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): update provider imports
Steven Enamakeld4b4115c5282
diff --git a/crates/openhuman-core/src/inference/provider/factory.rs b/crates/openhuman-core/src/inference/provider/factory.rsindex 8fe0553104..edee170dac 100644--- a/crates/openhuman-core/src/inference/provider/factory.rs+++ b/crates/openhuman-core/src/inference/provider/factory.rs@@ -55,7 +55,7 @@ pub(crate) use managed_backend::{make_openhuman_backend_model_for_options, make_openhuman_backend_model_for_thread_in,make_openhuman_backend_model_in,};-use subprocess_providers::{build_claude_code_model, claude_agent_sdk_model_from_string};+use subprocess_providers::OpenHumanMcpEndpoint;use tinyinference_providers::route::split_model_and_temperature;/// Test-only seam: inject a mock [`ChatModel`] so e2e tests can drive the@@ -82,7 +82,6 @@ use crate::config::Config;use crate::security::credentials::AuthService;use crate::security::egress::EgressLedger;use std::sync::Arc;-use tinyagents_harness::providers::claude_agent_sdk::ClaudeAgentSdkProvider;use tinyinference_llm::model::{ChatModel, ModelRequest, ModelResponse, ModelStream};use tinyinference_llm::providers::openai::codex::{openai_codex_client_version, openai_codex_user_agent, OPENAI_CODEX_ACCOUNT_HEADER,