SDK regeneration

.fern/metadata.json

@@ -1,5 +1,5 @@
 {
-  "cliVersion": "4.4.4",
+  "cliVersion": "5.0.0",
   "generatorName": "fernapi/fern-python-sdk",
   "generatorVersion": "4.37.0",
   "generatorConfig": {
@@ -12,5 +12,6 @@
       "skip_validation": true
     },
     "exclude_types_from_init_exports": true
-  }
+  },
+  "originGitCommit": "b55cdf73dddbda3aa248668eefd04d21d60ee675"
 }

.gitignore

@@ -3,4 +3,3 @@
 __pycache__/
 dist/
 poetry.toml
-.venv/

src/agora_agent/agents/client.py

@@ -10,7 +10,6 @@
 from .types.get_history_agents_response import GetHistoryAgentsResponse
 from .types.get_turns_agents_response import GetTurnsAgentsResponse
 from .types.interrupt_agents_response import InterruptAgentsResponse
-from .types.list_agents_request_state import ListAgentsRequestState
 from .types.list_agents_response import ListAgentsResponse
 from .types.list_agents_response_data_list_item import ListAgentsResponseDataListItem
 from .types.speak_agents_request_priority import SpeakAgentsRequestPriority
@@ -161,7 +160,7 @@ def list(
         channel: typing.Optional[str] = None,
         from_time: typing.Optional[float] = None,
         to_time: typing.Optional[float] = None,
-        state: typing.Optional[ListAgentsRequestState] = None,
+        state: typing.Optional[str] = None,
         limit: typing.Optional[int] = None,
         cursor: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
@@ -183,8 +182,8 @@ def list(
         to_time : typing.Optional[float]
             The end timestamp (in seconds) for the query. Default is current time.
 
-        state : typing.Optional[ListAgentsRequestState]
-            The agent state to filter by. Only one state can be specified per query:
+        state : typing.Optional[str]
+            The agent state filter. You can specify one or more agent states as a comma-separated list in a single request, for example `state=0,1,2`:
             - `IDLE` (0): Agent is idle.
             - `STARTING` (1): The agent is being started.
             - `RUNNING` (2): The agent is running.
@@ -729,7 +728,7 @@ async def list(
         channel: typing.Optional[str] = None,
         from_time: typing.Optional[float] = None,
         to_time: typing.Optional[float] = None,
-        state: typing.Optional[ListAgentsRequestState] = None,
+        state: typing.Optional[str] = None,
         limit: typing.Optional[int] = None,
         cursor: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
@@ -751,8 +750,8 @@ async def list(
         to_time : typing.Optional[float]
             The end timestamp (in seconds) for the query. Default is current time.
 
-        state : typing.Optional[ListAgentsRequestState]
-            The agent state to filter by. Only one state can be specified per query:
+        state : typing.Optional[str]
+            The agent state filter. You can specify one or more agent states as a comma-separated list in a single request, for example `state=0,1,2`:
             - `IDLE` (0): Agent is idle.
             - `STARTING` (1): The agent is being started.
             - `RUNNING` (2): The agent is running.

src/agora_agent/agents/raw_client.py

@@ -15,7 +15,6 @@
 from .types.get_history_agents_response import GetHistoryAgentsResponse
 from .types.get_turns_agents_response import GetTurnsAgentsResponse
 from .types.interrupt_agents_response import InterruptAgentsResponse
-from .types.list_agents_request_state import ListAgentsRequestState
 from .types.list_agents_response import ListAgentsResponse
 from .types.list_agents_response_data_list_item import ListAgentsResponseDataListItem
 from .types.speak_agents_request_priority import SpeakAgentsRequestPriority
@@ -115,7 +114,7 @@ def list(
         channel: typing.Optional[str] = None,
         from_time: typing.Optional[float] = None,
         to_time: typing.Optional[float] = None,
-        state: typing.Optional[ListAgentsRequestState] = None,
+        state: typing.Optional[str] = None,
         limit: typing.Optional[int] = None,
         cursor: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
@@ -137,8 +136,8 @@ def list(
         to_time : typing.Optional[float]
             The end timestamp (in seconds) for the query. Default is current time.
 
-        state : typing.Optional[ListAgentsRequestState]
-            The agent state to filter by. Only one state can be specified per query:
+        state : typing.Optional[str]
+            The agent state filter. You can specify one or more agent states as a comma-separated list in a single request, for example `state=0,1,2`:
             - `IDLE` (0): Agent is idle.
             - `STARTING` (1): The agent is being started.
             - `RUNNING` (2): The agent is running.
@@ -656,7 +655,7 @@ async def list(
         channel: typing.Optional[str] = None,
         from_time: typing.Optional[float] = None,
         to_time: typing.Optional[float] = None,
-        state: typing.Optional[ListAgentsRequestState] = None,
+        state: typing.Optional[str] = None,
         limit: typing.Optional[int] = None,
         cursor: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
@@ -678,8 +677,8 @@ async def list(
         to_time : typing.Optional[float]
             The end timestamp (in seconds) for the query. Default is current time.
 
-        state : typing.Optional[ListAgentsRequestState]
-            The agent state to filter by. Only one state can be specified per query:
+        state : typing.Optional[str]
+            The agent state filter. You can specify one or more agent states as a comma-separated list in a single request, for example `state=0,1,2`:
             - `IDLE` (0): Agent is idle.
             - `STARTING` (1): The agent is being started.
             - `RUNNING` (2): The agent is running.

src/agora_agent/agents/types/get_history_agents_response_contents_item.py

@@ -21,6 +21,21 @@ class GetHistoryAgentsResponseContentsItem(UncheckedBaseModel):
     Message content.
     """
 
+    speech_start_ms: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    The start timestamp of the speech segment in milliseconds, relative to the beginning of the current session. Returned only when `llm.vendor='custom'`.
+    """
+
+    speech_end_ms: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    The end timestamp of the speech segment in milliseconds, relative to the beginning of the current session. Returned only when `llm.vendor='custom'`.
+    """
+
+    speech_algorithmic_delay: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    The total delay in milliseconds introduced by audio processing algorithms, including noise reduction, background voice suppression, and voiceprint locking, after audio is captured from the user's microphone. Use this value to align timestamps with cloud recording audio. Returned only when `llm.vendor='custom'`, `contents[].role='user'`, and actual voice input is present.
+    """
+
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
     else:

src/agora_agent/agents/types/start_agents_request_properties.py

@@ -54,7 +54,7 @@ class StartAgentsRequestProperties(UncheckedBaseModel):
 
     idle_timeout: typing.Optional[int] = pydantic.Field(default=None)
     """
-    Sets the timeout after all the users specified in `remote_rtc_uids` are detected to have left the channel. When the timeout value is exceeded, the agent automatically stops and exits the channel. A value of `0` means that the agent does not exit until it is stopped manually.
+    Sets the timeout after all the users specified in `remote_rtc_uids` are detected to have left the channel. When the timeout value is exceeded, the agent automatically stops and exits the channel. A value of `0` disables exit due to channel idle timeout only; it does not allow the agent to run indefinitely. Regardless of this value, the maximum runtime of a single task is 72 hours, after which the agent automatically exits.
     """
 
     geofence: typing.Optional[StartAgentsRequestPropertiesGeofence] = pydantic.Field(default=None)

src/agora_agent/agents/types/start_agents_request_properties_avatar.py

@@ -26,6 +26,7 @@ class StartAgentsRequestPropertiesAvatar(UncheckedBaseModel):
     - `anam`: Anam (Beta)
     - `generic`: Generic (Beta)
     - `sensetime`: SenseTime Avatar
+    - `spatius`: Spatius Avatar
     """
 
     params: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(default=None)

src/agora_agent/agents/types/start_agents_request_properties_avatar_vendor.py

@@ -3,5 +3,5 @@
 import typing
 
 StartAgentsRequestPropertiesAvatarVendor = typing.Union[
-    typing.Literal["akool", "liveavatar", "anam", "generic", "sensetime", "heygen"], typing.Any
+    typing.Literal["akool", "liveavatar", "anam", "generic", "sensetime", "spatius", "heygen"], typing.Any
 ]

src/agora_agent/agents/types/start_agents_request_properties_parameters.py

@@ -59,6 +59,13 @@ class StartAgentsRequestPropertiesParameters(UncheckedBaseModel):
     - `aiserver`: Optimized for interactions between the user and the conversational AI agent in terms of latency and network resilience.
     """
 
+    opt_out: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Whether to disable data retention for the current session:
+    - `false`: Default. Session data retention remains enabled.
+    - `true`: Disables session data retention. When disabled, historical session content cannot be used for troubleshooting, effectiveness review, or agent optimization.
+    """
+
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
     else:

src/agora_agent/agents/types/start_agents_request_properties_turn_detection_config_end_of_speech.py

@@ -26,6 +26,7 @@ class StartAgentsRequestPropertiesTurnDetectionConfigEndOfSpeech(UncheckedBaseMo
     End of speech detection mode:
     - `vad`: Based on VAD (Voice Activity Detection). Detects silence duration.
     - `semantic`: Based on semantic triggering. Uses semantic understanding to determine when conversation ends.
+    - `manual`: The client explicitly submits the end of the user turn through signaling.
     """
 
     vad_config: typing.Optional[StartAgentsRequestPropertiesTurnDetectionConfigEndOfSpeechVadConfig] = pydantic.Field(

src/agora_agent/agents/types/start_agents_request_properties_turn_detection_config_end_of_speech_mode.py

@@ -3,5 +3,5 @@
 import typing
 
 StartAgentsRequestPropertiesTurnDetectionConfigEndOfSpeechMode = typing.Union[
-    typing.Literal["vad", "semantic"], typing.Any
+    typing.Literal["vad", "semantic", "manual"], typing.Any
 ]

src/agora_agent/agents/types/start_agents_request_properties_turn_detection_config_start_of_speech.py

@@ -30,6 +30,7 @@ class StartAgentsRequestPropertiesTurnDetectionConfigStartOfSpeech(UncheckedBase
     - `vad`: Based on VAD (Voice Activity Detection). Uses audio signal detection.
     - `keywords`: Deprecated. Use `interruption.mode = "keywords"` instead.
     - `disabled`: Deprecated. Use `interruption.enable = false` with `interruption.disabled_config.strategy` to configure the handling strategy.
+    - `manual`: The client explicitly submits the start of the user turn through signaling.
     """
 
     vad_config: typing.Optional[StartAgentsRequestPropertiesTurnDetectionConfigStartOfSpeechVadConfig] = pydantic.Field(

src/agora_agent/agents/types/start_agents_request_properties_turn_detection_config_start_of_speech_mode.py

@@ -3,5 +3,5 @@
 import typing
 
 StartAgentsRequestPropertiesTurnDetectionConfigStartOfSpeechMode = typing.Union[
-    typing.Literal["vad", "keywords", "disabled"], typing.Any
+    typing.Literal["vad", "keywords", "disabled", "manual"], typing.Any
 ]

src/agora_agent/core/client_wrapper.py

@@ -26,10 +26,10 @@ def __init__(
 
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "agora-agents/v2.2.1",
+            "User-Agent": "agora-agents/v2.3.2",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "agora-agents",
-            "X-Fern-SDK-Version": "v2.2.1",
+            "X-Fern-SDK-Version": "v2.3.2",
             **(self.get_custom_headers() or {}),
         }
         headers["Authorization"] = httpx.BasicAuth(self._get_username(), self._get_password())._auth_header

src/agora_agent/types/asr.py

@@ -19,6 +19,7 @@
 from .sarvam_asr_params import SarvamAsrParams
 from .speechmatics_asr_params import SpeechmaticsAsrParams
 from .tencent_asr_params import TencentAsrParams
+from .x_ai_asr_params import XAiAsrParams
 from .xfyun_asr_params import XfyunAsrParams
 from .xfyun_bigmodel_asr_params import XfyunBigmodelAsrParams
 from .xfyun_dialect_asr_params import XfyunDialectAsrParams
@@ -189,6 +190,21 @@ class Config:
             extra = pydantic.Extra.allow
 
 
+class Asr_Xai(UncheckedBaseModel):
+    vendor: typing.Literal["xai"] = "xai"
+    language: typing.Optional[AsrLanguage] = None
+    params: XAiAsrParams
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow
+
+
 class Asr_Xfyun(UncheckedBaseModel):
     vendor: typing.Literal["xfyun"] = "xfyun"
     language: typing.Optional[AsrLanguage] = None
@@ -247,6 +263,7 @@ class Config:
         Asr_Assemblyai,
         Asr_Speechmatics,
         Asr_Sarvam,
+        Asr_Xai,
         Asr_Xfyun,
         Asr_XfyunBigmodel,
         Asr_XfyunDialect,

src/agora_agent/types/generic_tts.py

@@ -0,0 +1,39 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2
+from ..core.unchecked_base_model import UncheckedBaseModel
+from .generic_tts_params import GenericTtsParams
+
+
+class GenericTts(UncheckedBaseModel):
+    """
+    Generic OpenAI-compatible Text-to-Speech configuration.
+    """
+
+    url: str = pydantic.Field()
+    """
+    Callback address of the generic TTS service.
+    """
+
+    headers: typing.Dict[str, str] = pydantic.Field()
+    """
+    Custom headers to include in requests to the generic TTS service.
+    """
+
+    params: GenericTtsParams
+    skip_patterns: typing.Optional[typing.List[int]] = pydantic.Field(default=None)
+    """
+    Controls whether the TTS module skips bracketed content when reading LLM response text.
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow