michelligabriele df5d5664e2 fix(vertex_ai): replace custom model names with actual Vertex AI model names in passthrough URLs (#19948) ... When the passthrough URL already contains project and location, the code was skipping the deployment lookup and forwarding the URL as-is to Vertex AI. For custom model names like gcp/google/gemini-2.5-flash, Vertex AI returned 404 because it only knows the actual model name (gemini-2.5-flash). The fix makes the deployment lookup always run, so the custom model name gets replaced with the actual Vertex AI model name before forwarding.		2026-01-28 16:22:16 -08:00
..
llm_provider_handlers	Guardrails API - support LLM tool call response checks on /chat/completions, /v1/responses, /v1/messages on regular + streaming calls (#17619)	2025-12-15 18:19:52 +05:30
test_llm_pass_through_endpoints.py	Fix: Header forwarding in bedrock passthrough	2026-01-13 09:45:14 +05:30
test_pass_through_endpoints.py	fix: pass through endpoints update registry (#19420)	2026-01-22 19:57:48 -08:00
test_passthrough_endpoints_common_utils.py	test fix location of encode bedrock runtime modelid arn	2025-08-22 17:34:09 -07:00
test_passthrough_guardrails.py	[Feat] Add guardrails for pass through endpoints (#17221)	2025-11-27 12:06:53 -08:00
test_passthrough_guardrails_field_targeting.py	chore: cleanup unused scripts and fix misplaced test file (#17611)	2025-12-08 19:00:55 -08:00
test_vertex_ai_batch_passthrough.py	Fix batch tests	2026-01-22 19:23:32 +05:30
test_vertex_passthrough_load_balancing.py	fix(vertex_ai): replace custom model names with actual Vertex AI model names in passthrough URLs (#19948)	2026-01-28 16:22:16 -08:00