This is a follow-up to my previous post on routing agents through LiteLLM. That post covered the architecture. This one covers what broke when I actually ran it.

Claude Code Doesn't Pass Through Arbitrary Model Names

The first thing I got wrong: I assumed model: local-sonnet in agent frontmatter would …

This is a follow-up to my previous post where I covered reducing token costs in a multi-agent pipeline. That post touched on local model fallback at a high level. This one goes deeper on how the routing layer actually works.

The Pipeline

I have five agents, split across two tiers …

Running a multi-agent pipeline for security research gets expensive fast. I have several agents doing sequential analysis work - reading commit diffs, running adversarial bypass analysis, building proof-of-concept exploits. Token costs compound at every step: system prompts, tool schemas, conversation history, and verbose outputs all stack up before a single useful …

Breach Report!

Why am I writing about healthcare breach reports? Well I like data, especially unsexy data. Also a couple friends (you might know who) and I are looking into some unsexy parts of industries that are underserved and in need of help to make impact for the better good …

I have been pretty facinated with type promotion bugs in the recent months. Why? Because I love when there is some crazy mixed data types with arithmetic. Something about math (in)correctly implemented always makes me geek out. For those not familiar with Type promotion, it's when data type values …