Langgraph Error Handling

What it does

When your agent uses it

• Users need to classify failures
• Add RetryPolicy for transient issues
• Build LLM recovery loops with Command routing
• Add human-in-the-loop with interrupt()/resume

Example prompts

• “/langgraph-error-handling”

Requirements

• Python 3
• Node.js

Workflow steps

3 steps, taken from the step headings in SKILL.md.

1. 1Retry Transient Failures
2. 2LLM Recovery Loop
3. 3Human-In-The-Loop Escalation

What it can do on your machine

Read from SKILL.md and the folder at commit a2d4a10. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (JavaScript and Python, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • uv

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Langgraph Error Handling loads about 1.5k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 387 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~88

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~18k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from soba-labs/langchain-agent-skills at commit a2d4a10, republished under its MIT licence (© soba-labs). 387 words, ~1,488 tokens.

name

langgraph-error-handling

description

Implement LangGraph error handling with current v1 patterns. Use when users need to classify failures, add RetryPolicy for transient issues, build LLM recovery loops with Command routing, add human-in-the-loop with interrupt()/resume, handle ToolNode errors, or choose a safe strategy between retry, recovery, and escalation.

from langgraph.types import RetryPolicy

builder.add_node(
    "call_api",
    call_api,
    retry_policy=RetryPolicy(max_attempts=3, initial_interval=1.0),
)

builder.addNode("callApi", callApi, {
  retryPolicy: { maxAttempts: 3, initialInterval: 1.0 },
});

from typing import Literal
from typing_extensions import NotRequired
from langgraph.graph import MessagesState
from langgraph.types import Command

class State(MessagesState):
    error: NotRequired[str]
    retry_count: NotRequired[int]

def agent(state: State) -> Command[Literal["tool", "__end__"]]:
    if state.get("retry_count", 0) >= 3:
        return Command(goto="__end__")
    if state.get("error"):
        return Command(goto="tool")
    return Command(goto="tool")

import { StateGraph, Command, END } from "@langchain/langgraph";

// If a node returns Command in JS, add `ends` on addNode.
builder.addNode("agent", agentNode, { ends: ["tool", END] });

from langgraph.types import interrupt, Command

def human_review(state):
    approved = interrupt({
        "question": "Proceed?",
        "payload": state["pending_action"],
    })
    return Command(goto="execute" if approved else "cancel")

# resume
graph.invoke(Command(resume=True), config={"configurable": {"thread_id": "t-1"}})

import { Command, interrupt } from "@langchain/langgraph";

const approved = interrupt({ question: "Proceed?" });
// later
await graph.invoke(new Command({ resume: true }), {
  configurable: { thread_id: "t-1" },
});

from langgraph.prebuilt import ToolNode

tool_node = ToolNode(tools, handle_tool_errors=True)
tool_node = ToolNode(tools, handle_tool_errors="Please try again.")
tool_node = ToolNode(tools, handle_tool_errors=(ValueError, TypeError))

uv run skills/langgraph-error-handling/scripts/classify_error.py TimeoutError --verbose
uv run skills/langgraph-error-handling/scripts/wrap_with_retry.py call_llm --with-llm-recovery

© soba-labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 15 other files (scripts, references, assets) in skills/langgraph-error-handling of soba-labs/langchain-agent-skills.

• SKILL.md
• assets/examples/human-loop-example/js/index.js
• assets/examples/human-loop-example/js/package.json
• assets/examples/human-loop-example/python/graph.py
• assets/examples/human-loop-example/python/requirements.txt
• assets/examples/retry-example/js/index.js
• assets/examples/retry-example/js/package.json
• assets/examples/retry-example/python/graph.py
• assets/examples/retry-example/python/requirements.txt
• references/error-types.md
• references/human-escalation.md
• references/llm-recovery.md
• … and 4 more

Open the folder on GitHubat commit a2d4a10