mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-11-22 13:29:19 +08:00
fix(proxy): report disabled Kompress at startup (#4217)
## Description When Kompress is intentionally disabled, startup currently falls through to the missing-dependency message, even though `/health` reports it as disabled. The startup logger now checks the resolved provider pipelines and reports `Kompress: DISABLED` when neither enables Kompress, while retaining install guidance when dependencies are missing. Fixes #4208 ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) - [ ] New feature (non-breaking change that adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to change) - [ ] Documentation update - [ ] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made - `headroom/proxy/server.py`: derive whether Kompress is enabled from the constructed Anthropic and OpenAI pipelines and log the disabled state before the missing-dependency fallback. - `tests/test_proxy_eager_preload_bind.py`: cover global and provider disablement, provider re-enablement, omitted compressor selection, and missing-dependency guidance. ## Testing - [x] Unit tests pass (`pytest`) - [x] Linting passes (`ruff check .`) - [ ] Type checking passes (`mypy headroom`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output ```text Focused proxy tests: 29 passed, 1 existing StarletteDeprecationWarning Repository-wide pytest: not completed; public-network tests stalled and the external tool installer did not finish Ruff check/format and git diff --check: passed mypy: unavailable in the job environment ``` ## Real Behavior Proof - Environment: Linux, Python 3.14.7, local source checkout with `uv sync --extra proxy`; no ML extra, model download, or provider request. Beacon and telemetry were disabled. - Exact command / steps: with `HEADROOM_DISABLE_KOMPRESS=1`, ran `.venv/bin/headroom proxy --host 127.0.0.1 --port 18791 --mode cache --no-http2`, then polled `/health` and checked `.checks.kompress`. - Observed result: HTTP 200; health reported `enabled=false`, `ready=true`, `status=disabled`; startup logged `Kompress: DISABLED`. - Not tested: provider requests, model downloads, macOS/Python 3.13, full pytest, and upstream CI. The command and compact output are recorded in `artifacts/20261015T041001Z_asset-01-1/live-behavior-command.md` and adjacent live-behavior artifacts. ## Runtime Rollout Safety - Rollout-managed feature(s): none. - Minimum rollout channel: N/A. - Stable/default behavior changed: startup reports disabled Kompress accurately instead of suggesting installation when it is disabled. - Kill switch / disable path: existing Kompress disable settings remain available. - Unsafe override required: no. - Qualification impact: none known. - Rollback path: revert this commit. ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review ## Checklist - [x] My code follows the project's style guidelines - [x] I have performed a self-review of my code - [ ] I have commented my code, particularly in hard-to-understand areas - [ ] I have made corresponding changes to the documentation - [ ] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [ ] New and existing unit tests pass locally with my changes - [x] I did **not** edit `CHANGELOG.md` — it is generated by release-please from my Conventional Commit PR title (a CI guard enforces this) ## Screenshots (if applicable) N/A. ## Additional Notes The focused suite emitted one Starlette deprecation warning from `starlette.testclient`; the full suite and upstream CI have not been verified. The two failure markers from the interrupted broad pytest run did not reproduce when their test files were run alone. No documentation or changelog changes were needed for this startup-log correction. <!-- devin-review-badge-begin --> --- <a href="https://app.devin.ai/review/headroomlabs-ai/headroom/pull/4217" target="_blank"><picture><source media="(prefers-color-scheme: dark)" srcset="https://static.devin.ai/assets/gh-devin-review-dark.svg?v=4"><img src="https://static.devin.ai/assets/gh-devin-review-light.svg?v=4" alt="Devin Review"></picture></a> <!-- devin-review-badge-end --> Co-authored-by: JD Davis <mxjerrett@gmail.com>
This commit is contained in:
@@ -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)")
|
||||
|
||||
|
||||
@@ -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()
|
||||
|
||||
|
||||
@pytest.mark.parametrize("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()
|
||||
|
||||
Reference in New Issue
Block a user