Add configurable streaming and embeddings support for OpenAI provider

crates/goose/src/providers/openai.rs

@@ -48,6 +48,8 @@ pub struct OpenAiProvider {
     project: Option<String>,
     model: ModelConfig,
     custom_headers: Option<HashMap<String, String>>,
+    enable_streaming: bool,
+    enable_embeddings: bool,
 }
 
 impl Default for OpenAiProvider {
@@ -74,6 +76,16 @@ impl OpenAiProvider {
             .or_else(|_| config.get_param("OPENAI_CUSTOM_HEADERS"))
             .ok()
             .map(parse_custom_headers);
+        let enable_streaming: bool = config
+            .get_param("OPENAI_ENABLE_STREAMING")
+            .unwrap_or_else(|_| "true".to_string())
+            .parse()
+            .unwrap_or(true);
+        let enable_embeddings: bool = config
+            .get_param("OPENAI_ENABLE_EMBEDDINGS")
+            .unwrap_or_else(|_| "true".to_string())
+            .parse()
+            .unwrap_or(true);
         let timeout_secs: u64 = config.get_param("OPENAI_TIMEOUT").unwrap_or(600);
         let client = Client::builder()
             .timeout(Duration::from_secs(timeout_secs))
@@ -88,6 +100,8 @@ impl OpenAiProvider {
             project,
             model,
             custom_headers,
+            enable_streaming,
+            enable_embeddings,
         })
     }
 
@@ -156,6 +170,8 @@ impl Provider for OpenAiProvider {
                 ConfigKey::new("OPENAI_ORGANIZATION", false, false, None),
                 ConfigKey::new("OPENAI_PROJECT", false, false, None),
                 ConfigKey::new("OPENAI_CUSTOM_HEADERS", false, true, None),
+                ConfigKey::new("OPENAI_ENABLE_STREAMING", false, false, Some("true")),
+                ConfigKey::new("OPENAI_ENABLE_EMBEDDINGS", false, false, Some("true")),
                 ConfigKey::new("OPENAI_TIMEOUT", false, false, Some("600")),
             ],
         )
@@ -232,7 +248,7 @@ impl Provider for OpenAiProvider {
     }
 
     fn supports_embeddings(&self) -> bool {
-        true
+        self.enable_embeddings
     }
 
     async fn create_embeddings(&self, texts: Vec<String>) -> Result<Vec<Vec<f32>>, ProviderError> {
@@ -242,7 +258,7 @@ impl Provider for OpenAiProvider {
     }
 
     fn supports_streaming(&self) -> bool {
-        true
+        self.enable_streaming
     }
 
     async fn stream(

documentation/docs/getting-started/providers.md

@@ -32,7 +32,7 @@ Goose relies heavily on tool calling capabilities and currently works best with
 | [Groq](https://groq.com/)                                                   | High-performance inference hardware and tools for LLMs.                                                                                                                                                                   | `GROQ_API_KEY`                                                                                                                                                                      |
 | [Ollama](https://ollama.com/)                                               | Local model runner supporting Qwen, Llama, DeepSeek, and other open-source models. **Because this provider runs locally, you must first [download and run a model](#local-llms).**  | `OLLAMA_HOST`                                                                                                                                                                       |
 | [Ramalama](https://ramalama.ai/)                                            | Local model using native [OCI](https://opencontainers.org/) container runtimes, [CNCF](https://www.cncf.io/) tools, and supporting models as OCI artifacts. Ramalama API an compatible alternative to Ollama and can be used with the Goose Ollama provider. Supports Qwen, Llama, DeepSeek, and other open-source models. **Because this provider runs locally, you must first [download and run a model](#local-llms).**  | `OLLAMA_HOST`                                                                                                                                                                       |
-| [OpenAI](https://platform.openai.com/api-keys)                              | Provides gpt-4o, o1, and other advanced language models. Also supports OpenAI-compatible endpoints (e.g., self-hosted LLaMA, vLLM, KServe). **o1-mini and o1-preview are not supported because Goose uses tool calling.** | `OPENAI_API_KEY`, `OPENAI_HOST` (optional), `OPENAI_ORGANIZATION` (optional), `OPENAI_PROJECT` (optional), `OPENAI_CUSTOM_HEADERS` (optional)                                       |
+| [OpenAI](https://platform.openai.com/api-keys)                              | Provides gpt-4o, o1, and other advanced language models. Also supports OpenAI-compatible endpoints (e.g., self-hosted LLaMA, vLLM, KServe). **o1-mini and o1-preview are not supported because Goose uses tool calling.** | `OPENAI_API_KEY`, `OPENAI_HOST` (optional), `OPENAI_ORGANIZATION` (optional), `OPENAI_PROJECT` (optional), `OPENAI_CUSTOM_HEADERS` (optional), `OPENAI_ENABLE_STREAMING` (optional), `OPENAI_ENABLE_EMBEDDINGS` (optional)                                       |
 | [OpenRouter](https://openrouter.ai/)                                        | API gateway for unified access to various models with features like rate-limiting management.                                                                                                                             | `OPENROUTER_API_KEY`                                                                                                                                                                |
 | [Snowflake](https://docs.snowflake.com/user-guide/snowflake-cortex/aisql#choosing-a-model) | Access the latest models using Snowflake Cortex services, including Claude models. **Requires a Snowflake account and programmatic access token (PAT)**.                                                     | `SNOWFLAKE_HOST`, `SNOWFLAKE_TOKEN`                                                                                                                                                                 |
 | [Venice AI](https://venice.ai/home)                                         | Provides access to open source models like Llama, Mistral, and Qwen while prioritizing user privacy. **Requires an account and an [API key](https://docs.venice.ai/overview/guides/generating-api-key)**.                 | `VENICE_API_KEY`, `VENICE_HOST` (optional), `VENICE_BASE_PATH` (optional), `VENICE_MODELS_PATH` (optional)                                                                          |
@@ -165,6 +165,8 @@ Goose supports using custom OpenAI-compatible endpoints, which is particularly u
 | `OPENAI_ORGANIZATION` | No | Organization ID for usage tracking and governance |
 | `OPENAI_PROJECT` | No | Project identifier for resource management |
 | `OPENAI_CUSTOM_HEADERS` | No | Additional headers to include in the request. Can be set via environment variable, configuration file, or CLI, in the format `HEADER_A=VALUE_A,HEADER_B=VALUE_B`. |
+| `OPENAI_ENABLE_STREAMING` | No | Enable or disable streaming support (defaults to true) |
+| `OPENAI_ENABLE_EMBEDDINGS` | No | Enable or disable embeddings support (defaults to true) |
 
 ### Example Configurations