fix: prevent MCP server hanging by adding concurrency, timeouts, and context propagation (#45)

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

internal/embedding/model.go

@@ -2,6 +2,7 @@
 package embedding
 
 import (
+	"context"
 	"fmt"
 	"sync"
 )
@@ -44,6 +45,14 @@ type EmbeddingModel interface {
 	// EmbedBatch generates embeddings for multiple texts.
 	EmbedBatch(texts []string) ([][]float32, error)
 
+	// EmbedWithContext generates an embedding for a single text with context-aware cancellation.
+	// The context controls mutex acquisition timeout — if ctx is cancelled while waiting
+	// for the model lock, the call returns immediately with ctx.Err().
+	EmbedWithContext(ctx context.Context, text string) ([]float32, error)
+
+	// EmbedBatchWithContext generates embeddings for multiple texts with context-aware cancellation.
+	EmbedBatchWithContext(ctx context.Context, texts []string) ([][]float32, error)
+
 	// Close releases model resources.
 	Close() error
 }