Update the "InterleavedTextMedia" type (#635)

## What does this PR do?

This is a long-pending change and particularly important to get done
now.

Specifically:
- we cannot "localize" (aka download) any URLs from media attachments
anywhere near our modeling code. it must be done within llama-stack.
- `PIL.Image` is infesting all our APIs via `ImageMedia ->
InterleavedTextMedia` and that cannot be right at all. Anything in the
API surface must be "naturally serializable". We need a standard `{
type: "image", image_url: "<...>" }` which is more extensible
- `UserMessage`, `SystemMessage`, etc. are moved completely to
llama-stack from the llama-models repository.

See https://github.com/meta-llama/llama-models/pull/244 for the
corresponding PR in llama-models.

## Test Plan

```bash
cd llama_stack/providers/tests

pytest -s -v -k "fireworks or ollama or together" inference/test_vision_inference.py
pytest -s -v -k "(fireworks or ollama or together) and llama_3b" inference/test_text_inference.py
pytest -s -v -k chroma memory/test_memory.py \
  --env EMBEDDING_DIMENSION=384 --env CHROMA_DB_PATH=/tmp/foobar

pytest -s -v -k fireworks agents/test_agents.py  \
   --safety-shield=meta-llama/Llama-Guard-3-8B \
   --inference-model=meta-llama/Llama-3.1-8B-Instruct
```

Updated the client sdk (see PR ...), installed the SDK in the same
environment and then ran the SDK tests:

```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=together pytest -s -v agents/test_agents.py
LLAMA_STACK_CONFIG=ollama pytest -s -v memory/test_memory.py

# this one needed a bit of hacking in the run.yaml to ensure I could register the vision model correctly
INFERENCE_MODEL=llama3.2-vision:latest LLAMA_STACK_CONFIG=ollama pytest -s -v inference/test_inference.py
```

llama_stack/providers/tests/memory/fixtures.py

@@ -24,6 +24,13 @@ from ..conftest import ProviderFixture, remote_stack_fixture
 from ..env import get_env_or_fail
 
 
+@pytest.fixture(scope="session")
+def embedding_model(request):
+    if hasattr(request, "param"):
+        return request.param
+    return request.config.getoption("--embedding-model", None)
+
+
 @pytest.fixture(scope="session")
 def memory_remote() -> ProviderFixture:
     return remote_stack_fixture()
@@ -107,7 +114,7 @@ MEMORY_FIXTURES = ["faiss", "pgvector", "weaviate", "remote", "chroma"]
 
 
 @pytest_asyncio.fixture(scope="session")
-async def memory_stack(inference_model, request):
+async def memory_stack(embedding_model, request):
     fixture_dict = request.param
 
     providers = {}
@@ -124,7 +131,7 @@ async def memory_stack(inference_model, request):
         provider_data,
         models=[
             ModelInput(
-                model_id=inference_model,
+                model_id=embedding_model,
                 model_type=ModelType.embedding,
                 metadata={
                     "embedding_dimension": get_env_or_fail("EMBEDDING_DIMENSION"),