From 11c36210934af6bec94c1beb3d92e5bbe0dc9c29 Mon Sep 17 00:00:00 2001
From: javis-bot <claude@tkrmagid.kr>
Date: Tue, 23 Jun 2026 03:27:33 +0900
Subject: [PATCH] fix: make container TTS engine env-driven so melo isn't
 overridden by piper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

docker/jarvis-config.template.json hardcoded "tts_engine": "piper". entrypoint
renders it into /app/config/jarvis.json, and bridge _tts_engine_setting() reads
that JSON BEFORE the env — so TTS_ENGINE=melo in .env was ignored and the bot
synthesised Korean with the English Piper voice (the "foreign accent" the user
heard); the warm melo-worker sat unused.

Template now carries ${TTS_ENGINE}; compose sets TTS_ENGINE=${TTS_ENGINE:-melo}
so envsubst renders the real engine. Verified: envsubst with TTS_ENGINE=melo
yields "tts_engine": "melo", and `docker compose config` passes TTS_ENGINE=melo.
Added a regression test that the template stays env-driven and renders the
configured engine.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---
 docker-compose.yml                 |  5 +++++
 docker/jarvis-config.template.json |  2 +-
 tests/test_tts_engine_config.py    | 35 ++++++++++++++++++++++++++++++
 3 files changed, 41 insertions(+), 1 deletion(-)
 create mode 100644 tests/test_tts_engine_config.py

diff --git a/docker-compose.yml b/docker-compose.yml
index 9f63909..3875900 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -66,6 +66,11 @@ services:
       WHISPER_MODEL: ${WHISPER_MODEL:-medium}
       WHISPER_DEVICE: ${WHISPER_DEVICE:-cuda}
       WHISPER_COMPUTE_TYPE: ${WHISPER_COMPUTE_TYPE:-float16}
+      # TTS engine. Rendered into /app/config/jarvis.json via envsubst (the
+      # bridge reads that JSON BEFORE the env, so it must carry the real engine,
+      # not the template's old hardcoded "piper" — otherwise Korean text is read
+      # by the English Piper voice). Default melo; .env can override.
+      TTS_ENGINE: ${TTS_ENGINE:-melo}
       # MeloTTS on the GPU (cu128 torch baked by docker/setup-melo.sh). CPU synth
       # serialised under load and pushed TTS to 7-8s; GPU does ~0.3s/sentence.
       MELO_DEVICE: ${MELO_DEVICE:-cuda}
diff --git a/docker/jarvis-config.template.json b/docker/jarvis-config.template.json
index a83fec0..dde5c3c 100644
--- a/docker/jarvis-config.template.json
+++ b/docker/jarvis-config.template.json
@@ -6,7 +6,7 @@
   "ollama_chat_model": "${OLLAMA_CHAT_MODEL}",
   "intent_judge_model": "${OLLAMA_INTENT_MODEL}",
   "tts_enabled": true,
-  "tts_engine": "piper",
+  "tts_engine": "${TTS_ENGINE}",
   "tts_piper_model_path": "${TTS_PIPER_MODEL_PATH}",
   "whisper_model": "${WHISPER_MODEL}",
   "whisper_backend": "faster-whisper",
diff --git a/tests/test_tts_engine_config.py b/tests/test_tts_engine_config.py
new file mode 100644
index 0000000..bb247e7
--- /dev/null
+++ b/tests/test_tts_engine_config.py
@@ -0,0 +1,35 @@
+"""The container's TTS engine must be env-driven, not hardcoded.
+
+Regression for a bug where docker/jarvis-config.template.json hardcoded
+`"tts_engine": "piper"`. The bridge reads the rendered /app/config/jarvis.json
+*before* the environment, so a hardcoded "piper" overrode `TTS_ENGINE=melo` in
+.env and the bot read Korean text with the English Piper voice ("foreign
+accent"). The template must carry `${TTS_ENGINE}` so envsubst (entrypoint.sh)
+renders whatever engine the deployment configured.
+"""
+
+import json
+import string
+from pathlib import Path
+
+TEMPLATE = Path(__file__).resolve().parent.parent / "docker" / "jarvis-config.template.json"
+
+
+def _render(**env) -> dict:
+    """Mimic entrypoint.sh `envsubst < template`: substitute env vars, leaving
+    any unset ones as literal text (valid JSON string values)."""
+    raw = TEMPLATE.read_text(encoding="utf-8")
+    return json.loads(string.Template(raw).safe_substitute(**env))
+
+
+def test_template_does_not_hardcode_an_engine():
+    raw = TEMPLATE.read_text(encoding="utf-8")
+    assert '"tts_engine": "${TTS_ENGINE}"' in raw
+    assert '"tts_engine": "piper"' not in raw
+    assert '"tts_engine": "melo"' not in raw
+
+
+def test_rendered_engine_follows_env():
+    assert _render(TTS_ENGINE="melo")["tts_engine"] == "melo"
+    assert _render(TTS_ENGINE="piper")["tts_engine"] == "piper"
+    assert _render(TTS_ENGINE="xtts")["tts_engine"] == "xtts"