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.

fix(proxy): report disabled Kompress at startup (#4217)

lorenzozane430ea4f4ebae
diff --git a/headroom/proxy/server.py b/headroom/proxy/server.py
index 1ac5fd80f..51cb6dd73 100644
--- a/headroom/proxy/server.py
+++ b/headroom/proxy/server.py
@@ -2196,6 +2196,12 @@ class HeadroomProxy(
self._kompress_status = eager_status["kompress"]
if eager_status.get("code_aware") == "enabled":
self._code_aware_status = "enabled"
+ kompress_enabled = any(
+ transform.config.enable_kompress
+ for pipeline in (self.anthropic_pipeline, self.openai_pipeline)
+ for transform in pipeline.transforms
+ if isinstance(transform, ContentRouter)
+ )
# Log component status
if self._kompress_status == "enabled":
@@ -2205,6 +2211,13 @@ class HeadroomProxy(
logger.info("Kompress: DEFERRED (warming in the background after startup)")
else:
logger.info("Kompress: DEFERRED (model loads on first request)")
+ elif not kompress_enabled and (
+ self.config.optimize
+ or self.config.disable_kompress
+ or self.config.disable_kompress_anthropic is True
+ or self.config.disable_kompress_openai is True
+ ):
+ logger.info("Kompress: DISABLED")
elif self.config.optimize:
logger.info("Kompress: not installed (pip install headroom-ai[ml] for ML compression)")
diff --git a/tests/test_proxy_eager_preload_bind.py b/tests/test_proxy_eager_preload_bind.py
index cfdd0baed..4502890a1 100644
--- a/tests/test_proxy_eager_preload_bind.py
+++ b/tests/test_proxy_eager_preload_bind.py
@@ -23,9 +23,20 @@ import headroom.proxy.server as server_mod
from headroom.proxy.server import ProxyConfig, create_app
-def _make_proxy(*, optimize: bool):
+def _make_proxy(
+ *,
+ optimize: bool,
+ disable_kompress: bool = False,
+ disable_kompress_anthropic: bool | None = None,
+ disable_kompress_openai: bool | None = None,
+ compressors: set[str] | None = None,
+):
config = ProxyConfig(
optimize=optimize,
+ disable_kompress=disable_kompress,
+ disable_kompress_anthropic=disable_kompress_anthropic,
+ disable_kompress_openai=disable_kompress_openai,
+ compressors=compressors,
cache_enabled=False,
rate_limit_enabled=False,
cost_tracking_enabled=False,
@@ -155,3 +166,120 @@ async def test_startup_reports_deferred_kompress(caplog):
assert not any("Kompress: not installed" in message for message in caplog.messages)
finally:
await proxy.shutdown()
+
+
[email protected]("optimize", [True, False])
+async def test_startup_reports_disabled_kompress(caplog, monkeypatch, optimize):
+ proxy = _make_proxy(optimize=optimize, disable_kompress=True)
+ monkeypatch.setattr(proxy, "_eager_preload_transforms", lambda: ({}, []))
+
+ try:
+ server_mod.logger.addHandler(caplog.handler)
+ try:
+ with caplog.at_level(logging.INFO, logger=server_mod.logger.name):
+ await proxy.startup()
+ finally:
+ server_mod.logger.removeHandler(caplog.handler)
+
+ assert "Kompress: DISABLED" in caplog.messages
+ assert (
+ "Kompress: not installed (pip install headroom-ai[ml] for ML compression)"
+ not in caplog.messages
+ )
+ finally:
+ await proxy.shutdown()
+
+
+async def test_startup_keeps_not_installed_message_when_kompress_is_missing(caplog, monkeypatch):
+ proxy = _make_proxy(optimize=True)
+ monkeypatch.setattr(proxy, "_eager_preload_transforms", lambda: ({}, []))
+
+ try:
+ server_mod.logger.addHandler(caplog.handler)
+ try:
+ with caplog.at_level(logging.INFO, logger=server_mod.logger.name):
+ await proxy.startup()
+ finally:
+ server_mod.logger.removeHandler(caplog.handler)
+
+ assert (
+ "Kompress: not installed (pip install headroom-ai[ml] for ML compression)"
+ in caplog.messages
+ )
+ finally:
+ await proxy.shutdown()
+
+
+async def test_startup_keeps_missing_message_when_provider_override_enables_kompress(
+ caplog, monkeypatch
+):
+ proxy = _make_proxy(
+ optimize=True,
+ disable_kompress=True,
+ disable_kompress_anthropic=False,
+ )
+ monkeypatch.setattr(proxy, "_eager_preload_transforms", lambda: ({}, []))
+
+ try:
+ server_mod.logger.addHandler(caplog.handler)
+ try:
+ with caplog.at_level(logging.INFO, logger=server_mod.logger.name):
+ await proxy.startup()
+ finally:
+ server_mod.logger.removeHandler(caplog.handler)
+
+ assert "Kompress: DISABLED" not in caplog.messages
+ assert (
+ "Kompress: not installed (pip install headroom-ai[ml] for ML compression)"
+ in caplog.messages
+ )
+ finally:
+ await proxy.shutdown()
+
+
+async def test_startup_reports_disabled_when_both_providers_disable_kompress(caplog, monkeypatch):
+ proxy = _make_proxy(
+ optimize=True,
+ disable_kompress_anthropic=True,
+ disable_kompress_openai=True,
+ )
+ monkeypatch.setattr(proxy, "_eager_preload_transforms", lambda: ({}, []))
+
+ try:
+ server_mod.logger.addHandler(caplog.handler)
+ try:
+ with caplog.at_level(logging.INFO, logger=server_mod.logger.name):
+ await proxy.startup()
+ finally:
+ server_mod.logger.removeHandler(caplog.handler)
+
+ assert "Kompress: DISABLED" in caplog.messages
+ assert (
+ "Kompress: not installed (pip install headroom-ai[ml] for ML compression)"
+ not in caplog.messages
+ )
+ finally:
+ await proxy.shutdown()
+
+
+async def test_startup_reports_disabled_when_compressor_selection_omits_kompress(
+ caplog, monkeypatch
+):
+ proxy = _make_proxy(optimize=True, compressors={"smart_crusher"})
+ monkeypatch.setattr(proxy, "_eager_preload_transforms", lambda: ({}, []))
+
+ try:
+ server_mod.logger.addHandler(caplog.handler)
+ try:
+ with caplog.at_level(logging.INFO, logger=server_mod.logger.name):
+ await proxy.startup()
+ finally:
+ server_mod.logger.removeHandler(caplog.handler)
+
+ assert "Kompress: DISABLED" in caplog.messages
+ assert (
+ "Kompress: not installed (pip install headroom-ai[ml] for ML compression)"
+ not in caplog.messages
+ )
+ finally:
+ await proxy.shutdown()