This commit is contained in:
lila 2026-07-06 15:21:52 +02:00
parent 1c4dcdd108
commit e89e3b7a70
6 changed files with 137 additions and 30 deletions

View file

@ -9,8 +9,9 @@ interface LlmResponse {
promptTokens: number;
completionTokens: number;
totalTokens: number;
promptTimeMs: number;
completionTimeMs: number;
promptTimeMs: number | null;
completionTimeMs: number | null;
totalTimeMs: number;
}
export interface EnrichmentResult {
@ -19,8 +20,9 @@ export interface EnrichmentResult {
promptTokens: number;
completionTokens: number;
totalTokens: number;
promptTimeMs: number;
completionTimeMs: number;
promptTimeMs: number | null;
completionTimeMs: number | null;
totalTimeMs: number;
};
}
@ -54,6 +56,60 @@ function sanitizeLlmOutput(raw: string): string {
return cleaned.slice(start, end + 1);
}
function validateSense(item: unknown, word: string, index: number): void {
if (typeof item !== "object" || item === null || Array.isArray(item)) {
throw new Error(`Sense ${index} for "${word}" is not an object`);
}
const sense = item as Record<string, unknown>;
if (typeof sense["sense"] !== "string" || !sense["sense"]) {
throw new Error(`Sense ${index} for "${word}": missing or invalid "sense"`);
}
if (typeof sense["example"] !== "string" || !sense["example"]) {
throw new Error(
`Sense ${index} for "${word}": missing or invalid "example"`,
);
}
if (
!["easy", "medium", "hard"].includes(sense["difficulty_level"] as string)
) {
throw new Error(`Sense ${index} for "${word}": invalid "difficulty_level"`);
}
if (
typeof sense["translations"] !== "object" ||
sense["translations"] === null
) {
throw new Error(`Sense ${index} for "${word}": missing "translations"`);
}
const trans = sense["translations"] as Record<string, unknown>;
for (const lang of ["de", "it", "es", "fr"]) {
if (!Array.isArray(trans[lang])) {
throw new Error(
`Sense ${index} for "${word}": missing or invalid "${lang}" translations`,
);
}
for (let j = 0; j < (trans[lang] as unknown[]).length; j++) {
const t = (trans[lang] as unknown[])[j] as Record<string, unknown>;
if (typeof t["word"] !== "string" || !t["word"]) {
throw new Error(
`Sense ${index} for "${word}": ${lang}[${j}] missing "word"`,
);
}
if (
!["masculine", "feminine", "neuter", null].includes(
t["gender"] as string | null,
)
) {
throw new Error(
`Sense ${index} for "${word}": ${lang}[${j}] invalid "gender"`,
);
}
}
}
}
/**
* Parses the LLM response string into a JavaScript object.
* Throws if the response is not valid JSON or not an object with expected keys.
@ -86,6 +142,12 @@ export function parseLlmResponse(
if (!Array.isArray(obj[word]) || (obj[word] as unknown[]).length === 0) {
throw new Error(`LLM output for "${word}" is not a non-empty array`);
}
// Validate each sense in the array
const senses = obj[word] as unknown[];
for (let i = 0; i < senses.length; i++) {
validateSense(senses[i], word, i);
}
}
return obj;
@ -145,6 +207,7 @@ export async function enrichWord(
totalTokens: llmResponse.totalTokens,
promptTimeMs: llmResponse.promptTimeMs,
completionTimeMs: llmResponse.completionTimeMs,
totalTimeMs: llmResponse.totalTimeMs,
},
};
}
@ -207,10 +270,13 @@ export async function enrichWordWithRetry(
totalTokens:
leftResult.metrics.totalTokens + rightResult.metrics.totalTokens,
promptTimeMs:
leftResult.metrics.promptTimeMs + rightResult.metrics.promptTimeMs,
(leftResult.metrics.promptTimeMs ?? 0) +
(rightResult.metrics.promptTimeMs ?? 0),
completionTimeMs:
leftResult.metrics.completionTimeMs +
rightResult.metrics.completionTimeMs,
(leftResult.metrics.completionTimeMs ?? 0) +
(rightResult.metrics.completionTimeMs ?? 0),
totalTimeMs:
leftResult.metrics.totalTimeMs + rightResult.metrics.totalTimeMs,
};
return { results: merged, metrics: mergedMetrics };