mirror of
https://github.com/lukaszraczylo/claude-mnemonic.git
synced 2026-06-05 23:03:55 +00:00
lukaszraczylo
29d57857ff
Root cause: synchronous MCP request processing combined with missing context propagation to the embedding layer caused indefinite hangs when ONNX inference was slow or the database was contended. Changes: - MCP server: dispatch each request in its own goroutine with semaphore (cap 10) and WaitGroup for clean shutdown drain - Embedding: add context-aware mutex acquisition (acquireMutex) so callers can bail out instead of blocking forever on a stuck ONNX model - Vector client: propagate context through getOrComputeEmbedding and replace bare RLock() calls with context-aware acquireRLockWithContext - Worker handlers: add 15s request-scoped timeouts to all search/context handlers (handleSearchByPrompt, handleContextInject, handleFileContext, handleContextCount, handleGetObservations/Summaries/Prompts) - Worker HTTP server: set WriteTimeout=60s (was 0); SSE endpoint extends deadline per-request via http.ResponseController Fixes #45