feat(costs): Filler-Übersetzung + OpenRouter-TTS kostenerfasst

- fillers.py translate_pool: usage:{include:true} + Ist-Kosten (Kategorie llm).
- OpenRouter-TTS: geschaetzte Kosten (Zeichen × openrouter_tts_usd_per_char,
  Kategorie tts) — der Audio-Endpunkt liefert keine inline-usage. Preis (Default
  ~$15/1M Zeichen) live-setzbar; an Modellpreis anpassbar.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

app/pipeline/fillers.py

@@ -17,6 +17,8 @@ import re
 
 import httpx
 
+from app.core.costs import record_openrouter_cost
+
 logger = logging.getLogger(__name__)
 
 ENDPOINT = "https://openrouter.ai/api/v1/chat/completions"
@@ -107,13 +109,15 @@ def make_openrouter_translator(api_key: str, model: str):
             f"no quotes, no extra words. Output ONLY a numbered list of the translations."
             f"\n\n{numbered}"
         )
-        payload = {"model": model, "temperature": 0.4,
+        payload = {"model": model, "temperature": 0.4, "usage": {"include": True},
                    "messages": [{"role": "user", "content": prompt}]}
         headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
         async with httpx.AsyncClient(timeout=httpx.Timeout(30.0)) as client:
             resp = await client.post(ENDPOINT, json=payload, headers=headers)
             resp.raise_for_status()
-        text = resp.json()["choices"][0]["message"]["content"]
+        data = resp.json()
+        record_openrouter_cost(data.get("usage"), "llm")
+        text = data["choices"][0]["message"]["content"]
         return _parse_numbered(text, len(phrases))
 
     return translate_pool