Reflexio Docs
API ReferenceSchemas

Configuration Models

Data structures for system configuration — profile extraction, playbook extraction, evaluation, storage, and LLM settings.

Configuration Models

Config

Root configuration object for the Reflexio system. Every nested type below is linked — click through to see the fields each accepts.

Prop

Type

StorageConfig

StorageConfig is a union type — pass whichever variant matches your deployment. None is also accepted (no storage configured yet).

StorageConfigSQLite

Local SQLite storage. The default for self-hosted open-source installs.

Prop

Type

StorageConfigSupabase

Supabase-backed storage for managed Reflexio Enterprise and self-hosted Supabase deployments.

Prop

Type

StorageConfigDisk

File-based storage with on-disk entities and QMD search.

Prop

Type

ToolUseConfig

Defines a tool that the agent can use.

Prop

Type

ProfileExtractorConfig

Configuration for profile extraction from interactions.

Prop

Type

UserPlaybookExtractorConfig

Configuration for user-playbook extraction. Also exposed as PlaybookConfig (deprecated alias).

Prop

Type

PlaybookAggregatorConfig

Configuration for playbook aggregation (clustering similar user playbooks into agent playbooks).

Prop

Type

DeduplicationConfig

Controls the hybrid-search behavior when looking for existing playbooks to dedup against.

Prop

Type

AgentSuccessConfig

Configuration for agent success evaluation.

Prop

Type

ExtractionPreset

Named presets that bundle batch_size and batch_interval. Accepts a string.

  • quick_chat — short conversations (support bots, quick Q&A). batch_size=5, batch_interval=3.
  • standard — general-purpose conversational agents. batch_size=10, batch_interval=5. (default)
  • long_form — long conversations (coding assistants, research). batch_size=25, batch_interval=10.
  • high_volume — high-traffic agents (1000+ daily interactions). batch_size=15, batch_interval=8.

APIKeyConfig

API key configuration for LLM providers. When custom_endpoint is configured, it takes priority over all other providers for LLM completion calls (but not embeddings).

Prop

Type

CustomEndpointConfig

OpenAI-compatible custom endpoint. Validated against SSRF (always blocks cloud metadata endpoints; blocks private IPs when REFLEXIO_BLOCK_PRIVATE_URLS=true).

Prop

Type

OpenAIConfig

OpenAI API configuration. At least one of api_key or azure_config must be provided.

Prop

Type

AzureOpenAIConfig

Prop

Type

AnthropicConfig

Prop

Type

OpenRouterConfig

Prop

Type

GeminiConfig

Prop

Type

MiniMaxConfig

Prop

Type

DeepSeekConfig

Prop

Type

DashScopeConfig

Prop

Type

ZAIConfig

Prop

Type

MoonshotConfig

Prop

Type

XAIConfig

Prop

Type

LLMConfig

LLM model configuration overrides. If a field is None, the system default is used.

Prop

Type