更新

backend/utils/log_limits.py

@@ -0,0 +1,101 @@
+"""Bound diagnostic payloads without changing live message processing."""
+
+from __future__ import annotations
+
+import json
+import os
+from typing import Any
+
+
+TRUNCATION_MARKER = "\n...[日志内容过长，已截断]"
+_MESSAGE_FIELDS = (
+    "type",
+    "url",
+    "uri",
+    "text",
+    "name",
+    "width",
+    "height",
+    "duration",
+    "sticker_id",
+    "mime_type",
+)
+
+
+def _env_limit(name: str, default: int, minimum: int, maximum: int) -> int:
+    try:
+        value = int(os.getenv(name, str(default)) or default)
+    except (TypeError, ValueError):
+        value = default
+    return max(minimum, min(maximum, value))
+
+
+def truncate_text(value: Any, limit: int) -> str:
+    text = "" if value is None else str(value)
+    if len(text) <= limit:
+        return text
+    keep = max(0, limit - len(TRUNCATION_MARKER))
+    return text[:keep] + TRUNCATION_MARKER
+
+
+def bound_system_log_detail(value: Any) -> str:
+    return truncate_text(
+        value,
+        _env_limit("KEFU_SYSTEM_LOG_MAX_CHARS", 4096, 512, 65536),
+    )
+
+
+def _compact_media_message(value: Any) -> Any:
+    if not isinstance(value, dict):
+        return truncate_text(value, 2048)
+    compact: dict[str, Any] = {}
+    for key in _MESSAGE_FIELDS:
+        if key not in value:
+            continue
+        item = value[key]
+        compact[key] = truncate_text(item, 2048) if isinstance(item, str) else item
+    compact["_log_truncated"] = True
+    return compact
+
+
+def bound_message_log_content(value: Any) -> str:
+    """Keep a valid compact media JSON payload when a log entry is oversized."""
+    limit = _env_limit("KEFU_MESSAGE_LOG_MAX_CHARS", 16384, 2048, 262144)
+    text = "" if value is None else str(value)
+    if len(text) <= limit:
+        return text
+
+    try:
+        parsed = json.loads(text)
+    except (TypeError, ValueError, json.JSONDecodeError):
+        return truncate_text(text, limit)
+
+    if isinstance(parsed, dict) and parsed.get("type"):
+        compact = _compact_media_message(parsed)
+    elif isinstance(parsed, dict) and isinstance(parsed.get("messages"), list):
+        compact = {
+            "messages": [
+                _compact_media_message(item)
+                for item in parsed["messages"][:20]
+            ],
+            "_log_truncated": True,
+        }
+    else:
+        return truncate_text(text, limit)
+
+    encoded = json.dumps(compact, ensure_ascii=False, separators=(",", ":"))
+    return encoded if len(encoded) <= limit else truncate_text(encoded, limit)
+
+
+def bound_raw_message_log_content(value: Any) -> str:
+    return truncate_text(
+        value,
+        _env_limit("KEFU_RAW_MESSAGE_LOG_MAX_CHARS", 32768, 4096, 262144),
+    )
+
+
+def bound_error_log_content(value: Any) -> str:
+    return truncate_text(
+        value,
+        _env_limit("KEFU_ERROR_LOG_MAX_CHARS", 4096, 512, 65536),
+    )

backend/utils/received_message_log.py

@@ -8,6 +8,7 @@ from typing import Optional
 
 from models.database import AsyncSessionLocal
 from models.models import ReceivedMessageLog
+from utils.log_limits import bound_raw_message_log_content
 
 logger = logging.getLogger("received_message_log")
 
@@ -23,8 +24,9 @@ async def record_received_message(
     message_type: Optional[int] = None,
     server_message_id: Optional[str] = None,
 ) -> None:
-    # 原样落库：不做 strip / parse / serialize，空字符串也记录
-    store_content = raw_content if raw_content is not None else ""
+    # The live message object remains untouched for matching/replying. Only
+    # this diagnostic copy is bounded before persistence.
+    store_content = bound_raw_message_log_content(raw_content)
 
     async with AsyncSessionLocal() as db:
         try:

backend/utils/system_logger.py

@@ -15,6 +15,8 @@ from collections import deque
 from datetime import datetime
 from typing import Optional
 
+from .log_limits import bound_system_log_detail, truncate_text
+
 logger = logging.getLogger("douyin_im.system")
 
 _VALID_LEVELS = ("info", "success", "warning", "error")
@@ -43,14 +45,16 @@ def record(
             "account_id": account_id,
             "level": level,
             "category": category,
-            "event": str(event or ""),
-            "detail": str(detail or ""),
+            "event": truncate_text(event, 255),
+            "detail": bound_system_log_detail(detail),
             "created_at": datetime.utcnow().isoformat(),
         }
         _buffer.appendleft(entry)
         _pending.append(entry)
 
-    msg = f"[{category}] {event}" + (f" | {detail}" if detail else "")
+    msg = f"[{category}] {entry['event']}" + (
+        f" | {entry['detail']}" if entry["detail"] else ""
+    )
     if level == "error":
         logger.error(msg)
     elif level == "warning":