II.
AgentCoreImpl overview
Reference · liveagent-core-impl:claude-code.core@1.x
Claude Code Core (1.x) overview
Inspect the raw attributes, linked wiki pages, and inbound or outbound graph edges for agent-core-impl:claude-code.core@1.x.
Attributes
displayName
Claude Code Core (1.x)
agentVersionId
agentVersion:claude:ge-0-0-0
packageRef
loopIteratorPolicy
tool-use-loop
loopIteratorNotes
Tool-use loop: each turn the model emits zero or more `tool_use` blocks; the runtime
executes them and appends `tool_result` blocks back into the message list. The loop
advances until the model returns an Anthropic Messages `stop_reason: "end_turn"`
(or `"tool_use"` after which tools are run and the next turn is fetched). The
PreCompact hook fires when context approaches the configured threshold and the
runtime injects a summarized history before the next turn.
contextManagementStrategy
platform-managed
compactionTriggerThresholdTokens
0
compactionTriggerNotes
PreCompact hook fires as the conversation approaches the active model's context
window (community-observed at ~70% fill). Vendor docs do not publish an exact
threshold; treat the integer field as TODO until Anthropic documents one.
subagentInvokerPolicy
tool-call-handoff
subagentInvokerNotes
Subagents are invoked via the built-in `Task` tool (a.k.a. the `Agent` tool). The
parent loop emits a `tool_use` for `Task` with a subagent name + prompt; the runtime
spawns a nested tool-use loop for the subagent and returns its final assistant text
as the `tool_result`. Up to 10 subagents can run in parallel.
resultSynthesisPolicy
model-direct
resultSynthesisNotes
The final assistant text is streamed verbatim to the host as it arrives; on
`stop_reason: "end_turn"` the runtime emits the `Stop` hook (and `SubagentStop`
for nested Task invocations) and closes the turn.
stopDetectionStrategy
structured-end-event
transportClientLibrary
@anthropic-ai/claude-agent-sdk
supportedTransportProtocols
parallelToolCallHandling
native
streamingFidelity
full
thinkingChannelHandling
passthrough
loopBudgetKnobs
- max_turns
- max_budget_usd
compactionTrigger
both
streamingBlocks
- text
- thinking
- tool_use
effortLevelDelegation
native
Outgoing edges
composes1
- agent:claude-code·AgentProductClaude Code
depends_on1
- source-ref:claude-code-github·SourceRefClaude Code (GitHub)
emits_message_type9
- protocol-message:system-message·ProtocolMessageSDKMessage / SystemMessage
- protocol-message:assistant-message·ProtocolMessageSDKMessage / AssistantMessage
- protocol-message:user-message·ProtocolMessageSDKMessage / UserMessage
- protocol-message:stream-event·ProtocolMessageSDKMessage / StreamEvent
- protocol-message:result-message-success·ProtocolMessageResultMessage subtype=success
- protocol-message:result-message-error-max-turns·ProtocolMessageResultMessage subtype=error_max_turns
- protocol-message:result-message-error-max-budget-usd·ProtocolMessageResultMessage subtype=error_max_budget_usd
- protocol-message:result-message-error-during-execution·ProtocolMessageResultMessage subtype=error_during_execution
- protocol-message:result-message-error-max-structured-output-retries·ProtocolMessageResultMessage subtype=error_max_structured_output_retries
fires_hook7
- hook-surface:pre-tool-use·HookSurfacePreToolUse (canonical)
- hook-surface:post-tool-use·HookSurfacePostToolUse (canonical)
- hook-surface:user-prompt-submit·HookSurfaceUserPromptSubmit (canonical)
- hook-surface:stop·HookSurfaceStop (canonical)
- hook-surface:claude.subagent-start·HookSurfaceSubagentStart (Claude Code)
- hook-surface:subagent-stop·HookSurfaceSubagentStop (canonical)
- hook-surface:pre-compact·HookSurfacePreCompact (canonical)
output_guard_applied_by1
- output-guard:claude-code-aup-refusal·OutputGuardClaude Code AUP refusal guard
realizes1
- layer:4-agent-core·LayerAgent-Core
speaks1
- model-transport:anthropic-messages·ModelTransportProtocolAnthropic Messages
supports5
- capability:can-multi-turn·CapabilityCan multi-turn
- capability:parallel-tool-calls·CapabilityParallel tool calls
- capability:streaming·CapabilityStreaming
- capability:supports-thinking·CapabilitySupports thinking
- capability:supports-tool-use·CapabilitySupports tool use
supports_effort_level5
- effort-level:low·EffortLevelEffort: low
- effort-level:medium·EffortLevelEffort: medium
- effort-level:high·EffortLevelEffort: high
- effort-level:xhigh·EffortLevelEffort: xhigh
- effort-level:max·EffortLevelEffort: max
supports_orchestration_primitive3
- orch-primitive:agent-dispatch·OrchestrationPrimitiveAgent Dispatch
- orch-primitive:budget-stop·OrchestrationPrimitiveBudget Stop
- orch-primitive:result-validation·OrchestrationPrimitiveResult Validation
Incoming edges
composed_of1
- agentVersion:claude:ge-0-0-0·AgentVersionClaude Code