Merge remote-tracking branch 'origin/main' into feat/user-onboarding

# Conflicts:
#	docs/api-reference/openapi.json
#	sdk/python/src/dograh_sdk/_generated_models.py
#	ui/src/client/index.ts
#	ui/src/components/AIModelConfigurationV2Editor.tsx

api/tests/test_huggingface_stt_service_factory.py

@@ -0,0 +1,131 @@
+from types import SimpleNamespace
+from unittest.mock import patch
+
+from api.services.configuration.check_validity import UserConfigurationValidator
+from api.services.configuration.registry import (
+    REGISTRY,
+    HuggingFaceLLMConfiguration,
+    HuggingFaceSTTConfiguration,
+    ServiceProviders,
+    ServiceType,
+)
+from api.services.pipecat.service_factory import (
+    create_llm_service,
+    create_stt_service,
+)
+
+
+def test_huggingface_stt_configuration_defaults_and_registry():
+    config = HuggingFaceSTTConfiguration(api_key="hf_test")
+
+    assert config.provider == ServiceProviders.HUGGINGFACE
+    assert config.model == "openai/whisper-large-v3-turbo"
+    assert config.base_url == "https://router.huggingface.co/hf-inference"
+    assert config.return_timestamps is False
+    assert (
+        REGISTRY[ServiceType.STT][ServiceProviders.HUGGINGFACE]
+        is HuggingFaceSTTConfiguration
+    )
+
+
+def test_huggingface_llm_configuration_defaults_and_registry():
+    config = HuggingFaceLLMConfiguration(api_key="hf_test")
+
+    assert config.provider == ServiceProviders.HUGGINGFACE
+    assert config.model == "openai/gpt-oss-120b:cerebras"
+    assert config.base_url == "https://router.huggingface.co/v1"
+    assert (
+        REGISTRY[ServiceType.LLM][ServiceProviders.HUGGINGFACE]
+        is HuggingFaceLLMConfiguration
+    )
+
+
+def test_create_huggingface_llm_service_uses_openai_compatible_router():
+    user_config = SimpleNamespace(
+        llm=SimpleNamespace(
+            provider=ServiceProviders.HUGGINGFACE.value,
+            api_key="hf_test",
+            model="deepseek-ai/DeepSeek-R1:fastest",
+            base_url="https://router.huggingface.co/v1",
+            bill_to="demo-org",
+        )
+    )
+
+    with patch(
+        "api.services.pipecat.service_factory.HuggingFaceLLMService"
+    ) as mock_service:
+        create_llm_service(user_config)
+
+    assert mock_service.call_count == 1
+    kwargs = mock_service.call_args.kwargs
+    assert kwargs["api_key"] == "hf_test"
+    assert kwargs["base_url"] == "https://router.huggingface.co/v1"
+    assert kwargs["bill_to"] == "demo-org"
+    assert kwargs["settings"].model == "deepseek-ai/DeepSeek-R1:fastest"
+    assert kwargs["settings"].temperature == 0.1
+
+
+def test_create_huggingface_stt_service_uses_hosted_defaults():
+    user_config = SimpleNamespace(
+        stt=SimpleNamespace(
+            provider=ServiceProviders.HUGGINGFACE.value,
+            api_key="hf_test",
+            model="openai/whisper-large-v3-turbo",
+            base_url="https://router.huggingface.co/hf-inference",
+            bill_to="demo-org",
+            return_timestamps=True,
+        )
+    )
+    audio_config = SimpleNamespace(transport_in_sample_rate=16000)
+
+    with patch(
+        "api.services.pipecat.service_factory.HuggingFaceSTTService"
+    ) as mock_service:
+        create_stt_service(user_config, audio_config)
+
+    assert mock_service.call_count == 1
+    kwargs = mock_service.call_args.kwargs
+    assert kwargs["api_key"] == "hf_test"
+    assert kwargs["base_url"] == "https://router.huggingface.co/hf-inference"
+    assert kwargs["bill_to"] == "demo-org"
+    assert kwargs["sample_rate"] == 16000
+    assert kwargs["settings"].model == "openai/whisper-large-v3-turbo"
+    assert kwargs["settings"].return_timestamps is True
+
+
+def test_validator_accepts_huggingface_stt_token_format():
+    validator = UserConfigurationValidator()
+
+    assert (
+        validator._validate_service(
+            HuggingFaceSTTConfiguration(api_key="hf_test"),
+            "stt",
+        )
+        == []
+    )
+    assert (
+        validator._validate_service(
+            HuggingFaceLLMConfiguration(api_key="hf_test"),
+            "llm",
+        )
+        == []
+    )
+
+
+def test_validator_rejects_non_huggingface_token_format():
+    validator = UserConfigurationValidator()
+
+    errors = validator._validate_service(
+        HuggingFaceSTTConfiguration(api_key="not-hf-token"),
+        "stt",
+    )
+
+    assert errors == [
+        {
+            "model": "stt",
+            "message": (
+                "Invalid Hugging Face API token format. Use a token that starts with "
+                "'hf_' and has Inference Providers permission."
+            ),
+        }
+    ]

api/tests/test_openai_tts_service_factory.py

@@ -0,0 +1,31 @@
+from types import SimpleNamespace
+from unittest.mock import patch
+
+from pipecat.services.openai._constants import OPENAI_SAMPLE_RATE
+
+from api.services.configuration.registry import ServiceProviders
+from api.services.pipecat.service_factory import create_tts_service
+
+
+def test_create_openai_tts_service_uses_openai_pcm_sample_rate():
+    user_config = SimpleNamespace(
+        tts=SimpleNamespace(
+            provider=ServiceProviders.OPENAI.value,
+            api_key="test-key",
+            model="gpt-4o-mini-tts",
+            voice="alloy",
+            base_url=None,
+        )
+    )
+    audio_config = SimpleNamespace(
+        transport_out_sample_rate=16000,
+        transport_in_sample_rate=16000,
+    )
+
+    with patch("api.services.pipecat.service_factory.OpenAITTSService") as mock_service:
+        create_tts_service(user_config, audio_config)
+
+    assert mock_service.call_count == 1
+    kwargs = mock_service.call_args.kwargs
+    assert kwargs["sample_rate"] == OPENAI_SAMPLE_RATE
+    assert kwargs["settings"].model == "gpt-4o-mini-tts"

api/tests/test_s3_signed_url.py

@@ -0,0 +1,30 @@
+from api.routes.s3_signed_url import (
+    _extract_legacy_workflow_run_id,
+    _extract_org_id_from_key,
+)
+
+
+def test_split_recording_keys_are_workflow_run_artifacts_not_org_keys():
+    assert _extract_legacy_workflow_run_id("recordings/1855/user.wav") == 1855
+    assert _extract_legacy_workflow_run_id("recordings/1855/bot.wav") == 1855
+
+    assert _extract_org_id_from_key("recordings/1855/user.wav") is None
+    assert _extract_org_id_from_key("recordings/1855/bot.wav") is None
+
+
+def test_legacy_recording_keys_do_not_fall_through_to_org_scoped_auth():
+    assert _extract_legacy_workflow_run_id("recordings/1855.wav") == 1855
+    assert _extract_legacy_workflow_run_id("recordings/1855/other.wav") is None
+
+    assert _extract_org_id_from_key("recordings/1855.wav") is None
+    assert _extract_org_id_from_key("recordings/1855/other.wav") is None
+
+
+def test_known_org_scoped_keys_extract_org_id():
+    assert _extract_org_id_from_key("campaigns/42/source.csv") == 42
+    assert _extract_org_id_from_key("knowledge_base/42/document/file.pdf") == 42
+    assert _extract_legacy_workflow_run_id("campaigns/42/source.csv") is None
+
+
+def test_unknown_numeric_prefix_is_not_treated_as_org_scoped():
+    assert _extract_org_id_from_key("unknown/42/file.wav") is None

api/tests/test_sarvam_service_factory.py

@@ -7,6 +7,7 @@ from pipecat.transcriptions.language import Language
 
 from api.services.configuration.registry import (
     SarvamLLMConfiguration,
+    SarvamTTSConfiguration,
     ServiceProviders,
 )
 from api.services.pipecat.audio_config import AudioConfig
@@ -14,6 +15,7 @@ from api.services.pipecat.service_factory import (
     create_llm_service,
     create_llm_service_from_provider,
     create_stt_service,
+    create_tts_service,
 )
 
 
@@ -112,3 +114,41 @@ class TestSarvamSTTServiceFactory:
 
         kwargs = mock_service.call_args.kwargs
         assert kwargs["settings"].language == expected_language
+
+
+class TestSarvamTTSServiceFactory:
+    def test_sarvam_tts_configuration_defaults(self):
+        config = SarvamTTSConfiguration(api_key="test-key")
+
+        assert config.provider == ServiceProviders.SARVAM
+        assert config.model == "bulbul:v2"
+        assert config.voice == "anushka"
+        assert config.language == "hi-IN"
+        assert config.speed == 1.0
+
+    def test_create_sarvam_tts_service_maps_speed_to_pace(self):
+        user_config = SimpleNamespace(
+            tts=SimpleNamespace(
+                provider=ServiceProviders.SARVAM.value,
+                api_key="test-key",
+                model="bulbul:v2",
+                voice="anushka",
+                language="hi-IN",
+                speed=1.25,
+            )
+        )
+        audio_config = AudioConfig(
+            transport_in_sample_rate=16000, transport_out_sample_rate=16000
+        )
+
+        with patch(
+            "api.services.pipecat.service_factory.SarvamTTSService"
+        ) as mock_service:
+            create_tts_service(user_config, audio_config)
+
+        kwargs = mock_service.call_args.kwargs
+        assert kwargs["api_key"] == "test-key"
+        assert kwargs["settings"].model == "bulbul:v2"
+        assert kwargs["settings"].voice == "anushka"
+        assert kwargs["settings"].language == Language.HI
+        assert kwargs["settings"].pace == 1.25

api/tests/test_smallest_service_factory.py

@@ -0,0 +1,80 @@
+from types import SimpleNamespace
+from unittest.mock import patch
+
+from api.services.configuration.check_validity import UserConfigurationValidator
+from api.services.configuration.registry import (
+    REGISTRY,
+    ServiceProviders,
+    ServiceType,
+    SmallestAISTTConfiguration,
+    SmallestAITTSConfiguration,
+)
+from api.services.pipecat.service_factory import create_tts_service
+
+
+def test_smallest_tts_configuration_defaults_and_registry():
+    config = SmallestAITTSConfiguration(api_key="test-key")
+
+    assert config.provider == ServiceProviders.SMALLEST
+    assert config.model == "lightning_v3.1"
+    assert config.voice == "sophia"
+    assert config.language == "en"
+    assert config.speed == 1.0
+    assert (
+        REGISTRY[ServiceType.TTS][ServiceProviders.SMALLEST]
+        is SmallestAITTSConfiguration
+    )
+
+
+def test_smallest_stt_configuration_defaults_and_registry():
+    config = SmallestAISTTConfiguration(api_key="test-key")
+
+    assert config.provider == ServiceProviders.SMALLEST
+    assert config.model == "pulse"
+    assert config.language == "en"
+    assert (
+        REGISTRY[ServiceType.STT][ServiceProviders.SMALLEST]
+        is SmallestAISTTConfiguration
+    )
+
+
+def test_validator_accepts_smallest_services():
+    validator = UserConfigurationValidator()
+
+    assert (
+        validator._validate_service(
+            SmallestAITTSConfiguration(api_key="test-key"),
+            "tts",
+        )
+        == []
+    )
+    assert (
+        validator._validate_service(
+            SmallestAISTTConfiguration(api_key="test-key"),
+            "stt",
+        )
+        == []
+    )
+
+
+def test_create_smallest_tts_service_normalizes_hyphenated_model_values():
+    user_config = SimpleNamespace(
+        tts=SimpleNamespace(
+            provider=ServiceProviders.SMALLEST.value,
+            api_key="test-key",
+            model="lightning-v3.1",
+            voice="sophia",
+            language="en",
+            speed=1.0,
+        )
+    )
+    audio_config = SimpleNamespace(transport_in_sample_rate=16000)
+
+    with patch(
+        "api.services.pipecat.service_factory.SmallestTTSService"
+    ) as mock_service:
+        create_tts_service(user_config, audio_config)
+
+    assert mock_service.call_count == 1
+    kwargs = mock_service.call_args.kwargs
+    assert kwargs["settings"].model == "lightning_v3.1"