platform-api-python-client 4.9.0__py3-none-any.whl → 4.10.0__py3-none-any.whl

platform_api_python_client/models/config_file_mount.py

@@ -0,0 +1,99 @@
+# coding: utf-8
+
+"""
+    Platform External API
+
+    No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
+
+    The version of the OpenAPI document: 0.1.0
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+from __future__ import annotations
+import pprint
+import re  # noqa: F401
+import json
+
+from pydantic import BaseModel, ConfigDict, Field, field_validator
+from typing import Any, ClassVar, Dict, List
+from typing_extensions import Annotated
+from typing import Optional, Set
+from typing_extensions import Self
+
+class ConfigFileMount(BaseModel):
+    """
+    ConfigFileMount
+    """ # noqa: E501
+    filename: Annotated[str, Field(min_length=1, strict=True, max_length=253)]
+    mount_path: Annotated[str, Field(min_length=1, strict=True)]
+    content: Annotated[str, Field(min_length=1, strict=True)]
+    __properties: ClassVar[List[str]] = ["filename", "mount_path", "content"]
+
+    @field_validator('filename')
+    def filename_validate_regular_expression(cls, value):
+        """Validates the regular expression"""
+        if not re.match(r"^[a-zA-Z0-9._-]+$", value):
+            raise ValueError(r"must validate the regular expression /^[a-zA-Z0-9._-]+$/")
+        return value
+
+    model_config = ConfigDict(
+        populate_by_name=True,
+        validate_assignment=True,
+        protected_namespaces=(),
+    )
+
+
+    def to_str(self) -> str:
+        """Returns the string representation of the model using alias"""
+        return pprint.pformat(self.model_dump(by_alias=True))
+
+    def to_json(self) -> str:
+        """Returns the JSON representation of the model using alias"""
+        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
+        return json.dumps(self.to_dict())
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Optional[Self]:
+        """Create an instance of ConfigFileMount from a JSON string"""
+        return cls.from_dict(json.loads(json_str))
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Return the dictionary representation of the model using alias.
+
+        This has the following differences from calling pydantic's
+        `self.model_dump(by_alias=True)`:
+
+        * `None` is only added to the output dict for nullable fields that
+          were set at model initialization. Other fields with value `None`
+          are ignored.
+        """
+        excluded_fields: Set[str] = set([
+        ])
+
+        _dict = self.model_dump(
+            by_alias=True,
+            exclude=excluded_fields,
+            exclude_none=True,
+        )
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of ConfigFileMount from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "filename": obj.get("filename"),
+            "mount_path": obj.get("mount_path"),
+            "content": obj.get("content")
+        })
+        return _obj
+
+

platform_api_python_client/models/create_c_serve_v3_deployment_request.py

@@ -43,10 +43,12 @@ class CreateCServeV3DeploymentRequest(BaseModel):
     max_replicas: StrictInt
     initial_replicas: Optional[StrictInt] = None
     concurrency: Optional[StrictInt] = None
+    cooldown_period: Optional[StrictInt] = None
     env_vars: Optional[Dict[str, StrictStr]] = None
     enable_logging: Optional[StrictBool] = True
     enable_node_model_cache: Optional[StrictBool] = False
-    __properties: ClassVar[List[str]] = ["max_surge", "max_unavailable", "name", "cluster_id", "hardware_instance_id", "user_annotations", "recipe", "cserve_version", "hf_token", "endpoint_bearer_token", "endpoint_certificate_authority", "min_replicas", "max_replicas", "initial_replicas", "concurrency", "env_vars", "enable_logging", "enable_node_model_cache"]
+    session_affinity: Optional[StrictBool] = Field(default=False, description="Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state.")
+    __properties: ClassVar[List[str]] = ["max_surge", "max_unavailable", "name", "cluster_id", "hardware_instance_id", "user_annotations", "recipe", "cserve_version", "hf_token", "endpoint_bearer_token", "endpoint_certificate_authority", "min_replicas", "max_replicas", "initial_replicas", "concurrency", "cooldown_period", "env_vars", "enable_logging", "enable_node_model_cache", "session_affinity"]
 
     @field_validator('name')
     def name_validate_regular_expression(cls, value):
@@ -142,6 +144,11 @@ class CreateCServeV3DeploymentRequest(BaseModel):
         if self.concurrency is None and "concurrency" in self.model_fields_set:
             _dict['concurrency'] = None
 
+        # set to None if cooldown_period (nullable) is None
+        # and model_fields_set contains the field
+        if self.cooldown_period is None and "cooldown_period" in self.model_fields_set:
+            _dict['cooldown_period'] = None
+
         return _dict
 
     @classmethod
@@ -169,9 +176,11 @@ class CreateCServeV3DeploymentRequest(BaseModel):
             "max_replicas": obj.get("max_replicas"),
             "initial_replicas": obj.get("initial_replicas"),
             "concurrency": obj.get("concurrency"),
+            "cooldown_period": obj.get("cooldown_period"),
             "env_vars": obj.get("env_vars"),
             "enable_logging": obj.get("enable_logging") if obj.get("enable_logging") is not None else True,
-            "enable_node_model_cache": obj.get("enable_node_model_cache") if obj.get("enable_node_model_cache") is not None else False
+            "enable_node_model_cache": obj.get("enable_node_model_cache") if obj.get("enable_node_model_cache") is not None else False,
+            "session_affinity": obj.get("session_affinity") if obj.get("session_affinity") is not None else False
         })
         return _obj
 

platform_api_python_client/models/create_inference_v3_deployment_request.py

@@ -21,6 +21,7 @@ from pydantic import BaseModel, ConfigDict, Field, StrictBool, StrictInt, Strict
 from typing import Any, ClassVar, Dict, List, Optional
 from typing_extensions import Annotated
 from platform_api_python_client.models.backend_protocol import BackendProtocol
+from platform_api_python_client.models.config_file_mount import ConfigFileMount
 from platform_api_python_client.models.image_pull_secret_credentials import ImagePullSecretCredentials
 from typing import Optional, Set
 from typing_extensions import Self
@@ -42,14 +43,18 @@ class CreateInferenceV3DeploymentRequest(BaseModel):
     max_replicas: StrictInt
     initial_replicas: Optional[StrictInt] = None
     concurrency: Optional[StrictInt] = None
+    cooldown_period: Optional[StrictInt] = None
     healthcheck: Optional[StrictStr] = None
     env_vars: Optional[Dict[str, StrictStr]] = None
     command: Optional[StrictStr] = None
     endpoint_bearer_token: Optional[StrictStr] = None
     endpoint_certificate_authority: Optional[StrictStr] = None
+    hf_token: Optional[StrictStr] = None
     backend_protocol: Optional[BackendProtocol] = None
     enable_logging: Optional[StrictBool] = False
-    __properties: ClassVar[List[str]] = ["max_surge", "max_unavailable", "name", "cluster_id", "hardware_instance_id", "user_annotations", "image_url", "image_pull_secret_credentials", "port", "min_replicas", "max_replicas", "initial_replicas", "concurrency", "healthcheck", "env_vars", "command", "endpoint_bearer_token", "endpoint_certificate_authority", "backend_protocol", "enable_logging"]
+    session_affinity: Optional[StrictBool] = Field(default=False, description="Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state.")
+    config_file: Optional[ConfigFileMount] = None
+    __properties: ClassVar[List[str]] = ["max_surge", "max_unavailable", "name", "cluster_id", "hardware_instance_id", "user_annotations", "image_url", "image_pull_secret_credentials", "port", "min_replicas", "max_replicas", "initial_replicas", "concurrency", "cooldown_period", "healthcheck", "env_vars", "command", "endpoint_bearer_token", "endpoint_certificate_authority", "hf_token", "backend_protocol", "enable_logging", "session_affinity", "config_file"]
 
     @field_validator('name')
     def name_validate_regular_expression(cls, value):
@@ -100,6 +105,9 @@ class CreateInferenceV3DeploymentRequest(BaseModel):
         # override the default output from pydantic by calling `to_dict()` of image_pull_secret_credentials
         if self.image_pull_secret_credentials:
             _dict['image_pull_secret_credentials'] = self.image_pull_secret_credentials.to_dict()
+        # override the default output from pydantic by calling `to_dict()` of config_file
+        if self.config_file:
+            _dict['config_file'] = self.config_file.to_dict()
         # set to None if max_surge (nullable) is None
         # and model_fields_set contains the field
         if self.max_surge is None and "max_surge" in self.model_fields_set:
@@ -130,6 +138,11 @@ class CreateInferenceV3DeploymentRequest(BaseModel):
         if self.concurrency is None and "concurrency" in self.model_fields_set:
             _dict['concurrency'] = None
 
+        # set to None if cooldown_period (nullable) is None
+        # and model_fields_set contains the field
+        if self.cooldown_period is None and "cooldown_period" in self.model_fields_set:
+            _dict['cooldown_period'] = None
+
         # set to None if healthcheck (nullable) is None
         # and model_fields_set contains the field
         if self.healthcheck is None and "healthcheck" in self.model_fields_set:
@@ -155,6 +168,16 @@ class CreateInferenceV3DeploymentRequest(BaseModel):
         if self.endpoint_certificate_authority is None and "endpoint_certificate_authority" in self.model_fields_set:
             _dict['endpoint_certificate_authority'] = None
 
+        # set to None if hf_token (nullable) is None
+        # and model_fields_set contains the field
+        if self.hf_token is None and "hf_token" in self.model_fields_set:
+            _dict['hf_token'] = None
+
+        # set to None if config_file (nullable) is None
+        # and model_fields_set contains the field
+        if self.config_file is None and "config_file" in self.model_fields_set:
+            _dict['config_file'] = None
+
         return _dict
 
     @classmethod
@@ -180,13 +203,17 @@ class CreateInferenceV3DeploymentRequest(BaseModel):
             "max_replicas": obj.get("max_replicas"),
             "initial_replicas": obj.get("initial_replicas"),
             "concurrency": obj.get("concurrency"),
+            "cooldown_period": obj.get("cooldown_period"),
             "healthcheck": obj.get("healthcheck"),
             "env_vars": obj.get("env_vars"),
             "command": obj.get("command"),
             "endpoint_bearer_token": obj.get("endpoint_bearer_token"),
             "endpoint_certificate_authority": obj.get("endpoint_certificate_authority"),
+            "hf_token": obj.get("hf_token"),
             "backend_protocol": obj.get("backend_protocol"),
-            "enable_logging": obj.get("enable_logging") if obj.get("enable_logging") is not None else False
+            "enable_logging": obj.get("enable_logging") if obj.get("enable_logging") is not None else False,
+            "session_affinity": obj.get("session_affinity") if obj.get("session_affinity") is not None else False,
+            "config_file": ConfigFileMount.from_dict(obj["config_file"]) if obj.get("config_file") is not None else None
         })
         return _obj
 

platform_api_python_client/models/create_job_deployment_request.py

@@ -0,0 +1,139 @@
+# coding: utf-8
+
+"""
+    Platform External API
+
+    No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
+
+    The version of the OpenAPI document: 0.1.0
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+from __future__ import annotations
+import pprint
+import re  # noqa: F401
+import json
+
+from pydantic import BaseModel, ConfigDict, Field, StrictBool, StrictInt, StrictStr, field_validator
+from typing import Any, ClassVar, Dict, List, Optional
+from typing_extensions import Annotated
+from platform_api_python_client.models.image_pull_secret_credentials import ImagePullSecretCredentials
+from typing import Optional, Set
+from typing_extensions import Self
+
+class CreateJobDeploymentRequest(BaseModel):
+    """
+    CreateJobDeploymentRequest
+    """ # noqa: E501
+    name: Annotated[str, Field(min_length=1, strict=True, max_length=20)]
+    cluster_id: StrictInt
+    hardware_instance_id: StrictInt
+    user_annotations: Optional[Dict[str, StrictStr]] = None
+    image_url: StrictStr
+    image_pull_secret_credentials: Optional[ImagePullSecretCredentials] = None
+    env_vars: Optional[Dict[str, StrictStr]] = None
+    command: Optional[StrictStr] = None
+    completions: Optional[StrictInt] = 1
+    parallelism: Optional[StrictInt] = 1
+    enable_logging: Optional[StrictBool] = True
+    __properties: ClassVar[List[str]] = ["name", "cluster_id", "hardware_instance_id", "user_annotations", "image_url", "image_pull_secret_credentials", "env_vars", "command", "completions", "parallelism", "enable_logging"]
+
+    @field_validator('name')
+    def name_validate_regular_expression(cls, value):
+        """Validates the regular expression"""
+        if not re.match(r"^[a-z][a-z0-9-]*$", value):
+            raise ValueError(r"must validate the regular expression /^[a-z][a-z0-9-]*$/")
+        return value
+
+    model_config = ConfigDict(
+        populate_by_name=True,
+        validate_assignment=True,
+        protected_namespaces=(),
+    )
+
+
+    def to_str(self) -> str:
+        """Returns the string representation of the model using alias"""
+        return pprint.pformat(self.model_dump(by_alias=True))
+
+    def to_json(self) -> str:
+        """Returns the JSON representation of the model using alias"""
+        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
+        return json.dumps(self.to_dict())
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Optional[Self]:
+        """Create an instance of CreateJobDeploymentRequest from a JSON string"""
+        return cls.from_dict(json.loads(json_str))
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Return the dictionary representation of the model using alias.
+
+        This has the following differences from calling pydantic's
+        `self.model_dump(by_alias=True)`:
+
+        * `None` is only added to the output dict for nullable fields that
+          were set at model initialization. Other fields with value `None`
+          are ignored.
+        """
+        excluded_fields: Set[str] = set([
+        ])
+
+        _dict = self.model_dump(
+            by_alias=True,
+            exclude=excluded_fields,
+            exclude_none=True,
+        )
+        # override the default output from pydantic by calling `to_dict()` of image_pull_secret_credentials
+        if self.image_pull_secret_credentials:
+            _dict['image_pull_secret_credentials'] = self.image_pull_secret_credentials.to_dict()
+        # set to None if user_annotations (nullable) is None
+        # and model_fields_set contains the field
+        if self.user_annotations is None and "user_annotations" in self.model_fields_set:
+            _dict['user_annotations'] = None
+
+        # set to None if image_pull_secret_credentials (nullable) is None
+        # and model_fields_set contains the field
+        if self.image_pull_secret_credentials is None and "image_pull_secret_credentials" in self.model_fields_set:
+            _dict['image_pull_secret_credentials'] = None
+
+        # set to None if env_vars (nullable) is None
+        # and model_fields_set contains the field
+        if self.env_vars is None and "env_vars" in self.model_fields_set:
+            _dict['env_vars'] = None
+
+        # set to None if command (nullable) is None
+        # and model_fields_set contains the field
+        if self.command is None and "command" in self.model_fields_set:
+            _dict['command'] = None
+
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of CreateJobDeploymentRequest from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "name": obj.get("name"),
+            "cluster_id": obj.get("cluster_id"),
+            "hardware_instance_id": obj.get("hardware_instance_id"),
+            "user_annotations": obj.get("user_annotations"),
+            "image_url": obj.get("image_url"),
+            "image_pull_secret_credentials": ImagePullSecretCredentials.from_dict(obj["image_pull_secret_credentials"]) if obj.get("image_pull_secret_credentials") is not None else None,
+            "env_vars": obj.get("env_vars"),
+            "command": obj.get("command"),
+            "completions": obj.get("completions") if obj.get("completions") is not None else 1,
+            "parallelism": obj.get("parallelism") if obj.get("parallelism") is not None else 1,
+            "enable_logging": obj.get("enable_logging") if obj.get("enable_logging") is not None else True
+        })
+        return _obj
+
+

platform_api_python_client/models/create_job_deployment_response.py

@@ -0,0 +1,92 @@
+# coding: utf-8
+
+"""
+    Platform External API
+
+    No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
+
+    The version of the OpenAPI document: 0.1.0
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+from __future__ import annotations
+import pprint
+import re  # noqa: F401
+import json
+
+from datetime import datetime
+from pydantic import BaseModel, ConfigDict, StrictInt, StrictStr
+from typing import Any, ClassVar, Dict, List
+from typing import Optional, Set
+from typing_extensions import Self
+
+class CreateJobDeploymentResponse(BaseModel):
+    """
+    CreateJobDeploymentResponse
+    """ # noqa: E501
+    id: StrictInt
+    created_at: datetime
+    endpoint_url: StrictStr
+    __properties: ClassVar[List[str]] = ["id", "created_at", "endpoint_url"]
+
+    model_config = ConfigDict(
+        populate_by_name=True,
+        validate_assignment=True,
+        protected_namespaces=(),
+    )
+
+
+    def to_str(self) -> str:
+        """Returns the string representation of the model using alias"""
+        return pprint.pformat(self.model_dump(by_alias=True))
+
+    def to_json(self) -> str:
+        """Returns the JSON representation of the model using alias"""
+        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
+        return json.dumps(self.to_dict())
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Optional[Self]:
+        """Create an instance of CreateJobDeploymentResponse from a JSON string"""
+        return cls.from_dict(json.loads(json_str))
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Return the dictionary representation of the model using alias.
+
+        This has the following differences from calling pydantic's
+        `self.model_dump(by_alias=True)`:
+
+        * `None` is only added to the output dict for nullable fields that
+          were set at model initialization. Other fields with value `None`
+          are ignored.
+        """
+        excluded_fields: Set[str] = set([
+        ])
+
+        _dict = self.model_dump(
+            by_alias=True,
+            exclude=excluded_fields,
+            exclude_none=True,
+        )
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of CreateJobDeploymentResponse from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "id": obj.get("id"),
+            "created_at": obj.get("created_at"),
+            "endpoint_url": obj.get("endpoint_url")
+        })
+        return _obj
+
+

platform_api_python_client/models/deployment_type.py

@@ -38,6 +38,7 @@ class DeploymentType(str, Enum):
     CSERVE_V3 = 'cserve_v3'
     DEPLOYMENT = 'deployment'
     RAG = 'rag'
+    JOB = 'job'
 
     @classmethod
     def from_json(cls, json_str: str) -> Self:

platform_api_python_client/models/get_c_serve_v3_deployment_response.py

@@ -18,7 +18,7 @@ import re  # noqa: F401
 import json
 
 from datetime import datetime
-from pydantic import BaseModel, ConfigDict, StrictBool, StrictInt, StrictStr
+from pydantic import BaseModel, ConfigDict, Field, StrictBool, StrictInt, StrictStr
 from typing import Any, ClassVar, Dict, List, Optional
 from platform_api_python_client.models.c_serve_v2_recipe import CServeV2Recipe
 from platform_api_python_client.models.deployment_status import DeploymentStatus
@@ -50,10 +50,12 @@ class GetCServeV3DeploymentResponse(BaseModel):
     endpoint_certificate_authority: Optional[StrictStr] = None
     endpoint_bearer_token: Optional[StrictStr] = None
     concurrency: Optional[StrictInt] = None
+    cooldown_period: Optional[StrictInt] = 1800
     env_vars: Optional[Dict[str, StrictStr]] = None
     enable_logging: Optional[StrictBool] = True
     enable_node_model_cache: Optional[StrictBool] = False
-    __properties: ClassVar[List[str]] = ["creator_email", "cluster_id", "id", "name", "endpoint_url", "image_url", "type", "status", "created_at", "hardware_instance_id", "revision_number", "user_annotations", "recipe", "cserve_version", "min_replicas", "max_replicas", "initial_replicas", "endpoint_certificate_authority", "endpoint_bearer_token", "concurrency", "env_vars", "enable_logging", "enable_node_model_cache"]
+    session_affinity: Optional[StrictBool] = Field(default=False, description="Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state.")
+    __properties: ClassVar[List[str]] = ["creator_email", "cluster_id", "id", "name", "endpoint_url", "image_url", "type", "status", "created_at", "hardware_instance_id", "revision_number", "user_annotations", "recipe", "cserve_version", "min_replicas", "max_replicas", "initial_replicas", "endpoint_certificate_authority", "endpoint_bearer_token", "concurrency", "cooldown_period", "env_vars", "enable_logging", "enable_node_model_cache", "session_affinity"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -164,9 +166,11 @@ class GetCServeV3DeploymentResponse(BaseModel):
             "endpoint_certificate_authority": obj.get("endpoint_certificate_authority"),
             "endpoint_bearer_token": obj.get("endpoint_bearer_token"),
             "concurrency": obj.get("concurrency"),
+            "cooldown_period": obj.get("cooldown_period") if obj.get("cooldown_period") is not None else 1800,
             "env_vars": obj.get("env_vars"),
             "enable_logging": obj.get("enable_logging") if obj.get("enable_logging") is not None else True,
-            "enable_node_model_cache": obj.get("enable_node_model_cache") if obj.get("enable_node_model_cache") is not None else False
+            "enable_node_model_cache": obj.get("enable_node_model_cache") if obj.get("enable_node_model_cache") is not None else False,
+            "session_affinity": obj.get("session_affinity") if obj.get("session_affinity") is not None else False
         })
         return _obj
 

platform_api_python_client/models/get_inference_v3_deployment_response.py

@@ -18,9 +18,10 @@ import re  # noqa: F401
 import json
 
 from datetime import datetime
-from pydantic import BaseModel, ConfigDict, StrictBool, StrictInt, StrictStr
+from pydantic import BaseModel, ConfigDict, Field, StrictBool, StrictInt, StrictStr
 from typing import Any, ClassVar, Dict, List, Optional
 from platform_api_python_client.models.backend_protocol import BackendProtocol
+from platform_api_python_client.models.config_file_mount import ConfigFileMount
 from platform_api_python_client.models.deployment_status import DeploymentStatus
 from platform_api_python_client.models.deployment_type import DeploymentType
 from platform_api_python_client.models.image_pull_secret_credentials import ImagePullSecretCredentials
@@ -48,6 +49,7 @@ class GetInferenceV3DeploymentResponse(BaseModel):
     max_replicas: StrictInt
     initial_replicas: Optional[StrictInt] = None
     concurrency: Optional[StrictInt] = None
+    cooldown_period: Optional[StrictInt] = 1800
     healthcheck: Optional[StrictStr] = None
     endpoint_certificate_authority: Optional[StrictStr] = None
     endpoint_bearer_token: Optional[StrictStr] = None
@@ -58,7 +60,9 @@ class GetInferenceV3DeploymentResponse(BaseModel):
     image_pull_secret_credentials: Optional[ImagePullSecretCredentials] = None
     backend_protocol: Optional[BackendProtocol] = None
     enable_logging: Optional[StrictBool] = True
-    __properties: ClassVar[List[str]] = ["creator_email", "cluster_id", "id", "name", "endpoint_url", "image_url", "type", "status", "created_at", "hardware_instance_id", "revision_number", "user_annotations", "container_port", "min_replicas", "max_replicas", "initial_replicas", "concurrency", "healthcheck", "endpoint_certificate_authority", "endpoint_bearer_token", "env_vars", "command", "command_args", "original_command", "image_pull_secret_credentials", "backend_protocol", "enable_logging"]
+    session_affinity: Optional[StrictBool] = Field(default=False, description="Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state.")
+    config_file: Optional[ConfigFileMount] = None
+    __properties: ClassVar[List[str]] = ["creator_email", "cluster_id", "id", "name", "endpoint_url", "image_url", "type", "status", "created_at", "hardware_instance_id", "revision_number", "user_annotations", "container_port", "min_replicas", "max_replicas", "initial_replicas", "concurrency", "cooldown_period", "healthcheck", "endpoint_certificate_authority", "endpoint_bearer_token", "env_vars", "command", "command_args", "original_command", "image_pull_secret_credentials", "backend_protocol", "enable_logging", "session_affinity", "config_file"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -102,6 +106,9 @@ class GetInferenceV3DeploymentResponse(BaseModel):
         # override the default output from pydantic by calling `to_dict()` of image_pull_secret_credentials
         if self.image_pull_secret_credentials:
             _dict['image_pull_secret_credentials'] = self.image_pull_secret_credentials.to_dict()
+        # override the default output from pydantic by calling `to_dict()` of config_file
+        if self.config_file:
+            _dict['config_file'] = self.config_file.to_dict()
         # set to None if image_url (nullable) is None
         # and model_fields_set contains the field
         if self.image_url is None and "image_url" in self.model_fields_set:
@@ -162,6 +169,11 @@ class GetInferenceV3DeploymentResponse(BaseModel):
         if self.image_pull_secret_credentials is None and "image_pull_secret_credentials" in self.model_fields_set:
             _dict['image_pull_secret_credentials'] = None
 
+        # set to None if config_file (nullable) is None
+        # and model_fields_set contains the field
+        if self.config_file is None and "config_file" in self.model_fields_set:
+            _dict['config_file'] = None
+
         return _dict
 
     @classmethod
@@ -191,6 +203,7 @@ class GetInferenceV3DeploymentResponse(BaseModel):
             "max_replicas": obj.get("max_replicas"),
             "initial_replicas": obj.get("initial_replicas"),
             "concurrency": obj.get("concurrency"),
+            "cooldown_period": obj.get("cooldown_period") if obj.get("cooldown_period") is not None else 1800,
             "healthcheck": obj.get("healthcheck"),
             "endpoint_certificate_authority": obj.get("endpoint_certificate_authority"),
             "endpoint_bearer_token": obj.get("endpoint_bearer_token"),
@@ -200,7 +213,9 @@ class GetInferenceV3DeploymentResponse(BaseModel):
             "original_command": obj.get("original_command"),
             "image_pull_secret_credentials": ImagePullSecretCredentials.from_dict(obj["image_pull_secret_credentials"]) if obj.get("image_pull_secret_credentials") is not None else None,
             "backend_protocol": obj.get("backend_protocol"),
-            "enable_logging": obj.get("enable_logging") if obj.get("enable_logging") is not None else True
+            "enable_logging": obj.get("enable_logging") if obj.get("enable_logging") is not None else True,
+            "session_affinity": obj.get("session_affinity") if obj.get("session_affinity") is not None else False,
+            "config_file": ConfigFileMount.from_dict(obj["config_file"]) if obj.get("config_file") is not None else None
         })
         return _obj