Provider API rejects audio/video content parts for multimodal models
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 48/100
Research direction
Start at the POST /provider/v1/chat/completions entry point and review the provider documentation describing accepted content parts. Confirm how input_audio and video_url data URLs are validated for the named models, then verify that valid audio and video requests are accepted without breaking existing text and image handling.
Written by the indexing model from the issue text.
Description
Feature Description
I’m trying to call these models through the Provider API:
meta/muse-spark-1.3-contributor
Qwen/Qwen3.8-Omni-Flash
using POST https://api.commandcode.ai/provider/v1/chat/completions.
I need to submit:
an MP3 as input_audio
an MP4 as video_url with a Base64 data URL
Both models return:
{
"error": {
"message": "Invalid input",
"type": "invalid_request_error",
"param": "messages.1.content"
}
}
Your provider documentation says “Text and images. Audio, file, and document parts are rejected by the schema,” but Qwen 3.8 Omni Flash is advertised as omni-modal and supports audio/video through its native OpenAI-compatible API.
Use Case
In the case of Qwen 3.8 Omni Flash, media understanding is its main feature. To not support media input would be an oversight. While the Command Code harness itself may not support media, there are a lot of applications that can.
Additional Context
No response
How important is this to you?
Important for my workflow
- Dominant language
- No language data
- Stars
- 4k
- Forks
- 350
- PR merge metrics
- No merged PRs in 30d
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from CommandCodeAI/command-code
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
CommandCodeAI/command-code#903 · 2 comments ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
CommandCodeAI/command-code#855 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
CommandCodeAI/command-code#841 · 1 comment ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
CommandCodeAI/command-code#655 · 1 comment ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
CommandCodeAI/command-code#608 ·
All issues in CommandCodeAI/command-code
Similar issues
-
area/config comp/cli comp/plugins P3 Plugin Catalog sweeper:risk-compatibility tool/memory type/bug
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
NousResearch/hermes-agent#119909 · 1 comment ·
-
bug configuration documentation examples policies processor tests training
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
huggingface/lerobot#4727 ·
-
📱 AI 日报 · 2026-09-23 Openai-content daily-post
Difficulty 1/5 Under an hour Newbie friendliness 85/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
run-llama/llama_index#23199 ·
-
p:2-high pydanty:bug
Difficulty 2/5 1-3 hours Newbie friendliness 90/100
pydantic/pydantic-ai#8642 · 2 comments ·