-
Notifications
You must be signed in to change notification settings - Fork 3.6k
Open
Labels
area:autocompleteRelates to the auto complete featureRelates to the auto complete featureide:jetbrainsRelates specifically to JetBrains extensionRelates specifically to JetBrains extensionkind:bugIndicates an unexpected problem or unintended behaviorIndicates an unexpected problem or unintended behaviorneeds-triageos:macHappening specifically on MacHappening specifically on Mac
Description
Before submitting your bug report
- I believe this is a bug. I'll try to join the Continue Discord for questions
- I'm not able to find an open issue that reports the same bug
- I've seen the troubleshooting guide on the Continue Docs
Relevant environment info
- OS: MacOS 14.7.4
- Continue version: latest
- IDE version: Intellij 2024.3.3
- Model: starcoder:3b
- config:
OR link to assistant in Continue hub:
Description
After I compile and run the latest version of the code, I can talk normally, but the auto-completion does not respond.
I got this in prompt.log:
##### Completion options #####
{
"contextLength": 8096,
"model": "qwen:0.5b",
"maxTokens": 4096,
"stop": [
"<|im_start|>",
"<|im_end|>"
]
}
##### Request options #####
{}
##### Prompt #####
<system>
Always include the language and file name in the info string when you write code blocks, for example '```python file.py'.
<user>
1
Completion:
The number "1" is a positive integer that comes after zero and before two negative integers. It represents the starting point of something or some unit system. The number "1" can be used to represent various concepts such as independence, unity, perfection, etc.
##### Completion options #####
{
"contextLength": 8096,
"model": "qwen:0.5b",
"maxTokens": 4096,
"stop": [
"<|im_start|>",
"<|im_end|>",
"<fim_prefix>",
"<fim_suffix>",
"<fim_middle>",
"<file_sep>",
"<|endoftext|>",
"</fim_middle>",
"</code>",
"/src/",
"#- coding: utf-8",
"```"
],
"temperature": 0.01,
"raw": true
}
##### Prompt #####
<fim_prefix>
// test.kt
class Test {
private var result: Double = 0.0
fun add(number: Double): Test {
result += number
return this
}
fun subtract(number: Double): Test {
result -= number
<fim_suffix>
return this
}
fun multiply(number: Double): Test {
result *= number
return this
}
fun divide(number: Double): Test {
result /= number
return this
}
fun getResult(): Double {
return result
}
fun reset(): Test {
result = 0.0
return this
}
}
<fim_middle>
Completion:
As you can see, there is output after chat, but no Completion in autocomplete.
Here is my config.json:
{
"models": [
{
"title": "Qwen2",
"provider": "ollama",
"model": "qwen:0.5b",
"apiBase": "http://127.0.0.1:11434"
}
],
"tabAutocompleteModel": {
"title": "Starcoder2",
"provider": "ollama",
"model": "starcoder2:3b",
"apiBase": "http://127.0.0.1:11434"
},
"contextProviders": [
{
"name": "code",
"params": {}
},
{
"name": "docs",
"params": {}
},
{
"name": "diff",
"params": {}
},
{
"name": "terminal",
"params": {}
},
{
"name": "problems",
"params": {}
},
{
"name": "folder",
"params": {}
},
{
"name": "codebase",
"params": {}
}
],
"slashCommands": [
{
"name": "share",
"description": "Export the current chat session to markdown"
},
{
"name": "cmd",
"description": "Generate a shell command"
},
{
"name": "commit",
"description": "Generate a git commit message"
}
]
}
To reproduce
No response
Log output
mboulton-fathom and slepkaviba
Metadata
Metadata
Assignees
Labels
area:autocompleteRelates to the auto complete featureRelates to the auto complete featureide:jetbrainsRelates specifically to JetBrains extensionRelates specifically to JetBrains extensionkind:bugIndicates an unexpected problem or unintended behaviorIndicates an unexpected problem or unintended behaviorneeds-triageos:macHappening specifically on MacHappening specifically on Mac