What should we do?
Replace the LangChain4j bridge for the googleVertexAi provider discriminator with a native implementation over the google-genai-java SDK. Keep the existing Vertex backend wiring (a Developer API backend toggle becomes available in Phase 2 via the new connector types).
Requirements:
- Streaming-first internal driver.
- Hardcoded
ModelCapabilities: text + image + document on user-message; text on tool-result; text on assistant-message.
- Vertex auth (service account / ADC) consistent with today's behavior, including proxy support.
- Stop-reason mapping, token usage, error classification consistent with the other native impls.
Why should we do it?
Day-one feature parity with the LangChain4j implementation for Google Vertex AI customers.
What should we do?
Replace the LangChain4j bridge for the
googleVertexAiprovider discriminator with a native implementation over thegoogle-genai-javaSDK. Keep the existing Vertex backend wiring (a Developer API backend toggle becomes available in Phase 2 via the new connector types).Requirements:
ModelCapabilities: text + image + document on user-message; text on tool-result; text on assistant-message.Why should we do it?
Day-one feature parity with the LangChain4j implementation for Google Vertex AI customers.