anomalyco / anomalyco/models.dev
Directory structure requirement may be unnecessary for providers without namespaced model IDs
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 6.9k
- Forks
- 1.7k
- Avg merge
- 3h 21m
- Merged PRs (30d)
- 873
Description
I have a question regarding the current directory structure requirement: If the model ID contains /, use subfolders. For example, for the model ID openai/gpt-5, create a folder openai/ and place a file named gpt-5.toml inside it.
However, some providers like Poe don't have this namespacing requirement for model IDs. From the OpenAI-compatible endpoint https://api.poe.com/v1/models, the model_id is returned directly without any / separator (e.g., Gemini-3-Pro).
In this case, is the subfolder structure still necessary? Because following the current subfolder convention would actually conflict with the official documentation examples, such as:
import os, openai
client = openai.OpenAI(
api_key=os.getenv("POE_API_KEY"),
base_url="https://api.poe.com/v1",
)
# Example: Using web search and thinking level with Gemini models
response = client.chat.completions.create(
model="Gemini-3-Pro", # No namespace prefix
messages=[{"role": "user", "content": "What are the latest developments in quantum computing?"}],
extra_body={
"web_search": True,
"thinking_level": "high"
}
)
The example shows model="Gemini-3-Pro" without any provider prefix, which wouldn't map cleanly to a poe/Gemini-3-Pro.toml structure if we strictly follow the subfolder rule for provider organization.
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.
Research direction
No source file or test is named. Start by tracing the directory-structure rule and comparing it with the Poe model ID examples; done means the repository convention clearly handles model IDs without / without conflicting with provider documentation.
Written by the indexing model from the issue text.
Assessment
- Domain
- data
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100