I wrote a small proxy that points points to a jev api and a frontier api.
My harness connects to the proxy and only sees the frontier api, models, commands, etc. When I send prompts with tool calls, proxy routes to jev, jev narrows the tools, proxy cleans/sends to the frontier api.
So far in my tests, about 60% less tool calls. I'm also going to implement model switching, so it can use cheaper models. I think my workbench harness needs its prompts cleaned up.
So far in my tests, about 60% less tool calls. I'm also going to implement model switching, so it can use cheaper models. I think my workbench harness needs its prompts cleaned up.