feat(keyboard): ship AI hint carousel, home library cards, and clipboard polish

Rotate AI idle suggestions with optional remote packs, move history/dictionary onto self-sizing Home preview cards, harden clipboard capture/prompting, and simplify keyboard chrome by dropping most liquid-glass shadows.
This commit is contained in:
Rocky
2026-08-13 01:00:51 +08:00
parent fd6e0d3e7e
commit 9f308fadd2
202 changed files with 10897 additions and 5962 deletions
@@ -0,0 +1,43 @@
// FlowAck.swift
// OSGKeyboard · Shared
import Foundation
/// Keyboard delivery acknowledgement. It carries the echoed result identity,
/// generation, and revision; matching identity/revision releases that terminal result.
public struct FlowAck: Codable, Equatable, Sendable {
public enum DeliveryOutcome: String, Codable, Sendable {
case replaced
case appended
case rejected
}
public let protocolVersion: Int
public let sessionId: UUID
public let utteranceId: UUID
public let commandSeq: Int64
public let hostGeneration: String?
public let revision: Int64?
public let deliveryOutcome: DeliveryOutcome?
public let consumedAt: TimeInterval
public init(
protocolVersion: Int = 1,
sessionId: UUID,
utteranceId: UUID,
commandSeq: Int64,
hostGeneration: String? = nil,
revision: Int64? = nil,
deliveryOutcome: DeliveryOutcome? = nil,
consumedAt: TimeInterval = Date().timeIntervalSince1970
) {
self.protocolVersion = protocolVersion
self.sessionId = sessionId
self.utteranceId = utteranceId
self.commandSeq = commandSeq
self.hostGeneration = hostGeneration
self.revision = revision
self.deliveryOutcome = deliveryOutcome
self.consumedAt = consumedAt
}
}
@@ -0,0 +1,87 @@
// FlowCommand.swift
// OSGKeyboard · Shared
import Foundation
public struct FlowCommand: Codable, Equatable, Sendable {
public enum Action: String, Codable, Sendable {
case startRecording
case stopRecording
case abort
/// Light warm-up: ASR locale/assets only no mic capture.
case prewarm
/// User has touched the mic; prime capture before tap/hold resolves.
case primeAudio
/// Touch ended without an utterance adopting the primed capture.
case cancelPrimeAudio
/// Remove one temporary AI conversation from host memory.
case endAIConversation
/// AI mode: submit a prefilled question and skip ASR.
case submitAIQuestion
}
/// Wire version that includes submitAIQuestion + aiQuestionText.
public static let currentProtocolVersion = 5
public let protocolVersion: Int
public let sessionId: UUID
public let utteranceId: UUID
public let commandSeq: Int64
public let action: Action
public let localeId: String
public let createdAt: TimeInterval
public let fieldContext: FlowFieldContext?
/// Dictation (default) vs explicit edit mode. Absent on legacy v1 dictation.
public let utteranceMode: FlowUtteranceMode?
/// Verified source for explicit last-input editing.
public let editSourceText: String?
public let sourceHistoryEntryID: UUID?
public let sourceHistoryEntryRevision: Int64?
/// Host-memory conversation used only by `.aiQuestion`.
public let aiConversationID: UUID?
/// Prefilled question used only by `.submitAIQuestion`.
public let aiQuestionText: String?
/// Absolute wall-clock deadlines survive extension reconstruction.
public let startDeadlineAt: TimeInterval?
public let processingDeadlineAt: TimeInterval?
public init(
protocolVersion: Int = FlowCommand.currentProtocolVersion,
sessionId: UUID,
utteranceId: UUID,
commandSeq: Int64,
action: Action,
localeId: String,
createdAt: TimeInterval = Date().timeIntervalSince1970,
fieldContext: FlowFieldContext? = nil,
utteranceMode: FlowUtteranceMode? = nil,
editSourceText: String? = nil,
sourceHistoryEntryID: UUID? = nil,
sourceHistoryEntryRevision: Int64? = nil,
aiConversationID: UUID? = nil,
aiQuestionText: String? = nil,
startDeadlineAt: TimeInterval? = nil,
processingDeadlineAt: TimeInterval? = nil
) {
self.protocolVersion = protocolVersion
self.sessionId = sessionId
self.utteranceId = utteranceId
self.commandSeq = commandSeq
self.action = action
self.localeId = localeId
self.createdAt = createdAt
self.fieldContext = fieldContext
self.utteranceMode = utteranceMode
self.editSourceText = editSourceText
self.sourceHistoryEntryID = sourceHistoryEntryID
self.sourceHistoryEntryRevision = sourceHistoryEntryRevision
self.aiConversationID = aiConversationID
self.aiQuestionText = aiQuestionText
self.startDeadlineAt = startDeadlineAt
self.processingDeadlineAt = processingDeadlineAt
}
public var resolvedUtteranceMode: FlowUtteranceMode {
utteranceMode ?? .dictation
}
}
@@ -0,0 +1,43 @@
// FlowFieldContext.swift
// OSGKeyboard · Shared
import Foundation
public struct FlowFieldContext: Codable, Equatable, Sendable {
public let precedingText: String?
public let followingText: String?
public let keyboardType: String?
public let returnKeyType: String?
public let isSecureEntry: Bool
/// Distinguishes a known-empty field from unavailable document context.
public let isEmptyField: Bool
public let isContextAvailable: Bool
public init(
precedingText: String? = nil,
followingText: String? = nil,
keyboardType: String? = nil,
returnKeyType: String? = nil,
isSecureEntry: Bool = false,
isEmptyField: Bool = false,
isContextAvailable: Bool = false
) {
self.precedingText = isSecureEntry ? nil : precedingText
self.followingText = isSecureEntry ? nil : followingText
self.keyboardType = keyboardType
self.returnKeyType = returnKeyType
self.isSecureEntry = isSecureEntry
self.isEmptyField = isSecureEntry ? false : isEmptyField
self.isContextAvailable = isSecureEntry ? false : isContextAvailable
}
public var deliveryFingerprint: String? {
guard !isSecureEntry else { return nil }
return [
keyboardType ?? "",
returnKeyType ?? "",
precedingText.map { String($0.suffix(80)) } ?? "",
followingText.map { String($0.prefix(40)) } ?? "",
].joined(separator: "|")
}
}
@@ -0,0 +1,67 @@
// FlowReadySnapshot.swift
// OSGKeyboard · Shared
import Foundation
public struct FlowReadySnapshot: Codable, Equatable, Sendable {
public enum Reason: String, Codable, Sendable {
case ready
case noSession
case starting
case audioEngineNotLive
case waitingForAudioProof
case recording
case processing
case awaitingDelivery
case permissionMissing
case appGroupUnavailable
case hostLost
case error
}
public let protocolVersion: Int
public let sessionId: UUID?
public let ready: Bool
public let reason: Reason
public let heartbeatAt: TimeInterval
public let readyAt: TimeInterval?
public let audioProofAt: TimeInterval?
public let engineMode: String
public let localeId: String
public let busyUtteranceId: UUID?
public let sessionExpiresAt: TimeInterval?
/// Host process generation that wrote this snapshot. A snapshot whose
/// generation no longer matches `FlowSessionKeys.hostGeneration` was
/// written by a dead process and is void immediately no need to wait
/// out the heartbeat-zombie window. Optional for wire compatibility with
/// snapshots written before this field existed.
public let hostGeneration: String?
public init(
protocolVersion: Int = 1,
sessionId: UUID?,
ready: Bool,
reason: Reason,
heartbeatAt: TimeInterval = Date().timeIntervalSince1970,
readyAt: TimeInterval? = nil,
audioProofAt: TimeInterval? = nil,
engineMode: String,
localeId: String,
busyUtteranceId: UUID? = nil,
sessionExpiresAt: TimeInterval? = nil,
hostGeneration: String? = nil
) {
self.protocolVersion = protocolVersion
self.sessionId = sessionId
self.ready = ready
self.reason = reason
self.heartbeatAt = heartbeatAt
self.readyAt = readyAt
self.audioProofAt = audioProofAt
self.engineMode = engineMode
self.localeId = localeId
self.busyUtteranceId = busyUtteranceId
self.sessionExpiresAt = sessionExpiresAt
self.hostGeneration = hostGeneration
}
}
@@ -0,0 +1,88 @@
// FlowResult.swift
// OSGKeyboard · Shared
import Foundation
public struct FlowResult: Codable, Equatable, Sendable {
public enum Status: String, Codable, Sendable {
case partial
case rawReady
/// AI-mode LLM answer draft (not ASR). Non-terminal.
case streaming
case final
case error
case aborted
case timeout
}
public let protocolVersion: Int
public let sessionId: UUID
public let utteranceId: UUID
public let commandSeq: Int64
public let status: Status
public let text: String?
public let warning: String?
public let errorKind: FlowSessionKeys.TranscriptionErrorKind?
/// Raw ASR survives polish/network failure and host process churn.
public let rawText: String?
public let hostGeneration: String?
/// Monotonically increases within one session/utterance; readers may discard
/// an equal or lower non-nil revision as a stale or duplicate delivery.
public let revision: Int64?
public let fieldFingerprint: String?
public let createdAt: TimeInterval
/// Echo of the command mode so the extension can skip raw fallback.
public let utteranceMode: FlowUtteranceMode?
/// History row created by normal dictation, or edited by edit mode.
public let historyEntryID: UUID?
public let historyEntryRevision: Int64?
/// Echoed for AI result validation; absent for dictation and edit.
public let aiConversationID: UUID?
public init(
protocolVersion: Int = FlowCommand.currentProtocolVersion,
sessionId: UUID,
utteranceId: UUID,
commandSeq: Int64,
status: Status,
text: String? = nil,
warning: String? = nil,
errorKind: FlowSessionKeys.TranscriptionErrorKind? = nil,
rawText: String? = nil,
hostGeneration: String? = nil,
revision: Int64? = nil,
fieldFingerprint: String? = nil,
createdAt: TimeInterval = Date().timeIntervalSince1970,
utteranceMode: FlowUtteranceMode? = nil,
historyEntryID: UUID? = nil,
historyEntryRevision: Int64? = nil,
aiConversationID: UUID? = nil
) {
self.protocolVersion = protocolVersion
self.sessionId = sessionId
self.utteranceId = utteranceId
self.commandSeq = commandSeq
self.status = status
self.text = text
self.warning = warning
self.errorKind = errorKind
self.rawText = rawText
self.hostGeneration = hostGeneration
self.revision = revision
self.fieldFingerprint = fieldFingerprint
self.createdAt = createdAt
self.utteranceMode = utteranceMode
self.historyEntryID = historyEntryID
self.historyEntryRevision = historyEntryRevision
self.aiConversationID = aiConversationID
}
public var resolvedUtteranceMode: FlowUtteranceMode {
utteranceMode ?? .dictation
}
/// Instruction deliveries must never insert raw ASR into the field.
public var allowsRawFallback: Bool {
resolvedUtteranceMode == .dictation
}
}
@@ -0,0 +1,33 @@
// FlowStartTransaction.swift
// OSGKeyboard · Shared
import Foundation
public struct FlowStartTransaction: Codable, Equatable, Sendable {
public enum Phase: String, Codable, Sendable {
case issued
case starting
case recording
case terminal
}
public let sessionID: UUID
public let utteranceID: UUID
public let deadlineAt: TimeInterval
public let phase: Phase
public let updatedAt: TimeInterval
public init(
sessionID: UUID,
utteranceID: UUID,
deadlineAt: TimeInterval,
phase: Phase,
updatedAt: TimeInterval = Date().timeIntervalSince1970
) {
self.sessionID = sessionID
self.utteranceID = utteranceID
self.deadlineAt = deadlineAt
self.phase = phase
self.updatedAt = updatedAt
}
}
@@ -0,0 +1,14 @@
// FlowTranscriptionError.swift
// OSGKeyboard · Shared
import Foundation
public struct FlowTranscriptionError: Equatable, Sendable {
public let message: String
public let kind: FlowSessionKeys.TranscriptionErrorKind
public init(message: String, kind: FlowSessionKeys.TranscriptionErrorKind) {
self.message = message
self.kind = kind
}
}