xyz.quasigod.lab.letta.defs

quasigod.spaces-alpha.bsky.network

Documentation

compactionSettings object

Automatic-compaction behavior for a conversation.

Properties

clipChars integer Optional

Maximum characters kept in the conversation window before compaction.

minimum: 0
mode string Optional

Compact the whole history, or only the oldest fraction beyond the sliding window.

Known values: all, sliding_window
model string Optional

Optional model override for the summarization call.

maxLength: 256 bytes
modelSettings unknown Optional

Free-form settings for the summarization model.

prompt string Optional

Custom summarization prompt. Null/absent uses the default.

maxLength: 100000 bytes
slidingWindowPercentage number Optional

Fraction of the context window retained after a sliding-window compaction.

minimum: 0maximum: 1
View raw schema 
{
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "description": "Compact the whole history, or only the oldest fraction beyond the sliding window.",
      "knownValues": [
        "all",
        "sliding_window"
      ]
    },
    "model": {
      "type": "string",
      "maxLength": 256,
      "description": "Optional model override for the summarization call."
    },
    "prompt": {
      "type": "string",
      "maxLength": 100000,
      "description": "Custom summarization prompt. Null/absent uses the default."
    },
    "clipChars": {
      "type": "integer",
      "minimum": 0,
      "description": "Maximum characters kept in the conversation window before compaction."
    },
    "modelSettings": {
      "type": "unknown",
      "description": "Free-form settings for the summarization model."
    },
    "slidingWindowPercentage": {
      "type": "number",
      "maximum": 1,
      "minimum": 0,
      "description": "Fraction of the context window retained after a sliding-window compaction."
    }
  },
  "description": "Automatic-compaction behavior for a conversation."
}
modelSettings object

Tunables for a model. The keys here are the ones letta reads and forwards to the model runtime.

Properties

contextWindowLimit integer Optional

Context window size in tokens. When absent, the model default is used.

minimum: 0
enableReasoner boolean Optional

Whether the reasoner is enabled when the model supports it. Expected to be true.

maxTokens integer Optional

Maximum output tokens per turn. Null lets the model decide.

minimum: 0
parallelToolCalls boolean Optional

Whether the model may issue multiple tool calls per turn. Expected to be true.

reasoningEffort string Optional

Reasoning effort knob (e.g. low/medium/high). Free-form: model providers differ.

maxLength: 32 bytes
thinkingDisabled boolean Optional

True when the model's thinking mode is explicitly disabled. Expected to be false.

View raw schema 
{
  "type": "object",
  "properties": {
    "maxTokens": {
      "type": "integer",
      "minimum": 0,
      "description": "Maximum output tokens per turn. Null lets the model decide."
    },
    "enableReasoner": {
      "type": "boolean",
      "description": "Whether the reasoner is enabled when the model supports it. Expected to be true."
    },
    "reasoningEffort": {
      "type": "string",
      "maxLength": 32,
      "description": "Reasoning effort knob (e.g. low/medium/high). Free-form: model providers differ."
    },
    "thinkingDisabled": {
      "type": "boolean",
      "description": "True when the model's thinking mode is explicitly disabled. Expected to be false."
    },
    "parallelToolCalls": {
      "type": "boolean",
      "description": "Whether the model may issue multiple tool calls per turn. Expected to be true."
    },
    "contextWindowLimit": {
      "type": "integer",
      "minimum": 0,
      "description": "Context window size in tokens. When absent, the model default is used."
    }
  },
  "description": "Tunables for a model. The keys here are the ones letta reads and forwards to the model runtime."
}

Lexicon Garden

@