Component
core/gateway/higress
Higress, an open-source gateway built on Envoy and configured through Kubernetes resources: its routes are ingresses, the services it reaches are its own registry's entries, and its controls are WebAssembly plugins on the routes they act on. It terminates client HTTP on its proxy port, publishing its host, port and protocol. It serves models: each model wired to its models socket is reached under an alias at /<alias>/v1 through Higress's AI proxy, sent to the endpoint and model name the model publishes, presenting the connection's credential from its Secret; over https it checks that the model's certificate chains to the system's trust anchors and names its host. Connections naming one alias in serves share its requests. It publishes the route of values.model as its endpoint and that alias as its model, so an agent's model socket takes it in place of a model; with nothing wired both are empty. On those routes it masks requests, keeps a token budget in its cache socket's store, records each model request in its access log and sets each route's retry, refusing by name what Higress cannot keep; it declares no callers. Reply validation, the fallback chain, the semantic cache, the prompt-injection shield and latency-based target selection halt the build naming what Higress lacks. It pulls its plugin modules from Higress's plugin registry at run time, which the cluster must reach and the build cannot check. It is realized on Kubernetes by `higress-chart` alone, and publishes the pod label, port name and path a scraper discovers its gateway's metrics by.
Procedencia
- Digest del contenido
- sha256:8b92c8a380a01667259d0b041b43a42dc1c93b50b58b21741d1cc4a57a8260f9
- Publicado
- 2026-11-10T10:11:55Z
- Identidad de firma
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
Firma
- Oficialapplication/vnd.dev.sigstore.bundle.v0.3+json
https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
sha256:ef9dfa3941c48639070a7b9379a7ff22eb5637b82b98304936be0d1c243fd7b7
Referencia en esta versión
oci://hub.aggrega.ai/component/core/gateway/higress:1.0.0Parámetros del desarrollador
Valores que el desarrollador establece en el Aggregate.
| Nombre | Tipo | Predeterminado | Obligatorio | Descripción |
|---|---|---|---|---|
| model | string | — | no | The alias this gateway publishes as its model, and whose route its published endpoint addresses — a serves value a models connection names, or the name of a connection naming none. It must be an alias the models socket serves, and the build halts naming this value otherwise; it is required while the models socket holds a connection, and omitted while it holds none. |
Dimensionamiento del operador
Dimensionamiento de la infraestructura que el operador ajusta para cada entorno.
| Nombre | Tipo | Predeterminado | Obligatorio | Descripción |
|---|---|---|---|---|
| http_port | integer (min 1, max 65535) | 80 | no | Proxy data-plane port consumers connect to. |
| source_version | string | — | no | Version of the Higress chart the chart-backed realization pulls. The realization holds the chart versions its configuration is proven at, and the build halts naming them on any other. |
| compute | object | — | no | — |
| overrides | object (open) | — | no | Provider-specific overrides. Accepts any nested structure. Each Recipe documents which keys it reads. |
Contrato de salida
Valores que este componente publica para los consumidores a través de la topología uses.
| Nombre | Tipo | Predeterminado | Obligatorio | Descripción |
|---|---|---|---|---|
| host | string | — | sí | In-cluster DNS name of the Service fronting the gateway's proxy, the name alone without a namespace. A consumer sends its client traffic here rather than to the service behind the gateway. |
| port | integer | — | sí | TCP port that Service accepts proxied traffic on, infra.http_port. |
| protocol | string | — | no | How the published address is spoken to — `http`, so a consumer composes an address on that scheme. |
| endpoint | string | — | no | Full base URL of the OpenAI-compatible API the gateway serves for the alias values.model names, with the host, the port and that alias's route already composed. A caller hands it to a client library as its base URL. Every other alias is served at the same host and port under its own name in the path. Empty while nothing is wired to the models socket. |
| model | string | — | no | The alias a consumer wired to the gateway sends as its model name: values.model. The route behind the endpoint asks each model for the name that model publishes, whatever name a request carries. Empty while nothing is wired to the models socket. |
| metrics_pod_selector | string | — | no | Kubernetes label selector matching the gateway's pods, for a scraper that discovers those pods directly rather than scraping one address. Published beside `metrics_pod_port` and `metrics_path`. |
| metrics_pod_port | string | — | no | Name of the container port on those pods that carries the metrics, `istio-prom`. |
| metrics_path | string | — | no | Path the metrics are served at on that port, `/stats/prometheus`. |
Sockets uses
Los sockets de dependencia a través de los cuales se conecta este componente. El destino de cada conexión cableada a través de un socket debe satisfacer su selector de etiquetas, y cada conexión puede llevar un acoplamiento en los slots que declara el socket. Cada conexión que el Aggregate o la Release cablea a través del socket debe llenar los slots obligatorios.
models
- Selector
- component.aggrega.ai/category=ai-model
- Inyección
- —
Slots que cada conexión a través de este socket puede llenar
| Slot | Selector | Obligatorio | Inyección | Sensible | Descripción |
|---|---|---|---|---|---|
| credential | feature.aggrega.ai/kind=secret | no | — | sí | Optional credential the gateway presents to the model this connection reaches, as a bearer token. When attached, the AI proxy's configuration names the Secret the credential publishes and the data key holding the key there, and the Higress controller reads the key from that Secret, in the gateway's namespace, so the key appears in no rendered file. The credential must publish both, and a Secret name holding a dot halts the build, because Higress reads the name up to its first dot; a realization naming its own Secret after the connection and this slot writes such a dot, so realize it with one naming an existing Secret whose name holds none. Unattached, the gateway adds no credential. |
cache
- Selector
- datastore.aggrega.ai/engine=kv
- Inyección
- —
Slots que cada conexión a través de este socket puede llenar
| Slot | Selector | Obligatorio | Inyección | Sensible | Descripción |
|---|---|---|---|---|---|
| credential | feature.aggrega.ai/kind=secret | no | — | sí | Optional password the gateway's token budget presents to the Redis-protocol store this connection reaches. When attached, the budget's configuration names the Secret the credential publishes and the data key holding the password there, and the Higress controller reads the password from that Secret, in the gateway's namespace, so it appears in no rendered file. The credential must publish both, and a Secret name holding a dot halts the build, because Higress reads the name up to its first dot; realize it with one naming an existing Secret whose name holds none. Unattached, the plugin connects with no password, which is what the shipped store components expect by default. |
Slots de acoplamiento
Puntos de enlace con nombre en los que una Feature se acopla a este componente. El selector de un slot restringe qué Feature puede llenarlo y su lista inject indica cómo puede entregarse el material de la Feature. Un slot obligatorio debe estar enlazado en cada instancia, mediante un acoplamiento en la instancia o en un ámbito superior, y un slot sensible se declara para manejar material secreto. Una Feature también puede acoplarse con un nombre que ningún slot declara.
No se declararon slots de acoplamiento.
Lista de permitidos de autoinyección
No se declararon canales de autoinyección.
Relaciones
Aristas tipadas hacia y desde otras entidades publicadas. Una referencia sin un destino publicado se muestra como una arista rota en lugar de como un enlace.
Usa
- usausa el socket «models»
component.aggrega.ai/category=ai-model
Slots de acoplamiento: credential
core/ai-model/ai21 v1.0.0 →core/ai-model/anthropic v1.0.0 →core/ai-model/azure-managed v1.0.0 →core/ai-model/azure-openai v1.0.0 →core/ai-model/azure-openai-embedding v1.0.0 →core/ai-model/bedrock v1.0.0 →core/ai-model/bedrock-embedding v1.0.0 →core/ai-model/cohere v1.0.0 →core/ai-model/databricks v1.0.0 →core/ai-model/docker-model-runner v1.0.0 →core/ai-model/gemini v1.0.0 →core/ai-model/huggingface v1.0.0 →core/ai-model/litellm v1.0.0 →core/ai-model/mistral v1.0.0 →core/ai-model/nemoguard-content-safety v1.0.0 →core/ai-model/nvidia-api v1.0.0 →core/ai-model/nvidia-nim v1.0.0 →core/ai-model/nvidia-nim-operator v1.0.0 →core/ai-model/ollama v1.0.0 →core/ai-model/openai v1.0.0 →core/ai-model/openai-compatible v1.0.0 →core/ai-model/openai-embedding v1.0.0 →core/ai-model/replicate v1.0.0 →core/ai-model/sagemaker v1.0.0 →core/ai-model/tei v1.0.0 →core/ai-model/tgi v1.0.0 →core/ai-model/vertex-ai v1.0.0 →core/ai-model/vertex-ai-embedding v1.0.0 →core/ai-model/vllm v1.0.0 → - usausa el socket «cache»
datastore.aggrega.ai/engine=kv
Slots de acoplamiento: credential
Usado por
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «model»
usa el socket «target_model»
usa el socket «extraction_model»
usa el socket «embedding_model»
usa el socket «upstream»
usa el socket «forward_target»
usa el socket «scrape_target»
usa el socket «store»
se aplica a
se aplica a
se aplica a
se aplica a
se aplica a
se aplica a
se aplica a
se aplica a
se aplica a
se aplica a
se aplica a
se aplica a
se aplica a
se aplica a
se aplica a
se aplica a
implementa