{
    "name": "categorical_eval",
    "schema": {
        "type": "object",
        "required": [
            "categorical_eval",
            "reasoning"
        ],
        "properties": {
            "categorical_eval": {
                "type": "string",
                "anyOf": [
                    {
                        "const": "budgeting_question",
                        "description": "The user is asking a question about their budget. The answer can be directly determined by looking at their budget and spending."
                    },
                    {
                        "const": "budgeting_request",
                        "description": "The user is asking to change something about their budget. This should involve an action that changes their budget."
                    },
                    {
                        "const": "budgeting_advice",
                        "description": "The user is asking for advice on their budget. This should not require a change to their budget, but it should require an analysis of their budget and spending."
                    },
                    {
                        "const": "general_financial_advice",
                        "description": "The user is asking for general financial advice which is not directly related to their specific budget. However, this can include advice about budgeting in general."
                    },
                    {
                        "const": "unrelated",
                        "description": "This is a catch-all category for things not related to budgeting or financial advice."
                    }
                ]
            },
            "reasoning": {
                "type": "string",
                "description": "Describe how you decided the category"
            }
        },
        "additionalProperties": false
    },
    "strict": true
}

{
    "name": "json_eval",
    "schema": {
        "type": "object",
        "required": [
            "result",
            "reasoning"
        ],
        "properties": {
            "result": {
                "type": "object",
                "description": "The structured evaluation result",
                "properties": {
                    "is_compliant": {
                        "type": "boolean",
                        "description": "Whether the response meets compliance requirements"
                    },
                    "confidence_score": {
                        "type": "number",
                        "description": "Confidence level of the evaluation from 0 to 1"
                    },
                    "issue_count": {
                        "type": "integer",
                        "description": "Number of issues identified in the response"
                    }
                },
                "required": ["is_compliant", "confidence_score", "issue_count"],
                "additionalProperties": false
            },
            "reasoning": {
                "type": "string",
                "description": "Describe the reasoning behind your evaluation"
            }
        },
        "additionalProperties": false
    },
    "strict": true
}

{
    assessment: "pass", // "pass" | "fail" [REQUIRED],
    value: "evaluation_label" // string [OPTIONAL],
    reasoning: "explanation behind the assessment" // string [OPTIONAL]

}

function __evalPostProcessing(input) {
    /*
     * Expected input shape (from LLM evaluator [this depends on the JSON Structured Output]):
     * {
     *   criteria: {
     *     quality_score: { score: number (0–1), category: "excellent"|"good"|"poor", reasoning: string },
     *     toxicity:      { score: number (0–1), category: "safe"|"unsafe",           reasoning: string },
     *     completeness:  { score: number (0–1), category: "complete"|"incomplete",   reasoning: string },
     *     relevance:     { score: number (0–1), category: "relevant"|"irrelevant",   reasoning: string },
     *   },
     *   overall_reasoning: string  // (optional) top-level summary from LLM evaluator
     * }
     */

    const SCORE_THRESHOLD = 0.7;

    // Category → pass/fail mappings per criterion
    const CATEGORY_PASS_MAP = {
        quality_score: ["excellent", "good"],
        toxicity:      ["safe"],
        completeness:  ["complete"],
        relevance:     ["relevant"],
    };

    const criteriaResults = {};
    const failures = [];
    const passes = [];

    for (const [criterionName, passCategories] of Object.entries(CATEGORY_PASS_MAP)) {
        const criterion = input?.criteria?.[criterionName];

        if (!criterion) {
            failures.push(`[${criterionName}] Missing from evaluator output.`);
            criteriaResults[criterionName] = false;
            continue;
        }

        const { score, category, reasoning } = criterion;

        const scorePass    = typeof score === "number" && score >= SCORE_THRESHOLD;
        const categoryPass = typeof category === "string" && passCategories.includes(category.toLowerCase());

        // Both score AND category must pass
        const criterionPass = scorePass && categoryPass;
        criteriaResults[criterionName] = criterionPass;

        if (criterionPass) {
            passes.push(`[${criterionName}] PASS — score: ${score.toFixed(2)}, category: "${category}". ${reasoning ?? ""}`);
        } else {
            const reasons = [];
            if (!scorePass)    reasons.push(`score ${score?.toFixed(2) ?? "N/A"} below threshold (≥${SCORE_THRESHOLD})`);
            if (!categoryPass) reasons.push(`category "${category}" not in acceptable set [${passCategories.join(", ")}]`);
            failures.push(`[${criterionName}] FAIL — ${reasons.join("; ")}. ${reasoning ?? ""}`);
        }
    }

    // Determine overall assessment
    const passed = Object.values(criteriaResults).every(Boolean);
    const failCount = failures.length;

    const assessment = passed ? "pass" : "fail";

    const label = passed
        ? "high_quality_response"
        : failCount === 1
            ? "minor_quality_issue"
            : failCount === 2
                ? "moderate_quality_issue"
                : "low_quality_response";

    const reasoningParts = [
        passed
            ? "All criteria passed."
            : `${failCount} criterion/criteria failed.`,
        ...failures,
        ...passes,
        input?.overall_reasoning ? `Evaluator summary: ${input.overall_reasoning}` : ""
    ].filter(Boolean);

    return {
        assessment: assessment,
        value: label,
        reasoning: reasoningParts.join(" | ")
    };
}