TTS: gate auto audio on inbound voice notes (#1667)

Co-authored-by: Sebastian <sebslight@gmail.com>

src/config/config.legacy-config-detection.accepts-imessage-dmpolicy.test.ts

@@ -138,6 +138,16 @@ describe("legacy config detection", () => {
     expect(res.config?.channels?.telegram?.groups?.["*"]?.requireMention).toBe(false);
     expect(res.config?.channels?.telegram?.requireMention).toBeUndefined();
   });
+  it("migrates messages.tts.enabled to messages.tts.auto", async () => {
+    vi.resetModules();
+    const { migrateLegacyConfig } = await import("./config.js");
+    const res = migrateLegacyConfig({
+      messages: { tts: { enabled: true } },
+    });
+    expect(res.changes).toContain("Moved messages.tts.enabled → messages.tts.auto (always).");
+    expect(res.config?.messages?.tts?.auto).toBe("always");
+    expect(res.config?.messages?.tts?.enabled).toBeUndefined();
+  });
   it("migrates legacy model config to agent.models + model lists", async () => {
     vi.resetModules();
     const { migrateLegacyConfig } = await import("./config.js");

src/config/legacy.migrations.part-3.ts

@@ -40,6 +40,26 @@ export const LEGACY_CONFIG_MIGRATIONS_PART_3: LegacyConfigMigration[] = [
       delete tools.bash;
     },
   },
+  {
+    id: "messages.tts.enabled->auto",
+    describe: "Move messages.tts.enabled to messages.tts.auto",
+    apply: (raw, changes) => {
+      const messages = getRecord(raw.messages);
+      const tts = getRecord(messages?.tts);
+      if (!tts) return;
+      if (tts.auto !== undefined) {
+        if ("enabled" in tts) {
+          delete tts.enabled;
+          changes.push("Removed messages.tts.enabled (messages.tts.auto already set).");
+        }
+        return;
+      }
+      if (typeof tts.enabled !== "boolean") return;
+      tts.auto = tts.enabled ? "always" : "off";
+      delete tts.enabled;
+      changes.push(`Moved messages.tts.enabled → messages.tts.auto (${String(tts.auto)}).`);
+    },
+  },
   {
     id: "agent.defaults-v2",
     describe: "Move agent config to agents.defaults and tools",

src/config/legacy.rules.ts

@@ -120,6 +120,10 @@ export const LEGACY_CONFIG_RULES: LegacyConfigRule[] = [
     message:
       "agent.imageModelFallbacks was replaced by agents.defaults.imageModel.fallbacks (auto-migrated on load).",
   },
+  {
+    path: ["messages", "tts", "enabled"],
+    message: "messages.tts.enabled was replaced by messages.tts.auto (auto-migrated on load).",
+  },
   {
     path: ["gateway", "token"],
     message: "gateway.token is ignored; use gateway.auth.token instead (auto-migrated on load).",

src/config/sessions/types.ts

@@ -4,6 +4,7 @@ import type { Skill } from "@mariozechner/pi-coding-agent";
 import type { NormalizedChatType } from "../../channels/chat-type.js";
 import type { ChannelId } from "../../channels/plugins/types.js";
 import type { DeliveryContext } from "../../utils/delivery-context.js";
+import type { TtsAutoMode } from "../types.tts.js";
 
 export type SessionScope = "per-sender" | "global";
 
@@ -42,6 +43,7 @@ export type SessionEntry = {
   verboseLevel?: string;
   reasoningLevel?: string;
   elevatedLevel?: string;
+  ttsAuto?: TtsAutoMode;
   execHost?: string;
   execSecurity?: string;
   execAsk?: string;

src/config/types.tts.ts

@@ -2,6 +2,8 @@ export type TtsProvider = "elevenlabs" | "openai" | "edge";
 
 export type TtsMode = "final" | "all";
 
+export type TtsAutoMode = "off" | "always" | "inbound" | "tagged";
+
 export type TtsModelOverrideConfig = {
   /** Enable model-provided overrides for TTS. */
   enabled?: boolean;
@@ -22,7 +24,9 @@ export type TtsModelOverrideConfig = {
 };
 
 export type TtsConfig = {
-  /** Enable auto-TTS (can be overridden by local prefs). */
+  /** Auto-TTS mode (preferred). */
+  auto?: TtsAutoMode;
+  /** Legacy: enable auto-TTS when `auto` is not set. */
   enabled?: boolean;
   /** Apply TTS to final replies only or to all replies (tool/block/final). */
   mode?: TtsMode;

src/config/zod-schema.core.ts

@@ -158,8 +158,10 @@ export const MarkdownConfigSchema = z
 
 export const TtsProviderSchema = z.enum(["elevenlabs", "openai", "edge"]);
 export const TtsModeSchema = z.enum(["final", "all"]);
+export const TtsAutoSchema = z.enum(["off", "always", "inbound", "tagged"]);
 export const TtsConfigSchema = z
   .object({
+    auto: TtsAutoSchema.optional(),
     enabled: z.boolean().optional(),
     mode: TtsModeSchema.optional(),
     provider: TtsProviderSchema.optional(),