---
title: "PUT /projects/{projectId}/scenario-suites/{suiteId}"
method: PUT
path: "/projects/{projectId}/scenario-suites/{suiteId}"
---

# PUT /projects/{projectId}/scenario-suites/{suiteId}

`PUT /projects/{projectId}/scenario-suites/{suiteId}`

## Request

- Base URL: `https://api.caveman.so/api/v1`
- URL: `https://api.caveman.so/api/v1/projects/{projectId}/scenario-suites/{suiteId}`
- Auth: one of:
  - OAuth 2
    - Authorization code: `/api/v1/oauth/authorize`
    - Token URL: `/api/v1/oauth/token` scopes: `eval:write`
  - HTTP bearer
  - API key in cookie `cave_access`
  - API key in cookie `__Secure-cave_identity.session_token`

PUT /api/v1/projects/{projectId}/scenario-suites/{suiteId} on the Caveman Cloud control plane. Requires the eval:write scope. Exposed to autonomous agents as the put_scenario_projects_projectid_scenario_suites_suiteid action of the caveman_evals_write tool (write access). Author versioned datasets, reusable evaluators and workbenches; create strict suites, ingest evidence, and run baselines. Evidence ingest supports dry_run — always dry-run first. Ask Caveman to draft quality criteria again within the drafting allowance, propose a criterion for a person to turn on, and hold the pull request that adds the Caveman check to CI. Track a criterion on a slice of traces in one step: from an agent it lands proposed, and a person turns it on. Queue units for review and label them (an agent's label is recorded as an agent's, never as human gold), and make a dataset from recorded traffic.

## Request body

- object
  - `revision` integer, required
  - `name` string, required
  - `document` object, required
    - `schema_version` unknown, required
    - `cases` object[], required
      - `id` string, required
      - `name` string, required
      - `situation` string, required
      - `persona` string
      - `source` 'operator' | 'trace' | 'synthetic' | 'regression', required
      - `source_id` string
      - `split` 'optimization' | 'holdout', required
      - `script` string[], nullable, required
      - `fixtures` unknown, required
      - `fixture_version` string, required
      - `criteria` object[], required
        - `id` string, required
        - `description` string, required
        - `kind` 'tool_result' | 'fixture_state' | 'llm', required
        - `tool` string
        - `path` string
        - `equals` unknown
    - `variants` object[], required
      - `id` string, required
      - `name` string, required
      - `connection_id` string, uuid, required
      - `agent_version` string, required
      - `policy_version` string, required
      - `parameters` object, nullable
    - `mode` 'frozen' | 'adaptive', required
    - `trials` integer, required
    - `max_turns` integer, required
    - `timeout_seconds` integer, required
    - `budget_micros` integer, required
    - `call_budget_micros` integer, required
    - `simulator` object
      - `provider` string, required
      - `model` string, required
      - `version` string, required
    - `judge` object
      - `provider` string, required
      - `model` string, required
      - `version` string, required
    - `seed` integer

## Response `200`

Tenant-scoped simulation evidence

- ScenarioSuite
  - `id` string, required
  - `name` string, required
  - `revision` integer, required
  - `document` ScenarioDocument, required
    - `schema_version` unknown, required
    - `cases` object[], required
      - `id` string, required
      - `name` string, required
      - `situation` string, required
      - `persona` string
      - `source` 'operator' | 'trace' | 'synthetic' | 'regression', required
      - `source_id` string
      - `split` 'optimization' | 'holdout', required
      - `script` string[], required
      - `fixtures` unknown, required
      - `fixture_version` string, required
      - `criteria` object[], required
        - `id` string, required
        - `description` string, required
        - `kind` 'tool_result' | 'fixture_state' | 'llm', required
        - `tool` string
        - `path` string
        - `equals` unknown
    - `variants` object[], required
      - `id` string, required
      - `name` string, required
      - `connection_id` string, uuid, required
      - `agent_version` string, required
      - `policy_version` string, required
      - `parameters` object
    - `mode` 'frozen' | 'adaptive', required
    - `trials` integer, required
    - `max_turns` integer, required
    - `timeout_seconds` integer, required
    - `budget_micros` integer, required
    - `call_budget_micros` integer, required
    - `simulator` object
      - `provider` string, required
      - `model` string, required
      - `version` string, required
    - `judge` object
      - `provider` string, required
      - `model` string, required
      - `version` string, required
    - `seed` integer
  - `updated_at` string, date-time, required

## Other responses

- `400`: Structured failure. `error.code` is stable; `error.request_id` is echoed in the x-cave-request-id header.
- `403`: Structured failure. `error.code` is stable; `error.request_id` is echoed in the x-cave-request-id header.
- `409`: Structured failure. `error.code` is stable; `error.request_id` is echoed in the x-cave-request-id header.
- `422`: Structured failure. `error.code` is stable; `error.request_id` is echoed in the x-cave-request-id header.
- `4XX`: Structured failure. `error.code` is stable; `error.request_id` is echoed in the x-cave-request-id header.
- `5XX`: Structured failure. `error.code` is stable; `error.request_id` is echoed in the x-cave-request-id header.

---

[API](https://skmtc.dev/caveman/apis/caveman-cloud-api.md) - [All operations](https://skmtc.dev/caveman/apis/caveman-cloud-api/llms.txt) - [OpenAPI document](https://skmtc.dev/caveman/apis/caveman-cloud-api/revisions/508312d01cfc?raw)