agent-core-impl:langgraph.core@current

{
  "id": "agent-core-impl:langgraph.core@current",
  "_kind": "AgentCoreImpl",
  "_file": "agent-stack/core-impls/langgraph-core-current.yaml",
  "_cluster": "agent-stack",
  "attributes": {
    "displayName": "LangGraph Graph Core (current)",
    "agentVersionId": "agent-version:langgraph@current",
    "packageRef": "source-ref:langgraph-github",
    "loopIteratorPolicy": "custom",
    "loopIteratorNotes": "The core loop is an explicit graph/state-machine authored by the application:\nnodes transform state, edges route control, and terminal conditions are part\nof the graph definition rather than a fixed CLI loop.\n",
    "contextManagementStrategy": "user-managed",
    "compactionTriggerNotes": "Context and memory are represented in graph state, stores, checkpointers, or\nmodel-call middleware chosen by the graph author.\n",
    "subagentInvokerPolicy": "nested-loop",
    "subagentInvokerNotes": "Custom multi-agent patterns can be encoded as subgraphs, supervisor graphs,\nhandoff nodes, or Deep Agents-style subagent harnesses.\n",
    "resultSynthesisPolicy": "post-processed",
    "resultSynthesisNotes": "Final outputs are graph-defined: the terminal state can be converted to chat\nmessages, structured outputs, events, or application-specific payloads.\n",
    "stopDetectionStrategy": "structured-end-event",
    "transportClientLibrary": "langchain-chat-model-abstraction",
    "supportedTransportProtocols": [
      "model-transport:openai-chat-completions",
      "model-transport:openai-responses",
      "model-transport:anthropic-messages",
      "model-transport:gemini-generate-content",
      "model-transport:openai-compat"
    ],
    "parallelToolCallHandling": "native",
    "streamingFidelity": "full",
    "thinkingChannelHandling": "model-dependent",
    "notes": "Represents LangGraph's framework-level core, not a single product loop. The\ngraph author chooses which model provider integrations and node semantics are\nactive for a concrete application.\n"
  },
  "outgoingEdges": [
    {
      "from": "agent-core-impl:langgraph.core@current",
      "to": "layer:4-agent-core",
      "kind": "realizes",
      "attributes": {}
    },
    {
      "from": "agent-core-impl:langgraph.core@current",
      "to": "agent:langgraph",
      "kind": "composes",
      "attributes": {
        "role": "core"
      }
    },
    {
      "from": "agent-core-impl:langgraph.core@current",
      "to": "model-transport:openai-chat-completions",
      "kind": "speaks",
      "attributes": {}
    },
    {
      "from": "agent-core-impl:langgraph.core@current",
      "to": "model-transport:openai-responses",
      "kind": "speaks",
      "attributes": {}
    },
    {
      "from": "agent-core-impl:langgraph.core@current",
      "to": "model-transport:anthropic-messages",
      "kind": "speaks",
      "attributes": {}
    },
    {
      "from": "agent-core-impl:langgraph.core@current",
      "to": "model-transport:gemini-generate-content",
      "kind": "speaks",
      "attributes": {}
    },
    {
      "from": "agent-core-impl:langgraph.core@current",
      "to": "model-transport:openai-compat",
      "kind": "speaks",
      "attributes": {}
    },
    {
      "from": "agent-core-impl:langgraph.core@current",
      "to": "source-ref:langgraph-docs",
      "kind": "sourced_from"
    },
    {
      "from": "agent-core-impl:langgraph.core@current",
      "to": "source-ref:langchain-agents-docs",
      "kind": "sourced_from"
    },
    {
      "from": "agent-core-impl:langgraph.core@current",
      "to": "capability:supports-tool-use",
      "kind": "supports",
      "attributes": {
        "versionRange": ">=0.0.0",
        "level": "full"
      }
    },
    {
      "from": "agent-core-impl:langgraph.core@current",
      "to": "capability:streaming",
      "kind": "supports",
      "attributes": {
        "versionRange": ">=0.0.0",
        "level": "full"
      }
    },
    {
      "from": "agent-core-impl:langgraph.core@current",
      "to": "capability:can-resume",
      "kind": "supports",
      "attributes": {
        "versionRange": ">=0.0.0",
        "level": "full"
      }
    }
  ],
  "incomingEdges": [
    {
      "from": "agent-version:langgraph@current",
      "to": "agent-core-impl:langgraph.core@current",
      "kind": "composed_of",
      "attributes": {
        "role": "core"
      }
    }
  ]
}