Skip to content

JSON output and preferred_next_label #1

Description

@btomaj

I'm trying to make sense of Attractor. There are two questions that have confounded me.

  1. Are you expecting the JSON to be part of Outcome, Outcome.context_updates, or stored in response.md?

    attractor-c/spec-dod.dot

    Lines 29 to 40 in 144e201

    Output a JSON object:
    {
    \"spec\": \"unified-llm\",
    \"sections\": {
    \"8.1\": { \"title\": \"Core Infrastructure\", \"items\": [ {\"text\": \"...\", \"pass\": true/false, \"reason\": \"...\"} ] },
    ...
    },
    \"total\": N,
    \"passed\": M,
    \"failed\": K,
    \"failed_items\": [ {\"section\": \"8.2\", \"text\": \"...\", \"reason\": \"...\"} ]
    }

  2. Are you expecting preferred_next_label to be set as part of the JSON, or am I misunderstanding some mechanism whereby Outcome.preferred_label is set?

    attractor-c/spec-dod.dot

    Lines 112 to 113 in 144e201

    If total_failing == 0 or verdict == \"only_deferred\", set preferred_next_label to \"Done\".
    Otherwise set preferred_next_label to \"Fix\"."

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions