fleet-memory/hindsight-api-slim/tests/test_provider_default_models.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

123 lines
5 KiB
Python

"""Test provider-specific default models in config."""
import os
import pytest
def test_provider_default_models():
"""Test that each provider has a default model and it's used when model is not explicitly set."""
from hindsight_api.config import PROVIDER_DEFAULT_MODELS, HindsightConfig, clear_config_cache
# Save original env vars
original_provider = os.environ.get("HINDSIGHT_API_LLM_PROVIDER")
original_model = os.environ.get("HINDSIGHT_API_LLM_MODEL")
try:
# Test each provider has a default
for provider, expected_model in PROVIDER_DEFAULT_MODELS.items():
clear_config_cache()
os.environ["HINDSIGHT_API_LLM_PROVIDER"] = provider
# Remove explicit model setting to test default
if "HINDSIGHT_API_LLM_MODEL" in os.environ:
del os.environ["HINDSIGHT_API_LLM_MODEL"]
config = HindsightConfig.from_env()
assert config.llm_provider == provider, f"Provider mismatch for {provider}"
assert config.llm_model == expected_model, f"Expected {expected_model} for {provider}, got {config.llm_model}"
finally:
# Restore original env vars
clear_config_cache()
if original_provider:
os.environ["HINDSIGHT_API_LLM_PROVIDER"] = original_provider
elif "HINDSIGHT_API_LLM_PROVIDER" in os.environ:
del os.environ["HINDSIGHT_API_LLM_PROVIDER"]
if original_model:
os.environ["HINDSIGHT_API_LLM_MODEL"] = original_model
elif "HINDSIGHT_API_LLM_MODEL" in os.environ:
del os.environ["HINDSIGHT_API_LLM_MODEL"]
def test_explicit_model_overrides_provider_default():
"""Test that explicit model setting overrides provider default."""
from hindsight_api.config import HindsightConfig, clear_config_cache
original_provider = os.environ.get("HINDSIGHT_API_LLM_PROVIDER")
original_model = os.environ.get("HINDSIGHT_API_LLM_MODEL")
try:
clear_config_cache()
os.environ["HINDSIGHT_API_LLM_PROVIDER"] = "anthropic"
os.environ["HINDSIGHT_API_LLM_MODEL"] = "claude-sonnet-4-5-20250929"
config = HindsightConfig.from_env()
assert config.llm_provider == "anthropic"
assert config.llm_model == "claude-sonnet-4-5-20250929", "Explicit model should override default"
finally:
clear_config_cache()
if original_provider:
os.environ["HINDSIGHT_API_LLM_PROVIDER"] = original_provider
elif "HINDSIGHT_API_LLM_PROVIDER" in os.environ:
del os.environ["HINDSIGHT_API_LLM_PROVIDER"]
if original_model:
os.environ["HINDSIGHT_API_LLM_MODEL"] = original_model
elif "HINDSIGHT_API_LLM_MODEL" in os.environ:
del os.environ["HINDSIGHT_API_LLM_MODEL"]
def test_per_operation_provider_default_model():
"""Test that per-operation providers use their own default models."""
from hindsight_api.config import HindsightConfig, clear_config_cache
original_provider = os.environ.get("HINDSIGHT_API_LLM_PROVIDER")
original_model = os.environ.get("HINDSIGHT_API_LLM_MODEL")
original_retain_provider = os.environ.get("HINDSIGHT_API_RETAIN_LLM_PROVIDER")
original_retain_model = os.environ.get("HINDSIGHT_API_RETAIN_LLM_MODEL")
try:
clear_config_cache()
os.environ["HINDSIGHT_API_LLM_PROVIDER"] = "openai"
# Remove explicit model to use provider default
if "HINDSIGHT_API_LLM_MODEL" in os.environ:
del os.environ["HINDSIGHT_API_LLM_MODEL"]
# Set retain-specific provider but not model
os.environ["HINDSIGHT_API_RETAIN_LLM_PROVIDER"] = "anthropic"
if "HINDSIGHT_API_RETAIN_LLM_MODEL" in os.environ:
del os.environ["HINDSIGHT_API_RETAIN_LLM_MODEL"]
config = HindsightConfig.from_env()
# Global LLM should use OpenAI default
assert config.llm_model == "gpt-4o-mini", f"Expected gpt-4o-mini, got {config.llm_model}"
# Retain should use Anthropic default
assert (
config.retain_llm_model == "claude-haiku-4-5-20251001"
), f"Expected claude-haiku-4-5-20251001, got {config.retain_llm_model}"
finally:
clear_config_cache()
if original_provider:
os.environ["HINDSIGHT_API_LLM_PROVIDER"] = original_provider
elif "HINDSIGHT_API_LLM_PROVIDER" in os.environ:
del os.environ["HINDSIGHT_API_LLM_PROVIDER"]
if original_model:
os.environ["HINDSIGHT_API_LLM_MODEL"] = original_model
elif "HINDSIGHT_API_LLM_MODEL" in os.environ:
del os.environ["HINDSIGHT_API_LLM_MODEL"]
if original_retain_provider:
os.environ["HINDSIGHT_API_RETAIN_LLM_PROVIDER"] = original_retain_provider
elif "HINDSIGHT_API_RETAIN_LLM_PROVIDER" in os.environ:
del os.environ["HINDSIGHT_API_RETAIN_LLM_PROVIDER"]
if original_retain_model:
os.environ["HINDSIGHT_API_RETAIN_LLM_MODEL"] = original_retain_model
elif "HINDSIGHT_API_RETAIN_LLM_MODEL" in os.environ:
del os.environ["HINDSIGHT_API_RETAIN_LLM_MODEL"]