Grant Gilliam
863136aeec
Phase 2 (call detection): CallDetector using CoreAudio per-process mic attribution (anarlog technique) — robust start+stop for Zoom/Teams/Signal/Meet, ignoring our own recording; auto-record toggle. Built; pending live multi-app confirmation by the user. Phase 3 (visual timeline foundation): AppAdapter protocol + SpeakerObservation, TimelineBuilder (hysteresis/overlap/self-merge/aliases), VisualTimeline (schema 1.1), TextRecognizer (Vision OCR), FrameSampler + GridCallAnalyzer (name OCR + saturated-highlight active-speaker attribution), SignalAdapter, VisualObserver (window capture; frames released, never saved; minimized->visual_gap, idle != gap). Synthetic-frame tested; adapter geometry pending real Signal fixtures + live VisualObserver validation. Phase 5 (backend hand-off): SparkControlClient (multipart label-merge, sequential, TLS-skip, 503 Retry-After/413), SessionPackager (chunk plan + WAV slice + timeline slice/rebase), TranscriptAssembler + SpeakersFile, TranscriptPipeline. Validated END-TO-END against the live backend (chunk -> label-merge -> speakers.json). Phase 6 (voiceprints): VoiceprintStore (known_voiceprints, persist named fingerprints, skip Unknown). Wired: 'Send to backend' button + transcript status, auto-send toggle (default off) + self-name setting. All adversarial-review findings fixed. App + XCTest suite build; tests pass.
73 lines
2.2 KiB
Swift
73 lines
2.2 KiB
Swift
import Foundation
|
|
|
|
/// `visual_timeline.json` (schema 1.1) — the app's primary visual output. Times
|
|
/// are seconds relative to session t0. Segments may overlap (crosstalk).
|
|
struct VisualTimeline: Codable {
|
|
var schemaVersion = "1.1"
|
|
let sessionId: String
|
|
let app: String
|
|
let adapterVersion: String
|
|
let t0Unix: Double
|
|
let durationSec: Double
|
|
let fpsSampled: Int
|
|
let selfName: String?
|
|
let participants: [Participant]
|
|
let segments: [Segment]
|
|
let visualGaps: [Gap]
|
|
|
|
struct Participant: Codable {
|
|
let name: String
|
|
let isSelf: Bool?
|
|
let aliases: [String]?
|
|
enum CodingKeys: String, CodingKey {
|
|
case name
|
|
case isSelf = "is_self"
|
|
case aliases
|
|
}
|
|
}
|
|
|
|
struct Segment: Codable, Equatable {
|
|
let start: Double
|
|
let end: Double
|
|
let name: String
|
|
let confidence: Double
|
|
let source: String // vision | accessibility | fused | mic_vad
|
|
}
|
|
|
|
struct Gap: Codable, Equatable {
|
|
let start: Double
|
|
let end: Double
|
|
let reason: String // minimized | tab_switched
|
|
}
|
|
|
|
enum CodingKeys: String, CodingKey {
|
|
case schemaVersion = "schema_version"
|
|
case sessionId = "session_id"
|
|
case app
|
|
case adapterVersion = "adapter_version"
|
|
case t0Unix = "t0_unix"
|
|
case durationSec = "duration_sec"
|
|
case fpsSampled = "fps_sampled"
|
|
case selfName = "self_name"
|
|
case participants
|
|
case segments
|
|
case visualGaps = "visual_gaps"
|
|
}
|
|
|
|
/// Write the rich `visual_timeline.json`.
|
|
func write(to url: URL) throws {
|
|
let encoder = JSONEncoder()
|
|
encoder.outputFormatting = [.prettyPrinted, .sortedKeys]
|
|
try encoder.encode(self).write(to: url)
|
|
}
|
|
|
|
/// The flat array `label-merge` wants: `[{start,end,name,confidence}]`,
|
|
/// dropping `source`. Slice/rebase to chunk-local seconds happens in Phase 5.
|
|
func flatTimelineData() throws -> Data {
|
|
let flat = segments.map { seg -> [String: Any] in
|
|
["start": seg.start, "end": seg.end, "name": seg.name, "confidence": seg.confidence]
|
|
}
|
|
return try JSONSerialization.data(withJSONObject: flat, options: [])
|
|
}
|
|
}
|