@b4run/evals 0.8.36 → 0.10.0
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/dist/tsconfig.tsbuildinfo +1 -1
- package/dist/types.d.ts +7 -1
- package/dist/types.d.ts.map +1 -1
- package/package.json +4 -4
package/dist/types.d.ts
CHANGED
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
import type { AgentRunResult, FixtureSet, ScriptBuilder } from "@b4run/testing";
|
|
1
|
+
import type { AgentHarnessMiddlewareContext, AgentRunResult, FixtureSet, ScriptBuilder } from "@b4run/testing";
|
|
2
2
|
/** One dataset row. `input` is the user message for agent routes (v1). */
|
|
3
3
|
export interface EvalCase {
|
|
4
4
|
readonly name?: string;
|
|
@@ -28,6 +28,12 @@ export interface EvalDefinition {
|
|
|
28
28
|
readonly route?: string;
|
|
29
29
|
readonly dataset: Dataset;
|
|
30
30
|
readonly scorers: readonly Scorer[];
|
|
31
|
+
/**
|
|
32
|
+
* The context the route's `middleware.ts` would have produced, forwarded to
|
|
33
|
+
* `createAgentHarness({ middlewareContext })` by `b4 eval`. A function is
|
|
34
|
+
* evaluated once per case.
|
|
35
|
+
*/
|
|
36
|
+
readonly middlewareContext?: AgentHarnessMiddlewareContext;
|
|
31
37
|
/** Sugar for gate.mean(threshold). Ignored if `gate` is set. */
|
|
32
38
|
readonly threshold?: number;
|
|
33
39
|
readonly gate?: GatePolicy;
|
package/dist/types.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,
|
|
1
|
+
{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,6BAA6B,EAC7B,cAAc,EACd,UAAU,EACV,aAAa,EACd,MAAM,gBAAgB,CAAA;AAEvB,0EAA0E;AAC1E,MAAM,WAAW,QAAQ;IACvB,QAAQ,CAAC,IAAI,CAAC,EAAE,MAAM,CAAA;IACtB,QAAQ,CAAC,KAAK,EAAE,OAAO,CAAA;IACvB,QAAQ,CAAC,QAAQ,CAAC,EAAE,OAAO,CAAA;IAC3B,sEAAsE;IACtE,QAAQ,CAAC,QAAQ,CAAC,EAAE,UAAU,GAAG,aAAa,CAAA;IAC9C,QAAQ,CAAC,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;CAC5C;AAED,mFAAmF;AACnF,MAAM,MAAM,OAAO,GAAG,SAAS,QAAQ,EAAE,GAAG,MAAM,GAAG,CAAC,MAAM,QAAQ,EAAE,GAAG,OAAO,CAAC,QAAQ,EAAE,CAAC,CAAC,CAAA;AAE7F,uEAAuE;AACvE,MAAM,MAAM,KAAK,GACb,MAAM,GACN,OAAO,GACP;IAAE,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,MAAM,CAAC,EAAE,MAAM,CAAA;CAAE,CAAA;AAEjF,MAAM,WAAW,MAAM;IACrB,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAA;IACrB,yEAAyE;IACzE,QAAQ,CAAC,SAAS,CAAC,EAAE,MAAM,CAAA;IAC3B,QAAQ,CAAC,KAAK,EAAE,CAAC,GAAG,EAAE,cAAc,EAAE,QAAQ,EAAE,QAAQ,KAAK,KAAK,GAAG,OAAO,CAAC,KAAK,CAAC,CAAA;CACpF;AAED,MAAM,WAAW,cAAc;IAC7B,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAA;IACrB,mFAAmF;IACnF,QAAQ,CAAC,KAAK,CAAC,EAAE,MAAM,CAAA;IACvB,QAAQ,CAAC,OAAO,EAAE,OAAO,CAAA;IACzB,QAAQ,CAAC,OAAO,EAAE,SAAS,MAAM,EAAE,CAAA;IACnC;;;;OAIG;IACH,QAAQ,CAAC,iBAAiB,CAAC,EAAE,6BAA6B,CAAA;IAC1D,gEAAgE;IAChE,QAAQ,CAAC,SAAS,CAAC,EAAE,MAAM,CAAA;IAC3B,QAAQ,CAAC,IAAI,CAAC,EAAE,UAAU,CAAA;CAC3B;AAED,oDAAoD;AACpD,MAAM,WAAW,SAAS;IACxB,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAA;IACvB,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAA;IACtB,QAAQ,CAAC,KAAK,CAAC,EAAE,MAAM,CAAA;IACvB,QAAQ,CAAC,MAAM,CAAC,EAAE,MAAM,CAAA;CACzB;AAED,MAAM,WAAW,UAAU;IACzB,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAA;IACrB,QAAQ,CAAC,MAAM,EAAE,SAAS,SAAS,EAAE,CAAA;IACrC,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAA;IACrB,uEAAuE;IACvE,QAAQ,CAAC,MAAM,EAAE,OAAO,CAAA;CACzB;AAED,MAAM,WAAW,eAAe;IAC9B,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAA;IACvB,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAA;IACrB,QAAQ,CAAC,SAAS,CAAC,EAAE,MAAM,CAAA;CAC5B;AAED,4CAA4C;AAC5C,MAAM,WAAW,YAAY;IAC3B,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAA;IACrB,QAAQ,CAAC,KAAK,EAAE,SAAS,UAAU,EAAE,CAAA;IACrC,QAAQ,CAAC,QAAQ,EAAE,SAAS,eAAe,EAAE,CAAA;IAC7C,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAA;CACtB;AAED,MAAM,WAAW,UAAW,SAAQ,YAAY;IAC9C,+EAA+E;IAC/E,QAAQ,CAAC,KAAK,EAAE,OAAO,CAAA;IACvB,QAAQ,CAAC,MAAM,EAAE,OAAO,CAAA;IACxB,QAAQ,CAAC,MAAM,CAAC,EAAE,MAAM,CAAA;CACzB;AAED,MAAM,MAAM,UAAU,GAAG;IAAE,QAAQ,CAAC,MAAM,EAAE,OAAO,CAAC;IAAC,QAAQ,CAAC,MAAM,CAAC,EAAE,MAAM,CAAA;CAAE,CAAA;AAC/E,MAAM,MAAM,UAAU,GAAG,CAAC,MAAM,EAAE,YAAY,KAAK,UAAU,CAAA;AAE7D,iFAAiF;AACjF,eAAO,MAAM,gBAAgB,MAAM,CAAA"}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@b4run/evals",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.10.0",
|
|
4
4
|
"private": false,
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "MIT",
|
|
@@ -39,12 +39,12 @@
|
|
|
39
39
|
"access": "public"
|
|
40
40
|
},
|
|
41
41
|
"peerDependencies": {
|
|
42
|
-
"@b4run/testing": "0.
|
|
42
|
+
"@b4run/testing": "0.10.0"
|
|
43
43
|
},
|
|
44
44
|
"devDependencies": {
|
|
45
45
|
"@types/node": "26.1.2",
|
|
46
|
-
"@b4run/config-typescript": "0.
|
|
47
|
-
"@b4run/testing": "0.
|
|
46
|
+
"@b4run/config-typescript": "0.10.0",
|
|
47
|
+
"@b4run/testing": "0.10.0"
|
|
48
48
|
},
|
|
49
49
|
"scripts": {
|
|
50
50
|
"build": "tsc -b tsconfig.json",
|