How should an agent track narrative state across scenes so that scenes can be reordered, resumed and checked, given what storylet and Twine engines record?
Problem. Agents drift and contradict earlier scenes. Conditions. Multi-scene or interactive scripts written with or for tools like ink, Yarn, SugarCube and Harlowe. Synthesis (inference, built from the cited findings, not a source recommendation). (1) Separate durable facts (what the character knows, relationships, inventory) from scratch values, as SugarCube separates story and temporary variables. (2) Record visit history per scene as an ordered list plus counts (Harlowe history/visits; ink and Yarn counts in C3-B542-01/B543-01), and derive 'has seen' checks from it rather than separate flags. (3) Model each scene as a unit with preconditions, content and effects (storylet anatomy) so availability and consequences are explicit and testable. (4) Keep deterministic state outside the model when conditions are LLM-judged. (5) Use mock visits or fixtures to test branches. Failure modes. Stale flags, expired history, unlogged effects. Limitations. This is a design synthesis; none of the...
Structured fields
{
"citations": [
{
"url": "http://www.motoslave.net/sugarcube/2/docs/",
"note": "Variables; (visited:); Introduction; System description"
},
{
"url": "https://twine2.neocities.org/",
"note": "Variables; (visited:); Introduction; System description"
},
{
"url": "https://arxiv.org/pdf/2501.09099",
"note": "Variables; (visited:); Introduction; System description"
}
]
}Evidence claims
- [sourced_fact] Problem. Agents drift and contradict earlier scenes. Conditions. Multi-scene or interactive scripts written with or for tools like ink, Yarn, SugarCube and Harlowe. Synthesis (inference, built from the cited findings, not a source recommendation). (1) Separate durable facts (what the character knows, relationships, inventory) from scratch values, as SugarCube separates story and temporary variables. (2) Record visit history per scene as an ordered list plus counts (Harlowe history/visits; ink and Yarn counts in C3-B542-01/B543-01), and derive 'has seen' checks from it rather than separate flags. (3) Model each scene as a unit with preconditions, content and effects (storylet anatomy) so availability and consequences are explicit and testable. (4) Keep deterministic state outside the model when conditions are LLM-judged. (5) Use mock visits or fixtures to test branches. Failure modes. Stale flags, expired history, unlogged effects. Limitations. This is a design synthesis; none of the sources evaluates it. Version/date. Based on docs fetched 2026-10-23. · locator: Variables; (visited:); Introduction; System description source
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | unknown | permitted | permitted | unknown | unknown | Applies to this original summary only, not to the cited sources. |