judge-laya
v0.2.2laya provider for the judge hub (judge-laya::evaluate, judge-laya::models::list, judge-laya::cancel) — the ModernBERT typed-decision checkpoints (English, multilingual, typed-decisions) downloaded from the Hugging Face Hub and run in-process with language routing; no API key or external service.
Install
iii trigger compose::add worker=judge-laya@0.2.2Run in your project with the iii engine running. Exact versions are immutable and digest-pinned.
Full markdown
/workers/judge-laya.md?version=0.2.2. Paste it into an LLM prompt or pipe it through curl from a worker.Install
iii trigger compose::add worker=judge-laya@0.2.2Configuration
- auto_route: false
auto_task_detection: false
batch_questions: 16
max_request_bytes: 8388608
max_timeout_ms: 300000
model: laya
preload:
threads: 8Dependencies
Readme
judge-laya
laya provider for the judge
hub, running inside the worker: no API key, no Python, no external service.
laya is a typed-decision model (ModernBERT-large 421M for English,
mmBERT-base 322M for 100+ languages, Apache-2.0) that answers Noul, Choice and
Score questions over JSON state in one encoder pass per question. The
checkpoint runs in llama.cpp (crates/llama-native, the engine every local
judge provider shares), the encoder and laya's decision head in one graph,
on the CPU, on Metal
(macOS) or on Vulkan (Linux x86_64: AMD, NVIDIA and Intel GPUs), picked
automatically at start.
Install
iii trigger compose::add worker=judge-layaThe functions register at start; the checkpoints load on demand. While laya
is the judge hub's default provider (provider: laya under Settings →
Workers → judge) they load at once and stay loaded. Otherwise the first call
that names "provider": "laya" (or comes from a session that picked it) loads
them, and they are released (VRAM included) after 10 minutes without calls; a
call that cannot wait for the load answers deadline while the load goes on
for the next one. The first load downloads the checkpoint
(843 MB for laya, 644 MB for laya-multilingual) from the Hugging Face Hub
into the hf-hub cache ($HF_HOME, default ~/.cache/huggingface) and
converts it once to the GGUF llama.cpp loads, under $HF_HOME/judge-laya/
(keyed by model and revision; under a second for laya, 844 MB).
To keep the checkpoints loaded while another provider is the default, turn
on Keep every local provider loaded (preload_all) in the judge settings.
A hub build that does not expose judge::configuration-id keeps the
checkpoints loaded from the start.
Air-gapped installs point III_LAYA_CHECKPOINT_DIR at
a directory holding model.safetensors, encoder/config.json,
rl_agent_config.json and tokenizer.json (plus an optional pre-converted
model.gguf; without it the checkpoint is converted into the temporary
directory); III_LAYA_GGUF swaps only the GGUF of the default model, and
cargo run --example convert_gguf converts one ahead of time.
The GGUF holds the checkpoint's own (fine-tuned) encoder and decision head
(two pre-norm blocks, the scorer and the question-type embedding) in
llama.cpp's modern-bert layout with a laya decision head, written by the
worker (src/gguf.rs): its tensors match b11379's convert_hf_to_gguf.py
byte for byte on all three checkpoints, and so do its model and decision.*
keys; it leaves out only that converter's names, classifier pooling, chat
template and llama.cpp tokenizer settings, and names pooling none and the
vocabulary's end of text as EOS, so llama.cpp loads it without warnings
(tests/gguf.rs checks the tiny checkpoint against the converter's output).
The graph scores every token for each question type; the worker reads its
question's column at the [MASK] markers (no pooling). Matrices stay f16:
Q8_0 moved laya's calibrated probabilities by up to 0.04 and flipped one
fixture answer at 512 tokens.
Hardware selection
- macOS: Metal is linked in; Apple Silicon GPUs run the model.
- Linux x86_64: llama.cpp's backends are modules loaded at start from the
binary's directory. The Vulkan module loads wherever a Vulkan loader and
driver exist (
libvulkan.so.1); without them it is skipped and the CPU runs the model. The package shipslibllama,libggml,libggml-base, the CPU variants and the Vulkan module beside the binary (the same layout as judge-clef). - Linux aarch64: CPU, statically linked.
gpu_layers: 0 keeps the model on the CPU even when a GPU is present. The
chosen device is logged at start as selected inference device and shown in
the settings form.
Make it the default under Settings → Workers → judge, then call the hub:
iii trigger judge::evaluate --timeout-ms 65000 --json '{
"timeout_ms": 60000, "provider": "laya",
"evaluations": [{
"id": "ticket-4411",
"state": {"subject": "Duplicate charge on invoice #4411",
"body": "We were billed twice for March. Refund the duplicate today or we cancel."},
"questions": {
"department": {"type": "choice", "criteria": {"billing": "invoices, payments, refunds", "technical": "bugs, outages"}},
"urgency": {"type": "score", "criteria": ["not urgent", "soon", "critical deadline or blocking issue"]},
"churn_risk": {"type": "noul", "instructions": "Does the user threaten to cancel or leave?"}
}
}]
}'Answers follow the shared contract exactly: noul is P(true); choice carries
the option probabilities and confidence; score carries the level
distribution, the probability-weighted score, confidence and the legend.
confidence is TypeSafe's (judge_contract::confidence), read from the
probabilities after the checkpoint's per-bucket temperature:
(n·p_max − 1) / (n − 1) for a choice, 1 − the expected distance from the
likeliest level over the levels' mean distance from the middle for a score. usage.input_tokens counts encoder
tokens, output_tokens is always 0 and usage_complete is true.
Measured on an i9-14900K and an RX 6900 XT (laya, warm medians): on Vulkan
one 43-token question answers in 17 ms, four questions over a ticket in 37 ms,
one full 512-token row in 47 ms and 16 of them (one 8192-token pass) in
0.67 s, 2–5x faster than when the decision head ran in candle on the CPU. On
the CPU (8 threads) the same requests take 0.08 s, 0.47 s, 0.8 s and 15 s:
the graph runs the head for all three question types, up to 16% slower than
the candle head was. Rows that fill the window cost more; laya's
bidirectional encoder reads state and question together, so nothing is shared
between questions (no prefix reuse). Keep timeout_ms honest for a big state
with a hundred questions, or route such callers to a hosted provider.
Configuration
Settings → Workers → judge-laya:
| Field | Default | Applied |
|---|---|---|
model |
laya |
next start (laya-multilingual for non-English, laya-typed-decisions for laya's four workflows) |
preload |
[] |
next start (extra checkpoints, ~1 GB of RAM each; 1.6 GB on the CPU) |
auto_route |
false |
new calls |
auto_task_detection |
false |
new calls |
revision |
main |
next start |
threads |
min(8, logical cores) | next start |
gpu_layers |
all layers when a GPU backend and device exist | next start (0 = CPU) |
batch_questions |
16 | new calls (at most 8192 tokens per pass: 8 questions for the 1024-token checkpoints) |
max_request_bytes |
8388608 | new calls |
max_timeout_ms |
300000 | new calls |
The form shows which checkpoint the running worker actually loaded (through
judge-laya::models::list, one card per loaded checkpoint with its
context_window) and warns when the selection needs a restart.
Routing (laya 0.3.5 Router)
A request naming model uses that checkpoint, which must be model or in
preload (invalid_request otherwise). Without it, each evaluation picks its
own checkpoint: with auto_task_detection, question ids that exactly form one
of laya's four typed-decisions workflows (agent_trace_observability,
customer_service, invoice_processing, security_incidents) go to
laya-typed-decisions; with auto_route, the state's script and language
(laya's dependency-free detector, ported with its fixtures) send non-English
states to laya-multilingual and English ones to laya. A target that is not
loaded falls back to the default. The response model is the checkpoint every
evaluation used, or the default when they differ; one forward never mixes
checkpoints.
Encoding notes
State and structured criteria are serialized exactly as laya's Python
json.dumps (", " and ": " separators), because the checkpoint was trained
on that spelling. Choice options are encoded in the contract's key order, and
JSON object keys (state, criteria) arrive sorted through the bus, so the
same logical request can tokenize differently than in Python laya, whose dicts
keep insertion order. laya is order-sensitive (one ticket flipped from
billing 0.57 to sales 0.69 when its four options were reordered), so
answers here are deterministic but not byte-identical to Python's; the port
itself matches Python's logits to 1e-4 on identical token sequences for the
English and multilingual checkpoints.
Sequences are capped at the checkpoint's window (512 tokens for laya, 1024
for laya-multilingual and laya-typed-decisions; option text ≤48 tokens
each, header ≤192 or ≤256): a request
whose options cannot all fit answers payload_too_large, longer states are
truncated on the right (logged as state truncated to the checkpoint window;
the model then answers without the dropped part). Requests naming a model
that is not loaded answer invalid_request.
For the full API, read the hub's reference.
Building
llama.cpp b11379 is compiled from source through crates/llama-native (see
judge-clef's README): curl, tar, patch, cmake and a C++17 compiler
are required, and no libclang; an offline build points
III_LLAMA_CPP_TARBALL at a copy of the source archive. Linux x86_64 builds
also need the Vulkan loader headers, the SPIR-V headers and glslc (Ubuntu:
libvulkan-dev spirv-headers glslc) to compile the Vulkan module. The build
copies the modules and libraries beside the binary, so target/release has
the published layout; the release catalog ships them as the artifact's
companions. Windows is not published yet.
API reference (JSON)
{
"functions": [
{
"description": "Signal cancellation of an active evaluation owned by the calling worker; the current batch finishes, later batches are skipped. Requires the same worker replica as the original call.",
"metadata": {
"internal": true
},
"name": "judge-laya::cancel",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"request_id": {
"maxLength": 128,
"minLength": 1,
"type": "string"
}
},
"required": [
"request_id"
],
"title": "CancelRequest",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"ErrorCode": {
"oneOf": [
{
"enum": [
"invalid_request",
"missing_key",
"payload_too_large",
"deadline",
"attempt_timeout",
"cancelled",
"http",
"transport",
"invalid_response"
],
"type": "string"
},
{
"description": "The selected `judge-<provider>` worker is not registered on the engine, or (a local provider) its model failed to load.",
"enum": [
"provider_unavailable"
],
"type": "string"
}
]
}
},
"oneOf": [
{
"additionalProperties": false,
"properties": {
"cancelled": {
"type": "boolean"
},
"status": {
"enum": [
"ok"
],
"type": "string"
}
},
"required": [
"cancelled",
"status"
],
"type": "object"
},
{
"additionalProperties": false,
"properties": {
"code": {
"$ref": "#/definitions/ErrorCode"
},
"status": {
"enum": [
"error"
],
"type": "string"
}
},
"required": [
"code",
"status"
],
"type": "object"
}
],
"title": "CancelResponse"
}
},
{
"description": "Returns this worker instance's effective configuration entry ID, without its value.",
"metadata": {
"internal": true
},
"name": "judge-laya::configuration-id",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Empty user request. Ignore transport metadata such as `_caller_worker_id`, which the engine adds to routed calls; no payload field selects the entry.",
"title": "ConfigurationIdentityRequest",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Only the entry ID is exposed; configuration values and secrets stay in the service.",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"title": "ConfigurationIdentityResponse",
"type": "object"
}
},
{
"description": "Evaluate Noul, Choice and Score questions against arbitrary JSON state with the laya model running inside this worker. Results are atomic; usage counts encoder tokens. No credentials or endpoints are accepted in the request.",
"metadata": {
"internal": true
},
"name": "judge-laya::evaluate",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"definitions": {
"Content": {
"anyOf": [
{
"type": "string"
},
{
"additionalProperties": true,
"type": "object"
},
{
"items": true,
"type": "array"
},
{
"type": "null"
}
],
"description": "Structured provider descriptions; top-level numbers/bools are not descriptions."
},
"Evaluation": {
"additionalProperties": false,
"properties": {
"id": {
"type": "string"
},
"questions": {
"additionalProperties": {
"$ref": "#/definitions/Question"
},
"minProperties": 1,
"type": "object"
},
"state": {
"$ref": "#/definitions/ScoreLevel"
}
},
"required": [
"id",
"questions",
"state"
],
"type": "object"
},
"Question": {
"oneOf": [
{
"additionalProperties": false,
"properties": {
"criteria": {
"anyOf": [
{
"additionalProperties": false,
"properties": {
"false": {
"$ref": "#/definitions/Content"
},
"true": {
"$ref": "#/definitions/Content"
}
},
"type": "object"
},
{
"type": "null"
}
]
},
"instructions": {
"allOf": [
{
"$ref": "#/definitions/Content"
}
],
"default": null
},
"type": {
"enum": [
"noul"
],
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
},
{
"additionalProperties": false,
"properties": {
"criteria": {
"additionalProperties": {
"$ref": "#/definitions/Content"
},
"maxProperties": 255,
"minProperties": 1,
"type": "object"
},
"instructions": {
"allOf": [
{
"$ref": "#/definitions/Content"
}
],
"default": null
},
"type": {
"enum": [
"choice"
],
"type": "string"
}
},
"required": [
"criteria",
"type"
],
"type": "object"
},
{
"additionalProperties": false,
"properties": {
"criteria": {
"items": {
"$ref": "#/definitions/ScoreLevel"
},
"maxItems": 10,
"minItems": 2,
"type": "array"
},
"instructions": {
"allOf": [
{
"$ref": "#/definitions/Content"
}
],
"default": null
},
"type": {
"enum": [
"score"
],
"type": "string"
}
},
"required": [
"criteria",
"type"
],
"type": "object"
}
]
},
"RequestOptions": {
"additionalProperties": false,
"properties": {
"attempt_timeout_ms": {
"description": "Bounds each network attempt separately from the whole-call deadline.",
"format": "uint64",
"minimum": 1,
"type": [
"integer",
"null"
]
}
},
"type": "object"
},
"ScoreLevel": {
"anyOf": [
{
"type": "string"
},
{
"additionalProperties": true,
"type": "object"
},
{
"items": true,
"type": "array"
}
],
"description": "Score levels require a description. Unlike instructions, Choice option descriptions and Noul criteria, the provider rejects a null level (HTTP422)."
}
},
"properties": {
"evaluations": {
"items": {
"$ref": "#/definitions/Evaluation"
},
"maxItems": 512,
"minItems": 1,
"type": "array"
},
"expires_at_unix_ms": {
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"model": {
"type": [
"string",
"null"
]
},
"options": {
"allOf": [
{
"$ref": "#/definitions/RequestOptions"
}
],
"default": {}
},
"request_id": {
"maxLength": 128,
"minLength": 1,
"type": [
"string",
"null"
]
},
"timeout_ms": {
"format": "uint64",
"minimum": 1,
"type": "integer"
}
},
"required": [
"evaluations",
"timeout_ms"
],
"title": "EvaluateRequest",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"Answer": {
"oneOf": [
{
"additionalProperties": false,
"properties": {
"noul": {
"format": "double",
"type": "number"
},
"type": {
"enum": [
"noul"
],
"type": "string"
}
},
"required": [
"noul",
"type"
],
"type": "object"
},
{
"additionalProperties": false,
"properties": {
"choice": {
"type": "string"
},
"confidence": {
"format": "double",
"type": "number"
},
"probabilities": {
"additionalProperties": {
"format": "double",
"type": "number"
},
"type": "object"
},
"type": {
"enum": [
"choice"
],
"type": "string"
}
},
"required": [
"choice",
"confidence",
"probabilities",
"type"
],
"type": "object"
},
{
"additionalProperties": false,
"properties": {
"confidence": {
"format": "double",
"type": "number"
},
"legend": {
"additionalProperties": {
"$ref": "#/definitions/ScoreLevel"
},
"type": "object"
},
"probabilities": {
"additionalProperties": {
"format": "double",
"type": "number"
},
"type": "object"
},
"score": {
"format": "double",
"type": "number"
},
"type": {
"enum": [
"score"
],
"type": "string"
}
},
"required": [
"confidence",
"legend",
"probabilities",
"score",
"type"
],
"type": "object"
}
]
},
"ErrorCode": {
"oneOf": [
{
"enum": [
"invalid_request",
"missing_key",
"payload_too_large",
"deadline",
"attempt_timeout",
"cancelled",
"http",
"transport",
"invalid_response"
],
"type": "string"
},
{
"description": "The selected `judge-<provider>` worker is not registered on the engine, or (a local provider) its model failed to load.",
"enum": [
"provider_unavailable"
],
"type": "string"
}
]
},
"EvaluationResult": {
"additionalProperties": false,
"properties": {
"answers": {
"additionalProperties": {
"$ref": "#/definitions/Answer"
},
"type": "object"
},
"usage": {
"anyOf": [
{
"$ref": "#/definitions/Usage"
},
{
"type": "null"
}
]
}
},
"required": [
"answers"
],
"type": "object"
},
"ProviderError": {
"additionalProperties": false,
"description": "Bounded provider diagnostics, with credentials and supplied header values redacted.",
"properties": {
"detail": true,
"message": {
"type": [
"string",
"null"
]
},
"truncated": {
"default": false,
"type": "boolean"
}
},
"type": "object"
},
"ScoreLevel": {
"anyOf": [
{
"type": "string"
},
{
"additionalProperties": true,
"type": "object"
},
{
"items": true,
"type": "array"
}
],
"description": "Score levels require a description. Unlike instructions, Choice option descriptions and Noul criteria, the provider rejects a null level (HTTP422)."
},
"Stats": {
"additionalProperties": false,
"description": "Known accepted usage, never a billing estimate. Unreported counters or failure/cancellation make usage_complete false.",
"properties": {
"attempts": {
"format": "uint",
"minimum": 0,
"type": "integer"
},
"elapsed_ms": {
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"input_tokens": {
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"output_tokens": {
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"questions": {
"format": "uint",
"minimum": 0,
"type": "integer"
},
"requests": {
"format": "uint",
"minimum": 0,
"type": "integer"
},
"usage_complete": {
"type": "boolean"
}
},
"required": [
"attempts",
"elapsed_ms",
"input_tokens",
"output_tokens",
"questions",
"requests",
"usage_complete"
],
"type": "object"
},
"Usage": {
"additionalProperties": false,
"description": "Each absent/null counter is unknown, independently of the other counter.",
"properties": {
"input_tokens": {
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"output_tokens": {
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
}
},
"type": "object"
}
},
"oneOf": [
{
"additionalProperties": false,
"properties": {
"model": {
"type": "string"
},
"results": {
"additionalProperties": {
"$ref": "#/definitions/EvaluationResult"
},
"type": "object"
},
"stats": {
"$ref": "#/definitions/Stats"
},
"status": {
"enum": [
"ok"
],
"type": "string"
}
},
"required": [
"model",
"results",
"stats",
"status"
],
"type": "object"
},
{
"additionalProperties": false,
"properties": {
"code": {
"$ref": "#/definitions/ErrorCode"
},
"http_status": {
"format": "uint16",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"provider_error": {
"anyOf": [
{
"$ref": "#/definitions/ProviderError"
},
{
"type": "null"
}
]
},
"retry_after_ms": {
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"stats": {
"$ref": "#/definitions/Stats"
},
"status": {
"enum": [
"error"
],
"type": "string"
}
},
"required": [
"code",
"stats",
"status"
],
"type": "object"
}
],
"title": "EvaluateResponse"
}
},
{
"description": "Describe the laya checkpoints, loading them if needed (name, encoder, revision, context window); the first card is the default. Performs no inference.",
"metadata": {
"internal": true
},
"name": "judge-laya::models::list",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"definitions": {
"RequestOptions": {
"additionalProperties": false,
"properties": {
"attempt_timeout_ms": {
"description": "Bounds each network attempt separately from the whole-call deadline.",
"format": "uint64",
"minimum": 1,
"type": [
"integer",
"null"
]
}
},
"type": "object"
}
},
"properties": {
"expires_at_unix_ms": {
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"options": {
"allOf": [
{
"$ref": "#/definitions/RequestOptions"
}
],
"default": {}
},
"request_id": {
"maxLength": 128,
"minLength": 1,
"type": [
"string",
"null"
]
},
"timeout_ms": {
"default": 30000,
"format": "uint64",
"minimum": 1,
"type": "integer"
}
},
"title": "ModelsRequest",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"ErrorCode": {
"oneOf": [
{
"enum": [
"invalid_request",
"missing_key",
"payload_too_large",
"deadline",
"attempt_timeout",
"cancelled",
"http",
"transport",
"invalid_response"
],
"type": "string"
},
{
"description": "The selected `judge-<provider>` worker is not registered on the engine, or (a local provider) its model failed to load.",
"enum": [
"provider_unavailable"
],
"type": "string"
}
]
},
"ModelCard": {
"properties": {
"context_window": {
"description": "Tokens one evaluation row can hold (question, options and state), when the provider has a fixed window. Callers size their states from it.",
"format": "uint32",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"description": {
"type": "string"
},
"max_options": {
"description": "Most options one Choice question (or levels one Score) can offer, when the provider has a fixed limit below the contract's 255. Callers size their option groups from it.",
"format": "uint32",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"name": {
"type": "string"
},
"release_date": {
"type": "string"
}
},
"required": [
"description",
"name",
"release_date"
],
"type": "object"
},
"ProviderError": {
"additionalProperties": false,
"description": "Bounded provider diagnostics, with credentials and supplied header values redacted.",
"properties": {
"detail": true,
"message": {
"type": [
"string",
"null"
]
},
"truncated": {
"default": false,
"type": "boolean"
}
},
"type": "object"
},
"Stats": {
"additionalProperties": false,
"description": "Known accepted usage, never a billing estimate. Unreported counters or failure/cancellation make usage_complete false.",
"properties": {
"attempts": {
"format": "uint",
"minimum": 0,
"type": "integer"
},
"elapsed_ms": {
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"input_tokens": {
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"output_tokens": {
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"questions": {
"format": "uint",
"minimum": 0,
"type": "integer"
},
"requests": {
"format": "uint",
"minimum": 0,
"type": "integer"
},
"usage_complete": {
"type": "boolean"
}
},
"required": [
"attempts",
"elapsed_ms",
"input_tokens",
"output_tokens",
"questions",
"requests",
"usage_complete"
],
"type": "object"
}
},
"oneOf": [
{
"additionalProperties": false,
"properties": {
"models": {
"items": {
"$ref": "#/definitions/ModelCard"
},
"type": "array"
},
"stats": {
"$ref": "#/definitions/Stats"
},
"status": {
"enum": [
"ok"
],
"type": "string"
}
},
"required": [
"models",
"stats",
"status"
],
"type": "object"
},
{
"additionalProperties": false,
"properties": {
"code": {
"$ref": "#/definitions/ErrorCode"
},
"http_status": {
"format": "uint16",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"provider_error": {
"anyOf": [
{
"$ref": "#/definitions/ProviderError"
},
{
"type": "null"
}
]
},
"retry_after_ms": {
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"stats": {
"$ref": "#/definitions/Stats"
},
"status": {
"enum": [
"error"
],
"type": "string"
}
},
"required": [
"code",
"stats",
"status"
],
"type": "object"
}
],
"title": "ModelsResponse"
}
},
{
"description": "Internal: reload laya configuration from authoritative storage.",
"metadata": {
"internal": true
},
"name": "judge-laya::on-config-change",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Trigger payload for `<worker>::on-config-change`. Advisory only: handlers re-fetch the authoritative value and ignore it, so a direct call can never inject config.",
"properties": {
"id": {
"default": null,
"description": "Configuration id that changed.",
"type": [
"string",
"null"
]
}
},
"title": "OnConfigChangeEvent",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Ack returned by the internal `<worker>::on-config-change` handler.",
"properties": {
"ok": {
"type": "boolean"
}
},
"required": [
"ok"
],
"title": "OnConfigChangeResponse",
"type": "object"
}
},
{
"description": "Serve the judge-laya worker's injected console UI assets (content function for its console:script / console:style / console:module triggers).",
"metadata": {
"internal": true
},
"name": "judge-laya::ui-content",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Input of the content function: the console asks for one asset by path.",
"properties": {
"path": {
"description": "The asset path from the trigger config (e.g. `state/page.js`).",
"type": "string"
}
},
"required": [
"path"
],
"title": "UiContentInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Output of the content function.",
"properties": {
"content": {
"description": "The asset source, verbatim.",
"type": "string"
},
"content_type": {
"description": "MIME type the console should serve the asset with.",
"type": "string"
}
},
"required": [
"content",
"content_type"
],
"title": "UiContentResult",
"type": "object"
}
}
],
"triggers": []
}