feat: extended CreateAgent timeout to 180 seconds (#519)

* feat: extended CreateAgent timeout to 180 seconds
feat: added debug info to StreamingDetectIntent
feat: added dtmf digits to WebhookRequest
feat: added FLOW as a new DiffType in TestRunDifference

PiperOrigin-RevId: 529897408

Source-Link: googleapis/googleapis@4de416f

Source-Link: googleapis/googleapis-gen@a9b661f
Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiYTliNjYxZjlmZWI3NWUyODAzZmUxYjViNjM1ZTM1Yjg5Y2IxYmM3NiJ9

* 🦉 Updates from OwlBot post-processor

See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md

* feat: extended CreateAgent timeout to 180 seconds
feat: added debug info to StreamingDetectIntent
feat: added dtmf digits to WebhookRequest
feat: added FLOW as a new DiffType in TestRunDifference

PiperOrigin-RevId: 530032469

Source-Link: googleapis/googleapis@ff708e3

Source-Link: googleapis/googleapis-gen@0578b38
Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiMDU3OGIzOGM2OGYwMjkzMjhhMjBiYWMyMmIyODgzNTNiZGFhYzRiNyJ9

* 🦉 Updates from OwlBot post-processor

See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md

---------

Co-authored-by: Owl Bot <gcf-owl-bot[bot]@users.noreply.github.com>

google/cloud/dialogflowcx/__init__.py

@@ -219,6 +219,7 @@
     UpdateSecuritySettingsRequest,
 )
 from google.cloud.dialogflowcx_v3.types.session import AudioInput
+from google.cloud.dialogflowcx_v3.types.session import CloudConversationDebuggingInfo
 from google.cloud.dialogflowcx_v3.types.session import DetectIntentRequest
 from google.cloud.dialogflowcx_v3.types.session import DetectIntentResponse
 from google.cloud.dialogflowcx_v3.types.session import DtmfInput
@@ -485,6 +486,7 @@
     "SecuritySettings",
     "UpdateSecuritySettingsRequest",
     "AudioInput",
+    "CloudConversationDebuggingInfo",
     "DetectIntentRequest",
     "DetectIntentResponse",
     "DtmfInput",

google/cloud/dialogflowcx_v3/__init__.py

@@ -167,6 +167,7 @@
 from .types.security_settings import SecuritySettings
 from .types.security_settings import UpdateSecuritySettingsRequest
 from .types.session import AudioInput
+from .types.session import CloudConversationDebuggingInfo
 from .types.session import DetectIntentRequest
 from .types.session import DetectIntentResponse
 from .types.session import DtmfInput
@@ -289,6 +290,7 @@
     "CalculateCoverageResponse",
     "Changelog",
     "ChangelogsClient",
+    "CloudConversationDebuggingInfo",
     "CompareVersionsRequest",
     "CompareVersionsResponse",
     "ContinuousTestResult",

google/cloud/dialogflowcx_v3/services/agents/async_client.py

@@ -573,7 +573,16 @@ async def sample_create_agent():
         # and friendly error handling.
         rpc = gapic_v1.method_async.wrap_method(
             self._client._transport.create_agent,
-            default_timeout=None,
+            default_retry=retries.Retry(
+                initial=0.1,
+                maximum=60.0,
+                multiplier=1.3,
+                predicate=retries.if_exception_type(
+                    core_exceptions.ServiceUnavailable,
+                ),
+                deadline=180.0,
+            ),
+            default_timeout=180.0,
             client_info=DEFAULT_CLIENT_INFO,
         )
 

google/cloud/dialogflowcx_v3/services/agents/transports/base.py

@@ -144,7 +144,16 @@ def _prep_wrapped_messages(self, client_info):
             ),
             self.create_agent: gapic_v1.method.wrap_method(
                 self.create_agent,
-                default_timeout=None,
+                default_retry=retries.Retry(
+                    initial=0.1,
+                    maximum=60.0,
+                    multiplier=1.3,
+                    predicate=retries.if_exception_type(
+                        core_exceptions.ServiceUnavailable,
+                    ),
+                    deadline=180.0,
+                ),
+                default_timeout=180.0,
                 client_info=client_info,
             ),
             self.update_agent: gapic_v1.method.wrap_method(

google/cloud/dialogflowcx_v3/types/__init__.py

@@ -160,6 +160,7 @@
 )
 from .session import (
     AudioInput,
+    CloudConversationDebuggingInfo,
     DetectIntentRequest,
     DetectIntentResponse,
     DtmfInput,
@@ -381,6 +382,7 @@
     "SecuritySettings",
     "UpdateSecuritySettingsRequest",
     "AudioInput",
+    "CloudConversationDebuggingInfo",
     "DetectIntentRequest",
     "DetectIntentResponse",
     "DtmfInput",

google/cloud/dialogflowcx_v3/types/agent.py

@@ -430,7 +430,7 @@ class ExportAgentResponse(proto.Message):
     Attributes:
         agent_uri (str):
             The URI to a file containing the exported agent. This field
-            is populated only if ``agent_uri`` is specified in
+            is populated if ``agent_uri`` is specified in
             [ExportAgentRequest][google.cloud.dialogflow.cx.v3.ExportAgentRequest].
 
             This field is a member of `oneof`_ ``agent``.

google/cloud/dialogflowcx_v3/types/audio_config.py

@@ -294,7 +294,13 @@ class InputAudioConfig(proto.Message):
             using the standard version of the specified model. Refer to
             `Cloud Speech API
             documentation <https://cloud.google.com/speech-to-text/docs/basics#select-model>`__
-            for more details.
+            for more details. If you specify a model, the following
+            models typically have the best performance:
+
+            -  phone_call (best for Agent Assist and telephony)
+            -  latest_short (best for Dialogflow non-telephony)
+            -  command_and_search (best for very short utterances and
+               commands)
         model_variant (google.cloud.dialogflowcx_v3.types.SpeechModelVariant):
             Optional. Which variant of the [Speech
             model][google.cloud.dialogflow.cx.v3.InputAudioConfig.model]
@@ -475,14 +481,24 @@ class OutputAudioConfig(proto.Message):
 
 
 class TextToSpeechSettings(proto.Message):
-    r"""Settings related to speech generating.
+    r"""Settings related to speech synthesizing.
 
     Attributes:
         synthesize_speech_configs (MutableMapping[str, google.cloud.dialogflowcx_v3.types.SynthesizeSpeechConfig]):
-            Configuration of how speech should be
-            synthesized, mapping from language
-            (https://dialogflow.com/docs/reference/language)
+            Configuration of how speech should be synthesized, mapping
+            from language
+            (https://cloud.google.com/dialogflow/cx/docs/reference/language)
             to SynthesizeSpeechConfig.
+
+            These settings affect:
+
+            -  The synthesize configuration used in `phone
+               gateway <https://cloud.google.com/dialogflow/cx/docs/concept/integration/phone-gateway>`__.
+
+            -  You no longer need to specify
+               [OutputAudioConfig.synthesize_speech_config][google.cloud.dialogflow.cx.v3.OutputAudioConfig.synthesize_speech_config]
+               when invoking API calls. Your agent will use the
+               pre-configured options for speech synthesizing.
     """
 
     synthesize_speech_configs: MutableMapping[

google/cloud/dialogflowcx_v3/types/gcs.py

@@ -35,11 +35,11 @@ class GcsDestination(proto.Message):
 
     Attributes:
         uri (str):
-            Required. The Google Cloud Storage URI for
-            the exported objects. A URI is of the form:
-              gs://bucket/object-name-or-prefix
-            Whether a full object name, or just a prefix,
-            its usage depends on the Dialogflow operation.
+            Required. The Google Cloud Storage URI for the exported
+            objects. A URI is of the form:
+            ``gs://bucket/object-name-or-prefix`` Whether a full object
+            name, or just a prefix, its usage depends on the Dialogflow
+            operation.
     """
 
     uri: str = proto.Field(

google/cloud/dialogflowcx_v3/types/session.py

@@ -36,6 +36,7 @@
         "DetectIntentRequest",
         "DetectIntentResponse",
         "StreamingDetectIntentRequest",
+        "CloudConversationDebuggingInfo",
         "StreamingDetectIntentResponse",
         "StreamingRecognitionResult",
         "QueryParameters",
@@ -259,6 +260,9 @@ class StreamingDetectIntentRequest(proto.Message):
             enabled, response stream still contains only one final
             ``DetectIntentResponse`` even if some ``Fulfillment``\ s in
             the agent have been configured to return partial responses.
+        enable_debugging_info (bool):
+            If true, ``StreamingDetectIntentResponse.debugging_info``
+            will get populated.
     """
 
     session: str = proto.Field(
@@ -284,6 +288,157 @@ class StreamingDetectIntentRequest(proto.Message):
         proto.BOOL,
         number=5,
     )
+    enable_debugging_info: bool = proto.Field(
+        proto.BOOL,
+        number=8,
+    )
+
+
+class CloudConversationDebuggingInfo(proto.Message):
+    r"""Cloud conversation info for easier debugging. It will get populated
+    in ``StreamingDetectIntentResponse`` or
+    ``StreamingAnalyzeContentResponse`` when the flag
+    ``enable_debugging_info`` is set to true in corresponding requests.
+
+    Attributes:
+        audio_data_chunks (int):
+            Number of input audio data chunks in
+            streaming requests.
+        result_end_time_offset (google.protobuf.duration_pb2.Duration):
+            Time offset of the end of speech utterance
+            relative to the beginning of the first audio
+            chunk.
+        first_audio_duration (google.protobuf.duration_pb2.Duration):
+            Duration of first audio chunk.
+        single_utterance (bool):
+            Whether client used single utterance mode.
+        speech_partial_results_end_times (MutableSequence[google.protobuf.duration_pb2.Duration]):
+            Time offsets of the speech partial results
+            relative to the beginning of the stream.
+        speech_final_results_end_times (MutableSequence[google.protobuf.duration_pb2.Duration]):
+            Time offsets of the speech final results (is_final=true)
+            relative to the beginning of the stream.
+        partial_responses (int):
+            Total number of partial responses.
+        speaker_id_passive_latency_ms_offset (int):
+            Time offset of Speaker ID stream close time
+            relative to the Speech stream close time in
+            milliseconds. Only meaningful for conversations
+            involving passive verification.
+        bargein_event_triggered (bool):
+            Whether a barge-in event is triggered in this
+            request.
+        speech_single_utterance (bool):
+            Whether speech uses single utterance mode.
+        dtmf_partial_results_times (MutableSequence[google.protobuf.duration_pb2.Duration]):
+            Time offsets of the DTMF partial results
+            relative to the beginning of the stream.
+        dtmf_final_results_times (MutableSequence[google.protobuf.duration_pb2.Duration]):
+            Time offsets of the DTMF final results
+            relative to the beginning of the stream.
+        single_utterance_end_time_offset (google.protobuf.duration_pb2.Duration):
+            Time offset of the end-of-single-utterance
+            signal relative to the beginning of the stream.
+        no_speech_timeout (google.protobuf.duration_pb2.Duration):
+            No speech timeout settings observed at
+            runtime.
+        is_input_text (bool):
+            Whether the streaming terminates with an
+            injected text query.
+        client_half_close_time_offset (google.protobuf.duration_pb2.Duration):
+            Client half close time in terms of input
+            audio duration.
+        client_half_close_streaming_time_offset (google.protobuf.duration_pb2.Duration):
+            Client half close time in terms of API
+            streaming duration.
+    """
+
+    audio_data_chunks: int = proto.Field(
+        proto.INT32,
+        number=1,
+    )
+    result_end_time_offset: duration_pb2.Duration = proto.Field(
+        proto.MESSAGE,
+        number=2,
+        message=duration_pb2.Duration,
+    )
+    first_audio_duration: duration_pb2.Duration = proto.Field(
+        proto.MESSAGE,
+        number=3,
+        message=duration_pb2.Duration,
+    )
+    single_utterance: bool = proto.Field(
+        proto.BOOL,
+        number=5,
+    )
+    speech_partial_results_end_times: MutableSequence[
+        duration_pb2.Duration
+    ] = proto.RepeatedField(
+        proto.MESSAGE,
+        number=6,
+        message=duration_pb2.Duration,
+    )
+    speech_final_results_end_times: MutableSequence[
+        duration_pb2.Duration
+    ] = proto.RepeatedField(
+        proto.MESSAGE,
+        number=7,
+        message=duration_pb2.Duration,
+    )
+    partial_responses: int = proto.Field(
+        proto.INT32,
+        number=8,
+    )
+    speaker_id_passive_latency_ms_offset: int = proto.Field(
+        proto.INT32,
+        number=9,
+    )
+    bargein_event_triggered: bool = proto.Field(
+        proto.BOOL,
+        number=10,
+    )
+    speech_single_utterance: bool = proto.Field(
+        proto.BOOL,
+        number=11,
+    )
+    dtmf_partial_results_times: MutableSequence[
+        duration_pb2.Duration
+    ] = proto.RepeatedField(
+        proto.MESSAGE,
+        number=12,
+        message=duration_pb2.Duration,
+    )
+    dtmf_final_results_times: MutableSequence[
+        duration_pb2.Duration
+    ] = proto.RepeatedField(
+        proto.MESSAGE,
+        number=13,
+        message=duration_pb2.Duration,
+    )
+    single_utterance_end_time_offset: duration_pb2.Duration = proto.Field(
+        proto.MESSAGE,
+        number=14,
+        message=duration_pb2.Duration,
+    )
+    no_speech_timeout: duration_pb2.Duration = proto.Field(
+        proto.MESSAGE,
+        number=15,
+        message=duration_pb2.Duration,
+    )
+    is_input_text: bool = proto.Field(
+        proto.BOOL,
+        number=16,
+    )
+    client_half_close_time_offset: duration_pb2.Duration = proto.Field(
+        proto.MESSAGE,
+        number=17,
+        message=duration_pb2.Duration,
+    )
+    client_half_close_streaming_time_offset: duration_pb2.Duration = proto.Field(
+        proto.MESSAGE,
+        number=18,
+        message=duration_pb2.Duration,
+    )
 
 
 class StreamingDetectIntentResponse(proto.Message):
@@ -332,6 +487,10 @@ class StreamingDetectIntentResponse(proto.Message):
             The response from detect intent.
 
             This field is a member of `oneof`_ ``response``.
+        debugging_info (google.cloud.dialogflowcx_v3.types.CloudConversationDebuggingInfo):
+            Debugging info that would get populated when
+            ``StreamingDetectIntentRequest.enable_debugging_info`` is
+            set to true.
     """
 
     recognition_result: "StreamingRecognitionResult" = proto.Field(
@@ -346,6 +505,11 @@ class StreamingDetectIntentResponse(proto.Message):
         oneof="response",
         message="DetectIntentResponse",
     )
+    debugging_info: "CloudConversationDebuggingInfo" = proto.Field(
+        proto.MESSAGE,
+        number=4,
+        message="CloudConversationDebuggingInfo",
+    )
 
 
 class StreamingRecognitionResult(proto.Message):
@@ -679,6 +843,8 @@ class QueryInput(proto.Message):
 
     4.  An event to be triggered.
 
+    5.  DTMF digits to invoke an intent and fill in parameter value.
+
     This message has `oneof`_ fields (mutually exclusive fields).
     For each oneof, at most one member field can be set at the same time.
     Setting any member of the oneof automatically clears all other
@@ -790,8 +956,9 @@ class QueryResult(proto.Message):
 
             This field is a member of `oneof`_ ``query``.
         dtmf (google.cloud.dialogflowcx_v3.types.DtmfInput):
-            If a [DTMF][DTMFInput] was provided as input, this field
-            will contain a copy of the [DTMFInput][].
+            If a [DTMF][google.cloud.dialogflow.cx.v3.DtmfInput] was
+            provided as input, this field will contain a copy of the
+            [DtmfInput][google.cloud.dialogflow.cx.v3.DtmfInput].
 
             This field is a member of `oneof`_ ``query``.
         language_code (str):