deepagents-code-reviewlisted

# Deep Agents Code Review When reviewing Deep Agents code, check for these categories of issues. ## Review gates (evidence-bound) Run these steps in order before and while you write findings. Skipping a step is a failed review. 1. **Locate** — Enumerate call sites in scope (`create_deep_agent`, `CompiledSubAgent`, `CompositeBackend`, custom `backend=`, `interrupt_on`, `checkpointer`, `store`). **Pass:** You list each relevant **file path** and **line number** (or a grep/search result that proves where the code lives). 2. **Anchor** — For each suspected issue, tie it to **quoted or line-referenced code** from those files, not to imports or names alone. **Pass:** Every finding includes **evidence** (`path:line` plus a short quote or “absent parameter” note showing the gap). 3. **Classify** — Map each anchored issue to one category below (Critical → Performance) and a severity. **Pass:** The category label matches what the cited code actually does or omits. 4. **Runtime claims** — If you say something will error, fail at runtime, or leak data, **Pass:** The cited snippet shows the exact API combo (e.g. `interrupt_on` set with no `checkpointer` in the same construction path), or you state **uncertain** and what would confirm it. If you cannot satisfy step 1, stop and say what file or search is missing instead of inferring issues from memory. ## Critical Issues ### 1. Missing Checkpointer with interrupt_on ```python # BAD - interrupt_on without checkpointer agent = create_