@cdoing/cli 0.1.0 → 0.1.1
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 +103 -0
- package/package.json +1 -1
package/README.md
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
1
|
+
# @cdoing/cli
|
|
2
|
+
|
|
3
|
+
Terminal-based AI coding assistant from [Cdoing Agent](https://github.com/awaisshah228/cdoing-agent) — an open-source, multi-provider alternative to Claude Code.
|
|
4
|
+
|
|
5
|
+
## Installation
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
npm install -g @cdoing/cli
|
|
9
|
+
# or
|
|
10
|
+
yarn global add @cdoing/cli
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
## Quick Start
|
|
14
|
+
|
|
15
|
+
```bash
|
|
16
|
+
# Run the CLI — launches setup wizard on first run
|
|
17
|
+
cdoing
|
|
18
|
+
|
|
19
|
+
# Or with a direct prompt
|
|
20
|
+
cdoing "explain this codebase"
|
|
21
|
+
|
|
22
|
+
# With specific provider and model
|
|
23
|
+
cdoing --provider openai --model gpt-4o
|
|
24
|
+
```
|
|
25
|
+
|
|
26
|
+
On first run with no API key configured, an interactive setup wizard guides you through provider, model, and authentication setup. Run `/setup` at any time to reconfigure.
|
|
27
|
+
|
|
28
|
+
## Features
|
|
29
|
+
|
|
30
|
+
- **Multi-provider** — Anthropic, OpenAI, Google, Ollama, custom OpenAI-compatible
|
|
31
|
+
- **20 built-in tools** — file read/write/edit, shell exec, search, web fetch, sub-agents, and more
|
|
32
|
+
- **Real-time streaming** — token-by-token output with tool call progress
|
|
33
|
+
- **Context providers** — `@terminal`, `@tree`, `@url`, `@codebase`, `@git`, `@diff`, `@clipboard`, `@file`
|
|
34
|
+
- **Permission system** — 5 modes from full prompting to auto-approve, with deny/allow/ask rules
|
|
35
|
+
- **Sandbox** — filesystem and network restrictions for safe execution
|
|
36
|
+
- **Slash commands** — `/setup`, `/compact`, `/clear`, `/plan`, `/help`, and more
|
|
37
|
+
- **Conversation history** — persistent across sessions
|
|
38
|
+
- **Plan mode** — read-only exploration without modifications
|
|
39
|
+
- **Effort control** — adjust response depth
|
|
40
|
+
|
|
41
|
+
## Authentication
|
|
42
|
+
|
|
43
|
+
### Interactive Setup
|
|
44
|
+
|
|
45
|
+
```bash
|
|
46
|
+
cdoing # First run triggers setup wizard
|
|
47
|
+
# or
|
|
48
|
+
/setup # Run inside the CLI at any time
|
|
49
|
+
```
|
|
50
|
+
|
|
51
|
+
### API Key
|
|
52
|
+
|
|
53
|
+
```bash
|
|
54
|
+
# Environment variable
|
|
55
|
+
export ANTHROPIC_API_KEY=sk-ant-...
|
|
56
|
+
export OPENAI_API_KEY=sk-...
|
|
57
|
+
export GOOGLE_API_KEY=...
|
|
58
|
+
|
|
59
|
+
# Or save permanently
|
|
60
|
+
cdoing config set api-key sk-ant-...
|
|
61
|
+
```
|
|
62
|
+
|
|
63
|
+
### OAuth (Claude Pro/Max)
|
|
64
|
+
|
|
65
|
+
```bash
|
|
66
|
+
cdoing --login # Opens browser for OAuth flow
|
|
67
|
+
cdoing --logout # Clear stored tokens
|
|
68
|
+
```
|
|
69
|
+
|
|
70
|
+
## CLI Flags
|
|
71
|
+
|
|
72
|
+
| Flag | Description |
|
|
73
|
+
|------|-------------|
|
|
74
|
+
| `--provider <name>` | LLM provider (anthropic, openai, google, ollama, custom) |
|
|
75
|
+
| `--model <name>` | Model to use |
|
|
76
|
+
| `--api-key <key>` | API key (overrides stored/env) |
|
|
77
|
+
| `--permission-mode <mode>` | Permission mode (default, acceptEdits, plan, dontAsk, bypassPermissions) |
|
|
78
|
+
| `--login` | Start OAuth login flow |
|
|
79
|
+
| `--logout` | Clear OAuth tokens |
|
|
80
|
+
| `--verbose` | Show debug output |
|
|
81
|
+
|
|
82
|
+
## Supported Providers
|
|
83
|
+
|
|
84
|
+
| Provider | Models | Auth |
|
|
85
|
+
|----------|--------|------|
|
|
86
|
+
| Anthropic (default) | Claude Sonnet 4.6, Opus 4.6, Haiku 4.5 | API key or OAuth |
|
|
87
|
+
| OpenAI | GPT-4o, GPT-4o mini, o3-mini | API key |
|
|
88
|
+
| Google | Gemini 2.0 Flash, 1.5 Pro, 1.5 Flash | API key |
|
|
89
|
+
| Ollama | LLaMA, Mistral, CodeLlama | Not required |
|
|
90
|
+
| Custom | Any OpenAI-compatible API | Configurable |
|
|
91
|
+
|
|
92
|
+
## Architecture
|
|
93
|
+
|
|
94
|
+
Built with:
|
|
95
|
+
|
|
96
|
+
- **Ink + React** — terminal UI with real-time rendering
|
|
97
|
+
- **Commander.js** — CLI argument parsing
|
|
98
|
+
- **@cdoing/core** — tools, permissions, sandbox, hooks, context providers
|
|
99
|
+
- **@cdoing/ai** — agent runner, LLM providers, context/token management
|
|
100
|
+
|
|
101
|
+
## License
|
|
102
|
+
|
|
103
|
+
MIT
|