fix: multiple issues with getting_started notebook (#1795)

Fixes multiple issues 

1. llama stack build of dependencies was breaking with incompatible
numpy / pandas when importing datasets

Moved the notebook to start a local server instead of using library as a
client. This way the setup is cleaner since its all contained and by
using `uv run --with` we can test both the server setup process too in
CI and release time.

2. The change to [1] surfaced some other issues 
- running `llama stack run` was defaulting to conda env name 
- provider data was not being managed properly 
- Some notebook cells (telemetry for evals) were not updated with latest
changes

Fixed all the issues and update the notebook. 

### Test 

1. Manually run it all in local env 
2. `pytest -v -s --nbval-lax docs/getting_started.ipynb`

llama_stack/distribution/utils/context.py

@@ -18,15 +18,19 @@ def preserve_contexts_async_generator(
     This is needed because we start a new asyncio event loop for each streaming request,
     and we need to preserve the context across the event loop boundary.
     """
+    # Capture initial context values
+    initial_context_values = {context_var.name: context_var.get() for context_var in context_vars}
 
     async def wrapper() -> AsyncGenerator[T, None]:
         while True:
             try:
-                item = await gen.__anext__()
-                context_values = {context_var.name: context_var.get() for context_var in context_vars}
-                yield item
+                # Restore context values before any await
                 for context_var in context_vars:
-                    _ = context_var.set(context_values[context_var.name])
+                    context_var.set(initial_context_values[context_var.name])
+
+                item = await gen.__anext__()
+                yield item
+
             except StopAsyncIteration:
                 break