feat: Add support for Conversations in Responses API (#3743)

# What does this PR do?
This PR adds support for Conversations in Responses.

<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->

## Test Plan
Unit tests
Integration tests

<Details>
<Summary>Manual testing with this script: (click to expand)</Summary>

```python
from openai import OpenAI

client = OpenAI()
client = OpenAI(base_url="http://localhost:8321/v1/", api_key="none")

def test_conversation_create():
    print("Testing conversation create...")
    conversation = client.conversations.create(
        metadata={"topic": "demo"},
        items=[
            {"type": "message", "role": "user", "content": "Hello!"}
        ]
    )
    print(f"Created: {conversation}")
    return conversation

def test_conversation_retrieve(conv_id):
    print(f"Testing conversation retrieve for {conv_id}...")
    retrieved = client.conversations.retrieve(conv_id)
    print(f"Retrieved: {retrieved}")
    return retrieved

def test_conversation_update(conv_id):
    print(f"Testing conversation update for {conv_id}...")
    updated = client.conversations.update(
        conv_id,
        metadata={"topic": "project-x"}
    )
    print(f"Updated: {updated}")
    return updated

def test_conversation_delete(conv_id):
    print(f"Testing conversation delete for {conv_id}...")
    deleted = client.conversations.delete(conv_id)
    print(f"Deleted: {deleted}")
    return deleted

def test_conversation_items_create(conv_id):
    print(f"Testing conversation items create for {conv_id}...")
    items = client.conversations.items.create(
        conv_id,
        items=[
            {
                "type": "message",
                "role": "user",
                "content": [{"type": "input_text", "text": "Hello!"}]
            },
            {
                "type": "message",
                "role": "user",
                "content": [{"type": "input_text", "text": "How are you?"}]
            }
        ]
    )
    print(f"Items created: {items}")
    return items

def test_conversation_items_list(conv_id):
    print(f"Testing conversation items list for {conv_id}...")
    items = client.conversations.items.list(conv_id, limit=10)
    print(f"Items list: {items}")
    return items

def test_conversation_item_retrieve(conv_id, item_id):
    print(f"Testing conversation item retrieve for {conv_id}/{item_id}...")
    item = client.conversations.items.retrieve(conversation_id=conv_id, item_id=item_id)
    print(f"Item retrieved: {item}")
    return item

def test_conversation_item_delete(conv_id, item_id):
    print(f"Testing conversation item delete for {conv_id}/{item_id}...")
    deleted = client.conversations.items.delete(conversation_id=conv_id, item_id=item_id)
    print(f"Item deleted: {deleted}")
    return deleted

def test_conversation_responses_create():
    print("\nTesting conversation create for a responses example...")
    conversation = client.conversations.create()
    print(f"Created: {conversation}")

    response = client.responses.create(
      model="gpt-4.1",
      input=[{"role": "user", "content": "What are the 5 Ds of dodgeball?"}],
      conversation=conversation.id,
    )
    print(f"Created response: {response} for conversation {conversation.id}")

    return response, conversation

def test_conversations_responses_create_followup(
        conversation,
        content="Repeat what you just said but add 'this is my second time saying this'",
    ):
    print(f"Using: {conversation.id}")

    response = client.responses.create(
      model="gpt-4.1",
      input=[{"role": "user", "content": content}],
      conversation=conversation.id,
    )
    print(f"Created response: {response} for conversation {conversation.id}")

    conv_items = client.conversations.items.list(conversation.id)
    print(f"\nRetrieving list of items for conversation {conversation.id}:")
    print(conv_items.model_dump_json(indent=2))

def test_response_with_fake_conv_id():
    fake_conv_id = "conv_zzzzzzzzz5dc81908289d62779d2ac510a2b0b602ef00a44"
    print(f"Using {fake_conv_id}")
    try:
        response = client.responses.create(
          model="gpt-4.1",
          input=[{"role": "user", "content": "say hello"}],
          conversation=fake_conv_id,
        )
        print(f"Created response: {response} for conversation {fake_conv_id}")
    except Exception as e:
        print(f"failed to create response for conversation {fake_conv_id} with error {e}")


def main():
    print("Testing OpenAI Conversations API...")

    # Create conversation
    conversation = test_conversation_create()
    conv_id = conversation.id

    # Retrieve conversation
    test_conversation_retrieve(conv_id)

    # Update conversation
    test_conversation_update(conv_id)

    # Create items
    items = test_conversation_items_create(conv_id)

    # List items
    items_list = test_conversation_items_list(conv_id)

    # Retrieve specific item
    if items_list.data:
        item_id = items_list.data[0].id
        test_conversation_item_retrieve(conv_id, item_id)

        # Delete item
        test_conversation_item_delete(conv_id, item_id)

    # Delete conversation
    test_conversation_delete(conv_id)

    response, conversation2 = test_conversation_responses_create()
    print('\ntesting reseponse retrieval')
    test_conversation_retrieve(conversation2.id)

    print('\ntesting responses follow up')
    test_conversations_responses_create_followup(conversation2)

    print('\ntesting responses follow up x2!')

    test_conversations_responses_create_followup(
        conversation2,
        content="Repeat what you just said but add 'this is my third time saying this'",
    )

    test_response_with_fake_conv_id()

    print("All tests completed!")


if __name__ == "__main__":
    main()
```
</Details>

---------

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>

llama_stack/core/conversations/conversations.py

@@ -193,12 +193,15 @@ class ConversationServiceImpl(Conversations):
         await self._get_validated_conversation(conversation_id)
 
         created_items = []
-        created_at = int(time.time())
+        base_time = int(time.time())
 
-        for item in items:
+        for i, item in enumerate(items):
             item_dict = item.model_dump()
             item_id = self._get_or_generate_item_id(item, item_dict)
 
+            # make each timestamp unique to maintain order
+            created_at = base_time + i
+
             item_record = {
                 "id": item_id,
                 "conversation_id": conversation_id,

llama_stack/core/resolver.py

@@ -150,6 +150,7 @@ async def resolve_impls(
     provider_registry: ProviderRegistry,
     dist_registry: DistributionRegistry,
     policy: list[AccessRule],
+    internal_impls: dict[Api, Any] | None = None,
 ) -> dict[Api, Any]:
     """
     Resolves provider implementations by:
@@ -172,7 +173,7 @@ async def resolve_impls(
 
     sorted_providers = sort_providers_by_deps(providers_with_specs, run_config)
 
-    return await instantiate_providers(sorted_providers, router_apis, dist_registry, run_config, policy)
+    return await instantiate_providers(sorted_providers, router_apis, dist_registry, run_config, policy, internal_impls)
 
 
 def specs_for_autorouted_apis(apis_to_serve: list[str] | set[str]) -> dict[str, dict[str, ProviderWithSpec]]:
@@ -280,9 +281,10 @@ async def instantiate_providers(
     dist_registry: DistributionRegistry,
     run_config: StackRunConfig,
     policy: list[AccessRule],
+    internal_impls: dict[Api, Any] | None = None,
 ) -> dict[Api, Any]:
     """Instantiates providers asynchronously while managing dependencies."""
-    impls: dict[Api, Any] = {}
+    impls: dict[Api, Any] = internal_impls.copy() if internal_impls else {}
     inner_impls_by_provider_id: dict[str, dict[str, Any]] = {f"inner-{x.value}": {} for x in router_apis}
     for api_str, provider in sorted_providers:
         # Skip providers that are not enabled

llama_stack/core/stack.py

@@ -326,12 +326,17 @@ class Stack:
 
         dist_registry, _ = await create_dist_registry(self.run_config.metadata_store, self.run_config.image_name)
         policy = self.run_config.server.auth.access_policy if self.run_config.server.auth else []
-        impls = await resolve_impls(
-            self.run_config, self.provider_registry or get_provider_registry(self.run_config), dist_registry, policy
-        )
 
-        # Add internal implementations after all other providers are resolved
-        add_internal_implementations(impls, self.run_config)
+        internal_impls = {}
+        add_internal_implementations(internal_impls, self.run_config)
+
+        impls = await resolve_impls(
+            self.run_config,
+            self.provider_registry or get_provider_registry(self.run_config),
+            dist_registry,
+            policy,
+            internal_impls,
+        )
 
         if Api.prompts in impls:
             await impls[Api.prompts].initialize()