mirror of
https://github.com/hanzoai/insights.git
synced 2026-10-30 16:15:31 +00:00
zeekay
1b367e2b62
The tree was a debranded snapshot of upstream taken around 2026-02-20, and upstream has moved about five months since. This replaces it with upstream master, mechanically re-derived: bin/debrand does the rename, and the pipeline and squashed migrations are restored from the shipped tree. Not a merge. The previous import replaced the tree wholesale in a single commit, so there is no shared content history to merge against. Reproducing the rename on the new tree is what actually converges. What survives: .hanzo/workflows, the Dockerfiles and bin/docker* entrypoints, compose files, LLM.md, and insights/migrations. The squashed initial migration is load-bearing — the live database records it by name, so upstream's ~918 individual migrations cannot come back. Nine products are dropped as unreferenced. Twenty-one more that we do not run are kept anyway because the core app still imports them; unpicking those is a refactor and does not belong in a rebase. This base does not build yet, and the reasons are not in the rename: upstream now wants Python 3.13.13 against our 3.12.12 and Django 5.2 against our 4.2, and the dependency manifests still name upstream packages that we republish under our own names. Those are decisions, not renames.
67 lines
2.2 KiB
Python
67 lines
2.2 KiB
Python
"""
|
|
Integration tests for Fireworks AI provider through the gateway.
|
|
|
|
Fireworks exposes an OpenAI-compatible API, so tests use the openai SDK
|
|
with LiteLLM-prefixed model names (fireworks_ai/...).
|
|
|
|
Skipped unless FIREWORKS_API_KEY is set.
|
|
Run with: FIREWORKS_API_KEY=<key> uv run pytest tests/integration/test_fireworks_sdk.py -v
|
|
"""
|
|
|
|
import os
|
|
|
|
import pytest
|
|
from openai import OpenAI
|
|
|
|
FIREWORKS_API_KEY = os.environ.get("FIREWORKS_API_KEY")
|
|
|
|
pytestmark = [
|
|
pytest.mark.skipif(not FIREWORKS_API_KEY, reason="FIREWORKS_API_KEY not set"),
|
|
pytest.mark.xfail(strict=False, reason="Fireworks deployment may be scaled to zero"),
|
|
]
|
|
|
|
MODEL = "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct"
|
|
|
|
|
|
class TestFireworksChatCompletions:
|
|
def test_non_streaming_request(self, openai_client: OpenAI):
|
|
response = openai_client.chat.completions.create(
|
|
model=MODEL,
|
|
messages=[{"role": "user", "content": "Say 'hello' and nothing else."}],
|
|
max_tokens=10,
|
|
)
|
|
|
|
assert response is not None
|
|
assert len(response.choices) > 0
|
|
assert response.choices[0].message.content is not None
|
|
assert response.usage is not None
|
|
assert response.usage.prompt_tokens > 0
|
|
assert response.usage.completion_tokens > 0
|
|
|
|
def test_streaming_request(self, openai_client: OpenAI):
|
|
stream = openai_client.chat.completions.create(
|
|
model=MODEL,
|
|
messages=[{"role": "user", "content": "Say 'hi' and nothing else."}],
|
|
max_tokens=10,
|
|
stream=True,
|
|
)
|
|
|
|
chunks = list(stream)
|
|
assert len(chunks) > 0
|
|
|
|
content_chunks = [c for c in chunks if c.choices and c.choices[0].delta.content]
|
|
assert len(content_chunks) > 0
|
|
|
|
def test_with_system_message(self, openai_client: OpenAI):
|
|
response = openai_client.chat.completions.create(
|
|
model=MODEL,
|
|
messages=[
|
|
{"role": "system", "content": "You are a helpful assistant that only says 'OK'."},
|
|
{"role": "user", "content": "Hello"},
|
|
],
|
|
max_tokens=10,
|
|
)
|
|
|
|
assert response is not None
|
|
assert response.choices[0].message.content is not None
|