Previous value: -"Simulation ID returned by simulation.create. Preserve Mcp-Session-Id to omit this field and use the session's current simulation; if your connector starts a fresh MCP session for each call (for example Grok Bot or Cursor), pass this explicit ID. A fresh session has no current-simulation pointer and returns NO_ACTIVE_SIMULATION when the ID is omitted. Anonymous capabilities are short-lived, bound to the creating anonymous client, and revoked when the demo expires or is deleted; do not treat the ID as a durable share link."New value: +"Simulation ID returned by simulation.create. Preserve Mcp-Session-Id to omit this field and use the session's current simulation; if your connector starts a fresh MCP session for each call (for example Grok Bot or Cursor), pass this explicit ID after every fresh initialization. A fresh session has no current-simulation pointer and returns NO_ACTIVE_SIMULATION when the ID is omitted. Anonymous capabilities are short-lived (30 minutes by default), unguessable, and revoked when the demo expires or is deleted; proxy IP changes do not invalidate them. Do not treat the ID as a durable share link."

Previous value: -"Simulation ID returned by simulation.create. Optional in demo sessions — omit to target this session's current simulation (set by simulation.create and updated by the most recent successful explicit use). If the session has no current simulation you get a NO_ACTIVE_SIMULATION result."New value: +"Simulation ID returned by simulation.create. Preserve Mcp-Session-Id to omit this field and use the session's current simulation; if your connector starts a fresh MCP session for each call (for example Grok Bot or Cursor), pass this explicit ID. A fresh session has no current-simulation pointer and returns NO_ACTIVE_SIMULATION when the ID is omitted. Anonymous capabilities are short-lived, bound to the creating anonymous client, and revoked when the demo expires or is deleted; do not treat the ID as a durable share link."

Added value: +{
+  "description": "50th-percentile latency in ms",
+  "type": "number"
+}

Added value: +{
+  "additionalProperties": false,
+  "description": "Read-only recovery progress; poll simulation.get or simulation.step until state is healthy",
+  "properties": {
+    "cooldown": {
+      "additionalProperties": false,
+      "properties": {
+        "completedSteps": {
+          "type": "number"
+        },
+        "remainingSteps": {
+          "type": "number"
+        },
+        "requiredSteps": {
+          "type": "number"
+        },
+        "target": {
+          "anyOf": [
+            {
+              "enum": [
+                "warning",
+                "healthy"
+              ],
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        }
+      },
+      "required": [
+        "target",
+        "completedSteps",
+        "requiredSteps",
+        "remainingSteps"
+      ],
+      "type": "object"
+    },
+    "parkWindow": {
+      "additionalProperties": false,
+      "properties": {
+        "completedSteps": {
+          "type": "number"
+        },
+        "remainingSteps": {
+          "type": "number"
+        },
+        "totalSteps": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "totalSteps",
+        "completedSteps",
+        "remainingSteps"
+      ],
+      "type": "object"
+    },
+    "state": {
+      "enum": [
+        "parked",
+        "cooling_down",
+        "healthy"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "state",
+    "parkWindow",
+    "cooldown"
+  ],
+  "type": "object"
+}

Previous value: -"Response detail level. 'compact' (default) returns only the principal metrics, per-resource status (id, name, status, cpuPercent, routedRps), and this step's events — keeps observations small for agent loops. 'full' returns the complete backend step response including the entire simulation object with all resource characteristics and connections."New value: +"Response detail level. 'compact' (default) returns only principal metrics, errorBreakdown when available, per-resource status (id, name, status, cpuPercent, routedRps, availabilityState, isRoutable, and recoveryBlockedReason when provided), and this step's events — keeps observations small for agent loops. 'full' returns the complete backend step response including the entire simulation object with all resource characteristics and connections."

Added value: +{
+  "additionalProperties": false,
+  "description": "Validated additive error contributors in percentage-point units; separates pool/DB, compute, capacity, CPU, storage, runtime-memory, and queue absorption effects",
+  "properties": {
+    "capacityOverload": {
+      "type": "number"
+    },
+    "computeFailure": {
+      "type": "number"
+    },
+    "cpuOverload": {
+      "type": "number"
+    },
+    "dbFailure": {
+      "type": "number"
+    },
+    "ociStorage": {
+      "type": "number"
+    },
+    "poolSaturation": {
+      "type": "number"
+    },
+    "queueAbsorption": {
+      "type": "number"
+    },
+    "runtimeMemory": {
+      "type": "number"
+    }
+  },
+  "required": [
+    "poolSaturation",
+    "dbFailure",
+    "computeFailure",
+    "capacityOverload",
+    "cpuOverload",
+    "ociStorage",
+    "queueAbsorption"
+  ],
+  "type": "object"
+}

Added value: +{
+  "description": "Availability derived from routed traffic: available = serving normally, degraded = critical/warning but still serving, unavailable = no traffic and not routable",
+  "enum": [
+    "available",
+    "degraded",
+    "unavailable"
+  ],
+  "type": "string"
+}

Added value: +{
+  "description": "Whether this compute/Kubernetes resource can receive traffic in this step; false distinguishes a failed/parked node from a critical node still serving",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Engine recovery guard currently preventing cooldown progress, when present (for example failure_park_window or idle_cpu_floor)",
+  "type": "string"
+}

Added value: +false

Removed value: -{
-  "description": "One-sentence goal for this session — e.g. 'train RL agent on AWS', 'compare GCP vs Azure costs', or 'run chaos test on database tier'.",
-  "type": "string"
-}

Removed value: -[
-  "context"
-]

Added value: +{
+  "additionalProperties": true,
+  "description": "Bounded resilience diagnostics summary (compact mode). Absent when the resilience model did not run. Use simulation.compare_resilience for full per-path detail.",
+  "properties": {
+    "bounded": {
+      "description": "True when a generated-traffic, traversal-work, or cascade-depth bound truncated model work",
+      "type": "boolean"
+    },
+    "incidentOutcome": {
+      "description": "Incident outcome: stable | degraded | cascading | protected | recovered",
+      "type": "string"
+    },
+    "pathCount": {
+      "description": "Number of dependency paths evaluated this step",
+      "type": "number"
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "description": "Retry amplification factor for this step (attemptedRps / originalRps). Values > 1.0 = amplification risk. null = model ran but no traffic. Absent = resilience model disabled.",
+  "type": [
+    "number",
+    "null"
+  ]
+}

Added value: +{
+  "description": "Self-hosted inference cost in USD per million tokens (null when no tokens are being processed) — present only on GPU inference simulations",
+  "type": [
+    "number",
+    "null"
+  ]
+}

Added value: +{
+  "description": "GPU utilization (%) — present only on simulations with a GPU inference kubernetes resource",
+  "type": "number"
+}

Added value: +{
+  "description": "USD/hr of GPU spend funding idle/standby capacity (HA overhead) — present only on GPU inference simulations",
+  "type": "number"
+}

Added value: +{
+  "description": "Share (0-1) of the GPU bill that is idle/standby capacity — present only on GPU inference simulations; values above 0.5 mean over half the GPU spend is HA overhead",
+  "type": "number"
+}

Added value: +{
+  "description": "Inference throughput in tokens/second — present only on GPU inference simulations",
+  "type": "number"
+}