gen-pr 2.15.0 → 2.16.1
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 +31 -31
- package/dist/action.js +1 -1
- package/dist/cli.js +1 -1
- package/dist/{main-DFwK9vqU.js → main-Cfdt-NGg.js} +2 -2
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -11,12 +11,12 @@ This tool delivers the ultimate "Vibe Coding" experience, allowing humans to foc
|
|
|
11
11
|
|
|
12
12
|
## Features
|
|
13
13
|
|
|
14
|
-
- **Planning Capability**: Uses LLMs to analyze source code and develop implementation strategies before making any changes.
|
|
15
14
|
- **Multiple AI Coding Tools**: Supports various coding tools, including:
|
|
16
15
|
- [Aider](https://aider.chat/): An interactive AI pair programming tool
|
|
17
16
|
- [Codex CLI](https://github.com/openai/codex): OpenAI's coding agent
|
|
18
17
|
- [Claude Code](https://github.com/anthropics/claude-code): Anthropic's agentic coding tool
|
|
19
18
|
- [Gemini CLI](https://github.com/google-gemini/gemini-cli): Google's AI coding assistant
|
|
19
|
+
- **Planning Capability**: Uses LLMs to analyze source code and develop implementation strategies before making any changes.
|
|
20
20
|
- **Flexible Integration**: Works as both a CLI tool and a GitHub Action
|
|
21
21
|
|
|
22
22
|
## Our Use Cases
|
|
@@ -56,12 +56,32 @@ Below is an analysis report generated by [calc-ai-contrib](https://github.com/Wi
|
|
|
56
56
|
|
|
57
57
|
### GitHub Actions
|
|
58
58
|
|
|
59
|
-
See [action.yml](action.yml) and [.github/workflows/
|
|
59
|
+
See [action.yml](action.yml) and [.github/workflows/gen-pr-example.yml](.github/workflows/gen-pr-example.yml).
|
|
60
60
|
|
|
61
61
|
### CLI
|
|
62
62
|
|
|
63
63
|
Here are some examples for creating PRs for issue [#89](https://github.com/WillBooster/gen-pr/issues/89).
|
|
64
64
|
|
|
65
|
+
#### Without Planning
|
|
66
|
+
|
|
67
|
+
Claude Code:
|
|
68
|
+
|
|
69
|
+
```sh
|
|
70
|
+
npx --yes gen-pr@latest --issue-number 89 --coding-tool claude-code
|
|
71
|
+
```
|
|
72
|
+
|
|
73
|
+
Codex:
|
|
74
|
+
|
|
75
|
+
```sh
|
|
76
|
+
npx --yes gen-pr@latest --issue-number 89 --coding-tool codex
|
|
77
|
+
```
|
|
78
|
+
|
|
79
|
+
Gemini CLI:
|
|
80
|
+
|
|
81
|
+
```sh
|
|
82
|
+
npx --yes gen-pr@latest --issue-number 89 --coding-tool gemini
|
|
83
|
+
```
|
|
84
|
+
|
|
65
85
|
#### With Planning (Strongly Recommended for Aider)
|
|
66
86
|
|
|
67
87
|
`gen-pr` can generate an implementation plan by reading files in the target repository using [Repomix](https://github.com/yamadashy/repomix).
|
|
@@ -73,10 +93,10 @@ Gemini 2.5 Pro (`gemini/gemini-2.5-pro`) for planning and Aider for coding:
|
|
|
73
93
|
npx --yes gen-pr@latest --issue-number 89 --planning-model gemini/gemini-2.5-pro --reasoning-effort high --repomix-extra-args="--compress --remove-empty-lines --include 'src/**/*.ts'" --aider-extra-args="--model gemini/gemini-2.5-pro --edit-format diff-fenced --test-cmd='yarn check-for-ai' --auto-test"
|
|
74
94
|
```
|
|
75
95
|
|
|
76
|
-
Claude Opus 4 on Bedrock (`bedrock/us.anthropic.claude-opus-4-
|
|
96
|
+
Claude Opus 4 on Bedrock (`bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0`) for planning and Aider for coding:
|
|
77
97
|
|
|
78
98
|
```sh
|
|
79
|
-
npx --yes gen-pr@latest --issue-number 89 --planning-model bedrock/us.anthropic.claude-opus-4-
|
|
99
|
+
npx --yes gen-pr@latest --issue-number 89 --planning-model bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0 --reasoning-effort high --repomix-extra-args="--compress --remove-empty-lines --include 'src/**/*.ts'" --aider-extra-args="--model bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0 --test-cmd='yarn check-for-ai' --auto-test"
|
|
80
100
|
```
|
|
81
101
|
|
|
82
102
|
Gemini 2.5 Pro (`gemini/gemini-2.5-pro`) for planning and Claude Code for coding:
|
|
@@ -109,26 +129,6 @@ Local Gemma 3n via Ollama (`ollama/gemma3n`) for planning and Aider for coding:
|
|
|
109
129
|
npx --yes gen-pr@latest --issue-number 89 --planning-model ollama/gemma3n --repomix-extra-args="--compress --remove-empty-lines --include 'src/**/*.ts'" --aider-extra-args="--model ollama/gemma3n --edit-format diff-fenced --test-cmd='yarn check-for-ai' --auto-test"
|
|
110
130
|
```
|
|
111
131
|
|
|
112
|
-
#### Without Planning
|
|
113
|
-
|
|
114
|
-
Claude Code:
|
|
115
|
-
|
|
116
|
-
```sh
|
|
117
|
-
npx --yes gen-pr@latest --issue-number 89 --coding-tool claude-code
|
|
118
|
-
```
|
|
119
|
-
|
|
120
|
-
Codex:
|
|
121
|
-
|
|
122
|
-
```sh
|
|
123
|
-
npx --yes gen-pr@latest --issue-number 89 --coding-tool codex
|
|
124
|
-
```
|
|
125
|
-
|
|
126
|
-
Gemini CLI:
|
|
127
|
-
|
|
128
|
-
```sh
|
|
129
|
-
npx --yes gen-pr@latest --issue-number 89 --coding-tool gemini
|
|
130
|
-
```
|
|
131
|
-
|
|
132
132
|
#### For PR ([#103](https://github.com/WillBooster/gen-pr/pull/103))
|
|
133
133
|
|
|
134
134
|
Codex:
|
|
@@ -143,9 +143,9 @@ You can create a YAML configuration file named `gen-pr.config.yml` or `gen-pr.co
|
|
|
143
143
|
|
|
144
144
|
```yaml
|
|
145
145
|
repomix-extra-args: "--compress --remove-empty-lines --include 'src/**/*.ts'"
|
|
146
|
-
aider-extra-args:
|
|
146
|
+
aider-extra-args: '--model gemini/gemini-2.5-pro --edit-format diff-fenced --no-gitignore'
|
|
147
147
|
coding-tool: claude-code
|
|
148
|
-
test-command:
|
|
148
|
+
test-command: 'yarn check-for-ai'
|
|
149
149
|
```
|
|
150
150
|
|
|
151
151
|
### Supported Model Format
|
|
@@ -166,20 +166,20 @@ The tool requires **model names defined on [llmlite](https://docs.litellm.ai/doc
|
|
|
166
166
|
|
|
167
167
|
Each provider uses standard environment variables for authentication:
|
|
168
168
|
|
|
169
|
+
- Coding Tools
|
|
170
|
+
- **Codex CLI**: `OPENAI_API_KEY`
|
|
171
|
+
- **Claude Code**: `ANTHROPIC_API_KEY` or `CLAUDE_CODE_OAUTH_TOKEN`
|
|
172
|
+
- **Gemini CLI**: `GEMINI_API_KEY` (or `GOOGLE_GENERATIVE_AI_API_KEY`)
|
|
169
173
|
- Planning Models
|
|
170
174
|
- **OpenAI**: `OPENAI_API_KEY`
|
|
171
175
|
- **Anthropic**: `ANTHROPIC_API_KEY`
|
|
172
|
-
- **Google Gemini**: `
|
|
176
|
+
- **Google Gemini**: `GEMINI_API_KEY` (or `GOOGLE_GENERATIVE_AI_API_KEY`)
|
|
173
177
|
- **Azure OpenAI**: `AZURE_OPENAI_API_KEY`, `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_API_VERSION`
|
|
174
178
|
- **AWS Bedrock**: `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_REGION` (or `AWS_REGION_NAME`)
|
|
175
179
|
- **Google Vertex AI**: `GOOGLE_APPLICATION_CREDENTIALS` or default service account
|
|
176
180
|
- **xAI**: `XAI_API_KEY`
|
|
177
181
|
- **OpenRouter**: `OPENROUTER_API_KEY`
|
|
178
182
|
- **Ollama**: `OLLAMA_BASE_URL` (default: `http://localhost:11434`), `OLLAMA_API_KEY` (optional)
|
|
179
|
-
- Coding Tools
|
|
180
|
-
- **Codex CLI**: `OPENAI_API_KEY`
|
|
181
|
-
- **Claude Code**: `ANTHROPIC_API_KEY`
|
|
182
|
-
- **Gemini CLI**: `GEMINI_API_KEY`
|
|
183
183
|
|
|
184
184
|
## License
|
|
185
185
|
|