From ebac3ef9d133f2fe280597ab13fa8af8d6e5ead1 Mon Sep 17 00:00:00 2001
From: Claude <noreply@anthropic.com>
Date: Sat, 3 Oct 2026 14:26:54 +0000
Subject: [PATCH] fix(media): disclose the transcription server before
 dictation uses it

Dictation falls back to the owner's transcription server when the voice
provider cannot transcribe, so that server is a voice recipient too: it is
listed for voice use (as "Transcription (<origin>)") whenever it would take
the recording, and not when the voice provider transcribes itself.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MRtGG9ARfqqhma3t85Ro2u
---
 apps/api/src/ai-consent.test.ts     | 21 +++++++++++++++++++++
 apps/api/src/ai-consent.ts          | 16 ++++++++++++++++
 packages/adapters/src/ai-consent.ts |  3 ++-
 3 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/apps/api/src/ai-consent.test.ts b/apps/api/src/ai-consent.test.ts
index 38f0a02..e76c3e7 100644
--- a/apps/api/src/ai-consent.test.ts
+++ b/apps/api/src/ai-consent.test.ts
@@ -157,6 +157,27 @@ describe("consent grants", () => {
     expect(JSON.stringify(status)).not.toContain("comfy-key");
     expect((await aiConsentStatus(deps, actor, { uses: ["voice"] })).recipients).toHaveLength(1);
   });
+  it("discloses the transcription server for dictation when the voice provider cannot transcribe", async () => {
+    const { deps, actor } = setup();
+    vi.mocked(deps.prisma.integrationProviderConfig.findUnique).mockResolvedValue({
+      id: "media",
+      ciphertext: "fake-media-ciphertext-voice",
+    } as never);
+    deps.secrets = {
+      load: vi.fn(() =>
+        JSON.stringify({ comfyui: null, transcription: { baseUrl: "http://127.0.0.1:8080/v1" } }),
+      ),
+    } as unknown as RouterDeps["secrets"];
+    vi.mocked(deps.prisma.spaceVoicePreference.findFirst).mockResolvedValue({
+      credential: { provider: "kokoro" },
+      voiceId: "af_heart",
+    } as never);
+    const status = await aiConsentStatus(deps, actor, { uses: ["voice"] });
+    expect(status.recipients.map((recipient) => [recipient.name, recipient.use])).toEqual([
+      ["Local voice", "voice"],
+      ["Transcription (http://127.0.0.1:8080)", "voice"],
+    ]);
+  });
   it("returns an operator policy without requiring a hosted provider", async () => {
     const { deps, actor } = setup();
     deps.env.privacyPolicyUrl = "https://example.com/privacy";
diff --git a/apps/api/src/ai-consent.ts b/apps/api/src/ai-consent.ts
index 076eff7..e10c905 100644
--- a/apps/api/src/ai-consent.ts
+++ b/apps/api/src/ai-consent.ts
@@ -9,6 +9,7 @@ import {
   parseModelSecret,
   selectConfiguredModel,
   toStringRecord,
+  voiceCatalogEntry,
 } from "@rakazo/adapters";
 import type { Actor, AiConsentQuery, AiConsentStatus, AiRecipient } from "@rakazo/contracts";
 import { AI_DATA_DISCLOSURES, AI_DISCLOSURE_VERSION, AI_PRIVACY_URL } from "@rakazo/contracts";
@@ -186,6 +187,21 @@ export async function aiConsentStatus(
   }
   for (const voice of voices)
     add(aiRecipient({ provider: voice.credential.provider, use: "voice" }));
+  if (uses.includes("voice")) {
+    // Dictation goes to the owner's transcription server when the voice provider cannot transcribe.
+    const transcription = (await loadMediaSettings(deps)).transcription;
+    const credential = transcription ? await findDefaultVoiceCredential(deps.prisma, actor) : null;
+    if (transcription && !(credential && voiceCatalogEntry(credential.provider)?.transcribe)) {
+      add(
+        aiRecipient({
+          provider: MEDIA_TRANSCRIPTION_PROVIDER_ID,
+          use: "voice",
+          baseUrl: transcription.baseUrl,
+          modelId: transcription.model,
+        }),
+      );
+    }
+  }
   if (includesMemory) {
     if (memoryOwner) {
       const memory = await deps.prisma.spaceMemoryConfig.findUnique({
diff --git a/packages/adapters/src/ai-consent.ts b/packages/adapters/src/ai-consent.ts
index d633f84..437ee1c 100644
--- a/packages/adapters/src/ai-consent.ts
+++ b/packages/adapters/src/ai-consent.ts
@@ -52,6 +52,8 @@ export function aiRecipient(input: {
 }
 
 function recipientName(provider: string, use: AiDataUse) {
+  // The transcription server also takes dictation, so it keeps its name for voice use.
+  if (provider === MEDIA_TRANSCRIPTION_PROVIDER_ID) return "Transcription";
   if (use === "voice") return voiceCatalogEntry(provider)?.name ?? provider;
   if (use === "memory") {
     if (provider === "supermemory") return "Supermemory";
@@ -61,6 +63,5 @@ function recipientName(provider: string, use: AiDataUse) {
   }
   if (provider === "cursor") return "Cursor";
   if (provider === MEDIA_COMFYUI_PROVIDER_ID) return "ComfyUI";
-  if (provider === MEDIA_TRANSCRIPTION_PROVIDER_ID) return "Transcription";
   return listPiCatalog().find((entry) => entry.provider === provider)?.providerName ?? provider;
 }