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.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
from __future__ import annotations
import pytest
from headroom.proxy.memory_injection_mode_policy import (
MEMORY_INJECTION_MODE_DEFAULT,
resolve_memory_injection_mode,
)
def test_resolve_memory_injection_mode_defaults_for_missing_value() -> None:
assert resolve_memory_injection_mode(None) == MEMORY_INJECTION_MODE_DEFAULT
assert resolve_memory_injection_mode("") == MEMORY_INJECTION_MODE_DEFAULT
assert resolve_memory_injection_mode(" ") == MEMORY_INJECTION_MODE_DEFAULT
def test_resolve_memory_injection_mode_accepts_known_values_case_insensitively() -> None:
assert resolve_memory_injection_mode("live_zone_tail") == "live_zone_tail"
assert resolve_memory_injection_mode(" DISABLED ") == "disabled"
assert resolve_memory_injection_mode(" Tool ") == "tool"
def test_get_memory_injection_mode_accepts_tool_from_env(monkeypatch: pytest.MonkeyPatch) -> None:
# Documented in memory_decision.py (mode_tool); must not raise per request.
from headroom.proxy.helpers import get_memory_injection_mode
monkeypatch.setenv("HEADROOM_MEMORY_INJECTION_MODE", "tool")
assert get_memory_injection_mode() == "tool"
def test_resolve_memory_injection_mode_rejects_unknown_values() -> None:
with pytest.raises(ValueError, match="HEADROOM_MEMORY_INJECTION_MODE"):
resolve_memory_injection_mode("system_prompt")
async def test_tool_mode_skips_context_search_but_keeps_decision_open(
monkeypatch: pytest.MonkeyPatch,
) -> None:
"""tool mode: no auto-injected context, memory tools stay registrable."""
from headroom.proxy.memory_decision import MemoryDecision
from headroom.proxy.memory_handler import MemoryConfig, MemoryHandler
monkeypatch.setenv("HEADROOM_MEMORY_INJECTION_MODE", "tool")
handler = MemoryHandler(MemoryConfig(enabled=True, backend="local"))
messages = [{"role": "user", "content": "what did I say about databases?"}]
assert await handler.search_and_format_context("u1", messages) is None
assert handler._initialized is False # returned before any backend lookup
decision = MemoryDecision.decide(
headers={}, memory_handler=handler, memory_user_id="u1", mode_name="tool"
)
assert decision.inject is True