Package com.github.copilot.sdk.json

Class ProviderConfig

java.lang.Object
com.github.copilot.sdk.json.ProviderConfig
public class ProviderConfig extends Object
Configuration for a custom API provider (BYOK - Bring Your Own Key).

This allows using your own OpenAI, Azure OpenAI, or other compatible API endpoints instead of the default Copilot backend. All setter methods return this for method chaining.

Example Usage - OpenAI


 var provider = new ProviderConfig().setType("openai").setBaseUrl("https://api.openai.com/v1").setApiKey("sk-...");

Example Usage - Azure OpenAI


 var provider = new ProviderConfig().setType("azure")
 		.setAzure(new AzureOptions().setEndpoint("https://my-resource.openai.azure.com").setDeployment("gpt-4"));
Since:
1.0.0
See Also:

  • Constructor Details

    • ProviderConfig

      public ProviderConfig()

  • Method Details

    • getType

      public String getType()
      Gets the provider type.
      Returns:
      the provider type (e.g., "openai", "azure")

    • setType

      public ProviderConfig setType(String type)
      Sets the provider type.

      Supported types include:

      • "openai" - OpenAI API
      • "azure" - Azure OpenAI Service
      Parameters:
      type - the provider type
      Returns:
      this config for method chaining

    • getWireApi

      public String getWireApi()
      Gets the wire API format.
      Returns:
      the wire API format

    • setWireApi

      public ProviderConfig setWireApi(String wireApi)
      Sets the wire API format for custom providers.

      This specifies the API format when using a custom provider that has a different wire protocol.

      Parameters:
      wireApi - the wire API format
      Returns:
      this config for method chaining

    • getBaseUrl

      public String getBaseUrl()
      Gets the base URL for the API.
      Returns:
      the API base URL

    • setBaseUrl

      public ProviderConfig setBaseUrl(String baseUrl)
      Sets the base URL for the API.

      For OpenAI, this is typically "https://api.openai.com/v1".

      Parameters:
      baseUrl - the API base URL
      Returns:
      this config for method chaining

    • getApiKey

      public String getApiKey()
      Gets the API key.
      Returns:
      the API key

    • setApiKey

      public ProviderConfig setApiKey(String apiKey)
      Sets the API key for authentication.
      Parameters:
      apiKey - the API key
      Returns:
      this config for method chaining

    • getBearerToken

      public String getBearerToken()
      Gets the bearer token.
      Returns:
      the bearer token

    • setBearerToken

      public ProviderConfig setBearerToken(String bearerToken)
      Sets a bearer token for authentication.

      This is an alternative to API key authentication.

      Note: The bearer token is a static token string. The SDK does not refresh this token automatically. If your token expires, requests will fail and you'll need to create a new session with a fresh token.

      Parameters:
      bearerToken - the bearer token
      Returns:
      this config for method chaining

    • getAzure

      public AzureOptions getAzure()
      Gets the Azure-specific options.
      Returns:
      the Azure options

    • setAzure

      public ProviderConfig setAzure(AzureOptions azure)
      Sets Azure-specific options for Azure OpenAI Service.
      Parameters:
      azure - the Azure options
      Returns:
      this config for method chaining
      See Also:

    • getHeaders

      public Map<String,String> getHeaders()
      Gets the custom HTTP headers for outbound provider requests.
      Returns:
      the headers map, or null if not set

    • setHeaders

      public ProviderConfig setHeaders(Map<String,String> headers)
      Sets custom HTTP headers to include in outbound provider requests.

      Use this to pass additional authentication headers or custom metadata to the provider API.

      Parameters:
      headers - the headers map
      Returns:
      this config for method chaining

    • getModelId

      public String getModelId()
      Gets the well-known model name used by the runtime.

      Used to look up agent configuration (tools, prompts, reasoning behavior) and default token limits. Also used as the wire model when getWireModel() is not set.

      Returns:
      the model ID, or null if not set

    • setModelId

      public ProviderConfig setModelId(String modelId)
      Sets the well-known model name used by the runtime.

      Used to look up agent configuration (tools, prompts, reasoning behavior) and default token limits. Also used as the wire model when getWireModel() is not set. Falls back to SessionConfig.getModel().

      Parameters:
      modelId - the model ID
      Returns:
      this config for method chaining

    • getWireModel

      public String getWireModel()
      Gets the model name sent to the provider API for inference.
      Returns:
      the wire model name, or null if not set

    • setWireModel

      public ProviderConfig setWireModel(String wireModel)
      Sets the model name sent to the provider API for inference.

      Use this when the provider's model name (e.g. an Azure deployment name or a custom fine-tune name) differs from getModelId(). Falls back to getModelId(), then SessionConfig.getModel().

      Parameters:
      wireModel - the wire model name
      Returns:
      this config for method chaining

    • getMaxPromptTokens

      public Integer getMaxPromptTokens()
      Gets the maximum prompt token override.
      Returns:
      the max prompt tokens, or null if not set

    • setMaxPromptTokens

      public ProviderConfig setMaxPromptTokens(Integer maxPromptTokens)
      Sets the maximum prompt tokens override.

      Overrides the resolved model's default max prompt tokens. The runtime triggers conversation compaction before sending a request when the prompt (system message, history, tool definitions, user message) would exceed this limit.

      Parameters:
      maxPromptTokens - the max prompt tokens
      Returns:
      this config for method chaining

    • getMaxOutputTokens

      public Integer getMaxOutputTokens()
      Gets the maximum output token override.
      Returns:
      the max output tokens, or null if not set

    • setMaxOutputTokens

      public ProviderConfig setMaxOutputTokens(Integer maxOutputTokens)
      Sets the maximum output tokens override.

      Overrides the resolved model's default max output tokens. When hit, the model stops generating and returns a truncated response.

      Parameters:
      maxOutputTokens - the max output tokens
      Returns:
      this config for method chaining