orq-ai-sdk 4.2.0rc48__py3-none-any.whl → 4.2.12__py3-none-any.whl

orq_ai_sdk/models/retrievedatasetop.py

@@ -81,7 +81,7 @@ class RetrieveDatasetResponseBody(BaseModel):
     created: Optional[datetime] = None
     r"""The date and time the resource was created"""
 
-    updated: Optional[datetime] = parse_datetime("2026-01-20T13:00:20.021Z")
+    updated: Optional[datetime] = parse_datetime("2026-01-27T09:10:34.517Z")
     r"""The date and time the resource was last updated"""
 
     @model_serializer(mode="wrap")

orq_ai_sdk/models/retrievedatasourceop.py

@@ -90,7 +90,7 @@ class RetrieveDatasourceResponseBody(BaseModel):
     r"""The number of chunks in the datasource"""
 
     id: Annotated[Optional[str], pydantic.Field(alias="_id")] = (
-        "01KFDQW6KSCQPGDN54DM6JRNRN"
+        "01KFZBGG96WJ7P91349B0NCQJ5"
     )
     r"""The unique identifier of the data source"""
 

orq_ai_sdk/models/retrieveidentityop.py

@@ -103,7 +103,7 @@ class RetrieveIdentityResponseBody(BaseModel):
     created: Optional[datetime] = None
     r"""The date and time the resource was created"""
 
-    updated: Optional[datetime] = parse_datetime("2026-01-20T13:00:20.021Z")
+    updated: Optional[datetime] = parse_datetime("2026-01-27T09:10:34.517Z")
     r"""The date and time the resource was last updated"""
 
     @model_serializer(mode="wrap")

orq_ai_sdk/models/retrievememoryop.py

@@ -37,8 +37,9 @@ class RetrieveMemoryResponseBodyTypedDict(TypedDict):
     r"""Memory successfully retrieved."""
 
     id: str
+    r"""Unique identifier for the memory. This is automatically generated by the system."""
     entity_id: str
-    r"""This property have been deprecated and moved to `_id`. Please refer to `_id` for future operations"""
+    r"""Customer provided entity ID for the memory. This is used to link the memory to a specific user/company/session/etc. Has to be unique within the memory store."""
     created: str
     updated: str
     store_id: str
@@ -53,6 +54,7 @@ class RetrieveMemoryResponseBody(BaseModel):
     r"""Memory successfully retrieved."""
 
     id: Annotated[str, pydantic.Field(alias="_id")]
+    r"""Unique identifier for the memory. This is automatically generated by the system."""
 
     entity_id: Annotated[
         str,
@@ -60,7 +62,7 @@ class RetrieveMemoryResponseBody(BaseModel):
             deprecated="warning: ** DEPRECATED ** - This will be removed in a future release, please migrate away from it as soon as possible."
         ),
     ]
-    r"""This property have been deprecated and moved to `_id`. Please refer to `_id` for future operations"""
+    r"""Customer provided entity ID for the memory. This is used to link the memory to a specific user/company/session/etc. Has to be unique within the memory store."""
 
     created: str
 

orq_ai_sdk/models/retrievetoolop.py

@@ -171,7 +171,7 @@ class RetrieveToolResponseBodyCodeExecutionTool(BaseModel):
     code_tool: RetrieveToolResponseBodyCodeTool
 
     id: Annotated[Optional[str], pydantic.Field(alias="_id")] = (
-        "tool_01KFDQW6FZM1GMF9GGSCQ23NQF"
+        "tool_01KFZBGG604CGG7H53H4C239C3"
     )
 
     display_name: Optional[str] = None
@@ -302,7 +302,7 @@ class RetrieveToolResponseBodyTools(BaseModel):
         RetrieveToolResponseBodyToolsSchema, pydantic.Field(alias="schema")
     ]
 
-    id: Optional[str] = "01KFDQW6FYH2DTV2TFN6WJ8KJB"
+    id: Optional[str] = "01KFZBGG5ZVG9PC6BRP0GD93XP"
 
     description: Optional[str] = None
 
@@ -433,7 +433,7 @@ class RetrieveToolResponseBodyMCPTool(BaseModel):
     mcp: RetrieveToolResponseBodyMcp
 
     id: Annotated[Optional[str], pydantic.Field(alias="_id")] = (
-        "tool_01KFDQW6FXHJK2ZBQ31SS9ERJT"
+        "tool_01KFZBGG5YBT50YCBTZ8XS31TR"
     )
 
     display_name: Optional[str] = None
@@ -734,7 +734,7 @@ class RetrieveToolResponseBodyHTTPTool(BaseModel):
     http: RetrieveToolResponseBodyHTTP
 
     id: Annotated[Optional[str], pydantic.Field(alias="_id")] = (
-        "tool_01KFDQW6FVKKJKZ74KTGPA6159"
+        "tool_01KFZBGG5WCA0DTA0WHVWVWDEK"
     )
 
     display_name: Optional[str] = None
@@ -929,7 +929,7 @@ class RetrieveToolResponseBodyJSONSchemaTool(BaseModel):
     json_schema: RetrieveToolResponseBodyJSONSchema
 
     id: Annotated[Optional[str], pydantic.Field(alias="_id")] = (
-        "tool_01KFDQW6FT6DTW2D8J75SWBZEK"
+        "tool_01KFZBGG5TYCZC00XA0DN9ZD6X"
     )
 
     display_name: Optional[str] = None
@@ -1128,7 +1128,7 @@ class RetrieveToolResponseBodyFunctionTool(BaseModel):
     function: RetrieveToolResponseBodyFunction
 
     id: Annotated[Optional[str], pydantic.Field(alias="_id")] = (
-        "tool_01KFDQW6FS48981SVSNKZ0XKT6"
+        "tool_01KFZBGG5REZQNNMMPKS6DVS8V"
     )
 
     display_name: Optional[str] = None

orq_ai_sdk/models/runagentop.py

@@ -388,9 +388,159 @@ class RunAgentModelConfigurationGuardrails(BaseModel):
     r"""Determines whether the guardrail runs on the input (user message) or output (model response)."""
 
 
+class RunAgentModelConfigurationFallbacksTypedDict(TypedDict):
+    model: str
+    r"""Fallback model identifier"""
+
+
+class RunAgentModelConfigurationFallbacks(BaseModel):
+    model: str
+    r"""Fallback model identifier"""
+
+
+class RunAgentModelConfigurationRetryTypedDict(TypedDict):
+    r"""Retry configuration for the request"""
+
+    count: NotRequired[float]
+    r"""Number of retry attempts (1-5)"""
+    on_codes: NotRequired[List[float]]
+    r"""HTTP status codes that trigger retry logic"""
+
+
+class RunAgentModelConfigurationRetry(BaseModel):
+    r"""Retry configuration for the request"""
+
+    count: Optional[float] = 3
+    r"""Number of retry attempts (1-5)"""
+
+    on_codes: Optional[List[float]] = None
+    r"""HTTP status codes that trigger retry logic"""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["count", "on_codes"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+RunAgentModelConfigurationType = Literal["exact_match",]
+
+
+class RunAgentModelConfigurationCacheTypedDict(TypedDict):
+    r"""Cache configuration for the request."""
+
+    type: RunAgentModelConfigurationType
+    ttl: NotRequired[float]
+    r"""Time to live for cached responses in seconds. Maximum 259200 seconds (3 days)."""
+
+
+class RunAgentModelConfigurationCache(BaseModel):
+    r"""Cache configuration for the request."""
+
+    type: RunAgentModelConfigurationType
+
+    ttl: Optional[float] = 1800
+    r"""Time to live for cached responses in seconds. Maximum 259200 seconds (3 days)."""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["ttl"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+RunAgentLoadBalancerType = Literal["weight_based",]
+
+
+class RunAgentLoadBalancerModelsTypedDict(TypedDict):
+    model: str
+    r"""Model identifier for load balancing"""
+    weight: NotRequired[float]
+    r"""Weight assigned to this model for load balancing"""
+
+
+class RunAgentLoadBalancerModels(BaseModel):
+    model: str
+    r"""Model identifier for load balancing"""
+
+    weight: Optional[float] = 0.5
+    r"""Weight assigned to this model for load balancing"""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["weight"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+class RunAgentLoadBalancer1TypedDict(TypedDict):
+    type: RunAgentLoadBalancerType
+    models: List[RunAgentLoadBalancerModelsTypedDict]
+
+
+class RunAgentLoadBalancer1(BaseModel):
+    type: RunAgentLoadBalancerType
+
+    models: List[RunAgentLoadBalancerModels]
+
+
+RunAgentModelConfigurationLoadBalancerTypedDict = RunAgentLoadBalancer1TypedDict
+r"""Load balancer configuration for the request."""
+
+
+RunAgentModelConfigurationLoadBalancer = RunAgentLoadBalancer1
+r"""Load balancer configuration for the request."""
+
+
+class RunAgentModelConfigurationTimeoutTypedDict(TypedDict):
+    r"""Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured."""
+
+    call_timeout: float
+    r"""Timeout value in milliseconds"""
+
+
+class RunAgentModelConfigurationTimeout(BaseModel):
+    r"""Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured."""
+
+    call_timeout: float
+    r"""Timeout value in milliseconds"""
+
+
 class RunAgentModelConfigurationParametersTypedDict(TypedDict):
     r"""Model behavior parameters that control how the model generates responses. Common parameters: `temperature` (0-1, randomness), `max_completion_tokens` (max output length), `top_p` (sampling diversity). Advanced: `frequency_penalty`, `presence_penalty`, `response_format` (JSON/structured), `reasoning_effort`, `seed` (reproducibility). Support varies by model - consult AI Gateway documentation."""
 
+    name: NotRequired[str]
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
     audio: NotRequired[Nullable[RunAgentModelConfigurationAudioTypedDict]]
     r"""Parameters for audio output. Required when audio output is requested with modalities: [\"audio\"]. Learn more."""
     frequency_penalty: NotRequired[Nullable[float]]
@@ -447,11 +597,24 @@ class RunAgentModelConfigurationParametersTypedDict(TypedDict):
     r"""Output types that you would like the model to generate. Most models are capable of generating text, which is the default: [\"text\"]. The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use: [\"text\", \"audio\"]."""
     guardrails: NotRequired[List[RunAgentModelConfigurationGuardrailsTypedDict]]
     r"""A list of guardrails to apply to the request."""
+    fallbacks: NotRequired[List[RunAgentModelConfigurationFallbacksTypedDict]]
+    r"""Array of fallback models to use if primary model fails"""
+    retry: NotRequired[RunAgentModelConfigurationRetryTypedDict]
+    r"""Retry configuration for the request"""
+    cache: NotRequired[RunAgentModelConfigurationCacheTypedDict]
+    r"""Cache configuration for the request."""
+    load_balancer: NotRequired[RunAgentModelConfigurationLoadBalancerTypedDict]
+    r"""Load balancer configuration for the request."""
+    timeout: NotRequired[RunAgentModelConfigurationTimeoutTypedDict]
+    r"""Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured."""
 
 
 class RunAgentModelConfigurationParameters(BaseModel):
     r"""Model behavior parameters that control how the model generates responses. Common parameters: `temperature` (0-1, randomness), `max_completion_tokens` (max output length), `top_p` (sampling diversity). Advanced: `frequency_penalty`, `presence_penalty`, `response_format` (JSON/structured), `reasoning_effort`, `seed` (reproducibility). Support varies by model - consult AI Gateway documentation."""
 
+    name: Optional[str] = None
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
+
     audio: OptionalNullable[RunAgentModelConfigurationAudio] = UNSET
     r"""Parameters for audio output. Required when audio output is requested with modalities: [\"audio\"]. Learn more."""
 
@@ -528,10 +691,26 @@ class RunAgentModelConfigurationParameters(BaseModel):
     guardrails: Optional[List[RunAgentModelConfigurationGuardrails]] = None
     r"""A list of guardrails to apply to the request."""
 
+    fallbacks: Optional[List[RunAgentModelConfigurationFallbacks]] = None
+    r"""Array of fallback models to use if primary model fails"""
+
+    retry: Optional[RunAgentModelConfigurationRetry] = None
+    r"""Retry configuration for the request"""
+
+    cache: Optional[RunAgentModelConfigurationCache] = None
+    r"""Cache configuration for the request."""
+
+    load_balancer: Optional[RunAgentModelConfigurationLoadBalancer] = None
+    r"""Load balancer configuration for the request."""
+
+    timeout: Optional[RunAgentModelConfigurationTimeout] = None
+    r"""Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured."""
+
     @model_serializer(mode="wrap")
     def serialize_model(self, handler):
         optional_fields = set(
             [
+                "name",
                 "audio",
                 "frequency_penalty",
                 "max_tokens",
@@ -554,6 +733,11 @@ class RunAgentModelConfigurationParameters(BaseModel):
                 "parallel_tool_calls",
                 "modalities",
                 "guardrails",
+                "fallbacks",
+                "retry",
+                "cache",
+                "load_balancer",
+                "timeout",
             ]
         )
         nullable_fields = set(
@@ -597,7 +781,7 @@ class RunAgentModelConfigurationParameters(BaseModel):
         return m
 
 
-class RunAgentModelConfigurationRetryTypedDict(TypedDict):
+class RunAgentModelConfigurationAgentsRetryTypedDict(TypedDict):
     r"""Retry configuration for model requests. Retries are triggered for specific HTTP status codes (e.g., 500, 429, 502, 503, 504). Supports configurable retry count (1-5) and custom status codes."""
 
     count: NotRequired[float]
@@ -606,7 +790,7 @@ class RunAgentModelConfigurationRetryTypedDict(TypedDict):
     r"""HTTP status codes that trigger retry logic"""
 
 
-class RunAgentModelConfigurationRetry(BaseModel):
+class RunAgentModelConfigurationAgentsRetry(BaseModel):
     r"""Retry configuration for model requests. Retries are triggered for specific HTTP status codes (e.g., 500, 429, 502, 503, 504). Supports configurable retry count (1-5) and custom status codes."""
 
     count: Optional[float] = 3
@@ -642,7 +826,7 @@ class RunAgentModelConfiguration2TypedDict(TypedDict):
     r"""A model ID string (e.g., `openai/gpt-4o` or `anthropic/claude-haiku-4-5-20251001`). Only models that support tool calling can be used with agents."""
     parameters: NotRequired[RunAgentModelConfigurationParametersTypedDict]
     r"""Model behavior parameters that control how the model generates responses. Common parameters: `temperature` (0-1, randomness), `max_completion_tokens` (max output length), `top_p` (sampling diversity). Advanced: `frequency_penalty`, `presence_penalty`, `response_format` (JSON/structured), `reasoning_effort`, `seed` (reproducibility). Support varies by model - consult AI Gateway documentation."""
-    retry: NotRequired[RunAgentModelConfigurationRetryTypedDict]
+    retry: NotRequired[RunAgentModelConfigurationAgentsRetryTypedDict]
     r"""Retry configuration for model requests. Retries are triggered for specific HTTP status codes (e.g., 500, 429, 502, 503, 504). Supports configurable retry count (1-5) and custom status codes."""
 
 
@@ -658,7 +842,7 @@ class RunAgentModelConfiguration2(BaseModel):
     parameters: Optional[RunAgentModelConfigurationParameters] = None
     r"""Model behavior parameters that control how the model generates responses. Common parameters: `temperature` (0-1, randomness), `max_completion_tokens` (max output length), `top_p` (sampling diversity). Advanced: `frequency_penalty`, `presence_penalty`, `response_format` (JSON/structured), `reasoning_effort`, `seed` (reproducibility). Support varies by model - consult AI Gateway documentation."""
 
-    retry: Optional[RunAgentModelConfigurationRetry] = None
+    retry: Optional[RunAgentModelConfigurationAgentsRetry] = None
     r"""Retry configuration for model requests. Retries are triggered for specific HTTP status codes (e.g., 500, 429, 502, 503, 504). Supports configurable retry count (1-5) and custom status codes."""
 
     @model_serializer(mode="wrap")
@@ -1050,9 +1234,161 @@ class RunAgentFallbackModelConfigurationGuardrails(BaseModel):
     r"""Determines whether the guardrail runs on the input (user message) or output (model response)."""
 
 
+class RunAgentFallbackModelConfigurationFallbacksTypedDict(TypedDict):
+    model: str
+    r"""Fallback model identifier"""
+
+
+class RunAgentFallbackModelConfigurationFallbacks(BaseModel):
+    model: str
+    r"""Fallback model identifier"""
+
+
+class RunAgentFallbackModelConfigurationRetryTypedDict(TypedDict):
+    r"""Retry configuration for the request"""
+
+    count: NotRequired[float]
+    r"""Number of retry attempts (1-5)"""
+    on_codes: NotRequired[List[float]]
+    r"""HTTP status codes that trigger retry logic"""
+
+
+class RunAgentFallbackModelConfigurationRetry(BaseModel):
+    r"""Retry configuration for the request"""
+
+    count: Optional[float] = 3
+    r"""Number of retry attempts (1-5)"""
+
+    on_codes: Optional[List[float]] = None
+    r"""HTTP status codes that trigger retry logic"""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["count", "on_codes"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+RunAgentFallbackModelConfigurationType = Literal["exact_match",]
+
+
+class RunAgentFallbackModelConfigurationCacheTypedDict(TypedDict):
+    r"""Cache configuration for the request."""
+
+    type: RunAgentFallbackModelConfigurationType
+    ttl: NotRequired[float]
+    r"""Time to live for cached responses in seconds. Maximum 259200 seconds (3 days)."""
+
+
+class RunAgentFallbackModelConfigurationCache(BaseModel):
+    r"""Cache configuration for the request."""
+
+    type: RunAgentFallbackModelConfigurationType
+
+    ttl: Optional[float] = 1800
+    r"""Time to live for cached responses in seconds. Maximum 259200 seconds (3 days)."""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["ttl"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+RunAgentLoadBalancerAgentsType = Literal["weight_based",]
+
+
+class RunAgentLoadBalancerAgentsModelsTypedDict(TypedDict):
+    model: str
+    r"""Model identifier for load balancing"""
+    weight: NotRequired[float]
+    r"""Weight assigned to this model for load balancing"""
+
+
+class RunAgentLoadBalancerAgentsModels(BaseModel):
+    model: str
+    r"""Model identifier for load balancing"""
+
+    weight: Optional[float] = 0.5
+    r"""Weight assigned to this model for load balancing"""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["weight"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+class RunAgentLoadBalancerAgents1TypedDict(TypedDict):
+    type: RunAgentLoadBalancerAgentsType
+    models: List[RunAgentLoadBalancerAgentsModelsTypedDict]
+
+
+class RunAgentLoadBalancerAgents1(BaseModel):
+    type: RunAgentLoadBalancerAgentsType
+
+    models: List[RunAgentLoadBalancerAgentsModels]
+
+
+RunAgentFallbackModelConfigurationLoadBalancerTypedDict = (
+    RunAgentLoadBalancerAgents1TypedDict
+)
+r"""Load balancer configuration for the request."""
+
+
+RunAgentFallbackModelConfigurationLoadBalancer = RunAgentLoadBalancerAgents1
+r"""Load balancer configuration for the request."""
+
+
+class RunAgentFallbackModelConfigurationTimeoutTypedDict(TypedDict):
+    r"""Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured."""
+
+    call_timeout: float
+    r"""Timeout value in milliseconds"""
+
+
+class RunAgentFallbackModelConfigurationTimeout(BaseModel):
+    r"""Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured."""
+
+    call_timeout: float
+    r"""Timeout value in milliseconds"""
+
+
 class RunAgentFallbackModelConfigurationParametersTypedDict(TypedDict):
     r"""Optional model parameters specific to this fallback model. Overrides primary model parameters if this fallback is used."""
 
+    name: NotRequired[str]
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
     audio: NotRequired[Nullable[RunAgentFallbackModelConfigurationAudioTypedDict]]
     r"""Parameters for audio output. Required when audio output is requested with modalities: [\"audio\"]. Learn more."""
     frequency_penalty: NotRequired[Nullable[float]]
@@ -1113,11 +1449,24 @@ class RunAgentFallbackModelConfigurationParametersTypedDict(TypedDict):
     r"""Output types that you would like the model to generate. Most models are capable of generating text, which is the default: [\"text\"]. The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use: [\"text\", \"audio\"]."""
     guardrails: NotRequired[List[RunAgentFallbackModelConfigurationGuardrailsTypedDict]]
     r"""A list of guardrails to apply to the request."""
+    fallbacks: NotRequired[List[RunAgentFallbackModelConfigurationFallbacksTypedDict]]
+    r"""Array of fallback models to use if primary model fails"""
+    retry: NotRequired[RunAgentFallbackModelConfigurationRetryTypedDict]
+    r"""Retry configuration for the request"""
+    cache: NotRequired[RunAgentFallbackModelConfigurationCacheTypedDict]
+    r"""Cache configuration for the request."""
+    load_balancer: NotRequired[RunAgentFallbackModelConfigurationLoadBalancerTypedDict]
+    r"""Load balancer configuration for the request."""
+    timeout: NotRequired[RunAgentFallbackModelConfigurationTimeoutTypedDict]
+    r"""Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured."""
 
 
 class RunAgentFallbackModelConfigurationParameters(BaseModel):
     r"""Optional model parameters specific to this fallback model. Overrides primary model parameters if this fallback is used."""
 
+    name: Optional[str] = None
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
+
     audio: OptionalNullable[RunAgentFallbackModelConfigurationAudio] = UNSET
     r"""Parameters for audio output. Required when audio output is requested with modalities: [\"audio\"]. Learn more."""
 
@@ -1198,10 +1547,26 @@ class RunAgentFallbackModelConfigurationParameters(BaseModel):
     guardrails: Optional[List[RunAgentFallbackModelConfigurationGuardrails]] = None
     r"""A list of guardrails to apply to the request."""
 
+    fallbacks: Optional[List[RunAgentFallbackModelConfigurationFallbacks]] = None
+    r"""Array of fallback models to use if primary model fails"""
+
+    retry: Optional[RunAgentFallbackModelConfigurationRetry] = None
+    r"""Retry configuration for the request"""
+
+    cache: Optional[RunAgentFallbackModelConfigurationCache] = None
+    r"""Cache configuration for the request."""
+
+    load_balancer: Optional[RunAgentFallbackModelConfigurationLoadBalancer] = None
+    r"""Load balancer configuration for the request."""
+
+    timeout: Optional[RunAgentFallbackModelConfigurationTimeout] = None
+    r"""Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured."""
+
     @model_serializer(mode="wrap")
     def serialize_model(self, handler):
         optional_fields = set(
             [
+                "name",
                 "audio",
                 "frequency_penalty",
                 "max_tokens",
@@ -1224,6 +1589,11 @@ class RunAgentFallbackModelConfigurationParameters(BaseModel):
                 "parallel_tool_calls",
                 "modalities",
                 "guardrails",
+                "fallbacks",
+                "retry",
+                "cache",
+                "load_balancer",
+                "timeout",
             ]
         )
         nullable_fields = set(
@@ -1267,7 +1637,7 @@ class RunAgentFallbackModelConfigurationParameters(BaseModel):
         return m
 
 
-class RunAgentFallbackModelConfigurationRetryTypedDict(TypedDict):
+class RunAgentFallbackModelConfigurationAgentsRetryTypedDict(TypedDict):
     r"""Retry configuration for this fallback model. Allows customizing retry count (1-5) and HTTP status codes that trigger retries."""
 
     count: NotRequired[float]
@@ -1276,7 +1646,7 @@ class RunAgentFallbackModelConfigurationRetryTypedDict(TypedDict):
     r"""HTTP status codes that trigger retry logic"""
 
 
-class RunAgentFallbackModelConfigurationRetry(BaseModel):
+class RunAgentFallbackModelConfigurationAgentsRetry(BaseModel):
     r"""Retry configuration for this fallback model. Allows customizing retry count (1-5) and HTTP status codes that trigger retries."""
 
     count: Optional[float] = 3
@@ -1309,7 +1679,7 @@ class RunAgentFallbackModelConfiguration2TypedDict(TypedDict):
     r"""A fallback model ID string. Must support tool calling."""
     parameters: NotRequired[RunAgentFallbackModelConfigurationParametersTypedDict]
     r"""Optional model parameters specific to this fallback model. Overrides primary model parameters if this fallback is used."""
-    retry: NotRequired[RunAgentFallbackModelConfigurationRetryTypedDict]
+    retry: NotRequired[RunAgentFallbackModelConfigurationAgentsRetryTypedDict]
     r"""Retry configuration for this fallback model. Allows customizing retry count (1-5) and HTTP status codes that trigger retries."""
 
 
@@ -1322,7 +1692,7 @@ class RunAgentFallbackModelConfiguration2(BaseModel):
     parameters: Optional[RunAgentFallbackModelConfigurationParameters] = None
     r"""Optional model parameters specific to this fallback model. Overrides primary model parameters if this fallback is used."""
 
-    retry: Optional[RunAgentFallbackModelConfigurationRetry] = None
+    retry: Optional[RunAgentFallbackModelConfigurationAgentsRetry] = None
     r"""Retry configuration for this fallback model. Allows customizing retry count (1-5) and HTTP status codes that trigger retries."""
 
     @model_serializer(mode="wrap")
@@ -1723,7 +2093,7 @@ class RunAgentAgentToolInputRunTools(BaseModel):
 
     schema_: Annotated[AgentToolInputRunSchema, pydantic.Field(alias="schema")]
 
-    id: Optional[str] = "01KFDQW5XYHWR61SGS16YJF3BC"
+    id: Optional[str] = "01KFZBGFPMXP6AK4GBEEHQJY9P"
 
     description: Optional[str] = None