economics.runs
The raw facts every economics metric is computed from: each recorded run with its task, variant, repetition, model, revision, success-gate verdicts and the totals derived from its provider usage, and the path of its record.
The raw facts every economics metric is computed from: each recorded run with its task, variant, repetition, model, revision, success-gate verdicts and the totals derived from its provider usage, and the path of its record.
- query
- behaviorally_verified
- module economics
- #economics
- #evidence
Exposure
Where this one definition is reachable. Absence is explicit: a surface not listed does not carry it.
| surface | as |
|---|---|
| MCP | tool majordomus_economics_runs |
| HTTP | GET /api/v1/economics/runs operationId economics.runs |
| command line | majordomus economics runs |
Schemas
The canonical input and output, from the Rust types; the MCP tool schema and the OpenAPI parameters and responses are derived from these.
input · EconomicsRunsQuery
The input of
economics.runs: optional filters on suite, task and variant, all of which
must match. An empty query lists every recorded run, and an unknown field is refused.
use majordomus_cli::economics::model::EconomicsRunsQuery;
let wire = serde_json::json!({ "suite": "pilot", "variant": "baseline" });
let q: EconomicsRunsQuery = serde_json::from_value(wire.clone()).unwrap();
assert!(q.task.is_none(), "an absent filter matches every task");
assert_eq!(serde_json::to_value(&q).unwrap(), wire, "absent filters are not written back");
let by_model = serde_json::json!({ "model": "claude-sonnet-5" });
assert!(serde_json::from_value::<EconomicsRunsQuery>(by_model).is_err());| property | type | required | description |
|---|---|---|---|
| suite | string | null | no | Only this suite. |
| task | string | null | no | Only this task. |
| variant | string | null | no | Only this variant. |
JSON Schema
{
"additionalProperties": false,
"description": "The input of `economics.runs`: optional filters on suite, task and variant, all of which\nmust match. An empty query lists every recorded run, and an unknown field is refused.\n\n```\nuse majordomus_cli::economics::model::EconomicsRunsQuery;\nlet wire = serde_json::json!({ \"suite\": \"pilot\", \"variant\": \"baseline\" });\nlet q: EconomicsRunsQuery = serde_json::from_value(wire.clone()).unwrap();\nassert!(q.task.is_none(), \"an absent filter matches every task\");\nassert_eq!(serde_json::to_value(&q).unwrap(), wire, \"absent filters are not written back\");\nlet by_model = serde_json::json!({ \"model\": \"claude-sonnet-5\" });\nassert!(serde_json::from_value::<EconomicsRunsQuery>(by_model).is_err());\n```",
"properties": {
"suite": {
"description": "Only this suite.",
"type": [
"string",
"null"
]
},
"task": {
"description": "Only this task.",
"type": [
"string",
"null"
]
},
"variant": {
"description": "Only this variant.",
"type": [
"string",
"null"
]
}
},
"title": "EconomicsRunsQuery",
"type": "object"
}output · EconomicsRunList
The answer of
economics.runs: the raw facts every metric is computed from.
use majordomus_cli::economics::model::EconomicsRunList;
let l: EconomicsRunList =
serde_json::from_value(serde_json::json!({ "count": 0, "runs": [] })).unwrap();
assert_eq!(l.count, l.runs.len());
assert!(l.diagnostics.is_empty(), "no diagnostics listed means none");| property | type | required | description |
|---|---|---|---|
| count | integer | yes | How many. |
| diagnostics | array | no | Records that could not be read. default [] |
| runs | array | yes | The runs, sorted by id. |
JSON Schema
{
"$defs": {
"EconomicsCheck": {
"description": "One success gate's verdict on a run.\n\n```\nuse majordomus_cli::economics::model::EconomicsCheck;\nlet c = EconomicsCheck { id: \"tests_kept\".into(), passed: true, detail: \"0 deleted\".into() };\nlet back: EconomicsCheck = serde_json::from_value(serde_json::to_value(&c).unwrap()).unwrap();\nassert_eq!(back, c);\n```",
"properties": {
"detail": {
"description": "What was found.",
"type": "string"
},
"id": {
"description": "The gate's id.",
"type": "string"
},
"passed": {
"description": "Whether it passed.",
"type": "boolean"
}
},
"required": [
"id",
"passed",
"detail"
],
"type": "object"
},
"EconomicsRunView": {
"description": "One run in brief, with its derived totals.\n\n```\nuse majordomus_cli::economics::model::EconomicsRunView;\nlet v: EconomicsRunView = serde_json::from_value(serde_json::json!({\n \"id\": \"vat-rounding--majordomus--r1\", \"suite\": \"pilot\", \"task\": \"vat-rounding\",\n \"variant\": \"majordomus\", \"repetition\": 1, \"model\": \"claude-sonnet-5\",\n \"revision\": \"8d37d011ef\", \"completed\": false, \"checks\": [], \"sessions\": 1,\n \"path\": \".ai/repo/benchmarks/economics/runs/pilot/vat-rounding--majordomus--r1.json\"\n}))\n.unwrap();\nassert!(v.usage.is_none(), \"a run whose provider reported no usage has no totals\");\nassert!(v.path.ends_with(&format!(\"{}.json\", v.id)));\n```",
"properties": {
"checks": {
"description": "Each gate's verdict.",
"items": {
"$ref": "#/$defs/EconomicsCheck"
},
"type": "array"
},
"completed": {
"description": "Whether every success gate passed.",
"type": "boolean"
},
"id": {
"description": "The run's id.",
"type": "string"
},
"model": {
"description": "The model requested.",
"type": "string"
},
"path": {
"description": "Where the raw record is.",
"type": "string"
},
"repetition": {
"description": "The repetition.",
"format": "uint32",
"minimum": 0,
"type": "integer"
},
"revision": {
"description": "The revision.",
"type": "string"
},
"sessions": {
"description": "Sessions.",
"format": "uint",
"minimum": 0,
"type": "integer"
},
"suite": {
"description": "The suite.",
"type": "string"
},
"task": {
"description": "The task.",
"type": "string"
},
"usage": {
"anyOf": [
{
"$ref": "#/$defs/EconomicsUsage"
},
{
"type": "null"
}
],
"description": "Totals, when the provider reported usage."
},
"variant": {
"description": "The variant.",
"type": "string"
}
},
"required": [
"id",
"suite",
"task",
"variant",
"repetition",
"model",
"revision",
"completed",
"checks",
"sessions",
"path"
],
"type": "object"
},
"EconomicsUsage": {
"description": "A run's totals, derived from its raw usage.\n\n```\nuse majordomus_cli::economics::model::EconomicsUsage;\nlet u = EconomicsUsage {\n input_uncached: 10, cache_write: 90, cache_read: 900, output: 50,\n total_input: 1000, total: 1050, requests: 3, ..EconomicsUsage::default()\n};\nassert_eq!(u.total_input, u.input_uncached + u.cache_write + u.cache_read);\nlet json = serde_json::to_value(&u).unwrap();\nassert!(json.get(\"reasoning\").is_none() && json.get(\"cost_microusd\").is_none());\n```",
"properties": {
"cache_read": {
"description": "Input read from the cache.",
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"cache_write": {
"description": "Input written to the cache.",
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"cost_microusd": {
"description": "The harness's cost projection, in millionths of a dollar, when every session had one.",
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"input_uncached": {
"description": "Input neither read from nor written to the cache.",
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"output": {
"description": "Output, reasoning included.",
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"reasoning": {
"description": "Reasoning tokens, when every request reported them.",
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"requests": {
"description": "Provider requests.",
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"tool_calls": {
"description": "Tool calls.",
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"total": {
"description": "All input and output.",
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"total_input": {
"description": "All input.",
"format": "uint64",
"minimum": 0,
"type": "integer"
}
},
"required": [
"input_uncached",
"cache_write",
"cache_read",
"output",
"total_input",
"total",
"requests",
"tool_calls"
],
"type": "object"
}
},
"description": "The answer of `economics.runs`: the raw facts every metric is computed from.\n\n```\nuse majordomus_cli::economics::model::EconomicsRunList;\nlet l: EconomicsRunList =\n serde_json::from_value(serde_json::json!({ \"count\": 0, \"runs\": [] })).unwrap();\nassert_eq!(l.count, l.runs.len());\nassert!(l.diagnostics.is_empty(), \"no diagnostics listed means none\");\n```",
"properties": {
"count": {
"description": "How many.",
"format": "uint",
"minimum": 0,
"type": "integer"
},
"diagnostics": {
"default": [],
"description": "Records that could not be read.",
"items": {
"type": "string"
},
"type": "array"
},
"runs": {
"description": "The runs, sorted by id.",
"items": {
"$ref": "#/$defs/EconomicsRunView"
},
"type": "array"
}
},
"required": [
"count",
"runs"
],
"title": "EconomicsRunList",
"type": "object"
}Policies
- benchmark
- required — a target on every transport the exposure declares; the cases are the input type's
- cache
- process — up to 16 entries in the process, 5s each, scoped by the registry fingerprint
Benchmark targets
Derived from the registry for this repository: one requirement per transport, and the cases the input type provides. The whole matrix is on the benchmarks page.