mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
## Description Add CrewAI and AutoGen tool compression integrations, following the same patterns as the existing LangChain agent integration (`HeadroomToolWrapper` / `wrap_tools_with_headroom`). Both delegate compression to `compress_tool_result()` from the MCP integration, with per-tool metrics tracking via `ToolCompressionMetrics` / `ToolMetricsCollector`. Closes #1379 ## Type of Change - [x] New feature (non-breaking change that adds functionality) ## Changes Made - Add `headroom/integrations/crewai/` — `HeadroomToolWrapper` subclasses CrewAI `BaseTool`, wraps `_run()` with compression - Add `headroom/integrations/autogen/` — `HeadroomToolWrapper` wraps AutoGen `FunctionTool` (sync and async) with compression - Wire both into `headroom/integrations/__init__.py` with aliased re-exports (avoids name collision with LangChain's `HeadroomToolWrapper`) - Add `[crewai]` and `[autogen]` optional dependency extras to `pyproject.toml` - Add 24 unit tests (12 per framework) under `tests/test_integrations/` - Add `.mdx` doc pages for both frameworks under `docs/content/docs/` - Update `CHANGELOG.md` with entries under `### Added` ## Testing - [x] Unit tests pass (`pytest`) - [x] Linting passes (`ruff check .`) - [ ] Type checking passes (`mypy headroom`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output ```text $ ruff check headroom/integrations/crewai headroom/integrations/autogen tests/test_integrations/crewai tests/test_integrations/autogen All checks passed! $ pytest tests/test_integrations/autogen -v 12 passed $ pytest tests/test_integrations/crewai -v 12 passed ``` ## Real Behavior Proof - Environment: Windows 11, Python 3.11, crewai 1.14.7, autogen-agentchat 0.7.5 - Exact command / steps: Ran standalone adapter demos and benchmark runner across 4 task types - Observed result: | Task | Tokens (raw) | Tokens (compressed) | Savings | |------|-------------|-------------------|---------| | Inventory JSON (80 items) | 5,044 | 1,532 | 69.6% | | Server logs (150 lines) | 8,712 | 314 | 96.4% | | Analytics query (100 rows) | 10,762 | 10,762 | 0% | | API docs (20 endpoints) | 8,043 | 8,043 | 0% | Compression results are identical across CrewAI and AutoGen — expected since both route through the same `compress_tool_result()` pipeline. - Not tested: Full end-to-end with a live LLM agent loop (demos test the compression pipeline standalone). LangGraph not included — headroom already has `headroom/integrations/langchain/langgraph.py`. ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review ## Checklist - [x] My code follows the project's style guidelines - [x] I have performed a self-review of my code - [x] I have commented my code, particularly in hard-to-understand areas - [x] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [x] New and existing unit tests pass locally with my changes - [x] I have updated the CHANGELOG.md if applicable ## Additional Notes - LangGraph integration is intentionally excluded — headroom already has one at `headroom/integrations/langchain/langgraph.py` - Re-exports in `__init__.py` are aliased (`CrewAIToolWrapper`, `AutoGenToolWrapper`) to avoid collision with the existing LangChain `HeadroomToolWrapper` - Both integrations follow the exact same conventions as the existing LangChain agents module: optional dep guard, `compress_tool_result()` delegation, metrics with 1000-entry cap, Google-style docstrings - `mypy` not checked due to Rust build dependency (`maturin`) that requires Application Control policy changes on this machine --------- Co-authored-by: Sneha27feb <sroy27.ai@gmail.com>
262 lines
8.1 KiB
Python
262 lines
8.1 KiB
Python
"""Tests for CrewAI agent tool integration.
|
|
|
|
Tests cover:
|
|
1. ToolCompressionMetrics - Dataclass for tool compression metrics
|
|
2. ToolMetricsCollector - Collector for compression metrics
|
|
3. HeadroomToolWrapper - Wrapper for CrewAI tools with compression
|
|
4. wrap_tools_with_headroom - Convenience function for wrapping multiple tools
|
|
5. get_tool_metrics / reset_tool_metrics - Global metrics access
|
|
"""
|
|
|
|
from datetime import datetime
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
try:
|
|
from crewai.tools.base_tool import tool as crewai_tool
|
|
|
|
CREWAI_AVAILABLE = True
|
|
except ImportError:
|
|
CREWAI_AVAILABLE = False
|
|
|
|
pytestmark = pytest.mark.skipif(not CREWAI_AVAILABLE, reason="CrewAI not installed")
|
|
|
|
|
|
def _make_large_output(n: int = 200) -> str:
|
|
"""Create a large JSON string to trigger compression."""
|
|
import json
|
|
|
|
return json.dumps({"items": [{"id": i, "data": "x" * 50} for i in range(n)]})
|
|
|
|
|
|
class TestToolCompressionMetrics:
|
|
"""Tests for ToolCompressionMetrics dataclass."""
|
|
|
|
def test_create_metrics(self):
|
|
from headroom.integrations.crewai.agents import ToolCompressionMetrics
|
|
|
|
metrics = ToolCompressionMetrics(
|
|
tool_name="search",
|
|
timestamp=datetime.now(),
|
|
chars_before=5000,
|
|
chars_after=2000,
|
|
chars_saved=3000,
|
|
compression_ratio=0.4,
|
|
was_compressed=True,
|
|
)
|
|
|
|
assert metrics.tool_name == "search"
|
|
assert metrics.chars_before == 5000
|
|
assert metrics.chars_saved == 3000
|
|
assert metrics.was_compressed is True
|
|
|
|
def test_metrics_all_fields_required(self):
|
|
from headroom.integrations.crewai.agents import ToolCompressionMetrics
|
|
|
|
with pytest.raises(TypeError):
|
|
ToolCompressionMetrics() # type: ignore[call-arg]
|
|
|
|
|
|
class TestToolMetricsCollector:
|
|
"""Tests for ToolMetricsCollector."""
|
|
|
|
def test_empty_summary(self):
|
|
from headroom.integrations.crewai.agents import ToolMetricsCollector
|
|
|
|
collector = ToolMetricsCollector()
|
|
summary = collector.get_summary()
|
|
assert summary["total_invocations"] == 0
|
|
assert summary["total_compressions"] == 0
|
|
|
|
def test_add_and_summary(self):
|
|
from headroom.integrations.crewai.agents import (
|
|
ToolCompressionMetrics,
|
|
ToolMetricsCollector,
|
|
)
|
|
|
|
collector = ToolMetricsCollector()
|
|
collector.add(
|
|
ToolCompressionMetrics(
|
|
tool_name="search",
|
|
timestamp=datetime.now(),
|
|
chars_before=5000,
|
|
chars_after=2000,
|
|
chars_saved=3000,
|
|
compression_ratio=0.4,
|
|
was_compressed=True,
|
|
)
|
|
)
|
|
|
|
summary = collector.get_summary()
|
|
assert summary["total_invocations"] == 1
|
|
assert summary["total_compressions"] == 1
|
|
assert summary["total_chars_saved"] == 3000
|
|
assert "search" in summary["by_tool"]
|
|
|
|
def test_caps_at_1000(self):
|
|
from headroom.integrations.crewai.agents import (
|
|
ToolCompressionMetrics,
|
|
ToolMetricsCollector,
|
|
)
|
|
|
|
collector = ToolMetricsCollector()
|
|
for _i in range(1050):
|
|
collector.add(
|
|
ToolCompressionMetrics(
|
|
tool_name="t",
|
|
timestamp=datetime.now(),
|
|
chars_before=100,
|
|
chars_after=100,
|
|
chars_saved=0,
|
|
compression_ratio=1.0,
|
|
was_compressed=False,
|
|
)
|
|
)
|
|
assert len(collector.metrics) == 1000
|
|
|
|
|
|
class TestGlobalMetrics:
|
|
"""Tests for global metrics functions."""
|
|
|
|
def test_get_and_reset(self):
|
|
from headroom.integrations.crewai.agents import get_tool_metrics, reset_tool_metrics
|
|
|
|
metrics = get_tool_metrics()
|
|
assert metrics is not None
|
|
reset_tool_metrics()
|
|
assert get_tool_metrics() is not metrics
|
|
|
|
|
|
class TestHeadroomToolWrapper:
|
|
"""Tests for HeadroomToolWrapper."""
|
|
|
|
@patch("headroom.integrations.crewai.agents.compress_tool_result")
|
|
def test_skips_short_output(self, mock_compress):
|
|
from headroom.integrations.crewai.agents import HeadroomToolWrapper, ToolMetricsCollector
|
|
|
|
@crewai_tool
|
|
def small_tool(query: str) -> str:
|
|
"""Return small output."""
|
|
return "short"
|
|
|
|
collector = ToolMetricsCollector()
|
|
wrapper = HeadroomToolWrapper(
|
|
small_tool,
|
|
min_chars_to_compress=1000,
|
|
metrics_collector=collector,
|
|
)
|
|
|
|
result = wrapper.run(query="test")
|
|
assert result == "short"
|
|
mock_compress.assert_not_called()
|
|
assert collector.get_summary()["total_compressions"] == 0
|
|
|
|
@patch("headroom.integrations.crewai.agents.compress_tool_result")
|
|
def test_compresses_large_output(self, mock_compress):
|
|
from headroom.integrations.crewai.agents import HeadroomToolWrapper, ToolMetricsCollector
|
|
|
|
large = _make_large_output()
|
|
mock_compress.return_value = "compressed"
|
|
|
|
@crewai_tool
|
|
def big_tool(query: str) -> str:
|
|
"""Return large output."""
|
|
return large
|
|
|
|
collector = ToolMetricsCollector()
|
|
wrapper = HeadroomToolWrapper(
|
|
big_tool,
|
|
min_chars_to_compress=100,
|
|
metrics_collector=collector,
|
|
)
|
|
|
|
result = wrapper.run(query="test")
|
|
assert result == "compressed"
|
|
mock_compress.assert_called_once()
|
|
assert collector.get_summary()["total_compressions"] == 1
|
|
|
|
@patch(
|
|
"headroom.integrations.crewai.agents.compress_tool_result",
|
|
side_effect=RuntimeError("boom"),
|
|
)
|
|
def test_passes_through_on_error(self, mock_compress):
|
|
from headroom.integrations.crewai.agents import HeadroomToolWrapper, ToolMetricsCollector
|
|
|
|
large = _make_large_output()
|
|
|
|
@crewai_tool
|
|
def flaky_tool(query: str) -> str:
|
|
"""Return large output."""
|
|
return large
|
|
|
|
collector = ToolMetricsCollector()
|
|
wrapper = HeadroomToolWrapper(
|
|
flaky_tool,
|
|
min_chars_to_compress=100,
|
|
metrics_collector=collector,
|
|
)
|
|
|
|
result = wrapper.run(query="test")
|
|
assert result == large
|
|
assert collector.get_summary()["total_compressions"] == 0
|
|
|
|
def test_preserves_tool_metadata(self):
|
|
from headroom.integrations.crewai.agents import HeadroomToolWrapper
|
|
|
|
@crewai_tool
|
|
def my_fn(x: int) -> str:
|
|
"""Do something useful."""
|
|
return str(x)
|
|
|
|
wrapper = HeadroomToolWrapper(my_fn)
|
|
assert wrapper.name == "my_fn"
|
|
assert wrapper.description == "Do something useful."
|
|
|
|
|
|
class TestWrapToolsWithHeadroom:
|
|
"""Tests for wrap_tools_with_headroom convenience function."""
|
|
|
|
@patch("headroom.integrations.crewai.agents.compress_tool_result")
|
|
def test_wraps_multiple_tools(self, mock_compress):
|
|
from headroom.integrations.crewai.agents import wrap_tools_with_headroom
|
|
|
|
@crewai_tool
|
|
def tool_a(q: str) -> str:
|
|
"""Tool A."""
|
|
return "a"
|
|
|
|
@crewai_tool
|
|
def tool_b(q: str) -> str:
|
|
"""Tool B."""
|
|
return "b"
|
|
|
|
wrapped = wrap_tools_with_headroom([tool_a, tool_b])
|
|
assert len(wrapped) == 2
|
|
assert wrapped[0].name == "tool_a"
|
|
assert wrapped[1].name == "tool_b"
|
|
|
|
@patch("headroom.integrations.crewai.agents.compress_tool_result")
|
|
def test_shared_metrics(self, mock_compress):
|
|
from headroom.integrations.crewai.agents import (
|
|
ToolMetricsCollector,
|
|
wrap_tools_with_headroom,
|
|
)
|
|
|
|
large = _make_large_output()
|
|
mock_compress.return_value = "compressed"
|
|
|
|
@crewai_tool
|
|
def big(q: str) -> str:
|
|
"""Big tool."""
|
|
return large
|
|
|
|
collector = ToolMetricsCollector()
|
|
wrapped = wrap_tools_with_headroom(
|
|
[big],
|
|
min_chars_to_compress=100,
|
|
metrics_collector=collector,
|
|
)
|
|
|
|
wrapped[0].run(q="test")
|
|
assert collector.get_summary()["total_invocations"] == 1
|