Documentation menu
Reference
API reference
Docs · markdown

API reference

The complete, always-current surface is machine-readable:

  • /openapi.json — every endpoint, request and response shapes
  • /llms.txt — one-line orientation for agents
  • /agents.md — operating instructions and the default loop
  • /agent-setup/prompt.md — required harness install, then the onboarding runbook in execution order
  • /onboard.md — backwards-compatible alias of the agent-setup prompt
  • /skill.md — the loop procedure as an installable skill

The endpoints you'll actually touch

EndpointAuthWhat
POST /v1/provisionnone / own keyIdempotent project + keys (agents prefer this)
POST /v1/signupnoneDeprecated non-idempotent alias of provision (same terms)
POST /v1/recoverrecovery codeRotate lost keys
POST /v1/traces · POST /v1/logs · POST /v1/metricsproducer keyOTLP ingest, all three pillars (JSON or protobuf)
POST /v1/feedback · /v1/feedback/audiofeedback keyTyped / spoken user feedback
GET /v1/ingest/healthany project keySetup status: last accepted / last rejected + reason
GET /v1/telemetryagent keyBounded record window; resolve ids from packets
POST /v1/runs/diagnoseagent keyThe improvement packet over HTTP
POST /v1/observations/open · /closeagent keyClaim the window, then admit cited Issues with recommendations
POST /v1/issues/decideagent keyRecord an attributed Issue disposition; actor is self-reported on this key-only lane
GET /v1/observationsagent keyThe observation ledger (open and decided)
POST /v1/runs/replay · GET ?replay_id=agent keyProve a prompt/model fix against captured failures pre-ship
POST /v1/runs/eval-specagent keyExecutable eval spec your coding agent runs against real code
POST /v1/evalsproducer or agent keyRecord eval results — failed evals cluster like production failures
GET /v1/loops · GET /v1/loops/<run_id>agent keyLoop history: runs, stages, verification
POST /v1/loops/eventsagent keyRecord grounded progress; verification outcomes are server-owned
POST /v1/runs/verifyagent keyWindow-over-window verification
GET/POST /v1/scoringagent keySession-scorecard weights (reason required to change)
GET/POST /v1/redactionagent keyData-scrubbing config (reason required)
POST /v1/projects/<id>/archiveagent keyStop ingest, downgrade keys — confirm with the project id

Schemas: /schema/handoff-packet.json · /schema/improvement-packet.json

Everything here is also reachable as MCP tools from a connected agent — same operations, same bounds, plus the loop's state machine.