anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 02:05:26 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

Custom provider docs incorrect #3744

New Issue
Open
opened 2026-02-16 17:41:18 -05:00 by yindo · 20 comments
yindo commented 2026-02-16 17:41:18 -05:00
Owner
Copy Link
Copy Source

Originally created by @cgilly2fast on GitHub (Dec 22, 2025).

Originally assigned to: @rekram1-node on GitHub.

Description

The below is incorrect there is no other option after running /connect in opencode

[Custom provider](https://opencode.ai/docs/providers/#custom-provider)
To add any OpenAI-compatible provider that’s not listed in the /connect command:

Tip

You can use any OpenAI-compatible provider with opencode. Most modern AI providers offer OpenAI-compatible APIs.

Run the /connect command and scroll down to Other.

Terminal window
$ /connect

┌  Add credential
│
◆  Select provider
│  ...
│  ● Other
└

OpenCode version

No response

Steps to reproduce

  1. $ opencode
  2. type and run '/connect'
  3. search for "other"

Screenshot and/or share link

No response

Operating System

mac OS 15.5

Terminal

vs code terminal

Originally created by @cgilly2fast on GitHub (Dec 22, 2025). Originally assigned to: @rekram1-node on GitHub. ### Description The below is incorrect there is no other option after running `/connect ` in opencode ``` [Custom provider](https://opencode.ai/docs/providers/#custom-provider) To add any OpenAI-compatible provider that’s not listed in the /connect command: Tip You can use any OpenAI-compatible provider with opencode. Most modern AI providers offer OpenAI-compatible APIs. Run the /connect command and scroll down to Other. Terminal window $ /connect ┌ Add credential │ ◆ Select provider │ ... │ ● Other └ ```` ### OpenCode version _No response_ ### Steps to reproduce 1. $ opencode 2. type and run '/connect' 3. search for "other" ### Screenshot and/or share link _No response_ ### Operating System mac OS 15.5 ### Terminal vs code terminal
yindo added the bugdocs labels 2026-02-16 17:41:18 -05:00
yindo commented 2026-02-16 17:41:18 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Dec 22, 2025):

This issue might be a duplicate of existing issues. Please check:

  • #5250: Request to include custom providers in /provider and /connect command

Feel free to ignore if none of these address your specific case.

@github-actions[bot] commented on GitHub (Dec 22, 2025): This issue might be a duplicate of existing issues. Please check: - #5250: Request to include custom providers in /provider and /connect command Feel free to ignore if none of these address your specific case.
yindo commented 2026-02-16 17:41:18 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 22, 2025):

Oof good catch!

I can fix this, in the meantime try opencode auth login instead

@rekram1-node commented on GitHub (Dec 22, 2025): Oof good catch! I can fix this, in the meantime try `opencode auth login` instead
yindo commented 2026-02-16 17:41:18 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 23, 2025):

/oc can you fix /connect in the tui (and maybe the server too if needed so that you can connect a custom provider too)?

@rekram1-node commented on GitHub (Dec 23, 2025): /oc can you fix /connect in the tui (and maybe the server too if needed so that you can connect a custom provider too)?
yindo commented 2026-02-16 17:41:18 -05:00
Author
Owner
Copy Link
Copy Source

@opencode-agent[bot] commented on GitHub (Dec 23, 2025):

Created PR #6014

New%20session%20-%202025-12-23T06%3A11%3A49.345Z
opencode session  |  github run

@opencode-agent[bot] commented on GitHub (Dec 23, 2025): Created PR #6014 <a href="https://opencode.ai/s/xCAflZA6"><img width="200" alt="New%20session%20-%202025-12-23T06%3A11%3A49.345Z" src="https://social-cards.sst.dev/opencode-share/TmV3IHNlc3Npb24gLSAyMDI1LTEyLTIzVDA2OjExOjQ5LjM0NVo=.png?model=opencode/claude-opus-4-5&version=1.0.190&id=xCAflZA6" /></a> [opencode session](https://opencode.ai/s/xCAflZA6)&nbsp;&nbsp;|&nbsp;&nbsp;[github run](/sst/opencode/actions/runs/20453017602)
yindo commented 2026-02-16 17:41:18 -05:00
Author
Owner
Copy Link
Copy Source

@aiyinyuedejustin commented on GitHub (Jan 3, 2026):

+1

@aiyinyuedejustin commented on GitHub (Jan 3, 2026): +1
yindo commented 2026-02-16 17:41:18 -05:00
Author
Owner
Copy Link
Copy Source

@Aaalice233 commented on GitHub (Jan 6, 2026):

+1

@Aaalice233 commented on GitHub (Jan 6, 2026): +1
yindo commented 2026-02-16 17:41:18 -05:00
Author
Owner
Copy Link
Copy Source

@Aaalice233 commented on GitHub (Jan 6, 2026):

I see no reason not to add this feature. Does literally nobody need the custom options?

@Aaalice233 commented on GitHub (Jan 6, 2026): I see no reason not to add this feature. Does literally nobody need the custom options?
yindo commented 2026-02-16 17:41:18 -05:00
Author
Owner
Copy Link
Copy Source

@Zhen-Bo commented on GitHub (Jan 6, 2026):

If you want to use your own endpoint, you need to follow these steps to set it up:

First, configure your opencode.json (remember to swap the baseURL with your own):

{
  "$schema": "https://opencode.ai/config.json",
  "model": "new-api/claude-opus-4-5-20251101",
  "provider": {
    "new-api": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "new-api",
      "options": {
        "baseURL": "http://10.10.10.1:2333/v1",
        "setCacheKey": true
      },
      "models": {
        "claude-opus-4-5-20251101": {
          "name": "Claude 4.5 Opus"
        }
      }
    }
  }
}

Then use opencode auth login {provider.custom_name} (or maybe the connect command?) to cache the api-key for your custom endpoint.
If you don't want to cache it, you can set the apiKey directly inside the provider's options.
You can modify custom_name to whatever endpoint name you prefer.

Important: The top-level model field (indicated in the structure above) is crucial. If it's left blank or incorrect, your opencode will keep receiving 429 errors (I don't even know where these 429s are coming from; my custom endpoint never received those requests).

Finally, open opencode again and type /model. You should be able to see your configured endpoint and model name.

Yesterday, I spent 2 hours digging through the source code and official documentation to debug this. After finally setting it up, I entered my project and ran /init... and opencode just froze dead.

I started the init task yesterday at 22:51:24. I watched my API endpoint logs: it received a request at 22:51:24, a second one at 22:51:28, a third at 22:53:04, and a fourth at 22:53:10. Then, absolutely nothing. No further requests were sent to my endpoint up until 23:07, yet opencode still displayed that it was "running".

It wasted nearly 3 hours of my time yesterday, and I got absolutely nothing out of it.

I saw official accounts on WeChat hyping this thing to the sky, saying how "easy" it is. They even claimed you could just say "Help me install the Oh My OpenCode plugin" inside opencode and it would auto-configure everything. The result? I just got a response saying: "It seems the user has a misunderstanding; opencode is installed successfully but there is no Oh My OpenCode plugin."

Maybe the official team is afraid that once this is actually set up, coding will become a breeze. So, they intentionally set the barrier for configuring custom endpoints as high as the Himalayas, just to ensure you don't miss out on the pain of coding without AI assistance.

Btw: To be honest, this is the biggest pile of sh*t I've eaten in 2026. If I were a QA for opencode, finding such terrible UX, I would absolutely never have let this be released.

Apologies for the outburst, this is the first time I've vented like this on GitHub.
It's just frustrating to see people hyping it up as effortless, when in reality, the actual hands-on experience is incredibly difficult. Combined with the fact that I spent 3 hours—time that should have been used for something meaningful—struggling with configuration only to end up with nothing.
I know that when a product fails like this, it's not just one person's error but usually a chain of oversights, but I just can't help being angry about it.

@Zhen-Bo commented on GitHub (Jan 6, 2026): If you want to use your own endpoint, you need to follow these steps to set it up: First, configure your `opencode.json` (remember to swap the `baseURL` with your own): ```json { "$schema": "https://opencode.ai/config.json", "model": "new-api/claude-opus-4-5-20251101", "provider": { "new-api": { "npm": "@ai-sdk/openai-compatible", "name": "new-api", "options": { "baseURL": "http://10.10.10.1:2333/v1", "setCacheKey": true }, "models": { "claude-opus-4-5-20251101": { "name": "Claude 4.5 Opus" } } } } } ``` Then use `opencode auth login {provider.custom_name}` (or maybe the connect command?) to cache the api-key for your custom endpoint. If you don't want to cache it, you can set the `apiKey` directly inside the provider's `options`. You can modify `custom_name` to whatever endpoint name you prefer. **Important:** The top-level `model` field (indicated in the structure above) is crucial. If it's left blank or incorrect, your opencode will keep receiving **429 errors** (I don't even know where these 429s are coming from; my custom endpoint never received those requests). Finally, open opencode again and type `/model`. You should be able to see your configured endpoint and model name. --- Yesterday, I spent **2 hours** digging through the source code and official documentation to debug this. After finally setting it up, I entered my project and ran `/init`... and opencode just froze dead. I started the init task yesterday at 22:51:24. I watched my API endpoint logs: it received a request at 22:51:24, a second one at 22:51:28, a third at 22:53:04, and a fourth at 22:53:10. Then, absolutely nothing. No further requests were sent to my endpoint up until 23:07, yet opencode still displayed that it was "running". It wasted nearly 3 hours of my time yesterday, and I got absolutely nothing out of it. I saw official accounts on WeChat hyping this thing to the sky, saying how "easy" it is. They even claimed you could just say "Help me install the Oh My OpenCode plugin" inside opencode and it would auto-configure everything. The result? I just got a response saying: *"It seems the user has a misunderstanding; opencode is installed successfully but there is no Oh My OpenCode plugin."* Maybe the official team is afraid that once this is actually set up, coding will become a breeze. So, they intentionally set the barrier for configuring custom endpoints as high as the Himalayas, just to ensure you don't miss out on the pain of coding without AI assistance. **Btw:** To be honest, this is the biggest pile of sh*t I've eaten in 2026. If I were a QA for opencode, finding such terrible UX, I would absolutely **never** have let this be released. --- Apologies for the outburst, this is the first time I've vented like this on GitHub. It's just frustrating to see people hyping it up as effortless, when in reality, the actual hands-on experience is incredibly difficult. Combined with the fact that I spent 3 hours—time that should have been used for something meaningful—struggling with configuration only to end up with nothing. I know that when a product fails like this, it's not just one person's error but usually a chain of oversights, but I just can't help being angry about it.
yindo commented 2026-02-16 17:41:18 -05:00
Author
Owner
Copy Link
Copy Source

@mudssky commented on GitHub (Jan 7, 2026):

opencode web cannot select custom providers

@mudssky commented on GitHub (Jan 7, 2026): opencode web cannot select custom providers
yindo commented 2026-02-16 17:41:19 -05:00
Author
Owner
Copy Link
Copy Source

@RomainTFasst commented on GitHub (Jan 12, 2026):

Thanks @Zhen-Bo for describing your method for creating custom endpoints here! I just spent two hours trying to get it to work. Why isn't it better documented?

@RomainTFasst commented on GitHub (Jan 12, 2026): Thanks @Zhen-Bo for describing your method for creating custom endpoints here! I just spent two hours trying to get it to work. Why isn't it better documented?
yindo commented 2026-02-16 17:41:19 -05:00
Author
Owner
Copy Link
Copy Source

@Mte90 commented on GitHub (Jan 13, 2026):

any updates for this?

I am not using opencode because is not clear how to use a custom provider

@Mte90 commented on GitHub (Jan 13, 2026): any updates for this? I am not using opencode because is not clear how to use a custom provider
yindo commented 2026-02-16 17:41:19 -05:00
Author
Owner
Copy Link
Copy Source

@intentionally-left-nil commented on GitHub (Jan 15, 2026):

The CLI also needs work. When you type opencode auth this is presented, but if you actually enter a URL you get an error:

opencode auth
  opencode auth login [url]  log in to a provider

opencode auth login REDACTED_URL
┌  Add credential
Error: Unexpected error, check log file at REDACTED for more details

undefined is not an object (evaluating 'wellknown.auth.command')
❯ tail ~/.local/share/opencode/log/2026-01-16T041006.log
INFO  2026-01-16T04:10:06 +211ms service=default version=1.1.19 args=["auth","login",REDACTED_URL] opencode
INFO  2026-01-16T04:10:06 +0ms service=default directory=REDACTED/opencode creating instance
INFO  2026-01-16T04:10:06 +0ms service=project directory=REDACTED/opencode fromDirectory
ERROR 2026-01-16T04:10:07 +709ms service=default name=TypeError message=undefined is not an object (evaluating 'wellknown.auth.command') stack=TypeError: undefined is not an object (evaluating 'wellknown.auth.command')
    at fn (src/cli/cmd/auth.ts:233:51)
    at processTicksAndRejections (native:7:39) fatal

For a workaround, I just launched /connect within the running TUI after setting up my opencode.json file appropriately.

@intentionally-left-nil commented on GitHub (Jan 15, 2026): The CLI also needs work. When you type `opencode auth` this is presented, but if you actually enter a URL you get an error: ``` opencode auth opencode auth login [url] log in to a provider ``` ``` opencode auth login REDACTED_URL ┌ Add credential Error: Unexpected error, check log file at REDACTED for more details undefined is not an object (evaluating 'wellknown.auth.command') ❯ tail ~/.local/share/opencode/log/2026-01-16T041006.log INFO 2026-01-16T04:10:06 +211ms service=default version=1.1.19 args=["auth","login",REDACTED_URL] opencode INFO 2026-01-16T04:10:06 +0ms service=default directory=REDACTED/opencode creating instance INFO 2026-01-16T04:10:06 +0ms service=project directory=REDACTED/opencode fromDirectory ERROR 2026-01-16T04:10:07 +709ms service=default name=TypeError message=undefined is not an object (evaluating 'wellknown.auth.command') stack=TypeError: undefined is not an object (evaluating 'wellknown.auth.command') at fn (src/cli/cmd/auth.ts:233:51) at processTicksAndRejections (native:7:39) fatal ``` For a workaround, I just launched /connect within the running TUI after setting up my `opencode.json` file appropriately.
yindo commented 2026-02-16 17:41:19 -05:00
Author
Owner
Copy Link
Copy Source

@Lsgo commented on GitHub (Jan 18, 2026):

I still don't understand how to configure third-party models. Could you provide a practical example for reference?
After I modified the opencode.json file, the target third-party model still does not show up in the /models directory. What's more, there is no error information to indicate the cause of this problem.
I would appreciate it if anyone could help analyze the possible reasons and give a solution.

"provider":
{
    "doubao":
    {
        "npm": "@ai-sdk/openai-compatible",
        "name": "doubao",
        "credentials":
        {
            "apiKey": "xxxxxxxxxxxxxxxxxxxxxxxxxxx"
        },
        "options":
        {
            "baseURL": "https://ark.cn-beijing.volces.com/api/coding"
        },
        "models":
        {
            "doubao-seed-code-preview-latest":
            {
                "name": "Doubao Seed Code Preview",
                "limit":
                {
                    "context": 256000,
                    "output": 32000
                }
            }
        }
    }
}
@Lsgo commented on GitHub (Jan 18, 2026): I still don't understand how to configure third-party models. Could you provide a practical example for reference? After I modified the opencode.json file, the target third-party model still does not show up in the /models directory. What's more, there is no error information to indicate the cause of this problem. I would appreciate it if anyone could help analyze the possible reasons and give a solution. "provider": { "doubao": { "npm": "@ai-sdk/openai-compatible", "name": "doubao", "credentials": { "apiKey": "xxxxxxxxxxxxxxxxxxxxxxxxxxx" }, "options": { "baseURL": "https://ark.cn-beijing.volces.com/api/coding" }, "models": { "doubao-seed-code-preview-latest": { "name": "Doubao Seed Code Preview", "limit": { "context": 256000, "output": 32000 } } } } }
yindo commented 2026-02-16 17:41:19 -05:00
Author
Owner
Copy Link
Copy Source

@Zhen-Bo commented on GitHub (Jan 18, 2026):

Complete Guide to Setting Up Your Own API Endpoint

Steps

  1. Install opencode (v1.1.25)
  2. Run source ~/.bashrc
  3. Run opencode auth login
  4. Scroll down to the bottom and select other
  5. Set up your custom provider ID (name), which only accepts a-z, 0-9 (e.g.: custom)
  6. Enter your API key
  7. Edit ~/.config/opencode/opencode.json
  8. Set up your opencode.json
    • Use @ai-sdk/openai for /v1/responses
    • Use @ai-sdk/openai-compatible for /v1/chat/completions
    • Use @ai-sdk/anthropic for /v1/messages
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "<your-provider-id>": {
      "npm": "@ai-sdk/openai",
      "name": "<Provider Display Name>",
      "options": {
        "baseURL": "<your-api-base-url>/v1",
        "setCacheKey": true
      },
      "models": {
        "<model-id>": {
          "name": "<Model Display Name>",
          "limit": {
            "context": 154840,
            "output": 16384
          }
        }
      }
    }
  },
  "model": "<your-provider-id>/<model-id>"
}
  1. Done!

Using a custom provider called myapi with model gpt-4o:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "myapi": {
      "npm": "@ai-sdk/openai",
      "name": "My Custom API",
      "options": {
        "baseURL": "https://api.example.com/v1",
        "setCacheKey": true
      },
      "models": {
        "gpt-4o": {
          "name": "GPT-4o",
          "limit": {
            "context": 154840,
            "output": 16384
          }
        }
      }
    }
  },
  "model": "myapi/gpt-4o"
}
@Zhen-Bo commented on GitHub (Jan 18, 2026): # Complete Guide to Setting Up Your Own API Endpoint ## Steps 1. Install opencode (v1.1.25) 2. Run `source ~/.bashrc` 3. Run `opencode auth login` 4. Scroll down to the bottom and select `other` 5. Set up your custom provider ID (name), which only accepts a-z, 0-9 (e.g.: `custom`) 6. Enter your API key 7. Edit `~/.config/opencode/opencode.json` 8. Set up your `opencode.json` - Use `@ai-sdk/openai` for `/v1/responses` - Use `@ai-sdk/openai-compatible` for `/v1/chat/completions` - Use `@ai-sdk/anthropic` for `/v1/messages` ```json { "$schema": "https://opencode.ai/config.json", "provider": { "<your-provider-id>": { "npm": "@ai-sdk/openai", "name": "<Provider Display Name>", "options": { "baseURL": "<your-api-base-url>/v1", "setCacheKey": true }, "models": { "<model-id>": { "name": "<Model Display Name>", "limit": { "context": 154840, "output": 16384 } } } } }, "model": "<your-provider-id>/<model-id>" } ``` 9. Done! --- Using a custom provider called `myapi` with model `gpt-4o`: ```JSON { "$schema": "https://opencode.ai/config.json", "provider": { "myapi": { "npm": "@ai-sdk/openai", "name": "My Custom API", "options": { "baseURL": "https://api.example.com/v1", "setCacheKey": true }, "models": { "gpt-4o": { "name": "GPT-4o", "limit": { "context": 154840, "output": 16384 } } } } }, "model": "myapi/gpt-4o" } ```
yindo commented 2026-02-16 17:41:19 -05:00
Author
Owner
Copy Link
Copy Source

@Zhen-Bo commented on GitHub (Jan 18, 2026):

Complete Guide to Setting Up Your Own API Endpoint

Steps

  1. Install opencode (v1.1.25)

  2. Run source ~/.bashrc

  3. Run opencode auth login

  4. Scroll down to the bottom and select other

  5. Set up your custom provider ID (name), which only accepts a-z, 0-9 (e.g.: custom)

  6. Enter your API key

  7. Edit ~/.config/opencode/opencode.json

  8. Set up your opencode.json

    • Use @ai-sdk/openai for /v1/responses
    • Use @ai-sdk/openai-compatible for /v1/chat/completions
    • Use @ai-sdk/anthropic for /v1/messages

{
"$schema": "https://opencode.ai/config.json",
"provider": {
"": {
"npm": "@ai-sdk/openai",
"name": "",
"options": {
"baseURL": "/v1",
"setCacheKey": true
},
"models": {
"": {
"name": "",
"limit": {
"context": 154840,
"output": 16384
}
}
}
}
},
"model": "/"
}
9. Done!

Using a custom provider called myapi with model gpt-4o:

{
"$schema": "https://opencode.ai/config.json",
"provider": {
"myapi": {
"npm": "@ai-sdk/openai",
"name": "My Custom API",
"options": {
"baseURL": "https://api.example.com/v1",
"setCacheKey": true
},
"models": {
"gpt-4o": {
"name": "GPT-4o",
"limit": {
"context": 154840,
"output": 16384
}
}
}
}
},
"model": "myapi/gpt-4o"
}

@Lsgo

@Zhen-Bo commented on GitHub (Jan 18, 2026): > # Complete Guide to Setting Up Your Own API Endpoint > ## Steps > 1. Install opencode (v1.1.25) > 2. Run `source ~/.bashrc` > 3. Run `opencode auth login` > 4. Scroll down to the bottom and select `other` > 5. Set up your custom provider ID (name), which only accepts a-z, 0-9 (e.g.: `custom`) > 6. Enter your API key > 7. Edit `~/.config/opencode/opencode.json` > 8. Set up your `opencode.json` > > * Use `@ai-sdk/openai` for `/v1/responses` > * Use `@ai-sdk/openai-compatible` for `/v1/chat/completions` > * Use `@ai-sdk/anthropic` for `/v1/messages` > > { > "$schema": "https://opencode.ai/config.json", > "provider": { > "<your-provider-id>": { > "npm": "@ai-sdk/openai", > "name": "<Provider Display Name>", > "options": { > "baseURL": "<your-api-base-url>/v1", > "setCacheKey": true > }, > "models": { > "<model-id>": { > "name": "<Model Display Name>", > "limit": { > "context": 154840, > "output": 16384 > } > } > } > } > }, > "model": "<your-provider-id>/<model-id>" > } > 9. Done! > > Using a custom provider called `myapi` with model `gpt-4o`: > > { > "$schema": "https://opencode.ai/config.json", > "provider": { > "myapi": { > "npm": "@ai-sdk/openai", > "name": "My Custom API", > "options": { > "baseURL": "https://api.example.com/v1", > "setCacheKey": true > }, > "models": { > "gpt-4o": { > "name": "GPT-4o", > "limit": { > "context": 154840, > "output": 16384 > } > } > } > } > }, > "model": "myapi/gpt-4o" > } @Lsgo
yindo commented 2026-02-16 17:41:19 -05:00
Author
Owner
Copy Link
Copy Source

@srggrs commented on GitHub (Jan 18, 2026):

Hi followed the instructions above but I get an error about the PromptCacheKeys

Bad Request: Bad request: json: unknown field "promptCacheKey"

opencode version 1.1.25

EDIT:
having a look as the opencode node_modules folder in ~/.opencode I can see the npm package @ai-sdk/openai-compatible is not installed, is that the issue?

@srggrs commented on GitHub (Jan 18, 2026): Hi followed the instructions above but I get an error about the PromptCacheKeys > Bad Request: Bad request: json: unknown field "promptCacheKey" opencode version 1.1.25 EDIT: having a look as the opencode node_modules folder in `~/.opencode` I can see the npm package `@ai-sdk/openai-compatible` is not installed, is that the issue?
yindo commented 2026-02-16 17:41:19 -05:00
Author
Owner
Copy Link
Copy Source

@Zhen-Bo commented on GitHub (Jan 19, 2026):

Hi followed the instructions above but I get an error about the PromptCacheKeys

Bad Request: Bad request: json: unknown field "promptCacheKey"

opencode version 1.1.25

EDIT: having a look as the opencode node_modules folder in ~/.opencode I can see the npm package @ai-sdk/openai-compatible is not installed, is that the issue?

Use @ai-sdk/openai or @ai-sdk/anthropic instead and try to update your api proxy.
OR you can try to do a fresh install with curl -fsSL https://opencode.ai/install | bash

@Zhen-Bo commented on GitHub (Jan 19, 2026): > Hi followed the instructions above but I get an error about the PromptCacheKeys > > > Bad Request: Bad request: json: unknown field "promptCacheKey" > > opencode version 1.1.25 > > EDIT: having a look as the opencode node_modules folder in `~/.opencode` I can see the npm package `@ai-sdk/openai-compatible` is not installed, is that the issue? Use `@ai-sdk/openai` or `@ai-sdk/anthropic` instead and try to update your api proxy. OR you can try to do a fresh install with `curl -fsSL https://opencode.ai/install | bash`
yindo commented 2026-02-16 17:41:19 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Jan 19, 2026):

@srggrs just don't set this "setCacheKey": true

@rekram1-node commented on GitHub (Jan 19, 2026): @srggrs just don't set this ` "setCacheKey": true`
yindo commented 2026-02-16 17:41:19 -05:00
Author
Owner
Copy Link
Copy Source

@srggrs commented on GitHub (Jan 19, 2026):

Thank you it worked!

@srggrs commented on GitHub (Jan 19, 2026): Thank you it worked!
yindo commented 2026-02-16 17:41:19 -05:00
Author
Owner
Copy Link
Copy Source

@lucapette commented on GitHub (Jan 23, 2026):

I used this

"provider": {
    "qwen-coding-plan": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Qwen Coding Plan",
      "options": {
        "baseURL": "https://coding-intl.dashscope.aliyuncs.com/v1",
        "apiKey": "{env:QWEN_API_KEY}"
      },
      "models": {
        "qwen3-coder-plus": {
          "name": "qwen3-coder-plus"
        }
      }
    }
  },

for the qwen coder coding plan. Docs are def out of sync because the schema doesn't match anymore

@lucapette commented on GitHub (Jan 23, 2026): I used this ```json "provider": { "qwen-coding-plan": { "npm": "@ai-sdk/openai-compatible", "name": "Qwen Coding Plan", "options": { "baseURL": "https://coding-intl.dashscope.aliyuncs.com/v1", "apiKey": "{env:QWEN_API_KEY}" }, "models": { "qwen3-coder-plus": { "name": "qwen3-coder-plus" } } } }, ``` for the qwen coder coding plan. Docs are def out of sync because the schema doesn't match anymore
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acp
bad
bug
discussion
docs
documentation
enhancement
extension
good first issue
growth
help-wanted
mcp
model-problem
needs:compliance
nix
opentui
perf
pull-request
Mirrored from GitHub Pull Request
 tui
web
windows
zen
No Label bug docs
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#3744
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?