refactor: review fixes and code improvements

- Add shared proxy module (bot/utils/proxy.py) to eliminate duplicate SOCKS5 parsing
- Fix AI client: escape HTML before Markdown→HTML conversion, unify timeouts,
  make health check optional and disabled by default, handle 429 retries
- Fix ai.py: correct forwarded message handling (aiogram 3.x forward_origin),
  pass relevant summaries via extra_system_content
- Fix dialogue.py: only respond to Astra's messages, use system context instead
  of prompt injection, answer on the limit message before phase transition
- Fix voice.py: load Whisper model in thread pool, safe WAV path generation
- Improve database.py: composite indexes, Boolean is_active, upsert file_id cache,
  add context cleanup helper
- Update weather.py and yadisk_download.py to use shared proxy connector
- Update yadisk.py: validate URL before cache clear, add download size limit,
  wrap sync file ops in to_thread
- Reuse S3 client via lru_cache
- Update setup_commands with /aiclear and /aiuser
- Update README, Dockerfile (Python 3.11), docker-compose (mount models)
- Pin dependency versions, remove unused httpx[socks]
- Add basic pytest tests for layout converter and voice normalization

bot/utils/memory.py

@@ -3,8 +3,11 @@ import logging
 import math
 import re
 
-from bot.utils.ai_client import _get_connector
+import aiohttp
+
+from bot.utils.proxy import get_proxy_connector
 from bot.utils.database import get_summaries, save_conversation_summary
+from bot.utils.ai_client import get_client_timeout, ask_ai_simple
 from config import ROUTERAI_API_KEY, ROUTERAI_BASE_URL
 
 logger = logging.getLogger(__name__)
@@ -29,26 +32,36 @@ async def create_embedding(text: str) -> list[float] | None:
         "encoding_format": "float",
     }
 
-    import aiohttp
-    from bot.utils.ai_client import get_client_timeout
-
-    connector = _get_connector()
+    connector = get_proxy_connector()
 
     try:
-        async with aiohttp.ClientSession(timeout=get_client_timeout(30), connector=connector) as session:
+        async with aiohttp.ClientSession(
+            timeout=get_client_timeout(30), connector=connector
+        ) as session:
             async with session.post(EMBEDDING_URL, json=payload, headers=headers) as response:
                 if response.status != 200:
                     error_body = await response.text()
-                    logger.warning("Embedding error | status=%s error=%s", response.status, error_body[:200])
+                    logger.warning(
+                        "Embedding error | status=%s error=%s",
+                        response.status,
+                        error_body[:200],
+                    )
                     return None
 
                 data = await response.json()
                 embedding = data["data"][0]["embedding"]
-                logger.info("Embedding created | dim=%d input_len=%d", len(embedding), min(len(text), 8000))
+                logger.info(
+                    "Embedding created | dim=%d input_len=%d",
+                    len(embedding),
+                    min(len(text), 8000),
+                )
                 return embedding
-    except Exception as e:
-        logger.error("Embedding request error: %s", e)
+    except Exception as exc:
+        logger.error("Embedding request error: %s", exc)
         return None
+    finally:
+        if connector:
+            await connector.close()
 
 
 def cosine_similarity(a: list[float], b: list[float]) -> float:
@@ -60,14 +73,18 @@ def cosine_similarity(a: list[float], b: list[float]) -> float:
     return dot / (norm_a * norm_b)
 
 
-async def find_relevant_summaries(user_id: int, chat_id: int, query: str, top_k: int = 3) -> list[str]:
+async def find_relevant_summaries(
+    user_id: int, chat_id: int, query: str, top_k: int = 3
+) -> list[str]:
     query_emb = await create_embedding(query)
     if not query_emb:
         return []
 
     summaries = await get_summaries(user_id, chat_id, limit=20)
     if not summaries:
-        logger.info("Relevant summaries | user=%d chat=%d no summaries found", user_id, chat_id)
+        logger.info(
+            "Relevant summaries | user=%d chat=%d no summaries found", user_id, chat_id
+        )
         return []
 
     scored = []
@@ -87,24 +104,30 @@ async def find_relevant_summaries(user_id: int, chat_id: int, query: str, top_k:
 
     logger.info(
         "Relevant summaries | user=%d chat=%d found=%d top_score=%.3f",
-        user_id, chat_id, len(top), top_score,
+        user_id,
+        chat_id,
+        len(top),
+        top_score,
     )
     return top
 
 
-async def save_summary_with_embedding(user_id: int, chat_id: int, summary_text: str) -> None:
+async def save_summary_with_embedding(
+    user_id: int, chat_id: int, summary_text: str
+) -> None:
     emb = await create_embedding(summary_text)
     embedding_json = json.dumps(emb) if emb else None
     await save_conversation_summary(user_id, chat_id, summary_text, embedding_json)
     logger.info(
         "Summary saved | user=%d chat=%d summary_len=%d emb=%s",
-        user_id, chat_id, len(summary_text), "yes" if emb else "no",
+        user_id,
+        chat_id,
+        len(summary_text),
+        "yes" if emb else "no",
     )
 
 
 async def generate_summary(messages: list[dict]) -> str | None:
-    from bot.utils.ai_client import ask_ai_simple
-
     messages_text = "\n".join(
         f"{'Пользователь' if m['role'] == 'user' else 'Астра'}: {m['content'][:300]}"
         for m in messages[-50:]
@@ -127,7 +150,7 @@ async def generate_summary(messages: list[dict]) -> str | None:
             logger.warning("Summary too short | len=%d", len(summary))
         else:
             logger.warning("Summary generation returned None")
-    except Exception as e:
-        logger.error("Summary generation error: %s", e)
+    except Exception as exc:
+        logger.error("Summary generation error: %s", exc)
 
     return None