feat: voice command mapping — context-gated approve/reject over voice

While a tool-permission gate is held on the active tab, spoken confirm phrases resolve it via the existing approve/reject WS channel — no server change (byte-shuttle intact). Everything else stays ordinary dictation. Safety: whole-utterance-exact matching + leading-negation guard + reject precedence + confidence gate (approve only) + a cancellable 1.5s confirm window whose commit re-validates gate identity/epoch/connectivity (TOCTOU guard) + stale-gate epoch bound at PTT-start. New pure modules public/voice-commands.ts and public/voice-confirm.ts at 100% coverage; wiring in voice/terminal-session/tabs/main. 1307 tests pass, typecheck clean, build:web OK. Independent code + security reviews flagged a confirm-window TOCTOU and an unwired cancel path — both fixed and covered. Plan: docs/PLAN_VOICE_COMMANDS.md.
2026-07-01 10:34:51 +02:00
parent 03612323c0
commit e4c327e25e
13 changed files with 1193 additions and 19 deletions
--- a/public/tabs.ts
+++ b/public/tabs.ts
@@ -32,6 +32,8 @@ import { mountPushToggle } from './push.js'
 import { mountQuickReply } from './quick-reply.js'
 import { mountTimeline, type TimelineHandle } from './timeline.js'
 import { createVoiceInput, type VoiceInput } from './voice.js'
+import { matchCommand, type VoiceMatchContext } from './voice-commands.js'
+import { createApproveConfirm, type ApproveConfirm } from './voice-confirm.js'

 const TABS_KEY = 'web-terminal:tabs'
 const ACTIVE_KEY = 'web-terminal:active'
@@ -42,6 +44,9 @@ const PERMISSION_MODE_KEY = 'web-terminal:permission-mode'
 *  (class `tg-stale`) once telemetry is older than this (B2). */
 const STATUSLINE_TTL_MS = 30_000

+/** VC decision C: how long the "未连接" not-connected flash stays visible. */
+const VOICE_NOT_CONNECTED_FLASH_MS = 1500
+
 /** All `--permission-mode` values (B4). 'auto' is high-risk and only offered
 *  when the server's ALLOW_AUTO_MODE allows it (SEC-M5, gated via /config/ui). */
 const ALL_PERMISSION_MODES: readonly PermissionMode[] = ['default', 'acceptEdits', 'plan', 'auto']
@@ -102,6 +107,11 @@ export class TabApp {
  private timelineBtn: HTMLButtonElement | null = null
  private voice: VoiceInput | null = null // A2: push-to-talk recognizer
  private voiceOverlay: HTMLElement | null = null // A2: interim-transcript overlay
+  // VC: context-gated confirm/reject command mapping (PLAN_VOICE_COMMANDS.md).
+  private readonly approveConfirm: ApproveConfirm = createApproveConfirm() // decision B
+  private voiceConfirmOverlay: HTMLElement | null = null // "听到：批准" / "未连接" (B, C)
+  private voicePttSession: TerminalSession | null = null // session captured at PTT-start (safeguard 5)
+  private voicePttEpoch = 0 // session.pendingEpoch captured at PTT-start (safeguard 5)

  constructor(paneHost: HTMLElement, tabBar: HTMLElement) {
    this.paneHost = paneHost
@@ -173,13 +183,23 @@ export class TabApp {
    document.body.appendChild(this.timelinePanel)
  }

-  /** A2: overlay that shows the live interim transcript while dictating. */
+  /** A2: overlay that shows the live interim transcript while dictating. VC: a
+   *  SEPARATE overlay carries "听到：批准" / "未连接" so hideInterim() (which
+   *  fires on PTT release) never clobbers it mid-confirm-window (§6). */
  private setupVoiceOverlay(): void {
    const overlay = document.createElement('div')
    overlay.id = 'voice-interim'
    overlay.style.display = 'none'
    document.body.appendChild(overlay)
    this.voiceOverlay = overlay
+
+    const confirmOverlay = document.createElement('div')
+    confirmOverlay.id = 'voice-confirm'
+    confirmOverlay.style.display = 'none'
+    // Tap-to-cancel an armed approve confirm window (§4 cancel trigger).
+    confirmOverlay.addEventListener('click', () => this.cancelArmedApprove())
+    document.body.appendChild(confirmOverlay)
+    this.voiceConfirmOverlay = confirmOverlay
  }

  /** B4: fetch the server UI config (allowAutoMode). Best-effort, never throws. */
@@ -351,11 +371,17 @@ export class TabApp {

  private startVoice(): void {
    if (!this.voice) {
-      this.voice = createVoiceInput((text) => this.sendToActive(text), {
-        onInterim: (t) => this.showInterim(t),
-      })
+      this.voice = createVoiceInput(
+        (text, confidence) => this.handleVoiceTranscript(text, confidence),
+        { onInterim: (t) => this.showInterim(t) },
+      )
    }
    if (!this.voice) return // SpeechRecognition unsupported — no-op (AC-A2.3)
+    // VC safeguard 5: bind this utterance to the CURRENTLY active session/epoch
+    // so a slow transcript can't approve a newer gate or a different tab.
+    const active = this.tabs[this.activeIndex]?.session ?? null
+    this.voicePttSession = active
+    this.voicePttEpoch = active?.pendingEpoch ?? 0
    this.showInterim('')
    this.voice.start()
  }
@@ -375,6 +401,102 @@ export class TabApp {
    if (this.voiceOverlay) this.voiceOverlay.style.display = 'none'
  }

+  /**
+   * VC — dispatch a final voice transcript (PLAN_VOICE_COMMANDS.md §6):
+   * context-gated confirm/reject resolve the held permission via the existing
+   * approve()/reject() WS channel; everything else (including a stale gate or
+   * a tab switch mid-utterance) falls through to ordinary dictation, byte-for-
+   * byte unchanged. Raw bytes are NEVER synthesized for approve/reject.
+   */
+  private handleVoiceTranscript(text: string, confidence?: number): void {
+    // A NEW utterance supersedes any pending approve confirm window: the user
+    // has spoken again, so never let a stale timer commit behind a fresh
+    // command (this is the "say another word" cancel trigger, §4). Combined
+    // with tap-to-cancel and the commit-time re-check below, it closes the
+    // TOCTOU race where a delayed approve could resolve a different gate.
+    this.cancelArmedApprove()
+
+    const session = this.tabs[this.activeIndex]?.session
+    if (!session) {
+      this.sendToActive(text)
+      return
+    }
+    const ctx: VoiceMatchContext = {
+      pendingApproval: session.pendingApproval,
+      gate: session.pendingGate,
+      confidence,
+    }
+    const action = matchCommand(text, ctx)
+    // Stale-gate guard: a command can only resolve the SAME session+gate it
+    // was spoken against; anything else (tab switch, a new pending flip) is
+    // downgraded to plain dictation rather than silently dropped.
+    const stale = session !== this.voicePttSession || session.pendingEpoch !== this.voicePttEpoch
+    if (action !== 'text' && stale) {
+      this.sendToActive(text)
+      return
+    }
+    if (action === 'reject') {
+      if (!this.isVoiceConnected(session)) return this.flashVoiceStatus('未连接', VOICE_NOT_CONNECTED_FLASH_MS)
+      session.reject()
+      this.updateApprovalBar()
+      return
+    }
+    if (action === 'approve') {
+      if (!this.isVoiceConnected(session)) return this.flashVoiceStatus('未连接', VOICE_NOT_CONNECTED_FLASH_MS)
+      // Decision B: arm a cancellable window instead of committing immediately.
+      // The commit RE-VALIDATES the gate identity (TOCTOU fix): if the held
+      // permission resolved and a NEW gate was raised during the ~1.5s window
+      // (pendingEpoch bumps), or the tab/WS changed, drop the approve — never
+      // silently approve a different, unseen/unheard gate.
+      const armedSession = session
+      const armedEpoch = session.pendingEpoch
+      this.approveConfirm.arm(
+        () => this.flashVoiceStatus('听到：批准（点此取消）'),
+        () => {
+          this.hideVoiceStatus()
+          const fresh =
+            armedSession.pendingApproval &&
+            armedSession.pendingGate === 'tool' &&
+            armedSession.pendingEpoch === armedEpoch &&
+            this.isVoiceConnected(armedSession)
+          if (!fresh) return // gate changed / WS dropped during the window → drop
+          armedSession.approve()
+          this.updateApprovalBar()
+        },
+      )
+      return
+    }
+    this.sendToActive(text) // UNCHANGED dictation path
+  }
+
+  /** Cancel a still-armed approve confirm window and clear its overlay. Invoked
+   *  on a new utterance, a reject, and a tap on the overlay (§4 cancel triggers). */
+  private cancelArmedApprove(): void {
+    if (!this.approveConfirm.isArmed()) return
+    this.approveConfirm.cancel()
+    this.hideVoiceStatus()
+  }
+
+  /** Decision C: approve()/reject() are silently dropped by sendMsg when the WS
+   *  isn't open — flash feedback instead of a silent no-op. */
+  private isVoiceConnected(session: TerminalSession): boolean {
+    return session.status === 'connected'
+  }
+
+  /** Transient voice-status text ("听到：批准" / "未连接") on a DIFFERENT overlay
+   *  than the interim transcript, so hideInterim() (PTT release) never clears
+   *  it mid-confirm-window. XSS-safe: textContent only. */
+  private flashVoiceStatus(text: string, autoHideMs?: number): void {
+    if (!this.voiceConfirmOverlay) return
+    this.voiceConfirmOverlay.textContent = text
+    this.voiceConfirmOverlay.style.display = 'block'
+    if (autoHideMs !== undefined) setTimeout(() => this.hideVoiceStatus(), autoHideMs)
+  }
+
+  private hideVoiceStatus(): void {
+    if (this.voiceConfirmOverlay) this.voiceConfirmOverlay.style.display = 'none'
+  }
+
  /** Toggle the activity-timeline panel for the active session (A4). */
  private toggleTimeline(): void {
    this.timelineOpen = !this.timelineOpen