jevrecipes

Recipe catalog / report-facets

Label the facets of a progress report

Which of these does report include: an outcome statement, supporting evidence, blockers, a next step, open questions?

You need to check an agent progress report for the parts a supervisor expects before accepting it, routing it, or asking the agent to fill in what is missing.

Explore this recipe interactively ยท Source and implementation guide

Use report-facets in TypeScript

Install with npm install jev-recipes. Requires Node.js 22.9 or newer and ES modules. Set TYPESAFE_API_KEY in your server environment for live calls, which send input to TypeSafe and use API quota. See the installation guide.

import { reportFacets } from 'jev-recipes/report-facets';

const result = await reportFacets({
  "report": "Migrated 4 of the 6 legacy endpoints to the new router; all 38 tests in tests/api pass (run log attached). The remaining two endpoints depend on the auth middleware rewrite, which is still blocked on the token format decision from the platform team. Next I will stub the middleware so the last two endpoints can be migrated behind a feature flag.",
  "minConfidence": 0.8
});
console.log(result);

Input contract

FieldTypeNeeded
reportstringRequired
minConfidencenumberOptional
Full input and result schemas
{
  "input": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "report": {
        "type": "string"
      },
      "minConfidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      }
    },
    "required": [
      "report"
    ]
  },
  "result": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "model": {
        "type": "string"
      },
      "usage": {
        "type": "object",
        "properties": {
          "input_tokens": {
            "type": "integer",
            "minimum": 0,
            "maximum": 9007199254740991
          },
          "output_tokens": {
            "type": "integer",
            "minimum": 0,
            "maximum": 9007199254740991
          }
        },
        "required": [
          "input_tokens",
          "output_tokens"
        ],
        "additionalProperties": false
      },
      "status": {
        "type": "string",
        "enum": [
          "ready",
          "review"
        ]
      },
      "detected": {
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "statesOutcome",
            "providesEvidence",
            "statesBlockers",
            "statesNextStep",
            "raisesQuestions"
          ]
        }
      },
      "labels": {
        "type": "object",
        "properties": {
          "statesOutcome": {
            "type": "object",
            "properties": {
              "status": {
                "type": "string",
                "enum": [
                  "ready",
                  "review"
                ]
              },
              "verdict": {
                "type": "string",
                "enum": [
                  "present",
                  "absent"
                ]
              },
              "probability": {
                "type": "number",
                "minimum": 0,
                "maximum": 1
              },
              "confidence": {
                "type": "number",
                "minimum": 0,
                "maximum": 1
              }
            },
            "required": [
              "status",
              "verdict",
              "probability",
              "confidence"
            ],
            "additionalProperties": false
          },
          "providesEvidence": {
            "type": "object",
            "properties": {
              "status": {
                "type": "string",
                "enum": [
                  "ready",
                  "review"
                ]
              },
              "verdict": {
                "type": "string",
                "enum": [
                  "present",
                  "absent"
                ]
              },
              "probability": {
                "type": "number",
                "minimum": 0,
                "maximum": 1
              },
              "confidence": {
                "type": "number",
                "minimum": 0,
                "maximum": 1
              }
            },
            "required": [
              "status",
              "verdict",
              "probability",
              "confidence"
            ],
            "additionalProperties": false
          },
          "statesBlockers": {
            "type": "object",
            "properties": {
              "status": {
                "type": "string",
                "enum": [
                  "ready",
                  "review"
                ]
              },
              "verdict": {
                "type": "string",
                "enum": [
                  "present",
                  "absent"
                ]
              },
              "probability": {
                "type": "number",
                "minimum": 0,
                "maximum": 1
              },
              "confidence": {
                "type": "number",
                "minimum": 0,
                "maximum": 1
              }
            },
            "required": [
              "status",
              "verdict",
              "probability",
              "confidence"
            ],
            "additionalProperties": false
          },
          "statesNextStep": {
            "type": "object",
            "properties": {
              "status": {
                "type": "string",
                "enum": [
                  "ready",
                  "review"
                ]
              },
              "verdict": {
                "type": "string",
                "enum": [
                  "present",
                  "absent"
                ]
              },
              "probability": {
                "type": "number",
                "minimum": 0,
                "maximum": 1
              },
              "confidence": {
                "type": "number",
                "minimum": 0,
                "maximum": 1
              }
            },
            "required": [
              "status",
              "verdict",
              "probability",
              "confidence"
            ],
            "additionalProperties": false
          },
          "raisesQuestions": {
            "type": "object",
            "properties": {
              "status": {
                "type": "string",
                "enum": [
                  "ready",
                  "review"
                ]
              },
              "verdict": {
                "type": "string",
                "enum": [
                  "present",
                  "absent"
                ]
              },
              "probability": {
                "type": "number",
                "minimum": 0,
                "maximum": 1
              },
              "confidence": {
                "type": "number",
                "minimum": 0,
                "maximum": 1
              }
            },
            "required": [
              "status",
              "verdict",
              "probability",
              "confidence"
            ],
            "additionalProperties": false
          }
        },
        "required": [
          "statesOutcome",
          "providesEvidence",
          "statesBlockers",
          "statesNextStep",
          "raisesQuestions"
        ],
        "additionalProperties": false
      }
    },
    "required": [
      "model",
      "usage",
      "status",
      "detected",
      "labels"
    ],
    "additionalProperties": false
  }
}

Saved example result

This hand-authored response demonstrates the contract. It is not a model accuracy measurement. Run it without an API key: npx jev-recipes demo report-facets.

{
  "model": "demo-fixture",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0
  },
  "status": "ready",
  "detected": [
    "statesOutcome",
    "providesEvidence",
    "statesBlockers",
    "statesNextStep"
  ],
  "labels": {
    "statesOutcome": {
      "status": "ready",
      "verdict": "present",
      "probability": 0.95,
      "confidence": 0.95
    },
    "providesEvidence": {
      "status": "ready",
      "verdict": "present",
      "probability": 0.88,
      "confidence": 0.88
    },
    "statesBlockers": {
      "status": "ready",
      "verdict": "present",
      "probability": 0.91,
      "confidence": 0.91
    },
    "statesNextStep": {
      "status": "ready",
      "verdict": "present",
      "probability": 0.93,
      "confidence": 0.93
    },
    "raisesQuestions": {
      "status": "ready",
      "verdict": "absent",
      "probability": 0.12,
      "confidence": 0.88
    }
  }
}

Evaluation evidence

Fixture only

No verified live accuracy measurement is available. Evaluate representative cases before using this decision in your workflow.

Use the evaluation guide to measure this decision on your own labeled cases.

Limitations

Related recipes