mateo-berri c85da0a75f fix(logging): key bridged /v1/messages rows on the id the caller received ... /v1/messages against a non-Anthropic model answers with the Responses id, but the spend row was built from a fresh ModelResponse, so it landed on a chatcmpl- uuid nobody can look up. Carry that id through the same way the Anthropic branch now does, and make the passthrough spend assertions fail on an empty lookup instead of skipping past it.		2026-09-03 01:15:06 -07:00
..
base_anthropic_messages_test.py
package-lock.json
package.json
test_anthropic_passthrough.py	fix(logging): key bridged /v1/messages rows on the id the caller received	2026-09-03 01:15:06 -07:00
test_anthropic_passthrough_basic.py
test_anthropic_passthrough_python_sdkpy
test_assembly_ai.py
test_gemini.js
test_gemini_with_spend.test.js
test_hosted_vllm_passthrough.py
test_local_gemini.js
test_local_vertex.js
test_mcp_routes.py
test_openai_assistants_passthrough.py	test(passthrough): drop the Azure assistants test, retired upstream on 2026-08-26	2026-08-27 23:58:23 -07:00
test_vertex.test.js
test_vertex_ai.py
test_vertex_with_spend.test.js
vertex_key.json
vertex_test_helpers.js