> ## Documentation Index
> Fetch the complete documentation index at: https://docs.reflections.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> The OpenAPI document at /api-reference/openapi.yaml defines the target contract. Its x-reflections-availability field and each operation's availability notice identify supported test and live forms. Do not infer implementation from a schema or code sample. Live keys support account details, reads of the licenses the calling account holds as licensee or issued as talent (GET /v1/licenses?role=issuer), and GET /v1/generations?license=… for the state of outputs under such a license (summaries only: no prompt, reference, bytes or metadata). Live image checks, submissions and receipts are built but not activated: until activation, a live POST /v1/checks or /v1/generations returns 403 live_not_activated, which must not be retried. Discovery and JWKS are at the origin root (https://app.reflections.ai/.well-known/...), not under /v1.
> Three rules hold everywhere: a decision is never an error (deny and escalate are 200 responses, and a live check still evaluating is a 202 with status checking); generate nothing for a named talent without an allow; deliver nothing until the generation is allow.
> The sandbox accepts personal rk_test_ keys. Persist a separate Idempotency-Key and body for each logical /v1 POST; retry an unknown outcome with the same key and body. OAuth and Talent API MCP remain planned.

# Planned operations

> The rest of the Talent API contract under the Talent License Protocol: operations, webhooks, sessions and the MCP server that are not served yet.

These pages complete the Talent API contract for the [Talent License Protocol](https://docs.reflections.ai/standard/overview.md),
so implementers can read the whole protocol in one place. They are **not served yet**, in test or
live mode. Each page is marked **Planned**, and its playground does not send requests.

The operations you can call today are in the [API reference](https://docs.reflections.ai/api-reference/introduction.md).
[Sandbox](https://docs.reflections.ai/sandbox.md#availability) lists them with their limits.

| Area | What it adds |
| - | - |
| Licensed material | Download the material a license covers |
| License requests, drafts, suspension and resumption | Ask for a license, draft one for a talent to sign, and pause or resume one |
| Connections and OAuth | A platform acting for a licensee, and clients acting for a person |
| Files | Upload media for checks, generations and verification |
| Sessions and the session stream | Decisions during live voice and video generation |
| Revocations | Create revocations and acknowledge them |
| Usage records and statements | Report usage and settle statements |
| Mandates and escalations | The queue a talent's representative works from |
| Webhook endpoints, events and webhooks | Signed notifications of every change |
| MCP server | The protocol as tools for agents |
| Test helpers | Sign, accept and revoke licenses in test mode |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.