Improve translation reliability and progress feedback

backend/llm_client.py

@@ -2,6 +2,7 @@
 
 import os
 from pathlib import Path
+from collections.abc import Awaitable, Callable
 
 from openai import AsyncOpenAI
 
@@ -22,6 +23,7 @@ def _load_llm_configs() -> list[LLMConfig]:
 
 _llm_configs: list[LLMConfig] = []
 _clients: dict[str, AsyncOpenAI] = {}  # alias -> client instance
+LLM_TIMEOUT_SECONDS = float(os.getenv("LLM_TIMEOUT_SECONDS", "180"))
 
 
 def get_llm_configs() -> list[LLMConfig]:
@@ -46,7 +48,8 @@ def get_client_for_alias(alias: str) -> tuple[AsyncOpenAI, LLMConfig]:
         client = AsyncOpenAI(
             api_key=cfg.api_key,
             base_url=cfg.base_url,
-            timeout=120.0,
+            timeout=LLM_TIMEOUT_SECONDS,
+            max_retries=0,
         )
         _clients[alias] = client
 
@@ -58,21 +61,33 @@ async def chat_complete(
     system_prompt: str,
     user_content: str,
     temperature: float = 0.3,
+    on_delta: Callable[[str], Awaitable[None]] | None = None,
 ) -> str:
     """Send a single-turn chat completion and return the assistant message."""
     client, cfg = get_client_for_alias(alias)
-
-    response = await client.chat.completions.create(
-        model=cfg.model,
-        messages=[
+    request = {
+        "model": cfg.model,
+        "messages": [
             {"role": "system", "content": system_prompt},
             {"role": "user", "content": user_content},
         ],
-        temperature=temperature,
-    )
+        "temperature": temperature,
+    }
+    if on_delta is None:
+        response = await client.chat.completions.create(**request)
+        content = response.choices[0].message.content or ""
+        return content.strip()
 
-    content = response.choices[0].message.content or ""
-    return content.strip()
+    stream = await client.chat.completions.create(**request, stream=True)
+    parts: list[str] = []
+    async for event in stream:
+        if not event.choices:
+            continue
+        delta = event.choices[0].delta.content or ""
+        if delta:
+            parts.append(delta)
+            await on_delta(delta)
+    return "".join(parts).strip()
 
 
 def get_context_size(alias: str) -> int | None: