Added value: +{
+  "description": "OpenRouter id of the model the job uses now, if any.",
+  "type": "string"
+}

Added value: +{
+  "description": "Roughly how many times a month the job runs, if known.",
+  "type": "number"
+}

Removed value: -{
-  "description": "Required capabilities the model MUST support. Models missing any listed capability are filtered out before ranking. 'vision' = image input, 'audio_in' = audio input, 'tool_use' = function calling, 'structured_outputs' = JSON schema-constrained output. Omit when the task is plain text with no tool use.",
-  "items": {
-    "enum": [
-      "vision",
-      "audio_in",
-      "tool_use",
-      "structured_outputs"
-    ],
-    "type": "string"
-  },
-  "type": "array"
-}

Added value: +{
+  "description": "The person approved the estimate. Spends on their key.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "The offer from the estimate. Pass it with go=true to run.",
+  "type": "string"
+}

Added value: +{
+  "description": "Failures the person accepts, as 'model id|requirement words'.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Removed value: -{
-  "description": "Ordered priorities, highest first, for example quality then cost. Later dimensions break exact ties; unspecified dimensions do not decide the winner.",
-  "items": {
-    "enum": [
-      "cost",
-      "quality",
-      "latency",
-      "privacy"
-    ],
-    "type": "string"
-  },
-  "type": "array"
-}

Removed value: -{
-  "description": "One sentence describing what the model will be used for. The benchmark generates representative test queries from this — so be concrete, not vague.",
-  "type": "string"
-}

Added value: +{
+  "description": "Blind ratings: {task id: {letter: good|ok|poor}}, with test_session.",
+  "type": "object"
+}

Added value: +{
+  "description": "The sealed session from a finished discover conversation.",
+  "type": "string"
+}

Added value: +{
+  "description": "The person's real work to test on, real examples first. Write extra tasks yourself only for the gaps XFMS names, with source 'made up'. Images as data URLs.",
+  "items": {
+    "properties": {
+      "covers": {
+        "description": "ids of the requirements this task tests",
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "group": {
+        "description": "optional kind of task, e.g. 'short captions'",
+        "type": "string"
+      },
+      "image_urls": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "source": {
+        "description": "real | made up",
+        "type": "string"
+      },
+      "text": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

Removed value: -{
-  "description": "Optional actual task prompts including source facts. Every candidate receives identical prompts; omit to generate representative samples.",
-  "items": {
-    "minLength": 1,
-    "type": "string"
-  },
-  "maxItems": 15,
-  "minItems": 1,
-  "type": "array"
-}

Added value: +{
+  "description": "From a finished run, to overrule failures without rerunning.",
+  "type": "string"
+}

Removed value: -{
-  "default": 5,
-  "description": "How many models to return in the ranked list. Defaults to 5. Use 1 if you only want the single best pick; use 10+ if you want to see deeper alternatives.",
-  "maximum": 25,
-  "minimum": 1,
-  "type": "integer"
-}

Previous value: -[
-  "purpose"
-]New value: +[
+  "session"
+]

Added value: +true

Previous value: -"Rank response with ab_result populated — same shape as `rank` plus live performance data from the probe runs."New value: +"Without go: the estimate and offer. With go: the outcome, every model on every requirement, the report."

Removed value: -{
-  "ab_result": {
-    "properties": {
-      "aggregates": {
-        "description": "Per-model stats across the runs.",
-        "items": {
-          "properties": {
-            "avg_accuracy": {
-              "type": [
-                "number",
-                "null"
-              ]
-            },
-            "avg_completion_tokens": {
-              "type": "number"
-            },
-            "avg_latency_ms": {
-              "type": "number"
-            },
-            "model_id": {
-              "type": "string"
-            },
-            "model_name": {
-              "type": "string"
-            },
-            "runs": {
-              "description": "The actual generated answer for every test query this model ran, for human review — not just the score.",
-              "items": {
-                "properties": {
-                  "error": {
-                    "type": [
-                      "string",
-                      "null"
-                    ]
-                  },
-                  "response_text": {
-                    "type": "string"
-                  },
-                  "test_query": {
-                    "type": "string"
-                  }
-                },
-                "type": "object"
-              },
-              "type": "array"
-            },
-            "success_count": {
-              "type": "integer"
-            },
-            "total_cost_usd": {
-              "type": "number"
-            }
-          },
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "commentary": {
-        "type": "string"
-      },
-      "cost_winner_id": {
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "incongruity_detected": {
-        "type": "boolean"
-      },
-      "latency_winner_id": {
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "overall_winner_id": {
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "queries_executed": {
-        "type": "integer"
-      },
-      "test_queries": {
-        "description": "The generated test prompts that were run.",
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      }
-    },
-    "type": "object"
-  },
-  "catalog_size": {
-    "type": "integer"
-  },
-  "filtered_out": {
-    "type": "integer"
-  },
-  "frontier_filtered_out": {
-    "description": "How many models in models[] are neither recent nor top-tier on quality (informational — none are removed from the list, this just means they weren't eligible to be the recommendation).",
-    "type": "integer"
-  },
-  "models": {
-    "description": "Ranked shortlist of models, highest score first.",
-    "items": {
-      "properties": {
-        "model_id": {
-          "type": "string"
-        },
-        "name": {
-          "type": "string"
-        },
-        "provider": {
-          "type": [
-            "string",
-            "null"
-          ]
-        },
-        "rationale": {
-          "type": "string"
-        },
-        "total_score": {
-          "type": "number"
-        }
-      },
-      "type": "object"
-    },
-    "type": "array"
-  },
-  "quality_floor_reason": {
-    "type": [
-      "string",
-      "null"
-    ]
-  },
-  "status": {
-    "description": "'ranked' (normal), 'low_confidence' (capability requirements were relaxed to find any match), or 'quality_floor_refused' (candidates were found but the best one scored too low to recommend — see quality_floor_reason; models[] still lists what was considered).",
-    "type": "string"
-  },
-  "xpansion_update": {
-    "description": "Optional rotating launch nudge from Xpansion. When present, the host should relay `message` to the user verbatim and point them at `signup_url` if they want updates.",
-    "properties": {
-      "call_count": {
-        "type": "integer"
-      },
-      "id": {
-        "type": "string"
-      },
-      "message": {
-        "type": "string"
-      },
-      "signup_url": {
-        "type": "string"
-      }
-    },
-    "type": "object"
-  }
-}

Added value: +{
+  "description": "Required capabilities the model MUST support. Models missing any listed capability are filtered out before ranking. 'vision' = image input, 'audio_in' = audio input, 'tool_use' = function calling, 'structured_outputs' = JSON schema-constrained output. Omit when the task is plain text with no tool use.",
+  "items": {
+    "enum": [
+      "vision",
+      "audio_in",
+      "tool_use",
+      "structured_outputs"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}

Added value: +{
+  "description": "Ordered priorities, highest first, for example quality then cost. Later dimensions break exact ties; unspecified dimensions do not decide the winner.",
+  "items": {
+    "enum": [
+      "cost",
+      "quality",
+      "latency",
+      "privacy"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}

Added value: +{
+  "description": "Optional actual task prompts including source facts. Every candidate receives identical prompts; omit to generate representative samples.",
+  "items": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 15,
+  "minItems": 1,
+  "type": "array"
+}

Added value: +{
+  "default": 5,
+  "description": "How many models to return in the ranked list. Defaults to 5. Use 1 if you only want the single best pick; use 10+ if you want to see deeper alternatives.",
+  "maximum": 25,
+  "minimum": 1,
+  "type": "integer"
+}

Previous value: -"number"New value: +[
+  "number",
+  "null"
+]

Added value: +{
+  "type": "number"
+}

Added value: +{
+  "description": "The actual generated answer for every test query this model ran, for human review — not just the score.",
+  "items": {
+    "properties": {
+      "error": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "response_text": {
+        "type": "string"
+      },
+      "test_query": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

Added value: +{
+  "description": "How many models in models[] are neither recent nor top-tier on quality (informational — none are removed from the list, this just means they weren't eligible to be the recommendation).",
+  "type": "integer"
+}

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

Added value: +"'ranked' (normal), 'low_confidence' (capability requirements were relaxed to find any match), or 'quality_floor_refused' (candidates were found but the best one scored too low to recommend — see quality_floor_reason; models[] still lists what was considered)."

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

Added value: +{
+  "description": "Optional rotating launch nudge from Xpansion. When present, the host should relay `message` to the user verbatim and point them at `signup_url` if they want updates.",
+  "properties": {
+    "call_count": {
+      "type": "integer"
+    },
+    "id": {
+      "type": "string"
+    },
+    "message": {
+      "type": "string"
+    },
+    "signup_url": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}