feat(chat): display token usage and tps in message footers (#1094)

app/src/main/java/com/m57/hermescontrol/data/model/SessionMessagesResponse.kt

@@ -4,6 +4,7 @@ import kotlinx.serialization.Serializable
 import kotlinx.serialization.json.JsonElement
 import kotlinx.serialization.json.JsonPrimitive
 import kotlinx.serialization.json.doubleOrNull
+import kotlinx.serialization.json.intOrNull
 import kotlinx.serialization.json.longOrNull
 
 @Serializable
@@ -50,10 +51,18 @@ data class SessionMessage(
     val display_kind: String? = null,
     /** Display-only metadata for the marker (e.g. delegation result counts). */
     val display_metadata: JsonElement? = null,
+    /** Token count recorded by the backend. */
+    val token_count: JsonElement? = null,
 ) {
     val timestampText: String?
         get() = (timestamp as? JsonPrimitive)?.content
 
+    val tokenCount: Int?
+        get() {
+            val prim = token_count as? JsonPrimitive ?: return null
+            return prim.intOrNull ?: prim.content.toIntOrNull()
+        }
+
     val timestampEpochMs: Long?
         get() {
             val prim = timestamp as? JsonPrimitive ?: return null

app/src/main/java/com/m57/hermescontrol/data/model/UsageSnapshotResponse.kt

@@ -20,6 +20,8 @@ data class UsageSnapshotResponse(
     val contextMax: Long? = null,
     /** Cumulative session total tokens. */
     val totalTokens: Long? = null,
+    /** Rolling tokens-per-second generation speed. */
+    val avgTps: Double? = null,
 )
 
 /**
@@ -38,5 +40,6 @@ fun parseUsageSnapshot(result: Any?): UsageSnapshotResponse? {
         contextUsed = (usageMap["context_used"] as? Number)?.toLong(),
         contextMax = (usageMap["context_max"] as? Number)?.toLong(),
         totalTokens = (usageMap["total"] as? Number)?.toLong(),
+        avgTps = (usageMap["avg_tps"] as? Number)?.toDouble(),
     )
 }