@eigenpal/cli 0.10.15 → 0.10.17
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/CHANGELOG.md +17 -0
- package/dist/cli.js +672 -3139
- package/dist/skill/reference/cli/run.md +1 -0
- package/dist/skill/reference/step-types.md +2 -0
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,22 @@
|
|
|
1
1
|
# @eigenpal/cli
|
|
2
2
|
|
|
3
|
+
## 0.10.16
|
|
4
|
+
|
|
5
|
+
### Patch Changes
|
|
6
|
+
|
|
7
|
+
- b1f0bca: `eigenpal run <workflow> --example <name>` now actually grades the example
|
|
8
|
+
instead of printing `PASS` whenever the run merely finished. It runs the
|
|
9
|
+
workflow's current published version on the server's stored dataset example, so
|
|
10
|
+
configured evaluators run automatically and the CLI surfaces the real weighted
|
|
11
|
+
score and per-evaluator pass/fail. Workflows with no evaluators fall back to a
|
|
12
|
+
structural diff of the output against the example's stored expected output. The
|
|
13
|
+
summary reports two separate signals: execution health (`ok`/`errored`) and
|
|
14
|
+
accuracy. Add `--fail-on-mismatch` to exit non-zero when a graded example fails.
|
|
15
|
+
|
|
16
|
+
Because the run uses the server-side example, push your latest dataset and
|
|
17
|
+
evaluators (`eigenpal workflow dataset push`, `eigenpal workflow evaluators
|
|
18
|
+
push`) before running `--example`.
|
|
19
|
+
|
|
3
20
|
## 0.10.9
|
|
4
21
|
|
|
5
22
|
### Patch Changes
|