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
"""Tests for pure memory query construction policy."""
from __future__ import annotations
from headroom.proxy.memory_query_policy import (
ASSISTANT_DELIM,
TOOL_DELIM,
USER_DELIM,
extract_memory_query_sources,
render_embedding_input,
)
def test_bounded_embedding_keeps_primary_question_and_context_tails() -> None:
user = "古い質問" * 2000 + " latest JWT question"
tool = "old tool output " * 1000 + " latest authentication failure"
assistant = "old assistant context " * 1000 + " inspect auth.py"
rendered = render_embedding_input(
user_text=user,
recent_tool_outputs=(tool,),
recent_assistant_turns=(assistant,),
max_chars=4096,
)
assert len(rendered) <= 4096
assert rendered.startswith(USER_DELIM + user[-2048:])
assert TOOL_DELIM + tool[-512:] in rendered
assert ASSISTANT_DELIM + assistant[-512:] in rendered
def test_bounded_embedding_spends_remaining_budget_on_newest_context() -> None:
rendered = render_embedding_input(
user_text="latest question",
recent_tool_outputs=tuple("x" * 600 + f" end-{i}" for i in range(10)),
recent_assistant_turns=("old background",),
max_chars=1200,
)
assert len(rendered) <= 1200
assert rendered.startswith(USER_DELIM + "latest question")
assert "end-9" in rendered and "end-8" in rendered
assert "end-0" not in rendered
assert "old background" not in rendered
def test_zero_embedding_budget_does_not_send_context_without_the_question() -> None:
assert (
render_embedding_input(
user_text="question",
recent_tool_outputs=("tool context",),
recent_assistant_turns=("assistant context",),
max_chars=0,
)
== ""
)
def test_extract_sources_uses_latest_user_and_recent_context_in_order() -> None:
messages = [
{"role": "user", "content": "first"},
{"role": "assistant", "content": "a1"},
{"role": "tool", "content": "t1"},
{"role": "assistant", "content": "a2"},
{"role": "tool", "content": "t2"},
{"role": "user", "content": "second"},
]
user_text, tool_outputs, assistant_turns = extract_memory_query_sources(
messages,
lookback_assistant=2,
lookback_tools=2,
)
assert user_text == "second"
assert tool_outputs == ("t1", "t2")
assert assistant_turns == ("a1", "a2")
def test_extract_sources_handles_anthropic_tool_result_without_user_text() -> None:
messages = [
{"role": "user", "content": "real user"},
{
"role": "user",
"content": [{"type": "tool_result", "content": [{"type": "text", "text": "nested"}]}],
},
]
user_text, tool_outputs, assistant_turns = extract_memory_query_sources(messages)
assert user_text == "real user"
assert tool_outputs == ("nested",)
assert assistant_turns == ()
def test_extract_sources_captures_anthropic_user_text_blocks() -> None:
"""Anthropic user turns carry the prompt as text blocks (the standard Claude
Code shape). The user's question must be captured — not dropped — so memory
retrieval keys on it."""
messages = [
{"role": "user", "content": [{"type": "text", "text": "help me refactor auth"}]},
]
user_text, _tool_outputs, _assistant_turns = extract_memory_query_sources(messages)
assert user_text == "help me refactor auth"
def test_extract_sources_skips_system_reminder_blocks() -> None:
"""Claude Code appends <system-reminder> harness blocks to the user turn.
Concatenated into the embedding input they dilute the real question below the
similarity floor so nothing is retrieved (#2195); they must be filtered out."""
messages = [
{
"role": "user",
"content": [
{"type": "text", "text": "how do I add caching to the auth handler?"},
{
"type": "text",
"text": "<system-reminder>\nThe user opened file x.\n</system-reminder>",
},
],
},
]
user_text, _tool_outputs, _assistant_turns = extract_memory_query_sources(messages)
assert user_text == "how do I add caching to the auth handler?"
assert "system-reminder" not in user_text
def test_extract_sources_reminder_only_turn_yields_no_user_text() -> None:
messages = [
{
"role": "user",
"content": [{"type": "text", "text": "<system-reminder>x</system-reminder>"}],
},
]
user_text, _tool_outputs, _assistant_turns = extract_memory_query_sources(messages)
assert user_text == ""
def test_extract_sources_captures_user_text_alongside_tool_result() -> None:
"""A user turn mixing a tool_result and a text block yields both: the text as
the user query and the tool output as context."""
messages = [
{
"role": "user",
"content": [
{"type": "tool_result", "content": "exit 0"},
{"type": "text", "text": "did the tests pass?"},
],
},
]
user_text, tool_outputs, _assistant_turns = extract_memory_query_sources(messages)
assert user_text == "did the tests pass?"
assert tool_outputs == ("exit 0",)