FlowSettings
Properties
Section titled “Properties”allowAgentToolLoop
Section titled “allowAgentToolLoop”allowAgentToolLoop:
boolean
Org-level master switch for the in-node AI tool loop (an ai node calling
bound adapters mid-inference). When off, every tool-loop node fails at run
time regardless of its own allowToolLoop. Defaults true.
allowAutonomousRun
Section titled “allowAutonomousRun”allowAutonomousRun:
boolean
Org-level master switch for autonomous runs (auto-accept + re-run the monitor’s fixes without a human gate). When off, an autonomous request is refused / downgraded to manual review. Defaults true.
allowCloudAi
Section titled “allowCloudAi”allowCloudAi:
boolean
allowLocalAi
Section titled “allowLocalAi”allowLocalAi:
boolean
Gate for the local OpenAI-compatible provider (on-device server). Independent of allowCloudAi because a localhost call isn’t egress.
confirmDestructive
Section titled “confirmDestructive”confirmDestructive:
boolean
Per-step destructive-action confirmation gate. When on, a run pauses before any node that performs a destructive operation and asks the user to confirm or cancel. Defaults to true.
hubUrl?
Section titled “hubUrl?”
optionalhubUrl?:string
Base URL of the Flow Hub service (registries + template publishing). Empty/absent = offline mode (embedded catalogs only).
llamaParams?
Section titled “llamaParams?”
optionalllamaParams?:Record<string,LlamaParams>
Per-model llama-server load settings, keyed by catalog model id.
llamaServerBinary?
Section titled “llamaServerBinary?”
optionalllamaServerBinary?:string
Path to the llama-server binary flow-studio launches to host an LLM.
llamaServerModel?
Section titled “llamaServerModel?”
optionalllamaServerModel?:string
Path to the LLM the managed server loads.
localAiBaseUrl?
Section titled “localAiBaseUrl?”
optionallocalAiBaseUrl?:string
Base address of the local server, stored as an origin (e.g. http://127.0.0.1:1234). The runtime appends /v1/chat/completions and /v1/models. A full URL is also accepted and normalised.
localAiModels?
Section titled “localAiModels?”
optionallocalAiModels?:string[]
Model ids discovered from the local server’s /v1/models, cached so the node inspector dropdown can offer them. Populated by Test connection.
maxAgenticIterations
Section titled “maxAgenticIterations”maxAgenticIterations:
number
Safety cap on auto-accepted fixes in one autonomous run; one budget shared by the backend convergence loop and the frontend monitor auto-fix loop.
maxAgenticSeconds
Section titled “maxAgenticSeconds”maxAgenticSeconds:
number
Wall-clock ceiling (seconds) for one autonomous convergence run; 0 = unlimited (autonomous run budgets).
maxAgenticTokens
Section titled “maxAgenticTokens”maxAgenticTokens:
number
Cumulative token ceiling (the executed flows’ AI nodes) for one autonomous convergence run; 0 = unlimited.
piiRules
Section titled “piiRules”piiRules:
CustomPiiRule[]
Admin-authored PII redaction rules layered on the built-in sanitizer. Applied to every AI-node input before inference.
providersEnabled
Section titled “providersEnabled”providersEnabled:
Record<string,boolean>
sandboxLocalLlm
Section titled “sandboxLocalLlm”sandboxLocalLlm:
boolean
OS-level isolation for the managed reasoning server. When on (macOS), llama-server runs under a sandbox-exec profile so loopback-only is enforced by the OS. Off by default.
schedulerEnabled
Section titled “schedulerEnabled”schedulerEnabled:
boolean
Master switch for background scheduled runs.
schedulerPollSecs
Section titled “schedulerPollSecs”schedulerPollSecs:
number
Poll interval in seconds for background scheduler loops.
theme:
UiTheme