n8n/AGENTS.md

AGENTS.md

This file provides guidance on how to work with the n8n repository.

Project Overview

n8n is a workflow automation platform written in TypeScript, using a monorepo structure managed by pnpm workspaces. It consists of a Node.js backend, Vue.js frontend, and extensible node-based workflow engine.

General Guidelines

• Always use pnpm
• Secrets on the command line: if a developer opted into anonymous dev metrics (scripts/dev-metrics), pnpm command arguments are recorded. Arguments of secret-carrying words (config, login, publish, token) — whether a subcommand or baked into a flag — are dropped, and the home dir is stripped from paths, but other args are sent as-is — so never put secrets in a command. Pass sensitive values via environment variables, which are never captured.
• When adding comments, keep them concise and to the point - explain the "why" in a line or two; don't be overly verbose. Comments should be scoped and relevant to the surrounding code, not just to the current task
• We use Linear as a ticket tracking system
• We use Posthog for feature flags
• To find registered telemetry events (names, descriptions, properties), run pnpm --filter @n8n/telemetry catalog (--json for structured output). The registry is being adopted incrementally, so search call sites if the catalog has no match. The n8n:telemetry skill covers adding or changing events
• When starting to work on a new ticket – create a new branch from fresh master with the name specified in Linear ticket
• When creating a new branch for a ticket in Linear - use the branch name suggested by Linear, unless it is a security fix (see Security Fix Hygiene below)
• Use mermaid diagrams in MD files when you need to visualise something
• Developing v3 features: land normal feature work on master behind an opt-in flag; introduce breaking changes only on the 3.x branch. See .github/DEVELOPING_V3.md.

Agent Skills and Claude Code Plugin

n8n shared skills live in .agents/skills/. Claude Code consumes them through symlinks in .claude/plugins/n8n/skills/; OpenCode reads .agents/skills/ directly. Harness-specific overrides remain real directories in the harness path, such as .opencode/skills/setup-mcps/. See skills README for editing and sync guidance.

n8n-specific Claude Code commands and agents live in .claude/plugins/n8n/ and are namespaced under n8n:. Use n8n: prefix when invoking them (e.g. /n8n:create-pr, /n8n:plan, n8n:developer agent). See plugin README for structure and details.

Essential Commands

Fresh checkout / agent setup

For a fresh checkout (cat-bot, a new hire, any agent verifying the repo builds), prefer pnpm agent:setup over running install + build + tests by hand. It chains them in one process, caps per-process memory and turbo concurrency so a 6GB box doesn't OOM, streams all output to .agent-setup/<step>.log (gitignored), and surfaces only a one-line summary per step plus the tail of the failing log. A machine-readable .agent-setup/summary.json is always written so a backgrounded run is readable in a single shot — no polling, no scrolling logs.

pnpm agent:setup                 # install → build → test (full suite)
pnpm agent:setup install         # one step at a time
pnpm agent:setup --json          # JSON summary on stdout (for scripts/agents)

Building

Use pnpm build to build all packages. ALWAYS redirect the output of the build command to a file:

pnpm build > build.log 2>&1

You can inspect the last few lines of the build log file to check for errors:

tail -n 20 build.log

If build outputs or the turbo cache are stale (e.g. after switching branches or worktrees) but dependencies haven't changed, use pnpm reset (lightweight by default) for a fast recovery: it cleans build outputs and force-rebuilds (keeping node_modules and untracked files). If that doesn't fix your issue, use pnpm reset --full, which also wipes untracked files and reinstalls dependencies.

Seeding a local instance with realistic data

An empty instance is a bad place to test anything that reasons about a user's work. Two seeds exist, and they do different jobs:

pnpm seed:account       # one plausible account: 10 workflows, credentials, runs, AI threads
pnpm inspect:activity   # a one-page viewer for the activity_event table

pnpm seed:account fills a local SQLite instance with a small, deliberately consistent estate — ten workflows that all use the Anthropic chat model and all touch Linear, the two data tables they read, working credentials built from your own API tokens, a fortnight of execution history, Instance AI conversations about those workflows, and (on builds that have the migration) a matching activity log. ANTHROPIC_API_KEY and LINEAR_API_KEY are optional — supply them (shell or packages/cli/.env) and the workflows run for real; leave them out and the credentials are still created and attached, holding a placeholder labelled (seed, fake key), so nothing is half-wired. Re-running with a token set upgrades the credential in place.

Reach for it whenever you need an instance that looks used: manual UI checks, demos, anything reading execution history, data tables, AI threads, or the activity log. Its consistency is deliberate — for every job where n8n offers a choice, exactly one node is used everywhere, so it doubles as a fixture for anything reasoning about what a user tends to reach for. Adding a workflow means following the CHOICES table in the script rather than picking again.

pnpm inspect:activity serves a single page on 127.0.0.1:5699 showing every column of activity_event, paginated, sortable on any column, with a free-text filter that searches the JSON data column too — so a run id or a failing node name finds its entry without knowing which field holds it. Read-only, no build step, no dependency, and loopback-only; it is a debug surface, not a product page, and the whole table is served unauthenticated to anything that can reach the port.

For a large synthetic org instead — ~500 workflows across ~30 projects, for dependency-graph and perf work — use scripts/instance-seeding/seedInstance.mjs. Both are documented in scripts/instance-seeding/AGENTS.md, including why credentials cannot be shared in a seed file.

Testing

• pnpm test - Run all tests
• pnpm test:affected - Runs tests based on what has changed since the last commit

Running a particular test file requires going to the directory of that test and running: pnpm test <test-file>.

When changing directories, use pushd to navigate into the directory and popd to return to the previous directory. When in doubt, use pwd to check your current directory.

Code Quality

• pnpm lint - Lint code
• pnpm typecheck - Run type checks

Always run lint and typecheck before committing code to ensure quality. Execute these commands from within the specific package directory you're working on (e.g., cd packages/cli && pnpm lint). Run the full repository check only when preparing the final PR. When your changes affect type definitions, interfaces in @n8n/api-types, or cross-package dependencies, build the system before running lint and typecheck.

Architecture Overview

Monorepo Structure: pnpm workspaces with Turbo build orchestration

Package Structure

The monorepo is organized into these key packages:

• packages/@n8n/api-types: Shared TypeScript interfaces between frontend and backend
• packages/workflow: Core workflow interfaces and types
• packages/core: Workflow execution engine
• packages/cli: Express server, REST API, and CLI commands
• packages/frontend/editor-ui: Vue 3 frontend application
• packages/frontend/@n8n/i18n: Internationalization for UI text
• packages/nodes-base: Built-in nodes for integrations
• packages/@n8n/nodes-langchain: AI/LangChain nodes
• packages/@n8n/instance-ai: "AI Assistant" in the UI, "Instance AI" in code — AI assistant backend. See its CLAUDE.md for architecture docs.
• @n8n/design-system: Vue component library for UI consistency
• @n8n/config: Centralized configuration management

Technology Stack

• Frontend: Vue 3 + TypeScript + Vite + Pinia + Storybook UI Library
• Backend: Node.js + TypeScript + Express + TypeORM
• Testing: Vitest (unit) + Playwright (E2E)
• Database: TypeORM with SQLite/PostgreSQL support
• Code Quality: Biome (for formatting) + ESLint + lefthook git hooks

Key Architectural Patterns

1. Dependency Injection: Uses @n8n/di for IoC container
2. Controller-Service-Repository: Backend follows MVC-like pattern
3. Event-Driven: Internal event bus for decoupled communication
4. Context-Based Execution: Different contexts for different node types
5. State Management: Frontend uses Pinia stores
6. Design System: Reusable components and design tokens are centralized in @n8n/design-system, where all pure Vue components should be placed to ensure consistency and reusability

Key Development Patterns

• Each package has isolated build configuration and can be developed independently
• Hot reload works across the full stack during development
• Node development uses dedicated node-dev CLI tool
• Workflow tests are JSON-based for integration testing
• AI features have dedicated development workflow (pnpm dev:ai)

Workflow Traversal Utilities

The n8n-workflow package exports graph traversal utilities from packages/workflow/src/common/. Use these instead of custom traversal logic.

Key concept: workflow.connections is indexed by source node. To find parent nodes, use mapConnectionsByDestination() to invert it first.

import { getParentNodes, getChildNodes, mapConnectionsByDestination } from 'n8n-workflow';

// Finding parent nodes (predecessors) - requires inverted connections
const connectionsByDestination = mapConnectionsByDestination(workflow.connections);
const parents = getParentNodes(connectionsByDestination, 'NodeName', 'main', 1);

// Finding child nodes (successors) - uses connections directly
const children = getChildNodes(workflow.connections, 'NodeName', 'main', 1);

TypeScript Best Practices

• NEVER use any type - use proper types or unknown
• Avoid type casting with as - use type guards or type predicates instead (except in test code where as is acceptable)
• Define shared interfaces in @n8n/api-types package for FE/BE communication
• Lazy-load heavy modules — if a module is only used in a specific code path (not every request), use await import() at point of use instead of top-level import. Applies especially to native modules and large parsers.

Error Handling

• Don't use the deprecated ApplicationError class anywhere — it's a compatibility shim kept only so community nodes keep resolving. Use one of these instead, picking by cause:
  • UserError — the user caused it (invalid input, unauthorized action, business-rule violation).
  • OperationalError — a transient, expected issue (network request failing, DB query timing out) that should be handled gracefully.
  • UnexpectedError — a bug in the code (logic mistake, unhandled case, failed assertion) that developers need to fix.
• Import from appropriate error classes in each package

Persistence layer & the TypeORM boundary

TypeORM (@n8n/typeorm) must stay in the persistence layer — the @n8n/db package or a backend module's own database/ folder (entity/repository files). Business logic — services, controllers, handlers, commands, factories — must not import from @n8n/typeorm (including @n8n/typeorm/... subpaths). In packages/cli this is enforced by the misplaced-n8n-typeorm-import lint rule; a new import (or an inline eslint-disable of the rule) fails CI.

• Pattern: when a query needs operators (In, IsNull, LessThan, FindOptionsWhere, …), put it behind a use-case-named repository method that takes plain parameters and returns domain-shaped values — not a generic find(options) passthrough.
• Transactions: transaction orchestration belongs in the persistence layer. Don't reach for .manager / .manager.transaction(...) or createQueryBuilder(...) in business logic. Use the sanctioned primitive in @n8n/db: inject the abstract TransactionRunner and wrap the unit of work in txRunner.run(ctx, async (ctx) => …). The callback receives an OperationContext carrying the active transaction; thread that ctx into the repository methods you call. run requires a context — pass an empty {} at the operation entry point, and reuse the one you were handed everywhere below it (a context that already carries a transaction is joined, not nested). Repositories extend BaseRepository and resolve the right EntityManager with this.managerFor(ctx); the Transaction handle is opaque and never exposes a driver type to business logic. See oauth-token.service.ts + oauth-*-token.repository.ts for a worked example.
• Anti-patterns reviewers reject — they hide the dependency instead of removing it:
  • String-matching TypeORM errors, e.g. error.name === 'QueryFailedError'.
  • Relabeling the import from @n8n/typeorm to @n8n/db to silence the rule (@n8n/db re-exports several operators/types, but this relabels the dependency rather than removing it).
  • Pushing .manager / createQueryBuilder into business logic to avoid an operator import — trades a visible leak for an invisible one.

Frontend Development

• Refer to packages/frontend/AGENTS.md
• All UI text must use i18n - add translations to @n8n/i18n package
• Use CSS variables directly - never hardcode spacing as px values
• data-testid must be a single value (no spaces or multiple values)
• Always use design-system-rules skill in reviews

Testing Guidelines

• Always work from within the package directory when running tests
• Mock all external dependencies in unit tests
• Prefer reusing hoisted shared mock<T>(...) fixtures when a typed mock is immutable and used across tests. This rule exists to avoid massive test slowdowns from repeatedly creating nested proxy mocks while preserving the type contract. Avoid replacing these with as unknown as T helpers for entities like User.
• Confirm test cases with user before writing unit tests
• Typecheck is critical before committing - always run pnpm typecheck
• When modifying pinia stores, check for unused computed properties
• For Vitest packages that use @n8n/di decorators, use createVitestConfigWithDecorators from @n8n/vitest-config/node-decorators. It enables SWC decoratorMetadata (esbuild doesn't emit it) and externalizes workspace packages that register services (@n8n/di, @n8n/config, @n8n/constants, n8n-workflow) so a single DI Container instance is shared across the runtime. Loading them through Vitest's pipeline alongside their CJS dist produces two Containers and Container.get(...) returns undefined.

What we use for testing and writing tests:

• For testing nodes and other backend components, we use Vitest for unit tests. Examples can be found in packages/nodes-base/nodes/**/*test*.
• We use nock for server mocking
• For frontend we use vitest
• For E2E tests we use Playwright. Run with pnpm --filter=n8n-playwright test:local. See packages/testing/playwright/README.md for details.
• To iterate on a feature without docker rebuilds, boot service containers and run the dev servers locally — pnpm --filter n8n-containers services --services postgres,redis,mailpit,proxy then pnpm dev:be (backend on 5678). For frontend hot reload, also run pnpm dev:fe:editor (8080). The root pnpm dev does not exist: it prints a notice and exits with code 0, thus pnpm dev && … looks successful but no server runs. See Develop against running containers.
• In a codespace agent session, use pnpm dev:up. It installs the missing dependencies, starts the backend, waits for health, shares the port with the org, and prints the URL. See .devcontainer/codespaces/README.md.
• For Playwright test maintenance/cleanup, see packages/testing/playwright/AGENTS.md (includes janitor tool for static analysis, dead code removal, architecture enforcement, and TCR workflows).

Common Development Tasks

When implementing features:

1. Define API types in packages/@n8n/api-types
2. Implement backend logic in packages/cli module, follow scripts/backend-module/backend-module-guide.md
3. Add API endpoints via controllers
4. Update frontend in packages/frontend/editor-ui with i18n support
5. Write tests with proper mocks
6. Run pnpm typecheck to verify types

Design Principles

Security Must Not Degrade the Building Experience

Security improvements, whether driven by enterprise requirements or internal standards, must NEVER add friction to the common-case building experience. When designing security-related features (defaults, behaviors, flows, error handling), apply these checks:

• No friction for the common case: A community builder's workflow should remain intuitive. Security should be invisible when it can be.
• Migration and upgrade paths: Existing users must have a clear, non-disruptive path forward when defaults or behaviors change.
• Security layers on top, not in competition: Great UX and strong security are not trade-offs. They're both required. If a design forces a choice between them, the design needs more work.

Security Fix Hygiene

This is a public repository. When working on security fixes, never expose the attack vector or vulnerability type in any public-facing artifact. Attackers monitor open-source repos for signals like branch names, commit messages, PR titles, test descriptions, and Linear URLs.

Rules for security fixes:

• Branch names: Do NOT use the Linear-suggested branch name if it reveals the vulnerability. Rename to describe the fix neutrally (e.g. node-1234-improve-request-handling, not node-1234-fix-ddos-vulnerability).
• Commit messages: Describe what the code now does, not the threat it prevents (e.g. fix: add payload size validation, not fix: prevent denial of service).
• Test descriptions: Use neutral, functional language (e.g. 'should sanitize query parameters', not 'should prevent SQL injection').
• Code comments: Do not describe the attack scenario in comments.
• Linear references: Never include the URL slug (e.g. .../N8N-1234/fix-ssrf-vulnerability).

Customer Confidentiality

This is a public repository. Never mention customer names in any public-facing artifact — not all customers have agreed to be named publicly, and naming them can reveal security-relevant details about their setup.

This applies to PR titles and descriptions, branch names, commit messages, code, code comments, test names and test data, and fixtures. When implementing a customer request, describe the use case neutrally (e.g. "a customer with a large multi-main setup", not the company name) and use generic placeholder names (e.g. Acme Corp) in tests and examples.

Github Guidelines

• When creating a PR, use the conventions in .github/pull_request_template.md and .github/pull_request_title_conventions.md.
• Use gh pr create --draft to create draft PRs.
• If there is a corresponding Linear ticket, reference it in the PR description using https://linear.app/n8n/issue/[TICKET-ID]. Do not create a Linear ticket on your own — ask first.
• always link to the github issue if mentioned in the linear ticket.