Evidence row 812658

What was observed

{
  "count": 5,
  "tools": [
    {
      "description": "No API key needed. Static-analyze a public GitHub repo (e.g. {\"repo\": \"owner/name\"}) or a set of source files for LLM token waste: uncached static prompts, frontier models on extraction tasks, hot loops, non-deterministic repeat calls, and prompt-caching mis-integration (caching gated on model names, volatile values in the system prompt, random ids in history, wrong-provider cache markers, misplaced breakpoints, cost math that ignores cached tokens). Returns findings with fixes and an estimated recoverable percentage.",
      "inputSchema": {
        "properties": {
          "files": {
            "description": "Alternative to repo: files to analyze",
            "items": {
              "properties": {
                "content": {
                  "type": "string"
                },
                "path": {
                  "type": "string"
                }
              },
              "required": [
                "path",
                "content"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "repo": {
            "description": "GitHub owner/name (public)",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "audit_repo_token_waste"
    },
    {
      "description": "No API key needed; only `model` is required (e.g. {\"model\": \"gpt-6.1-sol\"}, defaults 2,000 tokens in and 400 out). Price a workload at list prices across models: cost per request and per month for the requested model, its cheaper sibling, and the effect of prompt caching. Pricing table version 2026-10-28.",
      "inputSchema": {
        "properties": {
          "compare_to": {
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "input_tokens": {
            "description": "per request; default 2000",
            "type": "number"
          },
          "model": {
            "description": "model id, e.g. gpt-6.1-sol or claude-sonnet-5-5",
            "type": "string"
          },
          "output_tokens": {
            "description": "per request; default 400",
            "type": "number"
          },
          "requests_per_month": {
            "type": "number"
          },
          "static_tokens": {
            "description": "portion of input_tokens that is a fixed prefix (system + tools)",
            "type": "number"
          }
        },
        "required": [
          "model"
        ],
        "type": "object"
      },
      "name": "calculate_model_arbitrage"
    },
    {
      "description": "No API key needed. Rewrite an OpenAI Chat/Responses or Anthropic Messages request body so its static prefix is provider-cacheable (Anthropic cache_control breakpoints, OpenAI prompt_cache_key). Returns the optimized body, what changed, the token profile and the projected per-request saving. Never changes the tokens the model sees.",
      "inputSchema": {
        "properties": {
          "body": {
            "description": "The request body",
            "type": "object"
          },
          "endpoint": {
            "enum": [
              "/v1/chat/completions",
              "/v1/responses",
              "/v1/messages"
            ],
            "type": "string"
          },
          "strategy": {
            "enum": [
              "static",
              "conversation"
            ],
            "type": "string"
          }
        },
        "required": [
          "body"
        ],
        "type": "object"
      },
      "name": "optimize_prompt_payload"
    },
    {
      "description": "Create a TokenZero workspace and key with no form. Returns the key once, the base URLs that route through it (OPENAI_BASE_URL / ANTHROPIC_BASE_URL), the one-click dashboard link and the badge URL. Free up to the monthly free tier; nothing is billed.",
      "inputSchema": {
        "properties": {
          "name": {
            "description": "workspace name (default mcp-agent)",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "provision_workspace"
    },
    {
      "description": "Live value scorecard for a TokenZero workspace: hard savings and net ROI per window, the four engines' contribution, speed, parity, availability and privacy posture, per-model breakdown and one-click recommendations. Needs the workspace key (tz_live_…); pass demo: true for a labelled sample.",
      "inputSchema": {
        "properties": {
          "demo": {
            "description": "return the sample scorecard instead",
            "type": "boolean"
          },
          "key": {
            "description": "workspace key (tz_live_…)",
            "type": "string"
          },
          "window": {
            "enum": [
              "24h",
              "7d",
              "30d",
              "all"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "workspace_metrics"
    }
  ]
}

What the leaf hashes

{"body":"ddc65eb1222f557183d020e516072fcb70ca897c498c1ca0513b778041a5ab11","id":812658,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793227962874065,"prev":766683,"subject":"4ae7b41c-60da-4ff7-994c-e845fb4edd7f","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-28 (231336 rows).

1. 0x37b83afdb3673e23421ed1f8f9647f3a73307485ea37bfcd46cf6a92673b8937
2. 0x751f572c8b6f49d6e0a654471261bb3c08dfb24d40c945cc25d6c4be89c38637
3. 0x0c8cd9bcccc043bd06d39654936d752f46e3d60b96e857ee2e24ad152d3c67f5
4. 0x0a31e68c693dca8e28e1ec23512e08c83401b82ae8aeadf910a4fa0ce9c3e9d4
5. 0x67f585bc2002fe1575c9ce05b8c6138c142e106ab9c9bab3ee7b74322eba67f8
6. 0xe6a13d1372dca1471dfde4d5fbf8189378fe8645e8fe7df3a0264a92bb76a6fa
7. 0xe0220a68dd58b533d6ad11040d2681ddaba20afe9be2f8eab866588b80792016
8. 0x5faf5eed72677a756fd0a1068effccf11e4f8d7ec318715d8502b9023c6373b2
9. 0xea6f62a16d993d749edd42afe0ea914e717c52712a04af109817605dd0d1020f
10. 0x14adbdf98cf2be780228d81e63d754a8235c8e467624fd5dd24289bcebc5c320
11. 0x7dfc938b15102117430ae68c0e61eaca99cea599701570a861f1e2b69c4f4bb7
12. 0x85a553efb556dd0b17c3ea6b3f000bb15ec137986a3b9a565d1ebd682306822f
13. 0x90adeeedf0030839d1cf4653c4092b1bee2a90ffabedf937d55b4fa91e36cb1b
14. 0x7b2e5f158ccf01de5b2c0c5b723d8c5a690e0d4e9302d283bc82cd202622595e
15. 0x91690f98682e078d41b8b72edeaea70473545a876fc3baa645fc988225096386
16. 0xaeb1503e5d0d358b256ba97a10178c357ddb8f55cc961925ccf0458aae5ebcae
17. 0xf078ea7d84d98dbeffed23d8e67b36751e60464ffd4cfdc005e0aa6f8cb9b459
18. 0xe027395fafb7fc41921c42ca0542524ea22204cbd5908b70b27f3d5fb26f5d0f

Day root

0x2c19037464cc4c493624565f01775d6446fc78eaa118fc6865bfe2bfca9ff78e

Chained

0xd1d7dee8322ceff8f4c8d83aa1fe4a4466825c2af1c97dbde3d35db61234f7be

Published

On Arc Testnet, block 69584042: 0x8bae2b1d097834c8b458513862d70d29ee807e98dc2e863b27250131c15b35ae