feat: checkpoint batching and release-gate stories

.scratch/distributed-gguf-runtime/evidence/DGR-013/results.json

@@ -0,0 +1,135 @@
+{
+  "schema_version": 1,
+  "evidence_kind": "synthetic-unit",
+  "model": {
+    "architecture": "dense-llama",
+    "n_layers": 6,
+    "vocab": 48,
+    "hidden": 32
+  },
+  "scenarios": [
+    {
+      "scenario": "clean",
+      "status": "completed",
+      "tokens": 8,
+      "matches_reference": true,
+      "kv_released": false
+    },
+    {
+      "scenario": "deadline",
+      "status": "failed",
+      "failure_kind": "deadline-exceeded",
+      "tokens": 2,
+      "kv_released": true
+    },
+    {
+      "scenario": "heartbeat_loss",
+      "status": "failed",
+      "failure_kind": "heartbeat-lost",
+      "tokens": 3,
+      "kv_released": true
+    },
+    {
+      "scenario": "cancel",
+      "status": "cancelled",
+      "failure_kind": "cancelled",
+      "tokens": 3,
+      "kv_released": true
+    },
+    {
+      "scenario": "worker_death",
+      "status": "unverified",
+      "failure_kind": "worker-death",
+      "tokens": 3,
+      "restartable": true,
+      "kv_released": true
+    },
+    {
+      "scenario": "stream_reset",
+      "status": "failed",
+      "failure_kind": "stream-reset",
+      "restartable": true
+    },
+    {
+      "scenario": "stale_epoch",
+      "status": "failed",
+      "failure_kind": "stale-epoch"
+    },
+    {
+      "scenario": "cache_miss",
+      "status": "failed",
+      "failure_kind": "cache-miss",
+      "tokens": 4,
+      "restartable": true
+    },
+    {
+      "scenario": "alpha_failover",
+      "final_status": "completed",
+      "final_epoch": 1,
+      "restarts": 1,
+      "restarted_from_token_zero": true,
+      "old_epoch_stale": true,
+      "attempt_statuses": [
+        "unverified",
+        "completed"
+      ]
+    }
+  ],
+  "work_ledger": {
+    "schema_version": 1,
+    "records": [
+      {
+        "session_id": "clean",
+        "route_epoch": 0,
+        "status": "completed",
+        "tokens": 8,
+        "failure_kind": null,
+        "detail": "",
+        "billable": true
+      },
+      {
+        "session_id": "cancel",
+        "route_epoch": 0,
+        "status": "cancelled",
+        "tokens": 3,
+        "failure_kind": "cancelled",
+        "detail": "operation cancelled: client-hangup",
+        "billable": false
+      },
+      {
+        "session_id": "worker",
+        "route_epoch": 0,
+        "status": "unverified",
+        "tokens": 3,
+        "failure_kind": "worker-death",
+        "detail": "worker died mid-step",
+        "billable": false
+      },
+      {
+        "session_id": "failover",
+        "route_epoch": 0,
+        "status": "unverified",
+        "tokens": 2,
+        "failure_kind": "worker-death",
+        "detail": "worker died mid-step",
+        "billable": false
+      },
+      {
+        "session_id": "failover",
+        "route_epoch": 1,
+        "status": "completed",
+        "tokens": 8,
+        "failure_kind": null,
+        "detail": "",
+        "billable": true
+      }
+    ],
+    "counts_by_status": {
+      "completed": 2,
+      "cancelled": 1,
+      "failed": 0,
+      "unverified": 2
+    },
+    "billable_tokens": 16
+  }
+}