Iii Error Handling logo

Iii Error Handling

OrganizationPopular
iii-hq
iii-error-handling

Handle iii engine and SDK errors across Node, Python, Rust, and browser workers. Use when interpreting error codes, retryability, RBAC denial, timeouts, handler failures, or SDK-specific exception surfaces.

Overview

Publisheriii-hq
Repositoryiii
Skill nameiii-error-handling
Stars
18.8K
Forks
1.3K
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by iii-hq on GitHub. Read the source before you install it.

Installation

Install the Iii Error Handling AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/iii-hq/iii/tree/main/skills/iii-error-handling
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/iii-hq/iii.git /tmp/iii
mkdir -p .claude/skills
cp -r /tmp/iii/skills/iii-error-handling .claude/skills/iii-error-handling
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Iii Error Handling in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Iii Error Handling on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Iii Error Handling is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Error Handling

iii has two broad error classes: SDK/local errors and engine/remote invocation errors. Agents should branch on the error code instead of matching only message strings.

Error Codes

Branch on exact code strings, but keep engine wire codes separate from SDK-local codes.

CodeEmitted byMeaningTypical handling
function_not_foundEngine and SDK local dispatchNo registered function is available under that IDCheck function ID, worker install/startup, discovery, and trigger type hints
invocation_errorEngine invocation/router pathEngine failed to route, record, or complete the invocationInspect engine logs, protocol state, and worker connectivity
invocation_stoppedEngine invocation handlerInvocation was cancelled or stopped by the engine/runtimeTreat as failed work; decide whether caller should retry
FORBIDDENRBAC / worker-gated engine functionsRBAC denied the actionDo not retry blindly; inspect policy, auth context, and allowed functions
timeoutA target worker's handler, forwarded verbatim by the engineNot produced by the engine or the Node/Python SDKs (they emit TIMEOUT); appears only if the worker you called returns itTreat as a timeout if you know the target worker emits it; otherwise branch on TIMEOUT
function_not_invokableSDK local dispatchRegistration exists but cannot be invoked as a normal local functionInspect registration/invocation type
invocation_failedSDK worker handler wrappersLocal worker handler, HTTP-invoked function wrapper, or SDK-side handler path failedInspect handler logs, stacktrace, and payload validation
TIMEOUTNode/Python SDK caller timeoutClient waited longer than trigger() timeoutIncrease timeout only if the workload is expected to run long; otherwise optimize or enqueue

Handler vs Engine Errors

  • Handler errors originate in user function code, SDK local dispatch, or HTTP-invoked endpoints.
  • Engine errors originate in routing, invocation state, RBAC, protocol handling, or worker-reported wire errors.
  • Queue retries only apply to enqueued work. Synchronous failures are returned directly to the caller.
  • Void dispatch does not return handler results, so use logs/observability for failures.

Retryability

  • Retry transient TIMEOUT (or a lowercase timeout returned by a target worker), transport, or worker reconnect failures only when the operation is idempotent.
  • Do not retry FORBIDDEN without changing auth/policy.
  • Do not retry function_not_found by calling the same ID repeatedly; discover functions or install/start the missing worker.
  • For reliable background work, use TriggerAction.Enqueue({ queue }) and queue retry/DLQ policy.

SDK Surfaces

Node

typescript
import { InvocationError } from 'iii-sdk'

try {
  await iii.trigger({ function_id: 'orders::charge', payload })
} catch (error) {
  if (error instanceof InvocationError && error.code === 'FORBIDDEN') {
    throw new Error('Policy denied orders::charge')
  }
  throw error
}

Python

python
from iii import InvocationError

try:
    result = iii.trigger({"function_id": "orders::charge", "payload": payload})
except InvocationError as exc:
    if exc.code == "FORBIDDEN":
        raise RuntimeError("Policy denied orders::charge")
    if exc.code in ("TIMEOUT", "timeout"):  # SDK caller timeout, or a lowercase code returned by the target worker
        raise RuntimeError("orders::charge timed out")
    raise RuntimeError(f"{exc.code}: {exc.message}")

Rust

rust
match iii.trigger(request).await {
    Ok(value) => value,
    Err(iii_sdk::Error::Timeout) => {
        return Err("orders::charge timed out".into());
    }
    Err(iii_sdk::Error::Remote { code, message, .. }) if code == "FORBIDDEN" => {
        return Err(format!("policy denied: {message}").into());
    }
    Err(err) => return Err(err.into()),
}

Browser

Browser trigger calls reject with JavaScript errors. Preserve the engine-provided code/message when present and show policy failures as permission errors in UI.

Pattern Boundaries

  • For invocation modes and enqueue decisions, prefer iii-core-primitives.
  • For SDK-specific exception classes and syntax, prefer iii-sdk-reference.
  • For workflow-level retry and DLQ design, prefer iii-architecture-patterns.
  • For RBAC policy design see the rbac-proxy worker; for logs and traces around worker failures, use the matching worker page on https://workers.iii.dev/.

When to Use

  • Use this skill when the task mentions iii errors, exception handling, failed invocations, timeouts, forbidden calls, retry behavior, or SDK error classes.

Boundaries

  • Do not retry non-idempotent work automatically unless it is enqueued under queue policy.
  • Do not treat RBAC denial as a missing worker.
  • Do not generate removed service APIs or adapter-extension APIs.

Frequently asked questions

What does the Iii Error Handling AI skill do?

Handle iii engine and SDK errors across Node, Python, Rust, and browser workers. Use when interpreting error codes, retryability, RBAC denial, timeouts, handler failures, or SDK-specific exception surfaces.

Why use Iii Error Handling on TypingMind?

Because you install it once and use it with any model. Iii Error Handling is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Iii Error Handling in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/iii-hq/iii/tree/main/skills/iii-error-handling. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Iii Error Handling?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Iii Error Handling?

As many as you like. As long as a model supports skills, you can use Iii Error Handling with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Iii Error Handling AI skill free?

It is published on GitHub by iii-hq. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇