judge-decider
v0.2.4decider provider for the judge hub (judge-decider::evaluate, judge-decider::models::list, judge-decider::cancel) — decider-4b v2 (a Qwen3.5-4B-Base fine-tune for typed decisions, GGUF) downloaded from the Hugging Face Hub and run in-process through llama.cpp, answering from the next-token logits of the option labels at its fitted temperature; picks Metal (macOS), Vulkan (Linux, when a driver is present) or the CPU automatically; no API key or external service.
Install
iii trigger compose::add worker=judge-deciderRun in your project with the iii engine running. Exact versions are immutable and digest-pinned.
Full markdown
/registry/workers/judge-decider.md. Paste it into an LLM prompt or pipe it through curl from a worker.Install
iii trigger compose::add worker=judge-decider@0.2.4Configuration
- context_tokens: 16384
max_request_bytes: 8388608
max_timeout_ms: 300000
model: decider-4b-v2
parallel_questions: 8
threads: 8Dependencies
Readme
judge-decider
decider provider for the
judge hub, running inside the worker: no API key, no Python,
no llama-server. decider-4b v2 is a Qwen3.5-4B-Base fine-tune trained for
exactly this readout (JevBench v1.4.2 rank 1, 64.1): one forward pass per
decision, a softmax over the next-token logits of the option labels at the
model's fitted temperature, no decoding. This worker reads it in decider's own
prompt layout through llama.cpp (crates/llama-native, the engine every local
judge provider shares) on the CPU, on Metal (macOS) or on Vulkan (Linux
x86_64: AMD, NVIDIA and Intel GPUs), picked automatically at start.
On an RX 6900 XT (Vulkan), against the other judge providers on the same machine:
| provider | labelled tickets: department / urgency / churn / refund | per ticket | directory::search_functions (22 capabilities): hit / top-1 / precision |
|---|---|---|---|
decider (decider-4b-v2) |
1.00 / 0.79 / 0.96 / 0.96 | 0.30 s | 22 / 22 / 0.94 |
semif (Qwen3.5-4B) |
0.88 / 0.62 / 1.00 / 1.00 | 0.29 s | 21 / 18 / 0.81 |
typesafe (hosted Jev) |
0.96 / 0.75 / 0.96 / 1.00 | 0.25 s | 22 / 22 / 0.99 |
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 (
GGML_BACKEND_DL). 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, so the same package works on GPU desktops, servers and containers. The CPU module is picked for the host (AVX2, AVX-512, AMX variants). The package shipslibllama,libggml,libggml-base, the CPU variants and the Vulkan module (≈71 MB) beside the binary, which finds them through its$ORIGINrunpath. - Linux aarch64: CPU, statically linked.
gpu_layers: 0 keeps the model on the CPU even when a GPU is present. The
chosen device is logged at start as selected inference device.
Install
iii trigger compose::add worker=judge-deciderThe functions register at start; the model loads on demand. While decider is
the judge hub's default provider (provider: decider under Settings →
Workers → judge) it loads at once and stays loaded. Otherwise the first call
that names "provider": "decider" (or comes from a session that picked it)
loads it, and it is released (VRAM included, about 6 GB) after 10 minutes
without calls. A call that cannot wait for the load answers deadline while
the load goes on for the next one. The first load downloads the pinned GGUF
(mindchain/decider-4b-v2-GGUF Q4_K_M, 2.7 GB, quantized by llama.cpp from
Mapika/decider-4b at tag v2) into the hf-hub cache ($HF_HOME, default
~/.cache/huggingface). To keep it 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 model loaded from the start. Air-gapped installs set
III_DECIDER_GGUF to a local GGUF file.
The repository's main is v2.1, which trades some of v2's accuracy on hard
decisions for sampled play and has no published GGUF; v2 is the JevBench
rank-1 revision.
Make it the hub's default, then call the hub:
iii trigger judge::evaluate --timeout-ms 65000 --json '{
"timeout_ms": 60000, "provider": "decider",
"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", "instructions": "Which team should handle it?", "criteria": {"billing": "invoices, payments, refunds", "technical": "bugs, outages"}},
"urgency": {"type": "score", "instructions": "How urgent is it?", "criteria": ["not urgent", "soon", "critical deadline or blocking issue"]},
"churn_risk": {"type": "noul", "instructions": "Does the user threaten to cancel or leave?"}
}
}]
}'How questions map to decider
The worker builds decider's plain state-first prompt as decider-ai 1.5.0's
/v1/systemone does (decider/systemone.py, decider/prompt_fast.py), one
independent prompt per decision:
Context:
<state>
Question: <instructions>
Options:
(A) <option>
(B) <option>
Answer: (The state is a string as-is, or Python JSON with _index written into every
element of an 8+ element array. Context: and each question block are
tokenized separately, as decider does; up to ten options render as one
string, more use one label token each (A–Z, then the two-letter labels
that are single tokens), up to 255 options. The label logits go through a
softmax at v2's temperature 1.935.
| Contract | decider options | Answer |
|---|---|---|
noul |
no then yes, each followed by its criteria description after : |
noul = P(yes) |
choice |
one per criterion, key: description |
argmax, probabilities, confidence |
score |
one yes/no prompt per level: |
the levels' P(yes) normalized; Σ i·p_i |
Score levels are judged in isolation (isolated_levels), without their number
or their neighbours, as decider-4b v2 was trained. confidence is decider's
(TypeSafe's definitions): for a choice (n·p_max − 1) / (n − 1), 0 for a
uniform distribution and 1 for all mass on one option; for a score
1 − the expected distance from the likeliest level over the mean distance of
the levels from the middle of the scale. A question without instructions asks
"Which answer fits the context?"; a noul needs instructions or a true /
false description. A prompt longer than context_tokens answers
payload_too_large: the state is never truncated.
Every prompt of one evaluation starts with the same Context: tokens. The
worker prefills them once, snapshots the sequence, restores it into up to
parallel_questions sequences and decodes the question blocks together in
one batch (iii_llama_runtime::scorer, shared with judge-semif). The
snapshot stays in the model's device memory (VRAM on a GPU), so restoring it
never goes through the host; the latest one is held until the next evaluation
replaces it, about 300 MB for a 7.6k-token context.
usage.input_tokens counts the decoded tokens (the shared prefix once).
tests/decider.rs checks the prompts and token ids against decider's own
rows and the answers (probabilities and confidence) against the bf16 weights
computed in float32 (tests/fixtures/make_decider_prompts.py): an f16
conversion agrees to 0.0025, Q8_0 to 0.0074, and the shipped Q4_K_M to 0.12
(0.14 on the CPU; 0.03 elsewhere) on a near-flat 12-option question. There
llama.cpp b11379 puts area0 (0.17) just above the reference's answer auth
(0.16 against 0.28), so that question's choice check fails. For the closer Q8_0
(4.5 GB), convert Mapika/decider-4b at v2 with llama.cpp's
convert_hf_to_gguf.py --outtype q8_0 --no-mtp and point III_DECIDER_GGUF
at it.
Configuration
Settings → Workers → judge-decider:
| Field | Default | Applied |
|---|---|---|
model |
decider-4b-v2 |
next start |
threads |
min(8, logical cores) | next start |
gpu_layers |
all layers when a GPU backend and device exist | next start (0 = CPU) |
context_tokens |
16384 | next start |
parallel_questions |
8 | next start (1 = one question per decode) |
max_request_bytes |
8388608 | new calls |
max_timeout_ms |
300000 | new calls |
Building
llama.cpp b11379 is compiled from source through crates/llama-native: its
build.rs downloads GitHub's source archive (checked against a pinned
sha256), builds it with cmake and compiles a small C shim against it, with no
bindgen. It needs curl, tar, patch, cmake and a C++17 compiler; an
offline build points III_LLAMA_CPP_TARBALL at a copy of the archive, checked
the same way. 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 (only the module links libvulkan, the binary does
not). 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.
For the full API, read the hub's reference.
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-decider::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": {
"$ref": "#/definitions/ErrorCode"
},
"status": {
"enum": [
"error"
],
"type": "string"
}
},
"required": [
"code",
"status"
],
"type": "object"
}
],
"title": "CancelResponse"
}
},
{
"description": "Returns this worker instance's effective configuration entry ID, without its value.",
"metadata": {
"internal": true
},
"name": "judge-decider::configuration-id",
"request_schema": {
"$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": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Only the entry ID is exposed; configuration values and secrets stay in the service.",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"title": "ConfigurationIdentityResponse",
"type": "object"
}
},
{
"description": "Evaluate Noul, Choice and Score questions against arbitrary JSON state with decider-4b (a GGUF LLM fine-tuned for typed decisions, read at the option labels) running inside this worker. Results are atomic; usage counts decoded prompt tokens. No credentials or endpoints are accepted in the request.",
"metadata": {
"internal": true
},
"name": "judge-decider::evaluate",
"request_schema": {
"$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 decider model, loading it if needed (name, pinned revision, device, context window); performs no inference.",
"metadata": {
"internal": true
},
"name": "judge-decider::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 decider configuration from authoritative storage.",
"metadata": {
"internal": true
},
"name": "judge-decider::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-decider worker's injected console UI assets (content function for its console:script / console:style / console:module triggers).",
"metadata": {
"internal": true
},
"name": "judge-decider::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": []
}