Evidence row 383764

What was observed

{
  "count": 7,
  "tools": [
    {
      "description": "Is my stack okay? Check a list of model ids against the record: scheduled retirements with days-remaining countdowns and migration targets, past retirements, and other breaking/action-required changes. Id matching tolerates dots vs dashes, dated snapshot suffixes, and bare or provider-prefixed forms. Call this at startup or in CI with the models you depend on.",
      "inputSchema": {
        "properties": {
          "models": {
            "description": "Model ids to check, e.g. [\"gpt-4o\", \"claude-sonnet-4-6\", \"gemini-2.5-flash\"].",
            "items": {
              "type": "string"
            },
            "maxItems": 50,
            "minItems": 1,
            "type": "array"
          }
        },
        "required": [
          "models"
        ],
        "type": "object"
      },
      "name": "check_model_dependencies"
    },
    {
      "description": "Estimate the USD cost of an LLM API call for a given model and token counts. Returns input/output/total cost, plus reseller markup vs. the upstream model when applicable.",
      "inputSchema": {
        "properties": {
          "input_tokens": {
            "description": "Number of input (prompt) tokens.",
            "minimum": 0,
            "type": "integer"
          },
          "model": {
            "description": "Model id in provider/model form, e.g. anthropic/claude-opus-4-8. Use list_models to discover ids.",
            "type": "string"
          },
          "output_tokens": {
            "description": "Number of output (completion) tokens.",
            "minimum": 0,
            "type": "integer"
          }
        },
        "required": [
          "model",
          "input_tokens",
          "output_tokens"
        ],
        "type": "object"
      },
      "name": "estimate_cost"
    },
    {
      "description": "Unified card for one model in a single call: normalized pricing, capabilities (context window, vision, reasoning, tags), availability, reseller markup vs. upstream, and a price-history summary (launch vs. current price, percent change, last change date, all-time low/high).",
      "inputSchema": {
        "properties": {
          "id": {
            "description": "Model id in provider/model form, e.g. openai/gpt-5-5.",
            "type": "string"
          }
        },
        "required": [
          "id"
        ],
        "type": "object"
      },
      "name": "get_model"
    },
    {
      "description": "Historical pricing time-series for a model or provider. Each point is a dated snapshot of the per-Mtok rates.",
      "inputSchema": {
        "properties": {
          "model": {
            "description": "Model id to fetch history for.",
            "type": "string"
          },
          "provider": {
            "description": "Provider id to fetch history for (all its models).",
            "type": "string"
          },
          "since": {
            "description": "ISO date (YYYY-MM-DD); only points on/after this date.",
            "type": "string"
          },
          "until": {
            "description": "ISO date (YYYY-MM-DD); only points on/before this date.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "get_price_history"
    },
    {
      "description": "Per-model retirement rows from the record: which model dies when, with runway and migration target. Default shows scheduled (upcoming) retirements sorted by shutdown date.",
      "inputSchema": {
        "properties": {
          "limit": {
            "description": "Max rows. Default 100.",
            "maximum": 500,
            "minimum": 1,
            "type": "integer"
          },
          "provider": {
            "description": "Filter to one provider id.",
            "type": "string"
          },
          "status": {
            "description": "Default scheduled.",
            "enum": [
              "scheduled",
              "retired",
              "all"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "list_deprecations"
    },
    {
      "description": "The changelog of record for the model layer: deprecations, price changes, launches, and the market events around them. Filter by severity to find what demands action: 'breaking' (model going away, ID changing), 'action_required' (price/rate-limit/context changes), 'informational' (releases, funding).",
      "inputSchema": {
        "properties": {
          "limit": {
            "description": "Max events. Default 50.",
            "maximum": 500,
            "minimum": 1,
            "type": "integer"
          },
          "provider": {
            "description": "Filter to events touching this provider.",
            "type": "string"
          },
          "severity": {
            "description": "Filter by what the event demands of consumers of the affected models.",
            "enum": [
              "breaking",
              "action_required",
              "informational"
            ],
            "type": "string"
          },
          "since": {
            "description": "ISO date (YYYY-MM-DD); events announced on/after.",
            "type": "string"
          },
          "status": {
            "description": "Verification status. Default 'verified' (human-confirmed). 'all' = verified + unverified.",
            "enum": [
              "verified",
              "unverified",
              "all",
              "corrected"
            ],
            "type": "string"
          },
          "type": {
            "description": "Event type, e.g. model_deprecation, pricing_change, model_launch.",
            "type": "string"
          },
          "until": {
            "description": "ISO date (YYYY-MM-DD); events announced on/before.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "list_events"
    },
    {
      "description": "List available models with their current pricing. Optionally filter by provider.",
      "inputSchema": {
        "properties": {
          "include_unavailable": {
            "description": "Include deprecated/restricted/unavailable models. Default false.",
            "type": "boolean"
          },
          "limit": {
            "description": "Max rows to return. Default 200.",
            "maximum": 1000,
            "minimum": 1,
            "type": "integer"
          },
          "provider": {
            "description": "Provider id, e.g. anthropic, openai, google, venice, openrouter.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "list_models"
    }
  ]
}

What the leaf hashes

{"body":"707a9ede2ed0ce39c38bf68a685026ee8cdbd1de169295e1addbed089de1619d","id":383764,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793060150962603,"prev":null,"subject":"11e0548d-6c80-4dd9-af50-94cbf3b5cfbe","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-27 (273461 rows).

1. 0x68cce02da376c8b13242db5b58ba646fd49d41272e7a1d88626a2dbd033c2c48
2. 0x7cb8aea5ff61e7433c9968ac16bf6c6d88629a0b767b6800f947bc475afb1ac5
3. 0x4a7245c8edbb3207f16e4d5ae6fdc31860846c195a8a593666aa2b173d42f1bd
4. 0xe1a10ee0eaf737838256411249b2ae9525002d7c403d5c2f6079858ca910076d
5. 0xd1e6116d4f070d951f9eb53cf1a6938c0184d8b80e245579a0a09e89a9b4daf7
6. 0xb5ff0558e8bf84e07b6d50bb1e643a04e71e90cc457bac837aed6b6a6a325ad1
7. 0x1c2c7642a7372a299acc566e78257d31e296e5558088034667e78f7092ceb249
8. 0x1ea323f9d8243cb157125b4ebaf5950bd125ab466c11b4e59838408f3940355b
9. 0xa92cf4bdbef6aa0308726d7e56655899495da465050674bdd0fc447e2f65b578
10. 0x00ee4ec221924673fa6acf662f12cf709c2f0ca6c815942293292e8811f4ea9d
11. 0x3b2482479d5e8e62d596166a26d5feccca7716478708e2d2eb271e54277db5ce
12. 0xff1b653b4de97259c183e79b75886676f24cb64cb6bbe1a90b1639f9b46e2c0b
13. 0x927616fada4e04588c09f6e02e8f6e3a1351bac8355e394da3bd0bf249a5c503
14. 0x3c5462812bd2f841e3d7deefc01555f18262fe5e0d5a7eb155330b7a7cb0388e
15. 0x6f00f0da417f4126951ba8ba9b7962c847e91f5c61364ad9ad47e5f979698a60
16. 0x23cf9bb4337ee8be7fcae368fd69d24c62c11fb45882127b4cd919bb96a19996
17. 0x0e01aa9525097570a6edaf32bfc959de57bf5c24317cf10c0716affea85ca60d
18. 0xa20d48798a34aba12eb9c7297722982d910f06c148f5e27ac59307422964a585
19. 0x9fc354c0ea3efc3f1b6548bb77ea902a50f2c9647647ea61592efce2bd795699

Day root

0xdd77e5e99da32c3f154180d63e3c3e6fe11e896a2c6896412ef6b5c4bcf7e795

Chained

0x23bb4dfd09f55c15ac3962f53578e02c6114d5bfd9bb451cf8794fb6e2817ef4

Published

On Arc Testnet, block 69414147: 0xb2ebd83aafeb765a0ce66e76aefb133ed06606c98038fd56191e2bcd1dcb77b4