Expired60% confidenceFactTime unknown
A new -R/--no-reasoning flag has been added to suppress reasoning token output, which is the only CLI-level change in this version.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
LLM 0.32a0 重大重构解析：向后兼容的架构升级如何应对多模态与工具调用时代
rss
Related Entities
Related Claims
UnverifiedLLM 0.32 added a -R/--no-reasoning flag to completely suppress the output of reasoning tokens.78% similarPartially VerifiedThe new version of LLM's CLI tool can display thinking text and final responses in different colors, outputs thinking text to stderr, and adds a -R/--no-reasoning flag to suppress reasoning token output.64% similarUnverifiedOutlines constructs a Finite State Machine (FSM) that dynamically masks tokens at each generation step that would render the format invalid, allowing the model to sample only from the subset of legal tokens.57% similarUnverified结构化的 CLI 命令输出语义密度高、冗余少，Agent 可用更少 token 完成同等信息量的理解与决策56% similarUnverifiedThe /fork command in Codex CLI can copy the current session into an independent branch, preserving all context while keeping subsequent modifications mutually isolated, similar to Git branching.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/35565API
curl https://kongchang.com/api/v1/knowledge/claims/35565MCP
get_claim(id=35565)