Before submitting your bug report
Relevant environment info
- OS: Windows 11
- Continue version: 1.2.11
- IDE version: VSCode 1.106.2
- Model: gpt-5-mini
- config:
name: Local Config
version: 1.0.0
schema: v1
models:
- name: usd GPT-5-mini
provider: openai
model: gpt-5-mini
apiBase: https://example.com/api
apiKey: XXX
roles:
- chat
- edit
useLegacyCompletionsEndpoint: false
OR link to agent in Continue hub:Description
Since version 1.2.11 of continue it seems to use the /responses API endpoint for requests to models of provider openai. Open WebUI does not support that endpoint yet open-webui/open-webui#11874 which leads to
error: HTTP 405 Method Not Allowed from https://example.com/api/responses
In version 1.2.10 of continue this was (and still is) working. I guess this could be fixed by giving users the opportunity to configure the api endpoint (not only apiBase and replace calls to /responses with /chat/completions/ or whatever was used before version 1.2.11.
To reproduce
- Setup Open WebUI
- Use the config I provided
- Send a request
Log output
[Extension Host] Error handling webview message: {
"msg": {
"messageId": "bd1dd203-55fc-4416-9c54-ab997a51d672",
"messageType": "llm/streamChat",
"data": {
"completionOptions": {
"reasoning": false
},
"title": "GPT-5-mini",
"messages": [
{
"role": "system",
"content": "<important_rules>\n You are in chat mode.\n\n If the user asks to make changes to files offer that they can use the Apply Button on the code block, or switch to Agent Mode to make the suggested updates automatically.\n If needed concisely explain to the user they can switch to agent mode using the Mode Selector dropdown and provide no other details.\n\n Always include the language and file name in the info string when you write code blocks.\n If you are editing \"src/main.py\" for example, your code block should start with ' src/main.py'\n\n When addressing code modification requests, present a concise code snippet that\n emphasizes only the necessary changes and uses abbreviated placeholders for\n unmodified sections. For example:\n\n /path/to/file\n // ... existing code ...\n\n {{ modified code here }}\n\n // ... existing code ...\n\n {{ another modification }}\n\n // ... rest of code ...\n \n\n In existing files, you should always restate the function or class that the snippet belongs to:\n\n /path/to/file\n // ... existing code ...\n\n function exampleFunction() {\n // ... existing code ...\n\n {{ modified code here }}\n\n // ... rest of function ...\n }\n\n // ... rest of code ...\n \n\n Since users have access to their complete file, they prefer reading only the\n relevant modifications. It's perfectly acceptable to omit unmodified portions\n at the beginning, middle, or end of files using these \"lazy\" comments. Only\n provide the complete file when explicitly requested. Include a concise explanation\n of changes unless the user specifically asks for code only.\n\n</important_rules>"
},
{
"role": "user",
"content": "hi"
}
],
"messageOptions": {
"precompiled": true
}
}
}
}
Error: HTTP 405 Method Not Allowed from https://example.com/api/responses
{"detail":"Method Not Allowed"}
gCs @ console.ts:139
$logExtensionHostMessage @ mainThreadConsole.ts:39
S @ rpcProtocol.ts:458
Q @ rpcProtocol.ts:443
M @ rpcProtocol.ts:373
L @ rpcProtocol.ts:299
(anonymous) @ rpcProtocol.ts:161
C @ event.ts:1201
fire @ event.ts:1232
fire @ ipc.net.ts:652
l.onmessage @ localProcessExtensionHost.ts:383
localProcessExtensionHost.ts:280 Extension Host
localProcessExtensionHost.ts:281 [@continuedev] error: HTTP 405 Method Not Allowed from https://example.com/api/responses
{"detail":"Method Not Allowed"} {"context":"llm_fetch","url":"https://example.com/api/responses","method":"POST","model":"gpt-5-mini","provider":"openai"}
[@continuedev] error: HTTP 405 Method Not Allowed from https://example.com/api/responses
{"detail":"Method Not Allowed"} {"context":"llm_stream_chat","model":"gpt-5-mini","provider":"openai","useOpenAIAdapter":true,"streamEnabled":true,"templateMessages":false}
Before submitting your bug report
Relevant environment info
Description
Since version 1.2.11 of continue it seems to use the
/responsesAPI endpoint for requests to models of provideropenai. Open WebUI does not support that endpoint yet open-webui/open-webui#11874 which leads toIn version 1.2.10 of continue this was (and still is) working. I guess this could be fixed by giving users the opportunity to configure the api endpoint (not only
apiBaseand replace calls to/responseswith/chat/completions/or whatever was used before version 1.2.11.To reproduce
Log output
[Extension Host] Error handling webview message: { "msg": { "messageId": "bd1dd203-55fc-4416-9c54-ab997a51d672", "messageType": "llm/streamChat", "data": { "completionOptions": { "reasoning": false }, "title": "GPT-5-mini", "messages": [ { "role": "system", "content": "<important_rules>\n You are in chat mode.\n\n If the user asks to make changes to files offer that they can use the Apply Button on the code block, or switch to Agent Mode to make the suggested updates automatically.\n If needed concisely explain to the user they can switch to agent mode using the Mode Selector dropdown and provide no other details.\n\n Always include the language and file name in the info string when you write code blocks.\n If you are editing \"src/main.py\" for example, your code block should start with ' src/main.py'\n\n When addressing code modification requests, present a concise code snippet that\n emphasizes only the necessary changes and uses abbreviated placeholders for\n unmodified sections. For example:\n\n /path/to/file\n // ... existing code ...\n\n {{ modified code here }}\n\n // ... existing code ...\n\n {{ another modification }}\n\n // ... rest of code ...\n \n\n In existing files, you should always restate the function or class that the snippet belongs to:\n\n /path/to/file\n // ... existing code ...\n\n function exampleFunction() {\n // ... existing code ...\n\n {{ modified code here }}\n\n // ... rest of function ...\n }\n\n // ... rest of code ...\n \n\n Since users have access to their complete file, they prefer reading only the\n relevant modifications. It's perfectly acceptable to omit unmodified portions\n at the beginning, middle, or end of files using these \"lazy\" comments. Only\n provide the complete file when explicitly requested. Include a concise explanation\n of changes unless the user specifically asks for code only.\n\n</important_rules>" }, { "role": "user", "content": "hi" } ], "messageOptions": { "precompiled": true } } } } Error: HTTP 405 Method Not Allowed from https://example.com/api/responses {"detail":"Method Not Allowed"} gCs @ console.ts:139 $logExtensionHostMessage @ mainThreadConsole.ts:39 S @ rpcProtocol.ts:458 Q @ rpcProtocol.ts:443 M @ rpcProtocol.ts:373 L @ rpcProtocol.ts:299 (anonymous) @ rpcProtocol.ts:161 C @ event.ts:1201 fire @ event.ts:1232 fire @ ipc.net.ts:652 l.onmessage @ localProcessExtensionHost.ts:383 localProcessExtensionHost.ts:280 Extension Host localProcessExtensionHost.ts:281 [@continuedev] error: HTTP 405 Method Not Allowed from https://example.com/api/responses {"detail":"Method Not Allowed"} {"context":"llm_fetch","url":"https://example.com/api/responses","method":"POST","model":"gpt-5-mini","provider":"openai"} [@continuedev] error: HTTP 405 Method Not Allowed from https://example.com/api/responses {"detail":"Method Not Allowed"} {"context":"llm_stream_chat","model":"gpt-5-mini","provider":"openai","useOpenAIAdapter":true,"streamEnabled":true,"templateMessages":false}