Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 7ec6923f07
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "Codex (@codex) review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "Codex (@codex) address that feedback".
| "max_input_tokens": 131072, | ||
| "max_output_tokens": 131072 | ||
| }, | ||
| "publishers/moonshotai/models/kimi-k2.5": { |
There was a problem hiding this comment.
Use deployable model key for Azure Kimi K2.5
Please avoid registering this Azure-only model under a slash-delimited publishers/... key, because Azure routing falls back to body.model as the deployment name when metadata.deployment is unset (proxy.ts builds /openai/deployments/${encodeURIComponent(model)}). With this key, the inferred deployment path becomes publishers%2Fmoonshotai%2Fmodels%2Fkimi-k2.5, which does not match normal Azure deployment naming and leads to DeploymentNotFound unless every endpoint is manually configured with an explicit deployment override.
Useful? React with 👍 / 👎.
Adding kimi-k2.5 to Azure provider. Details taken from: https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/kimi-k2-5-now-in-microsoft-foundry/4492321