Component
core/ai-agent/agenta-services
The model-facing service of an agent workspace: the tier that talks to language-model providers on the platform's behalf. It serves the completion and chat endpoints the console's playground calls, holds the adapter layer that presents one interface over many providers, and starts an agent run by handing it to the runner. It reads the platform's relational model through backend, uses cache and queue as the control-plane API does, keeps the files an agent produces in the object store wired through store, and reaches auth_core to establish who a request belongs to and runner to start, watch and cancel a run. Wire here to invoke a model or start an agent run. That is the line between this service and core/ai-agent/agenta-api, which owns the platform's own data: a caller listing agents or reading a trace talks to that one, and a caller asking for a completion or a run talks to this one. Both are needed, and neither is a superset of the other. Realized on Kubernetes via its Helm Recipe, which synthesizes the service as a stateless Deployment behind a ClusterIP Service on its HTTP port. It exports its host, port, endpoint and protocol to consumers.
Herkunft
- Inhalts-Digest
- sha256:fb888f5eccf68284b1e49710d9007a26ec1d52d8009444dc28b557d8c309db9b
- Veröffentlicht
- 2026-11-10T10:07:20Z
- Signaturidentität
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
Signatur
- Offiziellapplication/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
sha256:5acaba54658deb52fab31ad4eb403335ad11d3bb74e674ded0f2c4defac01a01
Referenz zu dieser Version
oci://hub.aggrega.ai/component/core/ai-agent/agenta-services:1.0.0Entwicklerparameter
Werte, die der Entwickler im Aggregate festlegt.
| Name | Typ | Standardwert | Erforderlich | Beschreibung |
|---|---|---|---|---|
| model_call_timeout_seconds | integer (min 1) | 120 | nein | How long a single model call may take before the service gives up on it. A long-running agent turn needs a wider window than a playground completion does. |
| max_concurrent_model_calls | integer (min 1) | 16 | nein | How many model calls the service will have outstanding at once. It bounds what one container holds open, so it is sized with compute.memory. |
Dimensionierung durch den Operator
Infrastrukturdimensionierung, die der Operator pro Umgebung anpasst.
| Name | Typ | Standardwert | Erforderlich | Beschreibung |
|---|---|---|---|---|
| port | integer (min 1024, max 65535) | 8080 | nein | Port the service serves its HTTP API on; consumers connect here. Most operators should omit this and let the Recipe assign the default (8080). |
| external_base_url | string | — | nein | Externally reachable base URL of the whole platform, as a browser reaches it through the ingress tier — for example https://agenta.example.com. The service composes the addresses it reports from it. The compiler cannot know a cluster's external hostname, so this carries no default and the Kubernetes realization halts at build until it is set. |
| engine_version | string | v0.114.1 | nein | Platform services container image tag. It tracks the same release as the control-plane API, so a Release moves both together. |
| web_workers | integer (min 1) | 2 | nein | Number of request-serving worker processes in one container. Raising it raises throughput and the container's memory ceiling together, so it is sized with compute.memory. |
| log_level | string (DEBUG | INFO | WARNING | ERROR | CRITICAL) | INFO | nein | Log verbosity the service emits. |
| compute | object | — | nein | — |
| overrides | object (open) | — | nein | Provider-specific overrides. Accepts any nested structure. Each Recipe documents which keys it reads. |
Ausgabevertrag
Werte, die diese Komponente über die uses-Topologie an Konsumenten veröffentlicht.
| Name | Typ | Standardwert | Erforderlich | Beschreibung |
|---|---|---|---|---|
| host | string | — | ja | In-cluster DNS name of the Service fronting the model-facing tier. The console's playground and anything else asking for a completion dial this name. |
| port | integer | — | ja | TCP port that Service accepts completion and chat requests on. It follows the port an operator set in the Release, so a consumer reads it rather than assuming a default. |
| endpoint | string | — | ja | Full in-cluster base URL of the completion and chat API, with the host and the port already composed. It is the address a peer tier calls, not the address a browser reaches. |
| protocol | string | — | nein | URL scheme to reach `host` and `port` over, for a consumer composing its own address rather than reading `endpoint`. |
uses-Sockets
Die Abhängigkeits-Sockets, über die sich diese Komponente verbindet. Das Ziel jeder über einen Socket verdrahteten Verbindung muss dessen Label-Selektor erfüllen, und jede Verbindung kann in den Slots, die der Socket deklariert, eine Anbindung tragen. Einen erforderlichen Slot muss jede Verbindung füllen, die das Aggregate oder das Release über den Socket verdrahtet.
backend
- Selektor
- component.aggrega.ai/category=datastore
- Injektion
- env
Slots, die jede Verbindung über diesen Socket füllen kann
| Slot | Selektor | Erforderlich | Injektion | Sensibel | Beschreibung |
|---|---|---|---|---|---|
| credential | feature.aggrega.ai/kind=secret | nein | env | ja | Password the service authenticates to the relational backend this connection reaches with, delivered as an env secret reference and substituted into the connection URL at run time. The same credential is attached to the control-plane API's backend connection, because both reach the same server. Unattached, the Recipe emits the development literal `apppass`, the default the standard-library relational Recipes leave in place; this catalog publishes it, so every Release that leaves the slot unattached shares that password. |
cache
- Selektor
- component.aggrega.ai/category=datastore
- Injektion
- env
Slots, die jede Verbindung über diesen Socket füllen kann
| Slot | Selektor | Erforderlich | Injektion | Sensibel | Beschreibung |
|---|---|---|---|---|---|
| server_ca | feature.aggrega.ai/kind=secret | nein | file | ja | Optional authority the platform's Redis client checks the cache's certificate against while the cache publishes protocol valkey-tls or redis-tls, where the image does not already trust the authority that signs it. Its Secret holds ca.crt. The Recipe mounts the whole Secret read-only and names the file in the connection's URL. The build halts on a server_ca publishing no Secret name, and on one wired to a cache served without TLS. Fill it with core/referenced-secret. |
queue
- Selektor
- component.aggrega.ai/category=datastore
- Injektion
- env
Slots, die jede Verbindung über diesen Socket füllen kann
| Slot | Selektor | Erforderlich | Injektion | Sensibel | Beschreibung |
|---|---|---|---|---|---|
| server_ca | feature.aggrega.ai/kind=secret | nein | file | ja | Optional authority the platform's Redis client checks the queue's certificate against while the queue publishes protocol valkey-tls or redis-tls, where the image does not already trust the authority that signs it. Its Secret holds ca.crt. The Recipe mounts the whole Secret read-only and names the file in the connection's URL. The build halts on a server_ca publishing no Secret name, and on one wired to a queue served without TLS. Fill it with core/referenced-secret. |
auth_core
- Selektor
- component.aggrega.ai/category=security
- Injektion
- env
Slots, die jede Verbindung über diesen Socket füllen kann
| Slot | Selektor | Erforderlich | Injektion | Sensibel | Beschreibung |
|---|---|---|---|---|---|
| credential | feature.aggrega.ai/kind=secret | nein | env | ja | API key presented to the authentication core this connection reaches. Where a key is attached to the core, the same one is attached here. Unattached, no key is sent. |
store
- Selektor
- component.aggrega.ai/type=resource,component.aggrega.ai/category=storage
- Injektion
- env
Slots, die jede Verbindung über diesen Socket füllen kann
| Slot | Selektor | Erforderlich | Injektion | Sensibel | Beschreibung |
|---|---|---|---|---|---|
| credential_id | feature.aggrega.ai/kind=secret | nein | env | ja | Access-key identifier the S3 client authenticates to the object store this connection reaches with, the identifier half of the pair whose secret half is this connection's credential. Unattached, the Recipe presents the identifier admin. |
| credential | feature.aggrega.ai/kind=secret | nein | env | ja | Secret key paired with this connection's credential_id. There is no default: the build halts when nothing fills this slot, unless the connection's values set unauthenticated: true. |
runner
- Selektor
- component.aggrega.ai/category=ai-agent
- Injektion
- env
Slots, die jede Verbindung über diesen Socket füllen kann
| Slot | Selektor | Erforderlich | Injektion | Sensibel | Beschreibung |
|---|---|---|---|---|---|
| credential | feature.aggrega.ai/kind=secret | nein | env | ja | Token presented on every call to the runner this connection reaches, which rejects an untokened request. The same credential is attached to the runner's own slot so both ends agree. Unattached, the Recipe emits the pinned development literal `dev-agenta-runner-change-me`, suitable for evaluation only and published in this catalog, so every Release that leaves the slot unattached shares it. |
Anbindungs-Slots
Benannte Bindungspunkte, an denen ein Feature an diese Komponente angebunden wird. Der Selektor eines Slots schränkt ein, welches Feature ihn füllen darf, und seine inject-Liste benennt, wie das Feature sein Material liefern darf. Ein erforderlicher Slot muss auf jeder Instanz gebunden sein, durch eine Anbindung an der Instanz oder in einem darüberliegenden Geltungsbereich, und ein sensibler Slot ist für den Umgang mit geheimem Material deklariert. Ein Feature kann auch unter einem Namen angebunden werden, den kein Slot deklariert.
| Slot | Selektor | Erforderlich | Injektion | Sensibel | Beschreibung |
|---|---|---|---|---|---|
| auth_key | feature.aggrega.ai/kind=secret | ja | env | ja | Required key the platform signs its own internal tokens with. It carries the same value as the control-plane API's slot. There is no default: the build halts when nothing fills this slot. |
| crypt_key | feature.aggrega.ai/kind=secret | ja | env | ja | Required key stored model-provider credentials are encrypted under. This service decrypts them to call a provider, so it carries the same value as the control-plane API's slot. There is no default: the build halts when nothing fills this slot. |
| services_internal_key | feature.aggrega.ai/kind=secret | nein | env | ja | Key this service and the control-plane API present to each other on internal calls. Both ends carry the same value. Unattached, the Recipe emits the pinned development literal `dev-agenta-internal-change-me`, suitable for evaluation only and published in this catalog, so every Release that leaves the slot unattached shares it. |
Zulassungsliste für Selbstinjektion
env
Beziehungen
Typisierte Kanten zu und von anderen veröffentlichten Entitäten. Eine Referenz ohne veröffentlichtes Ziel wird als unterbrochene Kante statt als Link dargestellt.
Verwendet
- verwendetverwendet Socket «backend»
component.aggrega.ai/category=datastore
Anbindungs-Slots: credential
core/datastore/chroma v1.0.0 →core/datastore/cognee v1.0.0 →core/datastore/documentdb v1.0.0 →core/datastore/elasticsearch v1.0.0 →core/datastore/etcd v1.0.0 →core/datastore/ferretdb v1.0.0 →core/datastore/mariadb v1.0.0 →core/datastore/mariadb-operator v1.0.0 →core/datastore/memcached v1.0.0 →core/datastore/milvus v1.0.0 →core/datastore/mysql v1.0.0 →core/datastore/mysql-innodb-cluster v1.0.0 →core/datastore/mysql-operator v1.0.0 →core/datastore/opensearch v1.0.0 →core/datastore/pgvector v1.0.0 →core/datastore/postgres v1.0.0 →core/datastore/qdrant v1.0.0 →core/datastore/redis v1.0.0 →core/datastore/timescaledb v1.0.0 →core/datastore/valkey v1.0.0 →core/datastore/weaviate v1.0.0 → - verwendetverwendet Socket «cache»
component.aggrega.ai/category=datastore
Anbindungs-Slots: server_ca
core/datastore/chroma v1.0.0 →core/datastore/cognee v1.0.0 →core/datastore/documentdb v1.0.0 →core/datastore/elasticsearch v1.0.0 →core/datastore/etcd v1.0.0 →core/datastore/ferretdb v1.0.0 →core/datastore/mariadb v1.0.0 →core/datastore/mariadb-operator v1.0.0 →core/datastore/memcached v1.0.0 →core/datastore/milvus v1.0.0 →core/datastore/mysql v1.0.0 →core/datastore/mysql-innodb-cluster v1.0.0 →core/datastore/mysql-operator v1.0.0 →core/datastore/opensearch v1.0.0 →core/datastore/pgvector v1.0.0 →core/datastore/postgres v1.0.0 →core/datastore/qdrant v1.0.0 →core/datastore/redis v1.0.0 →core/datastore/timescaledb v1.0.0 →core/datastore/valkey v1.0.0 →core/datastore/weaviate v1.0.0 → - verwendetverwendet Socket «queue»
component.aggrega.ai/category=datastore
Anbindungs-Slots: server_ca
core/datastore/chroma v1.0.0 →core/datastore/cognee v1.0.0 →core/datastore/documentdb v1.0.0 →core/datastore/elasticsearch v1.0.0 →core/datastore/etcd v1.0.0 →core/datastore/ferretdb v1.0.0 →core/datastore/mariadb v1.0.0 →core/datastore/mariadb-operator v1.0.0 →core/datastore/memcached v1.0.0 →core/datastore/milvus v1.0.0 →core/datastore/mysql v1.0.0 →core/datastore/mysql-innodb-cluster v1.0.0 →core/datastore/mysql-operator v1.0.0 →core/datastore/opensearch v1.0.0 →core/datastore/pgvector v1.0.0 →core/datastore/postgres v1.0.0 →core/datastore/qdrant v1.0.0 →core/datastore/redis v1.0.0 →core/datastore/timescaledb v1.0.0 →core/datastore/valkey v1.0.0 →core/datastore/weaviate v1.0.0 → - verwendetverwendet Socket «auth_core»
component.aggrega.ai/category=security
Anbindungs-Slots: credential
core/security/cert-manager v1.0.0 →core/security/external-secrets v1.0.0 →core/security/fms-guardrails-orchestrator v1.0.0 →core/security/keycloak v1.0.0 →core/security/kong-ai-pii-service v1.0.0 →core/security/nemo-guardrails v1.0.0 →core/security/nemoguard-jailbreak-detect v1.0.0 →core/security/openbao v1.0.0 →core/security/presidio-analyzer v1.0.0 →core/security/presidio-anonymizer v1.0.0 →core/security/sealed-secrets v1.0.0 →core/security/supertokens v1.0.0 →core/security/trustyai-guardrails-gateway v1.0.0 →core/security/trustyai-huggingface-detector v1.0.0 → - verwendetverwendet Socket «store»
component.aggrega.ai/type=resource,component.aggrega.ai/category=storage
Anbindungs-Slots: credential_id, credential
- verwendetverwendet Socket «runner»
component.aggrega.ai/category=ai-agent
Anbindungs-Slots: credential
core/ai-agent/a2a-remote v1.0.0 →core/ai-agent/agent-framework v1.0.0 →core/ai-agent/agent-framework v1.1.0 →core/ai-agent/agenta-api v1.0.0 →core/ai-agent/agenta-cron v1.0.0 →core/ai-agent/agenta-migrations v1.0.0 →core/ai-agent/agenta-runner v1.0.0 →core/ai-agent/agenta-web v1.0.0 →core/ai-agent/agenta-web-mobile v1.0.0 →core/ai-agent/agenta-worker-queues v1.0.0 →core/ai-agent/agenta-worker-streams v1.0.0 →core/ai-agent/anthropic v1.0.0 →core/ai-agent/autogen v1.0.0 →core/ai-agent/autogpt v1.0.0 →core/ai-agent/bedrock v1.0.0 →core/ai-agent/bland v1.0.0 →core/ai-agent/claude-agent-sdk v1.0.0 →core/ai-agent/crewai v1.0.0 →core/ai-agent/crewai v1.1.0 →core/ai-agent/dify v1.0.0 →core/ai-agent/dify v1.1.0 →core/ai-agent/dify-plugin-daemon v1.0.0 →core/ai-agent/dify-sandbox v1.0.0 →core/ai-agent/dify-ssrf-proxy v1.0.0 →core/ai-agent/dify-web v1.0.0 →core/ai-agent/dify-web v1.1.0 →core/ai-agent/dify-worker v1.0.0 →core/ai-agent/dify-worker v1.1.0 →core/ai-agent/dify-worker-beat v1.0.0 →core/ai-agent/dify-worker-beat v1.1.0 →core/ai-agent/dynamiq v1.0.0 →core/ai-agent/flowise v1.0.0 →core/ai-agent/flowise v1.1.0 →core/ai-agent/gemini v1.0.0 →core/ai-agent/google-adk v1.0.0 →core/ai-agent/google-adk v1.1.0 →core/ai-agent/griptape v1.0.0 →core/ai-agent/gumloop v1.0.0 →core/ai-agent/haystack v1.0.0 →core/ai-agent/langflow v1.0.0 →core/ai-agent/langflow v1.1.0 →core/ai-agent/langgraph v1.0.0 →core/ai-agent/langgraph v1.1.0 →core/ai-agent/letta v1.0.0 →core/ai-agent/librechat v1.0.0 →core/ai-agent/librechat v1.1.0 →core/ai-agent/librechat v1.2.0 →core/ai-agent/lindy v1.0.0 →core/ai-agent/livekit-agent-worker v1.0.0 →core/ai-agent/llamaindex v1.0.0 →core/ai-agent/mastra v1.0.0 →core/ai-agent/metagpt v1.0.0 →core/ai-agent/n8n v1.0.0 →core/ai-agent/n8n v1.1.0 →core/ai-agent/open-webui v1.0.0 →core/ai-agent/openai-agents-sdk v1.0.0 →core/ai-agent/openclaw v1.0.0 →core/ai-agent/openhands v1.0.0 →core/ai-agent/phidata v1.0.0 →core/ai-agent/promptflow v1.0.0 →core/ai-agent/pydantic-ai v1.0.0 →core/ai-agent/retell v1.0.0 →core/ai-agent/rivet v1.0.0 →core/ai-agent/semantic-kernel v1.0.0 →core/ai-agent/smolagents v1.0.0 →core/ai-agent/vapi v1.0.0 →core/ai-agent/vertex-ai v1.0.0 →
Verwendet von
verwendet Socket «runner»
verwendet Socket «api»
verwendet Socket «api»
verwendet Socket «services»
verwendet Socket «api»
verwendet Socket «services»
verwendet Socket «services»
verwendet Socket «sandbox»
verwendet Socket «plugin_daemon»
verwendet Socket «ssrf_proxy»
verwendet Socket «sandbox»
verwendet Socket «plugin_daemon»
verwendet Socket «ssrf_proxy»
verwendet Socket «api»
verwendet Socket «ssrf_proxy»
verwendet Socket «api»
verwendet Socket «api»
verwendet Socket «sandbox»
verwendet Socket «plugin_daemon»
verwendet Socket «ssrf_proxy»
verwendet Socket «sandbox»
verwendet Socket «plugin_daemon»
verwendet Socket «ssrf_proxy»
verwendet Socket «target_agent»
verwendet Socket «upstream»
verwendet Socket «forward_target»
verwendet Socket «scrape_target»
verwendet Socket «store»
gilt für
gilt für
gilt für
gilt für
gilt für
gilt für
gilt für
implementiert