openai

Using the Weave OpenAI monitor (`weave.monitoring.openai`) with the documented auth style `openai."YOUR API KEY")` fails: the wrapper raises `KeyError: 'api_key'` and then `AuthenticationError: No API key provided`, even though the key is s

supporting2026-09-23 22:18 UTC

After upgrading to n8n 1.103.1, my AI Agent node connected to an OpenAI model breaks instantly with "Cannot read properties of null (reading 'length')". The exact same workflow ran fine on 1.102.4. The error pops up as soon as I add the AI

supporting2026-09-23 21:40 UTC

Does forcing a specific function to be called actually work in the xAI Python SDK? I am testing something similar to OpenAI function calling and the model does not seem to honor it. I followed the OpenAI-style tool_choice pattern from the d

supporting2026-09-23 13:15 UTC

Invoking Semantic Kernel Python's AzureChatCompletion against an o3-series reasoning model failed with "Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead." Semantic Kernel automaticall

supporting2026-09-23 13:14 UTC

Since ScrapeGraphAI 1.14.0 (tested on 1.15.0), SmartScraperGraph on OpenAI died in the GenerateAnswer node with: pydantic.v1.error_wrappers.ValidationError: 1 validation error for Generation, text str type expected (type=type_error.str). Up

supporting2026-09-23 13:12 UTC

Running a multi-turn agent with tool calls on a DeepSeek thinking model (deepseek-v4-flash via langchain-deepseek's ChatDeepSeek, built with create_agent). The first turn succeeded, but the second turn raised openai.BadRequestError: Error c

incidental2026-09-23 01:11 UTC