Unverified50% confidenceConceptExact time
The stop reason is a core control signal in the LLM Agent loop, used to indicate why the current model response ended; common values include end_turn, tool_use, max_tokens, and so on.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe control flow rule of the agent loop is: as long as the stop reason is still tool use, keep looping; when the stop reason becomes end turn, stop and return plain text.80% similarVerifiedstop_reason is a field in the Anthropic Claude API response, with common values including end_turn, max_tokens, and tool_use.78% similarUnverifiedThe termination condition of an agentic loop typically falls into one of two categories: the model returns a plain-text response (stop_reason is end_turn), or the preset maximum number of iterations is reached.74% similarUnverified驱动Agent Loop循环的两个信号来自模型返回的stop_reason字段：当stop_reason等于tool_use时宿主执行工具并继续循环，否则循环退出73% similarUnverifiedAnthropic describes the client-side loop as a while loop based on stop reason: if the stop reason is tool_use, execute the tool and continue; exit upon encountering any other stop reason.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1056105API
curl https://kongchang.com/api/v1/knowledge/claims/1056105MCP
get_claim(id=1056105)