Deploy viewer and games

data/report/metrics.json

@@ -88,6 +88,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 21482.0,
         "cost_usd_per_game": 0.004903
       },
@@ -168,6 +170,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 21482.0,
         "cost_usd_per_game": 0.004903
       },
@@ -248,6 +252,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 21482.0,
         "cost_usd_per_game": 0.004903
       }
@@ -322,6 +328,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 42470.0,
         "cost_usd_per_game": 0.009611
       },
@@ -394,6 +402,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 42470.0,
         "cost_usd_per_game": 0.009611
       }
@@ -476,6 +486,8 @@
         "night_targeted": 0.0,
         "voted_out": 1.0,
         "invalid_output_rate": 0.14285714285714285,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 24416.0,
         "cost_usd_per_game": 0.005542
       },
@@ -556,6 +568,8 @@
         "night_targeted": 0.0,
         "voted_out": 1.0,
         "invalid_output_rate": 0.14285714285714285,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 24416.0,
         "cost_usd_per_game": 0.005542
       },
@@ -636,6 +650,8 @@
         "night_targeted": 0.0,
         "voted_out": 1.0,
         "invalid_output_rate": 0.14285714285714285,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 24416.0,
         "cost_usd_per_game": 0.005542
       }
@@ -709,6 +725,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 42128.0,
         "cost_usd_per_game": 0.009533
       },
@@ -780,6 +798,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 42128.0,
         "cost_usd_per_game": 0.009533
       }
@@ -867,6 +887,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.2,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 35950.0,
         "cost_usd_per_game": 0.008219
       },
@@ -952,6 +974,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.2,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 35950.0,
         "cost_usd_per_game": 0.008219
       },
@@ -1037,6 +1061,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.2,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 35950.0,
         "cost_usd_per_game": 0.008219
       }
@@ -1119,6 +1145,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 21362.0,
         "cost_usd_per_game": 0.004831
       },
@@ -1199,6 +1227,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 21362.0,
         "cost_usd_per_game": 0.004831
       },
@@ -1279,6 +1309,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 21362.0,
         "cost_usd_per_game": 0.004831
       }
@@ -1363,6 +1395,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 15722.0,
         "cost_usd_per_game": 0.003667
       },
@@ -1445,6 +1479,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 15722.0,
         "cost_usd_per_game": 0.003667
       },
@@ -1527,6 +1563,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 15722.0,
         "cost_usd_per_game": 0.003667
       }
@@ -1620,6 +1658,8 @@
       "night_targeted": 0.42857142857142855,
       "voted_out": 0.14285714285714285,
       "invalid_output_rate": 0.05172413793103448,
+      "provider_errors": 0,
+      "provider_error_rate": 0.0,
       "tokens_per_game": 29075.714285714286,
       "cost_usd_per_game": 0.006615142857142857
     },
@@ -1705,6 +1745,8 @@
       "night_targeted": 1.0,
       "voted_out": 0.0,
       "invalid_output_rate": 0.2,
+      "provider_errors": 0,
+      "provider_error_rate": 0.0,
       "tokens_per_game": 35950.0,
       "cost_usd_per_game": 0.008219
     },
@@ -1787,6 +1829,8 @@
       "night_targeted": 1.0,
       "voted_out": 0.0,
       "invalid_output_rate": 0.0,
+      "provider_errors": 0,
+      "provider_error_rate": 0.0,
       "tokens_per_game": 15722.0,
       "cost_usd_per_game": 0.003667
     },
@@ -1874,6 +1918,8 @@
       "night_targeted": 0.6,
       "voted_out": 0.2,
       "invalid_output_rate": 0.08823529411764706,
+      "provider_errors": 0,
+      "provider_error_rate": 0.0,
       "tokens_per_game": 23786.4,
       "cost_usd_per_game": 0.005432400000000001
     },
@@ -1954,6 +2000,8 @@
       "night_targeted": 0.3333333333333333,
       "voted_out": 0.3333333333333333,
       "invalid_output_rate": 0.05263157894736842,
+      "provider_errors": 0,
+      "provider_error_rate": 0.0,
       "tokens_per_game": 22420.0,
       "cost_usd_per_game": 0.005092
     },
@@ -2027,6 +2075,8 @@
       "night_targeted": 0.0,
       "voted_out": 0.0,
       "invalid_output_rate": 0.0,
+      "provider_errors": 0,
+      "provider_error_rate": 0.0,
       "tokens_per_game": 42299.0,
       "cost_usd_per_game": 0.009572
     }

data/report/report.md

@@ -154,15 +154,15 @@ Truthful claims from the log, the same for both label sources: how often each li
 
 ## Cost and reliability
 
-| Model | Invalid output rate | USD per game |
-|---|---|---|
-| gemini-flash | 0% | 0.0096 |
-| gemma-4-26b | 0% | 0.0095 |
-| deepseek-v3.1 | 0% | 0.0049 |
-| gemini-flash-lite | 14% | 0.0055 |
-| gpt-oss-120b | 20% | 0.0082 |
-| llama-4-maverick | 0% | 0.0048 |
-| qwen3-235b | 0% | 0.0037 |
+| Model | Invalid output rate | Provider errors | USD per game |
+|---|---|---|---|
+| gemini-flash | 0% | 0 | 0.0096 |
+| gemma-4-26b | 0% | 0 | 0.0095 |
+| deepseek-v3.1 | 0% | 0 | 0.0049 |
+| gemini-flash-lite | 14% | 0 | 0.0055 |
+| gpt-oss-120b | 20% | 0 | 0.0082 |
+| llama-4-maverick | 0% | 0 | 0.0048 |
+| qwen3-235b | 0% | 0 | 0.0037 |
 
 ## Speed
 

devui/schema/metrics.schema.json

@@ -405,6 +405,19 @@
             }
           ]
         },
+        "provider_errors": {
+          "type": "integer"
+        },
+        "provider_error_rate": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
         "tokens_per_game": {
           "anyOf": [
             {
@@ -441,6 +454,8 @@
         "night_targeted",
         "voted_out",
         "invalid_output_rate",
+        "provider_errors",
+        "provider_error_rate",
         "tokens_per_game",
         "cost_usd_per_game"
       ],

index.html

@@ -15,7 +15,7 @@
     <meta name="twitter:title" content="SocietySim" />
     <meta name="twitter:description" content="LLM agents from different labs play Werewolf. Watch who lies, who gets caught, and who wins." />
     <meta name="twitter:image" content="https://society-sim.us/og/card.png" />
-    <script type="module" crossorigin src="./assets/index-B_Jd99NA.js"></script>
+    <script type="module" crossorigin src="./assets/index-BzmtSTSR.js"></script>
     <link rel="stylesheet" crossorigin href="./assets/index-DPs3dK6n.css">
   </head>
   <body>

metrics.json

@@ -88,6 +88,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 21482.0,
         "cost_usd_per_game": 0.004903
       },
@@ -168,6 +170,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 21482.0,
         "cost_usd_per_game": 0.004903
       },
@@ -248,6 +252,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 21482.0,
         "cost_usd_per_game": 0.004903
       }
@@ -322,6 +328,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 42470.0,
         "cost_usd_per_game": 0.009611
       },
@@ -394,6 +402,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 42470.0,
         "cost_usd_per_game": 0.009611
       }
@@ -476,6 +486,8 @@
         "night_targeted": 0.0,
         "voted_out": 1.0,
         "invalid_output_rate": 0.14285714285714285,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 24416.0,
         "cost_usd_per_game": 0.005542
       },
@@ -556,6 +568,8 @@
         "night_targeted": 0.0,
         "voted_out": 1.0,
         "invalid_output_rate": 0.14285714285714285,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 24416.0,
         "cost_usd_per_game": 0.005542
       },
@@ -636,6 +650,8 @@
         "night_targeted": 0.0,
         "voted_out": 1.0,
         "invalid_output_rate": 0.14285714285714285,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 24416.0,
         "cost_usd_per_game": 0.005542
       }
@@ -709,6 +725,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 42128.0,
         "cost_usd_per_game": 0.009533
       },
@@ -780,6 +798,8 @@
         "night_targeted": 0.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 42128.0,
         "cost_usd_per_game": 0.009533
       }
@@ -867,6 +887,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.2,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 35950.0,
         "cost_usd_per_game": 0.008219
       },
@@ -952,6 +974,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.2,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 35950.0,
         "cost_usd_per_game": 0.008219
       },
@@ -1037,6 +1061,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.2,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 35950.0,
         "cost_usd_per_game": 0.008219
       }
@@ -1119,6 +1145,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 21362.0,
         "cost_usd_per_game": 0.004831
       },
@@ -1199,6 +1227,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 21362.0,
         "cost_usd_per_game": 0.004831
       },
@@ -1279,6 +1309,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 21362.0,
         "cost_usd_per_game": 0.004831
       }
@@ -1363,6 +1395,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 15722.0,
         "cost_usd_per_game": 0.003667
       },
@@ -1445,6 +1479,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 15722.0,
         "cost_usd_per_game": 0.003667
       },
@@ -1527,6 +1563,8 @@
         "night_targeted": 1.0,
         "voted_out": 0.0,
         "invalid_output_rate": 0.0,
+        "provider_errors": 0,
+        "provider_error_rate": 0.0,
         "tokens_per_game": 15722.0,
         "cost_usd_per_game": 0.003667
       }
@@ -1620,6 +1658,8 @@
       "night_targeted": 0.42857142857142855,
       "voted_out": 0.14285714285714285,
       "invalid_output_rate": 0.05172413793103448,
+      "provider_errors": 0,
+      "provider_error_rate": 0.0,
       "tokens_per_game": 29075.714285714286,
       "cost_usd_per_game": 0.006615142857142857
     },
@@ -1705,6 +1745,8 @@
       "night_targeted": 1.0,
       "voted_out": 0.0,
       "invalid_output_rate": 0.2,
+      "provider_errors": 0,
+      "provider_error_rate": 0.0,
       "tokens_per_game": 35950.0,
       "cost_usd_per_game": 0.008219
     },
@@ -1787,6 +1829,8 @@
       "night_targeted": 1.0,
       "voted_out": 0.0,
       "invalid_output_rate": 0.0,
+      "provider_errors": 0,
+      "provider_error_rate": 0.0,
       "tokens_per_game": 15722.0,
       "cost_usd_per_game": 0.003667
     },
@@ -1874,6 +1918,8 @@
       "night_targeted": 0.6,
       "voted_out": 0.2,
       "invalid_output_rate": 0.08823529411764706,
+      "provider_errors": 0,
+      "provider_error_rate": 0.0,
       "tokens_per_game": 23786.4,
       "cost_usd_per_game": 0.005432400000000001
     },
@@ -1954,6 +2000,8 @@
       "night_targeted": 0.3333333333333333,
       "voted_out": 0.3333333333333333,
       "invalid_output_rate": 0.05263157894736842,
+      "provider_errors": 0,
+      "provider_error_rate": 0.0,
       "tokens_per_game": 22420.0,
       "cost_usd_per_game": 0.005092
     },
@@ -2027,6 +2075,8 @@
       "night_targeted": 0.0,
       "voted_out": 0.0,
       "invalid_output_rate": 0.0,
+      "provider_errors": 0,
+      "provider_error_rate": 0.0,
       "tokens_per_game": 42299.0,
       "cost_usd_per_game": 0.009572
     }