Schemas

Search Models

Data structures for unified search across all entity types.

ConversationTurnmodel

A single turn in a conversation history, used to give the server enough context to reformulate a search query.

Prop	Type
`role`	string
`content`	string

UnifiedSearchRequestrequest model

Request model for searching across all entity types in a single call.

Prop	Type
`query`	string
`top_k`	integer
`threshold`	float
`agent_version`	string
`playbook_name`	string
`user_id`	string
`source`	string
`request_id`	string
`tags`	array[string]
`entity_types`	array[string]
`agent_playbook_status_filter`	array[PlaybookStatus]
`conversation_history`	array[ConversationTurn]
`enable_reformulation`	boolean
`enable_agent_answer`	boolean
`search_mode`	SearchMode
`session_id`	string
`interaction_id`	integer

UnifiedSearchResponseresponse model

Response model for unified search across all entity types.

Info

Retrieved results are reranked by a cross-encoder and dropped below a per-arm relevance floor (see retrieval_floor in the configuration models). Unified search also omits source user playbooks already represented by returned agent playbooks. As a result, each result array may contain fewer than top_k items — including an empty array — when nothing clears the floor or user playbooks are suppressed. An empty array means nothing was relevant, not that the search failed.

When a retrieval experiment is active, the response includes experiment. Holdout searches also return success=true, but all learning result arrays are empty and retrieval is skipped. Dashboard inspection bypasses experiment assignment.

Prop	Type
`success`	boolean
`profiles`	array[UserProfile]
`agent_playbooks`	array[AgentPlaybook]
`user_playbooks`	array[UserPlaybook]
`reformulated_query`	string
`degraded`	boolean
`search_mode_effective`	string
`agent_answer`	string
`agent_trace`	string
`rehydrated_text`	string
`experiment`	RetrievalExperimentAssignment
`msg`	string

RetrievalExperimentAssignmentmodel

Attribution returned by unified, profile, user-playbook, and agent-playbook learning searches while an experiment applies.

Prop	Type
`experiment_id`	string
`arm`	"treatment" \| "holdout"

PreviousRequest Models Next claude-smart