Unverified50% confidenceFactExact time
In the agent context, a single turn may contain multiple tool calls, and the SDK executes them sequentially and appends each step's result to the context until Claude decides to stop calling tools.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Agents SDK can be used to configure input guardrails, restrict the list of tools, and set max_turns to prevent infinite loops72% similarUnverifiedClaude Agent SDK supports multi-step reasoning, tool calls, and environment interaction, including capabilities such as code writing, file operations, and command execution.71% similarUnverifiedHarness breaks a single agent job into Turns and Steps, where one Turn can contain multiple Steps, and each Step initiates a model request, receives output as a stream, and handles tool calls and results71% similarUnverifiedEach iteration cycle of an Agent consists of three phases—model inference, tool invocation, and result return—and latency accumulates at every step70% similarUnverifiedClaude Managed Agents的代理循环（Agent Loop）仍运行在Anthropic基础设施上，而工具执行迁移到企业自己配置的环境中69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/983799API
curl https://kongchang.com/api/v1/knowledge/claims/983799MCP
get_claim(id=983799)