feat(memory): add relation graph for conflict detection and retrieval

bot/vikingbot/config/loader.py

@@ -4,11 +4,14 @@
 import os
 from pathlib import Path
 from typing import Any
+
 from loguru import logger
+
 from vikingbot.config.schema import Config
 
 CONFIG_PATH = None
 
+
 def get_config_path() -> Path:
     """Get the path to ov.conf config file.
 
@@ -217,4 +220,4 @@ def camel_to_snake(name: str) -> str:
 def snake_to_camel(name: str) -> str:
     """Convert snake_case to camelCase."""
     components = name.split("_")
-    return components[0] + "".join(x.title() for x in components[1:])
+    return components[0] + "".join(x.title() for x in components[1:])

bot/vikingbot/config/schema.py

@@ -40,8 +40,10 @@ class SandboxMode(str, Enum):
     SHARED = "shared"
     PER_CHANNEL = "per-channel"
 
+
 class AgentMemoryMode(str, Enum):
     """Agent memory mode enumeration."""
+
     PER_SESSION = "per-session"
     SHARED = "shared"
     PER_CHANNEL = "per-channel"
@@ -109,7 +111,10 @@ class FeishuChannelConfig(BaseChannelConfig):
     encrypt_key: str = ""
     verification_token: str = ""
     allow_from: list[str] = Field(default_factory=list)  ## 允许更新Agent对话的Feishu用户ID列表
-    thread_require_mention: bool = Field(default=True, description="话题群模式下是否需要@才响应：默认True=所有消息必须@才响应；False=新话题首条消息无需@，后续回复必须@")
+    thread_require_mention: bool = Field(
+        default=True,
+        description="话题群模式下是否需要@才响应：默认True=所有消息必须@才响应；False=新话题首条消息无需@，后续回复必须@",
+    )
 
     def channel_id(self) -> str:
         # Use app_id directly as the ID
@@ -396,7 +401,9 @@ class ProviderConfig(BaseModel):
 
     api_key: str = ""
     api_base: Optional[str] = None
-    extra_headers: Optional[dict[str, str]] = Field(default_factory=dict)  # Custom headers (e.g. APP-Code for AiHubMix)
+    extra_headers: Optional[dict[str, str]] = Field(
+        default_factory=dict
+    )  # Custom headers (e.g. APP-Code for AiHubMix)
 
 
 class ProvidersConfig(BaseModel):
@@ -734,4 +741,4 @@ def from_safe_name(safe_name: str):
         file_name_split = safe_name.split("__")
         return SessionKey(
             type=file_name_split[0], channel_id=file_name_split[1], chat_id=file_name_split[2]
-        )
+        )

bot/vikingbot/openviking_mount/ov_server.py

@@ -1,9 +1,9 @@
 import asyncio
 import hashlib
-from typing import List, Dict, Any, Optional
+import time
+from typing import Any, Dict, List, Optional
 
 from loguru import logger
-import time
 
 import openviking as ov
 from vikingbot.config.loader import load_config
@@ -99,9 +99,7 @@ async def find(self, query: str, target_uri: Optional[str] = None):
             return await self.client.find(query, target_uri=target_uri)
         return await self.client.find(query)
 
-    async def add_resource(
-        self, local_path: str, desc: str
-    ) -> Optional[Dict[str, Any]]:
+    async def add_resource(self, local_path: str, desc: str) -> Optional[Dict[str, Any]]:
         """添加资源到 Viking"""
         result = await self.client.add_resource(path=local_path, reason=desc)
         return result
@@ -327,7 +325,9 @@ async def search_memory(
 
     async def grep(self, uri: str, pattern: str, case_insensitive: bool = False) -> Dict[str, Any]:
         """通过模式（正则表达式）搜索内容"""
-        return await self.client.grep(uri, pattern, case_insensitive=case_insensitive, node_limit=10)
+        return await self.client.grep(
+            uri, pattern, case_insensitive=case_insensitive, node_limit=10
+        )
 
     async def glob(self, pattern: str, uri: Optional[str] = None) -> Dict[str, Any]:
         """通过 glob 模式匹配文件"""
@@ -337,7 +337,8 @@ async def commit(self, session_id: str, messages: list[dict[str, Any]], user_id:
         """提交会话"""
         import re
         import uuid
-        from openviking.message.part import Part, TextPart, ToolPart
+
+        from openviking.message.part import TextPart, ToolPart
 
         user_exists = await self._check_user_exists(user_id)
         if not user_exists:

openviking/models/embedder/__init__.py

@@ -25,7 +25,6 @@
 )
 from openviking.models.embedder.jina_embedders import JinaDenseEmbedder
 from openviking.models.embedder.openai_embedders import OpenAIDenseEmbedder
-from openviking.models.embedder.voyage_embedders import VoyageDenseEmbedder
 from openviking.models.embedder.vikingdb_embedders import (
     VikingDBDenseEmbedder,
     VikingDBHybridEmbedder,
@@ -36,6 +35,7 @@
     VolcengineHybridEmbedder,
     VolcengineSparseEmbedder,
 )
+from openviking.models.embedder.voyage_embedders import VoyageDenseEmbedder
 
 __all__ = [
     # Base classes

openviking/parse/parsers/excel.py

@@ -142,7 +142,9 @@ def _format_xls_cell(cell, wb, xlrd) -> str:
                 dt = xlrd.xldate_as_tuple(cell.value, wb.datemode)
                 # Include time component if non-zero
                 if dt[3] or dt[4] or dt[5]:
-                    return f"{dt[0]:04d}-{dt[1]:02d}-{dt[2]:02d} {dt[3]:02d}:{dt[4]:02d}:{dt[5]:02d}"
+                    return (
+                        f"{dt[0]:04d}-{dt[1]:02d}-{dt[2]:02d} {dt[3]:02d}:{dt[4]:02d}:{dt[5]:02d}"
+                    )
                 return f"{dt[0]:04d}-{dt[1]:02d}-{dt[2]:02d}"
             except Exception:
                 return str(cell.value)
@@ -151,8 +153,13 @@ def _format_xls_cell(cell, wb, xlrd) -> str:
         if cell.ctype == xlrd.XL_CELL_ERROR:
             # xlrd error code map
             error_map = {
-                0x00: "#NULL!", 0x07: "#DIV/0!", 0x0F: "#VALUE!",
-                0x17: "#REF!", 0x1D: "#NAME?", 0x24: "#NUM!", 0x2A: "#N/A",
+                0x00: "#NULL!",
+                0x07: "#DIV/0!",
+                0x0F: "#VALUE!",
+                0x17: "#REF!",
+                0x1D: "#NAME?",
+                0x24: "#NUM!",
+                0x2A: "#N/A",
             }
             return error_map.get(cell.value, f"#ERR({cell.value})")
         if cell.ctype == xlrd.XL_CELL_NUMBER:

openviking/parse/parsers/legacy_doc.py

@@ -19,7 +19,7 @@
 logger = get_logger(__name__)
 
 
-    # Max stream size to read (50MB) — prevents DoS from crafted files
+# Max stream size to read (50MB) — prevents DoS from crafted files
 _MAX_STREAM_SIZE = 50 * 1024 * 1024
 # Max character count sanity cap for ccpText
 _MAX_CCP_TEXT = 10_000_000
@@ -154,9 +154,7 @@ def _extract_from_ole(self, ole) -> str:
         if fc_clx <= 0 or lcb_clx <= 0 or fc_clx + lcb_clx > len(table_data):
             return self._simple_text_extract(word_doc, ccp_text)
 
-        return self._extract_via_clx(
-            word_doc, table_data, fc_clx, lcb_clx, ccp_text
-        )
+        return self._extract_via_clx(word_doc, table_data, fc_clx, lcb_clx, ccp_text)
 
     def _simple_text_extract(self, word_doc: bytes, ccp_text: int) -> str:
         """
@@ -177,7 +175,10 @@ def _simple_text_extract(self, word_doc: bytes, ccp_text: int) -> str:
             raw = word_doc[text_start:end]
             text = raw.decode("utf-16-le", errors="replace")
             # Sanity: if mostly printable, it's likely correct
-            if sum(1 for c in text[:200] if c.isprintable() or c in "\n\r\t") > len(text[:200]) * 0.5:
+            if (
+                sum(1 for c in text[:200] if c.isprintable() or c in "\n\r\t")
+                > len(text[:200]) * 0.5
+            ):
                 return self._clean_word_text(text)
 
         # Fall back to CP1252 single-byte
@@ -277,7 +278,9 @@ def _extract_via_clx(
                     raw = word_doc[byte_offset:byte_end]
                     text_parts.append(self._decode_cp1252(raw))
                 else:
-                    logger.warning(f"Piece {i} extends beyond stream ({byte_end} > {len(word_doc)})")
+                    logger.warning(
+                        f"Piece {i} extends beyond stream ({byte_end} > {len(word_doc)})"
+                    )
             else:
                 # UTF-16LE
                 byte_offset = fc_real
@@ -286,7 +289,9 @@ def _extract_via_clx(
                     raw = word_doc[byte_offset:byte_end]
                     text_parts.append(raw.decode("utf-16-le", errors="replace"))
                 else:
-                    logger.warning(f"Piece {i} extends beyond stream ({byte_end} > {len(word_doc)})")
+                    logger.warning(
+                        f"Piece {i} extends beyond stream ({byte_end} > {len(word_doc)})"
+                    )
 
             chars_extracted += piece_char_count
 
@@ -305,7 +310,7 @@ def _clean_word_text(text: str) -> str:
         """Normalize Word control characters to readable equivalents."""
         text = text.replace("\r\n", "\n").replace("\r", "\n")
         # \x07 = cell/row end, \x0B = soft line break, \x0C = section break
-        text = text.replace("\x07", "\t").replace("\x0B", "\n").replace("\x0C", "\n\n")
+        text = text.replace("\x07", "\t").replace("\x0b", "\n").replace("\x0c", "\n\n")
         return text
 
     def _fallback_extract(self, path: Path) -> str:

openviking/parse/registry.py

@@ -19,14 +19,14 @@
 
 # Import will be handled dynamically to avoid dependency issues
 from openviking.parse.parsers.html import HTMLParser
+
+# Import markitdown-inspired parsers
+from openviking.parse.parsers.legacy_doc import LegacyDocParser
 from openviking.parse.parsers.markdown import MarkdownParser
 from openviking.parse.parsers.media import AudioParser, ImageParser, VideoParser
 from openviking.parse.parsers.pdf import PDFParser
 from openviking.parse.parsers.powerpoint import PowerPointParser
 from openviking.parse.parsers.text import TextParser
-
-# Import markitdown-inspired parsers
-from openviking.parse.parsers.legacy_doc import LegacyDocParser
 from openviking.parse.parsers.word import WordParser
 from openviking.parse.parsers.zip_parser import ZipParser