If You’re Not Using These Three Guards in Your AI Agent, It Has Already Sent

Use this as an operator-facing rebuild of the ideas in “If You’re Not Using These Three Guards in Your AI Agent, It Has Already Sent Your Secrets to the Provider”: clear stages, ordered code slots, and recovery notes that survive a handoff. The Overview stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline.

First: What is middleware, and why does it exist?

For the First What is middleware stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion. Put human approval on edges that spend money or change production data. Compile-time wiring does not equal business completeness.

The guard that catches secrets before they reach the model:

For the The guard that catches stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments. Prefer structured outputs with schema validation over free-form prose when the next step is code or a tool call.

PIIMiddleware

For the PIIMiddleware stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph. Put human approval on edges that spend money or change production data. Compile-time wiring does not equal business completeness. For the PIIMiddleware stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline.

from langchain.agents.middleware import PIIMiddleware

PIIMiddleware(
    "email",
    strategy="redact",            # replaces match with [REDACTED_EMAIL]
    apply_to_input=True,          # scans what you type
    apply_to_tool_results=True,   # scans what tools return - never skip this
)

import re
API_KEY_PATTERN = r"(?:sk-|ghp_|AKIA)[a-zA-Z0-9]{20,48}"
# sk-   → OpenAI and Anthropic keys
# ghp_  → GitHub personal access tokens
# AKIA  → AWS access key IDs
PIIMiddleware(
    "api_key",
    detector=API_KEY_PATTERN,
    strategy="redact",
    apply_to_input=True,
    apply_to_tool_results=True,
)

The approval gate that stops silent deletions:

When working through the The approval gate that stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.

HumanInTheLoopMiddleware

When working through the HumanInTheLoopMiddleware stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.

from langchain.agents.middleware import HumanInTheLoopMiddleware
from langgraph.checkpoint.sqlite import SqliteSaver

# The checkpointer is not optional. Without it, resume is impossible.
with SqliteSaver.from_conn_string("./review_agent.db") as checkpointer:
    agent = create_agent(
        model="anthropic:claude-sonnet-4-20250514",
        tools=[read_file, list_directory, write_file, search_codebase],
        middleware=[
            HumanInTheLoopMiddleware(
                interrupt_on={
                    "write_file": True,       # always pause before writing
                    "read_file": False,        # reading is safe - no pause needed
                    "list_directory": False,
                    "search_codebase": False,
                }
            ),
        ],
        checkpointer=checkpointer,            # saved to SQLite, persists across restarts
    )

# First call — agent hits the interrupt at write_file and pauses
result = agent.invoke(
    {"messages": [{"role": "user", "content": "Review and fix the config files"}]},
    config={"configurable": {"thread_id": "session-001"}}
    # thread_id ties the saved state to this specific session
)


# result.interrupted == True
# result.pending_tool_call == {"name": "write_file", "args": {"path": "src/config.py", ...}}
# You show this to the user and wait for approval
# User approves - resume the same thread
final_result = agent.invoke(
    Command(resume=True),
    config={"configurable": {"thread_id": "session-001"}}
    # same thread_id - loads state from the checkpointer and picks up where it stopped
)

Two rate limits, two different failure modes you need both

When working through the Two rate limits two stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node. When working through the Two rate limits two stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline.

from langchain.agents.middleware import ModelCallLimitMiddleware, ToolCallLimitMiddleware

ModelCallLimitMiddleware(
    max_calls=30,
    on_limit="raise",   # raises MaxCallsExceeded - catch this in your application
)
ToolCallLimitMiddleware(
    max_calls=60,
    on_limit="raise",
)

The ordering rule that almost no tutorial mentions and that silently breaks your safety layer

The The ordering rule that stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.

middleware=[
    # PIIMiddleware always first — it must see raw, untransformed data
    PIIMiddleware("api_key", detector=API_KEY_PATTERN, strategy="redact",
                  apply_to_input=True, apply_to_tool_results=True),
    PIIMiddleware("email", strategy="redact",
                  apply_to_input=True, apply_to_tool_results=True),

# Limits next - exact position within the group is flexible
    ModelCallLimitMiddleware(max_calls=30, on_limit="raise"),
    ToolCallLimitMiddleware(max_calls=60, on_limit="raise"),
    # Human-in-the-loop last in the safety group
    # (it fires in the after_model hook regardless of list position,
    # but last is a readable convention)
    HumanInTheLoopMiddleware(interrupt_on={"write_file": True}),
]

Putting it together: A code review agent with the same safety properties as Cursor

The Putting it together A stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.

from langchain.agents import create_agent
from langchain.agents.middleware import (
    PIIMiddleware,
    HumanInTheLoopMiddleware,
    ModelCallLimitMiddleware,
    ToolCallLimitMiddleware,
)
from langgraph.checkpoint.sqlite import SqliteSaver

# Custom pattern for secrets common in codebases
API_KEY_PATTERN = r"(?:sk-|ghp_|AKIA)[a-zA-Z0-9]{20,48}"
# sk-   → OpenAI / Anthropic keys
# ghp_  → GitHub personal access tokens
# AKIA  → AWS access key IDs
with SqliteSaver.from_conn_string("./review_agent.db") as checkpointer:
    agent = create_agent(
        model="anthropic:claude-sonnet-4-20250514",
        tools=[read_file, list_directory, write_file, search_codebase],
        middleware=[
            # 1. Catch secrets before they reach the model - on both surfaces
            PIIMiddleware(
                "api_key",
                detector=API_KEY_PATTERN,
                strategy="redact",
                apply_to_input=True,
                apply_to_tool_results=True,  # this is the one that catches .env reads
            ),
            PIIMiddleware(
                "email",
                strategy="redact",
                apply_to_input=True,
                apply_to_tool_results=True,
            ),
            # 2. Hard resource limits - stops infinite loops and runaway sessions
            ModelCallLimitMiddleware(max_calls=30, on_limit="raise"),
            ToolCallLimitMiddleware(max_calls=60, on_limit="raise"),
            # 3. Approval gate - nothing gets written without your explicit sign-off
            HumanInTheLoopMiddleware(
                interrupt_on={
                    "write_file": True,
                    "read_file": False,
                    "list_directory": False,
                    "search_codebase": False,
                }
            ),
        ],
        checkpointer=checkpointer,  # required for interrupt/resume to work
    )

Agent: I'd like to update src/config.py to fix the circular import.
       Here is what I plan to write:
--- src/config.py ---
       from typing import Optional
       from pydantic import BaseModel
       class Settings(BaseModel):
           debug: bool = False
           database_url: str = "sqlite:///app.db"
       ...
       Approve this change? (yes/no)
User: yes
Agent: Written. Moving to tests/test_config.py next.

The agent cannot touch anything silently. Every write surfaces for review before it happens. Secrets in any file the agent reads are replaced with [REDACTED_API_KEY] before reaching the model — which also means they never appear in the approval prompt you read. What you are reviewing is already clean.

Operational checklist

When working through the Operational checklist stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest.

Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish.

Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.

Pin dependency versions and record the image digest that ran the demo. Reproducibility beats tribal knowledge.

Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline.

Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.

Before promoting the stack, freeze versions, capture a golden transcript for the critical path, and confirm rollback steps. Shared environments need rate limits, tenancy checks, and a clear owner for secret rotation. Prefer boring reliability over clever one-off demos.

Batch note for 8540643b792a: keep provider keys out of the repo, set a per-session token ceiling, and store transcripts next to the eval fixtures so later model swaps stay comparable.

For the hardening note 0 stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish.

Hardening detail 0/723: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.

When working through the hardening note 1 stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion.

Hardening detail 1/723: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.

The hardening note 2 stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph.

Hardening detail 2/723: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.

For the hardening note 3 stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline.

Hardening detail 3/723: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.

When working through the hardening note 4 stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments.

Hardening detail 4/723: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.

The hardening note 5 stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish.

Hardening detail 5/723: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.