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
fix(inference): serialize readiness test with provider override
Steven Enamakela3df43f92f16
diff --git a/crates/openhuman-core/src/core/observability.rs b/crates/openhuman-core/src/core/observability.rsindex abb1100545..e63383d2e0 100644--- a/crates/openhuman-core/src/core/observability.rs+++ b/crates/openhuman-core/src/core/observability.rs@@ -989,8 +989,8 @@ pub fn is_session_expired_message(msg: &str) -> bool {&& msg.contains("\"error\":\"Invalid token\""))// TAURI-RUST-N — same OpenHuman backend "Invalid token" envelope// wrapped by the tinyagents `ProviderError::Display` format- // (`TinyAgentsError::Provider(Box<ProviderError>)`). The crate-native- // Historical `OpenHumanBackendModel` delegated to `OpenAiModel`+ // (`TinyAgentsError::Provider(Box<ProviderError>)`). The historical+ // `OpenHumanBackendModel` delegated to `OpenAiModel`// which formats errors as `"{provider} returned HTTP {status}: {body}"`,// producing `"OpenHuman returned HTTP 401: ..."` — different from the// `"OpenHuman API error (401"` prefix the classic `api_error` path emits.diff --git a/crates/openhuman-core/src/inference/readiness_tests.rs b/crates/openhuman-core/src/inference/readiness_tests.rsindex 185fe4d522..3372f5ce95 100644--- a/crates/openhuman-core/src/inference/readiness_tests.rs+++ b/crates/openhuman-core/src/inference/readiness_tests.rs@@ -9,6 +9,8 @@ async fn cached_probe_serves_definitive_negative_results() {use std::sync::atomic::{AtomicUsize, Ordering};use std::sync::Arc;+ let _model_override_guard =+ crate::inference::provider::factory::test_provider_override::exclusive();let tmp = TempDir::new().unwrap();let mut config = Config {workspace_dir: tmp.path().join("workspace"),