Tom Brandenburg

Same issue here on Windows 11 and Warp v0.2025.09.17.08.11.stable_02

+1 for making it optional. In my company we also have endpoints like: * https://....azure-api.net/openai/deployments/gpt-5/chat/completions?api-version=2025-01-01-preview and it gets generated by opencode like: * https://....azure-api.net/openai/deployments/gpt-5/v1/chat/completions?api-version=2025-01-01-preview I had to add LiteLLM in...

Hej guys, I found this setting in Vercel's AI SDK: https://github.com/vercel/ai/blob/main/content/providers/01-ai-sdk-providers/04-azure.mdx?plain=1#L89 I would probably go down this way. Other ideas?

Stupid question (currently travelling just with my mobile): Is opencode using the Azure responses API?

Hej guys, diving deeper I realized that the JSON-options are actually passed to the provider creation method. So I tried running with: ``` { "$schema": "https://opencode.ai/config.json", "provider": { "azure": {...

> we're not using deployments for the responses API just https://subdomain.openai.azure.com/openai/responses?api-version=2025-03-01-preview - so this does not work either. Which results into a contribution to Vercel's SDK and how it is...

Same here with claude-sonnet-4. It happens with a big Playwright Testing Suite and several screenshots.