Azure Durable Functions · Agentic Access

Azure Durable Functions Agentic Access

x-agentic-access generated

Azure Durable Functions exposes 14 API operations that an AI agent could call, of which 10 are state-changing ‘acting’ operations. This is a recommended x-agentic-access execution contract — the scope, audience, consequence tier, short-lived token constraints, and escalation each action should carry before it is handed to an autonomous agent.

By consequence: 4 read, 9 write, and 1 safety-critical.

1 operation are classed safety-critical and should require human-in-the-loop approval at runtime.

Contracts are classified heuristically from the provider’s OpenAPI and refresh on every APIs.io network build; audience is bound per deployment. The model follows Curity’s Access Intelligence (apidays Munich 2026). Browse every provider’s agent contracts at agentic-access.apis.io.

API CompositionDurable ExecutionServerless OrchestrationWorkflow
Operations: 14 Acting: 10 Human-in-the-loop: 1 Method: generated

By consequence

read 4 write 9 safety-critical 1

Highest-consequence actions

The physical and safety-critical operations an agent could invoke — the ones that most warrant scoped tokens, tight TTLs, and escalation. Full per-operation contracts are in the source below.

MethodPathConsequenceHuman-in-loop
POST /runtime/webhooks/durabletask/instances/{instanceId}/terminate safety-critical required

Source

Agentic Access

Raw ↑ 
generated: '2026-07-15'
method: generated
source: openapi/durable-functions-http-api-openapi.yml
description: Recommended x-agentic-access execution contracts, classified heuristically from
  the OpenAPI. A governance starting point for exposing this API to AI agents — review and bind
  audience per deployment. See research/curity/agentic-governance/.
summary:
  operations: 14
  by_action_class:
    acting: 10
    connected: 4
  by_consequence:
    write: 9
    read: 4
    safety-critical: 1
  human_in_the_loop_required: 1
operations:
- path: /runtime/webhooks/durabletask/orchestrators/{functionName}
  method: post
  operationId: startOrchestration
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /runtime/webhooks/durabletask/orchestrators/{functionName}/{instanceId}
  method: post
  operationId: startOrchestrationWithId
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /runtime/webhooks/durabletask/instances
  method: get
  operationId: listInstances
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /runtime/webhooks/durabletask/instances
  method: delete
  operationId: purgeInstances
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /runtime/webhooks/durabletask/instances/{instanceId}
  method: get
  operationId: getInstanceStatus
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /runtime/webhooks/durabletask/instances/{instanceId}
  method: delete
  operationId: purgeInstance
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /runtime/webhooks/durabletask/instances/{instanceId}/raiseEvent/{eventName}
  method: post
  operationId: raiseEvent
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /runtime/webhooks/durabletask/instances/{instanceId}/terminate
  method: post
  operationId: terminateInstance
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /runtime/webhooks/durabletask/instances/{instanceId}/suspend
  method: post
  operationId: suspendInstance
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /runtime/webhooks/durabletask/instances/{instanceId}/resume
  method: post
  operationId: resumeInstance
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /runtime/webhooks/durabletask/instances/{instanceId}/rewind
  method: post
  operationId: rewindInstance
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /runtime/webhooks/durabletask/entities/{entityName}/{entityKey}
  method: get
  operationId: getEntity
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /runtime/webhooks/durabletask/entities/{entityName}/{entityKey}
  method: post
  operationId: signalEntity
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /runtime/webhooks/durabletask/entities/{entityName}
  method: get
  operationId: listEntities
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none