Hive Civilization · OpenAPI Overlay 1.0.0

API Evangelist conversational phrasing for Thehiveryiq Com Smsh Learned API

3 actions 3 updates phrasing extends openapi/thehiveryiq-com-smsh-learned-api-openapi.yml
Generated by API Evangelist Written by API Evangelist tooling for Hive Civilization's API. It is a proposal applied on top of the contract, not a document Hive Civilization publishes.
View Overlay File View on GitHub Overlay Specification

What the actions change

x-apievangelist-phrasing

Targets 3

$.info
$.paths['/v1/smsh/judge'].post
$.paths['/v1/smsh/learned_prune'].post

OpenAPI Overlay

Raw ↑ 
# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
  title: API Evangelist conversational phrasing for Thehiveryiq Com Smsh Learned API
  version: 1.0.0
extends: openapi/thehiveryiq-com-smsh-learned-api-openapi.yml
actions:
- target: $.info
  update:
    x-apievangelist-phrasing:
      method: generated
      generated: '2026-09-26'
      generator: build-phrasing.py
      label: Generated by API Evangelist
      operations: 2
- target: $.paths['/v1/smsh/judge'].post
  update:
    x-apievangelist-phrasing:
      intent: Score how important each span of text is
      effect: read
      questions:
      - Which parts of my prompt matter most to the downstream answer?
      - Can I choose the judge model and number of spans scored?
      instructions:
      - text: Score span importance in "{text}".
        slots:
          text: requestBody.text
      - text: Split {text} into at most {max_spans} spans and score each with {model}.
        slots:
          text: requestBody.text
          max_spans: requestBody.max_spans
          model: requestBody.model
      method: generated
      generated: '2026-09-26'
- target: $.paths['/v1/smsh/learned_prune'].post
  update:
    x-apievangelist-phrasing:
      intent: Compress text by pruning low-importance spans
      effect: read
      questions:
      - How can I shrink a long prompt by dropping its least important spans?
      - Can I set a target compression ratio for pruning?
      instructions:
      - text: Prune "{text}" down to compression ratio {target_ratio}.
        slots:
          text: requestBody.text
          target_ratio: requestBody.target_ratio
      - text: Compress {text}, keeping spans above importance {importance_floor}.
        slots:
          text: requestBody.text
          importance_floor: requestBody.importance_floor
      method: generated
      generated: '2026-09-26'