Command Code

Harness Engineering

Models hallucinate and make mistakes. The harness is what decides whether that ruins your session.

Most of what gets reported as a model failing is really a model plus a harness failing, with the harness left out of the description. This section is where we write up the harness side: what breaks, what we fixed, and what the numbers looked like before and after.

Posts

Tool Call Repairs Four repeating mistakes cover most open-model tool call failures. Repairing them, and telling the model what it should have sent, is what makes them stop.

The Read Tool The highest-volume tool in the harness, rebuilt around cost per successful read. Bounded windows, recovery notes, a read-before-write ledger, and a benchmark of ten harnesses.

In progress

  • Cache repairs, on keeping prompt caches intact across long sessions.
  • Cache thrash repairs, on the edit patterns that quietly invalidate a cache mid-session.
  • /design engineering, on the same audit-then-treat idea applied to visual design.