ceos/opencode
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: edit local models

Browse source
This commit is contained in:
Jay V 2025-07-10 13:49:24 -04:00
commit d2c862e32d
2 changed files with 66 additions and 74 deletions
Download patch file Download diff file Expand all files Collapse all files

99
packages/web/src/content/docs/docs/config.mdx
View file

@ -43,6 +43,25 @@ Your editor should be able to validate and autocomplete based on the schema.
---
### Modes
opencode comes with two built-in modes: _build_, the default with all tools enabled. And _plan_, restricted mode with file modification tools disabled. You can override these built-in modes or define your own custom modes with the `mode` option.
```json title="opencode.json"
{
"$schema": "https://opencode.ai/config.json",
"mode": {
"build": { },
"plan": { },
"my-custom-mode": { }
}
}
```
[Learn more here](/docs/modes).
---
### Models
You can configure the providers and models you want to use in your opencode config through the `provider` and `model` options.
@ -55,43 +74,7 @@ You can configure the providers and models you want to use in your opencode conf
}
```
[Learn more here](/docs/models).
#### Custom Providers
You can also define custom providers in your configuration. This is useful for connecting to services that are not natively supported but are OpenAI API-compatible, such as local models served through LM Studio or Ollama.
Here's an example of how to configure a local on-device model from LM Studio:
```json title="opencode.json"
{
"$schema": "https://opencode.ai/config.json",
"model": "lmstudio/google/gemma-3n-e4b",
"provider": {
"lmstudio": {
"npm": "@ai-sdk/openai-compatible",
"name": "LM Studio (local)",
"options": {
"baseURL": "http://127.0.0.1:1234/v1"
},
"models": {
"google/gemma-3n-e4b": {
"name": "Gemma 3n-e4b (local)"
}
}
}
}
}
```
In this example:
- `lmstudio` is the custom provider ID.
- `npm` specifies the package to use for this provider. `@ai-sdk/openai-compatible` is used for any OpenAI-compatible API.
- `name` is the display name for the provider in the UI.
- `options.baseURL` is the endpoint for the local server.
- `models` is a map of model IDs to their configurations. The model name will be displayed in the model selection list.
- The `model` key at the root is set to the full ID of the model you want to use, which is `provider_id/model_id`.
You can also configure [local models](/docs/models#local). [Learn more](/docs/models).
---
@ -170,48 +153,6 @@ You can configure MCP servers you want to use through the `mcp` option.
---
### Modes
You can configure different modes for opencode through the `mode` option. Modes allow you to customize the behavior, tools, and prompts for different use cases.
opencode comes with two built-in modes: `build` (default with all tools enabled) and `plan` (restricted mode with file modification tools disabled). You can override these built-in modes or create your own custom modes.
```json title="opencode.json"
{
"$schema": "https://opencode.ai/config.json",
"mode": {
"build": {
"model": "anthropic/claude-sonnet-4-20250514",
"prompt": "{file:./prompts/build.txt}",
"tools": {
"write": true,
"edit": true,
"bash": true
}
},
"plan": {
"tools": {
"write": false,
"edit": false,
"bash": false
}
},
"review": {
"prompt": "{file:./prompts/code-review.txt}",
"tools": {
"write": false,
"edit": false,
"bash": false
}
}
}
}
```
[Learn more here](/docs/modes).
---
### Disabled providers
You can disable providers that are loaded automatically through the `disabled_providers` option. This is useful when you want to prevent certain providers from being loaded even if their credentials are available.