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/utils/inference/openai_compat.py

@@ -11,9 +11,14 @@ from llama_models.llama3.api.chat_format import ChatFormat
 from llama_models.llama3.api.datatypes import StopReason
 
 from llama_stack.apis.inference import *  # noqa: F403
-
 from pydantic import BaseModel
 
+from llama_stack.apis.common.content_types import ImageContentItem, TextContentItem
+
+from llama_stack.providers.utils.inference.prompt_adapter import (
+    convert_image_content_to_url,
+)
+
 
 class OpenAICompatCompletionChoiceDelta(BaseModel):
     content: str
@@ -90,11 +95,15 @@ def process_chat_completion_response(
 ) -> ChatCompletionResponse:
     choice = response.choices[0]
 
-    completion_message = formatter.decode_assistant_message_from_content(
+    raw_message = formatter.decode_assistant_message_from_content(
         text_from_choice(choice), get_stop_reason(choice.finish_reason)
     )
     return ChatCompletionResponse(
-        completion_message=completion_message,
+        completion_message=CompletionMessage(
+            content=raw_message.content,
+            stop_reason=raw_message.stop_reason,
+            tool_calls=raw_message.tool_calls,
+        ),
         logprobs=None,
     )
 
@@ -246,3 +255,32 @@ async def process_chat_completion_stream_response(
             stop_reason=stop_reason,
         )
     )
+
+
+async def convert_message_to_openai_dict(
+    message: Message, download: bool = False
+) -> dict:
+    async def _convert_content(content) -> dict:
+        if isinstance(content, ImageContentItem):
+            return {
+                "type": "image_url",
+                "image_url": {
+                    "url": await convert_image_content_to_url(
+                        content, download=download
+                    ),
+                },
+            }
+        else:
+            text = content.text if isinstance(content, TextContentItem) else content
+            assert isinstance(text, str)
+            return {"type": "text", "text": text}
+
+    if isinstance(message.content, list):
+        content = [await _convert_content(c) for c in message.content]
+    else:
+        content = [await _convert_content(message.content)]
+
+    return {
+        "role": message.role,
+        "content": content,
+    }