bugfixing #3

data-pipeline/pipeline.ts

@@ -118,6 +118,7 @@ async function main() {
             totalTokens: result.metrics.totalTokens,
             promptTimeMs: result.metrics.promptTimeMs,
             completionTimeMs: result.metrics.completionTimeMs,
+            totalTimeMs: result.metrics.totalTimeMs,
           });
         }
 

data-pipeline/utils/enrich-word.ts

@@ -9,8 +9,9 @@ interface LlmResponse {
   promptTokens: number;
   completionTokens: number;
   totalTokens: number;
-  promptTimeMs: number;
+  promptTimeMs: number | null;
-  completionTimeMs: number;
+  completionTimeMs: number | null;
+  totalTimeMs: number;
 }
 
 export interface EnrichmentResult {
@@ -19,8 +20,9 @@ export interface EnrichmentResult {
     promptTokens: number;
     completionTokens: number;
     totalTokens: number;
-    promptTimeMs: number;
+    promptTimeMs: number | null;
-    completionTimeMs: number;
+    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 +
+        (leftResult.metrics.completionTimeMs ?? 0) +
-        rightResult.metrics.completionTimeMs,
+        (rightResult.metrics.completionTimeMs ?? 0),
+      totalTimeMs:
+        leftResult.metrics.totalTimeMs + rightResult.metrics.totalTimeMs,
     };
 
     return { results: merged, metrics: mergedMetrics };

data-pipeline/utils/llm-adapters/gemini.ts

@@ -26,8 +26,9 @@ export class GeminiAdapter implements LlmAdapter {
     promptTokens: number;
     completionTokens: number;
     totalTokens: number;
-    promptTimeMs: number;
+    promptTimeMs: number | null;
-    completionTimeMs: number;
+    completionTimeMs: number | null;
+    totalTimeMs: number;
   }> {
     const url = `https://generativelanguage.googleapis.com/v1beta/models/${this.model}:generateContent?key=${this.apiKey}`;
 
@@ -72,8 +73,9 @@ export class GeminiAdapter implements LlmAdapter {
       promptTokens,
       completionTokens,
       totalTokens: json.usageMetadata.totalTokenCount,
-      promptTimeMs: totalTimeMs * 0.3,
+      promptTimeMs: null,
-      completionTimeMs: totalTimeMs * 0.7,
+      completionTimeMs: null,
+      totalTimeMs,
     };
   }
 }

data-pipeline/utils/llm-adapters/openai-compatible.ts

@@ -29,8 +29,9 @@ export class OpenAiCompatibleAdapter implements LlmAdapter {
     promptTokens: number;
     completionTokens: number;
     totalTokens: number;
-    promptTimeMs: number;
+    promptTimeMs: number | null;
-    completionTimeMs: number;
+    completionTimeMs: number | null;
+    totalTimeMs: number;
   }> {
     const payload: Record<string, unknown> = {
       messages: [
@@ -78,16 +79,14 @@ export class OpenAiCompatibleAdapter implements LlmAdapter {
     const promptTokens = json.usage.prompt_tokens;
     const completionTokens = json.usage.completion_tokens;
 
-    const promptTimeMs = json.timings?.prompt_ms ?? totalTimeMs * 0.3;
-    const completionTimeMs = json.timings?.predicted_ms ?? totalTimeMs * 0.7;
-
     return {
       content,
       promptTokens,
       completionTokens,
       totalTokens: json.usage.total_tokens,
-      promptTimeMs,
+      promptTimeMs: json.timings?.prompt_ms ?? null,
-      completionTimeMs,
+      completionTimeMs: json.timings?.predicted_ms ?? null,
+      totalTimeMs,
     };
   }
 }

data-pipeline/utils/llm-adapters/types.ts

@@ -7,7 +7,8 @@ export interface LlmAdapter {
     promptTokens: number;
     completionTokens: number;
     totalTokens: number;
-    promptTimeMs: number;
+    promptTimeMs: number | null;
-    completionTimeMs: number;
+    completionTimeMs: number | null;
+    totalTimeMs: number;
   }>;
 }

data-pipeline/utils/pipeline-timer.ts

@@ -2,8 +2,9 @@ interface LlmMetrics {
   promptTokens: number;
   completionTokens: number;
   totalTokens: number;
-  promptTimeMs: number;
+  promptTimeMs: number | null;
-  completionTimeMs: number;
+  completionTimeMs: number | null;
+  totalTimeMs: number;
 }
 
 interface PipelineMetrics {
@@ -18,6 +19,7 @@ interface PipelineMetrics {
   totalTokens: number;
   totalPromptTimeMs: number;
   totalCompletionTimeMs: number;
+  totalTimeMs: number;
   currentWordStartTime?: Date;
 }
 
@@ -40,6 +42,7 @@ export class PipelineTimer {
       totalTokens: 0,
       totalPromptTimeMs: 0,
       totalCompletionTimeMs: 0,
+      totalTimeMs: 0,
     };
   }
 
@@ -59,9 +62,14 @@ export class PipelineTimer {
       this.metrics.totalPromptTokens += llmMetrics.promptTokens;
       this.metrics.totalCompletionTokens += llmMetrics.completionTokens;
       this.metrics.totalTokens += llmMetrics.totalTokens;
+      if (llmMetrics.promptTimeMs !== null) {
         this.metrics.totalPromptTimeMs += llmMetrics.promptTimeMs;
+      }
+      if (llmMetrics.completionTimeMs !== null) {
         this.metrics.totalCompletionTimeMs += llmMetrics.completionTimeMs;
       }
+      this.metrics.totalTimeMs += llmMetrics.totalTimeMs;
+    }
   }
 
   recordSkipped(): void {
@@ -125,22 +133,40 @@ export class PipelineTimer {
             0,
           )
         : "0";
+    const avgTotalTimeMs =
+      this.metrics.llmCalls > 0
+        ? (this.metrics.totalTimeMs / this.metrics.llmCalls).toFixed(0)
+        : "0";
+
+    const unifiedThroughput =
+      this.metrics.totalTimeMs > 0
+        ? (
+            this.metrics.totalTokens /
+            (this.metrics.totalTimeMs / 1000)
+          ).toFixed(1)
+        : "N/A";
+
+    const hasDetailedTimings =
+      this.metrics.totalPromptTimeMs > 0 ||
+      this.metrics.totalCompletionTimeMs > 0;
+
     const avgPromptSpeed =
       this.metrics.totalPromptTimeMs > 0
         ? (
             this.metrics.totalPromptTokens /
             (this.metrics.totalPromptTimeMs / 1000)
           ).toFixed(1)
-        : "0";
+        : "N/A";
+
     const avgCompletionSpeed =
       this.metrics.totalCompletionTimeMs > 0
         ? (
             this.metrics.totalCompletionTokens /
             (this.metrics.totalCompletionTimeMs / 1000)
           ).toFixed(1)
-        : "0";
+        : "N/A";
 
-    return [
+    const lines = [
       `⏱️  Pipeline Summary`,
       `   Duration: ${durationSec}s`,
       `   Processed: ${this.metrics.wordsProcessed}`,
@@ -153,8 +179,20 @@ export class PipelineTimer {
       `   Calls: ${this.metrics.llmCalls}`,
       `   Avg prompt tokens: ${avgPromptTokens}`,
       `   Avg completion tokens: ${avgCompletionTokens}`,
+      `   Avg total tokens: ${avgPromptTokens + avgCompletionTokens}`,
+      `   Avg total request time: ${avgTotalTimeMs}ms`,
+      `   Avg throughput: ${unifiedThroughput} tok/s`,
+    ];
+
+    if (hasDetailedTimings) {
+      lines.push(
+        ``,
+        `   [Local breakdown]`,
         `   Avg prompt speed: ${avgPromptSpeed} tok/s`,
         `   Avg completion speed: ${avgCompletionSpeed} tok/s`,
-    ].join("\n");
+      );
+    }
+
+    return lines.join("\n");
   }
 }