Paul Kompfner 312837a1d4 test: add run_inference tests for OpenAIResponsesLLMService ...

Uses real LLMContext and adapter (only HTTP client is mocked) to test
basic inference, client exception propagation, system_instruction
override, empty context fallback, and max_tokens override.

2026-03-20 21:34:22 -04:00

37 KiB

Raw Blame History

View Raw