Conversation
Add --agent parameter to configure default agent_id and auto-generate user_id for memory operations. This simplifies usage by eliminating the need to specify these parameters in each tool call. When configured via --agent: - agent_id defaults to the configured agent - user_id defaults to "user_of_<agent_id>"
- Consolidate search_memory and recall_context into unified query_memory - Add list_memories tool for browsing memory overview - Add min_salience parameter for importance-based filtering - Update parameter names for consistency (limit → k) - Improve get_memory implementation with proper ID lookup
Add clearer error messages for missing memory_id parameter, improve tool descriptions to guide users, and introduce a new get_all_memories tool that simplifies retrieving all memories.
- Increase default list limit from 20 to 100 with max of 1000 - Remove get_all_memories tool (redundant with updated list_memories) - Simplify tool descriptions for clarity - Update schema validation for list_memories limit parameter
The cortex-mem-tools module consolidates common memory operations used by both cortex-mem-mcp and cortex-mem-rig. This removes duplicate code and provides a unified interface for memory storage, querying, listing, and retrieval operations.
This introduces a new shared module that provides unified memory operations to eliminate code duplication between cortex-mem-rig and cortex-mem-mcp. The module includes: - MemoryOperations struct for core memory handling - Common error types and result handling - Unified request/response data structures - Helper
Extract common argument mapping logic and tool definitions into cortex-mem-tools to eliminate code duplication between cortex-mem-mcp and cortex-mem-rig. This removes the large map_to_payload function and inline tool definitions from the MCP service, replacing them with shared utilities.
This commit adds a new file `mcp_tools.rs` containing MCP tool definitions for memory operations including store, query, list, and get memory. It also provides utilities for mapping MCP arguments to internal payloads and converting error types to MCP error codes.
The cortex-mem-rig crate has been refactored to provide a more consistent interface with cortex-mem-mcp. The single multi-action tool has been split into four distinct tools that mirror the MCP protocol tools: - StoreMemoryTool for storing new memories - QueryMemoryTool for searching memories using semantic similarity - ListMemoriesTool for listing memories with filtering - GetMemoryTool for retrieving a specific memory by ID The old MemoryTool is deprecated but still functional for backward compatibility. This change improves type safety and provides a cleaner, more focused interface for each memory operation.
The search API now separates the query string from other search parameters when calling the memory service. Added comprehensive logging throughout the memory service for better debugging. Error messages are now in Chinese to match the existing localization.
Clean up client code by removing debug console.log statements and mock data functionality. Simplifies the API client and page component logic to focus on production behavior only.
- Replace mock data with actual API calls in dashboard and monitor pages - Add comprehensive health checking with latency tracking and timeout controls - Update proxy configuration to target correct backend port (3000) - Improve error handling and loading states throughout the application - Enhance system status display with detailed connection information
Change service detection logic to use API endpoint response as the primary determinant of service availability. Health check is now secondary and its failure doesn't affect service status if API is accessible.
Added formatDate function to display Chinese localized dates and removed the unused actions column from the memories table.
Replace Set-based selection tracking with a reactive Map that directly maps memory IDs to their selected state. This improves reactivity and simplifies checkbox bindings by eliminating the need for the isSelected function.
- Remove batchMark function and its button from UI - Replace individual delete calls with batchDelete API call
- Extract memory IDs before delete operation for batch API
Implement pagination with 20 items per page, including page navigation, current page highlighting, and automatic reset to first page when filtering or sorting. Update selection logic to work with paginated data and display appropriate pagination information.
The memory browser now displays truncated content in the table with a click-to-view option. Clicking on any memory entry opens a modal showing the complete content in a well-formatted view. This improves usability when dealing with long memory entries while maintaining a clean table layout.
Add Chart.js integration for analytics visualization Update status color logic for dark mode compatibility Extend memory ID display in monitor logs Delete Litho documentation files Update analysis summaries</think> Refine analytics page with Chart.js visualization and status colors - Remove light theme background from status color functions - Increase memory ID substring display in monitor logs - Add Chart.js integration for trend visualization - Update analytics data structure for chart rendering - Remove Litho documentation files - Update project analysis summaries</think> Refine analytics visualization and status display - Implement Chart.js line chart for memory trends with gradient fill - Update status color functions to remove light theme backgrounds - Extend memory ID display in monitor logs from 8 to 22 characters - Remove Litho documentation and update summary reports - Enhance analytics page with interactive chart and improved layout
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.