@walwal-harness/cli 1.0.1 → 1.0.2

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.
Files changed (6) hide show
  1. package/README.md +1 -1
  2. package/assets/templates/HARNESS.md +3 -3
  3. package/assets/templates/config.json +1 -1
  4. package/package.json +1 -1
  5. package/skills/evaluator-functional/SKILL.md +1 -1
  6. package/skills/evaluator-visual/SKILL.md +1 -1
package/README.md CHANGED
@@ -26,7 +26,7 @@
26
26
  ```
27
27
  Planner → Generator-BE → Generator-FE → Evaluator-Func → Evaluator-Visual
28
28
  │ FAIL
29
- └──→ 재작업 (max 3회)
29
+ └──→ 재작업 (max 10회)
30
30
  ```
31
31
 
32
32
  ### FE-ONLY (기존 API에 프론트엔드 연동)
package/assets/templates/HARNESS.md CHANGED
@@ -74,9 +74,9 @@ Planner → Gen-BE → Eval-Func(API-only) → Archive
74
74
  ### 공통 — 실패 시 루프
75
75
 
76
76
  ```
77
- Eval-Func FAIL → failure_location에 따라 Gen-BE 또는 Gen-FE 재작업 (max 3회)
78
- Eval-Visual FAIL → Gen-FE 재작업 (max 3회)
79
- 3회 초과 → 사용자 개입 요청
77
+ Eval-Func FAIL → failure_location에 따라 Gen-BE 또는 Gen-FE 재작업 (max 10회)
78
+ Eval-Visual FAIL → Gen-FE 재작업 (max 10회)
79
+ 10회 초과 → 사용자 개입 요청
80
80
  ```
81
81
 
82
82
  ## 수동 프롬프트 실행 방법
package/assets/templates/config.json CHANGED
@@ -74,7 +74,7 @@
74
74
  "reason": "프론트가 존재하지 않는 API를 호출하는 실패 방지"
75
75
  },
76
76
  "retry_on_fail": true,
77
- "max_retries_per_sprint": 3,
77
+ "max_retries_per_sprint": 10,
78
78
  "archive_on_sprint_complete": true
79
79
  },
80
80
  "paths": {
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@walwal-harness/cli",
3
- "version": "1.0.1",
3
+ "version": "1.0.2",
4
4
  "description": "Production harness for AI agent engineering — Planner, Generator(BE/FE), Evaluator(Func/Visual) with Gotcha management",
5
5
  "bin": {
6
6
  "walwal-harness": "bin/init.js"
package/skills/evaluator-functional/SKILL.md CHANGED
@@ -55,4 +55,4 @@ Playwright 도구 → [도구 레퍼런스](references/playwright-tools.md)
55
55
  ## After Evaluation
56
56
 
57
57
  - **PASS** → Evaluator-Visual 핸드오프
58
- - **FAIL** → `failure_location` 기반 라우팅 (backend/frontend), max 3회
58
+ - **FAIL** → `failure_location` 기반 라우팅 (backend/frontend), max 10회
package/skills/evaluator-visual/SKILL.md CHANGED
@@ -38,4 +38,4 @@ disable-model-invocation: true
38
38
  ## After Evaluation
39
39
 
40
40
  - **PASS** → progress.txt 업데이트, Archive 실행 요청
41
- - **FAIL** → Generator-Frontend 재작업 (비주얼=항상 프론트), max 3회
41
+ - **FAIL** → Generator-Frontend 재작업 (비주얼=항상 프론트), max 10회