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/inference/test_vision_inference.py

@@ -7,16 +7,19 @@
 from pathlib import Path
 
 import pytest
-from PIL import Image as PIL_Image
 
 
 from llama_models.llama3.api.datatypes import *  # noqa: F403
 from llama_stack.apis.inference import *  # noqa: F403
+from llama_stack.apis.common.content_types import ImageContentItem, TextContentItem, URL
 
 from .utils import group_chunks
 
 THIS_DIR = Path(__file__).parent
 
+with open(THIS_DIR / "pasta.jpeg", "rb") as f:
+    PASTA_IMAGE = f.read()
+
 
 class TestVisionModelInference:
     @pytest.mark.asyncio
@@ -24,12 +27,12 @@ class TestVisionModelInference:
         "image, expected_strings",
         [
             (
-                ImageMedia(image=PIL_Image.open(THIS_DIR / "pasta.jpeg")),
+                ImageContentItem(data=PASTA_IMAGE),
                 ["spaghetti"],
             ),
             (
-                ImageMedia(
-                    image=URL(
+                ImageContentItem(
+                    url=URL(
                         uri="https://www.healthypawspetinsurance.com/Images/V3/DogAndPuppyInsurance/Dog_CTA_Desktop_HeroImage.jpg"
                     )
                 ),
@@ -58,7 +61,12 @@ class TestVisionModelInference:
             model_id=inference_model,
             messages=[
                 UserMessage(content="You are a helpful assistant."),
-                UserMessage(content=[image, "Describe this image in two sentences."]),
+                UserMessage(
+                    content=[
+                        image,
+                        TextContentItem(text="Describe this image in two sentences."),
+                    ]
+                ),
             ],
             stream=False,
             sampling_params=SamplingParams(max_tokens=100),
@@ -89,8 +97,8 @@ class TestVisionModelInference:
             )
 
         images = [
-            ImageMedia(
-                image=URL(
+            ImageContentItem(
+                url=URL(
                     uri="https://www.healthypawspetinsurance.com/Images/V3/DogAndPuppyInsurance/Dog_CTA_Desktop_HeroImage.jpg"
                 )
             ),
@@ -106,7 +114,12 @@ class TestVisionModelInference:
                     messages=[
                         UserMessage(content="You are a helpful assistant."),
                         UserMessage(
-                            content=[image, "Describe this image in two sentences."]
+                            content=[
+                                image,
+                                TextContentItem(
+                                    text="Describe this image in two sentences."
+                                ),
+                            ]
                         ),
                     ],
                     stream=True,