Coding Review — LangGraph

Files

• graph_coding_review.py — LangGraph nodes + interrupt
• README.md — Run notes

Full prompt / config / code

Copy

# graph_coding_review.py — Coding Review (LangGraph sketch)
# pip install langgraph langchain-core (pin yourself)
# Use a local chat model binder; do not embed secrets.

from typing import TypedDict, Literal
from langgraph.graph import StateGraph, END

SYSTEM = """You are a code review specialist. Goal: find bugs and risks in the pasted diff/file.

RULES:
- Do not rewrite the whole codebase. Comment on the provided snippet only.
- Flag: correctness, security, missing tests, irreversible ops, secrets.
- Never suggest committing secrets, force-push, or rm -rf style cleanup.
- Propose patches as unified-diff style snippets when useful.
- Stop with a severity-ordered list. Human decides merges.

OUTPUT:
1) Summary (2-4 sentences)
2) Issues table: severity | location | issue | suggested fix
3) Tests to add
4) What looks fine"""

class State(TypedDict):
    user_input: str
    draft: str
    approved: bool
    notes: str

def produce(state: State) -> State:
    # Pseudo: call your local model with SYSTEM + state["user_input"]
    draft = "[MODEL OUTPUT PLACEHOLDER — wire your local LLM here]\n" + state["user_input"][:500]
    return {**state, "draft": draft, "notes": "awaiting human"}

def human_gate(state: State) -> State:
    # In real use: interrupt / input() / UI approval.
    # Default False so nothing auto-publishes.
    return {**state, "approved": False}

def route_after_gate(state: State) -> Literal["done", "revise"]:
    return "done" if state.get("approved") else "done"  # stage-1: always end after gate

g = StateGraph(State)
g.add_node("produce", produce)
g.add_node("human_gate", human_gate)
g.set_entry_point("produce")
g.add_edge("produce", "human_gate")
g.add_conditional_edges("human_gate", route_after_gate, {"done": END, "revise": "produce"})
app = g.compile()

if __name__ == "__main__":
    out = app.invoke({"user_input": "PASTE_EXAMPLE_IN", "draft": "", "approved": False, "notes": ""})
    print(out)

Example in

Review this Python snippet:
```
def pay(user, amount):
    charge(user.card, amount)
    send_receipt(user.email)
```
Context: internal tool, no retries yet.

Example out

Summary: Charge-then-receipt with no idempotency or failure handling.
Issues:
- high | charge() | no idempotency key | add key + status check
- med | send_receipt | may fire after partial failure | gate on success
Tests: simulate charge timeout; duplicate submit.
Looks fine: clear happy-path shape.

Model / runtime notes

Graph includes an explicit human checkpoint. Stage-1 ends after gate (no infinite revise loop).

Canonical Team

Parent: coding-review · implementation_id: langgraph/coding-review

GitHub source

teams/coding-review/langgraph · commit eb87e8e049fdf9908e438305ff827c7b617505b5 · license: free-use-at-own-risk

Structural check: PASS · env: structural (structural only — does not set Verified)

Related Library items

• ollama/coding-review
• lm-studio/coding-review
• open-webui/coding-review
• n8n/coding-review

Related marketplace Team pages

Soft thematic links only — not identity merges. Marketplace Teams ≠ Library AI Team records.

• Claude Review (marketplace Team page — separate entity)
• Claude PR (marketplace Team page — separate entity)