// AZ-660 / AZ-661 — vendored copy of the `../detections` gRPC contract.
//
// The authoritative schema lives in the `../detections` repository
// (per `_docs/02_document/architecture.md §10`). This vendored copy
// is kept in lock-step with that schema via the `schema_version`
// field on `DetectionResponse`: any breaking schema change MUST
// bump the version, and the client (built against the version pinned
// in `DetectionClientConfig::expected_schema_version`) MUST emit a
// hard `schema_mismatch` error if the server reports a different
// version. The schema version is the explicit handshake that lets
// the autopilot run alongside an evolving detection service without
// silently downcasting unknown response shapes.
//
// Wire shape (one bi-directional stream per session):
//   client ─► FrameRequest stream ────► server (../detections)
//   client ◄── DetectionResponse stream ◄── server
//
// `FrameRequest` carries the encoded pixel buffer and the source
// frame's monotonic timestamp; the response correlates back via
// `frame_seq`. Frames with `ai_locked = true` upstream are filtered
// by the client and never sent — the server therefore never sees a
// FrameRequest for an AI-locked frame.

syntax = "proto3";

package azaion.detection.v1;

service DetectionService {
  // One bi-directional stream per client session. The server may
  // close the stream at any time; the client reconnects with
  // bounded backoff (`DetectionClientConfig::reconnect_*`).
  rpc Stream(stream FrameRequest) returns (stream DetectionResponse);
}

// Pixel formats mirrored from `shared::models::frame::PixelFormat`.
// Encoded as a proto enum so the wire is self-describing.
enum PixelFormat {
  PIXEL_FORMAT_UNSPECIFIED = 0;
  PIXEL_FORMAT_NV12 = 1;
  PIXEL_FORMAT_YUV420P = 2;
  PIXEL_FORMAT_RGB24 = 3;
}

// One inference request per frame. The client tracks `frame_seq`
// for response correlation (the response carries the same value
// in `frame_seq`).
message FrameRequest {
  uint64 frame_seq = 1;
  // Capture timestamp (monotonic, ns) — used by the client to
  // compute per-frame round-trip latency from the response.
  uint64 capture_ts_monotonic_ns = 2;
  uint32 width = 3;
  uint32 height = 4;
  PixelFormat pix_fmt = 5;
  bytes pixels = 6;
}

// Bounding box in [0,1] normalized coordinates (mirrors
// `shared::models::frame::BoundingBox`).
message BoundingBox {
  float x_min = 1;
  float y_min = 2;
  float x_max = 3;
  float y_max = 4;
}

// One detection inside a `DetectionResponse`.
message Detection {
  uint32 class_id = 1;
  string class_name = 2;
  float confidence = 3;
  BoundingBox bbox_normalized = 4;
  optional bytes mask_or_polyline = 5;
  uint64 source_frame_seq = 6;
}

// Server-streamed response. `schema_version` is the handshake the
// client validates against `expected_schema_version`; any mismatch
// is a hard `schema_mismatch` error and the response is rejected.
// `model_version` may change at runtime when the inference model
// is hot-swapped — the client emits a `ModelVersionChanged` event
// on the first response with a new version.
message DetectionResponse {
  uint32 schema_version = 1;
  string model_version = 2;
  uint64 frame_seq = 3;
  // Server-side processing latency for THIS frame, in milliseconds.
  // The client also computes its own round-trip latency from
  // `capture_ts_monotonic_ns` so it can detect transport latency
  // independently of server-internal latency.
  uint32 latency_ms = 4;
  repeated Detection detections = 5;
}