GET /projects/{projectId}/eval-workbenches/{workbenchId}/runs/compare
GET /api/v1/projects/{projectId}/eval-workbenches/{workbenchId}/runs/compare on the Caveman Cloud control plane. Requires any one of the scopes payload:read, trace:read_metadata. Exposed to autonomous agents as the compare_runs action of the caveman_evals tool (read access). Versioned datasets, reusable evaluators, workbench documents, strict suites, and evaluation evidence.
get/projects/{projectId}/eval-workbenches/{workbenchId}/runs/compare
Request
- Base URLhttps://api.caveman.so/api/v1
- URLhttps://api.caveman.so/api/v1/projects/{projectId}/eval-workbenches/{workbenchId}/runs/compare
- Auth
- OAuth 2Authorization code: /api/v1/oauth/authorizeToken URL: /api/v1/oauth/token scopes: payload:read, trace:read_metadata
- or HTTP bearer
- or API key in cookie cave_access
- or API key in cookie __Secure-cave_identity.session_token
Query parameters
baseline_run_idstring uuid
candidate_run_idstring uuid required
policy'kernel' | 'strict'
Response
Successful response. Exact status depends on synchronous or durable delivery outcome.
Changes
No recorded changes to this operation across all 1 revision of this API.