OptionalActivationReuse policy (D7). KeyFields name the row fields whose values form the dedup key; omit for whole-rendered-context keying. Scope defaults to this pipeline so a shared dictionary is opt-in and readable.
OptionalCaptureCapture the model's rationale into the history row's Reasoning column (D20).
How prompt context is built for each row. Exactly one Source is required.
OptionalEntityDocumentID?: stringRender an Entity Document (supports ${Relationship(...)} and __Parent chaining).
OptionalFields?: string[]Simplest form: project these fields. Default when nothing else is set.
OptionalInputMapping?: Record<string, string>Optional value remap layered on whatever the above produced.
OptionalQueryID?: stringRun an APPROVED MJ: Query, parameterized from the row. The reach a relationship walk cannot give.
OptionalQueryParams?: Record<string, string>Parameter name -> row-field ref, for QueryID.
OptionalRecordAsUserMessage?: booleanOpt-in, LLM pipelines with Fields only: send the Fields values as one JSON user message, the template as the
system message, so a value holding an instruction stays data.
OptionalEscalationDecision pipelines only: re-run records the decision model is unsure of through an LLM pipeline.
A record escalates when ANY of its outputs' confidence is below this (0 < floor < 1).
The MJ: Record Processes ID of the LLM Feature Pipeline to escalate to.
One or more outputs produced per row.
OptionalPipelineThe name of an MJ: Feature Pipeline Types row. Absent means LLM.
OptionalProcessorOptional subclass hook registration (P1-6).
The prompt. User-visible and user-editable (D11).
OptionalUnattendedUnattended version-change handling (default: both on).
OptionalWatermarkSkip rows whose watermark says nothing they depend on has changed (P1-7).
When set, the pipeline is gated on a stored golden-set result.