agent-rita

Use every time the user asks to fix, debug, repair, patch, harden, clean up, or investigate broken behavior in this repo. Applies especially to agent harness, model/tool routing, SQL family, widget data, MCP, streaming, workspace bridge, citations, artifacts, evals, and tests. Enforces the repo's lean-harness rule: reproduce defects faithfully, fix at the root, keep the model responsible for choosing paths, avoid deterministic retries, avoid content/word-based routing, avoid hidden normalization, and reject overfit special cases.

Reproduce-and-fix loop for bugs in this repo (Hono + Bun + Vercel AI SDK + MCP). Write a FAILING test/eval that reproduces the bug FIRST, confirm it fails for the RIGHT reason, apply the minimal fix, confirm it passes — the test/eval stays as a regression guard. Use when fixing a reported bug, "X is broken / doesn't work", wrong tool routing, wrong/missing answer, or hardening a defect-prone path. For adding coverage to already-working code, just write the test in the right tier per TESTING.md.