Repository navigation
[BUG] Gemini models in WSL env: Request contains an invalid argument. #12202
Description
Problem (one or two sentences)
When using any gemini model in a project in vscode that is in wsl environment I get the following error. see below for logs.
Context (who is affected and when)
Users of Gemini models in wsl environment
Reproduction steps
-
Computer version info
WSL version: 2.4.12.0
Kernel version: 5.15.167.4-1
WSLg version: 1.0.65
MSRDC version: 1.2.5716
Direct3D version: 1.611.1-81528511
DXCore version: 10.0.26100.1-240331-1435.ge-release
Windows version: 10.0.26200.8246 -
roo version
3.53.0 -
vscode version
Version: 1.117.0 (user setup)
Commit: 10c8e557c8b9f9ed0a87f61f1c9a44bde731c409
Date: 2026-04-21T16:12:14-07:00
Electron: 39.8.7
ElectronBuildId: 13841579
Chromium: 142.0.7444.265
Node.js: 22.22.1
V8: 14.2.231.22-electron.0
OS: Windows_NT x64 10.0.26200 -
select gemini model and send a message when vscode is inialized in wsl
Expected result
google accepting request
Actual result
google not accepting request
Variations tried (optional)
No response
App Version
3.53.0
API Provider (optional)
Google Gemini
Model Used (optional)
N/A
Roo Code Task Links (optional)
No response
Relevant logs or errors (optional)
// Please share this file with Roo Code Support ([email protected]) to diagnose the issue faster
// Just make sure you're OK sharing the contents of the conversation below.
{
"error": {
"timestamp": "2026-04-26T18:33:49.190Z",
"version": "3.53.0",
"provider": "gemini",
"model": "gemini-3-flash-preview",
"details": "Gemini generate context stream error: {\"error\":{\"message\":\"{\\n \\\"error\\\": {\\n \\\"code\\\": 400,\\n \\\"message\\\": \\\"Request contains an invalid argument.\\\",\\n \\\"status\\\": \\\"INVALID_ARGUMENT\\\"\\n }\\n}\\n\",\"code\":400,\"status\":\"Bad Request\"}}"
},
"history": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "<user_message>\ntest\n</user_message>"
},
{
"type": "text",
"text": "<environment_details>\n# VSCode Visible Files\n../../../../tmp/roo-diagnostics-019dcb0f-1777228321009.json\n\n# VSCode Open Tabs\nrole-group-system-design.md,../../../../tmp/roo-diagnostics-019dcb0f-1777228321009.json\n\n# Current Time\nCurrent time in ISO 8601 UTC format: 2026-04-26T18:33:45.591Z\nUser time zone: Europe/Leiden, UTC+2:00\n\n# Current Cost\n$0.00\n\n# Current Mode\n<slug>ask</slug>\n<name>❓ Ask</name>\n<model>gemini-3-flash-preview</model>\n\n\n# Current Workspace Directory (/home/user/code/project) Files\n\n(File list truncated. Use list_files on specific subdirectories if you need to explore further.)\nYou have not created a todo list yet. Create one with `update_todo_list` if your task is complicated or involves multiple steps.\n</environment_details>"
}
],
"ts": 1777228425642
}
]
}
Activity
TanteJossa commentedon Apr 27, 2026
@roomote
{
"candidates": [
{
"content": {
"parts": [
{
"text": "Hello! How can I help you today?"
}
],
"role": "model"
},
"finishReason": "STOP",
"index": 0
}
],
"usageMetadata": {
"promptTokenCount": 1,
"candidatesTokenCount": 9,
"totalTokenCount": 169,
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 1
}
],
"thoughtsTokenCount": 159
},
"modelVersion": "gemini-2.5-flash",
"responseId": "b77vadOkN6e0vd8iIwAk"
}
I think there could be 2 options:
TanteJossa commentedon Apr 29, 2026
@roomote