@eigenpal/cli 0.4.15 → 0.4.16

package/dist/cli.js

@@ -67845,7 +67845,7 @@ var init_evaluator_config = __esm(() => {
     returns: "a number in [0, 1] (the `: number` annotation is required)",
     throws: "caught and scored as 0"
   };
-  CUSTOM_SCRIPT_FUNCTION_DESCRIPTION = `Full TypeScript declaration of \`function scoreScript(expected, actual): number { ... }\`. ` + `Receives \`expected\` (${CUSTOM_SCRIPT_CONTRACT.expected}) ` + `and \`actual\` (${CUSTOM_SCRIPT_CONTRACT.actual}), returns ${CUSTOM_SCRIPT_CONTRACT.returns}. ` + `The \`: number\` return-type annotation is required and enforced at parse time. ` + `Throws are ${CUSTOM_SCRIPT_CONTRACT.throws}.`;
+  CUSTOM_SCRIPT_FUNCTION_DESCRIPTION = `Full TypeScript source for optional \`type\` aliases plus \`function scoreScript(expected, actual): number { ... }\`. ` + `Receives \`expected\` (${CUSTOM_SCRIPT_CONTRACT.expected}) ` + `and \`actual\` (${CUSTOM_SCRIPT_CONTRACT.actual}), returns ${CUSTOM_SCRIPT_CONTRACT.returns}. ` + `The \`: number\` return-type annotation is required and enforced at parse time. ` + `Throws are ${CUSTOM_SCRIPT_CONTRACT.throws}.`;
   CustomScriptConfigSchema = exports_external.object({
     function: exports_external.string().min(1, { message: "required" }).max(CUSTOM_SCRIPT_MAX_BYTES, {
       message: `must be ≤ ${CUSTOM_SCRIPT_MAX_BYTES} bytes`
@@ -67999,14 +67999,18 @@ var init_judge = __esm(() => {
 
 // ../types/src/eval/score-function.ts
 function defaultScoreFunction() {
-  return `/**
+  return `type WorkflowOutput = Record<string, unknown>;
+type Expected = WorkflowOutput;
+type Actual = WorkflowOutput;
+
+/**
  * Score the workflow output against the example's expected output.
  * Return a number in [0, 1]; throws are caught and scored as 0.
  *
  * The \`: number\` return-type annotation is required and enforced at
  * push time. The body is compiled to JS via sucrase before sandbox.
  */
-function scoreScript(expected: Expected, actual: Actual): number {
+function scoreScript(expected: WorkflowOutput, actual: WorkflowOutput): number {
   return JSON.stringify(actual) === JSON.stringify(expected) ? 1 : 0;
 }
 `;
@@ -181225,7 +181229,7 @@ import { fileURLToPath as fileURLToPath6 } from "url";
 // package.json
 var package_default = {
   name: "@eigenpal/cli",
-  version: "0.4.15",
+  version: "0.4.16",
   description: "Eigenpal CLI — author and run document workflows from your terminal. Agent-ready.",
   keywords: [
     "eigenpal",

package/dist/skill/reference/evaluators.md

@@ -109,7 +109,13 @@ one of the keys in `labels`; the harness then looks up the score.
   config:
     passThreshold: 1.0
     function: |
-      function scoreScript(expected: Expected, actual: Actual): number {
+      type WorkflowOutput = {
+        totalAmount: number;
+      };
+      type Expected = WorkflowOutput;
+      type Actual = WorkflowOutput;
+
+      function scoreScript(expected: WorkflowOutput, actual: WorkflowOutput): number {
         const a = actual.totalAmount ?? 0;
         const e = expected.totalAmount ?? 0;
         return Math.abs(a - e) <= 0.01 ? 1 : 0;
@@ -117,12 +123,13 @@ one of the keys in `labels`; the harness then looks up the score.
 ```
 
 Same WASM sandbox as `transform.script` (5s wall clock, 10 MB heap, no
-network). The YAML stores the **whole** `function scoreScript(expected,
-actual): number { ... }` declaration verbatim, same text the dashboard
-editor shows. The `: number` return-type annotation is required and
-enforced at parse time. `Expected` / `Actual` are in-scope type aliases
-in the dashboard editor (both are the workflow's output shape); plain
-`unknown` works too if you don't want them.
+network). The YAML stores the **whole** typed score source (optional
+`type` aliases plus `function scoreScript(expected, actual): number { ... }`)
+verbatim, same text the dashboard editor shows. The `: number` return-type annotation is required and
+enforced at parse time. The dashboard seeds new evaluators with a
+`WorkflowOutput` type alias derived from the workflow's `output:`
+declaration, plus `Expected` / `Actual` aliases for compatibility. Plain
+`unknown` works too if you don't want a typed signature.
 
 The signature shape is **locked**:
 
@@ -267,7 +274,7 @@ _Generated from `EvalConfigYamlSchema` in `@eigenpal/types/src/eval/evaluator-co
 
 | Field | Type | Required | Default | Description |
 | --- | --- | --- | --- | --- |
-| `function` | string | yes |  | Full TypeScript declaration of `function scoreScript(expected, actual): number { ... }`. Receives `expected` (the example's expected output) and `actual` (the workflow's actual output), returns a number in [0, 1] (the `: number` annotation is required). The `: number` return-type annotation is required and enforced at parse time. Throws are caught and scored as 0. |
+| `function` | string | yes |  | Full TypeScript source for optional `type` aliases plus `function scoreScript(expected, actual): number { ... }`. Receives `expected` (the example's expected output) and `actual` (the workflow's actual output), returns a number in [0, 1] (the `: number` annotation is required). The `: number` return-type annotation is required and enforced at parse time. Throws are caught and scored as 0. |
 | `timeoutMs` | integer | no | `5000` | Maximum wall-clock time the script can run before it's killed and the run is marked failed. |
 | `memoryLimitMb` | integer | no | `10` | Maximum memory the sandbox may allocate. Increase if the script processes large arrays or strings. |
 | `passThreshold` | number | no | `1` | Minimum script score this evaluator must reach for a run to pass. |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@eigenpal/cli",
-  "version": "0.4.15",
+  "version": "0.4.16",
   "description": "Eigenpal CLI — author and run document workflows from your terminal. Agent-ready.",
   "keywords": [
     "eigenpal",