the language
max_tokens
per-call output token cap. One of 59 words the served contract declares, projected from workflow.schema.json, the same file your editor validates against.
- 1surfaceinfer
- optionaleverywherea choice, never a miss
- integer | stringtypethe declared shape
- 3skeletonscarry this key
the contract
1 declarationDescriptions are the schema's own; the deeper invariants (value languages and regexes) ride the same projection. A miss is a nika check finding before anything runs.
- infer
integer | stringper-call output token capinside infer:
in a real file
from the website-brief skeletonwebsite-brief.nika.yaml
brief: with: crawl_site: ${{ tasks.crawl_site.output }} infer: max_tokens: 1200 prompt: | # SLOT: the one model job · what should the brief capture? From this site crawl, produce a creative brief: the domain of activity, the dominant visual theme, the audience, the usable colors and image assets. Crawl digest · ${{ with.crawl_site }} schema: # SLOT: the typed shape downstream tasks rely on type: object additionalProperties: false properties: domain: { type: string } theme: { type: string } audience: { type: string } colors: { type: array, items: { type: string } } assets: { type: array, items: { type: string } } required: [domain, theme, audience, colors, assets]a verbatim slice, real line numbers from website-brief.nika.yaml, conformance-gated upstream on every spec push. open the full skeleton →
cross-references
skeletons that carry it
accepted by
defined by
The whole grammar in one place: the four verbs · the standard library · the spec. Try it in the playground. Read the reference →