15ea23d5d6
* feat: introduce hindsight-api-slim and hindsight-all-slim packages Closes #552 - Move all source code from hindsight-api/ to new hindsight-api-slim/ - hindsight-api-slim has heavy ML deps (torch, sentence-transformers, transformers, einops, flashrank, mlx, mlx-lm, safetensors) and pg0-embedded as optional extras: [local-ml], [embedded-db], [all] - hindsight-api becomes a zero-code meta-package depending on hindsight-api-slim[all] for full backward compatibility - Add hindsight-all-slim meta-package: hindsight-api-slim + client + embed - hindsight-all updated to depend on hindsight-api-slim[all] - pg0.py: lazy-import pg0 with clear ImportError pointing to [embedded-db] - Dockerfile: replace sed hack with proper uv sync --extra flags - Update release.yml, test.yml, lint.sh, release.sh, CLAUDE.md and all path references throughout the repo * refactor: rename hindsight/ directory to hindsight-all/ * docs: document hindsight-api-slim and hindsight-all-slim package variants Add package variants table and extras explanation to installation.md * docs: remove emojis from installation.md, use professional tone * docs: link Docker slim variant to pip package variants section * docs: consolidate Docker image variants into single table * ci: fix working-directory paths after package restructure - Replace all hindsight-api → hindsight-api-slim in test.yml - Replace hindsight → hindsight-all in test.yml - Add --extra embedded-db to test-embed API install step * ci: add local-ml and embedded-db extras to API sync steps These extras were previously implicit in the old hindsight-api package (which bundled everything). Now that hindsight-api-slim uses optional extras, we must explicitly request local-ml and embedded-db in CI. * ci: add API install step with embedded-db to test-embed smoke test The smoke test starts hindsight-api as a daemon, which requires pg0-embedded. Add a dedicated install step for hindsight-api-slim with embedded-db extra so the daemon can start successfully. * ci: remove --no-install-project when using optional extras When --no-install-project is combined with --extra, the optional deps are not installed because extras require the project to be active. Remove --no-install-project from steps that need local-ml or embedded-db. * ci: fix ordering of uv sync steps to preserve optional extras When uv sync runs for a different workspace member, it removes optional extras installed for other members. Fix by always running extra-requiring API sync last, after other workspace member syncs. Also remove --no-install-project from embedded-db sync in test-embed, as --no-install-project prevents optional extras from being active. * ci: add local-ml extra to test-embed API install for smoke test The smoke test starts the full API server which needs sentence-transformers for local embeddings (default provider). Add local-ml extra to the install. * ci: simplify extras with --all-extras and add slim pip smoke test - Replace explicit --extra local-ml --extra embedded-db with --all-extras for cleaner, more maintainable sync steps - Add test-pip-slim job: tests hindsight-api-slim[embedded-db] without local ML models, using Cohere for embeddings/reranking (mirrors Docker slim smoke test approach) * ci: simplify slim smoke test to health check only (mirrors Docker test)
247 lines
8.6 KiB
Python
247 lines
8.6 KiB
Python
"""
|
|
Test that LLM calls record token metrics via the metrics collector.
|
|
"""
|
|
import os
|
|
from unittest.mock import MagicMock, patch
|
|
import pytest
|
|
from hindsight_api.engine.llm_wrapper import LLMProvider
|
|
from hindsight_api.metrics import (
|
|
MetricsCollector,
|
|
NoOpMetricsCollector,
|
|
get_metrics_collector,
|
|
)
|
|
|
|
|
|
def get_groq_api_key() -> str | None:
|
|
"""Get Groq API key from environment."""
|
|
return os.getenv("GROQ_API_KEY")
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_llm_metrics_recorded_for_groq():
|
|
"""
|
|
Test that LLM metrics are recorded when making LLM calls via Groq.
|
|
Uses openai/gpt-oss-20b as recommended by Hindsight.
|
|
"""
|
|
api_key = get_groq_api_key()
|
|
if not api_key:
|
|
pytest.skip("Skipping: GROQ_API_KEY not set")
|
|
|
|
# Create a mock metrics collector to track record_llm_call calls
|
|
mock_collector = MagicMock(spec=MetricsCollector)
|
|
|
|
# Patch the provider module where get_metrics_collector is actually called
|
|
with patch("hindsight_api.engine.providers.openai_compatible_llm.get_metrics_collector", return_value=mock_collector):
|
|
llm = LLMProvider(
|
|
provider="groq",
|
|
api_key=api_key,
|
|
base_url="",
|
|
model="openai/gpt-oss-20b",
|
|
)
|
|
|
|
# Make an LLM call with clear instruction
|
|
response = await llm.call(
|
|
messages=[
|
|
{"role": "system", "content": "You are a helpful assistant. Always respond."},
|
|
{"role": "user", "content": "What is 2+2? Reply with just the number."}
|
|
],
|
|
max_completion_tokens=50,
|
|
scope="test_metrics",
|
|
)
|
|
|
|
# Verify record_llm_call was called - this is the main test
|
|
assert mock_collector.record_llm_call.called, "record_llm_call should have been called"
|
|
|
|
# Get the call arguments
|
|
call_kwargs = mock_collector.record_llm_call.call_args.kwargs
|
|
|
|
# Verify the call had correct structure
|
|
assert call_kwargs["provider"] == "groq", f"Expected provider='groq', got {call_kwargs}"
|
|
assert call_kwargs["model"] == "openai/gpt-oss-20b", f"Expected model='openai/gpt-oss-20b', got {call_kwargs}"
|
|
assert call_kwargs["scope"] == "test_metrics", f"Expected scope='test_metrics', got {call_kwargs}"
|
|
assert call_kwargs["duration"] > 0, f"Expected duration > 0, got {call_kwargs['duration']}"
|
|
assert call_kwargs["input_tokens"] > 0, f"Expected input_tokens > 0, got {call_kwargs['input_tokens']}"
|
|
assert call_kwargs["output_tokens"] >= 0, f"Expected output_tokens >= 0, got {call_kwargs['output_tokens']}"
|
|
assert call_kwargs["success"] is True, f"Expected success=True, got {call_kwargs['success']}"
|
|
|
|
print(f"\nLLM metrics recorded:")
|
|
print(f" provider: {call_kwargs['provider']}")
|
|
print(f" model: {call_kwargs['model']}")
|
|
print(f" scope: {call_kwargs['scope']}")
|
|
print(f" duration: {call_kwargs['duration']:.3f}s")
|
|
print(f" input_tokens: {call_kwargs['input_tokens']}")
|
|
print(f" output_tokens: {call_kwargs['output_tokens']}")
|
|
print(f" response: {response}")
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_llm_metrics_recorded_for_structured_output():
|
|
"""
|
|
Test that LLM metrics are recorded for structured output (JSON) calls.
|
|
"""
|
|
api_key = get_groq_api_key()
|
|
if not api_key:
|
|
pytest.skip("Skipping: GROQ_API_KEY not set")
|
|
|
|
from pydantic import BaseModel
|
|
|
|
class SimpleResponse(BaseModel):
|
|
greeting: str
|
|
language: str
|
|
|
|
mock_collector = MagicMock(spec=MetricsCollector)
|
|
|
|
# Patch the provider module where get_metrics_collector is actually called
|
|
with patch("hindsight_api.engine.providers.openai_compatible_llm.get_metrics_collector", return_value=mock_collector):
|
|
llm = LLMProvider(
|
|
provider="groq",
|
|
api_key=api_key,
|
|
base_url="",
|
|
model="openai/gpt-oss-20b",
|
|
)
|
|
|
|
# Make a structured output call
|
|
response = await llm.call(
|
|
messages=[{"role": "user", "content": "Say hello in French. Return greeting and language."}],
|
|
response_format=SimpleResponse,
|
|
max_completion_tokens=100,
|
|
scope="structured_output_test",
|
|
)
|
|
|
|
# Verify structured response
|
|
assert isinstance(response, SimpleResponse)
|
|
assert response.greeting is not None
|
|
assert response.language is not None
|
|
|
|
# Verify record_llm_call was called
|
|
assert mock_collector.record_llm_call.called, "record_llm_call should have been called"
|
|
|
|
call_kwargs = mock_collector.record_llm_call.call_args.kwargs
|
|
assert call_kwargs["input_tokens"] > 0
|
|
assert call_kwargs["output_tokens"] > 0
|
|
|
|
print(f"\nStructured output LLM metrics:")
|
|
print(f" greeting: {response.greeting}")
|
|
print(f" language: {response.language}")
|
|
print(f" input_tokens: {call_kwargs['input_tokens']}")
|
|
print(f" output_tokens: {call_kwargs['output_tokens']}")
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_noop_collector_when_metrics_disabled():
|
|
"""
|
|
Test that NoOpMetricsCollector is returned when metrics are not initialized.
|
|
This verifies the fallback behavior doesn't break LLM calls.
|
|
"""
|
|
api_key = get_groq_api_key()
|
|
if not api_key:
|
|
pytest.skip("Skipping: GROQ_API_KEY not set")
|
|
|
|
# Without initializing metrics, get_metrics_collector returns NoOpMetricsCollector
|
|
collector = get_metrics_collector()
|
|
assert isinstance(collector, NoOpMetricsCollector), "Should return NoOpMetricsCollector when not initialized"
|
|
|
|
# Make an LLM call - should work fine with NoOp collector
|
|
llm = LLMProvider(
|
|
provider="groq",
|
|
api_key=api_key,
|
|
base_url="",
|
|
model="openai/gpt-oss-20b",
|
|
)
|
|
|
|
response = await llm.call(
|
|
messages=[{"role": "user", "content": "Say 'test' in one word."}],
|
|
max_completion_tokens=50,
|
|
)
|
|
|
|
assert response is not None
|
|
print(f"\nLLM call succeeded with NoOpMetricsCollector: {response}")
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_return_usage_returns_tuple():
|
|
"""
|
|
Test that return_usage=True returns (result, TokenUsage) tuple.
|
|
"""
|
|
from hindsight_api.engine.response_models import TokenUsage
|
|
|
|
api_key = get_groq_api_key()
|
|
if not api_key:
|
|
pytest.skip("Skipping: GROQ_API_KEY not set")
|
|
|
|
llm = LLMProvider(
|
|
provider="groq",
|
|
api_key=api_key,
|
|
base_url="",
|
|
model="openai/gpt-oss-20b",
|
|
)
|
|
|
|
# Call with return_usage=True
|
|
result, usage = await llm.call(
|
|
messages=[
|
|
{"role": "system", "content": "You are a helpful assistant."},
|
|
{"role": "user", "content": "What is 2+2? Reply with just the number."}
|
|
],
|
|
max_completion_tokens=50,
|
|
return_usage=True,
|
|
)
|
|
|
|
# Verify result is the response text
|
|
assert result is not None
|
|
assert isinstance(result, str)
|
|
|
|
# Verify usage is TokenUsage model with valid counts
|
|
assert isinstance(usage, TokenUsage)
|
|
assert usage.input_tokens > 0, f"Expected input_tokens > 0, got {usage.input_tokens}"
|
|
assert usage.output_tokens >= 0, f"Expected output_tokens >= 0, got {usage.output_tokens}"
|
|
assert usage.total_tokens == usage.input_tokens + usage.output_tokens
|
|
|
|
print(f"\nreturn_usage=True test:")
|
|
print(f" result: {result}")
|
|
print(f" usage: {usage}")
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_return_usage_with_structured_output():
|
|
"""
|
|
Test that return_usage=True works with structured output (JSON).
|
|
"""
|
|
from pydantic import BaseModel
|
|
from hindsight_api.engine.response_models import TokenUsage
|
|
|
|
api_key = get_groq_api_key()
|
|
if not api_key:
|
|
pytest.skip("Skipping: GROQ_API_KEY not set")
|
|
|
|
class MathAnswer(BaseModel):
|
|
answer: int
|
|
explanation: str
|
|
|
|
llm = LLMProvider(
|
|
provider="groq",
|
|
api_key=api_key,
|
|
base_url="",
|
|
model="openai/gpt-oss-20b",
|
|
)
|
|
|
|
# Call with return_usage=True and structured output
|
|
result, usage = await llm.call(
|
|
messages=[{"role": "user", "content": "What is 5+3? Return the answer and a brief explanation."}],
|
|
response_format=MathAnswer,
|
|
max_completion_tokens=100,
|
|
return_usage=True,
|
|
)
|
|
|
|
# Verify result is the parsed response
|
|
assert isinstance(result, MathAnswer)
|
|
assert result.answer == 8
|
|
assert result.explanation is not None
|
|
|
|
# Verify usage is TokenUsage model
|
|
assert isinstance(usage, TokenUsage)
|
|
assert usage.input_tokens > 0
|
|
assert usage.output_tokens > 0
|
|
|
|
print(f"\nStructured output with return_usage=True:")
|
|
print(f" result: {result}")
|
|
print(f" usage: {usage}")
|