9
9
  import "./chunk-76FOHROU.js";
10
10
  import "./chunk-BPGJ4HBU.js";
11
11
  import {
@@ -20,7 +20,7 @@ import {
20
20
  parseJsonlResults,
21
21
  writeArtifacts,
22
22
  writeInitialBenchmarkArtifact
23
- } from "./chunk-ZPFM52HV.js";
23
+ } from "./chunk-RFJM2UBD.js";
24
24
  import "./chunk-NPVGBFF6.js";
25
25
  import "./chunk-M7BUKBAF.js";
26
26
  import "./chunk-5H446C7X.js";
@@ -41,4 +41,4 @@ export {
41
41
  writeInitialBenchmarkArtifact,
42
42
  writePerTestArtifacts
43
43
  };
44
- //# sourceMappingURL=artifact-writer-7PXSB6LM.js.map
44
+ //# sourceMappingURL=artifact-writer-STR7E5UO.js.map