Terminal agents are growing a new kind of muscle: not just better tools, but better middleware. In both Codex and Gemini CLI, the moment right after you hit Enter is becoming programmable territory.
The newest source-readable trail points away from model mystique and toward the workflows that test, trace, serialize, and maintain agent behavior.
After shipping more visible control planes, agent projects are now tightening the places where tools, plugins, credentials, chat context, and test runs are allowed to flow.
A set of Codex, Hermes Agent, Gemini CLI, and Crush commits shows agent tools packaging the machinery around the model: shells, platform adapters, context profiles, and skill catalogs.
Recent Crush and LangChain changes show agent infrastructure turning hidden boundaries - shell permission, context overflow, and model token limits - into runtime contracts that users and developers can see.
The long-form map behind the daily paper: context, tools, loops, memory, delegation, safety, interface, and trust.