HALOWERKAialignwerk
resource hog
Divides observed CPU, memory-time, network, tool-call and wall-time usage by caller-supplied budgets, reports exceeded dimensions and ranks observations by the maximum ratio. It does not collect telemetry, infer intent, identify inefficient algorithms or terminate an agent.
POST https://aialign.halowerk.com/v1/resource-hogEingaben
| Feld | Typ | Pflicht | Beschreibung |
|---|---|---|---|
| budgets | object | Ja | |
| observations | array | Ja |
Vollständiges Eingabeschema anzeigen
{
"type": "object",
"required": [
"budgets",
"observations"
],
"additionalProperties": false,
"properties": {
"budgets": {
"type": "object",
"required": [
"cpu_seconds",
"memory_gb_seconds",
"network_mb",
"tool_calls",
"wall_seconds"
],
"additionalProperties": false,
"properties": {
"cpu_seconds": {
"type": "number",
"minimum": 1e-06,
"maximum": 1000000000000000
},
"memory_gb_seconds": {
"type": "number",
"minimum": 1e-06,
"maximum": 1000000000000000000
},
"network_mb": {
"type": "number",
"minimum": 1e-06,
"maximum": 1000000000000000
},
"tool_calls": {
"type": "number",
"minimum": 1e-06,
"maximum": 1000000000000
},
"wall_seconds": {
"type": "number",
"minimum": 1e-06,
"maximum": 1000000000000000
}
}
},
"observations": {
"type": "array",
"minItems": 1,
"maxItems": 100000,
"items": {
"type": "object",
"required": [
"agent_id",
"cpu_seconds",
"memory_gb_seconds",
"network_mb",
"tool_calls",
"wall_seconds"
],
"additionalProperties": false,
"properties": {
"agent_id": {
"type": "string",
"minLength": 1,
"maxLength": 128
},
"cpu_seconds": {
"type": "number",
"minimum": 0,
"maximum": 1000000000000000
},
"memory_gb_seconds": {
"type": "number",
"minimum": 0,
"maximum": 1000000000000000000
},
"network_mb": {
"type": "number",
"minimum": 0,
"maximum": 1000000000000000
},
"tool_calls": {
"type": "integer",
"minimum": 0,
"maximum": 1000000000000
},
"wall_seconds": {
"type": "number",
"minimum": 0,
"maximum": 1000000000000000
}
}
}
}
}
}Veröffentlichtes Eingabebeispiel
{
"budgets": {
"cpu_seconds": 600,
"memory_gb_seconds": 2400,
"network_mb": 500,
"tool_calls": 80,
"wall_seconds": 900
},
"observations": [
{
"agent_id": "planner-1",
"cpu_seconds": 410,
"memory_gb_seconds": 1900,
"network_mb": 130,
"tool_calls": 44,
"wall_seconds": 720
},
{
"agent_id": "crawler-2",
"cpu_seconds": 780,
"memory_gb_seconds": 3200,
"network_mb": 940,
"tool_calls": 115,
"wall_seconds": 880
}
]
}Ergebnis & Dokumentation
Veröffentlichtes Ergebnisschema anzeigen
{
"$ref": "https://aialign.halowerk.com/v1/resource-hog/schema#/outputSchema"
}Veröffentlichtes Ergebnisbeispiel öffnen
Maschinenlesbare Dokumentation dieses Hubs
Quelle dieser Seite: der veröffentlichte HALOWERK-Katalog. Stand: 2026-11-01, 15:19 UTC.
Weitere Endpunkte dieses Hubs
- Aialignwerk0,005 USDC
agent collusion
POSThttps://aialign.halowerk.com/v1/agent-collusionRequires the same agents in each supplied round, computes each pair’s observed action agreement, expected agreement from marginal action frequencies and chance-corrected kappa, then flags high positive agreement against a supplied threshold
- Aialignwerk0,004 USDC
bias audit
POSThttps://aialign.halowerk.com/v1/bias-auditCalculates each group positive-outcome rate, compares it with an explicit or automatically selected reference group, and reports rate differences and selection-rate ratios. Aggregate disparity metrics do not establish discrimination, fairne
- Aialignwerk0,003 USDC
capability eval
POSThttps://aialign.halowerk.com/v1/capability-evalComputes weighted pass rates and weighted scores from caller-labeled test outcomes, with deterministic category summaries. It does not run tests, validate labels, measure untested capabilities or establish deployment safety; the result is o