Configuration Models

Config

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

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.

StorageConfigSupabase

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

StorageConfigPostgres

Native PostgreSQL-backed storage for RDS or bring-your-own Postgres deployments.

ToolUseConfig

Defines a tool that the agent can use.

ProfileExtractorConfig

Configuration for profile extraction from interactions.

UserPlaybookExtractorConfig

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

PlaybookAggregatorConfig

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

DeduplicationConfig

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

ReflectionConfig

Configuration for the post-publish sliding-window reflection step, which asks the LLM whether any cited user playbook / profile rows should be replaced.

RetrievalFloorConfig

Configuration for the read-path relevance floor applied on unified search (/api/search). Retrieved candidates are reranked by a cross-encoder, and any result whose relevance score falls below the per-arm floor is dropped. Because filtering happens after retrieval, a search arm can return fewer than top_k results — including zero — when nothing clears its floor.

Floors are raw cross-encoder logits, not probabilities, so they are not bounded to [0, 1] and can be negative. The default of -5.0 is a conservative starting point that admits most candidates; calibrate it per corpus to tune precision vs. recall.

PlaybookOptimizerConfig

Opt-in (disabled by default) GEPA-backed optimizer for playbook content. Requires exactly one assistant backend — webhook_url or assistant_script_path, not both.

PendingToolCallConfig

Configuration for non-blocking pending tool calls (async information tools) during classic extraction.

AgentSuccessConfig

Configuration for agent success evaluation.

ExtractionPreset

Named presets that bundle window_size and stride_size. Accepts a string.

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

CustomEndpointConfig

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

OpenAIConfig

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

AzureOpenAIConfig

AnthropicConfig

OpenRouterConfig

GeminiConfig

MiniMaxConfig

DeepSeekConfig

DashScopeConfig

ZAIConfig

MoonshotConfig

XAIConfig

LLMConfig

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