centdix 8e6b519a0d feat(aichat): simplify flow mode edits (#6981)
* draft

* Phase 1: Remove deprecated granular flow AI tools

Simplify AI chat flow mode to use only YAML-based editing:
- Remove all commented-out granular tools (add_step, remove_step, set_code, etc.)
- Clean up FlowAIChatHelpers interface to only essential methods
- Update system prompts to focus on YAML-only workflow
- Remove unused imports and type definitions

This is part of a larger refactoring to simplify the flow editing
experience to a single YAML editing tool with automatic diff visualization.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* use minified json

* use openflow in system prompt

* handle inputs

* cleaning

* cleaning

* diffmode in flowgraph

* remove acceptrejectmodule

* use new diff mode

* cleaning

* better props

* better logic

* cleaning

* accept reject logic

* use get set

* draft manager

* use diff manager

* draft

* Refactor flowDiffManager to be instance-based with auto-computation

- Remove singleton export, making it instantiable per FlowGraphV2
- Add afterFlow state tracking for auto-diff computation
- Add beforeInputSchema/afterInputSchema for schema change tracking
- Add $effect for reactive auto-computation when beforeFlow/afterFlow changes
- Add setAfterFlow() and setInputSchemas() methods
- Simplify accept/reject methods to just mark pending=false
- Add validation to throw error when accepting/rejecting without beforeFlow
- Update setSnapshot to accept undefined for clearing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Refactor FlowGraphV2 to own diffManager instance

- Import and create diffManager instance per FlowGraphV2
- Remove onAcceptModule and onRejectModule props
- Add validation $effect to error if both diffBeforeFlow and moduleActions provided
- Add $effect to sync props (diffBeforeFlow or moduleActions) to diffManager
- Add $effect to watch current flow changes and update afterFlow
- Replace computedDiff with diffManager.moduleActions
- Use raw modules instead of merged flow (diffManager handles merging)
- Expose getDiffManager() and setBeforeFlow() methods
- Pass diffManager to graph context instead of callbacks
- Remove $inspect for removed props

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Update FlowModuleSchemaMap to use FlowGraphV2's diffManager

- Remove import of flowDiffManager singleton
- Update setBeforeFlow to call graph.setBeforeFlow()
- Update setModuleActions and getModuleActions to use graph.getDiffManager()
- Add getDiffManager() proxy method
- Simplify handleAcceptModule and handleRejectModule to use new API
- Handle editor state separately from diff operations
- Remove diffBeforeFlow, moduleActions, onAcceptModule, onRejectModule props passed to FlowGraphV2
- Remove onAcceptModule and onRejectModule from Props interface and destructured props

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Update FlowAIChat to use flowModuleSchemaMap's diffManager

- Remove import of flowDiffManager singleton
- Update revertToSnapshot to use flowModuleSchemaMap.getDiffManager()
- Add null check for diffManager before using

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Verify FlowGraphDiffViewer compatibility with refactored architecture

FlowGraphDiffViewer already uses the correct prop patterns:
- Before graph: moduleActions prop (display-only mode)
- After graph: diffBeforeFlow prop (full diff mode with auto-computation)

Each FlowGraphV2 instance creates its own diffManager, making the side-by-side
view work correctly with independent diff state per graph.

No code changes required.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Update graph components to use diffManager instead of callbacks

- Update graphBuilder.svelte.ts to pass diffManager instead of onAcceptModule/onRejectModule
- Update InputNode and ModuleN type definitions with diffManager
- Update ModuleNode.svelte to pass diffManager to MapItem
- Update MapItem.svelte to pass diffManager to FlowModuleSchemaItem
- Update FlowModuleSchemaItem.svelte to use diffManager directly for accept/reject
- Replace callback-based accept/reject with direct diffManager calls
- Only show accept/reject buttons when beforeFlow exists and action is pending

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Fix removed modules not showing in diff viewer

Problem: After refactoring, removed modules were no longer appearing in the
diff viewer because we changed effectiveModules from using the merged flow
(which includes removed modules) to using raw modules.

Solution:
- Add mergedFlow state to flowDiffManager to store timeline's merged flow
- Add markRemovedAsShadowed parameter support for side-by-side view
- Store timeline.mergedFlow in auto-computation $effect
- Add getter for mergedFlow and setMarkRemovedAsShadowed method
- Clear mergedFlow in clearSnapshot()
- Update FlowGraphV2 to set markRemovedAsShadowed in diffManager
- Update effectiveModules/FailureModule/PreprocessorModule to use mergedFlow

The merged flow contains all modules including removed ones, enabling:
- Unified view: Removed modules appear in red with "removed" badge
- Side-by-side view: Removed modules show as shadowed in After graph

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Simplify accept/reject logic by removing actions instead of toggling pending state

Previously, accepting or rejecting a module action would set pending to false but keep the action in the moduleActions map. This caused a bug where the $effect would overwrite moduleActions with fresh actions having pending: true, making accept/reject buttons reappear on previously handled modules.

Now, when a user accepts or rejects a module action, we remove it entirely from the moduleActions map. This is simpler and fixes the button reappearing issue.

Changes:
- acceptModule: Remove action from moduleActions instead of setting pending: false
- rejectModule: Remove action from moduleActions instead of setting pending: false
- checkAndClearSnapshot: Check if moduleActions is empty instead of checking pending states
- Fix typo: getModuleFromFrom → getModuleFromFlow

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* cleaning

* fix logic

* make diff drawer part of manager

* accept submodules

* fixes

* Phase 4: Add checkAndApplyChanges() helper to flowDiffManager

- Added new checkAndApplyChanges() function to apply mergedFlow to flowStore when all changes are decided
- This replaces the old checkAndClearSnapshot() behavior and ensures flowStore is updated atomically
- Handles both flow structure and input schema updates

* Phase 2: Simplify acceptModule() - only modify mergedFlow

- Remove flowStore mutations from acceptModule()
- For removed modules: just delete the shadowed (__prefix) version from mergedFlow
- For added/modified: no action needed (already correct in mergedFlow)
- Call checkAndApplyChanges() to apply changes when all decided

* Phase 3: Simplify rejectModule() - only modify mergedFlow

- Remove all flowStore mutations from rejectModule()
- For added modules: delete from mergedFlow
- For removed modules: replace shadowed (__) module with original from beforeFlow
- For modified modules: restore old version in mergedFlow
- For Input schema: revert afterInputSchema
- Call checkAndApplyChanges() to apply changes when all decided

* Phase 5: Verify acceptAll/rejectAll work with new architecture

- acceptAll() and rejectAll() already pass options correctly to acceptModule/rejectModule
- They will automatically benefit from checkAndApplyChanges()
- No changes needed for this phase

* Phase 6: Remove FlowGraphV2 reactive effect that updates afterFlow

- Removed the  (lines 252-266) that continuously updated afterFlow
- This effect created reactive loops when flowStore changed
- afterFlow should only be set once when AI generates changes via setFlowYaml()
- The initial sync effect (lines 226-250) is kept for prop-driven diff mode

* Phase 7: Update FlowAIChat setFlowYaml to use diffManager

- Changed setFlowYaml() to use diffManager.setAfterFlow() instead of modifying flowStore
- flowStore remains unchanged during AI review phase
- Changes are staged in mergedFlow for user review
- Only applied to flowStore when all changes are accepted/rejected
- Added error handling for missing diffManager

* Fix linter warnings

- Remove unused FlowTimeline type import
- Fix ChangeTracker initialization with proper type parameter
- Keep deleteModuleFromFlow and checkAndClearSnapshot for potential future use

* Update plan document with implementation status

- Mark all phases as complete
- Add commit references
- Update file checklist
- Add implementation summary at top of document

* Add comprehensive implementation summary document

- Detailed overview of architecture changes
- Before/after comparisons for each file
- Complete testing scenarios checklist
- Troubleshooting guide
- Migration notes and backwards compatibility info

* Show pending modules in editor panel

- Pass diffManager from FlowModuleSchemaMap to FlowEditorPanel
- Add effectiveModules derived value that uses mergedFlow when in diff mode
- Update module iteration to use effectiveModules instead of flowStore
- Allows users to view added/modified modules during AI review
- Fixes issue where clicking on pending modules showed nothing

* Add implementation summary for show pending modules feature

* fix

* shorter system prompt

* Fix Input schema diff mode issues

- Add Accept/Reject buttons to Input node (previously only showed Diff button)
- Pass diffManager to FlowInput component
- Add effectiveSchema derived value that uses afterInputSchema when in diff mode
- Add effectiveDisabled to prevent editing Input when reviewing AI changes
- Update FlowInputViewer to show pending schema changes
- Fixes issue where Input schema changes couldn't be accepted/rejected
- Fixes issue where pending Input schema wasn't visible in the panel

* Disable delete and move buttons when in pending mode

- Add effectiveDeletable derived value that checks diffManager.hasPendingChanges
- Replace all instances of deletable with effectiveDeletable in template
- Prevents delete/move operations when AI changes are being reviewed
- Delete and move buttons are hidden when there are pending changes
- Buttons reappear once all changes are accepted or rejected
- Prevents conflicting operations during review phase

* no move or delte when reviewing

* use context

* inline script reduction

* use json

* rollback to direct modif

* fix merge

* cleaning

* fix reject removed

* add set step code tool

* better prompt

* add back relevant tools

* add back accept reject

* use edit mode for pending

* fix input

* remove unneeded effect

* cleaner + bug fix

* fix failure and preprocessor

* fix show diff for failure module

* fix accept reject on failre module

* no auto add module to context

* cleaning

* add back effect

* cleaning

* fix multiple setflowjson

* track effectivemoduleactions for graph rendering

* nit prompt

* styling

* rm md files

* rm flake copy

* cleaning

* fix z index

* fix revert

* only change before after

* use add remove modify tools

* input + failure + preproc tools

* parsing issues

* nit

* use raw schema for tools

* resolve ref for gemini

* fix schema

* show test on graph

* much cleaner logic

* ignore empty assets

* Remove debug console.log statements from production code

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Remove debug $inspect calls from FlowGraphV2

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Add error logging to setFlowJson before re-throwing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Standardize null/undefined handling to prefer null

- Use .nullable().optional() instead of .nullish() in Zod schemas
- Simplify addModuleToFlow signature to use string | null
- Coerce undefined to null when extracting parsed args
- Simplify null checks to only check !== null

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Remove debug console.log from AI tool functions

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Extract special module IDs to constants

Add SPECIAL_MODULE_IDS constant with INPUT, PREPROCESSOR, and FAILURE
to avoid magic strings throughout the flow AI chat code.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Add cleanup for diffDrawer reference on unmount

Prevents potential memory leaks by clearing the diffDrawer reference
when the FlowGraphV2 component is destroyed.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Use structuredClone instead of JSON.parse(JSON.stringify())

structuredClone is more efficient and type-safe for deep cloning objects.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Cache module lookups in reconstructMergedFlow

Move getAllModulesMap and getAllModuleIds calls outside the loop to avoid
redundant recomputation. Track merged IDs incrementally as modules are added.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Revert "Use structuredClone instead of JSON.parse(JSON.stringify())"

This reverts commit a62ba5b980.

* cleaning

* allow delete

* better openflow for ai agents + truncate system prompt

* handle ai agent tools

* fix set code for tool

* fix wrong cancel request called

* mark tool calls as canceled

* get lang instructions

* use streamiing args

* give db url to claude

* fix revert

* save and clear when leaving editor

* keep whitespace in user message

* uniformize colors

* fix diff button

* remove db from backend claude

* remove move module tool

* no failure and preprocessor

* fix error given to llm

* fix z index

* fix ts errors

* cleaning

* fix add module logic

* fix(copilot): add 'tools' to branchPath description for aiagent containers

The branchPath parameter description was missing 'tools' option for aiagent
containers and didn't mention branchall support.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(copilot): correct AI agent tool IDs and summaries documentation

Tool summaries CAN contain spaces (they're human-readable descriptions).
Only tool IDs must avoid spaces.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(copilot): remove reference to non-existent set_flow_json tool

The set_module_code tool description referenced set_flow_json which
doesn't exist as an exposed tool (it's an internal helper).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(copilot): clarify inspect_inline_script is read-only

The tool description incorrectly suggested it could modify code.
This tool only inspects - use set_module_code to modify.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(copilot): clarify afterId behavior for AI agent tools

Updated wording to clarify that afterId can be used but is optional
for AI agent tools since tool order doesn't affect execution.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* refactor(copilot): remove unused id param from get_instructions_for_code_generation

The id parameter was only used to check for preprocessor, which is no
longer needed. Simplified the tool to only require the language param.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* docs(copilot): add result format to search_scripts tool description

Helps AI understand what data format to expect from the tool.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* docs(copilot): add result format to resource_type tool description

Helps AI understand what data format to expect from the tool and
provides example resource type names.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* nit

* Add support for adding branches to branchall/branchone via add_module

Previously, add_module could only add modules inside existing branches.
Now, using insideId with branchPath=null will add a NEW branch to a
branchall or branchone container.

API:
- add_module({ insideId: "my_branchall", branchPath: null, value: { summary: "New Branch", skip_failure: false, modules: [] } })
- add_module({ insideId: "my_branchone", branchPath: null, value: { summary: "Condition", expr: "...", modules: [] } })

Changes:
- Extended addModuleToFlow to handle branchPath=null case
- Updated validation to allow branchPath=null when adding branches
- Updated tool descriptions and system prompt documentation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* nit

* add remove branch tool

* check all ids for duplicates

* no dup

* nit

* cleaning

* fix dup ids

* split core.ts

* only mount diff drawer if useful

* remove wrong logic

* update exprs

* fix

* chore(flow): Add unit tests to flow diff manager (#7291)

* setup

* add basic tests for flowdiff

* add complex tests

* fix branch issue

* more complex tests

* add flow diff manager tests

* add utils

* better handling of moved case

* more tests for move case

* add buggy test case

* rm

* rework config

* cleaning

* fix config

* rm

* fix for reverting type change module

* all good

* rm

* add missing testmode

---------

Co-authored-by: Claude <noreply@anthropic.com>
2025-12-08 19:08:14 +01:00
2024-02-08 16:09:11 +01:00
2025-11-18 15:44:23 +00:00
2025-09-09 14:19:54 +00:00
2025-12-05 13:29:56 +00:00
2023-08-26 09:17:07 +02:00
2025-09-02 21:42:17 +00:00
2025-04-21 16:53:23 +02:00
2025-10-17 07:24:57 +00:00
2025-12-08 10:34:16 +00:00
2025-12-02 17:25:34 +00:00
2025-12-03 13:48:25 +00:00
2025-03-07 15:08:19 +01:00
2022-05-05 04:25:58 +02:00
2024-02-08 16:09:11 +01:00

windmill.dev

Open-source developer infrastructure for internal tools (APIs, background jobs, workflows and UIs). Self-hostable alternative to Retool, Pipedream, Superblocks and a simplified Temporal with autogenerated UIs and custom UIs to trigger workflows and scripts as internal apps.

Scripts are turned into sharable UIs automatically, and can be composed together into flows or used into richer apps built with low-code. Supported script languages supported are: Python, TypeScript, Go, Bash, SQL, and GraphQL.

Package version Docker Image CI Package version

Commit activity Discord Shield

Try it - Docs - Discord - Hub - Contributor's guide

Windmill - Developer platform for APIs, background jobs, workflows and UIs

Windmill is fully open-sourced (AGPLv3) and Windmill Labs offers dedicated instance and commercial support and licenses.

Windmill Diagram

https://github.com/windmill-labs/windmill/assets/122811744/0b132cd1-ee67-4505-822f-0c7ee7104252

Main Concepts

  1. Define a minimal and generic script in Python, TypeScript, Go or Bash that solves a specific task. The code can be defined in the provided Web IDE or synchronized with your own GitHub repo (e.g. through VS Code extension):

    Step 1

  2. Your scripts parameters are automatically parsed and generate a frontend.

Step 2

Step 3

  1. Make it flow! You can chain your scripts or scripts made by the community shared on WindmillHub.

    Step 3

  2. Build complex UIs on top of your scripts and flows.

    Step 4

Scripts and flows can also be triggered by a cron schedule (e.g. '_/5 _ * * *') or through webhooks.

You can build your entire infra on top of Windmill!

Show me some actual script code

//import any dependency  from npm
import * as wmill from "windmill-client";
import * as cowsay from "cowsay@1.5.0";

// fill the type, or use the +Resource type to get a type-safe reference to a resource
type Postgresql = {
  host: string;
  port: number;
  user: string;
  dbname: string;
  sslmode: string;
  password: string;
};

export async function main(
  a: number,
  b: "my" | "enum",
  c: Postgresql,
  d = "inferred type string from default arg",
  e = { nested: "object" }
  //f: wmill.Base64
) {
  const email = process.env["WM_EMAIL"];
  // variables are permissioned and by path
  let variable = await wmill.getVariable("f/company-folder/my_secret");
  const lastTimeRun = await wmill.getState();
  // logs are printed and always inspectable
  console.log(cowsay.say({ text: "hello " + email + " " + lastTimeRun }));
  await wmill.setState(Date.now());

  // return is serialized as JSON
  return { foo: d, variable };
}

CLI

We have a powerful CLI to interact with the windmill platform and sync your scripts from local files, GitHub repos and to run scripts and flows on the instance from local commands. See more details.

CLI Screencast

Running scripts locally

You can run your script locally easily, you simply need to pass the right environment variables for the wmill client library to fetch resources and variables from your instance if necessary. See more: https://www.windmill.dev/docs/advanced/local_development.

To develop & test locally scripts & flows, we recommend using the Windmill VS Code extension: https://www.windmill.dev/docs/cli_local_dev/vscode-extension.

Stack

  • Postgres as the database.
  • Backend in Rust with the following highly-available and horizontally scalable. Architecture:
    • Stateless API backend.
    • Workers that pull jobs from a queue in Postgres (and later, Kafka or Redis. Upvote #173 if interested).
  • Frontend in Svelte.
  • Scripts executions are sandboxed using Google's nsjail.
  • Javascript runtime is the deno_core rust library (which itself uses the rusty_v8 and hence V8 underneath).
  • TypeScript runtime is Bun and deno.
  • Python runtime is python3.
  • Golang runtime is 1.19.1.

Fastest Self-Hostable Workflow Engine

We have compared Windmill to other self-hostable workflow engines (Airflow, Prefect & Temporal) and Windmill is the most performant solution for both benchmarks: one flow composed of 40 lightweight tasks & one flow composed of 10 long-running tasks.

All methodology & results on our Benchmarks page.

Fastest workflow engine

Security

Sandboxing

Windmill can use nsjail. It is production multi-tenant grade secure. Do not take our word for it, take fly.io's one.

Secrets, credentials and sensitive values

There is one encryption key per workspace to encrypt the credentials and secrets stored in Windmill's K/V store.

In addition, we strongly recommend that you encrypt the whole Postgres database. That is what we do at https://app.windmill.dev.

Performance

Once a job started, there is no overhead compared to running the same script on the node with its corresponding runner (Deno/Go/Python/Bash). The added latency from a job being pulled from the queue, started, and then having its result sent back to the database is ~50ms. A typical lightweight deno job will take around 100ms total.

Architecture

How to self-host

We only provide docker-compose setup here. For more advanced setups, like compiling from source or using without a postgres super user, see Self-Host documentation.

Docker compose

Windmill can be deployed using 3 files: (docker-compose.yml, Caddyfile and a .env) in a single command.

Make sure Docker is started, and run:

curl https://raw.githubusercontent.com/windmill-labs/windmill/main/docker-compose.yml -o docker-compose.yml
curl https://raw.githubusercontent.com/windmill-labs/windmill/main/Caddyfile -o Caddyfile
curl https://raw.githubusercontent.com/windmill-labs/windmill/main/.env -o .env

docker compose up -d

Go to http://localhost et voilà :)

The default super-admin user is: admin@windmill.dev / changeme.

From there, you can follow the setup app and create other users.

More details in Self-Host Documention.

Kubernetes (k8s) and Helm charts

We publish helm charts at: https://github.com/windmill-labs/windmill-helm-charts.

Run from binaries

Each release includes the corresponding binaries for x86_64. You can simply download the latest windmill binary using the following set of bash commands.

BINARY_NAME='windmill-amd64' # or windmill-ee-amd64 for the enterprise edition
LATEST_RELEASE=$(curl -L -s -H 'Accept: application/json' https://github.com/windmill-labs/windmill/releases/latest)
LATEST_VERSION=$(echo $LATEST_RELEASE | sed -e 's/.*"tag_name":"\([^"]*\)".*/\1/')
ARTIFACT_URL="https://github.com/windmill-labs/windmill/releases/download/$LATEST_VERSION/$BINARY_NAME"
wget "$ARTIFACT_URL" -O windmill

OAuth, SSO & SMTP

Windmill Community Edition allows to configure the OAuth, SSO (including Google Workspace SSO, Microsoft/Azure and Okta) directly from the UI in the superadmin settings. Do note that there is a limit of 10 SSO users on the community edition.

See documentation.

Commercial license

See the LICENSE file for the full license text.

The "Community Edition" of Windmill available in the docker images hosted under ghcr.io/windmill-labs/windmill and the github binary releases contains the files under the AGPLv3 and Apache 2 sources but also includes proprietary and non-public code and features which are not open source and under the following terms: Windmill Labs, Inc. grants a right to use all the features of the "Community Edition" for free without restrictions other than the limits and quotas set in the software and a right to distribute the community edition as is but not to sell, resell, serve Windmill as a managed service, modify or wrap under any form without an explicit agreement.

The binary compilable from source code in this repository without the "enterprise" feature flag is open-source under the LICENSE-AGPLv3 License terms and conditions.

To re-expose directly any Windmill parts to your users as a feature of your product, with the exception of iframed public Windmill "apps", or to build a feature on top of "Windmill Community Edition" that you sell commercially or embed in a distributable product or binary, you must get a commercial license. Contact us at sales@windmill.dev if you have any questions. To do the same from the binary compiled from the source code in this repository without the "enterprise" feature flag, you must comply with the AGPLv3 license terms and conditions or get a commercial license from Windmill Labs, Inc.

To use Windmill "Community Edition" as is internally in your organization, or to use its APIs as is, you do NOT need a commercial license.

Integrations

In Windmill, integrations are referred to as resources and resource types. Each Resource has a Resource Type that defines the schema that the resource needs to implement.

On self-hosted instances, you might want to import all the approved resource types from WindmillHub. A setup script will prompt you to have it being synced automatically everyday.

Environment Variables

Environment Variable name Default Description Api Server/Worker/All
DATABASE_URL The Postgres database url. All
WORKER_GROUP default The worker group the worker belongs to and get its configuration pulled from Worker
MODE standalone The mode if the binary. Possible values: standalone, worker, server, agent All
METRICS_ADDR None (ee only) The socket addr at which to expose Prometheus metrics at the /metrics path. Set to "true" to expose it on port 8001 All
JSON_FMT false Output the logs in json format instead of logfmt All
BASE_URL http://localhost:8000 The base url that is exposed publicly to access your instance. Is overriden by the instance settings if any. Server
ZOMBIE_JOB_TIMEOUT 30 The timeout after which a job is considered to be zombie if the worker did not send pings about processing the job (every server check for zombie jobs every 30s) Server
RESTART_ZOMBIE_JOBS true If true then a zombie job is restarted (in-place with the same uuid and some logs), if false the zombie job is failed Server
SLEEP_QUEUE 50 The number of ms to sleep in between the last check for new jobs in the DB. It is multiplied by NUM_WORKERS such that in average, for one worker instance, there is one pull every SLEEP_QUEUE ms. Worker
KEEP_JOB_DIR false Keep the job directory after the job is done. Useful for debugging. Worker
LICENSE_KEY (EE only) None License key checked at startup for the Enterprise Edition of Windmill Worker
SLACK_SIGNING_SECRET None The signing secret of your Slack app. See Slack documentation Server
COOKIE_DOMAIN None The domain of the cookie. If not set, the cookie will be set by the browser based on the full origin Server
DENO_PATH /usr/bin/deno The path to the deno binary. Worker
PYTHON_PATH The path to the python binary if wanting to not have it managed by uv. Worker
GO_PATH /usr/bin/go The path to the go binary. Worker
GOPRIVATE The GOPRIVATE env variable to use private go modules Worker
GOPROXY The GOPROXY env variable to use Worker
NETRC The netrc content to use a private go registry Worker
PY_CONCURRENT_DOWNLOADS 20 Sets the maximum number of in-flight concurrent python downloads that windmill will perform at any given time. Worker
PATH None The path environment variable, usually inherited Worker
HOME None The home directory to use for Go and Bash , usually inherited Worker
DATABASE_CONNECTIONS 50 (Server)/3 (Worker) The max number of connections in the database connection pool All
SUPERADMIN_SECRET None A token that would let the caller act as a virtual superadmin superadmin@windmill.dev Server
TIMEOUT_WAIT_RESULT 20 The number of seconds to wait before timeout on the 'run_wait_result' endpoint Worker
QUEUE_LIMIT_WAIT_RESULT None The number of max jobs in the queue before rejecting immediately the request in 'run_wait_result' endpoint. Takes precedence on the query arg. If none is specified, there are no limit. Worker
DENO_AUTH_TOKENS None Custom DENO_AUTH_TOKENS to pass to worker to allow the use of private modules Worker
DISABLE_RESPONSE_LOGS false Disable response logs Server
CREATE_WORKSPACE_REQUIRE_SUPERADMIN true If true, only superadmins can create new workspaces Server
MIN_FREE_DISK_SPACE_MB 15000 Minimum amount of free space on worker. Sends critical alert if worker has less free space. Worker
RUN_UPDATE_CA_CERTIFICATE_AT_START false If true, runs CA certificate update command at startup before other initialization All
RUN_UPDATE_CA_CERTIFICATE_PATH /usr/sbin/update-ca-certificates Path to the CA certificate update command/script to run when RUN_UPDATE_CA_CERTIFICATE_AT_START is true All

Run a local dev setup

Using Nix (Recommended).

See the ./frontend/README_DEV.md file for all running options.

only Frontend

This will use the backend of https://app.windmill.dev but your own frontend with hot-code reloading. Note that you will need to use a username / password login due to CSRF checks using a different auth provider.

In the frontend/ directory:

  1. install the dependencies with npm install (or pnpm install or yarn)
  2. generate the windmill client:
npm run generate-backend-client
## on mac use
npm run generate-backend-client-mac
  1. Run your dev server with npm run dev
  2. Et voilà, windmill should be available at http://localhost/

Backend + Frontend

See the ./frontend/README_DEV.md file for all running options.

  1. Start a local Postgres database using for instance the start-dev-db.sh script which will make a database available at postgres://postgres:changeme@localhost:5432/windmill Then run the migrations using the following command:
    cargo install sqlx-cli
    env DATABASE_URL=<YOUR_DATABASE_URL> sqlx migrate run
    
    This will also avoid compile time issue with sqlx's query! macro.
  2. (optional, linux only) Install nsjail and have it accessible in your PATH
  3. Install bun, deno and python3 (+ any languages you want to use), have the bins at /usr/bin/bun,/usr/bin/deno, and /usr/local/bin/python3 or set the corresponding environment variables.
  4. (optional) Install the lld linker
  5. Go to frontend/:
    1. npm install, npm run generate-backend-client then REMOTE=http://localhost:8000 npm run dev
    2. You might need to set some extra heap space for the node runtime export NODE_OPTIONS="--max-old-space-size=4096"
    3. Create an empty frontend/build folder using mkdir frontend/build
  6. Go to backend/:
    1. env DATABASE_URL=<YOUR_DATABASE_URL> RUST_LOG=info cargo run
    2. You can specify any feature flag you want to enable, for example cargo run --features python to enable the python executor.
  7. Et voilà, windmill should be available at http://localhost:3000

Contributors

Windmill Labs, Inc 2023

S
Description
Open-source developer platform to power your entire infra and turn scripts into webhooks, workflows and UIs. Fastest workflow engine (13x vs Airflow). Open-source alternative to Retool and Temporal.
Readme 860 MiB
Languages
Rust 33.3%
TypeScript 24.5%
Svelte 24.3%
HTML 13.8%
JavaScript 1.6%
Other 2.3%