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
feat(embed): add provider options and reasoning effort setters
Steven Enamakelc77e08bc4d33
diff --git a/crates/openhuman-embed/src/harness/provider.rs b/crates/openhuman-embed/src/harness/provider.rsindex 5f018dea05..dc472e6362 100644--- a/crates/openhuman-embed/src/harness/provider.rs+++ b/crates/openhuman-embed/src/harness/provider.rs@@ -96,6 +96,24 @@ impl Provider {}}+ /// Set provider-specific defaults on this routed provider. Requests may+ /// override these values by key.+ pub fn provider_options(mut self, options: serde_json::Value) -> Self {+ if let Some(route) = self.route.as_mut() {+ route.provider_options = Some(options);+ }+ self+ }++ /// Set the reasoning effort used for this provider's model, including+ /// runtime-owned scheduled work.+ pub fn reasoning_effort(mut self, effort: tinyinference_llm::model::ReasoningEffort) -> Self {+ if let Some(route) = self.route.as_mut() {+ route.reasoning_effort = Some(effort);+ }+ self+ }+/// Use whatever inference the machine's own configuration resolves to —/// the account's managed backend, or a local Ollama / LM Studio, or a BYOK/// provider.