Merge branch 'feature/intelligent-polish-and-personal-dict' into main
Resolved real conflicts introduced by translation-polish-2 (#3) and docs refresh (#4) being merged to main during development: - OSGKeyboardShared/Models/ProviderConfig.swift Add polishIntensity field alongside translationTargetLocaleId / polishScenarioId / handednessPreference. Both new fields coexist. - OSGKeyboardShared/Services/AppGroupStore.swift Keep main's translation setters; add polishIntensity setter, detectedAppContext setter, and personalDictionary getter/setter. - OSGKeyboardShared/Services/PolishingService.swift Merge v0.2.1 translate-and-polish path with v0.3.0 context-aware intelligent prompt. New polish() entry point accepts both modes; translation mode still uses TranslationPrompt, polish mode now uses buildPrompt(for:context:). - OSGKeyboard/Views/SettingsView.swift Compose localEngineSettingsSection (main) with polishIntensitySection, languageAndModelsSection, systemPromptLinkSection, personalDictionaryLinkSection (feature). - OSGKeyboardShared/{en,zh-Hans}.lproj/Shared.strings Concat scenario keys + polish intensity / app context / dictionary keys. Auto-merged without conflict: - AppGroupStore new methods (localASRBackend, etc.) - FlowSessionManager, KeyboardViewController (auto-merged) - MaterialIcon, HistoryView (auto-merged, my icons added on top) Co-authored-by: Mavis <Mavis@hkgood.dev>
This commit is contained in:
Mavis
@@ -0,0 +1,56 @@
|
||||
// AppContext.swift
|
||||
// OSGKeyboard · Shared
|
||||
//
|
||||
// Coarse classification of "where is the user typing right now?".
|
||||
// We use it to pick a tone / style guideline for the LLM polish
|
||||
// step (e.g. code stays technical, chat stays casual).
|
||||
//
|
||||
// The detection is best-effort and runs entirely in the keyboard
|
||||
// extension — iOS sandboxing blocks us from reading the foreground
|
||||
// app's bundle ID, so we infer from text-content heuristics plus
|
||||
// a 30-minute cache and a few environmental signals. See
|
||||
// `AppContextDetector` for the actual algorithm.
|
||||
|
||||
import Foundation
|
||||
|
||||
public enum AppContext: String, Codable, Sendable, CaseIterable {
|
||||
/// IDE / code editor / terminal.
|
||||
case code
|
||||
/// Mail composer (long form, formal-ish).
|
||||
case email
|
||||
/// IM / chat (short lines, casual).
|
||||
case chat
|
||||
/// Notes / long-form document.
|
||||
case document
|
||||
/// Anything we cannot classify confidently.
|
||||
case unknown
|
||||
|
||||
/// User-facing label for the Settings view's preview banner.
|
||||
public var labelKey: String {
|
||||
switch self {
|
||||
case .code: return "appContext.code"
|
||||
case .email: return "appContext.email"
|
||||
case .chat: return "appContext.chat"
|
||||
case .document: return "appContext.document"
|
||||
case .unknown: return "appContext.unknown"
|
||||
}
|
||||
}
|
||||
|
||||
/// Tone / style constraint appended to the LLM prompt. Kept
|
||||
/// intentionally short — the LLM does better with 1-2 sharp
|
||||
/// instructions than a wall of rules.
|
||||
public var polishGuideline: String {
|
||||
switch self {
|
||||
case .code:
|
||||
return "Code context: preserve English identifiers, variable names, file paths, and indentation-relevant whitespace exactly. Do not natural-language them. Keep code snippets unformatted; do not wrap in code fences."
|
||||
case .email:
|
||||
return "Email context: you may add a polite greeting or sign-off if the user clearly forgot one. Reasonable paragraph breaks. Keep tone professional but not stiff."
|
||||
case .chat:
|
||||
return "Chat context: keep it short, conversational, and emoji-friendly. Drop formalities. Preserve the speaker's casual voice."
|
||||
case .document:
|
||||
return "Document context: add structure — split into paragraphs, use lists when the user enumerates. Keep tone written-formal. Do not invent headings the user did not say."
|
||||
case .unknown:
|
||||
return "Unknown context: pick a neutral, friendly tone. Err on the side of minimal changes."
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,131 @@
|
||||
// PersonalDictionary.swift
|
||||
// OSGKeyboard · Shared
|
||||
//
|
||||
// User-curated list of terms the LLM must never rewrite. Persisted
|
||||
// in the App Group (JSON-encoded) so both the main app's Settings
|
||||
// UI and the keyboard extension's LLM call read the same data.
|
||||
//
|
||||
// Sources (mutually exclusive per entry):
|
||||
// - `.manual` user typed it in by hand
|
||||
// - `.history` auto-extracted from the user's transcription
|
||||
// history by `DictionaryLearner`
|
||||
// - `.contacts` imported from the iOS Contacts framework
|
||||
// - `.recentEdit` extracted from edits the user made to a
|
||||
// polished transcript before sending
|
||||
//
|
||||
// The dictionary is intentionally read-mostly: writes only happen
|
||||
// from the main app (or from a low-frequency background task). The
|
||||
// keyboard extension never writes to it.
|
||||
|
||||
import Foundation
|
||||
|
||||
public struct PersonalDictionary: Codable, Sendable, Equatable {
|
||||
public var entries: [Entry]
|
||||
public var version: Int
|
||||
|
||||
public init(entries: [Entry] = [], version: 1) {
|
||||
self.entries = entries
|
||||
self.version = version
|
||||
}
|
||||
|
||||
public struct Entry: Codable, Sendable, Equatable, Identifiable {
|
||||
public let id: UUID
|
||||
public var term: String
|
||||
public var aliases: [String]
|
||||
public var category: Category
|
||||
public var source: Source
|
||||
public var createdAt: Date
|
||||
public var usageCount: Int
|
||||
|
||||
public init(
|
||||
id: UUID = UUID(),
|
||||
term: String,
|
||||
aliases: [String] = [],
|
||||
category: Category,
|
||||
source: Source,
|
||||
createdAt: Date = Date(),
|
||||
usageCount: Int = 0
|
||||
) {
|
||||
self.id = id
|
||||
self.term = term
|
||||
self.aliases = aliases
|
||||
self.category = category
|
||||
self.source = source
|
||||
self.createdAt = createdAt
|
||||
self.usageCount = usageCount
|
||||
}
|
||||
|
||||
public enum Category: String, Codable, Sendable, CaseIterable {
|
||||
/// Person / place / brand / organization.
|
||||
case properNoun
|
||||
/// API, framework, library, language, file format.
|
||||
case technical
|
||||
/// Initialism like LLM, iOS, ML.
|
||||
case acronym
|
||||
/// Product name (Typeless, OSGKeyboard, ChatGPT).
|
||||
case productName
|
||||
/// Anything that does not fit the above.
|
||||
case custom
|
||||
|
||||
public var labelKey: String {
|
||||
switch self {
|
||||
case .properNoun: return "dict.category.properNoun"
|
||||
case .technical: return "dict.category.technical"
|
||||
case .acronym: return "dict.category.acronym"
|
||||
case .productName: return "dict.category.productName"
|
||||
case .custom: return "dict.category.custom"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
public enum Source: String, Codable, Sendable, CaseIterable {
|
||||
case manual
|
||||
case history
|
||||
case contacts
|
||||
case recentEdit
|
||||
|
||||
public var labelKey: String {
|
||||
switch self {
|
||||
case .manual: return "dict.source.manual"
|
||||
case .history: return "dict.source.history"
|
||||
case .contacts: return "dict.source.contacts"
|
||||
case .recentEdit: return "dict.source.recentEdit"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Renders the entry for the LLM prompt. Includes aliases
|
||||
/// in parentheses so the LLM recognizes voice variants
|
||||
/// ("k8s" → "Kubernetes") without renaming.
|
||||
public func promptFragment() -> String {
|
||||
if aliases.isEmpty { return term }
|
||||
return "\(term)（\(aliases.joined(separator: " / "))）"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
extension PersonalDictionary {
|
||||
public static let empty = PersonalDictionary()
|
||||
|
||||
/// Renders the entire dictionary as a prompt fragment. Entries
|
||||
/// are grouped by category so the LLM can scan quickly. Empty
|
||||
/// dictionary returns "" so the caller can blindly concatenate.
|
||||
public func promptFragment() -> String {
|
||||
guard !entries.isEmpty else { return "" }
|
||||
let grouped = Dictionary(grouping: entries, by: { $0.category })
|
||||
var lines: [String] = []
|
||||
for category in Entry.Category.allCases {
|
||||
guard let bucket = grouped[category], !bucket.isEmpty else { continue }
|
||||
let terms = bucket
|
||||
.sorted { $0.usageCount > $1.usageCount }
|
||||
.map { $0.promptFragment() }
|
||||
.joined(separator: "、")
|
||||
lines.append("【\(category.rawValue)】\(terms)")
|
||||
}
|
||||
guard !lines.isEmpty else { return "" }
|
||||
return (
|
||||
"以下为用户专有词汇，**必须**原样保留，**绝不**改写或翻译：" +
|
||||
"\n" + lines.joined(separator: "\n")
|
||||
)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,51 @@
|
||||
// PolishContext.swift
|
||||
// OSGKeyboard · Shared
|
||||
//
|
||||
// Bag of inputs the LLM polish service needs. Caller assembles it
|
||||
// before calling `IntelligentPolishingService.polish(_:context:)`.
|
||||
// Splitting it out keeps the polish service's signature stable as
|
||||
// we add more signals (app context, intensity, personal dictionary,
|
||||
// preceding text, etc.) over time.
|
||||
|
||||
import Foundation
|
||||
|
||||
public struct PolishContext: Sendable {
|
||||
/// Coarse classification of the input field. When `.unknown` the
|
||||
/// LLM is told to pick a neutral tone on its own.
|
||||
public let appContext: AppContext
|
||||
|
||||
/// User-configured intensity. Drives how aggressively the LLM
|
||||
/// is allowed to rewrite.
|
||||
public let intensity: PolishIntensity
|
||||
|
||||
/// Optional preceding text (e.g. a few hundred characters of
|
||||
/// what the user already typed before the recording). The LLM
|
||||
/// uses it to resolve "this / 那个 / 刚才" references and to
|
||||
/// bias terminology choices.
|
||||
public let precedingText: String?
|
||||
|
||||
/// Cap on how many characters of `precedingText` we actually
|
||||
/// include in the prompt. The full preceding text is often
|
||||
/// hundreds of KB in a long note — we only need the tail.
|
||||
public let maxPrecedingChars: Int
|
||||
|
||||
public init(
|
||||
appContext: AppContext = .unknown,
|
||||
intensity: PolishIntensity = .default,
|
||||
precedingText: String? = nil,
|
||||
maxPrecedingChars: Int = 500
|
||||
) {
|
||||
self.appContext = appContext
|
||||
self.intensity = intensity
|
||||
self.precedingText = precedingText
|
||||
self.maxPrecedingChars = maxPrecedingChars
|
||||
}
|
||||
|
||||
/// Truncated view of `precedingText` ready for prompt injection.
|
||||
/// Returns `nil` when there is nothing meaningful to add.
|
||||
public var precedingForPrompt: String? {
|
||||
guard let raw = precedingText, !raw.isEmpty else { return nil }
|
||||
if raw.count <= maxPrecedingChars { return raw }
|
||||
return String(raw.suffix(maxPrecedingChars))
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,76 @@
|
||||
// PolishIntensity.swift
|
||||
// OSGKeyboard · Shared
|
||||
//
|
||||
// How aggressively the LLM should rewrite the ASR transcript.
|
||||
//
|
||||
// Persisted in `AppGroupStore` via `ProviderConfig` so the keyboard
|
||||
// extension can honour the chosen intensity during live dictation.
|
||||
|
||||
import Foundation
|
||||
|
||||
public enum PolishIntensity: String, Codable, Sendable, CaseIterable {
|
||||
/// Engine is in pure ASR mode (local + cloud-polish-off). The LLM
|
||||
/// is never called; the raw transcript is inserted as-is. This
|
||||
/// value is mostly a UI default — the actual behaviour is
|
||||
/// determined by `engineMode` + `localModeCloudPolishEnabled`.
|
||||
case off
|
||||
|
||||
/// Drop only isolated filler words (嗯 / 呃 / 那个 / 就是 / 然后)
|
||||
/// and obvious duplicated fragments. Everything else stays.
|
||||
case light
|
||||
|
||||
/// Correction + light polish: drop fillers, fix homophone errors,
|
||||
/// adjust obviously-broken word order, add punctuation. Preserves
|
||||
/// the speaker's voice and intent.
|
||||
case medium
|
||||
|
||||
/// Full structural rewrite: split long sentences, auto-number
|
||||
/// enumerated items, format as paragraphs / lists. Use for
|
||||
/// meeting notes, weekly reports, blog drafts.
|
||||
case heavy
|
||||
|
||||
/// User-facing label key for the Settings picker. Localized
|
||||
/// through `SharedL10n` so the same key works in the main app
|
||||
/// and the keyboard extension.
|
||||
public var labelKey: String {
|
||||
switch self {
|
||||
case .off: return "polish.intensity.off"
|
||||
case .light: return "polish.intensity.light"
|
||||
case .medium: return "polish.intensity.medium"
|
||||
case .heavy: return "polish.intensity.heavy"
|
||||
}
|
||||
}
|
||||
|
||||
/// Short description shown under the picker. Same localization
|
||||
/// story as `labelKey`.
|
||||
public var descriptionKey: String {
|
||||
switch self {
|
||||
case .off: return "polish.intensity.off.desc"
|
||||
case .light: return "polish.intensity.light.desc"
|
||||
case .medium: return "polish.intensity.medium.desc"
|
||||
case .heavy: return "polish.intensity.heavy.desc"
|
||||
}
|
||||
}
|
||||
|
||||
/// Inline guideline injected into the LLM prompt. The polish
|
||||
/// service appends this verbatim so the LLM has an explicit,
|
||||
/// non-ambiguous constraint per call.
|
||||
public var promptGuideline: String {
|
||||
switch self {
|
||||
case .off:
|
||||
return "Do not change the input at all. Output the original text verbatim."
|
||||
case .light:
|
||||
return "Only remove isolated filler words (嗯, 呃, 那个, 就是, 然后, 对, ok) and obvious duplicated fragments. Do not change any other words, word order, or punctuation."
|
||||
case .medium:
|
||||
return "Correct obvious speech-recognition errors (homophones, missing/extra characters). Remove filler words and duplicated fragments. Adjust obviously-broken word order. Add punctuation. Do not restructure sentences, invent facts, or change the speaker's voice."
|
||||
case .heavy:
|
||||
return "Apply medium corrections, then optionally restructure: split long sentences, auto-number enumerated items into markdown lists, group related ideas into paragraphs. Preserve every fact, number, and proper noun."
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
extension PolishIntensity {
|
||||
/// Default for new installs. `medium` is what Typeless and Wispr
|
||||
/// Flow also use as their first-run default.
|
||||
public static let `default`: PolishIntensity = .medium
|
||||
}
|
||||
@@ -53,6 +53,8 @@ public final class ProviderConfig: ObservableObject, @unchecked Sendable {
|
||||
static let translationTargetLocaleId = "config.translationTargetLocaleId"
|
||||
static let polishScenarioId = "config.polishScenarioId"
|
||||
static let handednessPreference = "config.handednessPreference"
|
||||
// v0.3.0: how aggressively the LLM should rewrite transcripts.
|
||||
static let polishIntensity = "config.polishIntensity"
|
||||
}
|
||||
|
||||
@Published public var providerId: String {
|
||||
@@ -201,6 +203,14 @@ public final class ProviderConfig: ObservableObject, @unchecked Sendable {
|
||||
PolishScenarioCatalog.isCustom(polishScenarioId)
|
||||
}
|
||||
|
||||
/// v0.3.0: how aggressively the LLM should rewrite the ASR
|
||||
/// transcript. Default is `medium` (Typeless-equivalent). The
|
||||
/// `off` value never calls the LLM — equivalent to "transcribe
|
||||
/// only" regardless of `engineMode`.
|
||||
@Published public var polishIntensity: PolishIntensity {
|
||||
didSet { defaults.set(polishIntensity.rawValue, forKey: Key.polishIntensity) }
|
||||
}
|
||||
|
||||
public var isConfigured: Bool {
|
||||
// Local engine (on-device ASR only) doesn't need an API key,
|
||||
// base URL, or model — the LLM round-trip is skipped entirely.
|
||||
@@ -311,6 +321,15 @@ public final class ProviderConfig: ObservableObject, @unchecked Sendable {
|
||||
self.handednessPreference = HandednessPreference.fromStored(
|
||||
resolvedDefaults.string(forKey: Key.handednessPreference)
|
||||
)
|
||||
// v0.3.0: polish intensity. Default to `.medium` for new
|
||||
// installs and upgrades; the existing `off` / `light` /
|
||||
// `heavy` values are honored.
|
||||
if let raw = resolvedDefaults.string(forKey: Key.polishIntensity),
|
||||
let intensity = PolishIntensity(rawValue: raw) {
|
||||
self.polishIntensity = intensity
|
||||
} else {
|
||||
self.polishIntensity = .default
|
||||
}
|
||||
|
||||
// Cloud no longer exposes off/transcribe; migrate legacy values.
|
||||
if self.engineMode == "cloud", self.modeId != "polish" {
|
||||
|
||||
Reference in New Issue
Block a user