basic-memory 0.12.1__tar.gz → 0.12.3__tar.gz

{basic_memory-0.12.1 → basic_memory-0.12.3}/CHANGELOG.md

@@ -1,6 +1,32 @@
 # CHANGELOG
 
 
+## v0.12.3 (2025-04-17)
+
+### Bug Fixes
+
+- Add extra logic for permalink generation with mixed Latin unicode and Chinese characters
+  ([`73ea91f`](https://github.com/basicmachines-co/basic-memory/commit/73ea91fe0d1f7ab89b99a1b691d59fe608b7fcbb))
+
+Signed-off-by: phernandez <paul@basicmachines.co>
+
+- Modify recent_activity args to be strings instead of enums
+  ([`3c1cc34`](https://github.com/basicmachines-co/basic-memory/commit/3c1cc346df519e703fae6412d43a92c7232c6226))
+
+Signed-off-by: phernandez <paul@basicmachines.co>
+
+
+## v0.12.2 (2025-04-08)
+
+### Bug Fixes
+
+- Utf8 for all file reads/write/open instead of default platform encoding
+  ([#91](https://github.com/basicmachines-co/basic-memory/pull/91),
+  [`2934176`](https://github.com/basicmachines-co/basic-memory/commit/29341763318408ea8f1e954a41046c4185f836c6))
+
+Signed-off-by: phernandez <paul@basicmachines.co>
+
+
 ## v0.12.1 (2025-04-07)
 
 ### Bug Fixes

{basic_memory-0.12.1 → basic_memory-0.12.3}/CLAUDE.md

@@ -172,4 +172,18 @@ With GitHub integration, the development workflow includes:
 4. **Documentation maintenance** - Claude can keep documentation updated as the code evolves
 
 With this integration, the AI assistant is a full-fledged team member rather than just a tool for generating code
-snippets.
+snippets.
+
+
+### Basic Memory Pro
+
+Basic Memory Pro is a desktop GUI application that wraps the basic-memory CLI/MCP tools:
+
+- Built with Tauri (Rust), React (TypeScript), and a Python FastAPI sidecar
+- Provides visual knowledge graph exploration and project management
+- Uses the same core codebase but adds a desktop-friendly interface
+- Project configuration is shared between CLI and Pro versions
+- Multiple project support with visual switching interface
+
+local repo: /Users/phernandez/dev/basicmachines/basic-memory-pro
+github: https://github.com/basicmachines-co/basic-memory-pro

{basic_memory-0.12.1 → basic_memory-0.12.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: basic-memory
-Version: 0.12.1
+Version: 0.12.3
 Summary: Local-first knowledge management combining Zettelkasten with knowledge graphs
 Project-URL: Homepage, https://github.com/basicmachines-co/basic-memory
 Project-URL: Repository, https://github.com/basicmachines-co/basic-memory
@@ -367,9 +367,9 @@ config:
       "command": "uvx",
       "args": [
         "basic-memory",
-        "mcp",
         "--project",
-        "your-project-name"
+        "your-project-name",
+        "mcp"
       ]
     }
   }

{basic_memory-0.12.1 → basic_memory-0.12.3}/README.md

@@ -333,9 +333,9 @@ config:
       "command": "uvx",
       "args": [
         "basic-memory",
-        "mcp",
         "--project",
-        "your-project-name"
+        "your-project-name",
+        "mcp"
       ]
     }
   }

{basic_memory-0.12.1 → basic_memory-0.12.3}/installer/installer.py

@@ -44,7 +44,7 @@ def update_claude_config():
 
     # Load existing config or create new
     if config_path.exists():
-        config = json.loads(config_path.read_text())
+        config = json.loads(config_path.read_text(encoding="utf-8"))
     else:
         config = {"mcpServers": {}}
 

{basic_memory-0.12.1 → basic_memory-0.12.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "basic-memory"
-version = "0.12.1"
+version = "0.12.3"
 description = "Local-first knowledge management combining Zettelkasten with knowledge graphs"
 readme = "README.md"
 requires-python = ">=3.12.1"

{basic_memory-0.12.1 → basic_memory-0.12.3}/src/basic_memory/__init__.py

@@ -1,3 +1,3 @@
 """basic-memory - Local-first knowledge management combining Zettelkasten with knowledge graphs"""
 
-__version__ = "0.12.1"
+__version__ = "0.12.3"

{basic_memory-0.12.1 → basic_memory-0.12.3}/src/basic_memory/cli/commands/import_memory_json.py

@@ -38,7 +38,7 @@ async def process_memory_json(
         read_task = progress.add_task("Reading memory.json...", total=None)
 
         # First pass - collect entities and relations
-        with open(json_path) as f:
+        with open(json_path, encoding="utf-8") as f:
             lines = f.readlines()
             progress.update(read_task, total=len(lines))
 

{basic_memory-0.12.1 → basic_memory-0.12.3}/src/basic_memory/markdown/entity_parser.py

@@ -104,7 +104,7 @@ class EntityParser:
             absolute_path = self.base_path / path
 
         # Parse frontmatter and content using python-frontmatter
-        file_content = absolute_path.read_text()
+        file_content = absolute_path.read_text(encoding="utf-8")
         return await self.parse_file_content(absolute_path, file_content)
 
     async def parse_file_content(self, absolute_path, file_content):

{basic_memory-0.12.1 → basic_memory-0.12.3}/src/basic_memory/mcp/tools/read_note.py

@@ -111,7 +111,7 @@ def format_not_found_message(identifier: str) -> str:
         ## Search Instead
         Try searching for related content:
         ```
-        search(query="{identifier}")
+        search_notes(query="{identifier}")
         ```
         
         ## Recent Activity
@@ -172,7 +172,7 @@ def format_related_results(identifier: str, results) -> str:
         ## Search For More Results
         To see more related content:
         ```
-        search(query="{identifier}")
+        search_notes(query="{identifier}")
         ```
         
         ## Create New Note

{basic_memory-0.12.1 → basic_memory-0.12.3}/src/basic_memory/mcp/tools/recent_activity.py

@@ -1,6 +1,6 @@
 """Recent activity tool for Basic Memory MCP server."""
 
-from typing import Optional, List
+from typing import List, Union
 
 from loguru import logger
 
@@ -14,7 +14,7 @@ from basic_memory.schemas.search import SearchItemType
 
 @mcp.tool(
     description="""Get recent activity from across the knowledge base.
-    
+
     Timeframe supports natural language formats like:
     - "2 days ago"  
     - "last week"
@@ -25,9 +25,9 @@ from basic_memory.schemas.search import SearchItemType
     """,
 )
 async def recent_activity(
-    type: Optional[List[SearchItemType]] = None,
-    depth: Optional[int] = 1,
-    timeframe: Optional[TimeFrame] = "7d",
+    type: Union[str, List[str]] = "",
+    depth: int = 1,
+    timeframe: TimeFrame = "7d",
     page: int = 1,
     page_size: int = 10,
     max_related: int = 10,
@@ -35,11 +35,14 @@ async def recent_activity(
     """Get recent activity across the knowledge base.
 
     Args:
-        type: Filter by content type(s). Valid options:
-            - ["entity"] for knowledge entities
-            - ["relation"] for connections between entities
-            - ["observation"] for notes and observations
+        type: Filter by content type(s). Can be a string or list of strings.
+            Valid options:
+            - "entity" or ["entity"] for knowledge entities
+            - "relation" or ["relation"] for connections between entities
+            - "observation" or ["observation"] for notes and observations
             Multiple types can be combined: ["entity", "relation"]
+            Case-insensitive: "ENTITY" and "entity" are treated the same.
+            Default is an empty string, which returns all types.
         depth: How many relation hops to traverse (1-3 recommended)
         timeframe: Time window to search. Supports natural language:
             - Relative: "2 days ago", "last week", "yesterday"
@@ -59,14 +62,17 @@ async def recent_activity(
         # Get all entities for the last 10 days (default)
         recent_activity()
 
-        # Get all entities from yesterday
+        # Get all entities from yesterday (string format)
+        recent_activity(type="entity", timeframe="yesterday")
+
+        # Get all entities from yesterday (list format)
         recent_activity(type=["entity"], timeframe="yesterday")
 
         # Get recent relations and observations
         recent_activity(type=["relation", "observation"], timeframe="today")
 
         # Look back further with more context
-        recent_activity(type=["entity"], depth=2, timeframe="2 weeks ago")
+        recent_activity(type="entity", depth=2, timeframe="2 weeks ago")
 
     Notes:
         - Higher depth values (>3) may impact performance with large result sets
@@ -86,11 +92,27 @@ async def recent_activity(
     if timeframe:
         params["timeframe"] = timeframe  # pyright: ignore
 
-    # send enum values if we have an enum, else send string value
+    # Validate and convert type parameter
     if type:
-        params["type"] = [  # pyright: ignore
-            type.value if isinstance(type, SearchItemType) else type for type in type
-        ]
+        # Convert single string to list
+        if isinstance(type, str):
+            type_list = [type]
+        else:
+            type_list = type
+
+        # Validate each type against SearchItemType enum
+        validated_types = []
+        for t in type_list:
+            try:
+                # Try to convert string to enum
+                if isinstance(t, str):
+                    validated_types.append(SearchItemType(t.lower()))
+            except ValueError:
+                valid_types = [t.value for t in SearchItemType]
+                raise ValueError(f"Invalid type: {t}. Valid types are: {valid_types}")
+
+        # Add validated types to params
+        params["type"] = [t.value for t in validated_types]  # pyright: ignore
 
     response = await call_get(
         client,

{basic_memory-0.12.1 → basic_memory-0.12.3}/src/basic_memory/sync/sync_service.py

@@ -1,9 +1,8 @@
 """Service for syncing files between filesystem and database."""
 
 import os
-
-from dataclasses import dataclass
-from dataclasses import field
+import time
+from dataclasses import dataclass, field
 from datetime import datetime
 from pathlib import Path
 from typing import Dict, Optional, Set, Tuple
@@ -18,7 +17,6 @@ from basic_memory.models import Entity
 from basic_memory.repository import EntityRepository, RelationRepository
 from basic_memory.services import EntityService, FileService
 from basic_memory.services.search_service import SearchService
-import time
 
 
 @dataclass
@@ -237,7 +235,7 @@ class SyncService:
         logger.debug(f"Parsing markdown file, path: {path}, new: {new}")
 
         file_path = self.entity_parser.base_path / path
-        file_content = file_path.read_text()
+        file_content = file_path.read_text(encoding="utf-8")
         file_contains_frontmatter = has_frontmatter(file_content)
 
         # entity markdown will always contain front matter, so it can be used up create/update the entity

{basic_memory-0.12.1 → basic_memory-0.12.3}/src/basic_memory/utils.py

@@ -5,11 +5,11 @@ import os
 import logging
 import re
 import sys
+import unicodedata
 from pathlib import Path
-from typing import Optional, Protocol, Union, runtime_checkable, List
+from typing import Optional, Protocol, Union, runtime_checkable, List, Any
 
 from loguru import logger
-from unidecode import unidecode
 
 
 @runtime_checkable
@@ -27,23 +27,23 @@ FilePath = Union[Path, str]
 logging.getLogger("opentelemetry.sdk.metrics._internal.instrument").setLevel(logging.ERROR)
 
 
-def generate_permalink(file_path: Union[Path, str, PathLike]) -> str:
-    """Generate a stable permalink from a file path.
-
-    Args:
-        file_path: Original file path (str, Path, or PathLike)
+def generate_permalink(file_path: Union[Path, str, Any]) -> str:
+    """
+    Generate a permalink from a file path.
 
     Returns:
         Normalized permalink that matches validation rules. Converts spaces and underscores
-        to hyphens for consistency.
+        to hyphens for consistency. Preserves non-ASCII characters like Chinese.
 
     Examples:
         >>> generate_permalink("docs/My Feature.md")
         'docs/my-feature'
-        >>> generate_permalink("specs/API (v2).md")
+        >>> generate_permalink("specs/API_v2.md")
         'specs/api-v2'
         >>> generate_permalink("design/unified_model_refactor.md")
         'design/unified-model-refactor'
+        >>> generate_permalink("中文/测试文档.md")
+        '中文/测试文档'
     """
     # Convert Path to string if needed
     path_str = str(file_path)
@@ -51,24 +51,74 @@ def generate_permalink(file_path: Union[Path, str, PathLike]) -> str:
     # Remove extension
     base = os.path.splitext(path_str)[0]
 
-    # Transliterate unicode to ascii
-    ascii_text = unidecode(base)
+    # Create a transliteration mapping for specific characters
+    transliteration_map = {
+        "ø": "o",  # Handle Søren -> soren
+        "å": "a",  # Handle Kierkegård -> kierkegard
+        "ü": "u",  # Handle Müller -> muller
+        "é": "e",  # Handle Café -> cafe
+        "è": "e",  # Handle Mère -> mere
+        "ê": "e",  # Handle Fête -> fete
+        "à": "a",  # Handle À la mode -> a la mode
+        "ç": "c",  # Handle Façade -> facade
+        "ñ": "n",  # Handle Niño -> nino
+        "ö": "o",  # Handle Björk -> bjork
+        "ä": "a",  # Handle Häagen -> haagen
+        # Add more mappings as needed
+    }
+
+    # Process character by character, transliterating Latin characters with diacritics
+    result = ""
+    for char in base:
+        # Direct mapping for known characters
+        if char.lower() in transliteration_map:
+            result += transliteration_map[char.lower()]
+        # General case using Unicode normalization
+        elif unicodedata.category(char).startswith("L") and ord(char) > 127:
+            # Decompose the character (e.g., ü -> u + combining diaeresis)
+            decomposed = unicodedata.normalize("NFD", char)
+            # If decomposition produced multiple characters and first one is ASCII
+            if len(decomposed) > 1 and ord(decomposed[0]) < 128:
+                # Keep only the base character
+                result += decomposed[0].lower()
+            else:
+                # For non-Latin scripts like Chinese, preserve the character
+                result += char
+        else:
+            # Add the character as is
+            result += char
+
+    # Handle special punctuation cases for apostrophes
+    result = result.replace("'", "")
 
     # Insert dash between camelCase
-    ascii_text = re.sub(r"([a-z0-9])([A-Z])", r"\1-\2", ascii_text)
+    # This regex finds boundaries between lowercase and uppercase letters
+    result = re.sub(r"([a-z0-9])([A-Z])", r"\1-\2", result)
+
+    # Insert dash between Chinese and Latin character boundaries
+    # This is needed for cases like "中文English" -> "中文-english"
+    result = re.sub(r"([\u4e00-\u9fff])([a-zA-Z])", r"\1-\2", result)
+    result = re.sub(r"([a-zA-Z])([\u4e00-\u9fff])", r"\1-\2", result)
 
-    # Convert to lowercase
-    lower_text = ascii_text.lower()
+    # Convert ASCII letters to lowercase, preserve non-ASCII characters
+    lower_text = "".join(c.lower() if c.isascii() and c.isalpha() else c for c in result)
 
-    # replace underscores with hyphens
+    # Replace underscores with hyphens
     text_with_hyphens = lower_text.replace("_", "-")
 
-    # Replace remaining invalid chars with hyphens
-    clean_text = re.sub(r"[^a-z0-9/\-]", "-", text_with_hyphens)
+    # Replace spaces and unsafe ASCII characters with hyphens, but preserve non-ASCII characters
+    # Include common Chinese character ranges and other non-ASCII characters
+    clean_text = re.sub(
+        r"[^a-z0-9\u4e00-\u9fff\u3000-\u303f\u3400-\u4dbf/\-]", "-", text_with_hyphens
+    )
 
     # Collapse multiple hyphens
     clean_text = re.sub(r"-+", "-", clean_text)
 
+    # Remove hyphens between adjacent Chinese characters only
+    # This handles cases like "你好-世界" -> "你好世界"
+    clean_text = re.sub(r"([\u4e00-\u9fff])-([\u4e00-\u9fff])", r"\1\2", clean_text)
+
     # Clean each path segment
     segments = clean_text.split("/")
     clean_segments = [s.strip("-") for s in segments]

{basic_memory-0.12.1 → basic_memory-0.12.3}/tests/api/test_resource_router.py

@@ -2,9 +2,9 @@
 
 import json
 from datetime import datetime, timezone
+from pathlib import Path
 
 import pytest
-from pathlib import Path
 
 from basic_memory.schemas import EntityResponse
 
@@ -346,7 +346,7 @@ async def test_put_resource_new_file(client, test_config, entity_repository, sea
     assert full_path.exists()
 
     # Verify file content
-    file_content = full_path.read_text()
+    file_content = full_path.read_text(encoding="utf-8")
     assert json.loads(file_content) == canvas_data
 
     # Verify entity was created in DB
@@ -420,7 +420,7 @@ async def test_put_resource_update_existing(client, test_config, entity_reposito
     assert response.status_code == 200
 
     # Verify file was updated
-    updated_content = full_path.read_text()
+    updated_content = full_path.read_text(encoding="utf-8")
     assert json.loads(updated_content) == updated_data
 
     # Verify entity was updated

{basic_memory-0.12.1 → basic_memory-0.12.3}/tests/cli/test_import_chatgpt.py

@@ -1,10 +1,11 @@
 """Tests for import_chatgpt command."""
 
 import json
+
 import pytest
 from typer.testing import CliRunner
 
-from basic_memory.cli.app import import_app, app
+from basic_memory.cli.app import app, import_app
 from basic_memory.cli.commands import import_chatgpt
 from basic_memory.config import config
 from basic_memory.markdown import EntityParser, MarkdownProcessor
@@ -144,7 +145,7 @@ def sample_conversation_with_hidden():
 def sample_chatgpt_json(tmp_path, sample_conversation):
     """Create a sample ChatGPT JSON file."""
     json_file = tmp_path / "conversations.json"
-    with open(json_file, "w") as f:
+    with open(json_file, "w", encoding="utf-8") as f:
         json.dump([sample_conversation], f)
     return json_file
 
@@ -167,7 +168,7 @@ async def test_process_chatgpt_json(tmp_path, sample_chatgpt_json):
     assert conv_path.exists()
 
     # Check content formatting
-    content = conv_path.read_text()
+    content = conv_path.read_text(encoding="utf-8")
     assert "# Test Conversation" in content
     assert "### User" in content
     assert "Hello, this is a test message" in content
@@ -183,14 +184,14 @@ async def test_process_code_blocks(tmp_path, sample_conversation_with_code):
 
     # Create test file
     json_file = tmp_path / "code_test.json"
-    with open(json_file, "w") as f:
+    with open(json_file, "w", encoding="utf-8") as f:
         json.dump([sample_conversation_with_code], f)
 
     await import_chatgpt.process_chatgpt_json(json_file, tmp_path, processor)
 
     # Check content
     conv_path = tmp_path / "20250111-code-test.md"
-    content = conv_path.read_text()
+    content = conv_path.read_text(encoding="utf-8")
     assert "```python" in content
     assert "def hello():" in content
     assert "```" in content
@@ -204,7 +205,7 @@ async def test_hidden_messages(tmp_path, sample_conversation_with_hidden):
 
     # Create test file
     json_file = tmp_path / "hidden_test.json"
-    with open(json_file, "w") as f:
+    with open(json_file, "w", encoding="utf-8") as f:
         json.dump([sample_conversation_with_hidden], f)
 
     results = await import_chatgpt.process_chatgpt_json(json_file, tmp_path, processor)
@@ -214,7 +215,7 @@ async def test_hidden_messages(tmp_path, sample_conversation_with_hidden):
 
     # Check content
     conv_path = tmp_path / "20250111-hidden-test.md"
-    content = conv_path.read_text()
+    content = conv_path.read_text(encoding="utf-8")
     assert "Visible message" in content
     assert "Hidden message" not in content
 

{basic_memory-0.12.1 → basic_memory-0.12.3}/tests/cli/test_import_claude_conversations.py

@@ -1,6 +1,7 @@
 """Tests for import_claude command (chat conversations)."""
 
 import json
+
 import pytest
 from typer.testing import CliRunner
 
@@ -44,7 +45,7 @@ def sample_conversation():
 def sample_conversations_json(tmp_path, sample_conversation):
     """Create a sample conversations.json file."""
     json_file = tmp_path / "conversations.json"
-    with open(json_file, "w") as f:
+    with open(json_file, "w", encoding="utf-8") as f:
         json.dump([sample_conversation], f)
     return json_file
 
@@ -65,7 +66,7 @@ async def test_process_chat_json(tmp_path, sample_conversations_json):
     # Check conversation file
     conv_path = tmp_path / "20250105-test-conversation.md"
     assert conv_path.exists()
-    content = conv_path.read_text()
+    content = conv_path.read_text(encoding="utf-8")
 
     # Check content formatting
     assert "### Human" in content
@@ -156,7 +157,7 @@ def test_import_conversation_with_attachments(tmp_path):
     }
 
     json_file = tmp_path / "with_attachments.json"
-    with open(json_file, "w") as f:
+    with open(json_file, "w", encoding="utf-8") as f:
         json.dump([conversation], f)
 
     # Set up environment
@@ -168,7 +169,7 @@ def test_import_conversation_with_attachments(tmp_path):
 
     # Check attachment formatting
     conv_path = tmp_path / "conversations/20250105-test-with-attachments.md"
-    content = conv_path.read_text()
+    content = conv_path.read_text(encoding="utf-8")
     assert "**Attachment: test.txt**" in content
     assert "```" in content
     assert "Test file content" in content

{basic_memory-0.12.1 → basic_memory-0.12.3}/tests/cli/test_import_claude_projects.py

@@ -1,6 +1,7 @@
 """Tests for import_claude_projects command."""
 
 import json
+
 import pytest
 from typer.testing import CliRunner
 
@@ -43,7 +44,7 @@ def sample_project():
 def sample_projects_json(tmp_path, sample_project):
     """Create a sample projects.json file."""
     json_file = tmp_path / "projects.json"
-    with open(json_file, "w") as f:
+    with open(json_file, "w", encoding="utf-8") as f:
         json.dump([sample_project], f)
     return json_file
 
@@ -70,14 +71,14 @@ async def test_process_projects_json(tmp_path, sample_projects_json):
     # Check document files
     doc1 = project_dir / "docs/test-document.md"
     assert doc1.exists()
-    content1 = doc1.read_text()
+    content1 = doc1.read_text(encoding="utf-8")
     assert "# Test Document" in content1
     assert "This is test content" in content1
 
     # Check prompt template
     prompt = project_dir / "prompt-template.md"
     assert prompt.exists()
-    prompt_content = prompt.read_text()
+    prompt_content = prompt.read_text(encoding="utf-8")
     assert "# Test Prompt" in prompt_content
     assert "This is a test prompt" in prompt_content
 
@@ -160,7 +161,7 @@ def test_import_project_without_prompt(tmp_path):
     }
 
     json_file = tmp_path / "no_prompt.json"
-    with open(json_file, "w") as f:
+    with open(json_file, "w", encoding="utf-8") as f:
         json.dump([project], f)
 
     # Set up environment

{basic_memory-0.12.1 → basic_memory-0.12.3}/tests/cli/test_import_memory_json.py

@@ -1,6 +1,7 @@
 """Tests for import_memory_json command."""
 
 import json
+
 import pytest
 from typer.testing import CliRunner
 
@@ -35,7 +36,7 @@ def sample_entities():
 def sample_json_file(tmp_path, sample_entities):
     """Create a sample memory.json file."""
     json_file = tmp_path / "memory.json"
-    with open(json_file, "w") as f:
+    with open(json_file, "w", encoding="utf-8") as f:
         for entity in sample_entities:
             f.write(json.dumps(entity) + "\n")
     return json_file
@@ -55,7 +56,7 @@ async def test_process_memory_json(tmp_path, sample_json_file):
     # Check file was created
     entity_file = tmp_path / "test/test_entity.md"
     assert entity_file.exists()
-    content = entity_file.read_text()
+    content = entity_file.read_text(encoding="utf-8")
     assert "Test observation 1" in content
     assert "Test observation 2" in content
     assert "test_relation [[related_entity]]" in content
@@ -120,7 +121,7 @@ def test_import_json_command_handle_old_format(tmp_path):
     ]
 
     json_file = tmp_path / "old_format.json"
-    with open(json_file, "w") as f:
+    with open(json_file, "w", encoding="utf-8") as f:
         for item in old_format:
             f.write(json.dumps(item) + "\n")
 

{basic_memory-0.12.1 → basic_memory-0.12.3}/tests/markdown/test_markdown_processor.py

@@ -8,10 +8,10 @@ from pathlib import Path
 
 import pytest
 
-from basic_memory.markdown.markdown_processor import MarkdownProcessor, DirtyFileError
+from basic_memory.markdown.markdown_processor import DirtyFileError, MarkdownProcessor
 from basic_memory.markdown.schemas import (
-    EntityMarkdown,
     EntityFrontmatter,
+    EntityMarkdown,
     Observation,
     Relation,
 )
@@ -41,7 +41,7 @@ async def test_write_new_minimal_file(markdown_processor: MarkdownProcessor, tmp
     await markdown_processor.write_file(path, markdown)
 
     # Read back and verify
-    content = path.read_text()
+    content = path.read_text(encoding="utf-8")
     assert "---" in content  # Has frontmatter
     assert "type: note" in content
     assert "permalink: test" in content
@@ -90,7 +90,7 @@ async def test_write_new_file_with_content(markdown_processor: MarkdownProcessor
     await markdown_processor.write_file(path, markdown)
 
     # Read back and verify
-    content = path.read_text()
+    content = path.read_text(encoding="utf-8")
 
     # Check content preserved exactly
     assert "# Custom Title" in content
@@ -169,7 +169,7 @@ async def test_dirty_file_detection(markdown_processor: MarkdownProcessor, tmp_p
     checksum = await markdown_processor.write_file(path, initial)
 
     # Modify file directly
-    path.write_text(path.read_text() + "\nModified!")
+    path.write_text(path.read_text(encoding="utf-8") + "\nModified!")
 
     # Try to update with old checksum
     update = EntityMarkdown(