Add a retrieval_mode field ("semantic" or "text") to the output of all
five query-driven tools so callers can distinguish vector search from
Postgres full-text fallback without inspecting server logs.
Tools updated: search_thoughts, recall_context, get_project_context,
summarize_thoughts, and related_thoughts (semantic neighbours only;
omitempty so field is absent when include_semantic is false or no query
is provided for the non-mandatory-query tools).
The shared semanticSearch helper now returns the mode as a third return
value. All callers updated; fixes two compile errors left by the
previous worker (summarize.go and links.go were not capturing the new
return).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* Introduce project_personas table with foreign keys to projects and agent_personas
* Add project_skills table with foreign key to projects and agent_skills
* Include override boolean field in agent_persona_skills and project_skills
* Update schema and migration files to reflect new tables and fields
* Enhance CORS handling to reflect request origin
* Introduced AccessLogEntry type for logging access details
* Updated AccessTracker to maintain a recent activity log
* Modified Metrics to include recent activity log in response
* Added RecentActivityLog component to display logged activities
- Implemented TraitsTab.svelte to handle CRUD operations for agent traits.
- Integrated grid for displaying traits with context menu actions for add, edit, and delete.
- Added trait instruction editing functionality with a dedicated editor.
- Updated AdminShell to include PersonasPage for navigation.
- Enhanced AppSidebar with a new entry for Personas.
- Extended ShellPage type to include 'personas'.
- Defined new types for AgentPersona, AgentPart, and AgentTrait in types.ts.
- Created tables for agent_personas, agent_parts, agent_traits, and character_arcs.
- Established relationships between personas, parts, skills, guardrails, and traits.
- Added arc stages and their corresponding parts, along with a persona_arc table to track current stages.
- Implemented cascading delete rules for referential integrity.
- Added language_tags, library_tags, framework_tags, and domain_tags to agent skills.
- Introduced new commands: get_skill and get_guardrail for fetching specific skills and guardrails.
- Updated database schema and migration scripts to accommodate new fields.
- Enhanced skill listing functionality to support filtering by new tags.
- Improved error handling and response structures for skill-related operations.
* Update default values for metadata and messages columns in thoughts and chat_histories tables
* Change tags column type to text[] with default in learnings, plans, agent_skills, and agent_guardrails tables
* Adjust index creation for tags columns in learnings and plans tables
All internal entity lookups now use bigserial primary keys (int64) while
GUIDs are retained for external/public identification. Updated store
functions (TouchProject, UpdateThoughtMetadata, AddThoughtAttachment) to
query by id instead of guid, added GetThoughtByID, changed semanticSearch
and all tool helpers to use *int64 project IDs, and updated retry/backfill
workers to use int64 thought IDs throughout.
* Implement ContentEditorField for inline editing of content
* Create ContentEditorModal for editing content in a modal
* Introduce FormerShell for managing forms related to skills and thoughts
* Enhance SkillsPage and ThoughtsPage with new components for better content management
* add public status handler and response types
* modify status API to restrict access and update client tracking
* adjust UI components to display public status information
* update routing to include public status endpoint
* Corrected "Advanced Module Control System" to "Avalon Memory Control Service" in documentation and UI components.
* Added status handling to the LoginInfoPanel and LoginPage components.
* Implemented new endpoints for robots.txt and llms.txt.
* Add tool tracking to AccessTracker and metrics
* Update tests to validate tool tracking functionality
* Modify middleware to record tool usage
* Enhance observability with tool context
* Update UI to display unique tools in metrics
* Implement maintenance page with task and log display
* Add backfill and metadata retry functionality
* Integrate grid component for project display in thoughts page
* Update types for maintenance tasks and logs
* Enhance sidebar and shell for new maintenance navigation
* Update project creation and retrieval to use generated models
* Modify skill addition and listing to utilize generated models
* Refactor thought handling to incorporate generated models
* Adjust tool annotations to align with new model structure
* Update API calls in the UI to use new ResolveSpec-based endpoints
* Enhance stats retrieval logic to aggregate thought metadata
* Add OAuth login handling in app and UI components
* Create new components for login and dashboard pages
* Refactor sidebar and navigation structure
* Introduce types for access entries and status responses
* Add function to extract MCP session ID from request headers and query parameters
* Update access log to include MCP session ID
fix(cli): simplify project lookup logic
* Refactor project retrieval to prefer GUID lookup when input is a valid UUID
* Introduce separate functions for fetching projects by GUID and name
* Introduced a new flag `--verbose` to enable detailed logging.
* Implemented logging for connection events in SSE and stdio commands.
* Added a utility function to handle verbose logging.
* Implement tests for migrating configuration from v1 to v2 for the litellm provider.
* Validate the structure and values of the migrated configuration.
* Ensure migration rejects newer versions of the configuration.
fix(validate): enhance AI provider validation logic
* Consolidate provider validation into a dedicated method.
* Ensure at least one provider is specified and validate its type.
* Check for required fields based on provider type.
fix(mcpserver): update tool set to use new enrichment tool
* Replace RetryMetadataTool with RetryEnrichmentTool in the ToolSet.
fix(tools): refactor tools to use embedding and metadata runners
* Update tools to utilize EmbeddingRunner and MetadataRunner instead of Provider.
* Adjust method calls to align with the new runner interfaces.
* Implement QueueThought method in BackfillTool for embedding generation
* Update CaptureTool to utilize embedding queuer for failed embeddings
* Add EmbeddingStatus field to Thought type for tracking embedding state
- Introduced new tools for managing agent skills and guardrails, including add, remove, and list operations.
- Updated README.md to document new commands and usage patterns for skills and guardrails.
- Enhanced server configuration to support longer read and write timeouts.
- Increased maximum upload size for files to 100 MB and adjusted related configurations.
- Created database migrations for agent skills, guardrails, and their associations with projects.
- Updated relevant code files to integrate new skills and guardrails into the application logic.
- Added file upload handler to process both multipart and raw file uploads.
- Implemented parsing logic for upload requests, including handling file metadata.
- Introduced SaveFileDecodedInput structure for handling decoded file uploads.
- Created unit tests for file upload parsing and validation.
feat: add metadata retry configuration and functionality
- Introduced MetadataRetryConfig to the application configuration.
- Implemented MetadataRetryer to handle retrying metadata extraction for thoughts.
- Added new tool for retrying failed metadata extractions.
- Updated thought metadata structure to include status and timestamps for metadata processing.
fix: enhance metadata normalization and error handling
- Updated metadata normalization functions to track status and errors.
- Improved handling of metadata extraction failures during thought updates and captures.
- Ensured that metadata status is correctly set during various operations.
refactor: streamline file saving logic in FilesTool
- Refactored Save method in FilesTool to utilize new SaveDecoded method.
- Simplified project and thought ID resolution logic during file saving.
- Implement maintenance tool for adding, logging, and retrieving tasks
- Create meals tool for managing recipes, meal plans, and shopping lists
- Introduce reparse metadata tool for updating thought metadata
- Add household knowledge, home maintenance, family calendar, meal planning, and professional CRM database migrations
- Grant necessary permissions for new database tables
- Add OAuth 2.0 support with authorization code flow and dynamic client registration.
- Introduce new handlers for OAuth metadata, client registration, authorization, and token issuance.
- Enhance authentication middleware to support OAuth client credentials.
- Create in-memory stores for authorization codes and tokens.
- Update configuration to include OAuth client details.
- Ensure validation checks for OAuth clients in the configuration.
warkanum
