@gnsx/genesys.agent.eval 1.0.0
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 +9 -0
- package/dist/src/adapters/anthropic-adapter.d.ts +24 -0
- package/dist/src/adapters/anthropic-adapter.d.ts.map +1 -0
- package/dist/src/adapters/anthropic-adapter.js +80 -0
- package/dist/src/adapters/anthropic-adapter.js.map +1 -0
- package/dist/src/adapters/gemini-adapter.d.ts +23 -0
- package/dist/src/adapters/gemini-adapter.d.ts.map +1 -0
- package/dist/src/adapters/gemini-adapter.js +79 -0
- package/dist/src/adapters/gemini-adapter.js.map +1 -0
- package/dist/src/adapters/ollama-adapter.d.ts +28 -0
- package/dist/src/adapters/ollama-adapter.d.ts.map +1 -0
- package/dist/src/adapters/ollama-adapter.js +54 -0
- package/dist/src/adapters/ollama-adapter.js.map +1 -0
- package/dist/src/adapters/openai-adapter.d.ts +24 -0
- package/dist/src/adapters/openai-adapter.d.ts.map +1 -0
- package/dist/src/adapters/openai-adapter.js +80 -0
- package/dist/src/adapters/openai-adapter.js.map +1 -0
- package/dist/src/adapters/pi-adapter.d.ts +27 -0
- package/dist/src/adapters/pi-adapter.d.ts.map +1 -0
- package/dist/src/adapters/pi-adapter.js +136 -0
- package/dist/src/adapters/pi-adapter.js.map +1 -0
- package/dist/src/agent-adapter.d.ts +130 -0
- package/dist/src/agent-adapter.d.ts.map +1 -0
- package/dist/src/agent-adapter.js +134 -0
- package/dist/src/agent-adapter.js.map +1 -0
- package/dist/src/args.d.ts +22 -0
- package/dist/src/args.d.ts.map +1 -0
- package/dist/src/args.js +224 -0
- package/dist/src/args.js.map +1 -0
- package/dist/src/cli-runner.d.ts +39 -0
- package/dist/src/cli-runner.d.ts.map +1 -0
- package/dist/src/cli-runner.js +105 -0
- package/dist/src/cli-runner.js.map +1 -0
- package/dist/src/embedding-judge.d.ts +93 -0
- package/dist/src/embedding-judge.d.ts.map +1 -0
- package/dist/src/embedding-judge.js +160 -0
- package/dist/src/embedding-judge.js.map +1 -0
- package/dist/src/index.d.ts +15 -0
- package/dist/src/index.d.ts.map +1 -0
- package/dist/src/index.js +20 -0
- package/dist/src/index.js.map +1 -0
- package/dist/src/judge.d.ts +95 -0
- package/dist/src/judge.d.ts.map +1 -0
- package/dist/src/judge.js +189 -0
- package/dist/src/judge.js.map +1 -0
- package/dist/src/launcher.d.ts +9 -0
- package/dist/src/launcher.d.ts.map +1 -0
- package/dist/src/launcher.js +129 -0
- package/dist/src/launcher.js.map +1 -0
- package/dist/src/reporter.d.ts +86 -0
- package/dist/src/reporter.d.ts.map +1 -0
- package/dist/src/reporter.js +384 -0
- package/dist/src/reporter.js.map +1 -0
- package/dist/src/runner.d.ts +75 -0
- package/dist/src/runner.d.ts.map +1 -0
- package/dist/src/runner.js +165 -0
- package/dist/src/runner.js.map +1 -0
- package/dist/src/test-loader.d.ts +66 -0
- package/dist/src/test-loader.d.ts.map +1 -0
- package/dist/src/test-loader.js +140 -0
- package/dist/src/test-loader.js.map +1 -0
- package/dist/src/types.d.ts +161 -0
- package/dist/src/types.d.ts.map +1 -0
- package/dist/src/types.js +7 -0
- package/dist/src/types.js.map +1 -0
- package/dist/src/utils/package.d.ts +16 -0
- package/dist/src/utils/package.d.ts.map +1 -0
- package/dist/src/utils/package.js +30 -0
- package/dist/src/utils/package.js.map +1 -0
- package/dist/tsconfig.tsbuildinfo +1 -0
- package/examples/basic-tests.yaml +22 -0
- package/package.json +41 -0
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
name: Basic Coding Tests
|
|
2
|
+
description: Simple tests to ensure the base harness works
|
|
3
|
+
|
|
4
|
+
context: |
|
|
5
|
+
You are a helpful coding assistant. When asked a question, respond with the answer only. Do not add any additional text or explanation.
|
|
6
|
+
|
|
7
|
+
tests:
|
|
8
|
+
- id: simple-add
|
|
9
|
+
input: what is 1 + 2?
|
|
10
|
+
expectedOutput: "3"
|
|
11
|
+
|
|
12
|
+
- id: simple-subtract
|
|
13
|
+
input: what is 1 - 2?
|
|
14
|
+
expectedOutput: "-1"
|
|
15
|
+
|
|
16
|
+
- id: simple-multiply
|
|
17
|
+
input: what is 1 * 2?
|
|
18
|
+
expectedOutput: "2"
|
|
19
|
+
|
|
20
|
+
- id: simple-divide
|
|
21
|
+
input: what is 1 / 2?
|
|
22
|
+
expectedOutput: "0.5"
|
package/package.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "@gnsx/genesys.agent.eval",
|
|
3
|
+
"version": "1.0.0",
|
|
4
|
+
"type": "module",
|
|
5
|
+
"description": "Agent evaluation harness for benchmarking AI agents against test suites",
|
|
6
|
+
"publishConfig": {
|
|
7
|
+
"access": "public"
|
|
8
|
+
},
|
|
9
|
+
"bin": {
|
|
10
|
+
"genesys-eval": "./dist/src/launcher.js"
|
|
11
|
+
},
|
|
12
|
+
"exports": {
|
|
13
|
+
".": "./dist/index.js",
|
|
14
|
+
"./package.json": "./package.json"
|
|
15
|
+
},
|
|
16
|
+
"main": "./dist/index.js",
|
|
17
|
+
"files": [
|
|
18
|
+
"dist",
|
|
19
|
+
"examples"
|
|
20
|
+
],
|
|
21
|
+
"scripts": {
|
|
22
|
+
"compile": "run-cmd tsc --build",
|
|
23
|
+
"build": "run-cmd tsc --build",
|
|
24
|
+
"dev": "tsx src/launcher.ts",
|
|
25
|
+
"lint": "run-cmd run-eslint ."
|
|
26
|
+
},
|
|
27
|
+
"dependencies": {
|
|
28
|
+
"@ai-sdk/anthropic": "^1.0.0",
|
|
29
|
+
"@ai-sdk/google": "^1.0.0",
|
|
30
|
+
"@ai-sdk/openai": "^1.0.0",
|
|
31
|
+
"@huggingface/transformers": "catalog:",
|
|
32
|
+
"ai": "catalog:",
|
|
33
|
+
"yaml": "catalog:",
|
|
34
|
+
"zod": "catalog:"
|
|
35
|
+
},
|
|
36
|
+
"devDependencies": {
|
|
37
|
+
"@gnsx/dev-tools": "workspace:*",
|
|
38
|
+
"@types/node": "catalog:"
|
|
39
|
+
},
|
|
40
|
+
"license": "UNLICENSED"
|
|
41
|
+
}
|