MediaWiki - User contributions [en]

AI on demand: Configuring OpenCode Desktop

2026-11-03T15:06:29Z

Sst-pde: /* Overview */

== Overview ==

[https://opencode.ai OpenCode] is an open-source AI coding agent, available as a desktop application, in the browser or via the terminal. It supports tool calls, MCP servers, skills, plugins, etc. for software development workflows. OpenCode can be configured to exclusively use AI models hosted by [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG] via its OpenAI-compatible API.

'''Note:''' This guide walks through configuring the desktop variant of OpenCode. If you are looking for guidance on setting up the terminal version of OpenCode, see [[AI on demand: Configuring OpenCode Terminal]]

The following steps describe how to create a basic OpenCode setup using models provided by stepping stone AG, and some good first steps to control and extend the agents capabilities.

{{Note|title=⚠️ Warning|content=Remember that agents such as OpenCode can autonomously perform actions on the system they run, such as reading / editing files, making web requests, executing terminal commands, etc. Agents may also interpret untrusted inputs such as skills or AGENTS.md files as instructions. Consider carefully which actions an agent should be allowed to execute, and whether a container or VM solution may be appropriate to prevent your agent from accessing sensitive information.}}

== Prerequisites ==

* A valid [https://www.stepping-stone.ch/en/products/artificial-intelligence AI on Demand] API key.
* Network access to <code>https://llm.stoney-cloud.com/v1</code>
* The ID of the AI models you wish to use with OpenCode (e.g.
* ''Optional:'' [https://nodejs.org Node.js] 20 or newer if you intend to install opencode via npm.

== Installation ==

Download and install the [https://opencode.ai/v2/docs#desktop binary / package] appropriate for your system.

Once complete, open the OpenCode desktop app to verify that the installation was successful

<gallery mode=packed heights=200px>
OpenCode Desktop homepage.png|OpenCode Desktop
</gallery>

== Configure provider and models ==

OpenCode desktop currently does not support adding custom model providers directly from its user interface. You will need to configure stepping stone AG as your provider by modifying your OpenCode configuration file to include the following:

<syntaxhighlight lang="json">
{
"$schema": "https://opencode.ai/config.json",
"providers": {
"stepping-stone": {
"name": "stepping stone AG",
"package": "@opencode/ai/providers/openai-compatible",
"env": ["STONEY_KEY"],
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1"
},
"models": {}
}
}
}
</syntaxhighlight>

On Linux machines, the default location of your personal configuration file is <code>~/.config/opencode/opencode.jsonc</code> or equivalent. See [https://opencode.ai/v2/docs/config/#locations https://opencode.ai/v2/docs/config/#locations] for more information on where to place the configuration file on your system.

'''Note:''' When configuring stepping stone AG as your provider as above, OpenCode expects to find your API key in an environment variable called <code>STONEY_KEY</code>. Alternatively you may add your key directly to the configuration file by removing the <code>"env": ["STONEY_KEY"],</code> line, and adding your key as follows:

<syntaxhighlight lang="json">
...
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1",
"apiKey": "YOUR API KEY GOES HERE",
},
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Your API key must be kept secret by you! Be careful where you store your key to prevent it from being stolen or abused by a third party.}}

Next, you should configure at least one model you wish to use with OpenCode. The following is a configuration for the <code>GLM-5.3-Flash</code> model provided by stepping stone AG:

<syntaxhighlight lang="json">
...
"models": {
"zai-org/GLM-5.3-Flash": {
"name": "GLM 5.3 Flash",
"limit": {
"context": 262144,
},
"cost": {
"input": 0.3,
"output": 1.5,
"cache": {
"read": 0.045,
},
},
},
}
</syntaxhighlight>

Replace <code>zai-org/GLM-5.3-Flash</code> with the ID of the particular model you wish to use, and refer to [https://www.stepping-stone.ch/en/products/artificial-intelligence https://www.stepping-stone.ch/en/products/artificial-intelligence] for pricing and context window limits. Additional model specific configuration can be added as needed. See [https://opencode.ai/v2/docs/models/ https://opencode.ai/v2/docs/models/] for further information on configuring models.

To check if your configuration is correct, restart OpenCode after changing the configuration file. If the configuration is correct, stepping stone AG should appear as a configured provider, and your selected model in the available models list.

<gallery mode=packed heights=200>
OpenCode_Home_button.png|1. Open home page
OpenCode_settings_menu.png|2. Open settings menu
OpenCode_Desktop_Stepping_Stone_Provider.png|3. Check that stepping stone AG appears as a provider
OpenCode_Desktop_Stepping_Stone_Model.png|4. Check that your selected model appears at the bottom of the list
</gallery>

Finally, start a new session, select the model you have just configured and enter a first prompt to test that the model is working correctly.

<gallery mode=packed heights=200>
OpenCode_Desktop_Stepping_Stone_Model_selected.png|1. Start a new session and select a stepping stone AG provided model
OpenCode_Desktop_First_Prompt.png|2. Enter a first prompt to check that the configuration works
</gallery>

== Configure appearance and notifications ==

You may customise the appearance and layout of the UI, notification settings, shortcuts and more via the settings menu.

<gallery mode=packed heights=200>
OpenCode_Desktop_settings.png|Available settings submenus
</gallery>

== Permissions ==

OpenCode provides a built in sandbox to limit what actions an agent is allowed to perform. You can configure permissions via the configuration file (there is currently no option to configure permissions via the user interface). Permissions are defined as a list of rules. For each action (e.g. read/write a file, execute a shell command, etc.), you may define a set of rules, each with a pattern determining when the rule applies, and an effect to determine if the action is allowed, denied or requires explicit approval by the user. The following shows some examples of permission rules:

<syntaxhighlight lang="json">
...
"permissions": [
{ "action": "shell", "resource": "*", "effect": "ask" },
{ "action": "shell", "resource": "git status *", "effect": "allow" },
{ "action": "shell", "resource": "git push *", "effect": "deny" },
{ "action": "skill", "resource": "*", "effect": "allow" },
{ "action": "read", "resource": "*", "effect": "allow" },
{ "action": "edit", "resource": "*.html", "effect": "allow" },
]
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Try to keep the permissions you define as restrictive as feasable. In particular, do not allow your agent to perform sensitive or dangerous actions without your explicit approval.}}

{{Note|title=⚠️ Warning|content=While OpenCode provides a sandbox controlled via permissions, you should never rely exclusively on the sandbox to ensure that your agent does not perform dangerous actions or accesses sensitive data. Always exercise good judgement when deciding what your agent should be allowed to do.}}

== Further steps ==

You now have a basic OpenCode agent setup available to you. You may further customise and extend OpenCode in a variety of ways, such as by adding skills, configuring MCP servers or OpenCode plugins.

Check [https://opencode.ai/v2/docs/ https://opencode.ai/v2/docs/] or the settings menu of OpenCode to see how you can extend your agent to your needs.

= References =

* [https://opencode.ai/v2/docs/ OpenCode documentation]
* [https://opencode.ai/v2/docs/providers OpenCode providers guide]
* [https://opencode.ai/v2/docs/config OpenCode configuration reference] and [https://opencode.ai/config.json configuration schema]
* [https://opencode.ai/v2/docs/permissions OpenCode permissions guide]
* [https://opencode.ai/v2/docs/mcp-servers OpenCode MCP servers guide]
* [https://modelcontextprotocol.io Model Context Protocol specification]
* [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG – Artificial Intelligence]
* [[AI on Demand: Usage]]

[[Category: AI on Demand]]
[[Category: OpenCode]]

AI on demand: Configuring OpenCode Terminal

2026-11-03T15:06:17Z

Sst-pde: /* Overview */

== Overview ==

[https://opencode.ai OpenCode] is an open-source AI coding agent, available as a desktop application, in the browser or via the terminal. It supports tool calls, MCP servers, skills, plugins, etc. for software development workflows. OpenCode can be configured to exclusively use AI models hosted by [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG] via its OpenAI-compatible API.

'''Note:''' This guide walks through configuring the terminal variant of OpenCode. If you are looking for guidance on setting up the terminal version of OpenCode, see [[AI on demand: Configuring OpenCode Desktop]]

The following steps describe how to create a basic OpenCode setup using models provided by stepping stone AG, and some good first steps to control and extend the agents capabilities.

{{Note|title=⚠️ Warning|content=Remember that agents such as OpenCode can autonomously perform actions on the system they run, such as reading / editing files, making web requests, executing terminal commands, etc. Agents may also interpret untrusted inputs such as skills or AGENTS.md files as instructions. Consider carefully which actions an agent should be allowed to execute, and whether a container or VM solution may be appropriate to prevent your agent from accessing sensitive information.}}

== Prerequisites ==

* A valid [https://www.stepping-stone.ch/en/products/artificial-intelligence AI on Demand] API key.
* Network access to <code>https://llm.stoney-cloud.com/v1</code>
* The ID of the AI models you wish to use with OpenCode (e.g.
* ''Optional:'' [https://nodejs.org Node.js] 20 or newer if you intend to install opencode via npm.

== Installation ==

Use your JavaScript package manager of choice to install the terminal variant of OpenCode:

<syntaxhighlight lang="bash">
npm install -g @opencode/cli
# or
bun install -g --trust @opencode/cli
# or
brew install anomalyco/tap/opencode-v2
</syntaxhighlight>

See [https://opencode.ai/v2/docs https://opencode.ai/v2/docs] for further information on how to install OpenCode.

Verify that the installation was successful by starting OpenCode:
<syntaxhighlight lang="bash">
opencode --version
opencode
</syntaxhighlight>

<gallery mode=packed heights=200>
OpenCode TUI.png|thumb|OpenCode Terminal
</gallery>

== Configure provider and models ==

To configure stepping stone AG as your provider, you must modify your OpenCode configuration file to include the following:

<syntaxhighlight lang="json">
{
"$schema": "https://opencode.ai/config.json",
"providers": {
"stepping-stone": {
"name": "stepping stone AG",
"package": "@opencode/ai/providers/openai-compatible",
"env": ["STONEY_KEY"],
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1"
},
"models": {}
}
}
}
</syntaxhighlight>

On Linux machines, the default location of your personal configuration file is <code>~/.config/opencode/opencode.jsonc</code> or equivalent. See [https://opencode.ai/v2/docs/config/#locations https://opencode.ai/v2/docs/config/#locations] for more information on where to place the configuration file on your system.

'''Note:''' When configuring stepping stone AG as your provider as above, OpenCode expects to find your API key in an environment variable called <code>STONEY_KEY</code>. Alternatively you may add your key directly to the configuration file by removing the <code>"env": ["STONEY_KEY"],</code> line, and adding your key as follows:

<syntaxhighlight lang="json">
...
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1",
"apiKey": "YOUR API KEY GOES HERE",
},
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Your API key must be kept secret by you! Be careful where you store your key to prevent it from being stolen or abused by a third party.}}

Next, you should configure at least one model you wish to use with OpenCode. The following is a configuration for the <code>GLM-5.3-Flash</code> model provided by stepping stone AG:

<syntaxhighlight lang="json">
...
"models": {
"zai-org/GLM-5.3-Flash": {
"name": "GLM 5.3 Flash",
"limit": {
"context": 262144,
},
"cost": {
"input": 0.3,
"output": 1.5,
"cache": {
"read": 0.045,
},
},
},
}
</syntaxhighlight>

Replace <code>zai-org/GLM-5.3-Flash</code> with the ID of the particular model you wish to use, and refer to [https://www.stepping-stone.ch/en/products/artificial-intelligence https://www.stepping-stone.ch/en/products/artificial-intelligence] for pricing and context window limits. Additional model specific configuration can be added as needed. See [https://opencode.ai/v2/docs/models/ https://opencode.ai/v2/docs/models/] for further information on configuring models.

To check if your configuration is correct, restart OpenCode after changing the configuration file. If the configuration is correct, you should be able to select the newly added model hosted by stepping stone AG from the list of available models. You can open a selection of all models available to you via the shortcut <code>CTRL + X</code>, <code>m</code>. You may need to scroll to the end of the displayed list.
<gallery mode=packed heights=200>
OpenCode_TUI_Model_selection.png|Model selection menu
</gallery>

Finally, select the newly added model, then enter a first prompt to test that the model is working correctly.
<gallery mode=packed heights=200>
OpenCode_TUI_Initial_prompt.png|Enter an initial prompt
OpenCode_TUI_Initial_prompt_response.png|Check that you receive a response
</gallery>

== Useful short-cuts and menus ==

The following is a list of useful shortcuts to get started with using OpenCode:

* <code>CTRL + P</code>: Open the main menu to interact with the agent, manage sessions and MCP servers, configuration, theming, etc.
* <code>CTRL + X</code> / <code>N</code>: Open a fresh session.
* <code>CTRL + X</code> / <code>L</code>: Switch to another existing session.
* <code>CTRL + X</code> / <code>W</code>: Close the current session tab.
* <code>CTRL + X</code> / <code>M</code>: Switch the current model.
* <code>CTRL + X</code> / <code>A</code>: Switch the current agent mode.
* <code>CTRL + X</code> / <code>Q</code>: Quit OpenCode.
* <code>CTRL + C</code>: Clear prompt input field.

== Permissions ==

OpenCode provides a built in sandbox to limit what actions an agent is allowed to perform. You can configure permissions via the configuration file (there is currently no option to configure permissions via the user interface). Permissions are defined as a list of rules. For each action (e.g. read/write a file, execute a shell command, etc.), you may define a set of rules, each with a pattern determining when the rule applies, and an effect to determine if the action is allowed, denied or requires explicit approval by the user. The following shows some examples of permission rules:

<syntaxhighlight lang="json">
...
"permissions": [
{ "action": "shell", "resource": "*", "effect": "ask" },
{ "action": "shell", "resource": "git status *", "effect": "allow" },
{ "action": "shell", "resource": "git push *", "effect": "deny" },
{ "action": "skill", "resource": "*", "effect": "allow" },
{ "action": "read", "resource": "*", "effect": "allow" },
{ "action": "edit", "resource": "*.html", "effect": "allow" },
]
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Try to keep the permissions you define as restrictive as feasable. In particular, do not allow your agent to perform sensitive or dangerous actions without your explicit approval.}}

{{Note|title=⚠️ Warning|content=While OpenCode provides a sandbox controlled via permissions, you should never rely exclusively on the sandbox to ensure that your agent does not perform dangerous actions or accesses sensitive data. Always exercise good judgement when deciding what your agent should be allowed to do.}}

== Further steps ==

You now have a basic OpenCode agent setup available to you. You may further customise and extend OpenCode in a variety of ways, such as by adding skills, configuring MCP servers or OpenCode plugins.

Check [https://opencode.ai/v2/docs/ https://opencode.ai/v2/docs/] to see how you can extend your configuration file to adapt your agent to your needs.

= References =

* [https://opencode.ai/v2/docs/ OpenCode documentation]
* [https://opencode.ai/v2/docs/providers OpenCode providers guide]
* [https://opencode.ai/v2/docs/config OpenCode configuration reference] and [https://opencode.ai/config.json configuration schema]
* [https://opencode.ai/v2/docs/permissions OpenCode permissions guide]
* [https://opencode.ai/v2/docs/mcp-servers OpenCode MCP servers guide]
* [https://modelcontextprotocol.io Model Context Protocol specification]
* [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG – Artificial Intelligence]
* [[AI on Demand: Usage]]

[[Category: AI on Demand]]
[[Category: OpenCode]]

AI on demand: Configuring OpenCode Terminal

2026-11-03T15:05:58Z

Sst-pde:

== Overview ==

[https://opencode.ai OpenCode] is an open-source AI coding agent, available as a desktop application, in the browser or via the terminal. It supports tool calls, MCP servers, skills, plugins, etc. for software development workflows. OpenCode can be configured to exclusively use AI models hosted by [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG] via its OpenAI-compatible API.

'''Note:''' This guide walks through configuring the terminal variant of OpenCode. If you are looking for guidance on setting up the terminal version of OpenCode, see [[AI on demand: Configure OpenCode Desktop]]

The following steps describe how to create a basic OpenCode setup using models provided by stepping stone AG, and some good first steps to control and extend the agents capabilities.

{{Note|title=⚠️ Warning|content=Remember that agents such as OpenCode can autonomously perform actions on the system they run, such as reading / editing files, making web requests, executing terminal commands, etc. Agents may also interpret untrusted inputs such as skills or AGENTS.md files as instructions. Consider carefully which actions an agent should be allowed to execute, and whether a container or VM solution may be appropriate to prevent your agent from accessing sensitive information.}}

== Prerequisites ==

* A valid [https://www.stepping-stone.ch/en/products/artificial-intelligence AI on Demand] API key.
* Network access to <code>https://llm.stoney-cloud.com/v1</code>
* The ID of the AI models you wish to use with OpenCode (e.g.
* ''Optional:'' [https://nodejs.org Node.js] 20 or newer if you intend to install opencode via npm.

== Installation ==

Use your JavaScript package manager of choice to install the terminal variant of OpenCode:

<syntaxhighlight lang="bash">
npm install -g @opencode/cli
# or
bun install -g --trust @opencode/cli
# or
brew install anomalyco/tap/opencode-v2
</syntaxhighlight>

See [https://opencode.ai/v2/docs https://opencode.ai/v2/docs] for further information on how to install OpenCode.

Verify that the installation was successful by starting OpenCode:
<syntaxhighlight lang="bash">
opencode --version
opencode
</syntaxhighlight>

<gallery mode=packed heights=200>
OpenCode TUI.png|thumb|OpenCode Terminal
</gallery>

== Configure provider and models ==

To configure stepping stone AG as your provider, you must modify your OpenCode configuration file to include the following:

<syntaxhighlight lang="json">
{
"$schema": "https://opencode.ai/config.json",
"providers": {
"stepping-stone": {
"name": "stepping stone AG",
"package": "@opencode/ai/providers/openai-compatible",
"env": ["STONEY_KEY"],
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1"
},
"models": {}
}
}
}
</syntaxhighlight>

On Linux machines, the default location of your personal configuration file is <code>~/.config/opencode/opencode.jsonc</code> or equivalent. See [https://opencode.ai/v2/docs/config/#locations https://opencode.ai/v2/docs/config/#locations] for more information on where to place the configuration file on your system.

'''Note:''' When configuring stepping stone AG as your provider as above, OpenCode expects to find your API key in an environment variable called <code>STONEY_KEY</code>. Alternatively you may add your key directly to the configuration file by removing the <code>"env": ["STONEY_KEY"],</code> line, and adding your key as follows:

<syntaxhighlight lang="json">
...
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1",
"apiKey": "YOUR API KEY GOES HERE",
},
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Your API key must be kept secret by you! Be careful where you store your key to prevent it from being stolen or abused by a third party.}}

Next, you should configure at least one model you wish to use with OpenCode. The following is a configuration for the <code>GLM-5.3-Flash</code> model provided by stepping stone AG:

<syntaxhighlight lang="json">
...
"models": {
"zai-org/GLM-5.3-Flash": {
"name": "GLM 5.3 Flash",
"limit": {
"context": 262144,
},
"cost": {
"input": 0.3,
"output": 1.5,
"cache": {
"read": 0.045,
},
},
},
}
</syntaxhighlight>

Replace <code>zai-org/GLM-5.3-Flash</code> with the ID of the particular model you wish to use, and refer to [https://www.stepping-stone.ch/en/products/artificial-intelligence https://www.stepping-stone.ch/en/products/artificial-intelligence] for pricing and context window limits. Additional model specific configuration can be added as needed. See [https://opencode.ai/v2/docs/models/ https://opencode.ai/v2/docs/models/] for further information on configuring models.

To check if your configuration is correct, restart OpenCode after changing the configuration file. If the configuration is correct, you should be able to select the newly added model hosted by stepping stone AG from the list of available models. You can open a selection of all models available to you via the shortcut <code>CTRL + X</code>, <code>m</code>. You may need to scroll to the end of the displayed list.
<gallery mode=packed heights=200>
OpenCode_TUI_Model_selection.png|Model selection menu
</gallery>

Finally, select the newly added model, then enter a first prompt to test that the model is working correctly.
<gallery mode=packed heights=200>
OpenCode_TUI_Initial_prompt.png|Enter an initial prompt
OpenCode_TUI_Initial_prompt_response.png|Check that you receive a response
</gallery>

== Useful short-cuts and menus ==

The following is a list of useful shortcuts to get started with using OpenCode:

* <code>CTRL + P</code>: Open the main menu to interact with the agent, manage sessions and MCP servers, configuration, theming, etc.
* <code>CTRL + X</code> / <code>N</code>: Open a fresh session.
* <code>CTRL + X</code> / <code>L</code>: Switch to another existing session.
* <code>CTRL + X</code> / <code>W</code>: Close the current session tab.
* <code>CTRL + X</code> / <code>M</code>: Switch the current model.
* <code>CTRL + X</code> / <code>A</code>: Switch the current agent mode.
* <code>CTRL + X</code> / <code>Q</code>: Quit OpenCode.
* <code>CTRL + C</code>: Clear prompt input field.

== Permissions ==

OpenCode provides a built in sandbox to limit what actions an agent is allowed to perform. You can configure permissions via the configuration file (there is currently no option to configure permissions via the user interface). Permissions are defined as a list of rules. For each action (e.g. read/write a file, execute a shell command, etc.), you may define a set of rules, each with a pattern determining when the rule applies, and an effect to determine if the action is allowed, denied or requires explicit approval by the user. The following shows some examples of permission rules:

<syntaxhighlight lang="json">
...
"permissions": [
{ "action": "shell", "resource": "*", "effect": "ask" },
{ "action": "shell", "resource": "git status *", "effect": "allow" },
{ "action": "shell", "resource": "git push *", "effect": "deny" },
{ "action": "skill", "resource": "*", "effect": "allow" },
{ "action": "read", "resource": "*", "effect": "allow" },
{ "action": "edit", "resource": "*.html", "effect": "allow" },
]
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Try to keep the permissions you define as restrictive as feasable. In particular, do not allow your agent to perform sensitive or dangerous actions without your explicit approval.}}

{{Note|title=⚠️ Warning|content=While OpenCode provides a sandbox controlled via permissions, you should never rely exclusively on the sandbox to ensure that your agent does not perform dangerous actions or accesses sensitive data. Always exercise good judgement when deciding what your agent should be allowed to do.}}

== Further steps ==

You now have a basic OpenCode agent setup available to you. You may further customise and extend OpenCode in a variety of ways, such as by adding skills, configuring MCP servers or OpenCode plugins.

Check [https://opencode.ai/v2/docs/ https://opencode.ai/v2/docs/] to see how you can extend your configuration file to adapt your agent to your needs.

= References =

* [https://opencode.ai/v2/docs/ OpenCode documentation]
* [https://opencode.ai/v2/docs/providers OpenCode providers guide]
* [https://opencode.ai/v2/docs/config OpenCode configuration reference] and [https://opencode.ai/config.json configuration schema]
* [https://opencode.ai/v2/docs/permissions OpenCode permissions guide]
* [https://opencode.ai/v2/docs/mcp-servers OpenCode MCP servers guide]
* [https://modelcontextprotocol.io Model Context Protocol specification]
* [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG – Artificial Intelligence]
* [[AI on Demand: Usage]]

[[Category: AI on Demand]]
[[Category: OpenCode]]

Main Page

2026-11-03T15:05:47Z

Sst-pde: /* Artificial Intelligence (AI) */

<div style="float:left; width:48%;">
== Introduction ==
Welcome to the wiki of our [https://www.openstack.org/ OpenStack] based [https://www.stoney-cloud.com/ stoney cloud] infrastructure.
This collection serves as a comprehensive resource for all aspects of our cloud environment. Here, you will find guides for managing and utilizing our stoney cloud.

== OpenStack - Getting started ==
[[Quickstart|OpenStack quick start guide]]

== OpenStack - Usage ==
[[:Category:Projects|Projects]]

[[:Category:Instances|Instances]]
* [[VM creation (Linux)]]
* [[VM creation (Windows)]]
* [[VM resize (Linux)]]
* [[VM resize (Windows)]]
* [[Flavor explanation]]
[[:Category:Volumes|Volumes]]
* [[Quota]]

[[:Category:Images|Images]]
* [[Image creation]]
[[:Category:Network|Network]]
* [[Security group rules]]
* [[IP usage]]

[[:Category:Object store|Object store]]
* [[S3 buckets]]

[[:Category:Kubernetes|Kubernetes]]
* [[Kubernetes management]]
* [[Kubernetes usage]]

[[:Category:Backup|Backup]]
* [[Kopia restore process]]
[[:Category:Troubleshooting|Troubleshooting]]
* [[PCI workaround]]
* [[Change user password]]

</div>

<div style="float:right; width:48%">

== Artificial Intelligence (AI) ==
[[AI on Demand: Usage]] (list models, show usage, ...)

[[:Category: General purpose models|General purpose models]]
* [[AI on demand: apertus-ai/Apertus-v1.5-8B]]
* [[AI on demand: deepseek-ai/DeepSeek-V4-Flash-0731]]
* [[AI on demand: google/gemma-4-31B-it]]
* [[AI on demand: MiniMaxAI/MiniMax-M2.5]]
* [[AI on demand: NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B]]
* [[AI on demand: openai/gpt-oss-120b]]
* [[AI on demand: opendatalab/MinerU2.5-2509-1.2B]]
* [[AI on demand: Qwen/Qwen3-Coder-Next]]
* [[AI on demand: Qwen/Qwen3.5-35B-A3B-FP8]]
* [[AI on demand: Qwen/Qwen3.8-27B]]
* [[AI on demand: zai-org/GLM-5.3-Flash]]

[[:Category: OCR models|OCR models]]
* [[AI on demand: allenai/olmOCR-2-7B]]
* [[AI on demand: lightonai/LightOnOCR-2-1B]]

[[:Category: Text to Image models|Text to Image models]]
* [[AI on demand: black-forest-labs/FLUX.1-schnell]]

[[:Category: Audio models|Audio models]]
* [[AI on demand: mistralai/Voxtral-Mini-3B-2507]]
* [[AI on demand: openai/whisper-large-v3]]

[[:Category: Embedding models|Embedding models]]
* [[AI on demand: BAAI/bge-m3]]

[[:Category: Reranking models|Reranking models]]
* [[AI on demand: BAAI/bge-reranker-v2-m3]]

[[:Category: System One decision models|System One decision models]]
* [[AI on demand: convaiinnovations/laya]]
* [[AI on demand: jaredpalmer/kev-27b]]
* [[AI on demand: Mapika/decider-31b]]

[[:Category: OpenCode]]
* [[AI on demand: Configuring OpenCode Desktop]]
* [[AI on demand: Configuring OpenCode Terminal]]

== Quick links ==
* [https://www.stoney-cloud.com/ stoney cloud Website]
* [https://dashboard.stoney-cloud.com/ stoney cloud Dashboard]
* [https://docs.openstack.org/horizon/latest/user/index.html Official OpenStack Dashboard Documentation]
* [https://docs.openstack.org/python-openstackclient/latest/cli/index.html Official OpenStack CLI Documentation]
</div>

<div style="clear:both; height:0px; line-height:0px;"></div>

__NOTOC__

AI on demand: Configuring OpenCode Terminal

2026-11-03T15:05:33Z

Sst-pde: Created page with "== Overview == [https://opencode.ai OpenCode] is an open-source AI coding agent, available as a desktop application, in the browser or via the terminal. It supports tool calls, MCP servers, skills, plugins, etc. for software development workflows. OpenCode can be configured to exclusively use AI models hosted by [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG] via its OpenAI-compatible API. '''Note:''' This guide walks through confi..."

== Overview ==

[https://opencode.ai OpenCode] is an open-source AI coding agent, available as a desktop application, in the browser or via the terminal. It supports tool calls, MCP servers, skills, plugins, etc. for software development workflows. OpenCode can be configured to exclusively use AI models hosted by [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG] via its OpenAI-compatible API.

'''Note:''' This guide walks through configuring the terminal variant of OpenCode. If you are looking for guidance on setting up the terminal version of OpenCode, see [[AI on Demand: Configure OpenCode Desktop]]

The following steps describe how to create a basic OpenCode setup using models provided by stepping stone AG, and some good first steps to control and extend the agents capabilities.

{{Note|title=⚠️ Warning|content=Remember that agents such as OpenCode can autonomously perform actions on the system they run, such as reading / editing files, making web requests, executing terminal commands, etc. Agents may also interpret untrusted inputs such as skills or AGENTS.md files as instructions. Consider carefully which actions an agent should be allowed to execute, and whether a container or VM solution may be appropriate to prevent your agent from accessing sensitive information.}}

== Prerequisites ==

* A valid [https://www.stepping-stone.ch/en/products/artificial-intelligence AI on Demand] API key.
* Network access to <code>https://llm.stoney-cloud.com/v1</code>
* The ID of the AI models you wish to use with OpenCode (e.g.
* ''Optional:'' [https://nodejs.org Node.js] 20 or newer if you intend to install opencode via npm.

== Installation ==

Use your JavaScript package manager of choice to install the terminal variant of OpenCode:

<syntaxhighlight lang="bash">
npm install -g @opencode/cli
# or
bun install -g --trust @opencode/cli
# or
brew install anomalyco/tap/opencode-v2
</syntaxhighlight>

See [https://opencode.ai/v2/docs https://opencode.ai/v2/docs] for further information on how to install OpenCode.

Verify that the installation was successful by starting OpenCode:
<syntaxhighlight lang="bash">
opencode --version
opencode
</syntaxhighlight>

<gallery mode=packed heights=200>
OpenCode TUI.png|thumb|OpenCode Terminal
</gallery>

== Configure provider and models ==

To configure stepping stone AG as your provider, you must modify your OpenCode configuration file to include the following:

<syntaxhighlight lang="json">
{
"$schema": "https://opencode.ai/config.json",
"providers": {
"stepping-stone": {
"name": "stepping stone AG",
"package": "@opencode/ai/providers/openai-compatible",
"env": ["STONEY_KEY"],
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1"
},
"models": {}
}
}
}
</syntaxhighlight>

On Linux machines, the default location of your personal configuration file is <code>~/.config/opencode/opencode.jsonc</code> or equivalent. See [https://opencode.ai/v2/docs/config/#locations https://opencode.ai/v2/docs/config/#locations] for more information on where to place the configuration file on your system.

'''Note:''' When configuring stepping stone AG as your provider as above, OpenCode expects to find your API key in an environment variable called <code>STONEY_KEY</code>. Alternatively you may add your key directly to the configuration file by removing the <code>"env": ["STONEY_KEY"],</code> line, and adding your key as follows:

<syntaxhighlight lang="json">
...
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1",
"apiKey": "YOUR API KEY GOES HERE",
},
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Your API key must be kept secret by you! Be careful where you store your key to prevent it from being stolen or abused by a third party.}}

Next, you should configure at least one model you wish to use with OpenCode. The following is a configuration for the <code>GLM-5.3-Flash</code> model provided by stepping stone AG:

<syntaxhighlight lang="json">
...
"models": {
"zai-org/GLM-5.3-Flash": {
"name": "GLM 5.3 Flash",
"limit": {
"context": 262144,
},
"cost": {
"input": 0.3,
"output": 1.5,
"cache": {
"read": 0.045,
},
},
},
}
</syntaxhighlight>

Replace <code>zai-org/GLM-5.3-Flash</code> with the ID of the particular model you wish to use, and refer to [https://www.stepping-stone.ch/en/products/artificial-intelligence https://www.stepping-stone.ch/en/products/artificial-intelligence] for pricing and context window limits. Additional model specific configuration can be added as needed. See [https://opencode.ai/v2/docs/models/ https://opencode.ai/v2/docs/models/] for further information on configuring models.

To check if your configuration is correct, restart OpenCode after changing the configuration file. If the configuration is correct, you should be able to select the newly added model hosted by stepping stone AG from the list of available models. You can open a selection of all models available to you via the shortcut <code>CTRL + X</code>, <code>m</code>. You may need to scroll to the end of the displayed list.
<gallery mode=packed heights=200>
OpenCode_TUI_Model_selection.png|Model selection menu
</gallery>

Finally, select the newly added model, then enter a first prompt to test that the model is working correctly.
<gallery mode=packed heights=200>
OpenCode_TUI_Initial_prompt.png|Enter an initial prompt
OpenCode_TUI_Initial_prompt_response.png|Check that you receive a response
</gallery>

== Useful short-cuts and menus ==

The following is a list of useful shortcuts to get started with using OpenCode:

* <code>CTRL + P</code>: Open the main menu to interact with the agent, manage sessions and MCP servers, configuration, theming, etc.
* <code>CTRL + X</code> / <code>N</code>: Open a fresh session.
* <code>CTRL + X</code> / <code>L</code>: Switch to another existing session.
* <code>CTRL + X</code> / <code>W</code>: Close the current session tab.
* <code>CTRL + X</code> / <code>M</code>: Switch the current model.
* <code>CTRL + X</code> / <code>A</code>: Switch the current agent mode.
* <code>CTRL + X</code> / <code>Q</code>: Quit OpenCode.
* <code>CTRL + C</code>: Clear prompt input field.

== Permissions ==

OpenCode provides a built in sandbox to limit what actions an agent is allowed to perform. You can configure permissions via the configuration file (there is currently no option to configure permissions via the user interface). Permissions are defined as a list of rules. For each action (e.g. read/write a file, execute a shell command, etc.), you may define a set of rules, each with a pattern determining when the rule applies, and an effect to determine if the action is allowed, denied or requires explicit approval by the user. The following shows some examples of permission rules:

<syntaxhighlight lang="json">
...
"permissions": [
{ "action": "shell", "resource": "*", "effect": "ask" },
{ "action": "shell", "resource": "git status *", "effect": "allow" },
{ "action": "shell", "resource": "git push *", "effect": "deny" },
{ "action": "skill", "resource": "*", "effect": "allow" },
{ "action": "read", "resource": "*", "effect": "allow" },
{ "action": "edit", "resource": "*.html", "effect": "allow" },
]
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Try to keep the permissions you define as restrictive as feasable. In particular, do not allow your agent to perform sensitive or dangerous actions without your explicit approval.}}

{{Note|title=⚠️ Warning|content=While OpenCode provides a sandbox controlled via permissions, you should never rely exclusively on the sandbox to ensure that your agent does not perform dangerous actions or accesses sensitive data. Always exercise good judgement when deciding what your agent should be allowed to do.}}

== Further steps ==

You now have a basic OpenCode agent setup available to you. You may further customise and extend OpenCode in a variety of ways, such as by adding skills, configuring MCP servers or OpenCode plugins.

Check [https://opencode.ai/v2/docs/ https://opencode.ai/v2/docs/] to see how you can extend your configuration file to adapt your agent to your needs.

= References =

* [https://opencode.ai/v2/docs/ OpenCode documentation]
* [https://opencode.ai/v2/docs/providers OpenCode providers guide]
* [https://opencode.ai/v2/docs/config OpenCode configuration reference] and [https://opencode.ai/config.json configuration schema]
* [https://opencode.ai/v2/docs/permissions OpenCode permissions guide]
* [https://opencode.ai/v2/docs/mcp-servers OpenCode MCP servers guide]
* [https://modelcontextprotocol.io Model Context Protocol specification]
* [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG – Artificial Intelligence]
* [[AI on Demand: Usage]]

[[Category: AI on Demand]]
[[Category: OpenCode]]

File:OpenCode TUI Initial prompt response.png

2026-11-03T14:58:10Z

Sst-pde:

File:OpenCode TUI Initial prompt.png

2026-11-03T14:56:54Z

Sst-pde:

File:OpenCode TUI Model selection.png

2026-11-03T14:54:53Z

Sst-pde:

File:OpenCode TUI.png

2026-11-03T14:52:00Z

Sst-pde: Sst-pde uploaded a new version of File:OpenCode TUI.png

OpenCode TUI adter startup

Main Page

2026-11-03T14:46:38Z

Sst-pde: /* Artificial Intelligence (AI) */

<div style="float:left; width:48%;">
== Introduction ==
Welcome to the wiki of our [https://www.openstack.org/ OpenStack] based [https://www.stoney-cloud.com/ stoney cloud] infrastructure.
This collection serves as a comprehensive resource for all aspects of our cloud environment. Here, you will find guides for managing and utilizing our stoney cloud.

== OpenStack - Getting started ==
[[Quickstart|OpenStack quick start guide]]

== OpenStack - Usage ==
[[:Category:Projects|Projects]]

[[:Category:Instances|Instances]]
* [[VM creation (Linux)]]
* [[VM creation (Windows)]]
* [[VM resize (Linux)]]
* [[VM resize (Windows)]]
* [[Flavor explanation]]
[[:Category:Volumes|Volumes]]
* [[Quota]]

[[:Category:Images|Images]]
* [[Image creation]]
[[:Category:Network|Network]]
* [[Security group rules]]
* [[IP usage]]

[[:Category:Object store|Object store]]
* [[S3 buckets]]

[[:Category:Kubernetes|Kubernetes]]
* [[Kubernetes management]]
* [[Kubernetes usage]]

[[:Category:Backup|Backup]]
* [[Kopia restore process]]
[[:Category:Troubleshooting|Troubleshooting]]
* [[PCI workaround]]
* [[Change user password]]

</div>

<div style="float:right; width:48%">

== Artificial Intelligence (AI) ==
[[AI on Demand: Usage]] (list models, show usage, ...)

[[:Category: General purpose models|General purpose models]]
* [[AI on demand: apertus-ai/Apertus-v1.5-8B]]
* [[AI on demand: deepseek-ai/DeepSeek-V4-Flash-0731]]
* [[AI on demand: google/gemma-4-31B-it]]
* [[AI on demand: MiniMaxAI/MiniMax-M2.5]]
* [[AI on demand: NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B]]
* [[AI on demand: openai/gpt-oss-120b]]
* [[AI on demand: opendatalab/MinerU2.5-2509-1.2B]]
* [[AI on demand: Qwen/Qwen3-Coder-Next]]
* [[AI on demand: Qwen/Qwen3.5-35B-A3B-FP8]]
* [[AI on demand: Qwen/Qwen3.8-27B]]
* [[AI on demand: zai-org/GLM-5.3-Flash]]

[[:Category: OCR models|OCR models]]
* [[AI on demand: allenai/olmOCR-2-7B]]
* [[AI on demand: lightonai/LightOnOCR-2-1B]]

[[:Category: Text to Image models|Text to Image models]]
* [[AI on demand: black-forest-labs/FLUX.1-schnell]]

[[:Category: Audio models|Audio models]]
* [[AI on demand: mistralai/Voxtral-Mini-3B-2507]]
* [[AI on demand: openai/whisper-large-v3]]

[[:Category: Embedding models|Embedding models]]
* [[AI on demand: BAAI/bge-m3]]

[[:Category: Reranking models|Reranking models]]
* [[AI on demand: BAAI/bge-reranker-v2-m3]]

[[:Category: System One decision models|System One decision models]]
* [[AI on demand: convaiinnovations/laya]]
* [[AI on demand: jaredpalmer/kev-27b]]
* [[AI on demand: Mapika/decider-31b]]

[[:Category: OpenCode]]
* [[AI on demand: Configuring OpenCode Desktop]]

== Quick links ==
* [https://www.stoney-cloud.com/ stoney cloud Website]
* [https://dashboard.stoney-cloud.com/ stoney cloud Dashboard]
* [https://docs.openstack.org/horizon/latest/user/index.html Official OpenStack Dashboard Documentation]
* [https://docs.openstack.org/python-openstackclient/latest/cli/index.html Official OpenStack CLI Documentation]
</div>

<div style="clear:both; height:0px; line-height:0px;"></div>

__NOTOC__

AI on Demand: Configuring OpenCode Desktop

2026-11-03T14:46:12Z

Sst-pde: Sst-pde moved page AI on Demand: Configuring OpenCode Desktop to AI on demand: Configuring OpenCode Desktop

#REDIRECT [[AI on demand: Configuring OpenCode Desktop]]

AI on demand: Configuring OpenCode Desktop

2026-11-03T14:46:12Z

Sst-pde: Sst-pde moved page AI on Demand: Configuring OpenCode Desktop to AI on demand: Configuring OpenCode Desktop

== Overview ==

[https://opencode.ai OpenCode] is an open-source AI coding agent, available as a desktop application, in the browser or via the terminal. It supports tool calls, MCP servers, skills, plugins, etc. for software development workflows. OpenCode can be configured to exclusively use AI models hosted by [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG] via its OpenAI-compatible API.

'''Note:''' This guide walks through configuring the desktop variant of OpenCode. If you are looking for guidance on setting up the terminal version of OpenCode, see [[AI on Demand: Configure OpenCode Terminal]]

The following steps describe how to create a basic OpenCode setup using models provided by stepping stone AG, and some good first steps to control and extend the agents capabilities.

{{Note|title=⚠️ Warning|content=Remember that agents such as OpenCode can autonomously perform actions on the system they run, such as reading / editing files, making web requests, executing terminal commands, etc. Agents may also interpret untrusted inputs such as skills or AGENTS.md files as instructions. Consider carefully which actions an agent should be allowed to execute, and whether a container or VM solution may be appropriate to prevent your agent from accessing sensitive information.}}

== Prerequisites ==

* A valid [https://www.stepping-stone.ch/en/products/artificial-intelligence AI on Demand] API key.
* Network access to <code>https://llm.stoney-cloud.com/v1</code>
* The ID of the AI models you wish to use with OpenCode (e.g.
* ''Optional:'' [https://nodejs.org Node.js] 20 or newer if you intend to install opencode via npm.

== Installation ==

Download and install the [https://opencode.ai/v2/docs#desktop binary / package] appropriate for your system.

Once complete, open the OpenCode desktop app to verify that the installation was successful

<gallery mode=packed heights=200px>
OpenCode Desktop homepage.png|OpenCode Desktop
</gallery>

== Configure provider and models ==

OpenCode desktop currently does not support adding custom model providers directly from its user interface. You will need to configure stepping stone AG as your provider by modifying your OpenCode configuration file to include the following:

<syntaxhighlight lang="json">
{
"$schema": "https://opencode.ai/config.json",
"providers": {
"stepping-stone": {
"name": "stepping stone AG",
"package": "@opencode/ai/providers/openai-compatible",
"env": ["STONEY_KEY"],
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1"
},
"models": {}
}
}
}
</syntaxhighlight>

On Linux machines, the default location of your personal configuration file is <code>~/.config/opencode/opencode.jsonc</code> or equivalent. See [https://opencode.ai/v2/docs/config/#locations https://opencode.ai/v2/docs/config/#locations] for more information on where to place the configuration file on your system.

'''Note:''' When configuring stepping stone AG as your provider as above, OpenCode expects to find your API key in an environment variable called <code>STONEY_KEY</code>. Alternatively you may add your key directly to the configuration file by removing the <code>"env": ["STONEY_KEY"],</code> line, and adding your key as follows:

<syntaxhighlight lang="json">
...
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1",
"apiKey": "YOUR API KEY GOES HERE",
},
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Your API key must be kept secret by you! Be careful where you store your key to prevent it from being stolen or abused by a third party.}}

Next, you should configure at least one model you wish to use with OpenCode. The following is a configuration for the <code>GLM-5.3-Flash</code> model provided by stepping stone AG:

<syntaxhighlight lang="json">
...
"models": {
"zai-org/GLM-5.3-Flash": {
"name": "GLM 5.3 Flash",
"limit": {
"context": 262144,
},
"cost": {
"input": 0.3,
"output": 1.5,
"cache": {
"read": 0.045,
},
},
},
}
</syntaxhighlight>

Replace <code>zai-org/GLM-5.3-Flash</code> with the ID of the particular model you wish to use, and refer to [https://www.stepping-stone.ch/en/products/artificial-intelligence https://www.stepping-stone.ch/en/products/artificial-intelligence] for pricing and context window limits. Additional model specific configuration can be added as needed. See [https://opencode.ai/v2/docs/models/ https://opencode.ai/v2/docs/models/] for further information on configuring models.

To check if your configuration is correct, restart OpenCode after changing the configuration file. If the configuration is correct, stepping stone AG should appear as a configured provider, and your selected model in the available models list.

<gallery mode=packed heights=200>
OpenCode_Home_button.png|1. Open home page
OpenCode_settings_menu.png|2. Open settings menu
OpenCode_Desktop_Stepping_Stone_Provider.png|3. Check that stepping stone AG appears as a provider
OpenCode_Desktop_Stepping_Stone_Model.png|4. Check that your selected model appears at the bottom of the list
</gallery>

Finally, start a new session, select the model you have just configured and enter a first prompt to test that the model is working correctly.

<gallery mode=packed heights=200>
OpenCode_Desktop_Stepping_Stone_Model_selected.png|1. Start a new session and select a stepping stone AG provided model
OpenCode_Desktop_First_Prompt.png|2. Enter a first prompt to check that the configuration works
</gallery>

== Configure appearance and notifications ==

You may customise the appearance and layout of the UI, notification settings, shortcuts and more via the settings menu.

<gallery mode=packed heights=200>
OpenCode_Desktop_settings.png|Available settings submenus
</gallery>

== Permissions ==

OpenCode provides a built in sandbox to limit what actions an agent is allowed to perform. You can configure permissions via the configuration file (there is currently no option to configure permissions via the user interface). Permissions are defined as a list of rules. For each action (e.g. read/write a file, execute a shell command, etc.), you may define a set of rules, each with a pattern determining when the rule applies, and an effect to determine if the action is allowed, denied or requires explicit approval by the user. The following shows some examples of permission rules:

<syntaxhighlight lang="json">
...
"permissions": [
{ "action": "shell", "resource": "*", "effect": "ask" },
{ "action": "shell", "resource": "git status *", "effect": "allow" },
{ "action": "shell", "resource": "git push *", "effect": "deny" },
{ "action": "skill", "resource": "*", "effect": "allow" },
{ "action": "read", "resource": "*", "effect": "allow" },
{ "action": "edit", "resource": "*.html", "effect": "allow" },
]
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Try to keep the permissions you define as restrictive as feasable. In particular, do not allow your agent to perform sensitive or dangerous actions without your explicit approval.}}

{{Note|title=⚠️ Warning|content=While OpenCode provides a sandbox controlled via permissions, you should never rely exclusively on the sandbox to ensure that your agent does not perform dangerous actions or accesses sensitive data. Always exercise good judgement when deciding what your agent should be allowed to do.}}

== Further steps ==

You now have a basic OpenCode agent setup available to you. You may further customise and extend OpenCode in a variety of ways, such as by adding skills, configuring MCP servers or OpenCode plugins.

Check [https://opencode.ai/v2/docs/ https://opencode.ai/v2/docs/] or the settings menu of OpenCode to see how you can extend your agent to your needs.

= References =

* [https://opencode.ai/v2/docs/ OpenCode documentation]
* [https://opencode.ai/v2/docs/providers OpenCode providers guide]
* [https://opencode.ai/v2/docs/config OpenCode configuration reference] and [https://opencode.ai/config.json configuration schema]
* [https://opencode.ai/v2/docs/permissions OpenCode permissions guide]
* [https://opencode.ai/v2/docs/mcp-servers OpenCode MCP servers guide]
* [https://modelcontextprotocol.io Model Context Protocol specification]
* [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG – Artificial Intelligence]
* [[AI on Demand: Usage]]

[[Category: AI on Demand]]
[[Category: OpenCode]]

AI on demand: Configuring OpenCode Desktop

2026-11-03T14:45:03Z

Sst-pde:

== Overview ==

[https://opencode.ai OpenCode] is an open-source AI coding agent, available as a desktop application, in the browser or via the terminal. It supports tool calls, MCP servers, skills, plugins, etc. for software development workflows. OpenCode can be configured to exclusively use AI models hosted by [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG] via its OpenAI-compatible API.

'''Note:''' This guide walks through configuring the desktop variant of OpenCode. If you are looking for guidance on setting up the terminal version of OpenCode, see [[AI on Demand: Configure OpenCode Terminal]]

The following steps describe how to create a basic OpenCode setup using models provided by stepping stone AG, and some good first steps to control and extend the agents capabilities.

{{Note|title=⚠️ Warning|content=Remember that agents such as OpenCode can autonomously perform actions on the system they run, such as reading / editing files, making web requests, executing terminal commands, etc. Agents may also interpret untrusted inputs such as skills or AGENTS.md files as instructions. Consider carefully which actions an agent should be allowed to execute, and whether a container or VM solution may be appropriate to prevent your agent from accessing sensitive information.}}

== Prerequisites ==

* A valid [https://www.stepping-stone.ch/en/products/artificial-intelligence AI on Demand] API key.
* Network access to <code>https://llm.stoney-cloud.com/v1</code>
* The ID of the AI models you wish to use with OpenCode (e.g.
* ''Optional:'' [https://nodejs.org Node.js] 20 or newer if you intend to install opencode via npm.

== Installation ==

Download and install the [https://opencode.ai/v2/docs#desktop binary / package] appropriate for your system.

Once complete, open the OpenCode desktop app to verify that the installation was successful

<gallery mode=packed heights=200px>
OpenCode Desktop homepage.png|OpenCode Desktop
</gallery>

== Configure provider and models ==

OpenCode desktop currently does not support adding custom model providers directly from its user interface. You will need to configure stepping stone AG as your provider by modifying your OpenCode configuration file to include the following:

<syntaxhighlight lang="json">
{
"$schema": "https://opencode.ai/config.json",
"providers": {
"stepping-stone": {
"name": "stepping stone AG",
"package": "@opencode/ai/providers/openai-compatible",
"env": ["STONEY_KEY"],
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1"
},
"models": {}
}
}
}
</syntaxhighlight>

On Linux machines, the default location of your personal configuration file is <code>~/.config/opencode/opencode.jsonc</code> or equivalent. See [https://opencode.ai/v2/docs/config/#locations https://opencode.ai/v2/docs/config/#locations] for more information on where to place the configuration file on your system.

'''Note:''' When configuring stepping stone AG as your provider as above, OpenCode expects to find your API key in an environment variable called <code>STONEY_KEY</code>. Alternatively you may add your key directly to the configuration file by removing the <code>"env": ["STONEY_KEY"],</code> line, and adding your key as follows:

<syntaxhighlight lang="json">
...
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1",
"apiKey": "YOUR API KEY GOES HERE",
},
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Your API key must be kept secret by you! Be careful where you store your key to prevent it from being stolen or abused by a third party.}}

Next, you should configure at least one model you wish to use with OpenCode. The following is a configuration for the <code>GLM-5.3-Flash</code> model provided by stepping stone AG:

<syntaxhighlight lang="json">
...
"models": {
"zai-org/GLM-5.3-Flash": {
"name": "GLM 5.3 Flash",
"limit": {
"context": 262144,
},
"cost": {
"input": 0.3,
"output": 1.5,
"cache": {
"read": 0.045,
},
},
},
}
</syntaxhighlight>

Replace <code>zai-org/GLM-5.3-Flash</code> with the ID of the particular model you wish to use, and refer to [https://www.stepping-stone.ch/en/products/artificial-intelligence https://www.stepping-stone.ch/en/products/artificial-intelligence] for pricing and context window limits. Additional model specific configuration can be added as needed. See [https://opencode.ai/v2/docs/models/ https://opencode.ai/v2/docs/models/] for further information on configuring models.

To check if your configuration is correct, restart OpenCode after changing the configuration file. If the configuration is correct, stepping stone AG should appear as a configured provider, and your selected model in the available models list.

<gallery mode=packed heights=200>
OpenCode_Home_button.png|1. Open home page
OpenCode_settings_menu.png|2. Open settings menu
OpenCode_Desktop_Stepping_Stone_Provider.png|3. Check that stepping stone AG appears as a provider
OpenCode_Desktop_Stepping_Stone_Model.png|4. Check that your selected model appears at the bottom of the list
</gallery>

Finally, start a new session, select the model you have just configured and enter a first prompt to test that the model is working correctly.

<gallery mode=packed heights=200>
OpenCode_Desktop_Stepping_Stone_Model_selected.png|1. Start a new session and select a stepping stone AG provided model
OpenCode_Desktop_First_Prompt.png|2. Enter a first prompt to check that the configuration works
</gallery>

== Configure appearance and notifications ==

You may customise the appearance and layout of the UI, notification settings, shortcuts and more via the settings menu.

<gallery mode=packed heights=200>
OpenCode_Desktop_settings.png|Available settings submenus
</gallery>

== Permissions ==

OpenCode provides a built in sandbox to limit what actions an agent is allowed to perform. You can configure permissions via the configuration file (there is currently no option to configure permissions via the user interface). Permissions are defined as a list of rules. For each action (e.g. read/write a file, execute a shell command, etc.), you may define a set of rules, each with a pattern determining when the rule applies, and an effect to determine if the action is allowed, denied or requires explicit approval by the user. The following shows some examples of permission rules:

<syntaxhighlight lang="json">
...
"permissions": [
{ "action": "shell", "resource": "*", "effect": "ask" },
{ "action": "shell", "resource": "git status *", "effect": "allow" },
{ "action": "shell", "resource": "git push *", "effect": "deny" },
{ "action": "skill", "resource": "*", "effect": "allow" },
{ "action": "read", "resource": "*", "effect": "allow" },
{ "action": "edit", "resource": "*.html", "effect": "allow" },
]
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Try to keep the permissions you define as restrictive as feasable. In particular, do not allow your agent to perform sensitive or dangerous actions without your explicit approval.}}

{{Note|title=⚠️ Warning|content=While OpenCode provides a sandbox controlled via permissions, you should never rely exclusively on the sandbox to ensure that your agent does not perform dangerous actions or accesses sensitive data. Always exercise good judgement when deciding what your agent should be allowed to do.}}

== Further steps ==

You now have a basic OpenCode agent setup available to you. You may further customise and extend OpenCode in a variety of ways, such as by adding skills, configuring MCP servers or OpenCode plugins.

Check [https://opencode.ai/v2/docs/ https://opencode.ai/v2/docs/] or the settings menu of OpenCode to see how you can extend your agent to your needs.

= References =

* [https://opencode.ai/v2/docs/ OpenCode documentation]
* [https://opencode.ai/v2/docs/providers OpenCode providers guide]
* [https://opencode.ai/v2/docs/config OpenCode configuration reference] and [https://opencode.ai/config.json configuration schema]
* [https://opencode.ai/v2/docs/permissions OpenCode permissions guide]
* [https://opencode.ai/v2/docs/mcp-servers OpenCode MCP servers guide]
* [https://modelcontextprotocol.io Model Context Protocol specification]
* [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG – Artificial Intelligence]
* [[AI on Demand: Usage]]

[[Category: AI on Demand]]
[[Category: OpenCode]]

Category:OpenCode

2026-11-03T14:44:39Z

Sst-pde: Created page with "Category: AI on Demand"

[[Category: AI on Demand]]

AI on Demand: Configuring OpenCode

2026-11-03T14:43:52Z

Sst-pde: Sst-pde moved page AI on Demand: Configuring OpenCode to AI on Demand: Configuring OpenCode Desktop

#REDIRECT [[AI on Demand: Configuring OpenCode Desktop]]

AI on demand: Configuring OpenCode Desktop

2026-11-03T14:43:52Z

Sst-pde: Sst-pde moved page AI on Demand: Configuring OpenCode to AI on Demand: Configuring OpenCode Desktop

== Overview ==

[https://opencode.ai OpenCode] is an open-source AI coding agent, available as a desktop application, in the browser or via the terminal. It supports tool calls, MCP servers, skills, plugins, etc. for software development workflows. OpenCode can be configured to exclusively use AI models hosted by [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG] via its OpenAI-compatible API.

'''Note:''' This guide walks through configuring the desktop variant of OpenCode. If you are looking for guidance on setting up the terminal version of OpenCode, see [[AI on Demand: Configure OpenCode Terminal]]

The following steps describe how to create a basic OpenCode setup using models provided by stepping stone AG, and some good first steps to control and extend the agents capabilities.

{{Note|title=⚠️ Warning|content=Remember that agents such as OpenCode can autonomously perform actions on the system they run, such as reading / editing files, making web requests, executing terminal commands, etc. Agents may also interpret untrusted inputs such as skills or AGENTS.md files as instructions. Consider carefully which actions an agent should be allowed to execute, and whether a container or VM solution may be appropriate to prevent your agent from accessing sensitive information.}}

== Prerequisites ==

* A valid [https://www.stepping-stone.ch/en/products/artificial-intelligence AI on Demand] API key.
* Network access to <code>https://llm.stoney-cloud.com/v1</code>
* The ID of the AI models you wish to use with OpenCode (e.g.
* ''Optional:'' [https://nodejs.org Node.js] 20 or newer if you intend to install opencode via npm.

== Installation ==

Download and install the [https://opencode.ai/v2/docs#desktop binary / package] appropriate for your system.

Once complete, open the OpenCode desktop app to verify that the installation was successful

<gallery mode=packed heights=200px>
OpenCode Desktop homepage.png|OpenCode Desktop
</gallery>

== Configure provider and models ==

OpenCode desktop currently does not support adding custom model providers directly from its user interface. You will need to configure stepping stone AG as your provider by modifying your OpenCode configuration file to include the following:

<syntaxhighlight lang="json">
{
"$schema": "https://opencode.ai/config.json",
"providers": {
"stepping-stone": {
"name": "stepping stone AG",
"package": "@opencode/ai/providers/openai-compatible",
"env": ["STONEY_KEY"],
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1"
},
"models": {}
}
}
}
</syntaxhighlight>

On Linux machines, the default location of your personal configuration file is <code>~/.config/opencode/opencode.jsonc</code> or equivalent. See [https://opencode.ai/v2/docs/config/#locations https://opencode.ai/v2/docs/config/#locations] for more information on where to place the configuration file on your system.

'''Note:''' When configuring stepping stone AG as your provider as above, OpenCode expects to find your API key in an environment variable called <code>STONEY_KEY</code>. Alternatively you may add your key directly to the configuration file by removing the <code>"env": ["STONEY_KEY"],</code> line, and adding your key as follows:

<syntaxhighlight lang="json">
...
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1",
"apiKey": "YOUR API KEY GOES HERE",
},
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Your API key must be kept secret by you! Be careful where you store your key to prevent it from being stolen or abused by a third party.}}

Next, you should configure at least one model you wish to use with OpenCode. The following is a configuration for the <code>GLM-5.3-Flash</code> model provided by stepping stone AG:

<syntaxhighlight lang="json">
...
"models": {
"zai-org/GLM-5.3-Flash": {
"name": "GLM 5.3 Flash",
"limit": {
"context": 262144,
},
"cost": {
"input": 0.3,
"output": 1.5,
"cache": {
"read": 0.045,
},
},
},
}
</syntaxhighlight>

Replace <code>zai-org/GLM-5.3-Flash</code> with the ID of the particular model you wish to use, and refer to [https://www.stepping-stone.ch/en/products/artificial-intelligence https://www.stepping-stone.ch/en/products/artificial-intelligence] for pricing and context window limits. Additional model specific configuration can be added as needed. See [https://opencode.ai/v2/docs/models/ https://opencode.ai/v2/docs/models/] for further information on configuring models.

To check if your configuration is correct, restart OpenCode after changing the configuration file. If the configuration is correct, stepping stone AG should appear as a configured provider, and your selected model in the available models list.

<gallery mode=packed heights=200>
OpenCode_Home_button.png|1. Open home page
OpenCode_settings_menu.png|2. Open settings menu
OpenCode_Desktop_Stepping_Stone_Provider.png|3. Check that stepping stone AG appears as a provider
OpenCode_Desktop_Stepping_Stone_Model.png|4. Check that your selected model appears at the bottom of the list
</gallery>

Finally, start a new session, select the model you have just configured and enter a first prompt to test that the model is working correctly.

<gallery mode=packed heights=200>
OpenCode_Desktop_Stepping_Stone_Model_selected.png|1. Start a new session and select a stepping stone AG provided model
OpenCode_Desktop_First_Prompt.png|2. Enter a first prompt to check that the configuration works
</gallery>

== Configure appearance and notifications ==

You may customise the appearance and layout of the UI, notification settings, shortcuts and more via the settings menu.

<gallery mode=packed heights=200>
OpenCode_Desktop_settings.png|Available settings submenus
</gallery>

== Permissions ==

OpenCode provides a built in sandbox to limit what actions an agent is allowed to perform. You can configure permissions via the configuration file (there is currently no option to configure permissions via the user interface). Permissions are defined as a list of rules. For each action (e.g. read/write a file, execute a shell command, etc.), you may define a set of rules, each with a pattern determining when the rule applies, and an effect to determine if the action is allowed, denied or requires explicit approval by the user. The following shows some examples of permission rules:

<syntaxhighlight lang="json">
...
"permissions": [
{ "action": "shell", "resource": "*", "effect": "ask" },
{ "action": "shell", "resource": "git status *", "effect": "allow" },
{ "action": "shell", "resource": "git push *", "effect": "deny" },
{ "action": "skill", "resource": "*", "effect": "allow" },
{ "action": "read", "resource": "*", "effect": "allow" },
{ "action": "edit", "resource": "*.html", "effect": "allow" },
]
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Try to keep the permissions you define as restrictive as feasable. In particular, do not allow your agent to perform sensitive or dangerous actions without your explicit approval.}}

{{Note|title=⚠️ Warning|content=While OpenCode provides a sandbox controlled via permissions, you should never rely exclusively on the sandbox to ensure that your agent does not perform dangerous actions or accesses sensitive data. Always exercise good judgement when deciding what your agent should be allowed to do.}}

== Further steps ==

You now have a basic OpenCode agent setup available to you. You may further customise and extend OpenCode in a variety of ways, such as by adding skills, configuring MCP servers or OpenCode plugins.

Check [https://opencode.ai/v2/docs/ https://opencode.ai/v2/docs/] or the settings menu of OpenCode to see how you can extend your agent to your needs.

= References =

* [https://opencode.ai/v2/docs/ OpenCode documentation]
* [https://opencode.ai/v2/docs/providers OpenCode providers guide]
* [https://opencode.ai/v2/docs/config OpenCode configuration reference] and [https://opencode.ai/config.json configuration schema]
* [https://opencode.ai/v2/docs/permissions OpenCode permissions guide]
* [https://opencode.ai/v2/docs/mcp-servers OpenCode MCP servers guide]
* [https://modelcontextprotocol.io Model Context Protocol specification]
* [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG – Artificial Intelligence]
* [[AI on Demand: Usage]]

[[Category: AI on Demand]]

AI on demand: Configuring OpenCode Desktop

2026-11-03T14:43:44Z

== Overview ==

[https://opencode.ai OpenCode] is an open-source AI coding agent, available as a desktop application, in the browser or via the terminal. It supports tool calls, MCP servers, skills, plugins, etc. for software development workflows. OpenCode can be configured to exclusively use AI models hosted by [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG] via its OpenAI-compatible API.

'''Note:''' This guide walks through configuring the desktop variant of OpenCode. If you are looking for guidance on setting up the terminal version of OpenCode, see [[AI on Demand: Configure OpenCode Terminal]]

The following steps describe how to create a basic OpenCode setup using models provided by stepping stone AG, and some good first steps to control and extend the agents capabilities.

{{Note|title=⚠️ Warning|content=Remember that agents such as OpenCode can autonomously perform actions on the system they run, such as reading / editing files, making web requests, executing terminal commands, etc. Agents may also interpret untrusted inputs such as skills or AGENTS.md files as instructions. Consider carefully which actions an agent should be allowed to execute, and whether a container or VM solution may be appropriate to prevent your agent from accessing sensitive information.}}

== Prerequisites ==

* A valid [https://www.stepping-stone.ch/en/products/artificial-intelligence AI on Demand] API key.
* Network access to <code>https://llm.stoney-cloud.com/v1</code>
* The ID of the AI models you wish to use with OpenCode (e.g.
* ''Optional:'' [https://nodejs.org Node.js] 20 or newer if you intend to install opencode via npm.

== Installation ==

Download and install the [https://opencode.ai/v2/docs#desktop binary / package] appropriate for your system.

Once complete, open the OpenCode desktop app to verify that the installation was successful

<gallery mode=packed heights=200px>
OpenCode Desktop homepage.png|OpenCode Desktop
</gallery>

== Configure provider and models ==

OpenCode desktop currently does not support adding custom model providers directly from its user interface. You will need to configure stepping stone AG as your provider by modifying your OpenCode configuration file to include the following:

<syntaxhighlight lang="json">
{
"$schema": "https://opencode.ai/config.json",
"providers": {
"stepping-stone": {
"name": "stepping stone AG",
"package": "@opencode/ai/providers/openai-compatible",
"env": ["STONEY_KEY"],
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1"
},
"models": {}
}
}
}
</syntaxhighlight>

On Linux machines, the default location of your personal configuration file is <code>~/.config/opencode/opencode.jsonc</code> or equivalent. See [https://opencode.ai/v2/docs/config/#locations https://opencode.ai/v2/docs/config/#locations] for more information on where to place the configuration file on your system.

'''Note:''' When configuring stepping stone AG as your provider as above, OpenCode expects to find your API key in an environment variable called <code>STONEY_KEY</code>. Alternatively you may add your key directly to the configuration file by removing the <code>"env": ["STONEY_KEY"],</code> line, and adding your key as follows:

<syntaxhighlight lang="json">
...
"settings": {
"baseURL": "https://llm.stoney-cloud.com/v1",
"apiKey": "YOUR API KEY GOES HERE",
},
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Your API key must be kept secret by you! Be careful where you store your key to prevent it from being stolen or abused by a third party.}}

Next, you should configure at least one model you wish to use with OpenCode. The following is a configuration for the <code>GLM-5.3-Flash</code> model provided by stepping stone AG:

<syntaxhighlight lang="json">
...
"models": {
"zai-org/GLM-5.3-Flash": {
"name": "GLM 5.3 Flash",
"limit": {
"context": 262144,
},
"cost": {
"input": 0.3,
"output": 1.5,
"cache": {
"read": 0.045,
},
},
},
}
</syntaxhighlight>

Replace <code>zai-org/GLM-5.3-Flash</code> with the ID of the particular model you wish to use, and refer to [https://www.stepping-stone.ch/en/products/artificial-intelligence https://www.stepping-stone.ch/en/products/artificial-intelligence] for pricing and context window limits. Additional model specific configuration can be added as needed. See [https://opencode.ai/v2/docs/models/ https://opencode.ai/v2/docs/models/] for further information on configuring models.

To check if your configuration is correct, restart OpenCode after changing the configuration file. If the configuration is correct, stepping stone AG should appear as a configured provider, and your selected model in the available models list.

<gallery mode=packed heights=200>
OpenCode_Home_button.png|1. Open home page
OpenCode_settings_menu.png|2. Open settings menu
OpenCode_Desktop_Stepping_Stone_Provider.png|3. Check that stepping stone AG appears as a provider
OpenCode_Desktop_Stepping_Stone_Model.png|4. Check that your selected model appears at the bottom of the list
</gallery>

Finally, start a new session, select the model you have just configured and enter a first prompt to test that the model is working correctly.

<gallery mode=packed heights=200>
OpenCode_Desktop_Stepping_Stone_Model_selected.png|1. Start a new session and select a stepping stone AG provided model
OpenCode_Desktop_First_Prompt.png|2. Enter a first prompt to check that the configuration works
</gallery>

== Configure appearance and notifications ==

You may customise the appearance and layout of the UI, notification settings, shortcuts and more via the settings menu.

<gallery mode=packed heights=200>
OpenCode_Desktop_settings.png|Available settings submenus
</gallery>

== Permissions ==

OpenCode provides a built in sandbox to limit what actions an agent is allowed to perform. You can configure permissions via the configuration file (there is currently no option to configure permissions via the user interface). Permissions are defined as a list of rules. For each action (e.g. read/write a file, execute a shell command, etc.), you may define a set of rules, each with a pattern determining when the rule applies, and an effect to determine if the action is allowed, denied or requires explicit approval by the user. The following shows some examples of permission rules:

<syntaxhighlight lang="json">
...
"permissions": [
{ "action": "shell", "resource": "*", "effect": "ask" },
{ "action": "shell", "resource": "git status *", "effect": "allow" },
{ "action": "shell", "resource": "git push *", "effect": "deny" },
{ "action": "skill", "resource": "*", "effect": "allow" },
{ "action": "read", "resource": "*", "effect": "allow" },
{ "action": "edit", "resource": "*.html", "effect": "allow" },
]
...
</syntaxhighlight>

{{Note|title=⚠️ Warning|content=Try to keep the permissions you define as restrictive as feasable. In particular, do not allow your agent to perform sensitive or dangerous actions without your explicit approval.}}

{{Note|title=⚠️ Warning|content=While OpenCode provides a sandbox controlled via permissions, you should never rely exclusively on the sandbox to ensure that your agent does not perform dangerous actions or accesses sensitive data. Always exercise good judgement when deciding what your agent should be allowed to do.}}

== Further steps ==

You now have a basic OpenCode agent setup available to you. You may further customise and extend OpenCode in a variety of ways, such as by adding skills, configuring MCP servers or OpenCode plugins.

Check [https://opencode.ai/v2/docs/ https://opencode.ai/v2/docs/] or the settings menu of OpenCode to see how you can extend your agent to your needs.

= References =

* [https://opencode.ai/v2/docs/ OpenCode documentation]
* [https://opencode.ai/v2/docs/providers OpenCode providers guide]
* [https://opencode.ai/v2/docs/config OpenCode configuration reference] and [https://opencode.ai/config.json configuration schema]
* [https://opencode.ai/v2/docs/permissions OpenCode permissions guide]
* [https://opencode.ai/v2/docs/mcp-servers OpenCode MCP servers guide]
* [https://modelcontextprotocol.io Model Context Protocol specification]
* [https://www.stepping-stone.ch/en/products/artificial-intelligence stepping stone AG – Artificial Intelligence]
* [[AI on Demand: Usage]]

[[Category: AI on Demand]]

File:OpenCode Desktop settings.png

2026-11-03T14:22:26Z

Sst-pde:

File:OpenCode Desktop First Prompt.png

2026-11-03T14:19:37Z

Sst-pde:

File:OpenCode Desktop Stepping Stone Model selected.png

2026-11-03T14:17:52Z

Sst-pde:

File:OpenCode Desktop Stepping Stone Model.png

2026-11-03T14:11:09Z

Sst-pde:

File:OpenCode Desktop Stepping Stone Provider.png

2026-11-03T14:10:16Z

Sst-pde:

File:OpenCode settings menu.png

2026-11-03T12:04:17Z

Sst-pde: Sst-pde uploaded a new version of File:OpenCode settings menu.png

OpenCode settings menu location highlighted

File:OpenCode Home button.png

2026-11-03T12:03:03Z

Sst-pde: Sst-pde uploaded a new version of File:OpenCode Home button.png

OpenCode Home button location highlighted

File:OpenCode custom provider.png

2026-11-03T10:42:29Z

Sst-pde:

OpenCode custom provider location highlighted

File:OpenCode settings menu.png

2026-11-03T10:41:42Z

Sst-pde:

OpenCode settings menu location highlighted

File:OpenCode Home button.png

2026-11-03T10:34:56Z

Sst-pde:

OpenCode Home button location highlighted

File:OpenCode TUI.png

2026-11-03T10:22:39Z

Sst-pde:

OpenCode TUI adter startup

File:OpenCode Desktop homepage.png

2026-11-03T10:13:29Z

Sst-pde:

OpenCode Desktop window after startup