Improve EPUB restoration, book terminology and Calibre QA workflow

src/translation/llm_client.py

@@ -44,7 +44,8 @@ class LLMClient:
     
     def __init__(self, api_key: str, base_url: str, model: str = "gpt-3.5-turbo",
                  requests_per_minute: int = 60, concurrent_requests: int = 5,
-                 extra_headers: Dict = None, chunk_dir: Path = None):
+                 extra_headers: Dict = None, chunk_dir: Path = None,
+                 timeout: float = 180, max_output_tokens: int = 16000, temperature=None):
         
         # Configure proxy client to avoid SOCKS issues and ensure connectivity
         import httpx
@@ -54,7 +55,7 @@ class LLMClient:
         proxy_url = os.environ.get("http_proxy") or os.environ.get("https_proxy")
         http_client = httpx.AsyncClient(
             proxy=proxy_url,
-            timeout=60.0,
+            timeout=timeout,
             follow_redirects=True
         ) if proxy_url else None
 
@@ -62,9 +63,13 @@ class LLMClient:
             base_url=base_url,
             api_key=api_key,
             default_headers=extra_headers,
-            http_client=http_client
+            http_client=http_client,
+            timeout=timeout,
+            max_retries=0
         )
         self.model = model
+        self.max_output_tokens = max_output_tokens
+        self.temperature = temperature
         
         self.rate_limiter = RateLimiter(requests_per_minute, concurrent_requests)
         self.prompts = self._load_prompts()
@@ -76,7 +81,7 @@ class LLMClient:
         
     def _load_prompts(self) -> Dict:
         try:
-            with open("config/prompts.json", "r", encoding="utf-8") as f:
+            with open(Path(__file__).resolve().parents[2] / "config/prompts.json", "r", encoding="utf-8") as f:
                 return json.load(f)
         except Exception as e:
             logger.error(f"Failed to load config/prompts.json: {e}")
@@ -130,7 +135,7 @@ Output Format:
             
         except Exception as e:
             logger.error(f"Translation failed: {e}")
-            return {item.entry_id: f"[Error - {str(e)}]" for item in items}
+            raise
 
     def _build_prompt_with_short_ids(self, items: List[ManifestEntry]) -> tuple:
         """
@@ -156,6 +161,8 @@ Output Format:
         Returns: Dict[entry_id, translated_text]
         """
         results = {}
+        seen = set()
+        duplicates = set()
         
         for line in response.split("\n"):
             line = line.strip()
@@ -175,16 +182,26 @@ Output Format:
                     if sub_match:
                         # Check if the inner ID matches the outer ID, or just strip it anyway
                         # Usually LLM repeats the same ID.
+                        if sub_match.group(1) != match.group(1):
+                            content = ''
+                            break
                         content = sub_match.group(2).strip()
                     else:
                         break
                 
+                if not content:
+                    continue
                 if short_id in id_map:
                     full_id = id_map[short_id]
+                    if short_id in seen:
+                        duplicates.add(full_id)
+                    seen.add(short_id)
                     results[full_id] = content
                 else:
                     logger.warning(f"Unknown short ID in response: {short_id}")
         
+        for full_id in duplicates:
+            results.pop(full_id, None)
         return results
 
     def _save_chunk(self, stage: str, content: str, system_prompt: str = None, 
@@ -215,15 +232,21 @@ Output Format:
     async def _make_request(self, system_prompt: str, user_prompt: str) -> str:
         await self.rate_limiter.acquire()
         try:
+            options = {"max_completion_tokens": self.max_output_tokens}
+            if self.temperature is not None:
+                options["temperature"] = self.temperature
             resp = await self.client.chat.completions.create(
                 model=self.model,
                 messages=[
                     {"role": "system", "content": system_prompt},
                     {"role": "user", "content": user_prompt}
                 ],
-                temperature=0.3,
+                **options,
             )
-            return resp.choices[0].message.content.strip()
+            choice = resp.choices[0]
+            if choice.finish_reason != "stop" or not choice.message.content:
+                raise ValueError(f"Incomplete model response: {choice.finish_reason}")
+            return choice.message.content.strip()
         finally:
             self.rate_limiter.release()