feat(语音日记): DiaryQuickSheet 接入语音输入(录音→整理→回退原话)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
link2026
2026-06-10 06:24:49 +08:00
parent b7e8ab33ec
commit 8c8599e77d

View File

@@ -37,6 +37,24 @@ struct DiaryQuickSheet: View {
@State private var detent: PresentationDetent = .large
@FocusState private var contentFocused: Bool
// MARK: (spec 2026-06-10-voice-diary)
enum VoicePhase: Equatable { case idle, recording, organizing }
@State private var voicePhase: VoicePhase = .idle
@State private var liveTranscript = ""
@State private var recordingSeconds = 0
/// 稿,退;
@State private var rawTranscript: String?
/// 稿,
/// () pill
@State private var organizedAppended: String?
/// ( / ),
@State private var voiceNote: String?
@State private var voiceDeniedAlert = false
@State private var voiceFlowTask: Task<Void, Never>?
@State private var recordingWatchdog: Task<Void, Never>?
private let dictation = SpeechDictationService()
private var hasContent: Bool {
!content.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty
}
@@ -45,7 +63,7 @@ struct DiaryQuickSheet: View {
if case .loading = phase { return true }
return false
}
private var canRequestSuggest: Bool { hasContent && !isLoading }
private var canRequestSuggest: Bool { hasContent && !isLoading && voicePhase == .idle }
private var canSubmit: Bool { hasContent }
var body: some View {
@@ -77,7 +95,29 @@ struct DiaryQuickSheet: View {
ScrollView(showsIndicators: false) {
VStack(alignment: .leading, spacing: 16) {
VStack(alignment: .leading, spacing: 8) {
sectionLabel(String(appLoc: "内容"))
HStack {
sectionLabel(String(appLoc: "内容"))
Spacer()
if SpeechDictationService.isAvailable, voicePhase == .idle {
Button(action: startVoice) {
HStack(spacing: 4) {
Image(systemName: "mic.fill")
.font(.tjScaled(11, weight: .semibold))
Text("说一段")
.font(.tjScaled(12, weight: .semibold))
}
.foregroundStyle(isLoading ? Tj.Palette.text3 : Tj.Palette.brick)
.padding(.horizontal, 10)
.padding(.vertical, 5)
.background(Capsule().strokeBorder(
isLoading ? Tj.Palette.line : Tj.Palette.brick.opacity(0.5),
lineWidth: 1))
.contentShape(Capsule())
}
.buttonStyle(.plain)
.disabled(isLoading) // AI AIRuntime
}
}
TextField("今天身体怎么样?吃了什么药、有什么感觉?",
text: $content, axis: .vertical)
.lineLimit(3...8)
@@ -93,6 +133,48 @@ struct DiaryQuickSheet: View {
RoundedRectangle(cornerRadius: Tj.Radius.sm, style: .continuous)
.strokeBorder(Tj.Palette.line, lineWidth: 1)
)
if voicePhase != .idle {
DiaryVoicePanel(
mode: voicePhase == .organizing
? .organizing
: .recording(elapsedSeconds: recordingSeconds),
transcript: liveTranscript,
onStop: stopVoiceAndOrganize,
onCancelOrganize: cancelOrganize
)
}
if let note = voiceNote {
HStack(spacing: 6) {
Image(systemName: "info.circle")
.font(.tjScaled(11))
.foregroundStyle(Tj.Palette.text3)
Text(note)
.font(.tjScaled(11))
.foregroundStyle(Tj.Palette.text3)
Spacer(minLength: 0)
}
}
if let organized = organizedAppended,
rawTranscript != nil,
content.range(of: organized) != nil {
Button(action: revertToRawTranscript) {
HStack(spacing: 4) {
Image(systemName: "arrow.uturn.backward")
.font(.tjScaled(10, weight: .semibold))
Text("改用原话")
.font(.tjScaled(11, weight: .semibold))
}
.foregroundStyle(Tj.Palette.ink)
.padding(.horizontal, 10)
.padding(.vertical, 5)
.background(Capsule().strokeBorder(Tj.Palette.line, lineWidth: 1))
.contentShape(Capsule())
}
.buttonStyle(.plain)
}
}
assistSection
@@ -143,7 +225,22 @@ struct DiaryQuickSheet: View {
.presentationDragIndicator(.hidden)
.presentationBackground(Tj.Palette.sand)
.presentationCornerRadius(Tj.Radius.xl)
.onDisappear { suggestTask?.cancel() }
.onDisappear {
suggestTask?.cancel()
voiceFlowTask?.cancel()
recordingWatchdog?.cancel()
dictation.abort()
}
.alert(String(appLoc: "需要麦克风与语音识别权限"), isPresented: $voiceDeniedAlert) {
Button(String(appLoc: "前往设置")) {
if let url = URL(string: UIApplication.openSettingsURLString) {
UIApplication.shared.open(url)
}
}
Button(String(appLoc: "取消"), role: .cancel) {}
} message: {
Text("语音记录全程在本机完成,声音和文字都不会上传。请在设置中允许麦克风和语音识别。")
}
}
// MARK: - AI
@@ -455,6 +552,95 @@ struct DiaryQuickSheet: View {
.foregroundStyle(Tj.Palette.text2)
}
// MARK:
private func startVoice() {
contentFocused = false
voiceNote = nil
voiceFlowTask = Task { @MainActor in
guard await dictation.requestAuthorization() else {
voiceDeniedAlert = true
return
}
do {
liveTranscript = ""
recordingSeconds = 0
try dictation.start { partial in liveTranscript = partial }
withAnimation(.snappy(duration: 0.2)) { voicePhase = .recording }
// + 3 (,)
recordingWatchdog = Task { @MainActor in
while !Task.isCancelled {
try? await Task.sleep(nanoseconds: 1_000_000_000)
guard !Task.isCancelled, voicePhase == .recording else { return }
recordingSeconds += 1
if recordingSeconds >= DiaryVoicePanel.maxRecordingSeconds {
stopVoiceAndOrganize()
return
}
}
}
} catch {
voiceNote = error.localizedDescription
voicePhase = .idle
}
}
}
private func stopVoiceAndOrganize() {
guard voicePhase == .recording else { return }
recordingWatchdog?.cancel()
voiceFlowTask = Task { @MainActor in
let transcript = (await dictation.stop())
.trimmingCharacters(in: .whitespacesAndNewlines)
liveTranscript = transcript
guard !transcript.isEmpty else {
withAnimation(.snappy(duration: 0.2)) { voicePhase = .idle }
voiceNote = String(appLoc: "没听清,再试一次")
return
}
rawTranscript = transcript
withAnimation(.snappy(duration: 0.2)) { voicePhase = .organizing }
do {
let result = try await DiaryAssistService.shared.organize(transcript: transcript)
guard !Task.isCancelled else { return }
appendToContent(result.text)
organizedAppended = result.text
lastRate = result.decodeRate
} catch is CancellationError {
// cancelOrganize 退,
} catch {
guard !Task.isCancelled else { return }
appendToContent(transcript) // 线 #5:退,
organizedAppended = nil
voiceNote = String(appLoc: "AI 整理失败,已填入原话")
}
withAnimation(.snappy(duration: 0.2)) { voicePhase = .idle }
}
}
/// : LLM,(退)
private func cancelOrganize() {
guard voicePhase == .organizing else { return }
voiceFlowTask?.cancel()
if let raw = rawTranscript {
appendToContent(raw)
organizedAppended = nil
voiceNote = String(appLoc: "已取消整理,填入原话")
}
withAnimation(.snappy(duration: 0.2)) { voicePhase = .idle }
}
/// :稿稿(spec §2:LLM )
private func revertToRawTranscript() {
guard let raw = rawTranscript,
let organized = organizedAppended,
let range = content.range(of: organized, options: .backwards) else { return }
withAnimation(.snappy(duration: 0.18)) {
content = content.replacingCharacters(in: range, with: raw)
organizedAppended = nil
}
}
/// AI (coveredDims) LLM,
/// ,
private func requestSuggestions() {