33c363d4d4
* test(ci): extend record/replay proxy to chat, embeddings, moderations, rerank, anthropic The record/replay proxy that took the gpt-image-1 spend E2E off the live OpenAI path now fronts every provider, so the other real-provider E2Es stop paying for and depending on live calls each commit. It keys per upstream and selects a non-OpenAI provider by a /__recorder_upstream/<host>/ path prefix carried on the model's api_base, since some litellm handlers (cohere rerank) drop custom request headers. Wired into build_and_test (chat, embeddings, moderations, image), the otel job (cohere rerank), and the anthropic-messages job via a reusable start_openai_record_replay_proxy command. Dropped the time.time()/uuid prompt cache-busters in the build_and_test chat tests, whose config has the response cache off, so identical requests are recordable. The image spend test now asserts a repeat call still bills spend, failing loudly if the proxy response cache is ever turned on. Responses, the anthropic passthrough, bedrock, and fake-endpoint tests are left live: their lifecycles, api_base assertions, providers, or fake targets make a stateless body-keyed cache either break them or add nothing. * docs(ci): note the recorder command's OpenAI default upstream and prefix override Addresses a review note: the shared start_openai_record_replay_proxy command defaults the upstream to OpenAI, so a non-OpenAI model must carry the /__recorder_upstream/<host>/ prefix on its api_base. Document that in the command description so a future caller does not assume the default follows the provider.
59 lines
1.8 KiB
YAML
59 lines
1.8 KiB
YAML
model_list:
|
|
- model_name: claude-sonnet-4-5-20250929
|
|
litellm_params:
|
|
model: "anthropic/claude-sonnet-4-5-20250929"
|
|
api_key: os.environ/ANTHROPIC_API_KEY
|
|
api_base: os.environ/RECORDER_ANTHROPIC_BASE_URL # In CI, routes through the record/replay proxy; unset elsewhere -> direct to Anthropic
|
|
|
|
- model_name: bedrock-claude-sonnet-3.5
|
|
litellm_params:
|
|
model: "bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0"
|
|
aws_region_name: "us-east-1"
|
|
|
|
- model_name: bedrock-claude-sonnet-4.6
|
|
litellm_params:
|
|
model: "bedrock/us.anthropic.claude-sonnet-4-6"
|
|
aws_region_name: "us-east-1"
|
|
|
|
- model_name: bedrock-claude-sonnet-4.5
|
|
litellm_params:
|
|
model: "bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0"
|
|
aws_region_name: "us-east-1"
|
|
|
|
- model_name: bedrock-claude-opus-4.5
|
|
litellm_params:
|
|
model: "bedrock/us.anthropic.claude-opus-4-5-20251101-v1:0"
|
|
aws_region_name: "us-east-1"
|
|
|
|
- model_name: bedrock-nova-pro
|
|
litellm_params:
|
|
model: "bedrock/us.amazon.nova-pro-v1:0"
|
|
aws_region_name: "us-east-1"
|
|
|
|
# Converse API models
|
|
- model_name: bedrock-converse-claude-sonnet-4.5
|
|
litellm_params:
|
|
model: "bedrock/converse/us.anthropic.claude-sonnet-4-5-20250929-v1:0"
|
|
aws_region_name: "us-east-1"
|
|
|
|
# Azure AI models
|
|
- model_name: azure-ai-claude-opus-4.5
|
|
litellm_params:
|
|
model: "azure_ai/claude-opus-4.5"
|
|
api_key: os.environ/AZURE_AI_API_KEY
|
|
api_base: os.environ/AZURE_AI_API_BASE
|
|
|
|
# Vertex AI models
|
|
- model_name: vertex-ai-claude-opus-4-6
|
|
litellm_params:
|
|
model: "vertex_ai/claude-opus-4-6"
|
|
vertex_ai_project: "pathrise-convert-1606954137718"
|
|
vertex_ai_location: "asia-southeast1"
|
|
|
|
general_settings:
|
|
forward_client_headers_to_llm_api: true
|
|
|
|
litellm_settings:
|
|
drop_params: true
|
|
modify_params: true
|