gen-pr 2.13.0 → 2.13.1
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 +28 -4
- package/dist/action.js +1 -1
- package/dist/cli.js +1 -1
- package/dist/main-DQHZniwI.js +2 -0
- package/package.json +6 -6
- package/dist/main-BlLRxvYA.js +0 -2
package/README.md
CHANGED
|
@@ -5,20 +5,44 @@
|
|
|
5
5
|
|
|
6
6
|
# gen-pr
|
|
7
7
|
|
|
8
|
-
A CLI and GitHub Action that automatically
|
|
8
|
+
A CLI and GitHub Action that automatically generates pull requests using AI (specifically, Large Language Models or LLMs) from GitHub issues and pull requests.
|
|
9
9
|
|
|
10
|
-
This tool
|
|
10
|
+
This tool delivers the ultimate "Vibe Coding" experience, allowing humans to focus solely on writing issues while AI handles all implementation details. Our vision is to create a workflow where developers only need to describe what they want, and the AI translates those requirements into working code.
|
|
11
11
|
|
|
12
12
|
## Features
|
|
13
13
|
|
|
14
|
-
- **Planning Capability**: Uses
|
|
15
|
-
- **Multiple AI Coding Tools**: Supports various coding tools including:
|
|
14
|
+
- **Planning Capability**: Uses LLMs to analyze source code and develop implementation strategies before making any changes.
|
|
15
|
+
- **Multiple AI Coding Tools**: Supports various coding tools, including:
|
|
16
16
|
- [Aider](https://aider.chat/): An interactive AI pair programming tool
|
|
17
17
|
- [Codex CLI](https://github.com/openai/codex): OpenAI's coding agent
|
|
18
18
|
- [Claude Code](https://github.com/anthropics/claude-code): Anthropic's agentic coding tool
|
|
19
19
|
- [Gemini CLI](https://github.com/google-gemini/gemini-cli): Google's AI coding assistant
|
|
20
20
|
- **Flexible Integration**: Works as both a CLI tool and a GitHub Action
|
|
21
21
|
|
|
22
|
+
## Our Use Cases
|
|
23
|
+
|
|
24
|
+
Currently, we use `gen-pr` to create scaffolding pull requests. We have five different `gen-pr` workflows to generate PRs with various combinations of LLMs and coding tools.
|
|
25
|
+
We review the pull requests, select the best one, and then continue to write code on the PR manually. This approach has successfully reduced the amount of manually written code.
|
|
26
|
+
Below is an analysis report generated by [calc-ai-contrib](https://github.com/WillBooster/calc-ai-contrib) for June 2025, during the development of [Exercode](https://exercode.willbooster.com/).
|
|
27
|
+
`AI` indicates the amount of code written fully automatically by `gen-pr`. We are very satisfied with the results and consider the AI contribution ratio a key metric for measuring our productivity.
|
|
28
|
+
|
|
29
|
+
```
|
|
30
|
+
╔══════════════════════════════════════════════════╗
|
|
31
|
+
║ CONTRIBUTION ANALYSIS REPORT ║
|
|
32
|
+
╠══════════════════════════════════════════════════╣
|
|
33
|
+
║ Date: 2025-06-01 to 2025-06-30 (PRs: 91) ║
|
|
34
|
+
║ Total Edits: 9,925 (+6,729 / -3,196) ║
|
|
35
|
+
╠══════════════════════════════════════════════════╣
|
|
36
|
+
║ AI vs Human: [█████░░░░░░░░░░░░░░░░░] 24% / 76% ║
|
|
37
|
+
║ Contributors: 1 AI, 6 Human ║
|
|
38
|
+
╚══════════════════════════════════════════════════╝
|
|
39
|
+
|
|
40
|
+
📊 DETAILED BREAKDOWN
|
|
41
|
+
────────────────────────────────────────
|
|
42
|
+
🤖 AI : [████░░░░░░░░░░░░] 24% | 2,365 Edits (+1,685 / -680)
|
|
43
|
+
👥 Human: [████████████░░░░] 76% | 7,560 Edits (+5,044 / -2,516)
|
|
44
|
+
```
|
|
45
|
+
|
|
22
46
|
## Requirements
|
|
23
47
|
|
|
24
48
|
- For development:
|