The guardrails' judge has its own command, and its trouble is shown
llmgw ctl guard judge status lists each judge model the policies ask: in the catalog, as a judge, replicas ready, its last failure to answer, and what is wrong in words. enable serves the missing one through model serve - Llama Guard 3 1B on CPUs, role guard, under the name the policies give it - with --replace for a model of that name that is not a judge; the console has it under Do. GET /api/v1/guard/judges, and the summary's judges, put the problem on ctl status and the console's Overview. A Llama Guard file served from the mirror page is added as a judge, under the name the policies ask, rather than as a model clients use the policies never find. ctl says plainly when the API answers with a page. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
2a942409ea
commit
a8bb417618
24 files changed
+667
-13
No files matched your search
@@ -894,6 +894,36 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"/api/v1/guard/judges": {
|
||||
"get": {
|
||||
"operationId": "getGuardJudges",
|
||||
"summary": "The judge models the policies ask, and what is wrong with each",
|
||||
"tags": [
|
||||
"guard"
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/JudgeView"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"401": {
|
||||
"$ref": "#/components/responses/Unauthorized"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/Error"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/api/v1/jobs": {
|
||||
"get": {
|
||||
"operationId": "getJobs",
|
||||
@@ -4359,6 +4389,52 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"JudgeView": {
|
||||
"type": "object",
|
||||
"description": "JudgeView is one judge model the guardrail policies ask, and whether it can answer them.",
|
||||
"properties": {
|
||||
"model": {
|
||||
"type": "string"
|
||||
},
|
||||
"policies": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": "Policies are those that ask it; Closed those that refuse what it cannot read (fail: closed)."
|
||||
},
|
||||
"closed": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"in_catalog": {
|
||||
"type": "boolean",
|
||||
"description": "InCatalog is whether a model of that name is in the catalog, and Judge whether it is there as a judge (role: guard)."
|
||||
},
|
||||
"judge": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"ready_replicas": {
|
||||
"type": "integer"
|
||||
},
|
||||
"wanted_replicas": {
|
||||
"type": "integer"
|
||||
},
|
||||
"last_error": {
|
||||
"type": "string",
|
||||
"description": "LastError is its last failure to give a verdict, if any."
|
||||
},
|
||||
"last_error_at": {
|
||||
"type": "string"
|
||||
},
|
||||
"problem": {
|
||||
"type": "string",
|
||||
"description": "Problem says, in words, what is wrong and what to do; empty when nothing is."
|
||||
}
|
||||
}
|
||||
},
|
||||
"Live": {
|
||||
"type": "object",
|
||||
"description": "Live is one of the cluster's adapters as its node last reported it.",
|
||||
@@ -5696,6 +5772,13 @@
|
||||
"control_planes": {
|
||||
"$ref": "#/components/schemas/ControlPlanes",
|
||||
"description": "ControlPlanes is the cluster's control planes when there is more than one: which leads, which stand by, and the floating address in front."
|
||||
},
|
||||
"judges": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/JudgeView"
|
||||
},
|
||||
"description": "Judges are the guardrails' judge models with something wrong."
|
||||
}
|
||||
}
|
||||
},
|
||||
|
||||
Reference in new issue
Block a user