Narrow settings.model at service boundaries, not via truthiness

Two services were reading `_settings.model` (typed `str | _NotGiven |
None` because NOT_GIVEN is the default) and coercing it with `or ""`
or similar. `_NotGiven.__bool__` returns False, so the runtime
behavior happened to work, but the type was a lie — pyright saw
`str | _NotGiven` flowing into APIs that required `str` or `str | None`.

- `AIService._sync_model_name_to_metrics`: use `isinstance(model, str)`
  narrowing with an empty-string fallback. Equivalent runtime behavior,
  honest type, no truthiness dependency on a sentinel.
- `SarvamLLMService.__init__`: validate the model is a real string
  before handing it to `_validate_model(str)`. A non-string model at
  this point is a configuration bug; raise `ValueError` so the error
  is clear and survives `python -O` (unlike an assert).

pyrightconfig.json

@@ -2,14 +2,8 @@
   "typeCheckingMode": "basic",
   "pythonVersion": "3.11",
   "pythonPlatform": "All",
-  "include": [
+  "include": ["scripts", "src/pipecat"],
-    "scripts",
+  "exclude": ["**/*_pb2.py", "**/__pycache__"],
-    "src/pipecat"
-  ],
-  "exclude": [
-    "**/*_pb2.py",
-    "**/__pycache__"
-  ],
   "ignore": [
     "tests",
     "src/pipecat/adapters/base_llm_adapter.py",
@@ -40,7 +34,6 @@
     "src/pipecat/processors/frameworks/rtvi/processor.py",
     "src/pipecat/processors/frameworks/strands_agents.py",
     "src/pipecat/processors/gstreamer/pipeline_source.py",
-    "src/pipecat/services/ai_service.py",
     "src/pipecat/services/anthropic/llm.py",
     "src/pipecat/services/assemblyai/stt.py",
     "src/pipecat/services/asyncai/tts.py",
@@ -106,7 +99,6 @@
     "src/pipecat/services/resembleai/tts.py",
     "src/pipecat/services/rime/tts.py",
     "src/pipecat/services/sambanova/llm.py",
-    "src/pipecat/services/sarvam/llm.py",
     "src/pipecat/services/sarvam/stt.py",
     "src/pipecat/services/sarvam/tts.py",
     "src/pipecat/services/simli/video.py",

src/pipecat/services/ai_service.py

@@ -66,8 +66,9 @@ class AIService(FrameProcessor):
         Args:
             model: The name of the AI model to use.
         """
+        model = self._settings.model
         self.set_core_metrics_data(
-            MetricsData(processor=self.name, model=self._settings.model or "")
+            MetricsData(processor=self.name, model=model if isinstance(model, str) else "")
         )
 
     async def start(self, frame: StartFrame):

src/pipecat/services/sarvam/llm.py

@@ -83,7 +83,10 @@ class SarvamLLMService(OpenAILLMService):
         if settings is not None:
             default_settings.apply_update(settings)
 
-        self._validate_model(default_settings.model)
+        model = default_settings.model
+        if not isinstance(model, str):
+            raise ValueError("Sarvam LLM requires a non-empty model string.")
+        self._validate_model(model)
 
         super().__init__(
             api_key=api_key,