* feat(ai-agent): built-in approval tool that parks the agent An AI agent step can now be given a built-in "Request approval" tool. The model calls `request_approval` with a message; the agent stores its conversation in the new `ai_agent_checkpoint` table, releases its worker by parking its own queue row like a workflow-as-code parent, and resumes with the answer (approved, approver, comment) or a timeout once someone answers from the run page. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(ai-agent): tie approval answers to their request and hold the turn - A turn that asks for approval runs none of its other calls; they are refused so the model repeats them after the answer. - The run page sends the request's call id. An answer naming another request is ignored and the agent parks again for the time left; `suspend` is zeroed when the answer is read, so answers sent while the agent runs are refused. - The checkpoint is read whatever the current roster holds, the answer's outcome is written by position, and a cancel that beats the park completes the job as cancelled. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(ai-agent): say why calls beside an invalid approval request were refused Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(ai-agent): one approval form per request, none on a finished run Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * feat(ai-agent): answer approval requests from a flow's chat Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(ai-agent): show chat approvals for agents that do not stream Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * feat(ai-agent): approval as a per-tool setting, built-in tool asks a question Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(ai-agent): say when a nested agent leaves out tools that require approval Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * feat(ai-agent): show chat approvals and questions on the tool's own card Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * feat(ai-agent): question choices, and approval buttons shared with approval steps Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * feat(ai-agent): show a waiting agent as suspended, and refused calls as not run Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(ai-agent): each added chat card shows its own call, answered marker keyed by job Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test(ai-agent): approve and reject a held call through resume_suspended Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * feat(ai-agent): require approval in a tool settings tab, plain descriptions on built-in tool panes Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(ai-agent): sentence case for the web search tool label Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * feat(ai-agent): built-in tool drawers explain themselves in the header subtitle Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(ai-agent): clearer question tool subtitle Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(ai-agent): badge the tool settings tab like run settings Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * chore(ai-agent): regenerate system prompts and MCP session files Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Windmill CLI
A simple CLI allowing interactions with windmill from the command line.

You can find more information in Windmill Docs
Installation
Install the wmill CLI tool using npm install -g windmill-cli.
Update to the latest version using wmill upgrade.
Workspaces
To get started run wmill workspace add or use the instructions from the
workspace settings.
Running Flows & Scripts
Run a script or flow using wmill flow/script run u/username/path/to/script and
pass any inputs using --data + Inputs specified as a JSON string or a file
using @ <filename> or stdin using @-.
Curl-style syntax using -d @- for stdin or -d @<filename> is also supported.
Flow Steps and Logs will be streamed during execution automatically.
Pushing Resources, Scripts & More
The CLI can push specifications to a windmill instance. See the examples/ folder for formats.
Switch to a different workspace
wmill workspace switch <workspace_name>
Sync a workspace
Pull
wmill sync pull
Push
wmill sync push
We recommend using the --yaml option to use yaml instead of json as the encoding format. Yaml will be made the default soon.
Pushing individual files
You can push individual resources using
wmill <type> push <file_name> \<remote_name\>. This does not require a special
folder layout or file name, as this is given at runtime.
Listing
All commands support listing by just not providing a subcommand, ie
wmill script will result in a list of scripts. Some allow additional options,
learn about this by specifying --help.
User Management
You can add & remove users via wmill user add/remove, and list them using
wmill user
Pulling
You can pull the entire workspace using wmill pull
Completion
The CLI comes with completions out of the box via wmill completions <shell>.
(Via cliffy)
Bash
To enable bash completions add the following line to your ~/.bashrc:
source <(wmill completions bash)
Fish
To enable fish completions add the following line to your
~/.config/fish/config.fish:
source (wmill completions fish | psub)
Zsh
To enable zsh completions add the following line to your ~/.zshrc:
source <(wmill completions zsh)
Development
AI Guidance Variants
wmill init can now materialize alternate AI guidance bundles without changing
the generated defaults in the repo, but this is exposed as internal env-var
overrides rather than public CLI flags.
Examples:
WMILL_INIT_AI_SKILLS_SOURCE=/path/to/custom/skills wmill init --use-default
WMILL_INIT_AI_SKILLS_SOURCE=/path/to/custom/skills WMILL_INIT_AI_AGENTS_SOURCE=/path/to/AGENTS.md wmill init --use-default
WMILL_INIT_AI_SKILLS_SOURCE=/path/to/custom/skills WMILL_INIT_AI_CLAUDE_SOURCE=/path/to/CLAUDE.md wmill init --use-default
This is the same guidance-writing path used by the benchmark CLI under
ai_evals/, so the benchmark harness and wmill init now generate the same
project guidance shape:
AGENTS.mdCLAUDE.md.agents/skills/*.claude/skills/*
windmill-yaml-validator
wmill lint imports the sibling windmill-yaml-validator package from source rather than
from npm, so its schemas always match the OpenAPI specs of the current checkout. bun install regenerates them through this package's preinstall script; run it again after
editing openflow.openapi.yaml or backend/windmill-api/openapi.yaml:
npm --prefix ../windmill-yaml-validator run gen
Running Tests
Prerequisites:
- PostgreSQL running locally (default:
postgres://postgres:changeme@localhost:5432) - Rust toolchain installed
Run tests locally (full features):
bun test test/
Run tests in CI mode (minimal features, skips EE tests):
CI_MINIMAL_FEATURES=true bun test test/
| Variable | Description |
|---|---|
CI_MINIMAL_FEATURES |
Set to true to skip EE-dependent tests |
DATABASE_URL |
PostgreSQL connection string |
EE_LICENSE_KEY |
Enterprise license key for EE features |
