feat(config): add maxRequestBytes for the unified body cap

The unified chat and embeddings routes reject bodies above 4 MiB. Long
agent sessions exceed this limit and receive a 413.

Add Config.maxRequestBytes. Zero or a negative value keeps the 4 MiB
default. A positive value raises the cap, clamped to 64 MiB.

An adversarial body decodes to about 12x live heap. An operator who raises
the cap must also set maxInFlightBodyRequests and the pod memory limit.

llmgateway.go

@@ -127,6 +127,12 @@ type Config struct {
 	// exposure (GET /admin/api/targets, llmgateway_target_healthy) stay
 	// on unconditionally regardless of this block's presence.
 	TargetHealth TargetHealthConfig `json:"targetHealth"`
+	// MaxRequestBytes raises the unified chat/embeddings body cap above the
+	// default maxUnifiedRequestBytes (4MiB), clamped to
+	// maxExplicitUnifiedRequestBytes. 0 or negative keeps the default. Size
+	// maxInFlightBodyRequests and the pod memory limit to match: an
+	// adversarial body decodes to ~12x live heap.
+	MaxRequestBytes int64 `json:"maxRequestBytes,omitempty"`
 	// MaxInFlightBodyRequests caps how many unified and media JSON/
 	// multipart requests (routes_unified.go's runUnified via
 	// readAndDecodeUnifiedBody; routes_media.go's decodeMediaJSONRequest/
@@ -771,6 +777,7 @@ type Gateway struct {
 	next                          http.Handler
 	events                        *eventLog
 	bodyAdmission                 chan struct{}
+	unifiedRequestBytes           int64
 	teeBudget                     *teeBudget
 	fanoutGate                    chan struct{}
 	failoverHealth                *requestHealthTracker
@@ -1061,6 +1068,13 @@ func newGateway(ctx context.Context, next http.Handler, config *Config, name str
 		}
 	}
 	g.bodyAdmission = make(chan struct{}, bodyAdmissionCap)
+	g.unifiedRequestBytes = maxUnifiedRequestBytes
+	if config.MaxRequestBytes > 0 {
+		g.unifiedRequestBytes = config.MaxRequestBytes
+		if g.unifiedRequestBytes > maxExplicitUnifiedRequestBytes {
+			g.unifiedRequestBytes = maxExplicitUnifiedRequestBytes
+		}
+	}
 	g.teeBudget = newTeeBudget(maxAccountingTeeTotalBytes)
 	g.fanoutGate = make(chan struct{}, mcpFederatedFanoutGlobalConcurrency)