fleet-memory/hindsight-api-slim/tests/test_config_validation.py
Nicolò Boschi 15ea23d5d6
feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560)
* 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)
2026-03-13 13:50:03 +01:00

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.