agentv 4.31.4-next.1 → 4.33.0-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 (37) hide show
  1. package/README.md +17 -3
  2. package/dist/{artifact-writer-OYJ7VYQD.js → artifact-writer-PLUZAGYD.js} +4 -4
  3. package/dist/chunk-2TDFJ2FZ.js +1234 -0
  4. package/dist/chunk-2TDFJ2FZ.js.map +1 -0
  5. package/dist/{chunk-MIEYJ3YP.js → chunk-6QEIZ33V.js} +1382 -317
  6. package/dist/chunk-6QEIZ33V.js.map +1 -0
  7. package/dist/{chunk-PDGEPSPO.js → chunk-HE3TRGCU.js} +786 -260
  8. package/dist/chunk-HE3TRGCU.js.map +1 -0
  9. package/dist/{chunk-6Y3W7HJP.js → chunk-QKZLKDXB.js} +569 -192
  10. package/dist/chunk-QKZLKDXB.js.map +1 -0
  11. package/dist/{chunk-Y35UPYKH.js → chunk-VASYLLBA.js} +1687 -470
  12. package/dist/chunk-VASYLLBA.js.map +1 -0
  13. package/dist/cli.js +5 -5
  14. package/dist/dashboard/assets/index-DBg02hJh.js +118 -0
  15. package/dist/dashboard/assets/index-F8mrCRqc.css +1 -0
  16. package/dist/{studio/assets/index-B_Ga8SID.js → dashboard/assets/index-w2eILJoK.js} +1 -1
  17. package/dist/{studio → dashboard}/index.html +3 -3
  18. package/dist/{dist-KBYJJAXA.js → dist-W63D37ZR.js} +60 -6
  19. package/dist/index.js +5 -5
  20. package/dist/{interactive-RCBFUZUL.js → interactive-T6F2GRDI.js} +5 -5
  21. package/dist/skills/agentv-eval-writer/SKILL.md +2 -1
  22. package/dist/skills/agentv-eval-writer/references/eval-schema.json +104 -0
  23. package/dist/skills/agentv-eval-writer/references/rubric-evaluator.md +20 -0
  24. package/dist/{ts-eval-loader-FRQF6KHR-PQPW5XQK.js → ts-eval-loader-EQJX3OLT-THE7D3GR.js} +2 -2
  25. package/package.json +2 -2
  26. package/dist/chunk-3Y24WATS.js +0 -729
  27. package/dist/chunk-3Y24WATS.js.map +0 -1
  28. package/dist/chunk-6Y3W7HJP.js.map +0 -1
  29. package/dist/chunk-MIEYJ3YP.js.map +0 -1
  30. package/dist/chunk-PDGEPSPO.js.map +0 -1
  31. package/dist/chunk-Y35UPYKH.js.map +0 -1
  32. package/dist/studio/assets/index-Bw-5reb7.js +0 -116
  33. package/dist/studio/assets/index-CYUVGyMn.css +0 -1
  34. /package/dist/{artifact-writer-OYJ7VYQD.js.map → artifact-writer-PLUZAGYD.js.map} +0 -0
  35. /package/dist/{dist-KBYJJAXA.js.map → dist-W63D37ZR.js.map} +0 -0
  36. /package/dist/{interactive-RCBFUZUL.js.map → interactive-T6F2GRDI.js.map} +0 -0
  37. /package/dist/{ts-eval-loader-FRQF6KHR-PQPW5XQK.js.map → ts-eval-loader-EQJX3OLT-THE7D3GR.js.map} +0 -0
package/README.md CHANGED
@@ -77,9 +77,9 @@ agentv compare .agentv/results/runs/<timestamp>/index.jsonl
77
77
  ## Output formats
78
78
 
79
79
  ```bash
80
- agentv eval evals/my-eval.yaml # JSONL (default)
81
- agentv eval evals/my-eval.yaml -o report.html # HTML dashboard
82
- agentv eval evals/my-eval.yaml -o results.xml # JUnit XML for CI
80
+ agentv eval evals/my-eval.yaml --output ./run # writes ./run/index.jsonl
81
+ agentv eval evals/my-eval.yaml --export report.html
82
+ agentv eval evals/my-eval.yaml --export results.xml # JUnit XML for CI
83
83
  ```
84
84
 
85
85
  ## TypeScript SDK
@@ -124,6 +124,20 @@ bun test
124
124
 
125
125
  See [AGENTS.md](AGENTS.md) for development guidelines.
126
126
 
127
+ ## Docker Dashboard Deployment
128
+
129
+ To simulate a one-command production deployment of AgentV Dashboard with the
130
+ AgentV examples project and a remote results repository:
131
+
132
+ ```bash
133
+ AGENTV_RESULTS_REPO=EntityProcess/agentv-evalresults \
134
+ scripts/setup-dashboard-deployment.sh
135
+ ```
136
+
137
+ The script clones AgentV examples into `~/agentv-dashboard`, clones the results
138
+ repo, writes the Dashboard project registry under `$AGENTV_HOME/config.yaml`,
139
+ builds the Docker image, and starts Dashboard at `http://localhost:3117`.
140
+
127
141
  ## License
128
142
 
129
143
  MIT
@@ -14,11 +14,11 @@ import {
14
14
  writeArtifactsFromResults,
15
15
  writeInitialBenchmarkArtifact,
16
16
  writePerTestArtifacts
17
- } from "./chunk-3Y24WATS.js";
18
- import "./chunk-6Y3W7HJP.js";
17
+ } from "./chunk-2TDFJ2FZ.js";
18
+ import "./chunk-QKZLKDXB.js";
19
19
  import "./chunk-QOBQ5XYF.js";
20
20
  import "./chunk-BPGJ4HBU.js";
21
- import "./chunk-MIEYJ3YP.js";
21
+ import "./chunk-6QEIZ33V.js";
22
22
  import "./chunk-NPVGBFF6.js";
23
23
  import "./chunk-M7BUKBAF.js";
24
24
  import "./chunk-5H446C7X.js";
@@ -38,4 +38,4 @@ export {
38
38
  writeInitialBenchmarkArtifact,
39
39
  writePerTestArtifacts
40
40
  };
41
- //# sourceMappingURL=artifact-writer-OYJ7VYQD.js.map
41
+ //# sourceMappingURL=artifact-writer-PLUZAGYD.js.map