Scale Intelligence■ Docs
Docs / Registers / tool si.act.keep_play

tool si.act.keep_play.

A play for a brand, written once by the platform as an original or by the tenant: its goal, its condition as a predicate over its population, its class, its tactic, the move it proposes, its measure, its window, its forecast rule, its comparison, when it stops, and its graph of moves as edges (`KeepPlayInput`); the…

Figure 1si.act.keep_playspecified
AGENT'S HOSTClaude Code orany MCP clientMCP SERVERsi.act.keep_playtasks, appsCORE: ACTinput KeepPlayInputCARDbody PlayThe host draws the card from ui://scale-intelligence/cards/Play.flows forwardthe result
Over MCP, si.act.keep_play takes KeepPlayInput and returns a card whose body is Play.

the play as the next version of its name under the brand, ready, or not ready with the first reason: the condition does not compile, the graph has a cycle naming the edge, an edge cannot be evaluated naming the edge and the population, an edge is neither always nor guarded. The call needs the act grant at the brand rung.

result
a card whose body is Play
read-only
no
destructive
yes
card address
ui://scale-intelligence/cards/Play
fieldtyperequirednote
playPlayyesits condition and its edges carry their predicates by hash; a predicate given in full under predicates is kept first
predicatesPredicatenothe condition’s and the edges’ predicates in full, kept by their hashes before the play

Claims#

claimstateroute or tool
The MCP server declares si.act.keep_play at contract 0476e35e6e275db5.targetsi.act.keep_play