@wix/eval-assertions 0.17.0 → 0.18.0
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/README.md +3 -2
- package/build/index.js +124 -95
- package/build/index.js.map +4 -4
- package/build/index.mjs +117 -94
- package/build/index.mjs.map +4 -4
- package/build/types/evaluators/assertion-evaluator.d.ts +4 -17
- package/build/types/evaluators/index.d.ts +2 -2
- package/build/types/evaluators/llm-judge-evaluator.d.ts +11 -0
- package/build/types/index.d.ts +2 -1
- package/build/types/tools/index.d.ts +1 -0
- package/build/types/tools/read-file-tool.d.ts +10 -0
- package/package.json +4 -3
package/build/types/index.d.ts
CHANGED
|
@@ -5,4 +5,5 @@
|
|
|
5
5
|
* Supports skill invocation checks, build validation, and LLM-based judging.
|
|
6
6
|
*/
|
|
7
7
|
export { AssertionSchema, SkillWasCalledAssertionSchema, BuildPassedAssertionSchema, TimeAssertionSchema, CostAssertionSchema, LlmJudgeAssertionSchema, type Assertion, type SkillWasCalledAssertion, type BuildPassedAssertion, type TimeAssertion, type CostAssertion, type LlmJudgeAssertion, LLMTraceSchema, LLMTraceStepSchema, LLMTraceSummarySchema, LLMBreakdownStatsSchema, TokenUsageSchema, LLMStepType, type LLMTrace, type LLMTraceStep, type LLMTraceSummary, type LLMBreakdownStats, type TokenUsage, AssertionResultSchema, AssertionResultStatus, type AssertionResult, type EvaluationInput, type FileDiff, } from "./types/index.js";
|
|
8
|
-
export { evaluateAssertions, registerEvaluator, getEvaluator, AssertionEvaluator, SkillWasCalledEvaluator, BuildPassedEvaluator, TimeEvaluator, CostEvaluator, LlmJudgeEvaluator, formatTraceForJudge, replacePlaceholders, stripMarkdownCodeBlock, validateJudgeResult, type AssertionContext, type LlmConfig, type
|
|
8
|
+
export { evaluateAssertions, registerEvaluator, getEvaluator, AssertionEvaluator, SkillWasCalledEvaluator, BuildPassedEvaluator, TimeEvaluator, CostEvaluator, LlmJudgeEvaluator, JudgeResultSchema, formatTraceForJudge, replacePlaceholders, stripMarkdownCodeBlock, validateJudgeResult, type AssertionContext, type LlmConfig, type JudgeResult, } from "./evaluators/index.js";
|
|
9
|
+
export { createReadFileTool } from "./tools/index.js";
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
export { createReadFileTool } from "./read-file-tool.js";
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@wix/eval-assertions",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.18.0",
|
|
4
4
|
"description": "Assertion framework for AI agent evaluations - supports skill invocation checks, build validation, and LLM-based judging",
|
|
5
5
|
"files": [
|
|
6
6
|
"build"
|
|
@@ -13,7 +13,8 @@
|
|
|
13
13
|
"build": "yarn run clean && yarn run build:cjs && yarn run build:esm && yarn run build:types",
|
|
14
14
|
"lint": "eslint .",
|
|
15
15
|
"typecheck": "tsc --noEmit",
|
|
16
|
-
"test": "node --import tsx --test tests/**/*.test.ts"
|
|
16
|
+
"test": "node --import tsx --test tests/**/*.test.ts",
|
|
17
|
+
"test:agent": "node --import tsx --test tests/**/*.agent-test.ts"
|
|
17
18
|
},
|
|
18
19
|
"dependencies": {
|
|
19
20
|
"@ai-sdk/anthropic": "^3.0.2",
|
|
@@ -60,5 +61,5 @@
|
|
|
60
61
|
],
|
|
61
62
|
"license": "MIT",
|
|
62
63
|
"author": "Wix",
|
|
63
|
-
"falconPackageHash": "
|
|
64
|
+
"falconPackageHash": "2862b952ba60dd90bbde91927c092b33ea729c4ddaf92ff2784d03c5"
|
|
64
65
|
}
|