feat(mcp): wire brain_context tool

Returns top-N relevant brain entries for a project context. Combines
BM25 hits on project name with 2-hop graph expansion via Track A's
graphstore (when BRAIN_GRAPH_ENABLED). Closes hyperguild#28.

Notes on implementation choices that deviate slightly from the spec:
- Excerpt length: 200 chars per spec (vs the 300 used by search.Result).
  truncateExcerpt clamps the already-stripped BM25 excerpt; graph-only
  neighbours load their excerpt from disk via a private readExcerpt
  helper (search.hydrate is unexported).
- Graph scoring: 0.6 / max(1, distance) per neighbour, so distance-1
  contributes 0.6 and distance-2 contributes 0.3. BM25 hits decay
  linearly from 3.0 (rank-0) to 1.0 (rank-2), giving BM25 hits a
  natural ceiling above pure-graph hits while still letting a doc
  surfaced via both edge types outrank a BM25-only one.
- Test placement: package mcp (internal) rather than mcp_test, because
  graphReader is unexported and WithGraph only accepts *PGStore; an
  internal test can install a dual-interface fake directly on s.graph
  without spinning up postgres.

Bump-Type: minor

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

ingestion/internal/mcp/server.go

@@ -1,6 +1,7 @@
 // Package mcp implements an MCP HTTP handler for the ingestion service.
 // Exposed tools: brain_query, brain_write, brain_index, brain_tunnel,
-// brain_ingest, brain_ingest_raw, brain_answer, brain_classify, session_log.
+// brain_ingest, brain_ingest_raw, brain_answer, brain_classify,
+// brain_graph, brain_context, session_log.
 package mcp
 
 import (
@@ -192,6 +193,8 @@ func (s *Server) handleCall(ctx context.Context, name string, args json.RawMessa
 		return s.brainClassify(ctx, args)
 	case "brain_graph":
 		return s.brainGraph(ctx, args)
+	case "brain_context":
+		return s.brainContext(ctx, args)
 	default:
 		return nil, fmt.Errorf("unknown tool: %s", name)
 	}