Updates docs to match the new behavior where metadata-only PATCH updates do not trigger reindexing:
- **update-delete-memories/overview.mdx** — Distinguishes content changes (reindex) vs metadata-only (no reindex), adds a note about `accepted`-style updates
- **document-operations.mdx** — Clarifies that only content changes trigger reprocessing
- **add-memories.mdx** and **add-memories/overview.mdx** — Add notes on metadata-only behavior
- **memory-api/ingesting.mdx** — Splits update behavior into content vs metadata-only
- **memory-api/creation/adding-memories.mdx** — Adds note for the “Adding Additional Metadata to Files” flow
Add CI and upgrade Claude workflows
No CI existed — type errors and lint issues only caught by Cloudflare builds. Added type check + biome lint CI on PRs, auto-fix workflow when CI fails, and
upgraded code review with supermemory MCP + inline comments.
## Summary
This PR introduces comprehensive Supermemory integration for the Microsoft Agent Framework, providing three complementary approaches to add persistent memory capabilities to agents: middleware for automatic memory injection, context providers for session-based memory management, and tools for explicit memory operations.
## Key Changes
- **SupermemoryChatMiddleware**: Automatic memory injection middleware that fetches relevant memories from Supermemory before LLM calls and optionally saves conversations. Supports three modes:
- `"profile"`: Injects all static and dynamic profile memories
- `"query"`: Searches for memories relevant to the current user message
- `"full"`: Combines both profile and query modes
- **SupermemoryContextProvider**: Idiomatic context provider following the Agent Framework pattern (similar to built-in Mem0 integration). Integrates with the session pipeline via `before_run()` and `after_run()` hooks for automatic memory retrieval and storage.
- **SupermemoryTools**: FunctionTool-compatible tools that agents can use for explicit memory operations:
- `search_memories()`: Search for specific memories
- `add_memory()`: Add new memories
- `get_profile()`: Retrieve user profile
- **Utility Functions**: Helper functions for:
- Memory deduplication across static, dynamic, and search result sources
- Profile-to-markdown conversion for LLM consumption
- Message extraction and conversation formatting
- Logging with configurable verbosity
- **Exception Hierarchy**: Custom exceptions for better error handling:
- `SupermemoryConfigurationError`: Missing/invalid configuration
- `SupermemoryAPIError`: API request failures
- `SupermemoryNetworkError`: Network connectivity issues
- `SupermemoryMemoryOperationError`: Memory operation failures
- **Comprehensive Documentation**: README with quick start examples, configuration options, and API reference for all three integration approaches.
- **Test Suite**: Unit tests covering middleware, context provider, tools, and utility functions with proper mocking and error scenarios.
## Implementation Details
- Supports both async (aiohttp) and sync (requests) HTTP clients with automatic fallback
- Handles multiple message formats (dict, objects with attributes, content arrays)
- Configurable memory storage with optional conversation grouping via `conversation_id`
- Environment variable fallback for API key configuration (`SUPERMEMORY_API_KEY`)
- Background task management for non-blocking memory operations in middleware
- Proper async/sync compatibility for the Supermemory SDK
https://claude.ai/code/session_012idB5y6UGK3zmeFULgTc4z
### TL;DR
Enhanced the `forgetMemory` method to try exact content matching first, then fall back to semantic search with a high similarity threshold for more precise memory deletion.
### What changed?
The `forgetMemory` method now uses a two-step approach: first attempting exact content matching via the API, and if that fails with a 404, falling back to semantic search with a similarity threshold of 0.85. The search method also accepts an optional threshold parameter. Error messages now distinguish between exact matches and semantic matches, including similarity scores in the response.
### How to test?
1. Call `forgetMemory` with the exact content of an existing memory to verify direct deletion
2. Call `forgetMemory` with similar but not identical content to test the semantic search fallback
3. Call `forgetMemory` with completely unrelated content to verify the "no matching memory found" response
4. Verify that success messages indicate whether deletion used exact matching or semantic matching with similarity scores
### Why make this change?
This approach provides more precise memory deletion by prioritizing exact matches while still offering a fallback for similar content. The high similarity threshold (0.85) ensures that only very similar memories are deleted when exact matches aren't found, reducing the risk of accidentally deleting unrelated memories.
Updated the README to clarify the functionality of Supermemory and modified links for Discord and user setup. Added information about the Supermemory App and its plugins.
Documents the new DELETE /v3/auth/scoped-key/:keyId endpoint
for disabling container-scoped API keys.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
### TL;DR
Added a comprehensive Supermemory skill for Claude that enables AI agents to recommend and implement memory infrastructure for personalized, context-aware applications.
### What changed?
Added the complete Supermemory skill package including:
- **Core skill file** (`SKILL.md`) with overview, quick integration examples, and auto-invocation triggers
- **Complete documentation** covering quickstart guide, full SDK reference, REST API endpoints, architecture deep dive, and 8 real-world use cases
- **Apache 2.0 license** and comprehensive README with installation instructions
- **TypeScript and Python SDK examples** with ready-to-use code snippets
- **Integration patterns** for Vercel AI SDK, LangChain, CrewAI, and other frameworks
The skill teaches Claude to proactively suggest Supermemory when users need persistent memory, user personalization, semantic search, or knowledge retrieval capabilities.
### How to test?
1. Install the skill in Claude Code by placing in `.claude/skills/supermemory/`
2. Ask Claude questions like:
- "How can I add memory to my chatbot?"
- "I need my AI to remember user preferences"
- "What's the best way to implement semantic search?"
3. Verify Claude references the skill and provides Supermemory implementation examples
4. Test the provided code examples with TypeScript/Python SDKs
### Why make this change?
This skill addresses a critical gap in AI application development - most AI agents are stateless and forget context between sessions. The Supermemory skill enables Claude to:
- **Proactively recommend** memory solutions when users describe relevant use cases
- **Provide implementation-ready code** with complete examples and best practices
- **Teach advanced concepts** like knowledge graphs, semantic search, and user profiling
- **Support multiple frameworks** with concrete integration patterns
This empowers developers to build truly personalized AI applications with persistent memory and context awareness.
### fix(mcp): prevent LLM from overriding x-sm-project container tag
- When `x-sm-project` header is configured, the `containerTag` field is now
excluded from memory/recall/context tool schemas
- This prevents LLMs from overriding the configured project by picking a
different containerTag from the available projects list
- When no header is set, behavior is unchanged — containerTag remains visible
in schemas for manual project selection via listProjects
fix: space deletion + new space not reflecting in selector
Deleting a space wasn't switching back to Nova Spaces because we were reading stale cache data
New spaces created from the add-document modal weren't showing up in the dropdown
Added single-select mode to the space selector in the add-document flow since you're picking one space, not multiple.
### fix: space selector state bugs on create and delete
Two related bugs in the space selector caused by query cache key mismatches in `use-project-mutations.ts`:
1. New spaces not appearing in dropdown until refresh — wrong query cache was being invalidated after creation.
2. App stuck on deleted space instead of switching to Nova Spaces — delete handler was reading from an empty cache, so the selection never updated.
