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
refactor(inference): import demotion helpers from their own module
Steven Enamakeld42254eb0aac
diff --git a/crates/openhuman-core/src/inference/provider/http_error.rs b/crates/openhuman-core/src/inference/provider/http_error.rsindex b45f83b65f..f41cee0ede 100644--- a/crates/openhuman-core/src/inference/provider/http_error.rs+++ b/crates/openhuman-core/src/inference/provider/http_error.rs@@ -14,9 +14,10 @@ use tinyinference_llm::failure::http::{classify_and_report_http_failure, ErrorReporter, ProviderHttpFailure, ProviderHttpFailureFacts,};use tinyinference_llm::failure::{- demote_decision, local_provider_no_model_loaded_user_message,- ollama_cloud_internal_500_user_message, should_report_provider_http_status, DemotionKind,+ local_provider_no_model_loaded_user_message, ollama_cloud_internal_500_user_message,+ should_report_provider_http_status,};+use tinyinference_llm::failure::demotion::{demote_decision, DemotionKind};/// Whether a non-2xx provider status is worth a per-attempt Sentry report.pub fn should_report_provider_http_failure(status: reqwest::StatusCode) -> bool {