Merge branch 'main' into pr-252

Author: groksrc

CLA.md

@@ -1,34 +1,71 @@
-Developer Certificate of Origin
-Version 1.1
-https://developercertificate.org/
+# Contributor License Agreement
 
-Copyright (C) 2004, 2006 The Linux Foundation and its contributors.
+## Copyright Assignment and License Grant
 
-Everyone is permitted to copy and distribute verbatim copies of this
-license document, but changing it is not allowed.
+By signing this Contributor License Agreement ("Agreement"), you accept and agree to the following terms and conditions
+for your present and future Contributions submitted
+to Basic Machines LLC. Except for the license granted herein to Basic Machines LLC and recipients of software
+distributed by Basic Machines LLC, you reserve all right,
+title, and interest in and to your Contributions.
 
-Developer's Certificate of Origin 1.1
+### 1. Definitions
 
-By making a contribution to this project, I certify that:
+"You" (or "Your") shall mean the copyright owner or legal entity authorized by the copyright owner that is making this
+Agreement with Basic Machines LLC.
 
-(a) The contribution was created in whole or in part by me and I
-have the right to submit it under the open source license
-indicated in the file; or
+"Contribution" shall mean any original work of authorship, including any modifications or additions to an existing work,
+that is intentionally submitted by You to Basic
+Machines LLC for inclusion in, or documentation of, any of the products owned or managed by Basic Machines LLC (the "
+Work").
 
-(b) The contribution is based upon previous work that, to the best
-of my knowledge, is covered under an appropriate open source
-license and I have the right under that license to submit that
-work with modifications, whether created in whole or in part
-by me, under the same open source license (unless I am
-permitted to submit under a different license), as indicated
-in the file; or
+### 2. Grant of Copyright License
 
-(c) The contribution was provided directly to me by some other
-person who certified (a), (b) or (c) and I have not modified
-it.
+Subject to the terms and conditions of this Agreement, You hereby grant to Basic Machines LLC and to recipients of
+software distributed by Basic Machines LLC a perpetual,
+worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the
+Work, and to permit persons to whom the Work is furnished to do so.
 
-(d) I understand and agree that this project and the contribution
-are public and that a record of the contribution (including all
-personal information I submit with it, including my sign-off) is
-maintained indefinitely and may be redistributed consistent with
-this project or the open source license(s) involved.
+### 3. Assignment of Copyright
+
+You hereby assign to Basic Machines LLC all right, title, and interest worldwide in all Copyright covering your
+Contributions. Basic Machines LLC may license the
+Contributions under any license terms, including copyleft, permissive, commercial, or proprietary licenses.
+
+### 4. Grant of Patent License
+
+Subject to the terms and conditions of this Agreement, You hereby grant to Basic Machines LLC and to recipients of
+software distributed by Basic Machines LLC a perpetual,
+worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to
+make, have made, use, offer to sell, sell, import, and
+otherwise transfer the Work.
+
+### 5. Developer Certificate of Origin
+
+By making a Contribution to this project, You certify that:
+
+(a) The Contribution was created in whole or in part by You and You have the right to submit it under this Agreement; or
+
+(b) The Contribution is based upon previous work that, to the best of Your knowledge, is covered under an appropriate
+open source license and You have the right under that
+license to submit that work with modifications, whether created in whole or in part by You, under this Agreement; or
+
+(c) The Contribution was provided directly to You by some other person who certified (a), (b) or (c) and You have not
+modified it.
+
+(d) You understand and agree that this project and the Contribution are public and that a record of the Contribution (
+including all personal information You submit with
+it, including Your sign-off) is maintained indefinitely and may be redistributed consistent with this project or the
+open source license(s) involved.
+
+### 6. Representations
+
+You represent that you are legally entitled to grant the above license and assignment. If your employer(s) has rights to
+intellectual property that you create that
+includes your Contributions, you represent that you have received permission to make Contributions on behalf of that
+employer, or that your employer has waived such rights
+for your Contributions to Basic Machines LLC.
+
+---
+
+This Agreement is effective as of the date you first submit a Contribution to Basic Machines LLC.

src/basic_memory/api/routers/resource_router.py

@@ -188,7 +188,7 @@ async def write_resource(
                     "content_type": content_type,
                     "file_path": file_path,
                     "checksum": checksum,
-                    "updated_at": datetime.fromtimestamp(file_stats.st_mtime),
+                    "updated_at": datetime.fromtimestamp(file_stats.st_mtime).astimezone(),
                 },
             )
             status_code = 200
@@ -200,8 +200,8 @@ async def write_resource(
                 content_type=content_type,
                 file_path=file_path,
                 checksum=checksum,
-                created_at=datetime.fromtimestamp(file_stats.st_ctime),
-                updated_at=datetime.fromtimestamp(file_stats.st_mtime),
+                created_at=datetime.fromtimestamp(file_stats.st_ctime).astimezone(),
+                updated_at=datetime.fromtimestamp(file_stats.st_mtime).astimezone(),
             )
             entity = await entity_repository.add(entity)
             status_code = 201

src/basic_memory/config.py

@@ -351,15 +351,22 @@ def setup_basic_memory_logging():  # pragma: no cover
         # print("Skipping duplicate logging setup")
         return
 
-    # Check for console logging environment variable
-    console_logging = os.getenv("BASIC_MEMORY_CONSOLE_LOGGING", "false").lower() == "true"
+    # Check for console logging environment variable - accept more truthy values
+    console_logging_env = os.getenv("BASIC_MEMORY_CONSOLE_LOGGING", "false").lower()
+    console_logging = console_logging_env in ("true", "1", "yes", "on")
+
+    # Check for log level environment variable first, fall back to config
+    log_level = os.getenv("BASIC_MEMORY_LOG_LEVEL")
+    if not log_level:
+        config_manager = ConfigManager()
+        log_level = config_manager.config.log_level
 
     config_manager = ConfigManager()
     config = get_project_config()
     setup_logging(
         env=config_manager.config.env,
         home_dir=user_home,  # Use user home for logs
-        log_level=config_manager.config.log_level,
+        log_level=log_level,
         log_file=f"{DATA_DIR_NAME}/basic-memory-{process_name}.log",
         console=console_logging,
     )

src/basic_memory/importers/chatgpt_importer.py

@@ -93,7 +93,7 @@ def _format_chat_content(
                 break
 
         # Generate permalink
-        date_prefix = datetime.fromtimestamp(created_at).strftime("%Y%m%d")
+        date_prefix = datetime.fromtimestamp(created_at).astimezone().strftime("%Y%m%d")
         clean_title = clean_filename(conversation["title"])
 
         # Format content

src/basic_memory/importers/utils.py

@@ -43,13 +43,13 @@ def format_timestamp(timestamp: Any) -> str:  # pragma: no cover
         except ValueError:
             try:
                 # Try unix timestamp as string
-                timestamp = datetime.fromtimestamp(float(timestamp))
+                timestamp = datetime.fromtimestamp(float(timestamp)).astimezone()
             except ValueError:
                 # Return as is if we can't parse it
                 return timestamp
     elif isinstance(timestamp, (int, float)):
         # Unix timestamp
-        timestamp = datetime.fromtimestamp(timestamp)
+        timestamp = datetime.fromtimestamp(timestamp).astimezone()
 
     if isinstance(timestamp, datetime):
         return timestamp.strftime("%Y-%m-%d %H:%M:%S")

src/basic_memory/markdown/entity_parser.py

@@ -130,6 +130,6 @@ async def parse_file_content(self, absolute_path, file_content):
             content=post.content,
             observations=entity_content.observations,
             relations=entity_content.relations,
-            created=datetime.fromtimestamp(file_stats.st_ctime),
-            modified=datetime.fromtimestamp(file_stats.st_mtime),
+            created=datetime.fromtimestamp(file_stats.st_ctime).astimezone(),
+            modified=datetime.fromtimestamp(file_stats.st_mtime).astimezone(),
         )

src/basic_memory/markdown/plugins.py

@@ -8,56 +8,68 @@
 # Observation handling functions
 def is_observation(token: Token) -> bool:
     """Check if token looks like our observation format."""
+    import re
     if token.type != "inline":  # pragma: no cover
         return False
-
-    content = token.content.strip()
+    # Use token.tag which contains the actual content for test tokens, fallback to content
+    content = (token.tag or token.content).strip()
     if not content:  # pragma: no cover
         return False
-
     # if it's a markdown_task, return false
     if content.startswith("[ ]") or content.startswith("[x]") or content.startswith("[-]"):
         return False
-
-    has_category = content.startswith("[") and "]" in content
+    
+    # Exclude markdown links: [text](url)
+    if re.match(r"^\[.*?\]\(.*?\)$", content):
+        return False
+    
+    # Exclude wiki links: [[text]]
+    if re.match(r"^\[\[.*?\]\]$", content):
+        return False
+    
+    # Check for proper observation format: [category] content
+    match = re.match(r"^\[([^\[\]()]+)\]\s+(.+)", content)
     has_tags = "#" in content
-    return has_category or has_tags
+    return bool(match) or has_tags
 
 
 def parse_observation(token: Token) -> Dict[str, Any]:
     """Extract observation parts from token."""
-    # Strip bullet point if present
-    content = token.content.strip()
-
-    # Parse [category]
+    import re
+    # Use token.tag which contains the actual content for test tokens, fallback to content
+    content = (token.tag or token.content).strip()
+    
+    # Parse [category] with regex
+    match = re.match(r"^\[([^\[\]()]+)\]\s+(.+)", content)
     category = None
-    if content.startswith("["):
-        end = content.find("]")
-        if end != -1:
-            category = content[1:end].strip() or None  # Convert empty to None
-            content = content[end + 1 :].strip()
-
+    if match:
+        category = match.group(1).strip()
+        content = match.group(2).strip()
+    else:
+        # Handle empty brackets [] followed by content
+        empty_match = re.match(r"^\[\]\s+(.+)", content)
+        if empty_match:
+            content = empty_match.group(1).strip()
+    
     # Parse (context)
     context = None
     if content.endswith(")"):
         start = content.rfind("(")
         if start != -1:
             context = content[start + 1 : -1].strip()
             content = content[:start].strip()
-
+    
     # Extract tags and keep original content
     tags = []
     parts = content.split()
     for part in parts:
         if part.startswith("#"):
-            # Handle multiple #tags stuck together
             if "#" in part[1:]:
-                # Split on # but keep non-empty tags
                 subtags = [t for t in part.split("#") if t]
                 tags.extend(subtags)
             else:
                 tags.append(part[1:])
-
+    
     return {
         "category": category,
         "content": content,
@@ -72,14 +84,16 @@ def is_explicit_relation(token: Token) -> bool:
     if token.type != "inline":  # pragma: no cover
         return False
 
-    content = token.content.strip()
+    # Use token.tag which contains the actual content for test tokens, fallback to content
+    content = (token.tag or token.content).strip()
     return "[[" in content and "]]" in content
 
 
 def parse_relation(token: Token) -> Dict[str, Any] | None:
     """Extract relation parts from token."""
     # Remove bullet point if present
-    content = token.content.strip()
+    # Use token.tag which contains the actual content for test tokens, fallback to content
+    content = (token.tag or token.content).strip()
 
     # Extract [[target]]
     target = None
@@ -213,10 +227,12 @@ def relation_rule(state: Any) -> None:
                         token.meta["relations"] = [rel]
 
                 # Always check for inline links in any text
-                elif "[[" in token.content:
-                    rels = parse_inline_relations(token.content)
-                    if rels:
-                        token.meta["relations"] = token.meta.get("relations", []) + rels
+                else:
+                    content = token.tag or token.content
+                    if "[[" in content:
+                        rels = parse_inline_relations(content)
+                        if rels:
+                            token.meta["relations"] = token.meta.get("relations", []) + rels
 
     # Add the rule after inline processing
     md.core.ruler.after("inline", "relations", relation_rule)

src/basic_memory/mcp/tools/build_context.py

@@ -111,7 +111,7 @@ async def build_context(
             metadata=MemoryMetadata(
                 depth=depth or 1,
                 timeframe=timeframe,
-                generated_at=datetime.now(),
+                generated_at=datetime.now().astimezone(),
                 primary_count=0,
                 related_count=0,
                 uri=migration_status,  # Include status in metadata

src/basic_memory/models/knowledge.py

@@ -1,6 +1,7 @@
 """Knowledge graph models."""
 
-from datetime import datetime
+from datetime import datetime, timezone
+from basic_memory.utils import ensure_timezone_aware
 from typing import Optional
 
 from sqlalchemy import (
@@ -73,8 +74,8 @@ class Entity(Base):
     checksum: Mapped[Optional[str]] = mapped_column(String, nullable=True)
 
     # Metadata and tracking
-    created_at: Mapped[datetime] = mapped_column(DateTime)
-    updated_at: Mapped[datetime] = mapped_column(DateTime)
+    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now().astimezone())
+    updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now().astimezone(), onupdate=lambda: datetime.now().astimezone())
 
     # Relationships
     project = relationship("Project", back_populates="entities")
@@ -103,6 +104,16 @@ def relations(self):
     def is_markdown(self):
         """Check if the entity is a markdown file."""
         return self.content_type == "text/markdown"
+    
+    def __getattribute__(self, name):
+        """Override attribute access to ensure datetime fields are timezone-aware."""
+        value = super().__getattribute__(name)
+        
+        # Ensure datetime fields are timezone-aware
+        if name in ('created_at', 'updated_at') and isinstance(value, datetime):
+            return ensure_timezone_aware(value)
+        
+        return value
 
     def __repr__(self) -> str:
         return f"Entity(id={self.id}, name='{self.title}', type='{self.entity_type}'"

src/basic_memory/models/project.py

@@ -52,9 +52,9 @@ class Project(Base):
     is_default: Mapped[Optional[bool]] = mapped_column(Boolean, default=None, nullable=True)
 
     # Timestamps
-    created_at: Mapped[datetime] = mapped_column(DateTime, default=lambda: datetime.now(UTC))
+    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC))
     updated_at: Mapped[datetime] = mapped_column(
-        DateTime, default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC)
+        DateTime(timezone=True), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC)
     )
 
     # Define relationships to entities, observations, and relations