@yanlinglabs/winter-conformance 0.0.17 → 0.0.22

package/goldens/hook-denied-round.trace.json

@@ -163,6 +163,27 @@
       "subtype": "success",
       "is_error": false,
       "result": "tool round done",
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
       "permission_denials": [
         {
           "tool_name": "test_tool",
@@ -171,7 +192,18 @@
             "probe": true
           }
         }
-      ]
+      ],
+      "modelUsage": {
+        "winter-test/echo": {
+          "inputTokens": "<inputTokens>",
+          "outputTokens": "<outputTokens>",
+          "cacheReadInputTokens": "<cacheReadInputTokens>",
+          "cacheCreationInputTokens": "<cacheCreationInputTokens>",
+          "webSearchRequests": 0,
+          "costUSD": 0,
+          "canonicalModel": "winter-test/echo"
+        }
+      }
     }
   }
 ]

package/goldens/hooked-tool-round.trace.json

@@ -149,7 +149,39 @@
       "subtype": "success",
       "is_error": false,
       "result": "tool round done",
-      "permission_denials": []
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
+      "permission_denials": [],
+      "modelUsage": {
+        "winter-test/echo": {
+          "inputTokens": "<inputTokens>",
+          "outputTokens": "<outputTokens>",
+          "cacheReadInputTokens": "<cacheReadInputTokens>",
+          "cacheCreationInputTokens": "<cacheCreationInputTokens>",
+          "webSearchRequests": 0,
+          "costUSD": 0,
+          "canonicalModel": "winter-test/echo"
+        }
+      }
     }
   }
 ]

package/goldens/interrupt.trace.json

@@ -124,6 +124,27 @@
       "subtype": "success",
       "is_error": false,
       "interrupted": true,
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
       "permission_denials": []
     }
   },

package/goldens/mcp-tool-round.trace.json

@@ -133,7 +133,39 @@
       "subtype": "success",
       "is_error": false,
       "result": "mcp sdk done",
-      "permission_denials": []
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
+      "permission_denials": [],
+      "modelUsage": {
+        "winter-test/echo": {
+          "inputTokens": "<inputTokens>",
+          "outputTokens": "<outputTokens>",
+          "cacheReadInputTokens": "<cacheReadInputTokens>",
+          "cacheCreationInputTokens": "<cacheCreationInputTokens>",
+          "webSearchRequests": 0,
+          "costUSD": 0,
+          "canonicalModel": "winter-test/echo"
+        }
+      }
     }
   }
 ]

package/goldens/mode-switch-mid-session.trace.json

@@ -119,7 +119,39 @@
       "subtype": "success",
       "is_error": false,
       "result": "first done",
-      "permission_denials": []
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
+      "permission_denials": [],
+      "modelUsage": {
+        "winter-test/echo": {
+          "inputTokens": "<inputTokens>",
+          "outputTokens": "<outputTokens>",
+          "cacheReadInputTokens": "<cacheReadInputTokens>",
+          "cacheCreationInputTokens": "<cacheCreationInputTokens>",
+          "webSearchRequests": 0,
+          "costUSD": 0,
+          "canonicalModel": "winter-test/echo"
+        }
+      }
     }
   },
   {
@@ -196,13 +228,45 @@
       "subtype": "success",
       "is_error": false,
       "result": "second done",
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
       "permission_denials": [
         {
           "tool_name": "mystery_tool",
           "tool_use_id": "c2",
           "tool_input": {}
         }
-      ]
+      ],
+      "modelUsage": {
+        "winter-test/echo": {
+          "inputTokens": "<inputTokens>",
+          "outputTokens": "<outputTokens>",
+          "cacheReadInputTokens": "<cacheReadInputTokens>",
+          "cacheCreationInputTokens": "<cacheCreationInputTokens>",
+          "webSearchRequests": 0,
+          "costUSD": 0,
+          "canonicalModel": "winter-test/echo"
+        }
+      }
     }
   }
 ]

package/goldens/multi-turn.trace.json

@@ -84,7 +84,39 @@
       "subtype": "success",
       "is_error": false,
       "result": "echo: <system-reminder>\nAvailable agent types for the Agent tool:\n- claude: Catch-all for any task that doesn't fit a more specific agent. (Tools: *)\n- Explore: Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions. (Tools: All tools except Agent, Artifact, ExitPlanMode, Edit, Write, NotebookEdit)\n- general-purpose: General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you. (Tools: *)\n- Plan: Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs. (Tools: All tools except Agent, Artifact, ExitPlanMode, Edit, Write, NotebookEdit)\n\nWhen you launch multiple agents for independent work, send them in a single message with multiple tool uses so they run concurrently.\n</system-reminder>\n\n<system-reminder>\nAs you answer the user's questions, you can use the following context:\n# currentDate\nToday's date is <FIXTURE-DATE>.\n\n      IMPORTANT: this context may or may not be relevant to your tasks. You should not respond to this context unless it is highly relevant to your task.\n</system-reminder>\n\n\nfirst",
-      "permission_denials": []
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
+      "permission_denials": [],
+      "modelUsage": {
+        "winter-test/echo": {
+          "inputTokens": "<inputTokens>",
+          "outputTokens": "<outputTokens>",
+          "cacheReadInputTokens": "<cacheReadInputTokens>",
+          "cacheCreationInputTokens": "<cacheCreationInputTokens>",
+          "webSearchRequests": 0,
+          "costUSD": 0,
+          "canonicalModel": "winter-test/echo"
+        }
+      }
     }
   },
   {
@@ -112,7 +144,39 @@
       "subtype": "success",
       "is_error": false,
       "result": "echo: second",
-      "permission_denials": []
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
+      "permission_denials": [],
+      "modelUsage": {
+        "winter-test/echo": {
+          "inputTokens": "<inputTokens>",
+          "outputTokens": "<outputTokens>",
+          "cacheReadInputTokens": "<cacheReadInputTokens>",
+          "cacheCreationInputTokens": "<cacheCreationInputTokens>",
+          "webSearchRequests": 0,
+          "costUSD": 0,
+          "canonicalModel": "winter-test/echo"
+        }
+      }
     }
   }
 ]

package/goldens/p6-anthropic-fake.trace.json

@@ -136,13 +136,34 @@
       "subtype": "success",
       "is_error": false,
       "result": "the provider scenario is done",
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
       "permission_denials": [],
       "modelUsage": {
         "anthropic/claude-sonnet-5": {
-          "inputTokens": 14,
-          "outputTokens": 7,
-          "cacheReadInputTokens": 0,
-          "cacheCreationInputTokens": 0,
+          "inputTokens": "<inputTokens>",
+          "outputTokens": "<outputTokens>",
+          "cacheReadInputTokens": "<cacheReadInputTokens>",
+          "cacheCreationInputTokens": "<cacheCreationInputTokens>",
           "webSearchRequests": 0,
           "costUSD": 0.000098,
           "contextWindow": 1048576,

package/goldens/p6-gemini-fake.trace.json

@@ -135,7 +135,41 @@
       "subtype": "success",
       "is_error": false,
       "result": "the provider scenario is done",
-      "permission_denials": []
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
+      "permission_denials": [],
+      "modelUsage": {
+        "google/gemini-2.5-flash": {
+          "inputTokens": "<inputTokens>",
+          "outputTokens": "<outputTokens>",
+          "cacheReadInputTokens": "<cacheReadInputTokens>",
+          "cacheCreationInputTokens": "<cacheCreationInputTokens>",
+          "webSearchRequests": 0,
+          "costUSD": 0.0000242,
+          "contextWindow": 1048576,
+          "canonicalModel": "google/gemini-2.5-flash",
+          "costBasis": "list"
+        }
+      }
     }
   }
 ]

package/goldens/p6-openai-chat-fake.trace.json

@@ -136,7 +136,42 @@
       "subtype": "success",
       "is_error": false,
       "result": "the provider scenario is done",
-      "permission_denials": []
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
+      "permission_denials": [],
+      "modelUsage": {
+        "deepseek/deepseek-v4-pro": {
+          "inputTokens": "<inputTokens>",
+          "outputTokens": "<outputTokens>",
+          "cacheReadInputTokens": "<cacheReadInputTokens>",
+          "cacheCreationInputTokens": "<cacheCreationInputTokens>",
+          "webSearchRequests": 0,
+          "costUSD": 0.00005016,
+          "contextWindow": 1000000,
+          "maxOutputTokens": 384000,
+          "canonicalModel": "deepseek/deepseek-v4-pro",
+          "costBasis": "list"
+        }
+      }
     }
   }
 ]

package/goldens/p6-openai-responses-fake.trace.json

@@ -135,16 +135,38 @@
       "subtype": "success",
       "is_error": false,
       "result": "the provider scenario is done",
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
       "permission_denials": [],
       "modelUsage": {
         "openai/gpt-4.1": {
-          "inputTokens": 14,
-          "outputTokens": 8,
-          "cacheReadInputTokens": 0,
-          "cacheCreationInputTokens": 0,
+          "inputTokens": "<inputTokens>",
+          "outputTokens": "<outputTokens>",
+          "cacheReadInputTokens": "<cacheReadInputTokens>",
+          "cacheCreationInputTokens": "<cacheCreationInputTokens>",
           "webSearchRequests": 0,
           "costUSD": 0.000092,
           "contextWindow": 1047576,
+          "maxOutputTokens": 32768,
           "canonicalModel": "openai/gpt-4.1",
           "costBasis": "list"
         }

package/goldens/p6-resolution-failure.trace.json

@@ -70,6 +70,27 @@
       "result": "model \"definitely-not-a-model-t10\" is not in provider \"anthropic\"'s catalog (its live catalog is authoritative, so absence is definitive)",
       "terminal_reason": "api_error",
       "api_error_status": null,
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
       "permission_denials": []
     }
   }

package/goldens/plain-query.trace.json

@@ -84,7 +84,39 @@
       "subtype": "success",
       "is_error": false,
       "result": "echo: <system-reminder>\nAvailable agent types for the Agent tool:\n- claude: Catch-all for any task that doesn't fit a more specific agent. (Tools: *)\n- Explore: Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions. (Tools: All tools except Agent, Artifact, ExitPlanMode, Edit, Write, NotebookEdit)\n- general-purpose: General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you. (Tools: *)\n- Plan: Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs. (Tools: All tools except Agent, Artifact, ExitPlanMode, Edit, Write, NotebookEdit)\n\nWhen you launch multiple agents for independent work, send them in a single message with multiple tool uses so they run concurrently.\n</system-reminder>\n\n<system-reminder>\nAs you answer the user's questions, you can use the following context:\n# currentDate\nToday's date is <FIXTURE-DATE>.\n\n      IMPORTANT: this context may or may not be relevant to your tasks. You should not respond to this context unless it is highly relevant to your task.\n</system-reminder>\n\n\nhi",
-      "permission_denials": []
+      "usage": {
+        "output_tokens_details": {
+          "thinking_tokens": 0
+        },
+        "input_tokens": "<input_tokens>",
+        "cache_creation_input_tokens": "<cache_creation_input_tokens>",
+        "cache_read_input_tokens": "<cache_read_input_tokens>",
+        "output_tokens": "<output_tokens>",
+        "server_tool_use": {
+          "web_search_requests": 0,
+          "web_fetch_requests": 0
+        },
+        "service_tier": "standard",
+        "cache_creation": {
+          "ephemeral_1h_input_tokens": 0,
+          "ephemeral_5m_input_tokens": 0
+        },
+        "inference_geo": "",
+        "iterations": [],
+        "speed": "standard"
+      },
+      "permission_denials": [],
+      "modelUsage": {
+        "winter-test/echo": {
+          "inputTokens": "<inputTokens>",
+          "outputTokens": "<outputTokens>",
+          "cacheReadInputTokens": "<cacheReadInputTokens>",
+          "cacheCreationInputTokens": "<cacheCreationInputTokens>",
+          "webSearchRequests": 0,
+          "costUSD": 0,
+          "canonicalModel": "winter-test/echo"
+        }
+      }
     }
   }
 ]