/deepagents-code-review

name: deepagents-code-review
description: Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common configuration and usage mistakes.

Deep Agents Code Review

When reviewing Deep Agents code, check for these categories of issues.

Anti-confabulation (gate 0 — runs before every other gate)

Before issuing **any** finding — flag a bug, anti-pattern, or improvement — you MUST echo the exact artifact you are judging, quoted from a source you read in **this** turn:

• The code finding: its `file:line` plus the cited code, read freshly now.
• The agent code under review: the `create_deep_agent`, backend, subagent, or middleware snippet your finding depends on, quoted from the file you just read.

> The artifact is the only source of truth. **Never** infer what you are reviewing from the branch name, the working directory, surrounding files, or recollection. If your mental model differs from the freshly read source, **the source wins.** A finding issued without a same-turn echo of its target is invalid — emit the echo first, or do not emit the finding.

This gate exists because an LLM under contextual priming will confidently flag code that is not in the file. It runs **before** the gates below.

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

# BAD - interrupt_on without checkpointer
agent = create_deep_agent(
    tools=[send_email],
    interrupt_on={"send_email": True},
    # No checkpointer! Interrupts will fail
)

# GOOD - checkpointer required for interrupts
from langgraph.checkpoint.memory import InMemorySaver

agent = create_deep_agent(
    tools=[send_email],
    interrupt_on={"send_email": True},
    checkpointer=InMemorySaver(),
)

2. Missing Store with StoreBackend

# BAD - StoreBackend without store
from deepagents.backends import StoreBackend

agent = create_deep_agent(
    backend=lambda rt: StoreBackend(rt),
    # No store! Will raise ValueError at runtime
)

# GOOD - provide store
from langgraph.store.memory import InMemoryStore

store = InMemoryStore()
agent = create_deep_agent(
    backend=lambda rt: StoreBackend(rt),
    store=store,
)

3. Missing thread_id with Checkpointer

# BAD - no thread_id when using checkpointer
agent = create_deep_agent(checkpointer=InMemorySaver())
agent.invoke({"messages": [...]})  # Error!

# GOOD - always provide thread_id
config = {"configurable": {"thread_id": "user-123"}}
agent.invoke({"messages": [...]}, config)

4. Relative Paths in Filesystem Tools

# BAD - relative paths not supported
read_file(path="src/main.py")
read_file(path="./config.json")

# GOOD - absolute paths required
read_file(path="/workspace/src/main.py")
read_file(path="/config.json")

5. Windows Paths in Virtual Filesystem

# BAD - Windows paths rejected
read_file(path="C:\\Users\\file.txt")
write_file(path="D:/projects/code.py", content="...")

# GOOD - Unix-style virtual paths
read_file(path="/workspace/file.txt")
write_file(path="/projects/code.py", content="...")

Backend Issues

6. StateBackend Expecting Persistence

# BAD - expecting files to persist across threads
agent = create_deep_agent()  # Uses StateBackend by default

# Thread 1
agent.invoke({"messages": [...]}, {"configurable": {"thread_id": "a"}})
# Agent writes to /data/report.txt

# Thread 2 - file won't exist!
agent.invoke({"messages": [...]}, {"configurable": {"thread_id": "b"}})
# Agent tries to read /data/report.txt - NOT FOUND

# GOOD - use StoreBackend or CompositeBackend for cross-thread persistence
agent = create_deep_agent(
    backend=CompositeBackend(
        default=StateBackend(),
        routes={"/data/": StoreBackend(store=store)},
    ),
    store=store,
)

7. FilesystemBackend Without root_dir Restriction

# BAD - unrestricted filesystem access
agent = create_deep_agent(
    backend=FilesystemBackend(root_dir="/"),  # Full system access!
)

# GOOD - scope to project directory
agent = create_deep_agent(
    backend=FilesystemBackend(root_dir="/home/user/project"),
)

8. CompositeBackend Route Order Confusion

# BAD - shorter prefix shadows longer prefix
agent = create_deep_agent(
    backend=CompositeBackend(
        default=StateBackend(),
        routes={
            "/mem/": backend_a,        # This catches /mem/long-term/ too!
            "/mem/long-term/": backend_b,  # Never reached
        },
    ),
)

# GOOD - CompositeBackend sorts by length automatically
# But be explicit about your intent:
agent = create_deep_agent(
    backend=C