> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praxis-ai.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Retrieve conversation histories for admin users
> Fetches conversation history data filtered by institution, user search term, and result limit
## OpenAPI
````yaml /mdx/api-reference/admin/admin-api.json post /api/admin/histories
openapi: 3.0.0
info:
title: Pria Admin API
version: 2.0.1
description: >-
Pria API Documentation Praxis's developer platform is a core part of our
mission to empower organizations to grow better. Our APIs are designed to
enable teams of any shape or size to build robust integrations that help
them customize and get the most value out of Pria. All Pria APIs are built
using REST conventions and designed to have a predictable URL structure.
They use many standard HTTP features, including methods (POST,
GET, PUT, DELETE) and error response codes.
All API calls are
made under https://hiimpria.ai/api and all responses return standard JSON.
In these docs, you'll find lists of all available endpoints for a given API,
along with interactive code blocks for building requests. For walkthroughs
of basic usage for these APIs, check out the API guides.
servers:
- url: https://pria.praxislxp.com
description: Pria API Server
security: []
tags:
- name: Authentication
description: User authentication, registration, and password management (/api/auth)
- name: OAuth
description: OAuth authentication providers - Google, GitHub, SSO (/api/auth/oauth)
- name: User
description: User profile management and account operations (/api/user)
- name: User Institutions
description: User institution memberships and switching (/api/user/institution)
- name: User Tools
description: Available tools for authenticated users (/api/user/tools)
- name: Institutions
description: Institution settings and configuration (/api/user/institution)
- name: Conversation
description: AI conversation and Q&A endpoints (/api/ai)
- name: Realtime
description: Real-time voice AI and WebRTC sessions (/api/ai/rt)
- name: Assistant
description: AI assistant configuration and management (/api/user/assistant)
- name: History
description: Conversation history and favorites (/api/user/history)
- name: RAG
description: >-
Document upload, embedding, and retrieval-augmented generation
(/api/user/files, /api/user/rag)
- name: Setting
description: Instance variables and settings management (/api/user/setting)
- name: Branding
description: Digital twin branding and customization (/api/agent/branding)
- name: Agent
description: Agent engagement and session management (/api/agent)
- name: SDK Launch
description: >-
SDK launch token signing and verification for secure iframe embedding
(/api/auth/sdk-sign, /api/auth/sdk-verify)
- name: Testing
description: Health checks, diagnostics, and test endpoints (/api/test)
- name: Admin Accounts
description: Account management for super admins (/api/admin/account)
- name: Admin Institutions
description: Institution management for admins (/api/admin/institution)
- name: Admin Users
description: User management for admins (/api/admin/user)
- name: Admin Entitlements
description: >-
User-institution relationships and permissions
(/api/admin/userInstitution)
- name: Admin Sessions
description: Session management for admins (/api/admin/session)
- name: Admin Histories
description: Conversation history management and analytics (/api/admin/history)
- name: Admin Assistants
description: AI assistant management for admins (/api/admin/assistant)
- name: Admin Questions
description: Institution question and prompt management (/api/admin/question)
- name: Admin Tools
description: Tool configuration management (/api/admin/tool)
- name: Admin AI Models
description: AI model configuration (/api/admin/aimodel)
- name: Admin MCP Servers
description: Model Context Protocol server management (/api/admin/mcpserver)
- name: Admin Feedbacks
description: User feedback management (/api/admin/feedback)
- name: Admin Uploads
description: Upload management (/api/admin/upload)
- name: Admin Charts
description: Analytics and visualization chart management (/api/admin/chart)
- name: Admin Memory
description: Admin inspection and editing of user/instance memory parameters.
- name: Admin Usage Limits
description: Per-user usage-vs-cap reporting and account-wide at-limit counts.
paths:
/api/admin/histories:
post:
tags:
- Admin Histories
summary: Retrieve conversation histories for admin users
description: >-
Fetches conversation history data filtered by institution, user search
term, and result limit
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/HistoriesRequest'
responses:
'200':
description: Successfully retrieved conversation histories
content:
application/json:
schema:
$ref: '#/components/schemas/HistoriesResponse'
'401':
description: Unauthorized - Invalid or missing access token
'403':
description: Forbidden - Insufficient permissions
'500':
description: Internal server error
security:
- apiKeyAuth: []
components:
schemas:
HistoriesRequest:
type: object
properties:
institution:
type: string
description: Institution ID to filter histories (space-separated for multiple)
usersearch:
type: string
description: >-
Search term to filter by user email, first name, or last name. Also
matches a raw 24-hex user _id (for actioned accounts whose PII has
been scrubbed).
account:
type: string
description: >-
Account ID to filter by account's institutions (space-separated for
multiple)
accountType:
type: string
enum:
- user
- admin
- super
description: Filter by user account type
course_name:
type: string
description: Filter by course name (case-insensitive partial match)
includeForgotten:
type: boolean
default: false
description: >-
When true, include conversations the user soft-deleted (forgotten);
each such row carries forgotten=true so the UI can label them.
Hidden by default.
includeInactive:
type: boolean
default: false
description: >-
Include users of any account status (not just non-deleted) in the
usersearch resolution, so inactive/actioned accounts surface.
Default false.
includeDeleted:
type: boolean
default: false
description: >-
Include soft-deleted (status:'deleted') history rows, not just
active. Default false.
daterange:
type: array
items:
type: string
format: date
nullable: true
minItems: 2
maxItems: 2
description: >-
Date range filter as [startDate, endDate]. Defaults to last 30 days
if not provided. Use null for open-ended ranges.
example:
- '2026-01-01'
- '2026-01-31'
page:
type: integer
minimum: 1
default: 1
description: Page number for pagination (1-based)
pageSize:
type: integer
minimum: 1
maximum: 5000
default: 1000
description: >-
Number of records per page (max 5000). Default 1000 for backward
compatibility.
limit:
type: integer
deprecated: true
description: 'Deprecated: use ''pageSize'' instead.'
limitsearch:
type: integer
deprecated: true
description: 'Deprecated: use ''pageSize'' instead.'
summary:
type: boolean
description: When true, returns an AI-generated summary instead of raw data
summaryInstruction:
type: string
description: Custom instruction for the AI summary generation
HistoriesResponse:
type: object
properties:
success:
type: boolean
data:
type: array
items:
$ref: '#/components/schemas/ConversationHistory'
total:
type: integer
description: Total number of matching records across all pages
hasMore:
type: boolean
description: Whether more pages exist beyond the current page
page:
type: integer
description: Current page number (1-based)
pageSize:
type: integer
description: Records per page (resolved/clamped value)
message:
type: string
ConversationHistory:
type: object
properties:
_id:
type: string
credits:
type: number
usage:
type: number
cached:
type: number
completion:
type: number
latencyMs:
type: number
ragDurationMs:
type: number
hasRagSearch:
type: boolean
description: >
True when this turn ran retrieval and produced at least one segment.
The full `ragSearch` array is NOT included in list responses — it
can be multi-KB per row and is fetched lazily via `GET
/api/admin/history/{id}/ragSearch` on `` expand.
ragSearchCount:
type: integer
description: Number of retrieved segments (used by the UI summary line).
ragSearchMode:
type: string
enum:
- RAG
- KAG
description: Retrieval mode this turn was captured under.
input:
type: string
inputs:
type: array
items:
type: string
output:
type: string
outputs:
type: array
items:
type: string
success:
type: boolean
user:
$ref: '#/components/schemas/User'
institution:
$ref: '#/components/schemas/Institution'
status:
type: string
query_duration_ms:
type: number
course_id:
type: number
course_name:
type: string
assistant:
type: object
nullable: true
description: Populated assistant reference
properties:
_id:
type: string
name:
type: string
conversation_model:
type: string
tools:
type: array
items:
$ref: '#/components/schemas/Tool'
created:
type: string
format: date-time
forgotten:
type: boolean
description: >-
True when the user soft-deleted this conversation from their
history. Returned only when includeForgotten=true in the request.
User:
type: object
properties:
_id:
type: string
description: User ID
email:
type: string
format: email
description: User email address
fname:
type: string
description: User first name
lname:
type: string
description: User last name
accountType:
type: string
description: User account type
status:
type: string
description: User status
lxp_user_id:
type: string
description: LXP user identifier
picture:
type: string
format: uri
description: Profile picture URL
lxp_user_type:
type: number
description: LXP user type
lxp_partner_id:
type: number
description: LXP partner identifier
lxp_partner_name:
type: string
description: LXP partner name
lxp_role_id:
type: number
description: LXP role identifier
lxp_role_name:
type: string
description: LXP role name
credits:
type: number
description: Available credits
creditsUsed:
type: number
description: Credits used
plan:
type: string
description: Subscription plan
institution:
$ref: '#/components/schemas/Institution'
remember_history_count:
type: number
description: History count setting
created:
type: string
format: date-time
description: Creation timestamp
Institution:
type: object
properties:
_id:
type: string
description: Institution ID
name:
type: string
description: Institution name
picture:
type: string
description: Institution picture URL
format: uri
credits:
type: integer
description: Available credits for the institution
creditsUsed:
type: integer
description: Number of credits used
creditsAwarded:
type: integer
description: Credits awarded to the institution
status:
type: string
enum:
- active
- inactive
description: Institution status
publicId:
type: string
description: Public identifier for the institution
publicAuthorizedUrls:
type: array
items:
type: string
description: List of authorized URLs for the institution
ainame:
type: string
description: AI name for the institution
contactEmail:
type: string
description: Contact email for the institution
poolCredits:
type: boolean
description: Whether credits are pooled
created:
type: string
format: date-time
description: Institution creation timestamp
lastActivityAt:
type: string
format: date-time
nullable: true
description: >-
Timestamp of the most recent activity (history save) cascaded from
users. Null if no activity has been recorded.
conversationModel:
type: string
description: AI conversation model used
account:
$ref: '#/components/schemas/Account'
agent:
$ref: '#/components/schemas/AgentWorkspaceAgentState'
nullable: true
description: >-
Agent workspace desired-state configuration for this institution,
when activation has been requested.
maxCompletionTokens:
type: integer
description: Maximum completion tokens allowed
creditsTotal:
type: number
description: Total credits available
nullable: true
creditsUsagePct:
type: number
description: Percentage of credits used
id:
type: string
description: Institution ID
displayAgentDetails:
type: boolean
description: Whether to display persisted tool details on saved History records
displayThinkingDetails:
type: boolean
description: >-
Whether to display persisted model thinking/reasoning details on
saved History records
displayRagSearchDetails:
type: boolean
description: >-
Whether to display persisted RAG/KAG retrieval segments on saved
History records
displayThinkingExecution:
type: boolean
description: >-
Whether to display the live thinking trace while a response is
streaming
displayToolExecution:
type: boolean
description: >-
Whether to display live tool execution indicators while a response
is streaming
Tool:
type: object
properties:
id:
type: string
name:
type: string
description: Unique tool name (e.g. get_browser, read_url, call_google_maps)
responseLength:
type: number
responseDurationMs:
type: number
success:
type: boolean
_id:
type: string
description: MongoDB ObjectId
description:
type: string
description: Short user-facing description of what the tool does
instructions:
type: string
description: Long-form instructions to the model on when/how to invoke this tool
argument_1:
type: string
description: >-
Natural-language description of the first argument the model should
pass
argument_2:
type: string
description: Natural-language description of the second argument
argument_3:
type: string
description: Natural-language description of the third argument
argument_4:
type: string
description: Natural-language description of the fourth argument
argument_5:
type: string
description: Natural-language description of the fifth argument
argument_6:
type: string
description: Natural-language description of the sixth argument
isArray:
type: boolean
default: false
description: >-
Whether this tool can be invoked multiple times in parallel
(array-returning)
rtEnabled:
type: boolean
default: false
description: Whether the tool is exposed in realtime (voice) conversations
rtOnly:
type: boolean
default: false
description: >-
Whether the tool is ONLY available in realtime conversations (hidden
from text mode)
categories:
type: array
items:
type: string
enum:
- research
- productivity
- creative
- communication
- learning
description: User-facing categories used to filter/group tools in the UI
status:
type: string
enum:
- active
- inactive
- deleted
default: active
description: >-
Lifecycle status. `deleted` tools are soft-deleted and excluded from
normal listings.
created:
type: string
format: date-time
description: Creation timestamp
unavailable:
type: boolean
description: >
Runtime-only flag (not stored). Set by GET /api/admin/tools for
Google-service
tools (call_google_maps, call_google_drive, etc.) when the user's
institution
has not enabled or connected the required Google Cloud service.
unavailableReason:
type: string
description: >
Runtime-only field (not stored). Human-readable reason a
Google-service tool
is unavailable (e.g. "Google OAuth not configured",
"Google Cloud not enabled for users", "Google Cloud not connected
for this instance").
description: >
A tool definition consumed by the Pria orchestrator. Field names match
the
Mongoose schema in routes/models/tool.js. Each `argument_N` is a
free-form
natural-language description of what value the model should pass for
that
positional argument — the orchestrator forwards it to the LLM as the
parameter description (NOT a JSON Schema definition).
Account:
type: object
properties:
_id:
type: string
description: Account ID
name:
type: string
description: Account name
managerEmail:
type: string
format: email
description: Email of the account's primary manager (required).
credits:
type: integer
description: Account credits.
domainUrls:
type: array
items:
type: string
description: Domains associated with the account.
status:
type: string
enum:
- active
- inactive
- deleted
description: Account status. Soft-delete sets this to `deleted`.
qualification:
type: string
description: Sales pipeline qualification (Suspect, Prospect, MQL, SQL, …).
created:
type: string
format: date-time
description: Creation timestamp
creditCaps:
type: object
description: Per-user credit caps (super-only). Disabled by default.
properties:
enabled:
type: boolean
default: false
perUserAccountTotal:
type: number
nullable: true
perUserInstitutionDefault:
type: number
nullable: true
perUser24hDefault:
type: number
nullable: true
AgentWorkspaceAgentState:
type: object
properties:
enabled:
type: boolean
status:
type: string
enum:
- not_enabled
- requested
- provisioning
- ready
- failed
- disabled
preset:
type: string
manifestYaml:
type: string
manifestDigest:
type: string
preferences:
$ref: '#/components/schemas/AgentWorkspacePreferences'
requestedBy:
type: string
requestedAt:
type: string
format: date-time
provisionedAt:
type: string
format: date-time
lastError:
type: string
AgentWorkspacePreferences:
type: object
properties:
cpu:
type: number
minimum: 0.25
maximum: 4
memoryMb:
type: integer
minimum: 512
maximum: 8192
storageGb:
type: integer
minimum: 5
maximum: 100
gui:
type: boolean
vncResolution:
type: string
example: 1280x800
securitySchemes:
apiKeyAuth:
type: apiKey
in: header
name: x-access-token
description: JWT token passed in x-access-token header
````