* 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)
109 lines
3.8 KiB
Python
109 lines
3.8 KiB
Python
"""
|
|
Tests for configuration validation.
|
|
|
|
Verifies that config validation catches invalid parameter combinations.
|
|
"""
|
|
|
|
import os
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def setup_test_env():
|
|
"""Set up environment for each test, restoring original values after."""
|
|
from hindsight_api.config import clear_config_cache
|
|
|
|
# Save original environment values
|
|
env_vars_to_save = [
|
|
"HINDSIGHT_API_RETAIN_MAX_COMPLETION_TOKENS",
|
|
"HINDSIGHT_API_RETAIN_CHUNK_SIZE",
|
|
"HINDSIGHT_API_LLM_PROVIDER",
|
|
"HINDSIGHT_API_LLM_MODEL",
|
|
]
|
|
|
|
# Save original values
|
|
original_values = {}
|
|
for key in env_vars_to_save:
|
|
original_values[key] = os.environ.get(key)
|
|
|
|
clear_config_cache()
|
|
|
|
yield
|
|
|
|
# Restore original environment
|
|
for key, original_value in original_values.items():
|
|
if original_value is None:
|
|
os.environ.pop(key, None)
|
|
else:
|
|
os.environ[key] = original_value
|
|
|
|
clear_config_cache()
|
|
|
|
|
|
def test_retain_max_completion_tokens_must_be_greater_than_chunk_size():
|
|
"""Test that RETAIN_MAX_COMPLETION_TOKENS > RETAIN_CHUNK_SIZE validation works."""
|
|
from hindsight_api.config import HindsightConfig
|
|
|
|
# Set invalid config: max_completion_tokens <= chunk_size
|
|
os.environ["HINDSIGHT_API_RETAIN_MAX_COMPLETION_TOKENS"] = "1000"
|
|
os.environ["HINDSIGHT_API_RETAIN_CHUNK_SIZE"] = "2000"
|
|
os.environ["HINDSIGHT_API_LLM_PROVIDER"] = "mock"
|
|
|
|
# Should raise ValueError with helpful message
|
|
with pytest.raises(ValueError) as exc_info:
|
|
HindsightConfig.from_env()
|
|
|
|
error_message = str(exc_info.value)
|
|
|
|
# Verify error message contains helpful information
|
|
assert "HINDSIGHT_API_RETAIN_MAX_COMPLETION_TOKENS" in error_message
|
|
assert "1000" in error_message
|
|
assert "HINDSIGHT_API_RETAIN_CHUNK_SIZE" in error_message
|
|
assert "2000" in error_message
|
|
assert "must be greater than" in error_message
|
|
assert "You have two options to fix this:" in error_message
|
|
assert "Increase HINDSIGHT_API_RETAIN_MAX_COMPLETION_TOKENS" in error_message
|
|
assert "Use a model that supports" in error_message
|
|
|
|
|
|
def test_retain_max_completion_tokens_equal_to_chunk_size_fails():
|
|
"""Test that RETAIN_MAX_COMPLETION_TOKENS == RETAIN_CHUNK_SIZE also fails."""
|
|
from hindsight_api.config import HindsightConfig
|
|
|
|
# Set invalid config: max_completion_tokens == chunk_size
|
|
os.environ["HINDSIGHT_API_RETAIN_MAX_COMPLETION_TOKENS"] = "3000"
|
|
os.environ["HINDSIGHT_API_RETAIN_CHUNK_SIZE"] = "3000"
|
|
os.environ["HINDSIGHT_API_LLM_PROVIDER"] = "mock"
|
|
|
|
# Should raise ValueError
|
|
with pytest.raises(ValueError) as exc_info:
|
|
HindsightConfig.from_env()
|
|
|
|
error_message = str(exc_info.value)
|
|
assert "must be greater than" in error_message
|
|
|
|
|
|
def test_valid_retain_config_succeeds():
|
|
"""Test that valid config with max_completion_tokens > chunk_size works."""
|
|
from hindsight_api.config import HindsightConfig
|
|
|
|
# Set valid config: max_completion_tokens > chunk_size
|
|
os.environ["HINDSIGHT_API_RETAIN_MAX_COMPLETION_TOKENS"] = "64000"
|
|
os.environ["HINDSIGHT_API_RETAIN_CHUNK_SIZE"] = "3000"
|
|
os.environ["HINDSIGHT_API_LLM_PROVIDER"] = "mock"
|
|
|
|
# Should not raise
|
|
config = HindsightConfig.from_env()
|
|
assert config.retain_max_completion_tokens == 64000
|
|
assert config.retain_chunk_size == 3000
|
|
|
|
|
|
# Note: The BadRequestError wrapping is implemented in fact_extraction.py
|
|
# but requires a complex integration test setup. The functionality is
|
|
# straightforward: when a BadRequestError containing keywords like
|
|
# "max_tokens", "max_completion_tokens", or "maximum context" is caught,
|
|
# it's wrapped in a ValueError with helpful guidance.
|
|
#
|
|
# The config validation tests above ensure users get early feedback
|
|
# about invalid configurations before runtime errors occur.
|