# Windmill Flow Building Guide ## OpenFlow Schema The OpenFlow schema (openflow.openapi.yaml) is the source of truth for flow structure. Refer to OPENFLOW_SCHEMA for the complete type definitions. ## Reserved Module IDs - `failure` - Reserved for failure handler module - `preprocessor` - Reserved for preprocessor module - `Input` - Reserved for flow input reference ## Hard Structural Rules These are strict Windmill schema rules. Follow them exactly. - `value.modules` is only for normal sequential steps - `value.preprocessor_module` and `value.failure_module` are special top-level fields inside `value`, not entries in `value.modules` - If a flow needs a preprocessor, create `value.preprocessor_module` with `id: preprocessor` - If a flow needs a failure handler, create `value.failure_module` with `id: failure` - Do NOT create regular modules inside `value.modules` named `preprocessor` or `failure` - `preprocessor_module` and `failure_module` only support `script` or `rawscript` - `preprocessor_module` runs before normal modules and cannot reference `results.*` - `failure_module` can use the `error` object with `error.message`, `error.step_id`, `error.name`, and `error.stack` - A flow whose `failure_module` runs still ends as failed, unless the handler returns an object with `recover: true`: the flow then ends as a success. This also holds when the failing step is inside a loop, a branch or a subflow. `recover` never changes which steps run; whether a loop or branch carries on past a failure is still decided by its own settings (`skip_failures`, `continue_on_error`) Correct shape: ```yaml value: preprocessor_module: id: preprocessor value: type: rawscript ... failure_module: id: failure value: type: rawscript ... modules: - id: process_event value: type: rawscript ... ``` Incorrect shape: ```yaml value: modules: - id: preprocessor ... - id: process_event ... - id: failure ... ``` ## Module ID Rules - Must be unique across the entire flow - Use underscores, not spaces (e.g., `fetch_data` not `fetch data`) - Use descriptive names that reflect the step's purpose ## AI Agent Modules An `aiagent` module runs an LLM that can call tools. Each entry of `value.tools` is a module-shaped object with an extra `value.tool_type`: `flowmodule` for a script/flow tool, `mcp` for an MCP server tool, `websearch` for web search. ```json { "id": "support_agent", "summary": "AI agent for customer support", "value": { "type": "aiagent", "input_transforms": { "provider": { "type": "static", "value": { "kind": "openai", "resource": "$res:f/ai_providers/openai", "model": "gpt-4o" } }, "output_type": { "type": "static", "value": "text" }, "user_message": { "type": "javascript", "expr": "flow_input.query" }, "system_prompt": { "type": "static", "value": "You are a helpful assistant." } }, "tools": [ { "id": "search_docs", "summary": "search_documentation", "description": "Search the product documentation. Use it whenever the user asks how a feature works.", "value": { "tool_type": "flowmodule", "type": "rawscript", "language": "bun", "content": "export async function main(query: string) { return ['doc1', 'doc2']; }", "input_transforms": { "query": { "type": "static", "value": "" } } } } ] } } ``` - `provider` is an object, not a bare resource string: `{ "kind": , "resource": "$res:", "model": }`. Required unless the module links to a saved agent through `value.agent`. Static is right for a flow run from a form; a chat flow wires its fields to flow inputs instead — see below ### Chat-Mode Flows A flow with `value.chat_input_enabled: true` is run from a chat instead of a form: the composer sends one message per turn and renders the conversation. It needs a required `user_message` string input, read by the agent. Any other flow input the composer does not edit itself is asked for under Configure inputs. **A static `provider` gives a chat that cannot change its model.** Feed it from flow inputs instead, either way round: one input carrying the whole object (`"expr": "flow_input.model_config"`) makes every field editable, or wire it field by field to fix some and expose others. A field the chat can write becomes a control in the composer — a provider picker, a model list, a thinking control — and a field left static is fixed, with no control drawn for it. `kind` is the one exception: the composer writes it only together with `resource`, since a provider is picked as a pair, so a `kind` input wired on its own stays askable under Configure inputs and nothing the run needs becomes unreachable. ```json { "id": "chat_agent", "value": { "type": "aiagent", "input_transforms": { "provider": { "type": "javascript", "expr": "({ kind: 'anthropic', resource: '$res:f/ai/claude', model: flow_input.model, reasoning_effort: flow_input.thinking })" }, "user_message": { "type": "javascript", "expr": "flow_input.user_message" }, "user_attachments": { "type": "javascript", "expr": "flow_input.files" }, "memory": { "type": "static", "value": { "kind": "compaction" } }, "streaming": { "type": "static", "value": true }, "output_type": { "type": "static", "value": "text" } }, "tools": [] } } ``` - Wiring field by field means one object literal whose values are literals or bare `flow_input.x` references. A spread, a call or a computed key leaves the composer unable to tell which input feeds which field, so it offers no control at all — a bare `flow_input.x` for the whole object is read instead as that one input carrying every field - `memory` is what lets the agent see earlier turns; without it every message starts from nothing - `streaming` on makes the answer and its thinking appear token by token instead of all at once - `user_attachments` points at a flow input typed as an array of s3 objects (`{ "type": "array", "items": { "type": "object", "resourceType": "s3object" } }`), so files sent with a message reach the agent - Running one needs a `memory_id` **query parameter** — not a flow argument — naming the conversation the turn belongs to: a fresh UUID starts one, reusing a UUID continues it. The chat supplies it itself; a run driven any other way has to pass it or the server refuses the job ### Tool Naming Rules These rules cover `flowmodule` tools, the ones the agent calls by name. A `websearch` tool's `summary` is a plain label (`Web Search`), and an `mcp` tool exposes the MCP server's own tool names, so neither is name-checked at all — leave those summaries as they are. - A flowmodule tool's `summary` is the **name the agent calls it by**, not a human label. Put the human-readable explanation in `description` - `summary` must match `^[a-zA-Z0-9_]+$`: letters, numbers and underscores only. No spaces, dashes, dots or accents — `search_documentation`, never `Search documentation` - Always set `summary`. It must be unique among that agent's tools, and must not be one of the reserved ids (`do`, `bg`, `ctx`, `state`, `if`, `else`, `for`, `delete`, `while`, `new`, `in`, `failure`, `preprocessor`, `as`, `Input`, `Result`, `Trigger`) - A tool name outside that character set fails any run that offers the tool to the agent, with `Invalid tool name`. The flow write tools refuse such a name. - Tool `id` follows the same rules as any module ID — unique across the flow, underscores not spaces - `description` is optional free text telling the agent when and how to call the tool. Set it whenever the name alone does not make that obvious; it overrides the description derived from the underlying script ## AI Decision Modules An `aidecision` module asks a decision model (TypeSafe's Jev, Cloudflare's Clef or OpenAI's Decisions API) typed questions about a `state` and answers each with calibrated probabilities instead of text. Prefer it over an `aiagent` when the step is a judgment (classify, route, score or a yes/no check) that needs no tools and no free text: it is faster, cheaper, and its answers have a fixed shape. ```json { "id": "triage", "summary": "Classify the ticket", "value": { "type": "aidecision", "input_transforms": { "provider": { "type": "static", "value": { "kind": "typesafe", "resource": "$res:f/ai/typesafe", "model": "jev-latest" } }, "state": { "type": "javascript", "expr": "flow_input.message" }, "questions": { "type": "static", "value": { "intent": { "type": "choice", "instructions": "What does the customer want?", "criteria": { "refund": "Money back", "bug": "Something is broken", "other": "Anything else" } }, "urgency": { "type": "score", "instructions": "How urgent is the ticket?", "criteria": ["Can wait", "This week", "Today", "Right now"] }, "angry": { "type": "noul", "instructions": "Is the customer angry?" } } } } } } ``` - `provider.kind` is `typesafe` (`model` `jev-latest` unless a version is pinned), `cloudflare` (`model` `clef`, or `clef-flash` for faster answers) or `openai` (`model` `gpt-6-luna`, never a chat model); the resource is of that same type - `state` is the content to evaluate: usually a text, such as the message to classify. To combine several values, pass an object with descriptive keys holding only what the questions need (`({ message: flow_input.message, plan: results.get_account.plan })`); an array of strings also works - `questions` maps each question name to `{ type, instructions, criteria }`: - `choice`: `criteria` maps each option to its description (up to 255 options). The answer has `choice`, `probabilities` and `confidence` - `score`: `criteria` is an ordered array of 2 to 10 level descriptions. The answer has `score`, `legend`, `probabilities` and `confidence` - `noul`: yes/no, `criteria` optionally `{ "true": ..., "false": ... }` descriptions. The answer has `noul`, the probability of yes from 0 to 1 - The result is `{ output, model, usage }` with `output` keyed by question name, so a later step reads `results.triage.output.intent.choice`, `results.triage.output.urgency.score` or `results.triage.output.angry.noul > 0.7` - On `openai` the same `questions` are translated for its Decisions API and the answers read the same way (`choice`, `score`, `noul`), except that `probabilities` is a list of `{ value, probability }` (plus `label` on a score) and a score has no `legend`. A question OpenAI refuses to answer fails the step. A `state` that is an array of user messages (`[{ role: "user", content: [{ type: "input_text", text }, { type: "input_image", image_url: "data:image/png;base64,..." }] }]`) is sent as is, which is how an image is evaluated; any other object or array is sent as JSON text ### Branching on the Answers To route on the answers, put a `branchone` right after the decision, one branch per option, with each `expr` reading the decision by id: ```json { "id": "route", "value": { "type": "branchone", "branches": [ { "summary": "refund", "expr": "results.triage.output.intent.choice === 'refund'", "modules": [...] }, { "summary": "bug", "expr": "results.triage.output.intent.choice === 'bug'", "modules": [...] } ], "default": [...] } } ``` For a yes/no question, one branch with `"expr": "results.triage.output.angry.noul >= 0.5"` (tune the threshold as needed) and the `default` as the "no" path. ### As an Agent Tool An `aidecision` can be a `flowmodule` tool of an `aiagent` (`"tool_type": "flowmodule", "type": "aidecision"`): set `state` to `{ "type": "ai" }` so the calling model supplies it, and only `output` goes back to the model. The Tool Naming Rules apply to its `summary`. Only a flow's own agent step can call one, not an agent used as a tool. ## Common Mistakes to Avoid - Missing `input_transforms` - Rawscript parameters won't receive values without them - Referencing future steps - `results.step_id` only works for steps that execute before the current one - Duplicate module IDs - Each module ID must be unique in the flow - AI agent flowmodule tool names with spaces - `summary` is the tool name and only accepts letters, numbers and underscores ## Data Flow Between Steps - `flow_input.property` - Access flow input parameters - `results.step_id` - Access output from a previous step only when that step result is in scope - `results.step_id.property` - Access specific property from a previous step output only when that step result is in scope - `flow_input.iter.value` - Current iteration value inside a `forloopflow`; in a `whileloopflow` it is just the iteration index (a plain number, same as `flow_input.iter.index`) - `flow_input.iter.index` - Current loop index when inside a loop (`forloopflow` or `whileloopflow`) - After a suspend step (approval), the next step's javascript expressions also get: - `resume` - the last resume payload (the resume form values); with `continue_on_disapprove_timeout`, a disapproval or timeout yields `{ error: { name: "SuspendedDisapproved" | "SuspendedTimedOut", message } }` instead - `resumes` - every resume payload, in arrival order - `approvers` - a plain array of strings, one per resume: for a resume through the `resume`/`cancel` URL from `getResumeUrls(approver)`, the `approver` passed there if any; otherwise (including the `approvalPage` link) the resuming user's username, else `"anonymous"`, e.g. `approvers[0]`. It is NOT the `{ resume_id, approver }` objects stored in the flow status, so `approvers[0].approver` is always undefined ## Loop Structure Rules - A `forloopflow` runs its `modules` once per element of `iterator`, a javascript expression returning an array (e.g. `results.get_items`); `parallel: true` runs the iterations concurrently, and `skip_failures: true` carries on past a failed iteration - For `whileloopflow`, break the loop with a module-level `stop_after_if`: on the loop module itself, or on an inner step (required when that step carries state via its own `results` — see below) - `stop_after_if` is always a sibling of `id` and `value` on a flow module — never a direct key of the loop's `value` object - `stop_after_all_iters_if` is for checks after the whole loop finishes, not the normal per-iteration break condition - `stop_after_if` is evaluated after each iteration: on the loop module, `result` is that iteration's result (what its last step returned); on an inner step, it is that step's result - `flow_input.iter.value` in a `whileloopflow` is just the iteration index (same number as `flow_input.iter.index`) — it never carries state, so `flow_input.iter.value.` is always undefined and a loop whose stop condition depends on it never terminates - To carry state across iterations, a step reads its own previous-iteration result via `results.` with a first-iteration fallback (e.g. `results.b ?? flow_input.start`) — but then the loop's `stop_after_if` MUST sit on that inner step, not on the loop module: a body that is exactly one plain step with the stop condition on the loop module runs on a fast path where `results.` is null on every iteration and the loop never terminates (bodies with 2+ steps, or whose single step has its own `stop_after_if`, retry or similar, resolve `results` across iterations regardless of stop placement) - For state that is just a counter, derive it from the index instead (e.g. `flow_input.iter.index + 1`) — that works in every configuration, including with `stop_after_if` on the loop module - If the user asks for a final scalar/object after a loop, add a normal step after the loop that extracts the final value from the loop result instead of returning the whole loop result array Correct `whileloopflow` shape: ```yaml - id: loop_until_done stop_after_if: expr: result.done === true skip_if_stopped: false value: type: whileloopflow skip_failures: false modules: - id: advance_state value: type: rawscript input_transforms: count: type: javascript expr: flow_input.iter.index + 1 - id: return_final_state value: type: rawscript input_transforms: final_state: type: javascript expr: results.loop_until_done[results.loop_until_done.length - 1] ``` Correct `whileloopflow` shape carrying state via `results` (stop condition on the inner step): ```yaml - id: loop_until_done value: type: whileloopflow skip_failures: false modules: - id: advance_state stop_after_if: expr: result.done === true skip_if_stopped: false value: type: rawscript input_transforms: state: type: javascript expr: results.advance_state ?? flow_input.initial_state ``` Incorrect `whileloopflow` patterns: ```yaml - id: loop_until_done value: type: whileloopflow stop_after_if: expr: result.done === true ``` ```yaml input_transforms: state: type: javascript # iter.value is a number (the iteration index); there is no previous-iteration state expr: flow_input.iter.value.count ``` ```yaml input_transforms: final_state: type: javascript expr: results.loop_until_done ``` ## Approval / Suspend Structure An approval step is a normal **script** step (`type: rawscript` or `type: script`) that is turned into an approval by adding a module-level `suspend`. Its script calls `wmill.getResumeUrls(approver)` to generate the secret resume/cancel URLs and returns them so they can be sent to the approver(s) (Slack, email, etc.) or approved from the run page. - `suspend` belongs on the flow module object itself, as a sibling of `id` and `value` - Never put `suspend` inside `value` - Do NOT use `type: identity` for an approval step. An identity step suspends but never produces the resume URLs, so approvers have no link to act on — it is not a functional approval. Correct shape: ```yaml - id: request_approval suspend: required_events: 1 resume_form: schema: type: object properties: comment: type: string required: [comment] value: type: rawscript language: bun input_transforms: approver: type: static value: '' content: | import * as wmill from "windmill-client" export async function main(approver?: string) { const urls = await wmill.getResumeUrls(approver) // send urls.resume / urls.cancel to the approver(s), e.g. via Slack or email return urls } ``` Incorrect shape (suspend misplaced inside `value`): ```yaml - id: request_approval value: type: rawscript suspend: required_events: 1 ``` Incorrect shape (identity has no resume URLs — not a real approval): ```yaml - id: request_approval suspend: required_events: 1 value: type: identity ``` ## Branch Result Scope Rules - A `branchone` runs the first of its `branches` whose `expr` is true, in order, and its `default` modules when none is; a `branchall` runs every branch (concurrently with `parallel: true`) - Inside a branch, you may reference earlier outer steps and earlier steps in the same branch - Outside a `branchone`, do NOT reference ids of steps that only exist inside its branches or default branch. Use `results.` instead - Outside a `branchall`, do NOT reference ids of steps inside its branches. Use `results.` instead - If downstream steps need a stable shape after a branch, make each branch return the same fields - When needed, add a normalization step immediately after the branch and consume `results.` there Correct after `branchone`: ```yaml - id: route_order value: type: branchone ... - id: send_confirmation value: input_transforms: routed: type: javascript expr: results.route_order ``` Incorrect after `branchone`: ```yaml expr: results.create_shipment expr: results.create_backorder ``` Correct after `branchall`: ```yaml - id: enrich_parallel value: type: branchall parallel: true ... - id: combine_data value: input_transforms: enrichments: type: javascript expr: results.enrich_parallel ``` ## Input Transforms Every rawscript module needs `input_transforms` to map function parameters to values: Static transform (fixed value): {"param_name": {"type": "static", "value": "fixed_string"}} JavaScript transform (dynamic expression): {"param_name": {"type": "javascript", "expr": "results.previous_step.data"}} ## Resource References - For flow inputs: Use type `"object"` with format `"resource-{type}"` (e.g., `"resource-postgresql"`) - For step inputs: Use static value `"$res:path/to/resource"` ## Reusing Existing Scripts and Flows Unless the user asked for new code, look for a workspace script or flow that already does a step's job before writing it, and reuse it by path instead of copying its logic into a rawscript: - a workspace script: `type: script` with `path` (e.g. `f/folder/send_email`) - a workspace flow, run as a subflow: `type: flow` with `path` - a Hub script: `type: script` with a `hub///` path The step's `input_transforms` must cover the reused item's inputs, so read its input schema first. ## Additional Prompt for AI A flow's input schema may carry a top-level `prompt_for_ai` string, as a script's can: its author's instructions to an AI choosing the inputs. Follow it when you pick arguments to run that flow, and keep it when you rewrite the schema. ## Organizing Flows: Groups and Notes Groups and notes shape how a flow reads in the editor; neither changes what it does. **Segment every non-trivial flow into groups without waiting to be asked.** Whenever a flow has more than a couple of steps, or consecutive steps form a stage ("fetch", "transform", "notify"), put them in a group, and aim for every meaningful step to belong to one. Use notes sparingly, for flow-wide information that belongs to no span of steps: the flow's purpose, key assumptions, warnings, TODOs. One note is usually enough; never label a run of steps with a note, which is what a group is for. `value.groups` lists the groups, each spanning the steps from `start_id` to `end_id`: - `start_id`, `end_id` (required): ids of the group's first and last step; the same id for both makes a one-step group - `summary`: the group's title - `note`: markdown shown under the title - `color`: one of `yellow`, `blue`, `green`, `purple`, `pink`, `orange`, `red`, `cyan`, `lime`, `gray`, never a hex code or CSS color; leave it out and the editor picks one - `autocollapse`: `true` shows the group collapsed by default The editor refuses to draw a flow whose groups break any of these rules: - `start_id` and `end_id` are steps of the same list: both top-level, or both in the same loop body or branch. A group can hold a loop or branch step whole, but cannot start outside one and end inside it - `start_id` does not come after `end_id` in that list - groups nest (one entirely inside another) but never partly overlap, and no two groups share both `start_id` and `end_id` - groups hold ordinary steps only: never `preprocessor`, `failure`, `Input`, `Result`, `Trigger`, or an AI agent's tools `value.notes` lists sticky notes, each with a unique `id`, markdown `text`, a `color` from the same list, and `type: free`. The `group` note type is deprecated; use `value.groups` instead. Leave a note's `position` and `size` out and they are filled in for you. ## Final Structural Self-Check Before finalizing a flow, verify: - any preprocessor is in `value.preprocessor_module` - any failure handler is in `value.failure_module` - any approval step has module-level `suspend` - no downstream step references inner branch step ids from outside the branch - every AI agent flowmodule tool has a unique `summary` made only of letters, numbers and underscores - every group starts and ends on steps of the same list, start before end, nesting without partial overlap ## S3 Object Operations Windmill provides built-in support for S3-compatible storage operations. To accept an S3 object as flow input: ```json { "type": "object", "properties": { "file": { "type": "object", "format": "resource-s3_object", "description": "File to process" } } } ``` ## Using Resources in Flows On Windmill, credentials and configuration are stored in resources. Resource types define the format of the resource. ### As Flow Input In the flow schema, set the property type to `"object"` with format `"resource-{type}"`: ```json { "type": "object", "properties": { "database": { "type": "object", "format": "resource-postgresql", "description": "Database connection" } } } ``` ### As Step Input (Static Reference) Reference a specific resource using `$res:` prefix: ```json { "database": { "type": "static", "value": "$res:f/folder/my_database" } } ``` ## OpenFlow Schema {"OpenFlow":{"type":"object","description":"Top-level flow definition containing metadata, configuration, and the flow structure","properties":{"summary":{"type":"string","description":"Short description of what this flow does"},"description":{"type":"string","description":"Detailed documentation for this flow"},"value":{"$ref":"#/components/schemas/FlowValue"},"schema":{"type":"object","description":"JSON Schema for flow inputs. Use this to define input parameters, their types, defaults, and validation. For resource inputs, set type to 'object' and format to 'resource-' (e.g., 'resource-stripe')"},"on_behalf_of_email":{"type":"string","description":"Address of the account the flow runs on behalf of. Derived from on_behalf_of on read; accepted on write, where it is resolved to the account it names."},"on_behalf_of":{"type":"string","description":"The flow runs with the permissions of this identity: u/{username}, g/{group}, or a bare email when the username is itself email-shaped. The only stored half of the identity; on_behalf_of_email is derived from it. Omit it when writing and it is resolved from that address instead."}},"required":["summary","value"]},"FlowValue":{"type":"object","description":"The flow structure containing modules and optional preprocessor/failure handlers","properties":{"modules":{"type":"array","description":"Array of steps that execute in sequence. Each step can be a script, subflow, loop, or branch","items":{"$ref":"#/components/schemas/FlowModule"}},"failure_module":{"description":"Special module that executes when the flow fails. Receives error object with message, name, stack, and step_id. Must have id 'failure'. Only supports script/rawscript types","$ref":"#/components/schemas/FlowModule"},"preprocessor_module":{"description":"Special module that runs before the first step on external triggers. Must have id 'preprocessor'. Only supports script/rawscript types. Cannot reference other step results","$ref":"#/components/schemas/FlowModule"},"same_worker":{"type":"boolean","description":"If true, all steps run on the same worker for better performance"},"preserve_step_tags":{"type":"boolean","description":"If true and the flow runs on a custom worker tag, steps that declare their own non-empty tag run on it instead of inheriting the flow tag. Steps without their own tag still inherit the flow tag."},"concurrent_limit":{"type":"number","description":"Maximum number of concurrent executions of this flow"},"concurrency_key":{"type":"string","description":"Expression to group concurrent executions (e.g., by user ID)"},"concurrency_time_window_s":{"type":"number","description":"Time window in seconds for concurrent_limit"},"debounce_delay_s":{"type":"integer","description":"Delay in seconds to debounce flow executions"},"debounce_key":{"type":"string","description":"Expression to group debounced executions"},"debounce_args_to_accumulate":{"type":"array","description":"Arguments to accumulate across debounced executions","items":{"type":"string"}},"max_total_debouncing_time":{"type":"integer","description":"Maximum total time in seconds that a job can be debounced"},"max_total_debounces_amount":{"type":"integer","description":"Maximum number of times a job can be debounced"},"skip_expr":{"type":"string","description":"JavaScript expression to conditionally skip the entire flow"},"cache_ttl":{"type":"number","description":"Cache duration in seconds for flow results"},"cache_ignore_s3_path":{"type":"boolean"},"delete_after_secs":{"type":"integer","description":"If set, delete the flow job's args, result and logs after this many seconds following job completion"},"flow_env":{"type":"object","description":"Environment variables available to all steps. Values can be strings, JSON values, or special references: '$var:path' (workspace variable) or '$res:path' (resource).","additionalProperties":{}},"priority":{"type":"number","description":"Execution priority (higher numbers run first)"},"early_return":{"type":"string","description":"JavaScript expression to return early from the flow"},"chat_input_enabled":{"type":"boolean","description":"Whether this flow accepts chat-style input"},"notes":{"type":"array","description":"Sticky notes attached to the flow","items":{"$ref":"#/components/schemas/FlowNote"}},"groups":{"type":"array","description":"Semantic groups of modules for organizational purposes","items":{"$ref":"#/components/schemas/FlowGroup"}}},"required":["modules"]},"Retry":{"type":"object","description":"Retry configuration for failed module executions","properties":{"constant":{"type":"object","description":"Retry with constant delay between attempts","properties":{"attempts":{"type":"integer","description":"Number of retry attempts"},"seconds":{"type":"integer","description":"Seconds to wait between retries"}}},"exponential":{"type":"object","description":"Retry with exponential backoff: the n-th retry waits multiplier \u00d7 seconds^n","properties":{"attempts":{"type":"integer","description":"Number of retry attempts"},"multiplier":{"type":"integer","description":"Multiplier for exponential backoff"},"seconds":{"type":"integer","minimum":1,"description":"Base of the exponential (seconds); the n-th retry waits multiplier \u00d7 seconds^n, where n counts constant retries too"},"random_factor":{"type":"integer","minimum":0,"maximum":100,"description":"Random jitter percentage (0-100) to avoid thundering herd"}}},"retry_if":{"$ref":"#/components/schemas/RetryIf"}}},"FlowNote":{"type":"object","description":"A sticky note attached to a flow for documentation and annotation","properties":{"id":{"type":"string","description":"Unique identifier for the note"},"text":{"type":"string","description":"Content of the note"},"position":{"type":"object","description":"Position of the note in the flow editor","properties":{"x":{"type":"number","description":"X coordinate"},"y":{"type":"number","description":"Y coordinate"}},"required":["x","y"]},"size":{"type":"object","description":"Size of the note in the flow editor","properties":{"width":{"type":"number","description":"Width in pixels"},"height":{"type":"number","description":"Height in pixels"}},"required":["width","height"]},"color":{"type":"string","description":"Color of the note, one of: yellow, blue, green, purple, pink, orange, red, cyan, lime, gray. Any other value renders unstyled."},"type":{"type":"string","enum":["free","group"],"description":"Type of note - 'free' for standalone notes. 'group' notes are deprecated; segment a flow with FlowValue.groups instead."},"locked":{"type":"boolean","default":false,"description":"Whether the note is locked and cannot be edited or moved"},"contained_node_ids":{"type":"array","items":{"type":"string"},"description":"For group notes, the IDs of nodes contained within this group"}},"required":["id","text","color","type"]},"FlowGroup":{"type":"object","description":"A semantic group of flow modules for organizational purposes. Does not affect execution \u2014 modules remain in their original position in the flow. Groups provide naming and collapsibility in the editor. Members are computed dynamically from all nodes on paths between start_id and end_id.","properties":{"summary":{"type":"string","description":"Display name for this group"},"note":{"type":"string","description":"Markdown note shown below the group header"},"autocollapse":{"type":"boolean","default":false,"description":"If true, this group is collapsed by default in the flow editor. UI hint only."},"start_id":{"type":"string","description":"ID of the first flow module in this group (topological entry point)"},"end_id":{"type":"string","description":"ID of the last flow module in this group (topological exit point)"},"color":{"type":"string","description":"Color for the group in the flow editor, one of: yellow, blue, green, purple, pink, orange, red, cyan, lime, gray. Omit it to let the editor pick one."}},"required":["start_id","end_id"]},"RetryIf":{"type":"object","description":"Conditional retry based on error or result","properties":{"expr":{"type":"string","description":"JavaScript expression that returns true to retry. Has access to 'result' and 'error' variables"}},"required":["expr"]},"StopAfterIf":{"type":"object","description":"Early termination condition for a module","properties":{"skip_if_stopped":{"type":"boolean","description":"If true, following steps are skipped when this condition triggers"},"expr":{"type":"string","description":"JavaScript expression evaluated after the module runs. Can use 'result' (step's result) or 'flow_input'. Return true to stop"},"error_message":{"type":"string","nullable":true,"description":"Custom error message when stopping with an error. Mutually exclusive with skip_if_stopped. If set to a non-empty string, the flow stops with this error. If empty string, a default error message is used. If null or omitted, no error is raised."},"error_include_result":{"type":"boolean","description":"When stopping with an error (error_message set), embed the stopping step's own result inside the raised error object (as error.result) instead of discarding it. The top-level result stays { error }. Defaults to false."}},"required":["expr"]},"FlowModule":{"type":"object","description":"A single step in a flow. Can be a script, subflow, loop, or branch","properties":{"id":{"type":"string","description":"Unique identifier for this step. Used to reference results via 'results.step_id'. Must be a valid identifier (alphanumeric, underscore, hyphen)"},"value":{"$ref":"#/components/schemas/FlowModuleValue"},"stop_after_if":{"description":"Early termination condition evaluated after this step completes","$ref":"#/components/schemas/StopAfterIf"},"stop_after_all_iters_if":{"description":"For loops only - early termination condition evaluated after all iterations complete","$ref":"#/components/schemas/StopAfterIf"},"skip_if":{"type":"object","description":"Conditionally skip this step based on previous results or flow inputs","properties":{"expr":{"type":"string","description":"JavaScript expression that returns true to skip. Can use 'flow_input' or 'results.'"}},"required":["expr"]},"sleep":{"description":"Delay before executing this step (in seconds or as expression)","$ref":"#/components/schemas/InputTransform"},"cache_ttl":{"type":"number","description":"Cache duration in seconds for this step's results"},"cache_ignore_s3_path":{"type":"boolean"},"timeout":{"description":"Maximum execution time in seconds (static value or expression)","$ref":"#/components/schemas/InputTransform"},"delete_after_secs":{"type":"integer","description":"If set, delete the step's args, result and logs after this many seconds following job completion"},"summary":{"type":"string","description":"Short description of what this step does"},"mock":{"type":"object","description":"Mock configuration for testing without executing the actual step","properties":{"enabled":{"type":"boolean","description":"If true, return mock value instead of executing"},"return_value":{"description":"Value to return when mocked"}}},"suspend":{"type":"object","description":"Configuration for approval/resume steps that wait for user input","properties":{"required_events":{"type":"integer","description":"Number of approvals required before continuing"},"timeout":{"type":"integer","description":"Timeout in seconds before auto-continuing or canceling"},"resume_form":{"type":"object","description":"Form schema for collecting input when resuming","properties":{"schema":{"type":"object","description":"JSON Schema for the resume form"}}},"user_auth_required":{"type":"boolean","description":"If true, only authenticated users can approve"},"user_groups_required":{"description":"Expression or list of groups that can approve","$ref":"#/components/schemas/InputTransform"},"self_approval_disabled":{"type":"boolean","description":"If true, the user who started the flow cannot approve"},"hide_cancel":{"type":"boolean","description":"If true, hide the cancel button on the approval form"},"continue_on_disapprove_timeout":{"type":"boolean","description":"If true, continue flow on timeout instead of canceling"},"skin":{"type":"string","enum":["detailed","minimal"],"description":"How the approval request is presented, on the approval page and in Slack/Teams approval messages. 'detailed' (used when unset) shows the flow details (arguments, graph, approvers); 'minimal' shows only the request: the step description, form and approve/reject actions"}}},"priority":{"type":"number","description":"Execution priority for this step (higher numbers run first)"},"continue_on_error":{"type":"boolean","description":"If true, flow continues even if this step fails"},"job_token_scopes":{"type":"array","nullable":true,"items":{"type":"string"},"description":"Scopes the token of this step's jobs is restricted to (domain:action[:resource], e.g. oidc:write), on top of the flow's own restriction: a step can only narrow it. Applies to everything the step runs (loop and branch bodies, AI agent tools)."},"retry":{"description":"Retry configuration if this step fails","$ref":"#/components/schemas/Retry"},"debouncing":{"description":"Debounce configuration for this step (EE only)","type":"object","properties":{"debounce_delay_s":{"type":"integer","description":"Delay in seconds to debounce this step's executions across flow runs"},"debounce_key":{"type":"string","description":"Expression to group debounced executions. Supports $workspace and $args[name]. Default: $workspace/flow/-"},"debounce_args_to_accumulate":{"type":"array","description":"Array-type arguments to accumulate across debounced executions","items":{"type":"string"}},"max_total_debouncing_time":{"type":"integer","description":"Maximum total time in seconds before forced execution"},"max_total_debounces_amount":{"type":"integer","description":"Maximum number of debounces before forced execution"}}}},"required":["value","id"]},"InputTransform":{"description":"Maps input parameters for a step. Can be a static value or a JavaScript expression that references previous results or flow inputs","oneOf":[{"$ref":"#/components/schemas/StaticTransform"},{"$ref":"#/components/schemas/JavascriptTransform"},{"$ref":"#/components/schemas/AiTransform"}],"discriminator":{"propertyName":"type","mapping":{"static":"#/components/schemas/StaticTransform","javascript":"#/components/schemas/JavascriptTransform","ai":"#/components/schemas/AiTransform"}}},"StaticTransform":{"type":"object","description":"Static value passed directly to the step. Use for hardcoded values or resource references like '$res:path/to/resource'","properties":{"value":{"description":"The static value. For resources, use format '$res:path/to/resource'"},"type":{"type":"string","enum":["static"]}},"required":["type"]},"JavascriptTransform":{"type":"object","description":"JavaScript expression evaluated at runtime. Can reference previous step results via 'results.step_id' or flow inputs via 'flow_input.property'. Inside for loops, use 'flow_input.iter.value' for the current iteration value (in while loops it equals 'flow_input.iter.index')","properties":{"expr":{"type":"string","description":"JavaScript expression returning the value. Available variables - results (object with all previous step results), flow_input (flow inputs), flow_input.iter (in loops)"},"type":{"type":"string","enum":["javascript"]}},"required":["expr","type"]},"AiTransform":{"type":"object","description":"Value resolved by the AI runtime for this input. The AI engine decides how to satisfy the parameter.","properties":{"type":{"type":"string","enum":["ai"]}},"required":["type"]},"AIProviderKind":{"type":"string","description":"Supported AI provider types","enum":["openai","azure_openai","azure_foundry","anthropic","mistral","deepseek","googleai","groq","openrouter","togetherai","customai","aws_bedrock","typesafe","cloudflare"]},"ProviderConfig":{"type":"object","description":"Complete AI provider configuration with resource reference and model selection","properties":{"kind":{"$ref":"#/components/schemas/AIProviderKind"},"resource":{"type":"string","description":"Resource reference in format '$res:{resource_path}' pointing to provider credentials"},"model":{"type":"string","description":"Model identifier (e.g., 'gpt-4', 'claude-3-opus-20240229', 'gemini-pro')"},"reasoning_effort":{"type":"string","description":"Provider-native reasoning effort token (e.g. 'low', 'high', 'none') for models that support extended thinking. Optional; unset leaves the provider default."}},"required":["kind","resource","model"]},"StaticProviderTransform":{"type":"object","description":"Static provider configuration passed directly to the AI agent","properties":{"value":{"$ref":"#/components/schemas/ProviderConfig"},"type":{"type":"string","enum":["static"]}},"required":["type","value"]},"ProviderTransform":{"description":"Provider configuration - can be static (ProviderConfig), JavaScript expression, or AI-determined","oneOf":[{"$ref":"#/components/schemas/StaticProviderTransform"},{"$ref":"#/components/schemas/JavascriptTransform"},{"$ref":"#/components/schemas/AiTransform"}],"discriminator":{"propertyName":"type","mapping":{"static":"#/components/schemas/StaticProviderTransform","javascript":"#/components/schemas/JavascriptTransform","ai":"#/components/schemas/AiTransform"}}},"MemoryOff":{"type":"object","description":"No conversation memory/context","properties":{"kind":{"type":"string","enum":["off"]}},"required":["kind"]},"MemoryWindow":{"type":"object","description":"Keeps the most recent messages of the memory named by the run's memory id (or the step's\n`memory_id`). Without a memory id the agent runs without memory.\n","properties":{"kind":{"type":"string","enum":["window"]},"context_length":{"type":"integer","description":"Number of most recent messages to load and store. 0 turns memory off."}},"required":["kind","context_length"]},"MemoryAuto":{"type":"object","deprecated":true,"description":"Deprecated, still read as it was written: the run's memory id, else the `memory_id` here.\nThe step's own `memory_id` is not read while this kind is set; switch the kind to `window`\nto use it. Without a `context_length`, or with 0, it is `off` and reads `previous_messages`.\n","properties":{"kind":{"type":"string","enum":["auto"]},"context_length":{"type":"integer","description":"Maximum number of messages to retain in context"},"memory_id":{"type":"string","description":"Identifier for persistent memory across agent invocations"}},"required":["kind"]},"MemoryCompaction":{"type":"object","description":"Keeps the whole memory named by the run's memory id (or the step's `memory_id`), replacing\nits older part with a summary as the conversation approaches the model's context window.\nWithout a memory id the agent runs without memory, and compaction bounds the run's own loop.\n","properties":{"kind":{"type":"string","enum":["compaction"]},"context_window":{"type":"integer","description":"Overrides the context window looked up from the model, in tokens. Only a model\nWindmill does not know needs one; those fall back to 128000.\n"}},"required":["kind"]},"MemoryMessage":{"type":"object","description":"A single message in conversation history","properties":{"role":{"type":"string","enum":["user","assistant","system"]},"content":{"type":"string"}},"required":["role","content"]},"MemoryManual":{"type":"object","deprecated":true,"description":"Deprecated, still read as it was written. Move the step to `off` with `previous_messages` instead.","properties":{"kind":{"type":"string","enum":["manual"]},"messages":{"type":"array","items":{"$ref":"#/components/schemas/MemoryMessage"}}},"required":["kind","messages"]},"MemoryConfig":{"description":"Managed memory, stored by Windmill and replayed with each request. The memory is named by a memory id, see `memory_id`. While it is off, a step can supply its history in `previous_messages`.","oneOf":[{"$ref":"#/components/schemas/MemoryOff"},{"$ref":"#/components/schemas/MemoryWindow"},{"$ref":"#/components/schemas/MemoryCompaction"},{"$ref":"#/components/schemas/MemoryAuto"},{"$ref":"#/components/schemas/MemoryManual"}],"discriminator":{"propertyName":"kind","mapping":{"off":"#/components/schemas/MemoryOff","window":"#/components/schemas/MemoryWindow","compaction":"#/components/schemas/MemoryCompaction","auto":"#/components/schemas/MemoryAuto","manual":"#/components/schemas/MemoryManual"}}},"StaticMemoryTransform":{"type":"object","description":"Static memory configuration passed directly to the AI agent","properties":{"value":{"$ref":"#/components/schemas/MemoryConfig"},"type":{"type":"string","enum":["static"]}},"required":["type","value"]},"MemoryTransform":{"description":"Memory configuration - can be static (MemoryConfig), JavaScript expression, or AI-determined","oneOf":[{"$ref":"#/components/schemas/StaticMemoryTransform"},{"$ref":"#/components/schemas/JavascriptTransform"},{"$ref":"#/components/schemas/AiTransform"}],"discriminator":{"propertyName":"type","mapping":{"static":"#/components/schemas/StaticMemoryTransform","javascript":"#/components/schemas/JavascriptTransform","ai":"#/components/schemas/AiTransform"}}},"FlowModuleValue":{"description":"The actual implementation of a flow step. Can be a script (inline or referenced), subflow, loop, branch, or special module type","oneOf":[{"$ref":"#/components/schemas/RawScript"},{"$ref":"#/components/schemas/PathScript"},{"$ref":"#/components/schemas/PathFlow"},{"$ref":"#/components/schemas/ForloopFlow"},{"$ref":"#/components/schemas/WhileloopFlow"},{"$ref":"#/components/schemas/BranchOne"},{"$ref":"#/components/schemas/BranchAll"},{"$ref":"#/components/schemas/Identity"},{"$ref":"#/components/schemas/AiAgent"},{"$ref":"#/components/schemas/AiDecision"}],"discriminator":{"propertyName":"type","mapping":{"rawscript":"#/components/schemas/RawScript","script":"#/components/schemas/PathScript","flow":"#/components/schemas/PathFlow","forloopflow":"#/components/schemas/ForloopFlow","whileloopflow":"#/components/schemas/WhileloopFlow","branchone":"#/components/schemas/BranchOne","branchall":"#/components/schemas/BranchAll","identity":"#/components/schemas/Identity","aiagent":"#/components/schemas/AiAgent","aidecision":"#/components/schemas/AiDecision"}}},"RawScript":{"type":"object","description":"Inline script with code defined directly in the flow. Use 'bun' as default language if unspecified. The script receives arguments from input_transforms","properties":{"input_transforms":{"type":"object","description":"Map of parameter names to their values (static or JavaScript expressions). These become the script's input arguments","additionalProperties":{"$ref":"#/components/schemas/InputTransform"}},"content":{"type":"string","description":"The script source code. Should export a 'main' function"},"language":{"type":"string","description":"Programming language for this script","enum":["deno","bun","bunnative","python3","go","bash","powershell","postgresql","mysql","bigquery","snowflake","mssql","oracledb","graphql","nativets","php","rust","ansible","csharp","nu","java","ruby","rlang","duckdb"]},"path":{"type":"string","description":"Optional path for saving this script"},"lock":{"type":"string","description":"Lock file content for dependencies"},"type":{"type":"string","enum":["rawscript"]},"tag":{"type":"string","description":"Worker group tag for execution routing"},"concurrent_limit":{"type":"number","description":"Maximum concurrent executions of this script"},"concurrency_time_window_s":{"type":"number","description":"Time window for concurrent_limit"},"custom_concurrency_key":{"type":"string","description":"Custom key for grouping concurrent executions"},"is_trigger":{"type":"boolean","description":"If true, this script is a trigger that can start the flow"},"assets":{"type":"array","description":"External resources this script accesses (S3 objects, resources, etc.)","items":{"type":"object","required":["path","kind"],"properties":{"path":{"type":"string","description":"Path to the asset"},"kind":{"type":"string","description":"Type of asset","enum":["s3object","resource","ducklake","datatable","volume","dbt"]},"access_type":{"type":"string","nullable":true,"description":"Access level for this asset","enum":["r","w","rw"]},"alt_access_type":{"type":"string","nullable":true,"description":"Alternative access level","enum":["r","w","rw"]}}}}},"required":["type","content","language","input_transforms"]},"PathScript":{"type":"object","description":"Reference to an existing script by path. Use this when calling a previously saved script instead of writing inline code","properties":{"input_transforms":{"type":"object","description":"Map of parameter names to their values (static or JavaScript expressions). These become the script's input arguments","additionalProperties":{"$ref":"#/components/schemas/InputTransform"}},"path":{"type":"string","description":"Path to the script in the workspace (e.g., 'f/scripts/send_email')"},"hash":{"type":"string","description":"Optional specific version hash of the script to use"},"type":{"type":"string","enum":["script"]},"tag_override":{"type":"string","description":"Override the script's default worker group tag"},"is_trigger":{"type":"boolean","description":"If true, this script is a trigger that can start the flow"}},"required":["type","path","input_transforms"]},"PathFlow":{"type":"object","description":"Reference to an existing flow by path. Use this to call another flow as a subflow","properties":{"input_transforms":{"type":"object","description":"Map of parameter names to their values (static or JavaScript expressions). These become the subflow's input arguments","additionalProperties":{"$ref":"#/components/schemas/InputTransform"}},"path":{"type":"string","description":"Path to the flow in the workspace (e.g., 'f/flows/process_user')"},"type":{"type":"string","enum":["flow"]}},"required":["type","path","input_transforms"]},"ForloopFlow":{"type":"object","description":"Executes nested modules in a loop over an iterator. Inside the loop, use 'flow_input.iter.value' to access the current iteration value, and 'flow_input.iter.index' for the index. Supports parallel execution for better performance on I/O-bound operations","properties":{"modules":{"type":"array","description":"Steps to execute for each iteration. These can reference the iteration value via 'flow_input.iter.value'","items":{"$ref":"#/components/schemas/FlowModule"}},"iterator":{"description":"JavaScript expression that returns an array to iterate over. Can reference 'results.step_id' or 'flow_input'","$ref":"#/components/schemas/InputTransform"},"skip_failures":{"type":"boolean","description":"If true, iteration failures don't stop the loop. Failed iterations return null"},"type":{"type":"string","enum":["forloopflow"]},"parallel":{"type":"boolean","description":"If true, iterations run concurrently (faster for I/O-bound operations). Use with parallelism to control concurrency"},"parallelism":{"description":"Maximum number of concurrent iterations when parallel=true. Limits resource usage. Can be static number or expression","$ref":"#/components/schemas/InputTransform"},"squash":{"type":"boolean"}},"required":["modules","iterator","skip_failures","type"]},"WhileloopFlow":{"type":"object","description":"Executes nested modules repeatedly until stopped. The implicit iterator is the iteration counter, so 'flow_input.iter.value' equals 'flow_input.iter.index' (0, 1, 2, ...) and never carries state. To carry state across iterations, a step reads its own previous-iteration result via 'results.' with a first-iteration fallback - the loop's stop_after_if must then be on that inner step (a plain single-step body with stop_after_if on the loop module does not resolve 'results' across iterations and never terminates); plain counters can instead be derived from 'flow_input.iter.index', which works in every configuration. stop_after_if is evaluated after each iteration - on the loop module 'result' is the last iteration's result","properties":{"modules":{"type":"array","description":"Steps to execute in each iteration","items":{"$ref":"#/components/schemas/FlowModule"}},"skip_failures":{"type":"boolean","description":"If true, iteration failures don't stop the loop. Failed iterations return null"},"type":{"type":"string","enum":["whileloopflow"]},"parallel":{"type":"boolean","description":"If true, iterations run concurrently (use with caution in while loops)"},"parallelism":{"description":"Maximum number of concurrent iterations when parallel=true","$ref":"#/components/schemas/InputTransform"},"squash":{"type":"boolean"}},"required":["modules","skip_failures","type"]},"BranchOne":{"type":"object","description":"Conditional branching where only the first matching branch executes. Branches are evaluated in order, and the first one with a true expression runs. If no branches match, the default branch executes","properties":{"branches":{"type":"array","description":"Array of branches to evaluate in order. The first branch with expr evaluating to true executes","items":{"type":"object","properties":{"summary":{"type":"string","description":"Short description of this branch condition"},"expr":{"type":"string","description":"JavaScript expression that returns boolean. Can use 'results.step_id' or 'flow_input'. First true expr wins"},"modules":{"type":"array","description":"Steps to execute if this branch's expr is true","items":{"$ref":"#/components/schemas/FlowModule"}}},"required":["modules","expr"]}},"default":{"type":"array","description":"Steps to execute if no branch expressions match","items":{"$ref":"#/components/schemas/FlowModule"}},"type":{"type":"string","enum":["branchone"]}},"required":["branches","default","type"]},"BranchAll":{"type":"object","description":"Parallel branching where all branches execute simultaneously. Unlike BranchOne, all branches run regardless of conditions. Useful for executing independent tasks concurrently","properties":{"branches":{"type":"array","description":"Array of branches that all execute (either in parallel or sequentially)","items":{"type":"object","properties":{"summary":{"type":"string","description":"Short description of this branch's purpose"},"skip_failure":{"type":"boolean","description":"If true, failure in this branch doesn't fail the entire flow"},"modules":{"type":"array","description":"Steps to execute in this branch","items":{"$ref":"#/components/schemas/FlowModule"}}},"required":["modules"]}},"type":{"type":"string","enum":["branchall"]},"parallel":{"type":"boolean","description":"If true, all branches execute concurrently. If false, they execute sequentially"}},"required":["branches","type"]},"AgentTool":{"type":"object","description":"A tool available to an AI agent. Can be a flow module or an external MCP (Model Context Protocol) tool","properties":{"id":{"type":"string","description":"Unique identifier for this tool. Cannot contain spaces - use underscores instead (e.g., 'get_user_data' not 'get user data')"},"summary":{"type":"string","description":"The name the AI agent calls this tool by, not a human label. On a flowmodule tool it must match ^[a-zA-Z0-9_]+$ - letters, numbers and underscores only (e.g. 'search_documentation', not 'Search documentation') - and always be set; on an mcp or websearch tool it is a plain label. Put the human-readable explanation in 'description'."},"description":{"type":"string","description":"Free-text description of the tool given to the AI to decide when and how to call it. Overrides the description auto-derived from the underlying script."},"job_token_scopes":{"type":"array","nullable":true,"items":{"type":"string"},"description":"Scopes the token of this tool's jobs is restricted to, on top of the agent step's own restriction: a tool can only narrow it."},"value":{"$ref":"#/components/schemas/ToolValue"}},"required":["id","value"]},"ToolValue":{"description":"The implementation of a tool. Can be a flow module (script/flow) or an MCP tool reference","oneOf":[{"$ref":"#/components/schemas/FlowModuleTool"},{"$ref":"#/components/schemas/McpToolValue"},{"$ref":"#/components/schemas/WebsearchToolValue"}],"discriminator":{"propertyName":"tool_type","mapping":{"flowmodule":"#/components/schemas/FlowModuleTool","mcp":"#/components/schemas/McpToolValue","websearch":"#/components/schemas/WebsearchToolValue"}}},"FlowModuleTool":{"description":"A tool implemented as a flow module (script, flow, etc.). The AI can call this like any other flow module","allOf":[{"type":"object","properties":{"tool_type":{"type":"string","enum":["flowmodule"]}},"required":["tool_type"]},{"$ref":"#/components/schemas/FlowModuleValue"}]},"WebsearchToolValue":{"type":"object","description":"A tool implemented as a websearch tool. The AI can call this like any other websearch tool","properties":{"tool_type":{"type":"string","enum":["websearch"]}},"required":["tool_type"]},"McpToolValue":{"type":"object","description":"Reference to an external MCP (Model Context Protocol) tool. The AI can call tools from MCP servers","properties":{"tool_type":{"type":"string","enum":["mcp"]},"resource_path":{"type":"string","description":"Path to the MCP resource/server configuration"},"include_tools":{"type":"array","description":"Whitelist of specific tools to include from this MCP server","items":{"type":"string"}},"exclude_tools":{"type":"array","description":"Blacklist of tools to exclude from this MCP server","items":{"type":"string"}}},"required":["tool_type","resource_path"]},"AiAgent":{"type":"object","description":"AI agent step that can use tools to accomplish tasks. The agent receives inputs and can call any of its configured tools to complete the task","properties":{"input_transforms":{"type":"object","description":"Input parameters for the AI agent mapped to their values","properties":{"provider":{"$ref":"#/components/schemas/ProviderTransform"},"output_type":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"Output format type.\nValid values: 'text' (default) - plain text response, 'image' - image generation\n"},"user_message":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"The user's prompt/message to the AI agent. Supports variable interpolation with\nflow.input syntax. Required unless memory is off and `previous_messages` supplies\nthe prompt; image output always needs it.\n"},"system_prompt":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"System instructions that guide the AI's behavior, persona, and response style. Optional."},"streaming":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"Boolean. If true, stream the AI response incrementally.\nStreaming events include: token_delta, reasoning_token_delta, tool_call, tool_call_arguments, tool_execution, tool_result\n"},"memory":{"$ref":"#/components/schemas/MemoryTransform"},"memory_id":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"String. Names the memory this step reads and writes, overriding the memory id the run\nwas started with (the chat conversation, an app chat session or the `memory_id` run\nparameter). Leave unset to use the run's memory id. A fixed value shares one memory\nacross every run; an expression such as `flow_input.customer_id` keeps one memory per\nkey. When it evaluates to an empty value the agent runs without memory. Read only\nwhile `memory` is `window` or `compaction`: it is ignored when memory is off, and an\nolder `auto` or `manual` memory reads neither history input.\n"},"previous_messages":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"Array of MemoryMessage. History supplied by the flow, sent between the system prompt\nand the user message. Read only while `memory` is off or absent: managed memory\nignores it, and an older `auto` or `manual` memory reads neither history input.\n"},"output_schema":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"JSON Schema object defining structured output format. Used when you need the AI to return data in a specific shape.\nSupports standard JSON Schema properties: type, properties, required, items, enum, pattern, minLength, maxLength, minimum, maximum, etc.\nExample: { type: 'object', properties: { name: { type: 'string' }, age: { type: 'integer' } }, required: ['name'] }\n"},"user_attachments":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"Array of file references (images or PDFs) for the AI agent.\nFormat: Array<{ bucket: string, key: string }> - S3 object references\nExample: [{ bucket: 'my-bucket', key: 'documents/report.pdf' }]\n"},"enabled_tools":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"Array of strings naming which of the tools configured in `tools` the agent may call\nthis run. Leaving it unset carries every one of them; an empty array carries none.\nA tool is named as the model is shown it. An entry the model is shown nothing of is\nnamed by what identifies it instead: an MCP server by its resource path, carrying\nevery tool it exposes (which of them stays that entry's include_tools/exclude_tools),\nand a websearch entry by the reserved name '__wm_web_search', whatever summary it carries\n(no tool may take that name).\nExample: ['get_user', 'u/admin/github_mcp', '__wm_web_search']\n"},"max_completion_tokens":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"Integer. Maximum number of tokens the AI will generate in its response.\nRange: 1 to 4,294,967,295. Typical values: 256-4096 for most use cases.\n"},"temperature":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"Float. Controls randomness/creativity of responses.\nRange: 0.0 to 2.0 (provider-dependent)\n- 0.0 = deterministic, focused responses\n- 0.7 = balanced (common default)\n- 1.0+ = more creative/random\n"},"max_iterations":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"Number. Limits how many times the agent can loop through reasoning and tool use.\nRange: 1-1000.\n"}}},"tools":{"type":"array","description":"Array of tools the agent can use. The agent decides which tools to call based on the task","items":{"$ref":"#/components/schemas/AgentTool"}},"type":{"type":"string","enum":["aiagent"]},"tag":{"type":"string","description":"Worker group tag for execution routing. If not set, the AI agent step runs on the flow's tag (default `flow`)"},"omit_output_from_conversation":{"type":"boolean","default":false,"description":"If true, this AI agent step does not persist its assistant or tool messages to the flow conversation when chat mode is enabled."},"agent":{"type":"string","description":"Path of a reusable `ai_agent` resource (hybrid linking). When set, the agent brain\nconfig (provider/model/system prompt/etc.) and tool set are resolved at runtime from\nthat resource; the module's input_transforms then only carry the flow-local inputs\n(user_message, user_attachments, enabled_tools and the history inputs memory_id and previous_messages).\n"},"tool_inputs":{"type":"object","description":"Host-local wiring for an agent's tool inputs, keyed by tool id then input key. Binds the\nreferenced agent's tools to this flow's context (flow_input/results) without mutating the\nshared resource; overlaid onto the tools' input_transforms at runtime \u2014 including when\n`agent` is unset, since a step forked for editing keeps these overrides until it is saved\nback or unlinked.\n","additionalProperties":{"type":"object","additionalProperties":{"$ref":"#/components/schemas/InputTransform"}}},"parallel":{"type":"boolean","description":"If true, the agent can execute multiple tool calls in parallel"}},"required":["type","input_transforms"]},"AiDecision":{"type":"object","description":"AI decision step: one call to a decision model (TypeSafe's Jev, Cloudflare's\nJev-compatible Clef, or OpenAI's Decisions API) that answers typed questions about a\nstate with calibrated probabilities, instead of generating text.\nPrefer it over an AI agent to classify, route, score or check something: it is fast,\ncheap and its answers are structured. Its result is { output: { : answer },\nmodel, usage }, so a later step reads e.g. results..output.intent.choice. To route on\nthe answers, follow it with a branchone whose branch exprs read\nresults..output..choice. Usable as an AI agent tool, where the calling agent\nsupplies the state.\n","properties":{"input_transforms":{"type":"object","description":"Input parameters for the decision mapped to their values","properties":{"provider":{"$ref":"#/components/schemas/ProviderTransform"},"state":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"What the questions are asked about: a string, an object or an array of strings.\nAn object with descriptive keys holding only what the questions need works best.\nExample: { message: flow_input.message, plan: results.a.plan }\n"},"questions":{"allOf":[{"$ref":"#/components/schemas/InputTransform"}],"description":"Object mapping each question name to { type, instructions, criteria }, where type is:\n- 'choice': criteria maps each option to its description (up to 255); the answer\n has choice, probabilities and confidence\n- 'score': criteria is an ordered array of 2 to 10 level descriptions; the answer\n has score, legend, probabilities and confidence\n- 'noul': yes/no, criteria optionally { true, false } descriptions; the answer has\n noul, the probability of yes (0 to 1)\nExample: { intent: { type: 'choice', instructions: 'What does the customer want?',\ncriteria: { refund: 'Money back', bug: 'Something is broken' } } }\n"}},"required":["provider","state","questions"]},"type":{"type":"string","enum":["aidecision"]},"tag":{"type":"string","description":"Worker group tag for execution routing. If not set, the step runs on the flow's tag (default `flow`)"}},"required":["type","input_transforms"]},"Identity":{"type":"object","description":"Pass-through module that returns its input unchanged. Useful for flow structure or as a placeholder","properties":{"type":{"type":"string","enum":["identity"]},"flow":{"type":"boolean","description":"If true, marks this as a flow identity (special handling)"}},"required":["type"]},"FlowStatus":{"type":"object","properties":{"step":{"type":"integer"},"modules":{"type":"array","items":{"$ref":"#/components/schemas/FlowStatusModule"}},"user_states":{"additionalProperties":true},"preprocessor_module":{"allOf":[{"$ref":"#/components/schemas/FlowStatusModule"}]},"failure_module":{"allOf":[{"$ref":"#/components/schemas/FlowStatusModule"},{"type":"object","properties":{"parent_module":{"type":"string"}}}]},"retry":{"type":"object","properties":{"fail_count":{"type":"integer"},"failed_jobs":{"type":"array","items":{"type":"string","format":"uuid"}}}}},"required":["step","modules","failure_module"]},"FlowStatusModule":{"type":"object","properties":{"type":{"type":"string","enum":["WaitingForPriorSteps","WaitingForEvents","WaitingForExecutor","InProgress","Success","Failure"]},"id":{"type":"string"},"job":{"type":"string","format":"uuid"},"count":{"type":"integer"},"progress":{"type":"integer"},"iterator":{"type":"object","properties":{"index":{"type":"integer"},"itered":{"type":"array","items":{}},"itered_len":{"type":"integer"},"args":{}}},"flow_jobs":{"type":"array","items":{"type":"string"}},"flow_jobs_success":{"type":"array","items":{"type":"boolean"}},"flow_jobs_duration":{"type":"object","properties":{"started_at":{"type":"array","items":{"type":"string"}},"duration_ms":{"type":"array","items":{"type":"integer"}}}},"branch_chosen":{"type":"object","properties":{"type":{"type":"string","enum":["branch","default"]},"branch":{"type":"integer"}},"required":["type"]},"branchall":{"type":"object","properties":{"branch":{"type":"integer"},"len":{"type":"integer"}},"required":["branch","len"]},"approvers":{"type":"array","items":{"type":"object","properties":{"resume_id":{"type":"integer"},"approver":{"type":"string"}},"required":["resume_id","approver"]}},"failed_retries":{"type":"array","items":{"type":"string","format":"uuid"}},"skipped":{"type":"boolean"},"agent_actions":{"type":"array","items":{"type":"object","oneOf":[{"type":"object","properties":{"job_id":{"type":"string","format":"uuid"},"function_name":{"type":"string"},"type":{"type":"string","enum":["tool_call"]},"module_id":{"type":"string"}},"required":["job_id","function_name","type","module_id"]},{"type":"object","properties":{"call_id":{"type":"string","format":"uuid"},"function_name":{"type":"string"},"resource_path":{"type":"string"},"type":{"type":"string","enum":["mcp_tool_call"]},"arguments":{"type":"object"}},"required":["call_id","function_name","resource_path","type"]},{"type":"object","properties":{"type":{"type":"string","enum":["web_search"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["message"]}},"required":["content","type"]}]}},"agent_actions_success":{"type":"array","items":{"type":"boolean"}}},"required":["type"]}}