Documentation Index
Fetch the complete documentation index at: https://docs.trulayer.ai/llms.txt
Use this file to discover all available pages before exploring further.
Control Loop v0.1 adds two new configuration fields (max_cascade_depth on policies and prompt_autoship_enabled on projects) and three new fields on evaluation responses (context, source_action_id, original_evaluation_id). This page explains what each default means for your existing setup and what, if anything, you need to change.
New fields and their defaults
prompt_autoship_enabled on projects
Default: false
Every existing and new project has prompt_autoship_enabled set to false unless you explicitly enable it. This means all ab_passed prompt deployments wait for an owner to approve them manually before going live. Nothing ships to production automatically until you opt in.
Action required: None, unless you want auto-ship. To enable it on a project, set prompt_autoship_enabled: true via PATCH /v1/projects/{id} or in Dashboard → Projects → [project] → Settings.
max_retry_depth on policies
Default: 3
max_retry_depth shipped in the 2026-04-30 release. If you have existing policies with action_type: retry, each one already has max_retry_depth: 3 — meaning after three retries on a single trace, the next attempt is auto-converted to an escalate action and routed to the HITL queue.
If you want more or fewer automatic retries before escalation, update the value on each policy via PATCH /v1/policies/{id} or in Dashboard → Control → Policies. Valid range: 1–10.
New evaluation fields
Three new optional fields appear on evaluation response objects (GET /v1/eval, GET /v1/eval/{id}) as of Control Loop v0.1:
| Field | Type | Default | Meaning |
|---|
context | "fresh" | "remediation" | "fresh" | Whether this eval scored a newly-ingested trace or a remediated re-run after a control action. |
source_action_id | string (uuid) | null | null | The control action that triggered this eval (only set when context = "remediation"). |
original_evaluation_id | string (uuid) | null | null | The baseline eval the regression detector compares against (only set when context = "remediation"). |
context: "fresh" and both FK fields as null. If your code reads evaluation responses, ensure your JSON deserialiser tolerates unknown or null fields (it should already, per the API versioning policy).
New prompt deployment endpoints
Five new endpoints are available under /v1/prompts/deployments:
| Method | Path |
|---|
GET | /v1/prompts/deployments |
GET | /v1/prompts/deployments/{id} |
POST | /v1/prompts/deployments/{id}/approve |
POST | /v1/prompts/deployments/{id}/reject |
POST | /v1/prompts/deployments/{id}/rollback |
Regression detection
Evaluations triggered by a control action’s remediated trace now carry context: "remediation". When the remediation eval’s score drops below the original eval’s score (the baseline stored in original_evaluation_id), TruLayer emits a RemediationRegression failure detection event. This is a new alert type — existing failure rules and webhooks are unaffected unless you add a new rule that matches on it.
Action required: None unless you want to surface regression alerts in your own tooling. If you use webhooks or the GET /v1/failures/clusters endpoint, regression events will appear automatically once the feature is active.
Summary checklist
| Change | Default | Action needed? |
|---|
prompt_autoship_enabled on projects | false (HITL approval required) | No, unless you want auto-ship |
max_retry_depth on policies | 3 (already set) | Only if you want a different limit |
context, source_action_id, original_evaluation_id on evals | Additive, null-safe | No — ensure your deserialiser tolerates extra fields |
| Prompt deployment endpoints | New, additive, dashboard-only | No action for SDK-only integrations |
RemediationRegression failure type | New, additive | No, unless you want to filter on it |
