CAcaveman

PUT /projects/{projectId}/eval-baseline

PUT /api/v1/projects/{projectId}/eval-baseline on the Caveman Cloud control plane. Requires the eval:write scope. Exposed to autonomous agents as the set_baseline 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.

put/projects/{projectId}/eval-baseline

Request

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

Request body

workbench_idstring uuid nullable
run_idstring uuid nullable
target_keystring
gate_policy'kernel' | 'strict'

The policy the experiment's comparisons are read by when a comparison names none: kernel follows the statistics, strict fails when any criterion got worse on any case. Needs workbench_id. Sent without run_id it leaves the baseline as it is.

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.