feat(mcp): expose brain_graph tool — neighbors, subgraph, path

Commit 3 of Track A. The MCP server now publishes a new tool that
opens the brain knowledge graph (entities + wikilink edges) for
external consumers (claude.ai connectors, gitea-mcp, agentsquad).

- tools_graph.go: brain_graph handler dispatches by op:
    neighbors  — 1-hop outgoing from slug, optional edge_type filter
    subgraph   — every reachable slug within depth hops (≤6)
    path       — shortest directed path src→dst within depth (≤8)
  Returns slug + entity metadata + edge_type + hop distance.

- server.go: handleCall routes "brain_graph" to brainGraph.

- handlers.go: tool descriptor with the op enum + per-op required
  fields documented in the description.

- server_test.go: TestServerToolsList expects brain_graph in the
  listing.

The tool returns an error when BRAIN_GRAPH_ENABLED is unset — same
shape as brain_answer when the answer LLM is unconfigured.

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

ingestion/internal/mcp/server.go

@@ -190,6 +190,8 @@ func (s *Server) handleCall(ctx context.Context, name string, args json.RawMessa
 		return s.brainAnswer(ctx, args)
 	case "brain_classify":
 		return s.brainClassify(ctx, args)
+	case "brain_graph":
+		return s.brainGraph(ctx, args)
 	default:
 		return nil, fmt.Errorf("unknown tool: %s", name)
 	}