fix(tts): tolerate a malformed tts_speed instead of 500-ing (#1450)

synthesize() and get_stats() parsed the stored tts_speed with a bare
float(settings.get("tts_speed", "1")). The manage_settings agent tool maps
"speech speed"/"voice speed" to tts_speed and, because the setting's default is
a string, writes the value through unvalidated — so an agent (or a hand-edited
settings.json) can store "fast" or "". After that, GET /api/tts/stats and POST
/api/tts/synthesize both 500 with ValueError until the JSON is corrected by hand.

Parse defensively via a _safe_speed() helper (non-numeric/empty/<=0 -> 1.0),
mirroring the settings layer's tolerance of corrupt config.

Adds tests/test_tts_speed_malformed.py (stats + synthesize) — both raise
ValueError before this change and pass after.
This commit is contained in:
Shaw
2026-06-03 01:12:03 -04:00
committed by GitHub
parent 844dbf6a22
commit d38fb4bc46
2 changed files with 45 additions and 2 deletions

View File

@@ -12,6 +12,18 @@ from typing import Optional, Dict, Any
logger = logging.getLogger(__name__)
def _safe_speed(value, default: float = 1.0) -> float:
"""Parse the stored tts_speed defensively. The settings layer tolerates
corrupt/agent-written config, so a non-numeric or empty value (e.g. an agent
setting "speech speed" = "fast", or a hand-edited settings.json) must not
crash synthesis or the stats endpoint with a ValueError."""
try:
speed = float(value)
except (TypeError, ValueError):
return default
return speed if speed > 0 else default
class TTSService:
"""Multi-provider TTS service.
@@ -136,7 +148,7 @@ class TTSService:
provider = settings["tts_provider"]
model = settings["tts_model"]
voice = settings["tts_voice"]
speed = float(settings.get("tts_speed", "1"))
speed = _safe_speed(settings.get("tts_speed", "1"))
if provider in ("disabled", "browser"):
return None
@@ -198,7 +210,7 @@ class TTSService:
"provider": provider,
"model": settings["tts_model"],
"voice": settings["tts_voice"],
"speed": float(settings.get("tts_speed", "1")),
"speed": _safe_speed(settings.get("tts_speed", "1")),
"cache_entries": len(cache_files),
"cache_size_mb": round(cache_size / (1024 * 1024), 2),
}