steward-cli 0.20.0 → 0.22.0
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 +34 -8
- package/dist/cli.js +13334 -70787
- package/package.json +1 -9
- package/dist/steward +0 -4
package/README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Steward
|
|
2
2
|
|
|
3
|
-
[](https://github.com/sapirrior/steward/releases)
|
|
4
4
|
[](https://www.npmjs.com/package/steward-cli)
|
|
5
5
|
[](LICENSE)
|
|
6
6
|
[](https://bun.sh)
|
|
@@ -74,14 +74,35 @@ Steward operates on a strictly local-first architecture:
|
|
|
74
74
|
|
|
75
75
|
## Provider Setup & Configuration
|
|
76
76
|
|
|
77
|
-
Steward supports local
|
|
77
|
+
Steward supports 11 local and cloud providers with native streaming, dynamic model discovery, and multi-turn tool calling. Configure via environment variables, `.env` file, or OAuth `/login`:
|
|
78
|
+
|
|
79
|
+
### OAuth & Device Code Login
|
|
80
|
+
|
|
81
|
+
Authenticate directly from the terminal without manual API key management:
|
|
82
|
+
|
|
83
|
+
```bash
|
|
84
|
+
# Authenticate with GitHub Copilot (Device Code flow)
|
|
85
|
+
/login github-copilot
|
|
86
|
+
|
|
87
|
+
# Authenticate with Anthropic or OpenRouter (Browser OAuth flow)
|
|
88
|
+
/login anthropic
|
|
89
|
+
/login openrouter
|
|
90
|
+
|
|
91
|
+
# View or logout from authenticated providers
|
|
92
|
+
/logout
|
|
93
|
+
```
|
|
78
94
|
|
|
79
95
|
### Local Models (Ollama, LM Studio, vLLM)
|
|
80
96
|
|
|
81
97
|
```bash
|
|
82
|
-
|
|
83
|
-
export
|
|
84
|
-
export
|
|
98
|
+
# Ollama
|
|
99
|
+
export OLLAMA_BASE_URL="http://localhost:11434"
|
|
100
|
+
export OLLAMA_MODEL="qwen2.5-coder:32b"
|
|
101
|
+
|
|
102
|
+
# Generic OpenAI-Compatible Endpoint (LM Studio, vLLM, LocalAI)
|
|
103
|
+
export CUSTOM_API_URL="http://localhost:1234/v1"
|
|
104
|
+
export CUSTOM_API_MODEL_NAME="qwen2.5-coder-32b-instruct"
|
|
105
|
+
export CUSTOM_API_KEY="optional-api-key"
|
|
85
106
|
```
|
|
86
107
|
|
|
87
108
|
### Cloud Providers
|
|
@@ -99,6 +120,9 @@ export OPENAI_API_KEY="sk-..."
|
|
|
99
120
|
# DeepSeek
|
|
100
121
|
export DEEPSEEK_API_KEY="sk-..."
|
|
101
122
|
|
|
123
|
+
# Groq
|
|
124
|
+
export GROQ_API_KEY="gsk_..."
|
|
125
|
+
|
|
102
126
|
# xAI
|
|
103
127
|
export XAI_API_KEY="xai-..."
|
|
104
128
|
|
|
@@ -115,11 +139,13 @@ export OPENROUTER_API_KEY="sk-or-v1-..."
|
|
|
115
139
|
|
|
116
140
|
| Command | Description |
|
|
117
141
|
| :--- | :--- |
|
|
118
|
-
| `/
|
|
119
|
-
| `/
|
|
142
|
+
| `/login` | Authenticate with cloud providers (`anthropic`, `openrouter`, `github-copilot`) |
|
|
143
|
+
| `/logout` | Log out from authenticated providers and clear stored credentials |
|
|
144
|
+
| `/model` | Switch active model or discover available models across providers |
|
|
120
145
|
| `/mode` | Cycle through or set active chat mode (`normal`, `chat`, `review`, `build`) |
|
|
121
146
|
| `/theme` | Change terminal color theme (`dark`, `light`, `dracula`, `dark-ansi`, `light-ansi`) |
|
|
122
|
-
| `/effort` | Adjust model reasoning effort level (`none`, `low`, `medium`, `high
|
|
147
|
+
| `/effort` | Adjust model reasoning effort level (`none`, `low`, `medium`, `high`) |
|
|
148
|
+
| `/rewind` | Revert workspace modifications and conversation state to any prior turn |
|
|
123
149
|
| `/sessions` | Browse, resume, or delete saved session transcripts |
|
|
124
150
|
| `/clear` | Clear the current conversation and start a new session |
|
|
125
151
|
| `/help` | View help manual and keyboard shortcuts |
|