ai-test-loop 1.0.0 → 1.0.1
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 +5 -5
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -11,7 +11,7 @@ optional output patterns decide pass/fail. The model never gets to *say* the wor
|
|
|
11
11
|
to *show* it.
|
|
12
12
|
|
|
13
13
|
> **Quer isso pronto para o seu time?** Os packs com entrega por e-mail, o gate com relatório
|
|
14
|
-
> e o guia de verificação estão em **https://skills.seu.pet/gratis/ai-test-loop**
|
|
14
|
+
> e o guia de verificação estão em **https://skills.seu.pet/gratis/ai-test-loop?utm_source=npm&utm_medium=readme&utm_campaign=ai-test-loop**
|
|
15
15
|
|
|
16
16
|
---
|
|
17
17
|
|
|
@@ -126,9 +126,9 @@ cost of being wrong. It is for artifacts a human will rely on.
|
|
|
126
126
|
This repo is the free, complete tool. The store has the ready-made packs for the cases where
|
|
127
127
|
writing the checks is the slow part — CI gates, visual regression, MCP servers, MLOps guards:
|
|
128
128
|
|
|
129
|
-
- Free download / e-mail delivery: **https://skills.seu.pet/gratis/ai-test-loop**
|
|
130
|
-
- Catalog: **https://skills.seu.pet**
|
|
131
|
-
- Want it installed and wired into your repo: **https://skills.seu.pet/servico**
|
|
129
|
+
- Free download / e-mail delivery: **https://skills.seu.pet/gratis/ai-test-loop?utm_source=npm&utm_medium=readme&utm_campaign=ai-test-loop**
|
|
130
|
+
- Catalog: **https://skills.seu.pet/?utm_source=npm&utm_medium=readme&utm_campaign=ai-test-loop**
|
|
131
|
+
- Want it installed and wired into your repo: **https://skills.seu.pet/servico?utm_source=npm&utm_medium=readme&utm_campaign=ai-test-loop**
|
|
132
132
|
|
|
133
133
|
## License
|
|
134
134
|
|
|
@@ -142,4 +142,4 @@ O loop de teste para agentes: o construtor não assina o próprio trabalho. Um c
|
|
|
142
142
|
de verdade, dá nota 0–100, repete até o limite e barra a entrega se houver achado de segurança.
|
|
143
143
|
`python3 scripts/loop_runner.py --config loop.json` — sem chave de API e sem dependência.
|
|
144
144
|
|
|
145
|
-
Versão com entrega por e-mail e os packs prontos: https://skills.seu.pet/gratis/ai-test-loop
|
|
145
|
+
Versão com entrega por e-mail e os packs prontos: https://skills.seu.pet/gratis/ai-test-loop?utm_source=npm&utm_medium=readme&utm_campaign=ai-test-loop
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "ai-test-loop",
|
|
3
|
-
"version": "1.0.
|
|
3
|
+
"version": "1.0.1",
|
|
4
4
|
"description": "Deterministic critic for AI agents: runs weighed checks for real, scores 0-100 and blocks delivery below the threshold. Stdlib-only runner.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"author": "Samuel Medeiros",
|
|
@@ -36,4 +36,4 @@
|
|
|
36
36
|
"scripts": {
|
|
37
37
|
"smoke": "node bin/cli.js --config templates/loop.example.json --dry-run"
|
|
38
38
|
}
|
|
39
|
-
}
|
|
39
|
+
}
|