agentv 4.32.0-next.1 → 4.34.0-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/README.md +4 -5
- package/dist/{artifact-writer-VDF7KRWL.js → artifact-writer-UWZX5JKX.js} +4 -4
- package/dist/{chunk-TAZBCVEZ.js → chunk-6QEIZ33V.js} +1340 -279
- package/dist/chunk-6QEIZ33V.js.map +1 -0
- package/dist/{chunk-IGTRNQAM.js → chunk-FK5FLLME.js} +2383 -674
- package/dist/chunk-FK5FLLME.js.map +1 -0
- package/dist/chunk-GPRZ7XSC.js +1234 -0
- package/dist/chunk-GPRZ7XSC.js.map +1 -0
- package/dist/{chunk-5JMFFG36.js → chunk-KMO527KH.js} +784 -1081
- package/dist/chunk-KMO527KH.js.map +1 -0
- package/dist/{chunk-LX5AK3P7.js → chunk-KP4SPQ2M.js} +585 -191
- package/dist/chunk-KP4SPQ2M.js.map +1 -0
- package/dist/cli.js +5 -5
- package/dist/dashboard/assets/{index-BdoQWnyM.js → index-79OddHgT.js} +1 -1
- package/dist/dashboard/assets/index-BPMAZqjE.css +1 -0
- package/dist/dashboard/assets/index-BycNIWwy.js +118 -0
- package/dist/dashboard/index.html +3 -3
- package/dist/{dist-GICSKMNP.js → dist-Z5VWSDOO.js} +58 -6
- package/dist/index.js +5 -5
- package/dist/{interactive-GIDBBDYZ.js → interactive-NTT2QLPR.js} +5 -5
- package/dist/skills/agentv-eval-writer/SKILL.md +2 -1
- package/dist/skills/agentv-eval-writer/references/eval-schema.json +104 -0
- package/dist/skills/agentv-eval-writer/references/rubric-evaluator.md +20 -0
- package/dist/{ts-eval-loader-Z6IUSDNA-YBOE4JIQ.js → ts-eval-loader-EQJX3OLT-THE7D3GR.js} +2 -2
- package/package.json +2 -2
- package/dist/chunk-2ZEY3WBH.js +0 -729
- package/dist/chunk-2ZEY3WBH.js.map +0 -1
- package/dist/chunk-5JMFFG36.js.map +0 -1
- package/dist/chunk-IGTRNQAM.js.map +0 -1
- package/dist/chunk-LX5AK3P7.js.map +0 -1
- package/dist/chunk-TAZBCVEZ.js.map +0 -1
- package/dist/dashboard/assets/index-DcPH8PyS.css +0 -1
- package/dist/dashboard/assets/index-EXkiwqam.js +0 -116
- /package/dist/{artifact-writer-VDF7KRWL.js.map → artifact-writer-UWZX5JKX.js.map} +0 -0
- /package/dist/{dist-GICSKMNP.js.map → dist-Z5VWSDOO.js.map} +0 -0
- /package/dist/{interactive-GIDBBDYZ.js.map → interactive-NTT2QLPR.js.map} +0 -0
- /package/dist/{ts-eval-loader-Z6IUSDNA-YBOE4JIQ.js.map → ts-eval-loader-EQJX3OLT-THE7D3GR.js.map} +0 -0
package/README.md
CHANGED
|
@@ -77,9 +77,8 @@ agentv compare .agentv/results/runs/<timestamp>/index.jsonl
|
|
|
77
77
|
## Output formats
|
|
78
78
|
|
|
79
79
|
```bash
|
|
80
|
-
agentv eval evals/my-eval.yaml
|
|
81
|
-
|
|
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
|
+
cat ./run/index.jsonl # JSONL results for scripts/CI
|
|
83
82
|
```
|
|
84
83
|
|
|
85
84
|
## TypeScript SDK
|
|
@@ -135,8 +134,8 @@ AGENTV_RESULTS_REPO=EntityProcess/agentv-evalresults \
|
|
|
135
134
|
```
|
|
136
135
|
|
|
137
136
|
The script clones AgentV examples into `~/agentv-dashboard`, clones the results
|
|
138
|
-
repo, writes the Dashboard project registry
|
|
139
|
-
Dashboard at `http://localhost:3117`.
|
|
137
|
+
repo, writes the Dashboard project registry under `$AGENTV_HOME/config.yaml`,
|
|
138
|
+
builds the Docker image, and starts Dashboard at `http://localhost:3117`.
|
|
140
139
|
|
|
141
140
|
## License
|
|
142
141
|
|
|
@@ -14,11 +14,11 @@ import {
|
|
|
14
14
|
writeArtifactsFromResults,
|
|
15
15
|
writeInitialBenchmarkArtifact,
|
|
16
16
|
writePerTestArtifacts
|
|
17
|
-
} from "./chunk-
|
|
18
|
-
import "./chunk-
|
|
17
|
+
} from "./chunk-GPRZ7XSC.js";
|
|
18
|
+
import "./chunk-KP4SPQ2M.js";
|
|
19
19
|
import "./chunk-QOBQ5XYF.js";
|
|
20
20
|
import "./chunk-BPGJ4HBU.js";
|
|
21
|
-
import "./chunk-
|
|
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-
|
|
41
|
+
//# sourceMappingURL=artifact-writer-UWZX5JKX.js.map
|