Files
windmill/openflow.openapi.yaml
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

968 lines
32 KiB
YAML

openapi: "3.0.3"
info:
version: 1.589.3
title: OpenFlow Spec
contact:
name: Ruben Fiszel
email: ruben@windmill.dev
url: https://windmill.dev
license:
name: Apache 2.0
url: https://www.apache.org/licenses/LICENSE-2.0.html
paths: {}
externalDocs:
description: documentation portal
url: https://windmill.dev
components:
schemas:
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-<type>' (e.g., 'resource-stripe')
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
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: number
description: Delay in seconds to debounce flow executions
debounce_key:
type: string
description: Expression to group debounced executions
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
flow_env:
type: object
description: Environment variables available to all steps
additionalProperties:
type: string
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"
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 (delay doubles each time)
properties:
attempts:
type: integer
description: Number of retry attempts
multiplier:
type: integer
description: Multiplier for exponential backoff
seconds:
type: integer
minimum: 1
description: Initial delay in seconds
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 (e.g., "yellow", "#ffff00")
type:
type: string
enum: [free, group]
description: Type of note - 'free' for standalone notes, 'group' for notes that group other nodes
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
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
description: Custom error message shown when stopping
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.<step_id>'
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_use:
type: boolean
description: If true, this step's result is deleted after use to save memory
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
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
retry:
description: Retry configuration if this step fails
$ref: "#/components/schemas/Retry"
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"
- $ref: "#/components/schemas/JavascriptTransform"
discriminator:
propertyName: type
mapping:
static: "#/components/schemas/StaticTransform"
javascript: "#/components/schemas/JavascriptTransform"
StaticTransform:
type: object
description: Static value passed directly to the step. Use for hardcoded values or resource references like '$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 loops, use 'flow_input.iter.value' for the current iteration value
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
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"
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"
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:
# to be made required once migration is over
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
- python3
- go
- bash
- powershell
- postgresql
- mysql
- bigquery
- snowflake
- mssql
- oracledb
- graphql
- nativets
- php
# TODO: Add missing languages
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
access_type:
type: string
description: Access level for this asset
enum: [r, w, rw]
alt_access_type:
type: string
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 while a condition is true. The loop checks the condition after each iteration. Use stop_after_if on modules to control loop termination
properties:
modules:
type: array
description: Steps to execute in each iteration. Use stop_after_if to control when the loop ends
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: Short description of what this tool does (shown to the AI)
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"
discriminator:
propertyName: tool_type
mapping:
flowmodule: "#/components/schemas/FlowModuleTool"
mcp: "#/components/schemas/McpToolValue"
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"
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/InputTransform"
output_type:
$ref: "#/components/schemas/InputTransform"
user_message:
$ref: "#/components/schemas/InputTransform"
system_prompt:
$ref: "#/components/schemas/InputTransform"
streaming:
$ref: "#/components/schemas/InputTransform"
messages_context_length:
$ref: "#/components/schemas/InputTransform"
output_schema:
$ref: "#/components/schemas/InputTransform"
user_images:
$ref: "#/components/schemas/InputTransform"
max_completion_tokens:
$ref: "#/components/schemas/InputTransform"
temperature:
$ref: "#/components/schemas/InputTransform"
required:
- provider
- user_message
- output_type
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
parallel:
type: boolean
description: If true, the agent can execute multiple tool calls in parallel
required:
- tools
- 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: {}
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: [message]
required:
- content
- type
agent_actions_success:
type: array
items:
type: boolean
required: [type]