Hermes Agent Outperforms Codex in Multi-Turn Tasks After Optimizations

Some new improvements to performance just went in. Python gets a bad wrap for performance but we aint looking to shabby against a trillion dollar co's rust codebase, beating codex at most multi-turn tasks we benchmarked (mt stands for multiturn) PR: https://github.com/NousResearch/hermes-agent/pull/31968