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
fix(compression): reject lossy unmarked tool output in unit router path (#1479)
Rod Boevde24cd5fc0b8
diff --git a/headroom/transforms/compression_units.py b/headroom/transforms/compression_units.pyindex e0c678fdf..0cfd6757e 100644--- a/headroom/transforms/compression_units.py+++ b/headroom/transforms/compression_units.py@@ -110,6 +110,17 @@ _CCR_MARKER_RE = re.compile(r"(?m)^.*(?:Retrieve more: hash=|Retrieve original: hash=|<<ccr:[^>]+>>).*$")+_LOSSY_UNMARKED_STRATEGIES = {+ CompressionStrategy.KOMPRESS.value,+ CompressionStrategy.TEXT.value,+ CompressionStrategy.CODE_AWARE.value,+}+++def _is_structured_shell_output(text: str) -> bool:+ nonempty_lines = [line for line in text.splitlines() if line.strip()]+ return len(nonempty_lines) >= 3+def find_content_router(transforms: object) -> ContentRouter | None:"""Return the first ContentRouter in a pipeline or iterable."""@@ -325,6 +336,19 @@ def compress_unit_with_router(reason="rejected_not_smaller",)+ if (+ unit.role == "tool"+ and unit.item_type == "local_shell_call_output"+ and _is_structured_shell_output(unit.text)+ and strategy in _LOSSY_UNMARKED_STRATEGIES+ ):+ if not _CCR_MARKER_RE.search(replacement):+ return _with_reason(+ strategy=strategy,+ router_result=router_result,+ reason="lossy_unrecoverable_tool_output",+ )+return UnitCompressionResult(original=unit.text,compressed=replacement,diff --git a/tests/test_compression_units.py b/tests/test_compression_units.pyindex 870f3563d..6081a447e 100644--- a/tests/test_compression_units.py+++ b/tests/test_compression_units.py@@ -35,18 +35,103 @@ def test_compression_unit_accepts_token_shrinking_replacement():text="alpha beta gamma delta epsilon",provider="openai",endpoint="responses",+ role="assistant",+ item_type="message",+ metadata={"compress_assistant": "true"},+ min_bytes=1,+ ),+ router=Router("alpha beta"),+ tokenizer=TokenCounter(),+ )++ assert result.modified is True+ assert result.tokens_saved == 3+ assert result.compressed == "alpha beta"+ assert "router:openai:responses:message:kompress" in result.transforms_applied+++def test_compression_unit_keeps_lossy_unmarked_tool_output_verbatim():+ original = (+ "src/app.py:12 render shell status panel\n"+ "src/ui.py:44 draw health badge\n"+ "src/theme.py:9 set accent color"+ )+ result = compress_unit_with_router(+ CompressionUnit(+ text=original,+ provider="openai",+ endpoint="responses",+ role="tool",+ item_type="local_shell_call_output",+ min_bytes=1,+ ),+ router=Router("shell output looks organized and green"),+ tokenizer=TokenCounter(),+ )++ assert result.modified is False+ assert result.reason == "lossy_unrecoverable_tool_output"+ assert result.original == original+ assert result.compressed == original+++def test_compression_unit_accepts_lossy_tool_output_when_recoverable():+ original = "alpha beta gamma delta epsilon zeta eta theta"+ result = compress_unit_with_router(+ CompressionUnit(+ text=original,+ provider="openai",+ endpoint="responses",role="tool",item_type="local_shell_call_output",min_bytes=1,),+ router=Router("summary <<ccr:abc123>>"),+ tokenizer=TokenCounter(),+ )++ assert result.modified is True+ assert result.reason is None+ assert result.compressed == "summary <<ccr:abc123>>"+++def test_compression_unit_still_compresses_non_shell_tool_output():+ result = compress_unit_with_router(+ CompressionUnit(+ text="alpha beta gamma delta epsilon zeta eta theta",+ provider="openai",+ endpoint="responses",+ role="tool",+ item_type="function_call_output",+ min_bytes=1,+ ),+ router=Router("summary for tool=0"),+ tokenizer=TokenCounter(),+ )++ assert result.modified is True+ assert result.reason is None+ assert result.compressed == "summary for tool=0"+++def test_compression_unit_still_compresses_assistant_text():+ result = compress_unit_with_router(+ CompressionUnit(+ text="alpha beta gamma delta epsilon",+ provider="openai",+ endpoint="responses",+ role="assistant",+ item_type="message",+ min_bytes=1,+ metadata={"compress_assistant": "true"},+ ),router=Router("alpha beta"),tokenizer=TokenCounter(),)assert result.modified is True- assert result.tokens_saved == 3+ assert result.reason is Noneassert result.compressed == "alpha beta"- assert "router:openai:responses:local_shell_call_output:kompress" in result.transforms_applieddef test_compression_unit_rejects_non_shrinking_replacement():@@ -108,8 +193,9 @@ def test_batch_compression_preserves_provider_slot_references():text="alpha beta gamma",provider="openai",endpoint="responses",- role="tool",- item_type="function_call_output",+ role="assistant",+ item_type="message",+ metadata={"compress_assistant": "true"},min_bytes=1,),slot=("input", 3, "output"),