@kyubiware/commit-mint 0.7.6 → 0.8.1
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 +25 -25
- package/dist/cli.mjs +556 -342
- package/dist/cli.mjs.map +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -36,17 +36,21 @@ cmint update # update cmint to the latest published version
|
|
|
36
36
|
|
|
37
37
|
See [all flags](#all-flags) for the full list.
|
|
38
38
|
|
|
39
|
-
##
|
|
39
|
+
## Providers
|
|
40
40
|
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
41
|
+
| Provider | Env var | Default model |
|
|
42
|
+
| -------- | ----------------- | -------------------- |
|
|
43
|
+
| Groq | `GROQ_API_KEY` | `openai/gpt-oss-20b` |
|
|
44
|
+
| Cerebras | `CEREBRAS_API_KEY` | `gpt-oss-120b` |
|
|
45
|
+
| Mistral | `MISTRAL_API_KEY` | `mistral-small` |
|
|
44
46
|
|
|
45
|
-
-
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
|
|
47
|
+
All three use OpenAI-compatible APIs and have a generous free tier. Groq uses the official SDK; Cerebras and
|
|
48
|
+
Mistral use a built-in fetch client. Per-provider model overrides: set
|
|
49
|
+
`model_groq`, `model_cerebras`, or `model_mistral` in `~/.commit-mint`.
|
|
50
|
+
Resolution order is `model_<provider>` → `model` → provider default.
|
|
51
|
+
|
|
52
|
+
`cmint config` walks you through provider, API key, model, locale, and
|
|
53
|
+
timeout.
|
|
50
54
|
|
|
51
55
|
## Pre-flight checks (`.cmintrc`)
|
|
52
56
|
|
|
@@ -112,6 +116,18 @@ What do you want to stage?
|
|
|
112
116
|
Run checks
|
|
113
117
|
```
|
|
114
118
|
|
|
119
|
+
## Self-update (`cmint update`)
|
|
120
|
+
|
|
121
|
+
`cmint update` checks the npm registry for a newer version and, if one exists,
|
|
122
|
+
runs the appropriate global install command for your package manager (detected
|
|
123
|
+
from `npm_config_user_agent` — npm, pnpm, yarn, or bun; falls back to npm).
|
|
124
|
+
|
|
125
|
+
- If you're already on the latest version, it exits silently.
|
|
126
|
+
- Otherwise it prints `current → latest` and asks for confirmation before
|
|
127
|
+
running the install (live npm output is streamed to your terminal).
|
|
128
|
+
- `cmint update -y` (or `--yes`) skips the confirmation prompt — useful in
|
|
129
|
+
scripts.
|
|
130
|
+
|
|
115
131
|
## AI Agent Mode
|
|
116
132
|
|
|
117
133
|
`cmint --agent` runs non-interactively with JSON output for AI coding agents.
|
|
@@ -194,22 +210,6 @@ they happen.
|
|
|
194
210
|
Errors are parsed from **lint-staged**, **biome**, **tsc**, **vitest**/**jest**,
|
|
195
211
|
and **eslint**. Unrecognized output falls back to a single raw-stderr entry.
|
|
196
212
|
|
|
197
|
-
## Providers
|
|
198
|
-
|
|
199
|
-
| Provider | Env var | Default model |
|
|
200
|
-
| -------- | ----------------- | -------------------- |
|
|
201
|
-
| Groq | `GROQ_API_KEY` | `openai/gpt-oss-20b` |
|
|
202
|
-
| Cerebras | `CEREBRAS_API_KEY` | `gpt-oss-120b` |
|
|
203
|
-
| Mistral | `MISTRAL_API_KEY` | `mistral-small` |
|
|
204
|
-
|
|
205
|
-
All three use OpenAI-compatible APIs. Groq uses the official SDK; Cerebras and
|
|
206
|
-
Mistral use a built-in fetch client. Per-provider model overrides: set
|
|
207
|
-
`model_groq`, `model_cerebras`, or `model_mistral` in `~/.commit-mint`.
|
|
208
|
-
Resolution order is `model_<provider>` → `model` → provider default.
|
|
209
|
-
|
|
210
|
-
`cmint config` walks you through provider, API key, model, locale, and
|
|
211
|
-
timeout.
|
|
212
|
-
|
|
213
213
|
## Configuration
|
|
214
214
|
|
|
215
215
|
`~/.commit-mint` (INI format). Run `cmint config` to edit.
|