feat(ai): handle google models through vertex AI #7768
Description
/ai similar to the anthropic provider for the ai chat and the ai agents (windmill-api and windmill-worker, ai_executor), add the same new platform 'google_vertex_ai' to the google ai provider. Here is an example curl: url -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" "https://aiplatform.googleapis.com/v1/projects/gen-lang-client-0835990556/locations/global/publishers/google/models/gemini-2.5-flash:generateContent" -d '{"contents": [{"role": "user", "parts": [{"text": "hello"}]}]}'. Here is an example response: { "candidates": [ { "content": { "role": "model", "parts": [ { "text": "Hello! How can I help you today?" } ] }, "finishReason": "STOP", "avgLogprobs": -0.42892474598354763 } ], "usageMetadata": { "promptTokenCount": 1, "candidatesTokenCount": 9, "totalTokenCount": 32, "trafficType": "ON_DEMAND", "promptTokensDetails": [ { "modality": "TEXT", "tokenCount": 1 } ], "candidatesTokensDetails": [ { "modality": "TEXT", "tokenCount": 9 } ], "thoughtsTokenCount": 22 }, "modelVersion": "gemini-2.5-flash", "createTime": "2026-02-03T11:46:25.215430Z", "responseId": "EeCBaYaTDeXDtfAPz8i1yAs" }. The response format is probably the same as the normal google ai request.. Request made by @centdix