Skip to content

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Merge upstream/main into feat/canonical-pipeline

JerrettDavis87a13ef2cd61
diff --cc tests/test_cli/test_wrap_copilot.py
index 0d948ec32,792feea84..a18e627a1
--- a/tests/test_cli/test_wrap_copilot.py
+++ b/tests/test_cli/test_wrap_copilot.py
@@@ -2,14 -2,15 +2,28 @@@
from __future__ import annotations
++import sys
++import types
from pathlib import Path
from unittest.mock import patch
import pytest
from click.testing import CliRunner
++if "fastapi" not in sys.modules:
++ fastapi_mod = types.ModuleType("fastapi")
++ fastapi_mod.FastAPI = type("FastAPI", (), {})
++ fastapi_mod.Request = type("Request", (), {})
++ fastapi_mod.WebSocket = type("WebSocket", (), {})
++ sys.modules["fastapi"] = fastapi_mod
++
++if "fastapi.responses" not in sys.modules:
++ responses_mod = types.ModuleType("fastapi.responses")
++ responses_mod.Response = type("Response", (), {})
++ sys.modules["fastapi.responses"] = responses_mod
++
from headroom.cli import wrap as wrap_cli
from headroom.cli.main import main
-from headroom.copilot_auth import DEFAULT_API_URL
@pytest.fixture