Merged
Conversation
Adds robust timeout detection and logging for Qdrant queries, introduces concurrency control with a semaphore, and ensures partial results are returned on timeouts. The Qdrant client manager now supports configurable HTTP timeouts via environment variables. The search implementation clamps rerank timeouts and adds fallback to learning reranker results if subprocess reranking fails. Remote upload client now consistently uses container paths for cache lookups and updates, improving cache consistency. Test cases are updated to use asyncio.run for coroutine execution.
Adds automatic storage of successful context_answer responses as memories in context_answer.py, configurable via environment variables. Updates mcp_indexer_server.py to support memory blending in code_search via new parameters (include_memories, memory_weight, per_source_limits). Adjusts Helm values for resource requests/limits and autoscaling for several services. Also refines tool routing in mcpServer.js to match any 'memory' prefix.
Added comprehensive TOOLS_METADATA for all search/answer tools and enriched the /readyz endpoint with tool metadata. Expanded and clarified docstrings for all major API functions to provide detailed usage, parameters, and examples. Updated .indexignore and retrieval filters to exclude common build, dist, and IDE artifacts. Increased max_neighbors in context_answer for improved subgraph context injection. Added more session default parameters to set_session_defaults.
Introduces an ASGI middleware to extract the Authorization header from HTTP requests and store the token in a context variable, enabling stateless token-based authentication. Updates mcp_auth.py to support direct admin/shared token authentication and modifies both mcp_indexer_server.py and mcp_memory_server.py to inject the middleware for non-stdio transports.
Introduces a new codebase volume to Kubernetes and Helm deployment templates for MCP memory services, ensuring proper mounting and separation of code metadata. Enhances authentication logic in mcp_auth.py to support auto-fallback to shared tokens and adds a new /auth/validate endpoint in upload_service.py for remote session validation, improving distributed authentication support.
🤖 Augment PR SummarySummary: This PR improves MCP server ergonomics and deployment defaults, while adding better auth/memory integration and hardening Qdrant/search behavior. Key Changes:
🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
Replaced deprecated 'get_event_loop().run_until_complete' with 'asyncio.run' in test_context_answer_path_mention.py and test_env_behavior.py. Updated docstring assertion in test_globs_and_snippet.py to match new content. Modified _DummyQdrantClient in test_qdrant_client_manager_pool.py to accept additional kwargs for improved flexibility.
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.