The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.
Rust agent-orchestrationai-agentsai-assistantdesktopllmlocal-firstmcppersonal-aiprivacyrustsecond-braintauri
test(inference): swap expected cache identities in managed model test
Steven Enamakele7eddad807c1
diff --git a/crates/openhuman-tinyhumans/src/inference/managed_model_tests.rs b/crates/openhuman-tinyhumans/src/inference/managed_model_tests.rsindex f29212a4c8..cf17861301 100644--- a/crates/openhuman-tinyhumans/src/inference/managed_model_tests.rs+++ b/crates/openhuman-tinyhumans/src/inference/managed_model_tests.rs@@ -32,7 +32,7 @@ fn managed_model_trims_a_configured_model_and_uses_the_product_default_when_blan.expect("configured model");assert_eq!(configured.cache_identity().as_deref(),- Some("openhuman:https://api.example.test/openai/v1:openrouter/deepseek/deepseek-v4-flash")+ Some("openhuman:https://api.example.test/openai/v1:reasoning-v1"));let blank = build_chat_model(@@ -46,6 +46,6 @@ fn managed_model_trims_a_configured_model_and_uses_the_product_default_when_blan.expect("blank model falls back to the product default");assert_eq!(blank.cache_identity().as_deref(),- Some("openhuman:https://api.example.test/openai/v1:reasoning-v1")+ Some("openhuman:https://api.example.test/openai/v1:openrouter/deepseek/deepseek-v4-flash"));}