Skip to content

Graphorin API reference v0.4.0


Graphorin API reference / @graphorin/memory / / ConsolidatorConfig

Interface: ConsolidatorConfig

Defined in: packages/memory/src/consolidator/types.ts:92

Locked-down configuration accepted by createConsolidator(...).

Stable

Properties

PropertyModifierTypeDescriptionDefined in
budgetAttributionreadonly"shared" | "per-trigger"-packages/memory/src/consolidator/types.ts:103
budgetResetSemanticsreadonly"utc" | "local" | "sliding-24h"-packages/memory/src/consolidator/types.ts:102
ceilingsreadonlyConsolidatorCeilings-packages/memory/src/consolidator/types.ts:96
cheapModelreadonlystring | nullCheap-model identifier used by the standard phase. null disables.packages/memory/src/consolidator/types.ts:99
contextualRetrievalreadonlyContextualRetrievalModeContextual retrieval for facts written by the standard phase (P1-3). 'late-chunk' (default at every tier) relies on the offline situating-context prefix the shared SemanticMemory computes for every write — no extra LLM call. 'llm' is the opt-in enrichment: the standard phase spends one budgeted cheap-model call per additive write to author a 1–2 sentence situating prefix, then passes it as the write's index text. 'off' indexes the bare text. The 'llm' mode is consolidator-only by construction — the hot write path never has a provider for contextualization.packages/memory/src/consolidator/types.ts:175
decayArchiveThresholdreadonlynumber-packages/memory/src/consolidator/types.ts:107
decayCapacityreadonlynumber | nullCapacity-bounded eviction target for the light phase (X-1). When set, each light pass archives the lowest-salience live facts in the LRU decay window down to this many — cost / staleness control, not an accuracy lever. null (the default at every tier) leaves storage unbounded, so behaviour is identical to pre-X-1. Archiving is a soft, recoverable move; nothing is hard-deleted.packages/memory/src/consolidator/types.ts:116
decayTauDaysreadonlynumber-packages/memory/src/consolidator/types.ts:106
deepModelreadonlystring | nullDeep-model identifier used by the deep phase. null disables.packages/memory/src/consolidator/types.ts:101
dlqBaseBackoffMsreadonlynumber-packages/memory/src/consolidator/types.ts:127
dlqMaxBackoffMsreadonlynumber-packages/memory/src/consolidator/types.ts:128
dlqMaxRetriesreadonlynumber-packages/memory/src/consolidator/types.ts:126
formEpisodesreadonlybooleanAuto-form a quarantined episode from each processed standard-phase slice (P1-2). Defaults on at the standard+ tiers, off at free / cheap / custom. The episode summary is one budgeted LLM call; when the budget is exhausted (or no episodic tier is wired) the phase degrades to fact-only behaviour.packages/memory/src/consolidator/types.ts:136
importanceScoringreadonlybooleanAsk the episode-summarization call for an LLM importance score (1–10, normalized to [0, 1]) so episodic triple-signal retrieval (recency × relevance × importance) runs on all three signals (P1-2). Importance is always a soft signal — it never gates retention. Defaults track formEpisodes.packages/memory/src/consolidator/types.ts:144
importanceThresholdreadonlynumberSum of recent episode importance (each in [0, 1]) at or above which reflection fires. Below it the pass makes no LLM call. Defaults to 3.packages/memory/src/consolidator/types.ts:161
lockWaitMsreadonlynumber-packages/memory/src/consolidator/types.ts:105
maxDeepConflictsPerRunreadonlynumber-packages/memory/src/consolidator/types.ts:125
maxStandardBatchSizereadonlynumber-packages/memory/src/consolidator/types.ts:124
noiseFiltersreadonlyreadonly ("default" | "minimal" | "none")[]-packages/memory/src/consolidator/types.ts:104
onExceedreadonlyOnBudgetExceed-packages/memory/src/consolidator/types.ts:97
phasesreadonlyreadonly ConsolidatorPhase[]-packages/memory/src/consolidator/types.ts:95
reflectionreadonlybooleanRun the deep-phase reflection pass (P1-1): when accumulated episode importance crosses importanceThreshold, synthesize higher-order, cited insights over recent memories (Generative Agents). Insights land quarantined + provenance: 'reflection' and are ranked below the facts they cite. Defaults on at the full tier only (off at free / cheap / standard / custom) — it is the most LLM-intensive phase. A no-op without an episodic tier or an insight-capable storage adapter.packages/memory/src/consolidator/types.ts:155
reflectionMaxQuestionsreadonlynumberUpper bound on salient questions reflection asks per pass. Defaults to 3.packages/memory/src/consolidator/types.ts:163
salienceWeightsreadonlySalienceWeightsWeights for the multi-signal salience score (X-1) that orders both threshold archiving and capacity eviction. Defaults to DEFAULT_SALIENCE_WEIGHTS; with neutral importance, active status, and first-party provenance salience equals plain retention.packages/memory/src/consolidator/types.ts:123
tierreadonlyConsolidatorTier-packages/memory/src/consolidator/types.ts:94
triggersreadonlyreadonly ConsolidatorTriggerSpec[]-packages/memory/src/consolidator/types.ts:93