Unverified50% confidenceFactExact time
Finish reason (finish_reason/stop_reason) is a model response metadata field indicating why generation ended: normal completion, reaching the max_tokens limit, triggering content filtering, or a tool call request, etc.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCommon values of the finish_reason field include stop (natural end) and length (truncated upon reaching the maximum token count).74% similarUnverifiedIn practice, stop_reason === 'tool_use' does not reliably reflect message structure: a response may contain a real tool call block yet report end_turn.71% similarUnverifiedOpenAI 流式响应以 data: [DONE] 标记结束，Anthropic 则使用 event: message_stop 事件类型68% similarUnverifiedOnly responses with a finish_reason of stop or tool_calls should be cached; responses truncated by length or those that errored should not be cached.67% similarUnverifiedIf finish_reason is length while the client still treats the content as a complete answer, this falls under the truncation_ambiguity failure classification.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1071741API
curl https://kongchang.com/api/v1/knowledge/claims/1071741MCP
get_claim(id=1071741)