Skip to content

Commit 221987d

Browse files
danbarrdanbarr
authoredFeb 10, 2025··
Docs for v0.1.17 (#75)
* Add muxing docs * Add OpenRouter endpoint docs * Add Kodu docs
1 parent 1a93f17 commit 221987d

31 files changed

+805
-221
lines changed
 

‎docs/about/changelog.md

+17-2
Original file line numberDiff line numberDiff line change
@@ -13,12 +13,27 @@ Major features and changes are noted here. To review all updates, see the
1313

1414
Related: [Upgrade CodeGate](../how-to/install.md#upgrade-codegate)
1515

16-
- **New integration: Open Interpreter** - xx Feb\
17-
2025 CodeGate v0.1.16 introduces support for
16+
- **Model muxing** - 7 Feb, 2025\
17+
With CodeGate v0.1.17 you can use the new `/v1/mux` endpoint to configure
18+
model selection based on your workspace! Learn more in the
19+
[model muxing guide](../features/muxing.md).
20+
21+
- **OpenRouter endpoint** - 7 Feb, 2025\
22+
CodeGate v0.1.17 adds a dedicated `/openrouter` provider endpoint for
23+
OpenRouter users. This endpoint currently works with Continue, Cline, and Kodu
24+
(Claude Coder).
25+
26+
- **New integration: Open Interpreter** - 4 Feb, 2025\
27+
CodeGate v0.1.16 added support for
1828
[Open Interpreter](https://github.com/openinterpreter/open-interpreter) with
1929
OpenAI-compatible APIs. Review the
2030
[integration guide](../integrations/open-interpreter.mdx) to get started.
2131

32+
- **New integration: Claude Coder** - 28 Jan, 2025\
33+
CodeGate v0.1.14 also introduced support for Kodu's
34+
[Claude Coder](https://www.kodu.ai/extension) extension. See the
35+
[integration guide](../integrations/kodu.mdx) to learn more.
36+
2237
- **New integration: Cline** - 28 Jan, 2025\
2338
CodeGate version 0.1.14 adds support for [Cline](https://cline.bot/) with
2439
Anthropic, OpenAI, Ollama, and LM Studio. See the

‎docs/features/muxing.md

+129
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,129 @@
1+
---
2+
title: Model muxing
3+
description: Configure a per-workspace LLM
4+
sidebar_position: 35
5+
---
6+
7+
## Overview
8+
9+
_Model muxing_ (or multiplexing), allows you to configure your AI assistant once
10+
and use [CodeGate workspaces](./workspaces.mdx) to switch between LLM providers
11+
and models without reconfiguring your development environment. This feature is
12+
especially useful when you're working on multiple projects or tasks that require
13+
different AI models.
14+
15+
For each CodeGate workspace, you can select the AI provider and model
16+
combination you want to use. Then, configure your AI coding tool to use the
17+
CodeGate muxing endpoint `http://localhost:8989/v1/mux` as an OpenAI-compatible
18+
API provider.
19+
20+
To change the model currently in use, simply switch your active CodeGate
21+
workspace.
22+
23+
```mermaid
24+
flowchart LR
25+
Client(AI Assistant/Agent)
26+
CodeGate{CodeGate}
27+
WS1[Workspace-A]
28+
WS2[Workspace-B]
29+
WS3[Workspace-C]
30+
LLM1(OpenAI/<br>o3-mini)
31+
LLM2(Ollama/<br>deepseek-r1)
32+
LLM3(OpenRouter/<br>claude-35-sonnet)
33+
34+
Client ---|/v1/mux| CodeGate
35+
CodeGate --> WS1
36+
CodeGate --> WS2
37+
CodeGate --> WS3
38+
WS1 --> |api| LLM1
39+
WS2 --> |api| LLM2
40+
WS3 --> |api| LLM3
41+
```
42+
43+
## Use cases
44+
45+
- You have a project that requires a specific model for a particular task, but
46+
you also need to switch between different models during the course of your
47+
work.
48+
- You want to experiment with different LLM providers and models without having
49+
to reconfigure your AI assistant/agent every time you switch.
50+
- Your AI coding assistant doesn't support a particular provider or model that
51+
you want to use. CodeGate's muxing provides an OpenAI-compatible abstraction
52+
layer.
53+
- You're working on a sensitive project and want to use a local model, but still
54+
have the flexibility to switch to hosted models for other work.
55+
- You want to control your LLM provider spend by using lower-cost models for
56+
some tasks that don't require the power of more advanced (and expensive)
57+
reasoning models.
58+
59+
## Configure muxing
60+
61+
To use muxing with your AI coding assistant, you need to add one or more AI
62+
providers to CodeGate, then select the model you want to use on a workspace.
63+
64+
CodeGate supports the following LLM providers for muxing:
65+
66+
- Anthropic
67+
- llama.cpp
68+
- LM Studio
69+
- Ollama
70+
- OpenAI (and compatible APIs)
71+
- OpenRouter
72+
- vLLM
73+
74+
### Add a provider
75+
76+
1. In the [CodeGate dashboard](http://localhost:9090), open the **Providers**
77+
page from the **Settings** menu.
78+
1. Click **Add Provider**.
79+
1. Enter a display name for the provider, then select the type from the
80+
drop-down list. The default endpoint and authentication type are filled in
81+
automatically.
82+
1. If you are using a non-default endpoint, update the **Endpoint** value.
83+
1. Optionally, add a **Description** for the provider.
84+
1. If the provider requires authentication, select the **API Key**
85+
authentication option and enter your key.
86+
87+
When you save the settings, CodeGate connects to the provider to retrieve the
88+
available models.
89+
90+
:::note
91+
92+
For locally-hosted models, you must use `http://host.docker.internal` instead of
93+
`http://localhost`
94+
95+
:::
96+
97+
### Select the model for a workspace
98+
99+
Open the settings of one of your [workspaces](./workspaces.mdx) from the
100+
Workspace selection menu or the
101+
[Manage Workspaces](http://localhost:9090/workspaces) screen.
102+
103+
In the **Preferred Model** section, select the model to use with the workspace.
104+
105+
### Manage existing providers
106+
107+
To edit a provider's settings, click the Manage button next to the provider in
108+
the list. For providers that require authentication, you can leave the API key
109+
field blank to preserve the current value.
110+
111+
To delete a provider, click the trash icon next to it. If this provider was in
112+
use by any workspaces, you will need to update their settings to choose a
113+
different provider/model.
114+
115+
### Refresh available models
116+
117+
To refresh the list of models available from a provider, in the Providers list,
118+
click the Manage button next to the provider to refresh, then save it without
119+
making any changes.
120+
121+
## Configure your client
122+
123+
Configure the OpenAI-compatible API base URL of your AI coding assistant/agent
124+
to `http://localhost:8989/v1/mux`. If your client requires a model name and/or
125+
API key, you can enter any values since CodeGate manages the model selection and
126+
authentication.
127+
128+
For specific instructions, see the
129+
[integration guide](../integrations/index.mdx) for your client.

‎docs/features/workspaces.mdx

+9-4
Original file line numberDiff line numberDiff line change
@@ -25,9 +25,13 @@ Workspaces offer several key features:
2525

2626
- **Custom instructions**: Customize your interactions with LLMs by augmenting
2727
your AI assistant's system prompt, enabling tailored responses and behaviors
28-
for different types of tasks. CodeGate includes a library of community prompts
29-
that can be easily customized for specific tasks. You can also create your
30-
own.
28+
for different types of tasks. Choose from CodeGate's library of community
29+
prompts or create your own.
30+
31+
- [**Model muxing**](./muxing.md): Configure the LLM provider/model for each
32+
workspace, allowing you to configure your AI assistant/agent once and switch
33+
between different models on the fly. This is useful when working on multiple
34+
projects or tasks that require different AI models.
3135

3236
- **Prompt and alert history**: Your LLM interactions (prompt history) and
3337
CodeGate security detections (alert history) are recorded in the active
@@ -112,7 +116,8 @@ In the workspace list, open the menu (**...**) next to a workspace to
112116
**Activate**, **Edit**, or **Archive** the workspace.
113117

114118
**Edit** opens the workspace settings page. From here you can rename the
115-
workspace, set the custom prompt instructions, or archive the workspace.
119+
workspace, select the LLM provider and model (see [Model muxing](./muxing.md)),
120+
set the custom prompt instructions, or archive the workspace.
116121

117122
**Archived** workspaces can be restored or permanently deleted from the
118123
workspace list or workspace settings screen.

‎docs/how-to/configure.md

+9-17
Original file line numberDiff line numberDiff line change
@@ -1,14 +1,15 @@
11
---
2-
title: Configure CodeGate
2+
title: Advanced configuration
33
description: Customizing CodeGate's application settings
4-
sidebar_position: 20
4+
sidebar_position: 30
55
---
66

77
## Customize CodeGate's behavior
88

9-
The CodeGate container runs with default settings to support Ollama, Anthropic,
10-
and OpenAI APIs with typical settings. To customize the behavior, you can add
11-
extra configuration parameters to the container as environment variables:
9+
The CodeGate container runs with defaults that work with supported LLM providers
10+
using typical settings. To customize CodeGate's application settings like
11+
provider endpoints and logging level, you can add extra configuration parameters
12+
to the container as environment variables:
1213

1314
```bash {2}
1415
docker run --name codegate -d -p 8989:8989 -p 9090:9090 \
@@ -31,22 +32,13 @@ CodeGate supports the following parameters:
3132
| `CODEGATE_OPENAI_URL` | `https://api.openai.com/v1` | Specifies the OpenAI engine API endpoint URL. |
3233
| `CODEGATE_VLLM_URL` | `http://localhost:8000` | Specifies the URL of the vLLM server to use. |
3334

34-
## Example: Use CodeGate with OpenRouter
35+
## Example: Use CodeGate with a remote Ollama server
3536

36-
[OpenRouter](https://openrouter.ai/) is an interface to many large language
37-
models. CodeGate's vLLM provider works with OpenRouter's API when used with the
38-
Continue IDE plugin.
39-
40-
To use OpenRouter, set the vLLM URL when you launch CodeGate:
37+
Set the Ollama server's URL when you launch CodeGate:
4138

4239
```bash {2}
4340
docker run --name codegate -d -p 8989:8989 -p 9090:9090 \
44-
-e CODEGATE_VLLM_URL=https://openrouter.ai/api \
41+
-e CODEGATE_OLLAMA_URL=https://my.ollama-server.example \
4542
--mount type=volume,src=codegate_volume,dst=/app/codegate_volume \
4643
--restart unless-stopped ghcr.io/stacklok/codegate
4744
```
48-
49-
Then,
50-
[configure the Continue IDE plugin](../integrations/continue.mdx?provider=vllm)
51-
to use CodeGate's vLLM endpoint (`http://localhost:8989/vllm`) along with the
52-
model you'd like to use and your OpenRouter API key.

‎docs/how-to/dashboard.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
title: Access the dashboard
33
description: View alerts and usage history
4-
sidebar_position: 30
4+
sidebar_position: 20
55
---
66

77
## Enable dashboard access

‎docs/index.md

+20-3
Original file line numberDiff line numberDiff line change
@@ -31,6 +31,20 @@ sequenceDiagram
3131
deactivate CodeGate
3232
```
3333

34+
## Key features
35+
36+
CodeGate includes several key features for privacy, security, and coding
37+
efficiency, including:
38+
39+
- [Secrets encryption](./features/secrets-encryption.md) to protect your
40+
sensitive credentials
41+
- [Dependency risk awareness](./features/dependency-risk.md) to update the LLM's
42+
knowledge of malicious or deprecated open source packages
43+
- [Model muxing](./features/muxing.md) to quickly select the best LLM
44+
provider/model for your current task
45+
- [Workspaces](./features/workspaces.mdx) to organize and customize your LLM
46+
interactions
47+
3448
## Supported environments
3549

3650
CodeGate supports several development environments and AI providers.
@@ -41,20 +55,23 @@ AI coding assistants / IDEs:
4155

4256
- **[Cline](./integrations/cline.mdx)** in Visual Studio Code
4357

44-
CodeGate supports Ollama, Anthropic, OpenAI-compatible APIs, and LM Studio
45-
with Cline
58+
CodeGate supports Ollama, Anthropic, OpenAI and compatible APIs, OpenRouter,
59+
and LM Studio with Cline
4660

4761
- **[Continue](./integrations/continue.mdx)** with Visual Studio Code and
4862
JetBrains IDEs
4963

5064
CodeGate supports the following AI model providers with Continue:
5165

5266
- Local / self-managed: Ollama, llama.cpp, vLLM
53-
- Hosted: Anthropic, OpenAI and OpenAI-compatible APIs like OpenRouter
67+
- Hosted: Anthropic, OpenAI and compatible APIs, and OpenRouter
5468

5569
- **[GitHub Copilot](./integrations/copilot.mdx)** with Visual Studio Code
5670
(JetBrains coming soon!)
5771

72+
- **[Kodu / Claude Coder](./integrations/kodu.mdx)** in Visual Studio Code with
73+
OpenAI-compatible APIs
74+
5875
- **[Open Interpreter](./integrations/open-interpreter.mdx)** with
5976
OpenAI-compatible APIs
6077

‎docs/integrations/aider.mdx

+3
Original file line numberDiff line numberDiff line change
@@ -17,6 +17,9 @@ CodeGate works with the following AI model providers through aider:
1717
- Hosted:
1818
- [OpenAI](https://openai.com/api/) and OpenAI-compatible APIs
1919

20+
You can also configure [CodeGate muxing](../features/muxing.md) to select your
21+
provider and model using [workspaces](../features/workspaces.mdx).
22+
2023
:::note
2124

2225
This guide assumes you have already installed aider using their

‎docs/integrations/cline.mdx

+37-4
Original file line numberDiff line numberDiff line change
@@ -18,7 +18,11 @@ CodeGate works with the following AI model providers through Cline:
1818
- [LM Studio](https://lmstudio.ai/)
1919
- Hosted:
2020
- [Anthropic](https://www.anthropic.com/api)
21-
- [OpenAI](https://openai.com/api/) and OpenAI-compatible APIs
21+
- [OpenAI](https://openai.com/api/) and compatible APIs
22+
- [OpenRouter](https://openrouter.ai/)
23+
24+
You can also configure [CodeGate muxing](../features/muxing.md) to select your
25+
provider and model using [workspaces](../features/workspaces.mdx).
2226

2327
## Install the Cline extension
2428

@@ -42,10 +46,36 @@ in the VS Code documentation.
4246

4347
import ClineProviders from '../partials/_cline-providers.mdx';
4448

49+
:::note
50+
51+
Cline has two modes: Plan and Act. Each mode can be uniquely configured with a
52+
different provider and model, so you need to configure both.
53+
54+
:::
55+
4556
To configure Cline to send requests through CodeGate:
4657

47-
1. Open the Cline extension sidebar from the VS Code Activity Bar and open its
48-
settings using the gear icon.
58+
1. Open the Cline extension sidebar from the VS Code Activity Bar. Note your
59+
current mode, Plan or Act.
60+
61+
<ThemedImage
62+
alt='Cline mode - plan'
63+
sources={{
64+
light: useBaseUrl('/img/integrations/cline-mode-plan-light.webp'),
65+
dark: useBaseUrl('/img/integrations/cline-mode-plan-dark.webp'),
66+
}}
67+
width={'400px'}
68+
/>
69+
<ThemedImage
70+
alt='Cline mode - act'
71+
sources={{
72+
light: useBaseUrl('/img/integrations/cline-mode-act-light.webp'),
73+
dark: useBaseUrl('/img/integrations/cline-mode-act-dark.webp'),
74+
}}
75+
width={'400px'}
76+
/>
77+
78+
1. Open the Cline settings using the gear icon.
4979

5080
<ThemedImage
5181
alt='Cline extension settings'
@@ -60,7 +90,10 @@ To configure Cline to send requests through CodeGate:
6090

6191
<ClineProviders />
6292

63-
1. Click **Done** to save the settings.
93+
1. Click **Done** to save the settings for your current mode.
94+
95+
1. Switch your Cline mode from Act to Plan or vice-versa, open the settings, and
96+
repeat the configuration for your desired provider & model.
6497

6598
## Verify configuration
6699

‎docs/integrations/continue.mdx

+132-86
Original file line numberDiff line numberDiff line change
@@ -18,12 +18,15 @@ CodeGate works with the following AI model providers through Continue:
1818

1919
- Local / self-managed:
2020
- [Ollama](https://ollama.com/)
21-
- [llama.cpp](https://github.com/ggerganov/llama.cpp)
2221
- [vLLM](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html)
22+
- [llama.cpp](https://github.com/ggerganov/llama.cpp) (advanced)
2323
- Hosted:
24-
- [OpenRouter](https://openrouter.ai/)
2524
- [Anthropic](https://www.anthropic.com/api)
2625
- [OpenAI](https://openai.com/api/)
26+
- [OpenRouter](https://openrouter.ai/)
27+
28+
You can also configure [CodeGate muxing](../features/muxing.md) to select your
29+
provider and model using [workspaces](../features/workspaces.mdx).
2730

2831
## Install the Continue plugin
2932

@@ -92,8 +95,9 @@ To configure Continue to send requests through CodeGate:
9295
"apiBase": "http://127.0.0.1:8989/<provider>"
9396
```
9497

95-
Replace `/<provider>` with one of: `/anthropic`, `/ollama`, `/openai`, or
96-
`/vllm` to match your LLM provider.
98+
Replace `/<provider>` with one of: `/v1/mux` (for CodeGate muxing),
99+
`/anthropic`, `/ollama`, `/openai`, `/openrouter`, or `/vllm` to match your
100+
LLM provider.
97101

98102
If you used a different API port when launching the CodeGate container,
99103
replace `8989` with your custom port number.
@@ -111,49 +115,37 @@ provider. Replace the values in ALL_CAPS. The configuration syntax is the same
111115
for VS Code and JetBrains IDEs.
112116

113117
<Tabs groupId="provider" queryString="provider">
114-
<TabItem value="ollama" label="Ollama" default>
115-
116-
You need Ollama installed on your local system with the server running
117-
(`ollama serve`) to use this provider.
118-
119-
CodeGate connects to `http://host.docker.internal:11434` by default. If you
120-
changed the default Ollama server port or to connect to a remote Ollama
121-
instance, launch CodeGate with the `CODEGATE_OLLAMA_URL` environment variable
122-
set to the correct URL. See [Configure CodeGate](../how-to/configure.md).
118+
<TabItem value="mux" label="CodeGate muxing" default>
123119

124-
Replace `MODEL_NAME` with the names of model(s) you have installed locally using
125-
`ollama pull`. See Continue's
126-
[Ollama provider documentation](https://docs.continue.dev/customize/model-providers/ollama).
120+
First, configure your [provider(s)](../features/muxing.md#add-a-provider) and
121+
select a model for each of your
122+
[workspace(s)](../features/workspaces.mdx#manage-workspaces) in the CodeGate
123+
dashboard.
127124

128-
We recommend the [Qwen2.5-Coder](https://ollama.com/library/qwen2.5-coder)
129-
series of models. Our minimum recommendation is:
130-
131-
- `qwen2.5-coder:7b` for chat
132-
- `qwen2.5-coder:1.5b` for autocomplete
133-
134-
These models balance performance and quality for typical systems with at least 4
135-
CPU cores and 16GB of RAM. If you have more compute resources available, our
136-
experimentation shows that larger models do yield better results.
125+
Configure Continue as shown. Note, the `model` and `apiKey` settings are
126+
required by Continue, but their value is not used.
137127

138128
```json title="~/.continue/config.json"
139129
{
140130
"models": [
141131
{
142-
"title": "CodeGate-Ollama",
143-
"provider": "ollama",
144-
"model": "MODEL_NAME",
145-
"apiBase": "http://localhost:8989/ollama"
132+
"title": "CodeGate-Mux",
133+
"provider": "openai",
134+
"model": "fake-value-not-used",
135+
"apiKey": "fake-value-not-used",
136+
"apiBase": "http://localhost:8989/v1/mux"
146137
}
147138
],
148139
"modelRoles": {
149-
"default": "CodeGate-Ollama",
150-
"summarize": "CodeGate-Ollama"
140+
"default": "CodeGate-Mux",
141+
"summarize": "CodeGate-Mux"
151142
},
152143
"tabAutocompleteModel": {
153-
"title": "CodeGate-Ollama-Autocomplete",
154-
"provider": "ollama",
155-
"model": "MODEL_NAME",
156-
"apiBase": "http://localhost:8989/ollama"
144+
"title": "CodeGate-Mux-Autocomplete",
145+
"provider": "openai",
146+
"model": "fake-value-not-used",
147+
"apiKey": "fake-value-not-used",
148+
"apiBase": "http://localhost:8989/v1/mux"
157149
}
158150
}
159151
```
@@ -195,6 +187,54 @@ Replace `YOUR_API_KEY` with your
195187
}
196188
```
197189

190+
</TabItem>
191+
<TabItem value="ollama" label="Ollama">
192+
193+
You need Ollama installed on your local system with the server running
194+
(`ollama serve`) to use this provider.
195+
196+
CodeGate connects to `http://host.docker.internal:11434` by default. If you
197+
changed the default Ollama server port or to connect to a remote Ollama
198+
instance, launch CodeGate with the `CODEGATE_OLLAMA_URL` environment variable
199+
set to the correct URL. See [Configure CodeGate](../how-to/configure.md).
200+
201+
Replace `MODEL_NAME` with the names of model(s) you have installed locally using
202+
`ollama pull`. See Continue's
203+
[Ollama provider documentation](https://docs.continue.dev/customize/model-providers/ollama).
204+
205+
We recommend the [Qwen2.5-Coder](https://ollama.com/library/qwen2.5-coder)
206+
series of models. Our minimum recommendation is:
207+
208+
- `qwen2.5-coder:7b` for chat
209+
- `qwen2.5-coder:1.5b` for autocomplete
210+
211+
These models balance performance and quality for typical systems with at least 4
212+
CPU cores and 16GB of RAM. If you have more compute resources available, our
213+
experimentation shows that larger models do yield better results.
214+
215+
```json title="~/.continue/config.json"
216+
{
217+
"models": [
218+
{
219+
"title": "CodeGate-Ollama",
220+
"provider": "ollama",
221+
"model": "MODEL_NAME",
222+
"apiBase": "http://localhost:8989/ollama"
223+
}
224+
],
225+
"modelRoles": {
226+
"default": "CodeGate-Ollama",
227+
"summarize": "CodeGate-Ollama"
228+
},
229+
"tabAutocompleteModel": {
230+
"title": "CodeGate-Ollama-Autocomplete",
231+
"provider": "ollama",
232+
"model": "MODEL_NAME",
233+
"apiBase": "http://localhost:8989/ollama"
234+
}
235+
}
236+
```
237+
198238
</TabItem>
199239
<TabItem value="openai" label="OpenAI">
200240

@@ -234,13 +274,26 @@ Replace `YOUR_API_KEY` with your
234274
</TabItem>
235275
<TabItem value="openrouter" label="OpenRouter">
236276

237-
CodeGate's vLLM provider supports OpenRouter, a unified interface for hundreds
238-
of commercial and open source models. You need an
239-
[OpenRouter](https://openrouter.ai/) account to use this provider.
277+
OpenRouter is a unified interface for hundreds of commercial and open source
278+
models. You need an [OpenRouter](https://openrouter.ai/) account to use this
279+
provider.
280+
281+
:::info Known issues
282+
283+
**Auto-completion support**: currently, CodeGate's `/openrouter` endpoint does
284+
not work with Continue's `tabAutocompleteModel` setting for fill-in-the-middle
285+
(FIM). We are
286+
[working to resolve this issue](https://github.com/stacklok/codegate/issues/980).
287+
288+
**DeepSeek models**: there is a bug in the current release version of Continue
289+
affecting DeepSeek models (ex: `deepseek/deepseek-r1`), you need to run the
290+
pre-release version of the Continue extension.
291+
292+
:::
240293

241294
Replace `MODEL_NAME` with one of the
242295
[available models](https://openrouter.ai/models), for example
243-
`qwen/qwen-2.5-coder-32b-instruct`.
296+
`anthropic/claude-3.5-sonnet`.
244297

245298
Replace `YOUR_API_KEY` with your
246299
[OpenRouter API key](https://openrouter.ai/keys).
@@ -250,20 +303,56 @@ Replace `YOUR_API_KEY` with your
250303
"models": [
251304
{
252305
"title": "CodeGate-OpenRouter",
253-
"provider": "vllm",
306+
"provider": "openrouter",
254307
"model": "MODEL_NAME",
255308
"apiKey": "YOUR_API_KEY",
256-
"apiBase": "http://localhost:8989/vllm"
309+
"apiBase": "http://localhost:8989/openrouter"
257310
}
258311
],
259312
"modelRoles": {
260313
"default": "CodeGate-OpenRouter",
261314
"summarize": "CodeGate-OpenRouter"
315+
}
316+
}
317+
```
318+
319+
</TabItem>
320+
<TabItem value="vllm" label="vLLM">
321+
322+
You need a
323+
[vLLM server](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html)
324+
running locally or access to a remote server to use this provider.
325+
326+
CodeGate connects to `http://localhost:8000` by default. If you changed the
327+
default Ollama server port or to connect to a remote Ollama instance, launch
328+
CodeGate with the `CODEGATE_VLLM_URL` environment variable set to the correct
329+
URL. See [Configure CodeGate](../how-to/configure.md).
330+
331+
A vLLM server hosts a single model. Continue automatically selects the available
332+
model, so the `model` parameter is not required. See Continue's
333+
[vLLM provider guide](https://docs.continue.dev/customize/model-providers/more/vllm)
334+
for more information.
335+
336+
If your server requires an API key, replace `YOUR_API_KEY` with the key.
337+
Otherwise, remove the `apiKey` parameter from both sections.
338+
339+
```json title="~/.continue/config.json"
340+
{
341+
"models": [
342+
{
343+
"title": "CodeGate-vLLM",
344+
"provider": "vllm",
345+
"apiKey": "YOUR_API_KEY",
346+
"apiBase": "http://localhost:8989/vllm"
347+
}
348+
],
349+
"modelRoles": {
350+
"default": "CodeGate-vLLM",
351+
"summarize": "CodeGate-vLLM"
262352
},
263353
"tabAutocompleteModel": {
264-
"title": "CodeGate-OpenRouter-Autocomplete",
354+
"title": "CodeGate-vLLM-Autocomplete",
265355
"provider": "vllm",
266-
"model": "MODEL_NAME",
267356
"apiKey": "YOUR_API_KEY",
268357
"apiBase": "http://localhost:8989/vllm"
269358
}
@@ -331,49 +420,6 @@ In the Continue config file, replace `MODEL_NAME` with the file name without the
331420
}
332421
```
333422

334-
</TabItem>
335-
<TabItem value="vllm" label="vLLM">
336-
337-
You need a
338-
[vLLM server](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html)
339-
running locally or access to a remote server to use this provider.
340-
341-
CodeGate connects to `http://localhost:8000` by default. If you changed the
342-
default Ollama server port or to connect to a remote Ollama instance, launch
343-
CodeGate with the `CODEGATE_VLLM_URL` environment variable set to the correct
344-
URL. See [Configure CodeGate](../how-to/configure.md).
345-
346-
A vLLM server hosts a single model. Continue automatically selects the available
347-
model, so the `model` parameter is not required. See Continue's
348-
[vLLM provider guide](https://docs.continue.dev/customize/model-providers/more/vllm)
349-
for more information.
350-
351-
If your server requires an API key, replace `YOUR_API_KEY` with the key.
352-
Otherwise, remove the `apiKey` parameter from both sections.
353-
354-
```json title="~/.continue/config.json"
355-
{
356-
"models": [
357-
{
358-
"title": "CodeGate-vLLM",
359-
"provider": "vllm",
360-
"apiKey": "YOUR_API_KEY",
361-
"apiBase": "http://localhost:8989/vllm"
362-
}
363-
],
364-
"modelRoles": {
365-
"default": "CodeGate-vLLM",
366-
"summarize": "CodeGate-vLLM"
367-
},
368-
"tabAutocompleteModel": {
369-
"title": "CodeGate-vLLM-Autocomplete",
370-
"provider": "vllm",
371-
"apiKey": "YOUR_API_KEY",
372-
"apiBase": "http://localhost:8989/vllm"
373-
}
374-
}
375-
```
376-
377423
</TabItem>
378424
</Tabs>
379425

‎docs/integrations/copilot.mdx

+1-1
Original file line numberDiff line numberDiff line change
@@ -235,7 +235,7 @@ Copilot chat and type `codegate version`. You should receive a response like
235235
"CodeGate version 0.1.13".
236236

237237
<ThemedImage
238-
alt='Verify Continue integration'
238+
alt='Verify Copilot integration'
239239
sources={{
240240
light: useBaseUrl('/img/integrations/copilot-codegate-version-light.webp'),
241241
dark: useBaseUrl('/img/integrations/copilot-codegate-version-dark.webp'),

‎docs/integrations/kodu.mdx

+126
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,126 @@
1+
---
2+
title: Use CodeGate with Claude Coder by Kodu.ai
3+
description: Configure the Kodu / Claude Coder extension for VS Code
4+
sidebar_label: Kodu / Claude Coder
5+
sidebar_position: 60
6+
---
7+
8+
import useBaseUrl from '@docusaurus/useBaseUrl';
9+
import ThemedImage from '@theme/ThemedImage';
10+
11+
[Claude Coder](https://www.kodu.ai/extension) by Kodu.ai is an AI coding agent
12+
extension for Visual Studio Code that can help programmers of all skill levels
13+
take their project from idea to execution.
14+
15+
CodeGate supports OpenAI-compatible APIs and OpenRouter with Claude Coder.
16+
17+
You can also configure [CodeGate muxing](../features/muxing.md) to select your
18+
provider and model using [workspaces](../features/workspaces.mdx).
19+
20+
## Install the Claude Coder extension
21+
22+
The Claude Coder extension is available in the
23+
[Visual Studio Marketplace](https://marketplace.visualstudio.com/items?itemName=kodu-ai.claude-dev-experimental).
24+
25+
Install the extension using the **Install** link on the Marketplace page or
26+
search for "Claude Coder" or "Kodu" in the Extensions panel within VS Code.
27+
28+
You can also install from the CLI:
29+
30+
```bash
31+
code --install-extension kodu-ai.claude-dev-experimental
32+
```
33+
34+
If you need help, see
35+
[Managing Extensions](https://code.visualstudio.com/docs/editor/extension-marketplace)
36+
in the VS Code documentation.
37+
38+
## Configure Claude Coder to use CodeGate
39+
40+
import KoduProviders from '../partials/_kodu-providers.mdx';
41+
42+
1. Open the Claude Coder extension sidebar from the VS Code Activity Bar and
43+
open its settings using the gear icon.
44+
45+
1. On the **Preferences** tab, scroll down and click the link next to "Want to
46+
use a custom provider?"
47+
48+
<ThemedImage
49+
alt='Claude Coder extension settings'
50+
sources={{
51+
light: useBaseUrl('/img/integrations/kodu-settings-light.webp'),
52+
dark: useBaseUrl('/img/integrations/kodu-settings-dark.webp'),
53+
}}
54+
width={'480px'}
55+
/>
56+
57+
1. Select your provider and configure as detailed here:
58+
59+
<KoduProviders />
60+
61+
1. Click **Save Settings** and confirm that you want to apply the model.
62+
63+
## Verify configuration
64+
65+
To verify that you've successfully connected Claude Coder / Kodu to CodeGate,
66+
start a new task in the Claude Coder sidebar and type `codegate version`. You
67+
should receive a response like "CodeGate version: v0.1.15":
68+
69+
<ThemedImage
70+
alt='Claude Coder verification'
71+
sources={{
72+
light: useBaseUrl('/img/integrations/kodu-codegate-version-light.webp'),
73+
dark: useBaseUrl('/img/integrations/kodu-codegate-version-dark.webp'),
74+
}}
75+
width={'520px'}
76+
/>
77+
78+
Start a new task and try asking CodeGate about a known malicious Python package:
79+
80+
```plain title="Claude Coder chat"
81+
Tell me how to use the invokehttp package from PyPI
82+
```
83+
84+
CodeGate responds with a warning and a link to the Stacklok Insight report about
85+
this package:
86+
87+
```plain title="Claude Coder chat"
88+
Warning: CodeGate detected one or more malicious, deprecated or archived packages.
89+
90+
• invokehttp: https://www.insight.stacklok.com/report/pypi/invokehttp
91+
92+
The `invokehttp` package from PyPI has been identified as malicious and should
93+
not be used. Please avoid using this package and consider using a trusted
94+
alternative such as `requests` for making HTTP requests in Python.
95+
96+
Here is an example of how to use the `requests` package:
97+
98+
...
99+
```
100+
101+
## Next steps
102+
103+
Learn more about CodeGate's features and how to use them:
104+
105+
- [Access the dashboard](../how-to/dashboard.md)
106+
- [CodeGate features](../features/index.mdx)
107+
108+
## Remove CodeGate
109+
110+
If you decide to stop using CodeGate, follow these steps to remove it and revert
111+
your environment.
112+
113+
1. Remove the custom base URL from your Claude Coder provider settings.
114+
115+
1. Stop and remove the CodeGate container:
116+
117+
```bash
118+
docker stop codegate && docker rm codegate
119+
```
120+
121+
1. If you launched CodeGate with a persistent volume, delete it to remove the
122+
CodeGate database and other files:
123+
124+
```bash
125+
docker volume rm codegate_volume
126+
```

‎docs/integrations/open-interpreter.mdx

+56-20
Original file line numberDiff line numberDiff line change
@@ -11,9 +11,12 @@ import TabItem from '@theme/TabItem';
1111
[Open Interpreter](https://github.com/openinterpreter/open-interpreter) lets
1212
LLMs run code locally through a ChatGPT-like interface in your terminal.
1313

14-
CodeGate works with [OpenAI](https://openai.com/api/) and OpenAI-compatible APIs
14+
CodeGate works with [OpenAI](https://openai.com/api/) and compatible APIs
1515
through Open Interpreter.
1616

17+
You can also configure [CodeGate muxing](../features/muxing.md) to select your
18+
provider and model using [workspaces](../features/workspaces.mdx).
19+
1720
:::note
1821

1922
This guide assumes you have already installed Open Interpreter using their
@@ -26,34 +29,67 @@ This guide assumes you have already installed Open Interpreter using their
2629
To configure Open Interpreter to send requests through CodeGate, run
2730
`interpreter` with the
2831
[API base setting](https://docs.openinterpreter.com/settings/all-settings#api-base)
29-
set to CodeGate's local API port, `http://localhost:8989/openai`.
32+
set to CodeGate's local API port, `http://localhost:8989/<provider>`.
3033

31-
By default, CodeGate connects to the [OpenAI API](https://openai.com/api/). To
32-
use a different OpenAI-compatible endpoint, set the `CODEGATE_OPENAI_URL`
33-
[configuration parameter](../how-to/configure.md#config-parameters) when you run
34-
CodeGate.
34+
<Tabs groupId="provider" queryString="provider">
35+
<TabItem value="mux" label="CodeGate muxing" default>
36+
First, configure your [provider(s)](../features/muxing.md#add-a-provider) and
37+
select a model for each of your
38+
[workspace(s)](../features/workspaces.mdx#manage-workspaces) in the CodeGate dashboard.
3539

36-
<Tabs>
37-
<TabItem value="current" label="Open Interpreter v0.4.x" default>
38-
```bash
39-
interpreter --api_base http://localhost:8989/openai --api_key YOUR_API_KEY --model MODEL_NAME
40-
```
40+
When you run `interpreter`, the API key parameter is required but the value is
41+
not used. The `--model` setting must start with `openai/` but the actual model
42+
is determined by your CodeGate workspace.
4143

42-
</TabItem>
43-
<TabItem value="dev" label="v1.0 dev branch">
44-
If you are running Open Interpreter's v1.0
45-
[development branch](https://github.com/OpenInterpreter/open-interpreter/tree/development):
44+
<Tabs groupId="interpreter-version">
45+
<TabItem value="current" label="Open Interpreter v0.4.x" default>
46+
```bash
47+
interpreter --api_base http://localhost:8989/v1/mux --api_key fake-value-not-used --model openai/fake-value-not-used
48+
```
4649

47-
```bash
48-
interpreter --api-base http://localhost:8989/openai --api-key YOUR_API_KEY --model MODEL_NAME
49-
```
50+
</TabItem>
51+
<TabItem value="dev" label="v1.0 dev branch">
52+
If you are running Open Interpreter's v1.0
53+
[development branch](https://github.com/OpenInterpreter/open-interpreter/tree/development):
5054

51-
</TabItem>
52-
</Tabs>
55+
```bash
56+
interpreter --api-base http://localhost:8989/v1/mux --api-key fake-value-not-used --model openai/fake-value-not-used
57+
```
58+
59+
</TabItem>
60+
61+
</Tabs>
62+
</TabItem>
63+
<TabItem value="openai" label="OpenAI">
64+
You need an [OpenAI API](https://openai.com/api/) account to use this provider.
65+
To use a different OpenAI-compatible endpoint, set the `CODEGATE_OPENAI_URL`
66+
[configuration parameter](../how-to/configure.md) when you launch CodeGate.
67+
68+
<Tabs groupId="interpreter-version">
69+
<TabItem value="current" label="Open Interpreter v0.4.x" default>
70+
```bash
71+
interpreter --api_base http://localhost:8989/openai --api_key YOUR_API_KEY --model MODEL_NAME
72+
```
73+
74+
</TabItem>
75+
<TabItem value="dev" label="v1.0 dev branch">
76+
If you are running Open Interpreter's v1.0
77+
[development branch](https://github.com/OpenInterpreter/open-interpreter/tree/development):
78+
79+
```bash
80+
interpreter --api-base http://localhost:8989/openai --api-key YOUR_API_KEY --model MODEL_NAME
81+
```
82+
83+
</TabItem>
84+
85+
</Tabs>
5386

5487
Replace `YOUR_API_KEY` with your OpenAI API key, and `MODEL_NAME` with your
5588
desired model, like `openai/gpt-4o-mini`.
5689

90+
</TabItem>
91+
</Tabs>
92+
5793
:::info
5894

5995
The `--model` parameter value must start with `openai/` for CodeGate to properly

‎docs/partials/_aider-providers.mdx

+62-44
Original file line numberDiff line numberDiff line change
@@ -5,56 +5,24 @@ import TabItem from '@theme/TabItem';
55

66
import LocalModelRecommendation from './_local-model-recommendation.md';
77

8-
<Tabs groupId="aider-provider" queryString="provider">
9-
<TabItem value="openai" label="OpenAI" default>
8+
<Tabs groupId="provider" queryString="provider">
9+
<TabItem value="mux" label="CodeGate muxing" default>
10+
First, configure your [provider(s)](../features/muxing.md#add-a-provider) and
11+
select a model for each of your
12+
[workspace(s)](../features/workspaces.mdx#manage-workspaces) in the CodeGate dashboard.
1013

11-
You need an [OpenAI API](https://openai.com/api/) account to use this provider.
12-
To use a different OpenAI-compatible endpoint, set the `CODEGATE_OPENAI_URL`
13-
[configuration parameter](../how-to/configure.md#config-parameters).
14-
15-
Before you run aider, set environment variables for your API key and to set the
16-
API base URL to CodeGate's API port. Alternately, use one of aider's other
17-
[supported configuration methods](https://aider.chat/docs/config/api-keys.html)
18-
to set the corresponding values.
19-
20-
<Tabs groupId="os">
21-
<TabItem value="macos" label="macOS / Linux" default>
22-
23-
```bash
24-
export OPENAI_API_KEY=<YOUR_API_KEY>
25-
export OPENAI_API_BASE=http://localhost:8989/openai
26-
```
27-
28-
:::note
29-
30-
To persist these variables, add them to your shell profile (e.g., `~/.bashrc` or
31-
`~/.zshrc`).
32-
33-
:::
14+
Run aider with the OpenAI base URL set to `http://localhost:8989/v1/mux`. You
15+
can do this with the `OPENAI_API_BASE` environment variable or on the command
16+
line as shown below.
3417

35-
</TabItem>
36-
<TabItem value="windows" label="Windows">
18+
The `--openai-api-key` parameter is required but the value is not used. The
19+
`--model` setting must start with `openai/` but the actual model is determined
20+
by your CodeGate workspace.
3721

3822
```bash
39-
setx OPENAI_API_KEY <YOUR_API_KEY>
40-
setx OPENAI_API_BASE http://localhost:8989/openai
23+
aider --openai-api-base http://localhost:8989/v1/mux --openai-api-key fake-value-not-used --model openai/fake-value-not-used
4124
```
4225

43-
:::note
44-
45-
Restart your shell after running `setx`.
46-
47-
:::
48-
49-
</TabItem>
50-
</Tabs>
51-
52-
Replace `<YOUR_API_KEY>` with your
53-
[OpenAI API key](https://platform.openai.com/api-keys).
54-
55-
Then run `aider` as normal. For more information, see the
56-
[aider docs for connecting to OpenAI](https://aider.chat/docs/llms/openai.html).
57-
5826
</TabItem>
5927
<TabItem value="ollama" label="Ollama">
6028

@@ -116,5 +84,55 @@ locally using `ollama pull`.
11684
For more information, see the
11785
[aider docs for connecting to Ollama](https://aider.chat/docs/llms/ollama.html).
11886

87+
</TabItem>
88+
<TabItem value="openai" label="OpenAI">
89+
90+
You need an [OpenAI API](https://openai.com/api/) account to use this provider.
91+
To use a different OpenAI-compatible endpoint, set the `CODEGATE_OPENAI_URL`
92+
[configuration parameter](../how-to/configure.md#config-parameters).
93+
94+
Before you run aider, set environment variables for your API key and to set the
95+
API base URL to CodeGate's API port. Alternately, use one of aider's other
96+
[supported configuration methods](https://aider.chat/docs/config/api-keys.html)
97+
to set the corresponding values.
98+
99+
<Tabs groupId="os">
100+
<TabItem value="macos" label="macOS / Linux" default>
101+
102+
```bash
103+
export OPENAI_API_KEY=<YOUR_API_KEY>
104+
export OPENAI_API_BASE=http://localhost:8989/openai
105+
```
106+
107+
:::note
108+
109+
To persist these variables, add them to your shell profile (e.g., `~/.bashrc` or
110+
`~/.zshrc`).
111+
112+
:::
113+
114+
</TabItem>
115+
<TabItem value="windows" label="Windows">
116+
117+
```bash
118+
setx OPENAI_API_KEY <YOUR_API_KEY>
119+
setx OPENAI_API_BASE http://localhost:8989/openai
120+
```
121+
122+
:::note
123+
124+
Restart your shell after running `setx`.
125+
126+
:::
127+
128+
</TabItem>
129+
</Tabs>
130+
131+
Replace `<YOUR_API_KEY>` with your
132+
[OpenAI API key](https://platform.openai.com/api-keys).
133+
134+
Then run `aider` as normal. For more information, see the
135+
[aider docs for connecting to OpenAI](https://aider.chat/docs/llms/openai.html).
136+
119137
</TabItem>
120138
</Tabs>

‎docs/partials/_cline-providers.mdx

+81-39
Original file line numberDiff line numberDiff line change
@@ -7,8 +7,28 @@ import ThemedImage from '@theme/ThemedImage';
77

88
import LocalModelRecommendation from './_local-model-recommendation.md';
99

10-
<Tabs groupId="cline-provider" queryString="provider">
11-
<TabItem value="anthropic" label="Anthropic" default>
10+
<Tabs groupId="provider" queryString="provider">
11+
<TabItem value="mux" label="CodeGate muxing" default>
12+
First, configure your [provider(s)](../features/muxing.md#add-a-provider) and
13+
select a model for each of your
14+
[workspace(s)](../features/workspaces.mdx#manage-workspaces) in the CodeGate dashboard.
15+
16+
In the Cline settings, choose **OpenAI Compatible** as your provider. Set the
17+
**Base URL** to `http://localhost:8989/v1/mux`. Enter anything you want into the
18+
API key and model ID fields; these are required but not used since the actual
19+
provider and model is determined by your CodeGate workspace.
20+
21+
<ThemedImage
22+
alt='Cline settings for muxing'
23+
sources={{
24+
light: useBaseUrl('/img/integrations/cline-provider-mux-light.webp'),
25+
dark: useBaseUrl('/img/integrations/cline-provider-mux-dark.webp'),
26+
}}
27+
width={'540px'}
28+
/>
29+
30+
</TabItem>
31+
<TabItem value="anthropic" label="Anthropic">
1232

1333
You need an [Anthropic API](https://www.anthropic.com/api) account to use this
1434
provider.
@@ -30,24 +50,47 @@ To enable CodeGate, enable **Use custom base URL** and enter
3050
/>
3151

3252
</TabItem>
33-
<TabItem value="openai" label="OpenAI">
53+
<TabItem value="lmstudio" label="LM Studio">
3454

35-
You need an [OpenAI API](https://openai.com/api/) account to use this provider.
36-
To use a different OpenAI-compatible endpoint, set the `CODEGATE_OPENAI_URL`
37-
[configuration parameter](../how-to/configure.md) when you launch CodeGate.
55+
You need LM Studio installed on your local system with a server running from LM
56+
Studio's **Developer** tab to use this provider. See the
57+
[LM Studio docs](https://lmstudio.ai/docs/api/server) for more information.
3858

39-
In the Cline settings, choose **OpenAI Compatible** as your provider, enter your
40-
OpenAI API key, and set your preferred model (example: `gpt-4o-mini`).
59+
Cline uses large prompts, so you will likely need to increase the context length
60+
for the model you've loaded in LM Studio. In the Developer tab, select the model
61+
you'll use with CodeGate, open the **Load** tab on the right and increase the
62+
**Context Length** to _at least_ 18k (18,432) tokens, then reload the model.
4163

42-
To enable CodeGate, set the **Base URL** to `https://localhost:8989/openai`.
64+
<ThemedImage
65+
alt='LM Studio dev server'
66+
sources={{
67+
light: useBaseUrl('/img/integrations/lmstudio-server-light.webp'),
68+
dark: useBaseUrl('/img/integrations/lmstudio-server-dark.webp'),
69+
}}
70+
width={'800px'}
71+
/>
72+
73+
CodeGate connects to `http://host.docker.internal:1234` by default. If you
74+
changed the default LM Studio server port, launch CodeGate with the
75+
`CODEGATE_LM_STUDIO_URL` environment variable set to the correct URL. See
76+
[Configure CodeGate](/how-to/configure.md).
77+
78+
In the Cline settings, choose LM Studio as your provider and set the **Base
79+
URL** to `http://localhost:8989/lm_studio`.
80+
81+
Set the **Model ID** to `lm_studio/<MODEL_NAME>`, where `<MODEL_NAME>` is the
82+
name of the model you're serving through LM Studio (shown in the Developer tab),
83+
for example `lm_studio/qwen2.5-coder-7b-instruct`.
84+
85+
<LocalModelRecommendation />
4386

4487
<ThemedImage
45-
alt='Cline settings for OpenAI'
88+
alt='Cline settings for LM Studio'
4689
sources={{
47-
light: useBaseUrl('/img/integrations/cline-provider-openai-light.webp'),
48-
dark: useBaseUrl('/img/integrations/cline-provider-openai-dark.webp'),
90+
light: useBaseUrl('/img/integrations/cline-provider-lmstudio-light.webp'),
91+
dark: useBaseUrl('/img/integrations/cline-provider-lmstudio-dark.webp'),
4992
}}
50-
width={'540px'}
93+
width={'635px'}
5194
/>
5295

5396
</TabItem>
@@ -79,47 +122,46 @@ locally using `ollama pull`.
79122
/>
80123

81124
</TabItem>
82-
<TabItem value="lmstudio" label="LM Studio">
125+
<TabItem value="openai" label="OpenAI">
83126

84-
You need LM Studio installed on your local system with a server running from LM
85-
Studio's **Developer** tab to use this provider. See the
86-
[LM Studio docs](https://lmstudio.ai/docs/api/server) for more information.
127+
You need an [OpenAI API](https://openai.com/api/) account to use this provider.
128+
To use a different OpenAI-compatible endpoint, set the `CODEGATE_OPENAI_URL`
129+
[configuration parameter](../how-to/configure.md) when you launch CodeGate.
87130

88-
Cline uses large prompts, so you will likely need to increase the context length
89-
for the model you've loaded in LM Studio. In the Developer tab, select the model
90-
you'll use with CodeGate, open the **Load** tab on the right and increase the
91-
**Context Length** to _at least_ 18k (18,432) tokens, then reload the model.
131+
In the Cline settings, choose **OpenAI Compatible** as your provider, enter your
132+
OpenAI API key, and set your preferred model (example: `gpt-4o-mini`).
133+
134+
To enable CodeGate, set the **Base URL** to `http://localhost:8989/openai`.
92135

93136
<ThemedImage
94-
alt='LM Studio dev server'
137+
alt='Cline settings for OpenAI'
95138
sources={{
96-
light: useBaseUrl('/img/integrations/lmstudio-server-light.webp'),
97-
dark: useBaseUrl('/img/integrations/lmstudio-server-dark.webp'),
139+
light: useBaseUrl('/img/integrations/cline-provider-openai-light.webp'),
140+
dark: useBaseUrl('/img/integrations/cline-provider-openai-dark.webp'),
98141
}}
99-
width={'800px'}
142+
width={'540px'}
100143
/>
101144

102-
CodeGate connects to `http://host.docker.internal:1234` by default. If you
103-
changed the default LM Studio server port, launch CodeGate with the
104-
`CODEGATE_LM_STUDIO_URL` environment variable set to the correct URL. See
105-
[Configure CodeGate](/how-to/configure.md).
145+
</TabItem>
146+
<TabItem value="openrouter" label="OpenRouter">
106147

107-
In the Cline settings, choose LM Studio as your provider and set the **Base
108-
URL** to `http://localhost:8989/lm_studio`.
148+
You need an [OpenRouter](https://openrouter.ai/) account to use this provider.
109149

110-
Set the **Model ID** to `lm_studio/<MODEL_NAME>`, where `<MODEL_NAME>` is the
111-
name of the model you're serving through LM Studio (shown in the Developer tab),
112-
for example `lm_studio/qwen2.5-coder-7b-instruct`.
150+
In the Cline settings, choose **OpenAI Compatible** as your provider (NOT
151+
OpenRouter), enter your
152+
[OpenRouter API key](https://openrouter.ai/settings/keys), and set your
153+
[preferred model](https://openrouter.ai/models) (example:
154+
`anthropic/claude-3.5-sonnet`).
113155

114-
<LocalModelRecommendation />
156+
To enable CodeGate, set the **Base URL** to `http://localhost:8989/openrouter`.
115157

116158
<ThemedImage
117-
alt='Cline settings for LM Studio'
159+
alt='Cline settings for OpenRouter'
118160
sources={{
119-
light: useBaseUrl('/img/integrations/cline-provider-lmstudio-light.webp'),
120-
dark: useBaseUrl('/img/integrations/cline-provider-lmstudio-dark.webp'),
161+
light: useBaseUrl('/img/integrations/cline-provider-openrouter-light.webp'),
162+
dark: useBaseUrl('/img/integrations/cline-provider-openrouter-dark.webp'),
121163
}}
122-
width={'635px'}
164+
width={'540px'}
123165
/>
124166

125167
</TabItem>

‎docs/partials/_kodu-providers.mdx

+45
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,45 @@
1+
{/* This content is pulled out as an include because Prettier can't handle the indentation needed to get this to appear in the right spot under a list item. */}
2+
3+
import Tabs from '@theme/Tabs';
4+
import TabItem from '@theme/TabItem';
5+
6+
<Tabs groupId="provider" queryString="provider">
7+
<TabItem value="mux" label="CodeGate muxing" default>
8+
First, configure your [provider(s)](../features/muxing.md#add-a-provider) and
9+
select a model for each of your
10+
[workspace(s)](../features/workspaces.mdx#manage-workspaces) in the CodeGate dashboard.
11+
12+
In the **Provider Settings** settings, select **OpenAI Compatible**. Set the
13+
**Base URL** to `http://localhost:8989/v1/mux`.
14+
15+
Enter anything you want into the Model ID and API key fields; these are not used
16+
since the actual provider and model is determined by your CodeGate workspace.
17+
18+
</TabItem>
19+
<TabItem value="openai" label="OpenAI">
20+
21+
You need an [OpenAI API](https://openai.com/api/) account to use this provider.
22+
To use a different OpenAI-compatible endpoint, set the `CODEGATE_OPENAI_URL`
23+
[configuration parameter](../how-to/configure.md) when you launch CodeGate.
24+
25+
In the **Provider Settings** settings, select **OpenAI Compatible**. Set the
26+
**Base URL** to `http://localhost:8989/openai`.
27+
28+
Enter the **Model ID** and your
29+
[OpenAI API key](https://platform.openai.com/api-keys). A reasoning model like
30+
`o1-mini` or `o3-mini` is recommended.
31+
32+
</TabItem>
33+
<TabItem value="openrouter" label="OpenRouter">
34+
35+
You need an [OpenRouter](https://openrouter.ai/) account to use this provider.
36+
37+
In the **Provider Settings** settings, select **OpenAI Compatible**. Set the
38+
**Base URL** to `http://localhost:8989/openrouter`.
39+
40+
Enter your [preferred model](https://openrouter.ai/models) for the **Model ID**
41+
(example: `anthropic/claude-3.5-sonnet`) and add your
42+
[OpenRouter API key](https://openrouter.ai/keys).
43+
44+
</TabItem>
45+
</Tabs>

‎eslint.config.mjs

+14
Original file line numberDiff line numberDiff line change
@@ -10,10 +10,13 @@ export default [
1010
{ ignores: ['.docusaurus/', 'build/', 'node_modules/'] },
1111
{ files: ['**/*.{js,mjs,cjs,ts,jsx,tsx}'] },
1212
{ languageOptions: { globals: globals.node } },
13+
1314
pluginJs.configs.recommended,
1415
...tseslint.configs.recommended,
1516
pluginReact.configs.flat.recommended,
1617
eslintConfigPrettier,
18+
19+
// Configs for .mdx files
1720
{
1821
...mdx.flat,
1922
processor: mdx.createRemarkProcessor({
@@ -23,8 +26,19 @@ export default [
2326
rules: {
2427
...mdx.flat.rules,
2528
'react/no-unescaped-entities': 'off',
29+
'react/jsx-no-undef': ['error', { allowGlobals: true }],
30+
},
31+
languageOptions: {
32+
...mdx.flat.languageOptions,
33+
globals: {
34+
...mdx.flat.languageOptions.globals,
35+
// Add global components from src/theme/MDXComponents.tsx here
36+
Columns: 'readonly',
37+
Column: 'readonly',
38+
},
2639
},
2740
},
41+
2842
{
2943
settings: {
3044
react: {

‎src/components/Column/index.tsx

+21
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,21 @@
1+
import React, { ReactNode, CSSProperties } from 'react';
2+
// Import clsx library for conditional classes.
3+
import clsx from 'clsx';
4+
5+
interface ColumnProps {
6+
children: ReactNode;
7+
className?: string;
8+
style?: CSSProperties;
9+
}
10+
11+
// Define the Column component as a function
12+
// with children, className, style as properties
13+
// Look https://infima.dev/docs/ for learn more.
14+
// Style only affects the element inside the column, but we could have also made the same distinction as for the classes.
15+
export default function Column({ children, className, style }: ColumnProps) {
16+
return (
17+
<div className={clsx('col', className)} style={style}>
18+
{children}
19+
</div>
20+
);
21+
}

‎src/components/Columns/index.tsx

+24
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
import React, { ReactNode, CSSProperties } from 'react';
2+
// Import clsx library for conditional classes.
3+
import clsx from 'clsx';
4+
5+
interface ColumnsProps {
6+
children: ReactNode;
7+
className?: string;
8+
style?: CSSProperties;
9+
}
10+
11+
// Define the Columns component as a function
12+
// with children, className, and style as properties
13+
// className will allow you to pass either your custom classes or the native infima classes https://infima.dev/docs/layout/grid.
14+
// Style" will allow you to either pass your custom styles directly, which can be an alternative to the "styles.module.css" file in certain cases.
15+
export default function Columns({ children, className, style }: ColumnsProps) {
16+
return (
17+
// This section encompasses the columns that we will integrate with children from a dedicated component to allow the addition of columns as needed
18+
<div className='container center'>
19+
<div className={clsx('row', className)} style={style}>
20+
{children}
21+
</div>
22+
</div>
23+
);
24+
}

‎src/theme/MDXComponents.tsx

+18
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,18 @@
1+
/*
2+
Extra components to load into the global scope.
3+
See https://docusaurus.io/docs/markdown-features/react#mdx-component-scope
4+
5+
To avoid linting errors, add these to the `languageOptions.globals` section
6+
for mdx files in the `eslint.config.mjs` file
7+
*/
8+
9+
import MDXComponents from '@theme-original/MDXComponents';
10+
import Columns from '@site/src/components/Columns';
11+
import Column from '@site/src/components/Column';
12+
13+
export default {
14+
// Reusing the default mapping
15+
...MDXComponents,
16+
Columns,
17+
Column,
18+
};

‎static/img/integrations/cline-mode-act-dark.webp

16.9 KB
Binary file not shown.

‎static/img/integrations/cline-mode-act-light.webp

18.2 KB
Binary file not shown.

‎static/img/integrations/cline-mode-plan-dark.webp

15 KB
Binary file not shown.

‎static/img/integrations/cline-mode-plan-light.webp

16.2 KB
Binary file not shown.

‎static/img/integrations/cline-provider-mux-dark.webp

48.8 KB
Binary file not shown.

‎static/img/integrations/cline-provider-mux-light.webp

51.3 KB
Binary file not shown.

‎static/img/integrations/cline-provider-openrouter-dark.webp

54.7 KB
Binary file not shown.

‎static/img/integrations/cline-provider-openrouter-light.webp

57.6 KB
Binary file not shown.

‎static/img/integrations/kodu-codegate-version-dark.webp

57.8 KB
Binary file not shown.

‎static/img/integrations/kodu-codegate-version-light.webp

60.3 KB
Binary file not shown.

‎static/img/integrations/kodu-settings-dark.webp

132 KB
Binary file not shown.

‎static/img/integrations/kodu-settings-light.webp

135 KB
Binary file not shown.

0 commit comments

Comments
 (0)
Please sign in to comment.