> ## 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.
# Run one of the caller's workflows now.
> Starts the workflow's agent through the same deploy chain a catalogue deploy uses. Manual trigger only — there is no scheduling and nothing runs unattended. The agent is resolved from the SAVED workflow; the request body is ignored entirely. If a session for that agent is already running, the existing session is returned with outcome `reused` — it is never presented as a fresh start.
When the outcome is `started` and the workflow has a non-empty instruction, the instruction is delivered to the new session on a BEST-EFFORT basis (bounded in-request retry). Delivery failure NEVER fails the run: the session did start. The result reports it separately via `instructionDelivered` / `deliveryState` / `deliveryCode`.
The instruction is NEVER delivered on a `reused` outcome. This system has no observable turn state, so an injected prompt could land mid-turn; the caller is told to open the session instead.
Workflows made by the Digital Twin (`madeBy: twin`) run in their own read-only session that closes after the turn, and never reuse a live one: a run while another is live answers 409 `workflow_busy`. They need automatic session cleanup (409 `auto_close_unavailable`), share a limit of 48 started runs per owner per 24 hours across chat, page and schedule (429 `run_limit`, recorded as a rejected run), and can be refused 409 `tool_group_unavailable` or `model_unavailable`. They are paid like any other agent use (owner ruling 10): the model follows the institution's credential mode (`user_oauth` the owner's own connection, `institution_oauth` the institution's connection, `api_key` the institution's key), refused 409 `credential_unavailable` when that route has no credential and 409 `model_route_changed` when it now serves a different model than the saved one. Delegated tokens get 403 `TWIN_MANAGED`. (A scheduled Twin run whose workflow agent is gone is released as failed with `WORKFLOW_AGENT_MISSING`; that code is internal to the scheduler.)
## OpenAPI
````yaml /mdx/api-reference/runtime/runtime-api.json post /api/user/agents/workflows/{id}/run
openapi: 3.0.0
info:
title: Pria Runtime API
version: 2.0.236
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.
A
session that a course page (Canvas) opened for an administrator — or that a
Digital Twin's sign-in provider opened for one of its people — starts with
user rights in that twin only: until the person confirms it's them with a
code (POST /api/user/launch-scope/challenge, then /api/auth/mfa-resend and
/api/auth/mfa-verify), every route outside that twin's day-to-day work
answers 403 with code LAUNCH_SCOPE_STEP_UP and the twin's id.
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: Audio Notes
description: Capture and ingest spoken notes into the personal vault
- name: Memory
description: User-facing memory parameters (personal + shared instance memory).
- name: My Data
description: >-
GDPR controls — personal-scope counts, async ZIP-by-email export, and
scoped soft-delete. Every endpoint pins `user = req.user._id` AND
`institution: null`; institution-scoped data is governed by the
institution's own retention policy and never reached from here.
- name: Questions
description: >-
User-facing read of the onboarding question bank used by the "create a
digital twin" wizard.
- name: Transcription
description: >-
One-shot speech-to-text for in-place dictation. Audio blob in, transcript
out — no Upload / History / RAG embeddings are persisted. Use
`/audio-notes` for anything durable.
paths:
/api/user/agents/workflows/{id}/run:
post:
tags:
- User
summary: Run one of the caller's workflows now.
description: >
Starts the workflow's agent through the same deploy chain a catalogue
deploy uses. Manual trigger only — there is no scheduling and nothing
runs unattended. The agent is resolved from the SAVED workflow; the
request body is ignored entirely. If a session for that agent is already
running, the existing session is returned with outcome `reused` — it is
never presented as a fresh start.
When the outcome is `started` and the workflow has a non-empty
instruction, the instruction is delivered to the new session on a
BEST-EFFORT basis (bounded in-request retry). Delivery failure NEVER
fails the run: the session did start. The result reports it separately
via `instructionDelivered` / `deliveryState` / `deliveryCode`.
The instruction is NEVER delivered on a `reused` outcome. This system
has no observable turn state, so an injected prompt could land mid-turn;
the caller is told to open the session instead.
Workflows made by the Digital Twin (`madeBy: twin`) run in their own
read-only session that closes after the turn, and never reuse a live
one: a run while another is live answers 409 `workflow_busy`. They need
automatic session cleanup (409 `auto_close_unavailable`), share a limit
of 48 started runs per owner per 24 hours across chat, page and schedule
(429 `run_limit`, recorded as a rejected run), and can be refused 409
`tool_group_unavailable` or `model_unavailable`. They are paid like any
other agent use (owner ruling 10): the model follows the institution's
credential mode (`user_oauth` the owner's own connection,
`institution_oauth` the institution's connection, `api_key` the
institution's key), refused 409 `credential_unavailable` when that route
has no credential and 409 `model_route_changed` when it now serves a
different model than the saved one. Delegated tokens get 403
`TWIN_MANAGED`. (A scheduled Twin run whose workflow agent is gone is
released as failed with `WORKFLOW_AGENT_MISSING`; that code is internal
to the scheduler.)
parameters:
- in: path
name: id
required: true
schema:
type: string
responses:
'202':
description: Started, or an already-running session was returned.
content:
application/json:
schema:
$ref: '#/components/schemas/AgentWorkflowRunResult'
'402':
description: Insufficient agentic credits.
content:
application/json:
schema:
$ref: '#/components/schemas/AgentWorkflowError'
'403':
description: >-
The agent is not enabled for this institution, or TWIN_MANAGED (a
delegated token on a Twin row).
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/AgentWorkflowError'
- $ref: '#/components/schemas/AgentWorkflowRunRejected'
'404':
description: Workflow not found, or its agent no longer exists.
content:
application/json:
schema:
$ref: '#/components/schemas/AgentWorkflowError'
'409':
description: >-
Workflow disabled, runtime cannot launch this agent, no credential
configured, or too many agents already running; for Twin rows also
workflow_busy, auto_close_unavailable (not recorded),
tool_group_unavailable, model_unavailable, credential_unavailable or
model_route_changed (recorded as rejected runs).
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/AgentWorkflowError'
- $ref: '#/components/schemas/AgentWorkflowRunRejected'
'429':
description: >-
run_limit — a Twin workflow owner has 48 started runs in the last 24
hours. Recorded as a rejected run.
content:
application/json:
schema:
$ref: '#/components/schemas/AgentWorkflowRunRejected'
security:
- apiKeyAuth: []
components:
schemas:
AgentWorkflowRunResult:
type: object
properties:
success:
type: boolean
outcome:
type: string
enum:
- started
- reused
workflowId:
type: string
runId:
type: string
sessionId:
type: string
workspaceId:
type: string
status:
type: string
agent:
type: object
nullable: true
description: >-
The bound agent. On a workflow made by the Digital Twin both fields
are empty strings (its binding is internal), and `message` names the
workflow.
properties:
key:
type: string
name:
type: string
reused:
type: boolean
description: >-
True when an existing session for this agent was returned instead of
a new one. Never presented as a fresh start.
instruction:
type: string
description: >-
The saved instruction. Also delivered to the session when outcome is
`started`; see instructionDelivered.
instructionDelivered:
type: boolean
description: >-
True only when the saved instruction was actually accepted by the
agent session. Independent of `outcome`.
deliveryState:
type: string
enum:
- n/a
- delivered
- not_ready
- failed
description: >
n/a — nothing to deliver, or delivery deliberately not attempted
(empty instruction, or outcome `reused`). delivered — the prompt
frame was accepted. not_ready — the session was not promptable
within the bounded in-request retry budget. failed — the guest agent
rejected or errored on the send.
deliveryCode:
type: string
description: >-
Machine-readable reason when not delivered, e.g. REUSED_SESSION,
SESSION_INCOMPLETE, NO_CONTROL_KEY, SEND_FAILED.
deliveryMessage:
type: string
description: User-safe reason when not delivered.
message:
type: string
AgentWorkflowError:
type: object
properties:
success:
type: boolean
example: false
code:
type: string
description: >-
Twin workflow codes: TWIN_MANAGED (403 — delegated desktop-agent or
impersonation token), TWIN_BINDING_FIXED (403 — a presetKey change
on a Twin row), INSTRUCTION_REQUIRED (400), schedule_too_frequent
(400), schedule_limit (409), workflow_busy / auto_close_unavailable
(409, not recorded as runs).
enum:
- INVALID_NAME
- INVALID_PRESET
- INSTRUCTION_TOO_LONG
- DUPLICATE_NAME
- AGENT_NOT_FOUND
- AGENT_NOT_ENABLED
- AGENT_RUNTIME_CAPABILITY_UNAVAILABLE
- NOT_FOUND
- WORKFLOW_DISABLED
- TWIN_MANAGED
- TWIN_BINDING_FIXED
- INSTRUCTION_REQUIRED
- schedule_too_frequent
- schedule_limit
- workflow_busy
- auto_close_unavailable
message:
type: string
AgentWorkflowRunRejected:
type: object
description: >-
A run refused after the run row was written (outcome `rejected`). Twin
workflow codes here include run_limit (429), tool_group_unavailable,
model_unavailable, credential_unavailable (the institution’s agent
credential route — its connection or API key, or the owner’s own
connection under user_oauth — cannot serve the workflow) and
model_route_changed (the credential route now serves a different model
than the one the workflow was saved with; never substituted) (409).
properties:
success:
type: boolean
example: false
outcome:
type: string
enum:
- rejected
workflowId:
type: string
runId:
type: string
code:
type: string
example: run_limit
message:
type: string
retryable:
type: boolean
details:
type: object
securitySchemes:
apiKeyAuth:
type: apiKey
in: header
name: x-access-token
description: JWT token passed in x-access-token header
````
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.