> ## Documentation Index > Fetch the complete documentation index at: https://docs.reilabs.org/llms.txt > Use this file to discover all available pages before exploring further. # HTTP and request contracts > Authenticate, address state, choose a route, and check request and response contracts. Use the same authenticated HTTP client across Adapt-1 workflows. The task determines the request body and the state it can change. ## Base URL and key ```text API base theme={null} https://rei-neuroadapt-api.reilabs.org/api/v1 ``` ```http Required headers theme={null} Authorization: Bearer Content-Type: application/json ``` Set `ADAPT1_API_KEY` in a server-side environment or secret store. Do not send it to browser clients, include it in prompts, or commit it with examples. The [quickstart](/docs/neuroadapt/quickstart) includes cURL, Python, and server-side JavaScript requests. Append route suffixes such as `/domains` or `/memory/query` to the versioned base. Address system routes such as `/version` from the host root. ## Identity and task scope | Identifier | What it controls | | ------------------------- | ------------------------------------------------------------- | | Bearer token | The authenticated owner and effective hosted session identity | | `domain_id` | A task contract and its scoped evidence and learned state | | Body `session_id` | A compatibility placeholder on routes that require it | | Episode or interaction ID | An application-defined sequence or interaction boundary | Use `"session_id": "ignored"` where a request requires the field. The hosted service derives the effective session from the bearer token. Changing the placeholder does not isolate State-gateway records. Use a fresh `domain_id` for an independent tutorial run. Keep the same Domain when reconnecting to compatible retained task state. Do not clear an existing Domain as an implicit setup step. ## Match the request to the operation | Application operation | Route relative to the API base | Request content | | --------------------------- | ------------------------------------ | -------------------------------------------------------------------- | | Create a task scope | `POST /domains` | Domain ID and the task declaration | | Submit an observation | `POST /domains/{domain_id}/events` | Event type and the observed values | | Request a current result | `POST /domains/{domain_id}/query` | Question, applicable context, and requested result fields | | Return a measured outcome | `POST /domains/{domain_id}/feedback` | Outcome and the binding to the executed decision or relevant context | | Inspect supporting evidence | `POST /domains/{domain_id}/explain` | The documented explanation request | | Query continuing evidence | `POST /memory/query` | `session_id`, `user_message`, and optional retrieval controls | Use configuration fragments within the complete request shape documented for the route. Keep application-only settings, trace IDs, executor timing, and private evaluation fields in the application record unless the route explicitly accepts them. ## Schema coverage The checked-in [OpenAPI snapshot](/neuroadapt-openapi.json) has the coverage gaps listed below. Validate guide-documented fields against the deployment used by your integration. | Surface | Documentation to use | | ------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | State query, correction, batch storage, and state-summary requests | The corresponding typed schemas and endpoint definitions in the OpenAPI snapshot | | Domain learning and Discovery configuration | The relevant Domain guide and its exact configuration example; the snapshot's Domain-create definition omits `learning` | | Domain query context and learning controls | The relevant workflow guide; the snapshot's query definition does not enumerate all documented context and learning controls | | Decision-bound or context-bound feedback | [Feedback guide](/docs/neuroadapt/make-behavior-improve-from-feedback); the snapshot omits documented fields such as `decision_id`, `relation`, `policy`, and `feedback_kind` | | Numeric trajectory configuration | [Machina configuration](/docs/machina/configuration); trajectory routes are not included in this OpenAPI snapshot | Before deployment, test the selected route with the documented learning settings. If the service rejects a field, preserve the validation error and resolve the contract mismatch before continuing. Record the source of each client model and which requests have passed deployment tests. Generate models only from confirmed field definitions. ## Read controls For the documented Domain prediction workflow, the read request uses: ```json Read controls ยท request fragment theme={null} { "update_memory_state": false, "allow_exploration": false } ``` `update_memory_state` controls the documented read-time state updates; `allow_exploration` controls exploration. During frozen evaluation, exclude event and feedback writes and verify the applicable learner-state identity or versions when exposed. Configure trajectory workflows with their documented operation controls. ## Validate the response Check the HTTP status and decode the JSON response. Validate the fields your application needs before consuming the result. For event ingestion, inspect learner eligibility. For a transition prediction, require `transition_prediction.status == "predicted"` before using predicted values. For feedback, inspect `credit_assignment.contextual_learning_applied` and the relevant sample count. Treat missing admission diagnostics as unverified learning. Preserve sanitized request bodies, response bodies, Domain IDs, admission reasons, and the operation actually executed. Exclude credentials. Treat stored observations and traces as potentially sensitive application data. ## Timeouts and retries Use a finite timeout. A timed-out write may have reached the service, so the examples leave mutation retries to the application's reconciliation logic. Rely on idempotency only when the route documents that guarantee. For an ambiguous write, stop the ordered loop, inspect the relevant state, and reconcile the request before submitting it again. See [errors and reliability](/docs/neuroadapt/errors-and-reliability) and [operations and retries](/docs/neuroadapt/operational-behavior-and-retries). Send a read-only request in your preferred language. Follow a complete observation-to-prediction example.