Include text/event-stream header only when stream=True

Summary:
We want to use the headers to negotiate content.

Sending this header in every request will cause server to return chunks, even without the stream=True param.

```
llama-stack-client inference chat-completion --message="Hello there"

{"event":{"event_type":"start","delta":"Hello"}}

{"event":{"event_type":"progress","delta":"!"}}

{"event":{"event_type":"progress","delta":" How"}}

{"event":{"event_type":"progress","delta":" are"}}

{"event":{"event_type":"progress","delta":" you"}}

{"event":{"event_type":"progress","delta":" today"}}
```

Test Plan:

```
pip install .

llama-stack-client configure --endpoint={endpoint} --api-key={api-key}

llama-stack-client inference chat-completion --message="Hello there"
ChatCompletionResponse(completion_message=CompletionMessage(content='Hello! How can I assist you today?', role='assistant', stop_reason='end_of_turn', tool_calls=[]), logprobs=None)
```

Author: vladimirivic

src/llama_stack_client/resources/inference.py

@@ -213,7 +213,8 @@ def chat_completion(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> InferenceChatCompletionResponse | Stream[InferenceChatCompletionResponse]:
-        extra_headers = {"Accept": "text/event-stream", **(extra_headers or {})}
+        if stream is True:
+            extra_headers = {"Accept": "text/event-stream", **(extra_headers or {})}
         extra_headers = {
             **strip_not_given(
                 {
@@ -364,7 +365,8 @@ def completion(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> InferenceCompletionResponse | Stream[InferenceCompletionResponse]:
-        extra_headers = {"Accept": "text/event-stream", **(extra_headers or {})}
+        if stream is True:
+            extra_headers = {"Accept": "text/event-stream", **(extra_headers or {})}
         extra_headers = {
             **strip_not_given(
                 {
@@ -623,7 +625,8 @@ async def chat_completion(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> InferenceChatCompletionResponse | AsyncStream[InferenceChatCompletionResponse]:
-        extra_headers = {"Accept": "text/event-stream", **(extra_headers or {})}
+        if stream is True:
+            extra_headers = {"Accept": "text/event-stream", **(extra_headers or {})}
         extra_headers = {
             **strip_not_given(
                 {
@@ -774,7 +777,8 @@ async def completion(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> InferenceCompletionResponse | AsyncStream[InferenceCompletionResponse]:
-        extra_headers = {"Accept": "text/event-stream", **(extra_headers or {})}
+        if stream is True:
+            extra_headers = {"Accept": "text/event-stream", **(extra_headers or {})}
         extra_headers = {
             **strip_not_given(
                 {