Unverified50% confidenceFactExact time
A request signature is a fingerprint generated by the gateway for each LLM call, composed of elements such as a hash of the prompt text, model parameters, and tool-call context.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn LLM calls, prompt tokens refer to the number of tokens contained in the input portion sent to the model, including the system prompt, schema summary, historical conversation, and current instruction; completion tokens are the output portion generated by the model.71% similarUnverifiedIn the can draft branch, after the LLM node (connected to Claude) generates a reply, the Gmail node uses the "create draft" operation to write the customer's email address and the AI reply into the drafts folder, which must be confirmed by a human before sending.67% similarUnverifiedSignTrace's core components include five processing stages: LLM-based dictionary augmentation, motion extraction, dictionary-style rewriting, seven-channel retrieval, and candidate re-ranking.62% similarUnverifiedA typical tool-call request includes fixed fields such as name (function name) and arguments (parameter dictionary).62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1080688API
curl https://kongchang.com/api/v1/knowledge/claims/1080688MCP
get_claim(id=1080688)