mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-17 04:34:25 +00:00
8283033c0e
The shared integration proxy configs left the five-minute /v1/models refresh on, so every proxy booted from them sent a GET /v1/models to each openai-compatible deployment at boot and every 300 s after, including the per-test deployments other cells register against their own scripted wires. A scripted provider that asserts on the exact requests it receives then saw a GET it never scripted, mid-test. Set disable_model_info_refresh in proxy_config.yaml, coordination_redis_proxy_config.yaml, and oci_proxy_test_config.yaml, and drop the three per-test copies of that setting from the observability cells that each loaded the stock config and set it themselves. Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
25 lines
619 B
YAML
25 lines
619 B
YAML
model_list:
|
|
- model_name: oci-cohere-command
|
|
litellm_params:
|
|
model: oci/cohere.command-latest
|
|
- model_name: oci-llama
|
|
litellm_params:
|
|
model: oci/meta.llama-3.3-70b-instruct
|
|
- model_name: oci-gemini
|
|
litellm_params:
|
|
model: oci/google.gemini-2.5-flash
|
|
- model_name: oci-grok
|
|
litellm_params:
|
|
model: oci/xai.grok-3-mini
|
|
- model_name: oci-embed
|
|
litellm_params:
|
|
model: oci/cohere.embed-v4.0
|
|
model_info:
|
|
mode: embedding
|
|
|
|
general_settings:
|
|
master_key: os.environ/LITELLM_MASTER_KEY
|
|
disable_model_info_refresh: true
|
|
|
|
litellm_settings:
|
|
drop_params: True
|