feat: add vocabulary-aware Transcriber and shared correction/result types

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

Sources/SstCore/Models.swift

@@ -24,6 +24,63 @@ public protocol AudioRecording {
 
 public protocol Transcriber {
     func transcribe(_ samples: [Float]) async throws -> String
+    /// Biases decoding towards `vocabulary`. Engines without bias support ignore the list.
+    func transcribe(_ samples: [Float], vocabulary: [String]) async throws -> String
+}
+
+public extension Transcriber {
+    func transcribe(_ samples: [Float], vocabulary: [String]) async throws -> String {
+        try await transcribe(samples)
+    }
+}
+
+/// One replacement made by the dictionary correction pass.
+/// `start`/`length` are UTF-16 offsets into the corrected text.
+public struct AppliedCorrection: Equatable, Codable, Sendable {
+    public var heard: String
+    public var wrote: String
+    public var rule: String
+    public var start: Int
+    public var length: Int
+
+    public init(heard: String, wrote: String, rule: String, start: Int, length: Int) {
+        self.heard = heard
+        self.wrote = wrote
+        self.rule = rule
+        self.start = start
+        self.length = length
+    }
+}
+
+public struct CorrectionResult: Equatable, Sendable {
+    public var text: String
+    public var corrections: [AppliedCorrection]
+
+    public init(text: String, corrections: [AppliedCorrection]) {
+        self.text = text
+        self.corrections = corrections
+    }
+}
+
+public protocol TextCorrecting {
+    func correct(_ text: String) -> CorrectionResult
+}
+
+/// A finished dictation, emitted just before the text is inserted.
+public struct DictationResult: Equatable, Sendable {
+    public var date: Date
+    public var duration: TimeInterval
+    public var rawText: String
+    public var finalText: String
+    public var corrections: [AppliedCorrection]
+
+    public init(date: Date, duration: TimeInterval, rawText: String, finalText: String, corrections: [AppliedCorrection]) {
+        self.date = date
+        self.duration = duration
+        self.rawText = rawText
+        self.finalText = finalText
+        self.corrections = corrections
+    }
 }
 
 public protocol Cleaner {

Tests/SstCoreTests/TranscriberVocabularyTests.swift

@@ -0,0 +1,21 @@
+import Foundation
+import Testing
+@testable import SstCore
+
+private struct PlainTranscriber: Transcriber {
+    func transcribe(_ samples: [Float]) async throws -> String { "plain \(samples.count)" }
+}
+
+struct TranscriberVocabularyTests {
+    @Test func vocabularyVariantFallsBackToPlainTranscribe() async throws {
+        let result = try await PlainTranscriber().transcribe([0, 0, 0], vocabulary: ["Anthropic"])
+        #expect(result == "plain 3")
+    }
+
+    @Test func appliedCorrectionRoundTripsThroughJSON() throws {
+        let original = AppliedCorrection(heard: "cloud code", wrote: "Claude Code", rule: "cloud code", start: 12, length: 11)
+        let data = try JSONEncoder().encode(original)
+        let decoded = try JSONDecoder().decode(AppliedCorrection.self, from: data)
+        #expect(decoded == original)
+    }
+}