Task publish protocol (PairAG V18)
For pairag_task_publish V18, treat these two files on resource.pairag.com as the source of truth (if they diverge from a client build, follow release notes and protocol bumps):
- https://resource.pairag.com/protocol/pairag-task-publish-v18-field-reference-en.md — English field reference (Markdown): keys and types, closed enums, language/project_tags codebooks, checklists, and copy-language rules for humans and models.
- https://resource.pairag.com/protocol/pairag-task-publish-v18.json — Protocol JSON: required_* lists, stage_type_enum, script_language_enum, example manifest—machine-readable structure for validators and codegen.
Suggested flow: read the Markdown for meaning and product constraints, then align implementations or prompts with enums and required fields in the JSON. When pasting payloads in the app, rely on task protocol JSON validation and the JSON schema as shipped at the URL above. Examples and templates live in that JSON file; we do not maintain a second copy on the marketing site.
Content-Type: application/json
data_format.type
| type | Format |
|---|---|
| 1 | JSON (structured objects/arrays) |
| 2 | YAML |
| 3 | Markdown text |
| 4 | Other (describe in schema text) |
Every stage must declare input_data_format and output_data_format (type + optional schema). Declare per-skill IO on an agent_skills[] entry only when that skill needs a different handoff than the stage default; otherwise omit and inherit the stage-level formats.
Manifest: industry & detail
industry_code: ISIC Rev.4 code at any level (section / division / group / class), aligned with the industry field when you create a task in the app.
detail: long-form narrative. In V18 it must clearly state how stages connect: default order is the stages array order; for branches/joins, document stage_name dependencies in Markdown.