Random Ensemble Prompt Relay Generator

Description

Assign supplied fragments to a shuffled cyclic participant order under exact fragment appearance caps and retain every handoff and occurrence.

A structured creative brief combines a supplied bank of fictional material with explicit sequencing, timing, or compatibility rules. IDs and tags make those constraints inspectable; they do not assess the artistic meaning or quality of a scene.

Assign supplied fragments to a shuffled cyclic participant order under exact fragment appearance caps and retain every handoff and occurrence.

When to use this tool

Use this generator to create reproducible ensemble prompt relay cases from the supplied model or bank. Inspect the returned evidence before using cases in a test or exercise.

How to use the tool and how it works

Supply participants, fragments, turns, maximumFragmentAppearances in the field shapes below. Set seed when you need an explicit replay.
Run the tool and correct any input error. For generated controls, distinguish a successful fixture containing an invalid case from failure to generate the fixture.
Read participantCycle, turns, fragmentUsage, rounds. Use the conventions below. Keep answer-bearing fields separate when presenting an exercise.

Shuffle a participant cycle, choose fragments with appearances remaining, and rotate turns through participants. Record fragment occurrence counts, preceding/following handoffs, and rounds sized to the participant count.^[1]

Input field	Meaning and units	Accepted input
participants	Participants	Required. Array of Text; minimum UTF-16 length 1; maximum UTF-16 length 64.; minimum items 1; maximum items 16.
fragments	Fragments	Required. Array of Object; no unknown keys.; minimum items 1; maximum items 16.
fragments[].id	Literal identifier used independently of display labels.	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 64.
fragments[].text	Text	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 1024.
turns	Turns	Required. Safe integer; minimum 1; maximum 32.
maximumFragmentAppearances	Maximum Fragment Appearances	Required. Safe integer; minimum 1; maximum 32.
seed	Optional numeric seed; takes precedence over context randomness. Without either, use the fixed tool.io default seed.	Optional. Safe integer.

Output field	Interpretation	Returned shape
participantCycle	Participant Cycle	Required. Array of Text; minimum UTF-16 length 1; maximum UTF-16 length 64.; minimum items 1; maximum items 16.
turns	Turns	Required. Array of Object; no unknown keys.; minimum items 1; maximum items 32.
turns[].turn	Turn	Required. Safe integer; minimum 1; maximum 32.
turns[].participantId	Participant Id	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 64.
turns[].fragmentId	Fragment Id	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 64.
turns[].text	Text	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 1024.
turns[].receivedFrom	Received From	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 64. or Null.
turns[].handoffTo	Handoff To	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 64. or Null.
turns[].occurrence	Occurrence	Required. Safe integer; minimum 1; maximum 32.
fragmentUsage	Fragment Usage	Required. Array of Object; no unknown keys.; minimum items 1; maximum items 16.
fragmentUsage[].fragmentId	Fragment Id	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 64.
fragmentUsage[].count	Count	Required. Safe integer; minimum 0; maximum 32.
rounds	Rounds	Required. Array of Array of Safe integer; minimum 1; maximum 32.; minimum items 1; maximum items 16.; minimum items 1; maximum items 32.
randomness	Replay source and normalized 32-bit seed, or null seed for an advancing context source.	Required. Object; no unknown keys.
randomness.seed	Optional safe-integer replay seed; normalization and precedence are explained below.	Required. Safe integer. or Null.
randomness.source	Source	Required. Text; one of "context", "seed".

An explicit safe-integer seed takes precedence over injected context randomness and is normalized to an unsigned 32-bit integer. With no seed and no context source, replay uses the fixed tool.io default seed. A context source must return finite values from zero inclusive to one exclusive; its advancing state must be retained separately. randomness records the source and normalized seed, or null for context. These generators are not cryptographic random sources.

json

{
  "input": {
    "participants": [
      "a",
      "b"
    ],
    "fragments": [
      {
        "id": "map",
        "text": "Find the map"
      },
      {
        "id": "bell",
        "text": "Hear the bell"
      }
    ],
    "turns": 2,
    "maximumFragmentAppearances": 1,
    "seed": 42
  },
  "output": {
    "participantCycle": [
      "b",
      "a"
    ],
    "turns": [
      {
        "turn": 1,
        "participantId": "b",
        "fragmentId": "bell",
        "text": "Hear the bell",
        "receivedFrom": null,
        "handoffTo": "a",
        "occurrence": 1
      },
      {
        "turn": 2,
        "participantId": "a",
        "fragmentId": "map",
        "text": "Find the map",
        "receivedFrom": "b",
        "handoffTo": null,
        "occurrence": 1
      }
    ],
    "fragmentUsage": [
      {
        "fragmentId": "map",
        "count": 1
      },
      {
        "fragmentId": "bell",
        "count": 1
      }
    ],
    "rounds": [
      [
        1,
        2
      ]
    ],
    "randomness": {
      "seed": 42,
      "source": "seed"
    }
  }
}

Limitations and assumptions

Fragments may repeat up to the supplied cap, while participants repeat cyclically. Handoffs are fictional prompts rather than a communication system; insufficient total appearances make the request infeasible.
A replay requires the same complete input and implementation. The stated sampling convention applies within its eligible space. A finite draw does not exhaust all possible outputs; repeats remain possible unless a distinct-selection rule is explicit.
The field tables state structural bounds; cross-field constraints and bounded search or output budgets also apply. Unknown keys are rejected where the object contract disallows them. Input errors are distinct from null fields and deliberate invalid controls in a successful output.

Alternative or Complementary methods

For a supplied example, inspect the returned construction or delegated check directly. To evaluate a consumer, also test cases chosen for its own boundaries; a generated finite corpus does not establish exhaustive coverage.

References

Tool behavior and example: Random Ensemble Prompt Relay Generator — tool.io

Similar or alternative tools

Random Character Walk Prompt Grid Generator
Sample distinct combinations of caller-approved movement adjectives and fictional goals into a bounded prompt board; callers review physical suitability.
Random Alternate Ending Comparison Packet Generator
Combine a supplied premise with distinct supplied endings and an explicit consequence-tag comparison without generating narrative prose.