phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-08 13:00:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into ragtool-migration

Browse source
This commit is contained in:
Francisco Arceo 2025-09-10 13:58:57 -06:00 • committed by GitHub
commit 9b27f81b75
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 318 additions and 40 deletions
Download patch file Download diff file Expand all files Collapse all files

12
tests/unit/utils/inference/test_inference_store.py
View file

@ -65,6 +65,9 @@ async def test_inference_store_pagination_basic():
input_messages = [OpenAIUserMessageParam(role="user", content=f"Test message for {completion_id}")]
await store.store_chat_completion(completion, input_messages)
# Wait for all queued writes to complete
await store.flush()
# Test 1: First page with limit=2, descending order (default)
result = await store.list_chat_completions(limit=2, order=Order.desc)
assert len(result.data) == 2
@ -108,6 +111,9 @@ async def test_inference_store_pagination_ascending():
input_messages = [OpenAIUserMessageParam(role="user", content=f"Test message for {completion_id}")]
await store.store_chat_completion(completion, input_messages)
# Wait for all queued writes to complete
await store.flush()
# Test ascending order pagination
result = await store.list_chat_completions(limit=1, order=Order.asc)
assert len(result.data) == 1
@ -143,6 +149,9 @@ async def test_inference_store_pagination_with_model_filter():
input_messages = [OpenAIUserMessageParam(role="user", content=f"Test message for {completion_id}")]
await store.store_chat_completion(completion, input_messages)
# Wait for all queued writes to complete
await store.flush()
# Test pagination with model filter
result = await store.list_chat_completions(limit=1, model="model-a", order=Order.desc)
assert len(result.data) == 1
@ -190,6 +199,9 @@ async def test_inference_store_pagination_no_limit():
input_messages = [OpenAIUserMessageParam(role="user", content=f"Test message for {completion_id}")]
await store.store_chat_completion(completion, input_messages)
# Wait for all queued writes to complete
await store.flush()
# Test without limit
result = await store.list_chat_completions(order=Order.desc)
assert len(result.data) == 2