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/agents/fixtures.py

@@ -9,7 +9,7 @@ import tempfile
 import pytest
 import pytest_asyncio
 
-from llama_stack.apis.models import ModelInput
+from llama_stack.apis.models import ModelInput, ModelType
 from llama_stack.distribution.datatypes import Api, Provider
 
 from llama_stack.providers.inline.agents.meta_reference import (
@@ -67,22 +67,42 @@ async def agents_stack(request, inference_model, safety_shield):
     for key in ["inference", "safety", "memory", "agents"]:
         fixture = request.getfixturevalue(f"{key}_{fixture_dict[key]}")
         providers[key] = fixture.providers
+        if key == "inference":
+            providers[key].append(
+                Provider(
+                    provider_id="agents_memory_provider",
+                    provider_type="inline::sentence-transformers",
+                    config={},
+                )
+            )
         if fixture.provider_data:
             provider_data.update(fixture.provider_data)
 
     inference_models = (
         inference_model if isinstance(inference_model, list) else [inference_model]
     )
+    models = [
+        ModelInput(
+            model_id=model,
+            model_type=ModelType.llm,
+            provider_id=providers["inference"][0].provider_id,
+        )
+        for model in inference_models
+    ]
+    models.append(
+        ModelInput(
+            model_id="all-MiniLM-L6-v2",
+            model_type=ModelType.embedding,
+            provider_id="agents_memory_provider",
+            metadata={"embedding_dimension": 384},
+        )
+    )
+
     test_stack = await construct_stack_for_test(
         [Api.agents, Api.inference, Api.safety, Api.memory],
         providers,
         provider_data,
-        models=[
-            ModelInput(
-                model_id=model,
-            )
-            for model in inference_models
-        ],
+        models=models,
         shields=[safety_shield] if safety_shield else [],
     )
     return test_stack