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

143 lines
5.2 KiB
Python

"""
Tests for agent management API (profile, disposition).
"""
import pytest
import uuid
from hindsight_api import MemoryEngine, RequestContext
from hindsight_api.api import CreateBankRequest, DispositionTraits
from hindsight_api.engine.memory_engine import Budget
def unique_agent_id(prefix: str) -> str:
"""Generate a unique agent ID for testing."""
return f"{prefix}_{uuid.uuid4().hex[:8]}"
class TestAgentProfile:
"""Tests for agent profile management."""
@pytest.mark.asyncio
async def test_get_agent_profile_creates_default(self, memory: MemoryEngine, request_context):
"""Test that getting a profile for a new agent creates default disposition."""
bank_id = unique_agent_id("test_profile_default")
profile = await memory.get_bank_profile(bank_id, request_context=request_context)
assert profile is not None
assert "disposition" in profile
disposition = profile["disposition"]
assert disposition["skepticism"] == 3
assert disposition["literalism"] == 3
assert disposition["empathy"] == 3
@pytest.mark.asyncio
async def test_update_agent_disposition(self, memory: MemoryEngine, request_context):
"""Test updating agent disposition traits."""
bank_id = unique_agent_id("test_profile_update")
profile = await memory.get_bank_profile(bank_id, request_context=request_context)
assert profile["disposition"]["skepticism"] == 3
new_disposition = {
"skepticism": 5,
"literalism": 4,
"empathy": 2,
}
await memory.update_bank_disposition(bank_id, new_disposition, request_context=request_context)
updated_profile = await memory.get_bank_profile(bank_id, request_context=request_context)
disposition = updated_profile["disposition"]
assert disposition["skepticism"] == new_disposition["skepticism"]
assert disposition["literalism"] == new_disposition["literalism"]
assert disposition["empathy"] == new_disposition["empathy"]
@pytest.mark.asyncio
async def test_list_agents(self, memory: MemoryEngine, request_context):
"""Test listing all agents."""
agent_id_1 = unique_agent_id("test_list")
agent_id_2 = unique_agent_id("test_list")
agent_id_3 = unique_agent_id("test_list")
await memory.get_bank_profile(agent_id_1, request_context=request_context)
await memory.get_bank_profile(agent_id_2, request_context=request_context)
await memory.get_bank_profile(agent_id_3, request_context=request_context)
agents = await memory.list_banks(request_context=request_context)
agent_ids = [a["bank_id"] for a in agents]
assert agent_id_1 in agent_ids
assert agent_id_2 in agent_ids
assert agent_id_3 in agent_ids
for agent in agents:
assert "bank_id" in agent
assert "disposition" in agent
assert "created_at" in agent
assert "updated_at" in agent
class TestAgentEndpoint:
"""Tests for agent PUT endpoint logic."""
@pytest.mark.asyncio
async def test_put_agent_create(self, memory: MemoryEngine, request_context):
"""Test creating an agent via PUT endpoint."""
bank_id = unique_agent_id("test_put_create")
request = CreateBankRequest(
disposition=DispositionTraits(
skepticism=4,
literalism=5,
empathy=2
),
)
profile = await memory.get_bank_profile(bank_id, request_context=request_context)
if request.disposition is not None:
await memory.update_bank_disposition(
bank_id,
request.disposition.model_dump(),
request_context=request_context,
)
final_profile = await memory.get_bank_profile(bank_id, request_context=request_context)
assert final_profile["disposition"]["skepticism"] == 4
assert final_profile["disposition"]["literalism"] == 5
class TestAgentDispositionIntegration:
"""Tests for disposition integration with other features."""
@pytest.mark.asyncio
async def test_think_uses_disposition(self, memory: MemoryEngine, request_context):
"""Test that THINK operation uses agent disposition."""
bank_id = unique_agent_id("test_think")
disposition = {
"skepticism": 5, # Very skeptical
"literalism": 4, # High literalism
"empathy": 2, # Low empathy
}
await memory.update_bank_disposition(bank_id, disposition, request_context=request_context)
await memory.retain_batch_async(
bank_id=bank_id,
contents=[
{"content": "Traditional painting techniques have been used for centuries"},
{"content": "Modern digital art is changing the art world"}
],
request_context=request_context,
)
result = await memory.reflect_async(
bank_id=bank_id,
query="What do you think about traditional vs modern art?",
budget=Budget.LOW,
request_context=request_context,
)
assert result.text is not None
assert len(result.text) > 0