For the complete documentation index, see llms.txt. This page is also available as Markdown.

Harness Context

Retrieve the neutral session-bootstrap context for a service for integration discovery without launching a hosted framework run.

Harness context is the neutral session-bootstrap projection for a service. It includes identity and reference instructions, world scope, tool descriptors, guardrails, the server-enforced write floor, and runtime hints for a customer integration. This operation does not launch a run.

The projection is PHI-free: it does not include scoped entities or rendered caller prose.

Get Harness Context

Fetch the neutral session-bootstrap context for a service

get

The retrievable CONTEXT edge of the world-model harness: identity + reference instructions, world scope, tool descriptors, guardrails, and an MCP write-policy summary. It shares the HarnessContext schema with the hosted harness but is not byte-identical to a hosted render. PHI-free (the API-run projection carries no scoped entities or rendered caller prose).

Authorizations
AuthorizationstringRequired

API key issued via POST /v1/{workspace_id}/api-keys. Pass the returned api_key value as a Bearer token.

Path parameters
workspace_idstring · uuidRequired
Query parameters
service_idstring · uuidRequired
version_setstring · max: 255OptionalDefault: release
Responses
200

Successful Response

application/json

A framework-neutral, retrievable service bootstrap projection.

context_versionintegerOptionalDefault: 1
config_fingerprintstringOptionalDefault: ""
sourcestringOptionalDefault: ""
get/v1/{workspace_id}/agent-runs/harness-context
GET /v1/{workspace_id}/agent-runs/harness-context?service_id=123e4567-e89b-12d3-a456-426614174000 HTTP/1.1
Host: platform.api-us.concurrence.com
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
{
  "context_version": 1,
  "config_fingerprint": "",
  "source": "",
  "identity": {
    "entry_actor_name": "",
    "name": "",
    "role": "",
    "developed_by": "",
    "instructions": "",
    "initial_state": ""
  },
  "world_scope": {
    "workspace_id": "123e4567-e89b-12d3-a456-426614174000",
    "scoped_entity_ids": [
      "123e4567-e89b-12d3-a456-426614174000"
    ],
    "allow_create": false
  },
  "tools": {
    "descriptors": [
      {
        "name": "text",
        "description": "",
        "input_schema": {
          "ANY_ADDITIONAL_PROPERTY": "anything"
        }
      }
    ],
    "read_tool_names": [
      "text"
    ],
    "write_tool_names": [
      "text"
    ]
  },
  "guardrails": {
    "guardrails": [
      {
        "ANY_ADDITIONAL_PROPERTY": "anything"
      }
    ],
    "global_boundary_constraints": [
      "text"
    ],
    "global_action_guidelines": [
      "text"
    ]
  },
  "write_floor": {
    "enforced_at": "mcp-world-tools-edge",
    "requires_entity_anchor": true,
    "clinical_write_principal": "provider-only",
    "clinical_write_scope": "any-entity-in-workspace",
    "enrichment_write_scope": "caller-anchor-only",
    "unanchored_or_api_key_writes": "none",
    "allow_create": false
  },
  "runtime": {
    "engage_model": "",
    "channel_kind": "",
    "language": "",
    "caller_context": ""
  }
}

Notes

  • This is a neutral API projection, not a byte-for-byte copy of a live session render.

  • Service resolution uses the requested version set. Missing or unavailable configuration can prevent the context from being built.

  • Tool descriptors are discovery hints. The world-tools edge still enforces the write floor and caller permissions.

  • The endpoint uses the standard read-rate policy.

Last updated

Was this helpful?